diff options
Diffstat (limited to 'fs')
497 files changed, 26739 insertions, 12590 deletions
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 014c8dd6296..57ccb7537da 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -448,7 +448,7 @@ void v9fs_evict_inode(struct inode *inode) struct v9fs_inode *v9inode = V9FS_I(inode); truncate_inode_pages(inode->i_mapping, 0); - end_writeback(inode); + clear_inode(inode); filemap_fdatawrite(inode->i_mapping); #ifdef CONFIG_9P_FSCACHE diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index a1e6c990cd4..e3dd2a1e2bf 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -68,24 +68,6 @@ static gid_t v9fs_get_fsgid_for_create(struct inode *dir_inode) return current_fsgid(); } -/** - * v9fs_dentry_from_dir_inode - helper function to get the dentry from - * dir inode. - * - */ - -static struct dentry *v9fs_dentry_from_dir_inode(struct inode *inode) -{ - struct dentry *dentry; - - spin_lock(&inode->i_lock); - /* Directory should have only one entry. */ - BUG_ON(S_ISDIR(inode->i_mode) && !list_is_singular(&inode->i_dentry)); - dentry = list_entry(inode->i_dentry.next, struct dentry, d_alias); - spin_unlock(&inode->i_lock); - return dentry; -} - static int v9fs_test_inode_dotl(struct inode *inode, void *data) { struct v9fs_inode *v9inode = V9FS_I(inode); @@ -415,7 +397,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir, if (dir->i_mode & S_ISGID) omode |= S_ISGID; - dir_dentry = v9fs_dentry_from_dir_inode(dir); + dir_dentry = dentry->d_parent; dfid = v9fs_fid_lookup(dir_dentry); if (IS_ERR(dfid)) { err = PTR_ERR(dfid); @@ -793,7 +775,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir, dir->i_ino, old_dentry->d_name.name, dentry->d_name.name); v9ses = v9fs_inode2v9ses(dir); - dir_dentry = v9fs_dentry_from_dir_inode(dir); + dir_dentry = dentry->d_parent; dfid = v9fs_fid_lookup(dir_dentry); if (IS_ERR(dfid)) return PTR_ERR(dfid); @@ -858,7 +840,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode, return -EINVAL; v9ses = v9fs_inode2v9ses(dir); - dir_dentry = v9fs_dentry_from_dir_inode(dir); + dir_dentry = dentry->d_parent; dfid = v9fs_fid_lookup(dir_dentry); if (IS_ERR(dfid)) { err = PTR_ERR(dfid); diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt index e95d1b64082..02257420274 100644 --- a/fs/Kconfig.binfmt +++ b/fs/Kconfig.binfmt @@ -33,7 +33,7 @@ config ARCH_BINFMT_ELF_RANDOMIZE_PIE config BINFMT_ELF_FDPIC bool "Kernel support for FDPIC ELF binaries" default y - depends on (FRV || BLACKFIN || (SUPERH32 && !MMU)) + depends on (FRV || BLACKFIN || (SUPERH32 && !MMU) || C6X) help ELF FDPIC binaries are based on ELF, but allow the individual load segments of a binary to be located in memory independently of each diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 45a0ce45d7b..1fceb320d2f 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -18,14 +18,6 @@ #define AFFS_GET_HASHENTRY(data,hashkey) be32_to_cpu(((struct dir_front *)data)->hashtable[hashkey]) #define AFFS_BLOCK(sb, bh, blk) (AFFS_HEAD(bh)->table[AFFS_SB(sb)->s_hashsize-1-(blk)]) -#ifdef __LITTLE_ENDIAN -#define BO_EXBITS 0x18UL -#elif defined(__BIG_ENDIAN) -#define BO_EXBITS 0x00UL -#else -#error Endianness must be known for affs to work. -#endif - #define AFFS_HEAD(bh) ((struct affs_head *)(bh)->b_data) #define AFFS_TAIL(sb, bh) ((struct affs_tail *)((bh)->b_data+(sb)->s_blocksize-sizeof(struct affs_tail))) #define AFFS_ROOT_HEAD(bh) ((struct affs_root_head *)(bh)->b_data) diff --git a/fs/affs/inode.c b/fs/affs/inode.c index 88a4b0b5005..8bc4a59f4e7 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -264,7 +264,7 @@ affs_evict_inode(struct inode *inode) } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); affs_free_prealloc(inode); cache_page = (unsigned long)AFFS_I(inode)->i_lc; if (cache_page) { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index d890ae3b2ce..95cffd38239 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -423,7 +423,7 @@ void afs_evict_inode(struct inode *inode) ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode); truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); afs_give_up_callback(vnode); @@ -134,9 +134,9 @@ static int aio_setup_ring(struct kioctx *ctx) info->mmap_size = nr_pages * PAGE_SIZE; dprintk("attempting mmap of %lu bytes\n", info->mmap_size); down_write(&ctx->mm->mmap_sem); - info->mmap_base = do_mmap(NULL, 0, info->mmap_size, - PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE, - 0); + info->mmap_base = do_mmap_pgoff(NULL, 0, info->mmap_size, + PROT_READ|PROT_WRITE, + MAP_ANONYMOUS|MAP_PRIVATE, 0); if (IS_ERR((void *)info->mmap_base)) { up_write(&ctx->mm->mmap_sem); info->mmap_size = 0; @@ -1446,13 +1446,17 @@ static ssize_t aio_setup_vectored_rw(int type, struct kiocb *kiocb, bool compat) ret = compat_rw_copy_check_uvector(type, (struct compat_iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec, 1); + &kiocb->ki_iovec); else #endif ret = rw_copy_check_uvector(type, (struct iovec __user *)kiocb->ki_buf, kiocb->ki_nbytes, 1, &kiocb->ki_inline_vec, - &kiocb->ki_iovec, 1); + &kiocb->ki_iovec); + if (ret < 0) + goto out; + + ret = rw_verify_area(type, kiocb->ki_filp, &kiocb->ki_pos, ret); if (ret < 0) goto out; @@ -1467,11 +1471,17 @@ out: return ret; } -static ssize_t aio_setup_single_vector(struct kiocb *kiocb) +static ssize_t aio_setup_single_vector(int type, struct file * file, struct kiocb *kiocb) { + int bytes; + + bytes = rw_verify_area(type, file, &kiocb->ki_pos, kiocb->ki_left); + if (bytes < 0) + return bytes; + kiocb->ki_iovec = &kiocb->ki_inline_vec; kiocb->ki_iovec->iov_base = kiocb->ki_buf; - kiocb->ki_iovec->iov_len = kiocb->ki_left; + kiocb->ki_iovec->iov_len = bytes; kiocb->ki_nr_segs = 1; kiocb->ki_cur_seg = 0; return 0; @@ -1496,10 +1506,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) if (unlikely(!access_ok(VERIFY_WRITE, kiocb->ki_buf, kiocb->ki_left))) break; - ret = security_file_permission(file, MAY_READ); - if (unlikely(ret)) - break; - ret = aio_setup_single_vector(kiocb); + ret = aio_setup_single_vector(READ, file, kiocb); if (ret) break; ret = -EINVAL; @@ -1514,10 +1521,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) if (unlikely(!access_ok(VERIFY_READ, kiocb->ki_buf, kiocb->ki_left))) break; - ret = security_file_permission(file, MAY_WRITE); - if (unlikely(ret)) - break; - ret = aio_setup_single_vector(kiocb); + ret = aio_setup_single_vector(WRITE, file, kiocb); if (ret) break; ret = -EINVAL; @@ -1528,9 +1532,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_READ))) break; - ret = security_file_permission(file, MAY_READ); - if (unlikely(ret)) - break; ret = aio_setup_vectored_rw(READ, kiocb, compat); if (ret) break; @@ -1542,9 +1543,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat) ret = -EBADF; if (unlikely(!(file->f_mode & FMODE_WRITE))) break; - ret = security_file_permission(file, MAY_WRITE); - if (unlikely(ret)) - break; ret = aio_setup_vectored_rw(WRITE, kiocb, compat); if (ret) break; diff --git a/fs/attr.c b/fs/attr.c index 73f69a6ce9e..0da90951d27 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,14 +47,14 @@ int inode_change_ok(const struct inode *inode, struct iattr *attr) /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && - (current_fsuid() != inode->i_uid || - attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN)) + (!uid_eq(current_fsuid(), inode->i_uid) || + !uid_eq(attr->ia_uid, inode->i_uid)) && !capable(CAP_CHOWN)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && - (current_fsuid() != inode->i_uid || - (!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) && + (!uid_eq(current_fsuid(), inode->i_uid) || + (!in_group_p(attr->ia_gid) && !gid_eq(attr->ia_gid, inode->i_gid))) && !capable(CAP_CHOWN)) return -EPERM; @@ -176,6 +176,11 @@ int notify_change(struct dentry * dentry, struct iattr * attr) return -EPERM; } + if ((ia_valid & ATTR_SIZE) && IS_I_VERSION(inode)) { + if (attr->ia_size != inode->i_size) + inode_inc_iversion(inode); + } + if ((ia_valid & ATTR_MODE)) { umode_t amode = attr->ia_mode; /* Flag setting protected by i_mutex */ diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h index eb1cc92cd67..908e1845541 100644 --- a/fs/autofs4/autofs_i.h +++ b/fs/autofs4/autofs_i.h @@ -110,7 +110,6 @@ struct autofs_sb_info { int sub_version; int min_proto; int max_proto; - int compat_daemon; unsigned long exp_timeout; unsigned int type; int reghost_enabled; @@ -270,6 +269,17 @@ int autofs4_fill_super(struct super_block *, void *, int); struct autofs_info *autofs4_new_ino(struct autofs_sb_info *); void autofs4_clean_ino(struct autofs_info *); +static inline int autofs_prepare_pipe(struct file *pipe) +{ + if (!pipe->f_op || !pipe->f_op->write) + return -EINVAL; + if (!S_ISFIFO(pipe->f_dentry->d_inode->i_mode)) + return -EINVAL; + /* We want a packet pipe */ + pipe->f_flags |= O_DIRECT; + return 0; +} + /* Queue management functions */ int autofs4_wait(struct autofs_sb_info *,struct dentry *, enum autofs_notify); diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 9dacb858670..aa9103f8f01 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -376,7 +376,7 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, err = -EBADF; goto out; } - if (!pipe->f_op || !pipe->f_op->write) { + if (autofs_prepare_pipe(pipe) < 0) { err = -EPIPE; fput(pipe); goto out; @@ -385,7 +385,6 @@ static int autofs_dev_ioctl_setpipefd(struct file *fp, sbi->pipefd = pipefd; sbi->pipe = pipe; sbi->catatonic = 0; - sbi->compat_daemon = is_compat_task(); } out: mutex_unlock(&sbi->wq_mutex); diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index d8dc002e9cc..8a4fed8ead3 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -19,7 +19,6 @@ #include <linux/parser.h> #include <linux/bitops.h> #include <linux/magic.h> -#include <linux/compat.h> #include "autofs_i.h" #include <linux/module.h> @@ -101,7 +100,7 @@ static int autofs4_show_options(struct seq_file *m, struct dentry *root) static void autofs4_evict_inode(struct inode *inode) { - end_writeback(inode); + clear_inode(inode); kfree(inode->i_private); } @@ -225,7 +224,6 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) set_autofs_type_indirect(&sbi->type); sbi->min_proto = 0; sbi->max_proto = 0; - sbi->compat_daemon = is_compat_task(); mutex_init(&sbi->wq_mutex); mutex_init(&sbi->pipe_mutex); spin_lock_init(&sbi->fs_lock); @@ -292,7 +290,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) printk("autofs: could not open pipe file descriptor\n"); goto fail_dput; } - if (!pipe->f_op || !pipe->f_op->write) + if (autofs_prepare_pipe(pipe) < 0) goto fail_fput; sbi->pipe = pipe; sbi->pipefd = pipefd; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 9c098db4334..da8876d38a7 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -91,24 +91,7 @@ static int autofs4_write(struct autofs_sb_info *sbi, return (bytes > 0); } - -/* - * The autofs_v5 packet was misdesigned. - * - * The packets are identical on x86-32 and x86-64, but have different - * alignment. Which means that 'sizeof()' will give different results. - * Fix it up for the case of running 32-bit user mode on a 64-bit kernel. - */ -static noinline size_t autofs_v5_packet_size(struct autofs_sb_info *sbi) -{ - size_t pktsz = sizeof(struct autofs_v5_packet); -#if defined(CONFIG_X86_64) && defined(CONFIG_COMPAT) - if (sbi->compat_daemon > 0) - pktsz -= 4; -#endif - return pktsz; -} - + static void autofs4_notify_daemon(struct autofs_sb_info *sbi, struct autofs_wait_queue *wq, int type) @@ -172,7 +155,8 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, { struct autofs_v5_packet *packet = &pkt.v5_pkt.v5_packet; - pktsz = autofs_v5_packet_size(sbi); + pktsz = sizeof(*packet); + packet->wait_queue_token = wq->wait_queue_token; packet->len = wq->name.len; memcpy(packet->name, wq->name.name, wq->name.len); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 37268c5bb98..1b35d6bd06b 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -292,7 +292,6 @@ static const struct inode_operations bad_inode_ops = .getxattr = bad_inode_getxattr, .listxattr = bad_inode_listxattr, .removexattr = bad_inode_removexattr, - /* truncate_range returns void */ }; diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index e23dc7c8b88..9870417c26e 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -174,7 +174,7 @@ static void bfs_evict_inode(struct inode *inode) truncate_inode_pages(&inode->i_data, 0); invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); if (inode->i_nlink) return; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 16f73541707..1b52956afe3 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -226,10 +226,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, NEW_AUX_ENT(AT_BASE, interp_load_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec->e_entry); - NEW_AUX_ENT(AT_UID, cred->uid); - NEW_AUX_ENT(AT_EUID, cred->euid); - NEW_AUX_ENT(AT_GID, cred->gid); - NEW_AUX_ENT(AT_EGID, cred->egid); + NEW_AUX_ENT(AT_UID, from_kuid_munged(cred->user_ns, cred->uid)); + NEW_AUX_ENT(AT_EUID, from_kuid_munged(cred->user_ns, cred->euid)); + NEW_AUX_ENT(AT_GID, from_kgid_munged(cred->user_ns, cred->gid)); + NEW_AUX_ENT(AT_EGID, from_kgid_munged(cred->user_ns, cred->egid)); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_RANDOM, (elf_addr_t)(unsigned long)u_rand_bytes); NEW_AUX_ENT(AT_EXECFN, bprm->exec); @@ -329,7 +329,6 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, if (!size) return addr; - down_write(¤t->mm->mmap_sem); /* * total_size is the size of the ELF (interpreter) image. * The _first_ mmap needs to know the full size, otherwise @@ -340,13 +339,12 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, */ if (total_size) { total_size = ELF_PAGEALIGN(total_size); - map_addr = do_mmap(filep, addr, total_size, prot, type, off); + map_addr = vm_mmap(filep, addr, total_size, prot, type, off); if (!BAD_ADDR(map_addr)) - do_munmap(current->mm, map_addr+size, total_size-size); + vm_munmap(map_addr+size, total_size-size); } else - map_addr = do_mmap(filep, addr, size, prot, type, off); + map_addr = vm_mmap(filep, addr, size, prot, type, off); - up_write(¤t->mm->mmap_sem); return(map_addr); } @@ -1356,8 +1354,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_flag = p->flags; rcu_read_lock(); cred = __task_cred(p); - SET_UID(psinfo->pr_uid, cred->uid); - SET_GID(psinfo->pr_gid, cred->gid); + SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); + SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index d390a0fffc6..3d77cf81ba3 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -627,10 +627,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); - NEW_AUX_ENT(AT_UID, (elf_addr_t) cred->uid); - NEW_AUX_ENT(AT_EUID, (elf_addr_t) cred->euid); - NEW_AUX_ENT(AT_GID, (elf_addr_t) cred->gid); - NEW_AUX_ENT(AT_EGID, (elf_addr_t) cred->egid); + NEW_AUX_ENT(AT_UID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->uid)); + NEW_AUX_ENT(AT_EUID, (elf_addr_t) from_kuid_munged(cred->user_ns, cred->euid)); + NEW_AUX_ENT(AT_GID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->gid)); + NEW_AUX_ENT(AT_EGID, (elf_addr_t) from_kgid_munged(cred->user_ns, cred->egid)); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_EXECFN, bprm->exec); @@ -1421,8 +1421,8 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_flag = p->flags; rcu_read_lock(); cred = __task_cred(p); - SET_UID(psinfo->pr_uid, cred->uid); - SET_GID(psinfo->pr_gid, cred->gid); + SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); + SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 6b2daf99fab..178cb70acc2 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -562,7 +562,7 @@ static int load_flat_file(struct linux_binprm * bprm, realdatastart = (unsigned long) -ENOMEM; printk("Unable to allocate RAM for process data, errno %d\n", (int)-realdatastart); - do_munmap(current->mm, textpos, text_len); + vm_munmap(textpos, text_len); ret = realdatastart; goto err; } @@ -586,8 +586,8 @@ static int load_flat_file(struct linux_binprm * bprm, } if (IS_ERR_VALUE(result)) { printk("Unable to read data+bss, errno %d\n", (int)-result); - do_munmap(current->mm, textpos, text_len); - do_munmap(current->mm, realdatastart, len); + vm_munmap(textpos, text_len); + vm_munmap(realdatastart, len); ret = result; goto err; } @@ -654,7 +654,7 @@ static int load_flat_file(struct linux_binprm * bprm, } if (IS_ERR_VALUE(result)) { printk("Unable to read code+data+bss, errno %d\n",(int)-result); - do_munmap(current->mm, textpos, text_len + data_len + extra + + vm_munmap(textpos, text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long)); ret = result; goto err; diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 613aa061823..790b3cddca6 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -505,7 +505,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_evict_inode(struct inode *inode) { - end_writeback(inode); + clear_inode(inode); kfree(inode->i_private); } @@ -19,12 +19,14 @@ #include <linux/swap.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/iocontext.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/mempool.h> #include <linux/workqueue.h> +#include <linux/cgroup.h> #include <scsi/sg.h> /* for struct sg_iovec */ #include <trace/events/block.h> @@ -418,6 +420,7 @@ void bio_put(struct bio *bio) * last put frees it */ if (atomic_dec_and_test(&bio->bi_cnt)) { + bio_disassociate_task(bio); bio->bi_next = NULL; bio->bi_destructor(bio); } @@ -505,9 +508,14 @@ EXPORT_SYMBOL(bio_clone); int bio_get_nr_vecs(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - return min_t(unsigned, + int nr_pages; + + nr_pages = min_t(unsigned, queue_max_segments(q), queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1); + + return min_t(unsigned, nr_pages, BIO_MAX_PAGES); + } EXPORT_SYMBOL(bio_get_nr_vecs); @@ -1641,6 +1649,64 @@ bad: } EXPORT_SYMBOL(bioset_create); +#ifdef CONFIG_BLK_CGROUP +/** + * bio_associate_current - associate a bio with %current + * @bio: target bio + * + * Associate @bio with %current if it hasn't been associated yet. Block + * layer will treat @bio as if it were issued by %current no matter which + * task actually issues it. + * + * This function takes an extra reference of @task's io_context and blkcg + * which will be put when @bio is released. The caller must own @bio, + * ensure %current->io_context exists, and is responsible for synchronizing + * calls to this function. + */ +int bio_associate_current(struct bio *bio) +{ + struct io_context *ioc; + struct cgroup_subsys_state *css; + + if (bio->bi_ioc) + return -EBUSY; + + ioc = current->io_context; + if (!ioc) + return -ENOENT; + + /* acquire active ref on @ioc and associate */ + get_io_context_active(ioc); + bio->bi_ioc = ioc; + + /* associate blkcg if exists */ + rcu_read_lock(); + css = task_subsys_state(current, blkio_subsys_id); + if (css && css_tryget(css)) + bio->bi_css = css; + rcu_read_unlock(); + + return 0; +} + +/** + * bio_disassociate_task - undo bio_associate_current() + * @bio: target bio + */ +void bio_disassociate_task(struct bio *bio) +{ + if (bio->bi_ioc) { + put_io_context(bio->bi_ioc); + bio->bi_ioc = NULL; + } + if (bio->bi_css) { + css_put(bio->bi_css); + bio->bi_css = NULL; + } +} + +#endif /* CONFIG_BLK_CGROUP */ + static void __init biovec_init_slabs(void) { int i; diff --git a/fs/block_dev.c b/fs/block_dev.c index e08f6a20a5b..c2bbe1fb132 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -70,7 +70,7 @@ static void bdev_inode_switch_bdi(struct inode *inode, spin_unlock(&dst->wb.list_lock); } -static sector_t max_block(struct block_device *bdev) +sector_t blkdev_max_block(struct block_device *bdev) { sector_t retval = ~((sector_t)0); loff_t sz = i_size_read(bdev->bd_inode); @@ -163,7 +163,7 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { - if (iblock >= max_block(I_BDEV(inode))) { + if (iblock >= blkdev_max_block(I_BDEV(inode))) { if (create) return -EIO; @@ -185,7 +185,7 @@ static int blkdev_get_blocks(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { - sector_t end_block = max_block(I_BDEV(inode)); + sector_t end_block = blkdev_max_block(I_BDEV(inode)); unsigned long max_blocks = bh->b_size >> inode->i_blkbits; if ((iblock + max_blocks) > end_block) { @@ -487,7 +487,7 @@ static void bdev_evict_inode(struct inode *inode) struct list_head *p; truncate_inode_pages(&inode->i_data, 0); invalidate_inode_buffers(inode); /* is it needed here? */ - end_writeback(inode); + clear_inode(inode); spin_lock(&bdev_lock); while ( (p = bdev->bd_inodes.next) != &bdev->bd_inodes ) { __bd_forget(list_entry(p, struct inode, i_devices)); diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 89b156d85d6..761e2cd8fed 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -227,7 +227,11 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans, if (ret > 0) { /* we need an acl */ ret = btrfs_set_acl(trans, inode, acl, ACL_TYPE_ACCESS); + } else { + cache_no_acl(inode); } + } else { + cache_no_acl(inode); } failed: posix_acl_release(acl); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f4e90748940..a383c18e74e 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -22,6 +22,80 @@ #include "ulist.h" #include "transaction.h" #include "delayed-ref.h" +#include "locking.h" + +struct extent_inode_elem { + u64 inum; + u64 offset; + struct extent_inode_elem *next; +}; + +static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb, + struct btrfs_file_extent_item *fi, + u64 extent_item_pos, + struct extent_inode_elem **eie) +{ + u64 data_offset; + u64 data_len; + struct extent_inode_elem *e; + + data_offset = btrfs_file_extent_offset(eb, fi); + data_len = btrfs_file_extent_num_bytes(eb, fi); + + if (extent_item_pos < data_offset || + extent_item_pos >= data_offset + data_len) + return 1; + + e = kmalloc(sizeof(*e), GFP_NOFS); + if (!e) + return -ENOMEM; + + e->next = *eie; + e->inum = key->objectid; + e->offset = key->offset + (extent_item_pos - data_offset); + *eie = e; + + return 0; +} + +static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte, + u64 extent_item_pos, + struct extent_inode_elem **eie) +{ + u64 disk_byte; + struct btrfs_key key; + struct btrfs_file_extent_item *fi; + int slot; + int nritems; + int extent_type; + int ret; + + /* + * from the shared data ref, we only have the leaf but we need + * the key. thus, we must look into all items and see that we + * find one (some) with a reference to our extent item. + */ + nritems = btrfs_header_nritems(eb); + for (slot = 0; slot < nritems; ++slot) { + btrfs_item_key_to_cpu(eb, &key, slot); + if (key.type != BTRFS_EXTENT_DATA_KEY) + continue; + fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + extent_type = btrfs_file_extent_type(eb, fi); + if (extent_type == BTRFS_FILE_EXTENT_INLINE) + continue; + /* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */ + disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); + if (disk_byte != wanted_disk_byte) + continue; + + ret = check_extent_in_eb(&key, eb, fi, extent_item_pos, eie); + if (ret < 0) + return ret; + } + + return 0; +} /* * this structure records all encountered refs on the way up to the root @@ -29,16 +103,56 @@ struct __prelim_ref { struct list_head list; u64 root_id; - struct btrfs_key key; + struct btrfs_key key_for_search; int level; int count; + struct extent_inode_elem *inode_list; u64 parent; u64 wanted_disk_byte; }; +/* + * the rules for all callers of this function are: + * - obtaining the parent is the goal + * - if you add a key, you must know that it is a correct key + * - if you cannot add the parent or a correct key, then we will look into the + * block later to set a correct key + * + * delayed refs + * ============ + * backref type | shared | indirect | shared | indirect + * information | tree | tree | data | data + * --------------------+--------+----------+--------+---------- + * parent logical | y | - | - | - + * key to resolve | - | y | y | y + * tree block logical | - | - | - | - + * root for resolving | y | y | y | y + * + * - column 1: we've the parent -> done + * - column 2, 3, 4: we use the key to find the parent + * + * on disk refs (inline or keyed) + * ============================== + * backref type | shared | indirect | shared | indirect + * information | tree | tree | data | data + * --------------------+--------+----------+--------+---------- + * parent logical | y | - | y | - + * key to resolve | - | - | - | y + * tree block logical | y | y | y | y + * root for resolving | - | y | y | y + * + * - column 1, 3: we've the parent -> done + * - column 2: we take the first key from the block to find the parent + * (see __add_missing_keys) + * - column 4: we use the key to find the parent + * + * additional information that's available but not required to find the parent + * block might help in merging entries to gain some speed. + */ + static int __add_prelim_ref(struct list_head *head, u64 root_id, - struct btrfs_key *key, int level, u64 parent, - u64 wanted_disk_byte, int count) + struct btrfs_key *key, int level, + u64 parent, u64 wanted_disk_byte, int count) { struct __prelim_ref *ref; @@ -49,10 +163,11 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id, ref->root_id = root_id; if (key) - ref->key = *key; + ref->key_for_search = *key; else - memset(&ref->key, 0, sizeof(ref->key)); + memset(&ref->key_for_search, 0, sizeof(ref->key_for_search)); + ref->inode_list = NULL; ref->level = level; ref->count = count; ref->parent = parent; @@ -63,52 +178,75 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id, } static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path, - struct ulist *parents, - struct extent_buffer *eb, int level, - u64 wanted_objectid, u64 wanted_disk_byte) + struct ulist *parents, int level, + struct btrfs_key *key_for_search, u64 time_seq, + u64 wanted_disk_byte, + const u64 *extent_item_pos) { - int ret; + int ret = 0; int slot; - struct btrfs_file_extent_item *fi; + struct extent_buffer *eb; struct btrfs_key key; + struct btrfs_file_extent_item *fi; + struct extent_inode_elem *eie = NULL; u64 disk_byte; -add_parent: - ret = ulist_add(parents, eb->start, 0, GFP_NOFS); - if (ret < 0) - return ret; - - if (level != 0) + if (level != 0) { + eb = path->nodes[level]; + ret = ulist_add(parents, eb->start, 0, GFP_NOFS); + if (ret < 0) + return ret; return 0; + } /* - * if the current leaf is full with EXTENT_DATA items, we must - * check the next one if that holds a reference as well. - * ref->count cannot be used to skip this check. - * repeat this until we don't find any additional EXTENT_DATA items. + * We normally enter this function with the path already pointing to + * the first item to check. But sometimes, we may enter it with + * slot==nritems. In that case, go to the next leaf before we continue. */ - while (1) { - ret = btrfs_next_leaf(root, path); - if (ret < 0) - return ret; - if (ret) - return 0; + if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) + ret = btrfs_next_old_leaf(root, path, time_seq); + while (!ret) { eb = path->nodes[0]; - for (slot = 0; slot < btrfs_header_nritems(eb); ++slot) { - btrfs_item_key_to_cpu(eb, &key, slot); - if (key.objectid != wanted_objectid || - key.type != BTRFS_EXTENT_DATA_KEY) - return 0; - fi = btrfs_item_ptr(eb, slot, - struct btrfs_file_extent_item); - disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); - if (disk_byte == wanted_disk_byte) - goto add_parent; + slot = path->slots[0]; + + btrfs_item_key_to_cpu(eb, &key, slot); + + if (key.objectid != key_for_search->objectid || + key.type != BTRFS_EXTENT_DATA_KEY) + break; + + fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); + disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); + + if (disk_byte == wanted_disk_byte) { + eie = NULL; + if (extent_item_pos) { + ret = check_extent_in_eb(&key, eb, fi, + *extent_item_pos, + &eie); + if (ret < 0) + break; + } + if (!ret) { + ret = ulist_add(parents, eb->start, + (unsigned long)eie, GFP_NOFS); + if (ret < 0) + break; + if (!extent_item_pos) { + ret = btrfs_next_old_leaf(root, path, + time_seq); + continue; + } + } } + ret = btrfs_next_old_item(root, path, time_seq); } - return 0; + if (ret > 0) + ret = 0; + return ret; } /* @@ -117,13 +255,14 @@ add_parent: */ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, int search_commit_root, + u64 time_seq, struct __prelim_ref *ref, - struct ulist *parents) + struct ulist *parents, + const u64 *extent_item_pos) { struct btrfs_path *path; struct btrfs_root *root; struct btrfs_key root_key; - struct btrfs_key key = {0}; struct extent_buffer *eb; int ret = 0; int root_level; @@ -151,36 +290,30 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; path->lowest_level = level; - ret = btrfs_search_slot(NULL, root, &ref->key, path, 0, 0); + ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq); pr_debug("search slot in root %llu (level %d, ref count %d) returned " "%d for key (%llu %u %llu)\n", (unsigned long long)ref->root_id, level, ref->count, ret, - (unsigned long long)ref->key.objectid, ref->key.type, - (unsigned long long)ref->key.offset); + (unsigned long long)ref->key_for_search.objectid, + ref->key_for_search.type, + (unsigned long long)ref->key_for_search.offset); if (ret < 0) goto out; eb = path->nodes[level]; - if (!eb) { - WARN_ON(1); - ret = 1; - goto out; - } - - if (level == 0) { - if (ret == 1 && path->slots[0] >= btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(root, path); - if (ret) - goto out; - eb = path->nodes[0]; + while (!eb) { + if (!level) { + WARN_ON(1); + ret = 1; + goto out; } - - btrfs_item_key_to_cpu(eb, &key, path->slots[0]); + level--; + eb = path->nodes[level]; } - /* the last two parameters will only be used for level == 0 */ - ret = add_all_parents(root, path, parents, eb, level, key.objectid, - ref->wanted_disk_byte); + ret = add_all_parents(root, path, parents, level, &ref->key_for_search, + time_seq, ref->wanted_disk_byte, + extent_item_pos); out: btrfs_free_path(path); return ret; @@ -190,8 +323,9 @@ out: * resolve all indirect backrefs from the list */ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, - int search_commit_root, - struct list_head *head) + int search_commit_root, u64 time_seq, + struct list_head *head, + const u64 *extent_item_pos) { int err; int ret = 0; @@ -200,6 +334,7 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, struct __prelim_ref *new_ref; struct ulist *parents; struct ulist_node *node; + struct ulist_iterator uiter; parents = ulist_alloc(GFP_NOFS); if (!parents) @@ -216,7 +351,8 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, if (ref->count == 0) continue; err = __resolve_indirect_ref(fs_info, search_commit_root, - ref, parents); + time_seq, ref, parents, + extent_item_pos); if (err) { if (ret == 0) ret = err; @@ -224,11 +360,14 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, } /* we put the first parent into the ref at hand */ - node = ulist_next(parents, NULL); + ULIST_ITER_INIT(&uiter); + node = ulist_next(parents, &uiter); ref->parent = node ? node->val : 0; + ref->inode_list = + node ? (struct extent_inode_elem *)node->aux : 0; /* additional parents require new refs being added here */ - while ((node = ulist_next(parents, node))) { + while ((node = ulist_next(parents, &uiter))) { new_ref = kmalloc(sizeof(*new_ref), GFP_NOFS); if (!new_ref) { ret = -ENOMEM; @@ -236,6 +375,8 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, } memcpy(new_ref, ref, sizeof(*ref)); new_ref->parent = node->val; + new_ref->inode_list = + (struct extent_inode_elem *)node->aux; list_add(&new_ref->list, &ref->list); } ulist_reinit(parents); @@ -245,10 +386,65 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info, return ret; } +static inline int ref_for_same_block(struct __prelim_ref *ref1, + struct __prelim_ref *ref2) +{ + if (ref1->level != ref2->level) + return 0; + if (ref1->root_id != ref2->root_id) + return 0; + if (ref1->key_for_search.type != ref2->key_for_search.type) + return 0; + if (ref1->key_for_search.objectid != ref2->key_for_search.objectid) + return 0; + if (ref1->key_for_search.offset != ref2->key_for_search.offset) + return 0; + if (ref1->parent != ref2->parent) + return 0; + + return 1; +} + +/* + * read tree blocks and add keys where required. + */ +static int __add_missing_keys(struct btrfs_fs_info *fs_info, + struct list_head *head) +{ + struct list_head *pos; + struct extent_buffer *eb; + + list_for_each(pos, head) { + struct __prelim_ref *ref; + ref = list_entry(pos, struct __prelim_ref, list); + + if (ref->parent) + continue; + if (ref->key_for_search.type) + continue; + BUG_ON(!ref->wanted_disk_byte); + eb = read_tree_block(fs_info->tree_root, ref->wanted_disk_byte, + fs_info->tree_root->leafsize, 0); + BUG_ON(!eb); + btrfs_tree_read_lock(eb); + if (btrfs_header_level(eb) == 0) + btrfs_item_key_to_cpu(eb, &ref->key_for_search, 0); + else + btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0); + btrfs_tree_read_unlock(eb); + free_extent_buffer(eb); + } + return 0; +} + /* * merge two lists of backrefs and adjust counts accordingly * * mode = 1: merge identical keys, if key is set + * FIXME: if we add more keys in __add_prelim_ref, we can merge more here. + * additionally, we could even add a key range for the blocks we + * looked into to merge even more (-> replace unresolved refs by those + * having a parent). * mode = 2: merge identical parents */ static int __merge_refs(struct list_head *head, int mode) @@ -262,20 +458,21 @@ static int __merge_refs(struct list_head *head, int mode) ref1 = list_entry(pos1, struct __prelim_ref, list); - if (mode == 1 && ref1->key.type == 0) - continue; for (pos2 = pos1->next, n2 = pos2->next; pos2 != head; pos2 = n2, n2 = pos2->next) { struct __prelim_ref *ref2; + struct __prelim_ref *xchg; ref2 = list_entry(pos2, struct __prelim_ref, list); if (mode == 1) { - if (memcmp(&ref1->key, &ref2->key, - sizeof(ref1->key)) || - ref1->level != ref2->level || - ref1->root_id != ref2->root_id) + if (!ref_for_same_block(ref1, ref2)) continue; + if (!ref1->parent && ref2->parent) { + xchg = ref1; + ref1 = ref2; + ref2 = xchg; + } ref1->count += ref2->count; } else { if (ref1->parent != ref2->parent) @@ -295,16 +492,17 @@ static int __merge_refs(struct list_head *head, int mode) * smaller or equal that seq to the list */ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, - struct btrfs_key *info_key, struct list_head *prefs) { struct btrfs_delayed_extent_op *extent_op = head->extent_op; struct rb_node *n = &head->node.rb_node; + struct btrfs_key key; + struct btrfs_key op_key = {0}; int sgn; int ret = 0; if (extent_op && extent_op->update_key) - btrfs_disk_key_to_cpu(info_key, &extent_op->key); + btrfs_disk_key_to_cpu(&op_key, &extent_op->key); while ((n = rb_prev(n))) { struct btrfs_delayed_ref_node *node; @@ -336,7 +534,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, struct btrfs_delayed_tree_ref *ref; ref = btrfs_delayed_node_to_tree_ref(node); - ret = __add_prelim_ref(prefs, ref->root, info_key, + ret = __add_prelim_ref(prefs, ref->root, &op_key, ref->level + 1, 0, node->bytenr, node->ref_mod * sgn); break; @@ -345,7 +543,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, struct btrfs_delayed_tree_ref *ref; ref = btrfs_delayed_node_to_tree_ref(node); - ret = __add_prelim_ref(prefs, ref->root, info_key, + ret = __add_prelim_ref(prefs, ref->root, NULL, ref->level + 1, ref->parent, node->bytenr, node->ref_mod * sgn); @@ -353,8 +551,6 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, } case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_delayed_data_ref *ref; - struct btrfs_key key; - ref = btrfs_delayed_node_to_data_ref(node); key.objectid = ref->objectid; @@ -367,7 +563,6 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, } case BTRFS_SHARED_DATA_REF_KEY: { struct btrfs_delayed_data_ref *ref; - struct btrfs_key key; ref = btrfs_delayed_node_to_data_ref(node); @@ -393,8 +588,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq, */ static int __add_inline_refs(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, - struct btrfs_key *info_key, int *info_level, - struct list_head *prefs) + int *info_level, struct list_head *prefs) { int ret = 0; int slot; @@ -410,7 +604,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, * enumerate all inline refs */ leaf = path->nodes[0]; - slot = path->slots[0] - 1; + slot = path->slots[0]; item_size = btrfs_item_size_nr(leaf, slot); BUG_ON(item_size < sizeof(*ei)); @@ -423,12 +617,9 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { struct btrfs_tree_block_info *info; - struct btrfs_disk_key disk_key; info = (struct btrfs_tree_block_info *)ptr; *info_level = btrfs_tree_block_level(leaf, info); - btrfs_tree_block_key(leaf, info, &disk_key); - btrfs_disk_key_to_cpu(info_key, &disk_key); ptr += sizeof(struct btrfs_tree_block_info); BUG_ON(ptr > end); } else { @@ -446,7 +637,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, switch (type) { case BTRFS_SHARED_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, 0, info_key, + ret = __add_prelim_ref(prefs, 0, NULL, *info_level + 1, offset, bytenr, 1); break; @@ -461,8 +652,9 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, break; } case BTRFS_TREE_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, offset, info_key, - *info_level + 1, 0, bytenr, 1); + ret = __add_prelim_ref(prefs, offset, NULL, + *info_level + 1, 0, + bytenr, 1); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; @@ -476,8 +668,8 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); root = btrfs_extent_data_ref_root(leaf, dref); - ret = __add_prelim_ref(prefs, root, &key, 0, 0, bytenr, - count); + ret = __add_prelim_ref(prefs, root, &key, 0, 0, + bytenr, count); break; } default: @@ -495,8 +687,7 @@ static int __add_inline_refs(struct btrfs_fs_info *fs_info, */ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 bytenr, - struct btrfs_key *info_key, int info_level, - struct list_head *prefs) + int info_level, struct list_head *prefs) { struct btrfs_root *extent_root = fs_info->extent_root; int ret; @@ -526,7 +717,7 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, switch (key.type) { case BTRFS_SHARED_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, 0, info_key, + ret = __add_prelim_ref(prefs, 0, NULL, info_level + 1, key.offset, bytenr, 1); break; @@ -542,8 +733,9 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, break; } case BTRFS_TREE_BLOCK_REF_KEY: - ret = __add_prelim_ref(prefs, key.offset, info_key, - info_level + 1, 0, bytenr, 1); + ret = __add_prelim_ref(prefs, key.offset, NULL, + info_level + 1, 0, + bytenr, 1); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; @@ -559,7 +751,7 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, key.offset = btrfs_extent_data_ref_offset(leaf, dref); root = btrfs_extent_data_ref_root(leaf, dref); ret = __add_prelim_ref(prefs, root, &key, 0, 0, - bytenr, count); + bytenr, count); break; } default: @@ -581,11 +773,12 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info, */ static int find_parent_nodes(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, - u64 seq, struct ulist *refs, struct ulist *roots) + u64 delayed_ref_seq, u64 time_seq, + struct ulist *refs, struct ulist *roots, + const u64 *extent_item_pos) { struct btrfs_key key; struct btrfs_path *path; - struct btrfs_key info_key = { 0 }; struct btrfs_delayed_ref_root *delayed_refs = NULL; struct btrfs_delayed_ref_head *head; int info_level = 0; @@ -644,8 +837,9 @@ again: btrfs_put_delayed_ref(&head->node); goto again; } - ret = __add_delayed_refs(head, seq, &info_key, + ret = __add_delayed_refs(head, delayed_ref_seq, &prefs_delayed); + mutex_unlock(&head->mutex); if (ret) { spin_unlock(&delayed_refs->lock); goto out; @@ -658,16 +852,17 @@ again: struct extent_buffer *leaf; int slot; + path->slots[0]--; leaf = path->nodes[0]; - slot = path->slots[0] - 1; + slot = path->slots[0]; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid == bytenr && key.type == BTRFS_EXTENT_ITEM_KEY) { ret = __add_inline_refs(fs_info, path, bytenr, - &info_key, &info_level, &prefs); + &info_level, &prefs); if (ret) goto out; - ret = __add_keyed_refs(fs_info, path, bytenr, &info_key, + ret = __add_keyed_refs(fs_info, path, bytenr, info_level, &prefs); if (ret) goto out; @@ -675,21 +870,18 @@ again: } btrfs_release_path(path); - /* - * when adding the delayed refs above, the info_key might not have - * been known yet. Go over the list and replace the missing keys - */ - list_for_each_entry(ref, &prefs_delayed, list) { - if ((ref->key.offset | ref->key.type | ref->key.objectid) == 0) - memcpy(&ref->key, &info_key, sizeof(ref->key)); - } list_splice_init(&prefs_delayed, &prefs); + ret = __add_missing_keys(fs_info, &prefs); + if (ret) + goto out; + ret = __merge_refs(&prefs, 1); if (ret) goto out; - ret = __resolve_indirect_refs(fs_info, search_commit_root, &prefs); + ret = __resolve_indirect_refs(fs_info, search_commit_root, time_seq, + &prefs, extent_item_pos); if (ret) goto out; @@ -708,15 +900,39 @@ again: BUG_ON(ret < 0); } if (ref->count && ref->parent) { - ret = ulist_add(refs, ref->parent, 0, GFP_NOFS); + struct extent_inode_elem *eie = NULL; + if (extent_item_pos && !ref->inode_list) { + u32 bsz; + struct extent_buffer *eb; + bsz = btrfs_level_size(fs_info->extent_root, + info_level); + eb = read_tree_block(fs_info->extent_root, + ref->parent, bsz, 0); + BUG_ON(!eb); + ret = find_extent_in_eb(eb, bytenr, + *extent_item_pos, &eie); + ref->inode_list = eie; + free_extent_buffer(eb); + } + ret = ulist_add_merge(refs, ref->parent, + (unsigned long)ref->inode_list, + (unsigned long *)&eie, GFP_NOFS); + if (!ret && extent_item_pos) { + /* + * we've recorded that parent, so we must extend + * its inode list here + */ + BUG_ON(!eie); + while (eie->next) + eie = eie->next; + eie->next = ref->inode_list; + } BUG_ON(ret < 0); } kfree(ref); } out: - if (head) - mutex_unlock(&head->mutex); btrfs_free_path(path); while (!list_empty(&prefs)) { ref = list_first_entry(&prefs, struct __prelim_ref, list); @@ -733,6 +949,28 @@ out: return ret; } +static void free_leaf_list(struct ulist *blocks) +{ + struct ulist_node *node = NULL; + struct extent_inode_elem *eie; + struct extent_inode_elem *eie_next; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(blocks, &uiter))) { + if (!node->aux) + continue; + eie = (struct extent_inode_elem *)node->aux; + for (; eie; eie = eie_next) { + eie_next = eie->next; + kfree(eie); + } + node->aux = 0; + } + + ulist_free(blocks); +} + /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must @@ -743,7 +981,9 @@ out: */ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, - u64 num_bytes, u64 seq, struct ulist **leafs) + u64 delayed_ref_seq, u64 time_seq, + struct ulist **leafs, + const u64 *extent_item_pos) { struct ulist *tmp; int ret; @@ -757,11 +997,12 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, return -ENOMEM; } - ret = find_parent_nodes(trans, fs_info, bytenr, seq, *leafs, tmp); + ret = find_parent_nodes(trans, fs_info, bytenr, delayed_ref_seq, + time_seq, *leafs, tmp, extent_item_pos); ulist_free(tmp); if (ret < 0 && ret != -ENOENT) { - ulist_free(*leafs); + free_leaf_list(*leafs); return ret; } @@ -783,10 +1024,12 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, */ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, - u64 num_bytes, u64 seq, struct ulist **roots) + u64 delayed_ref_seq, u64 time_seq, + struct ulist **roots) { struct ulist *tmp; struct ulist_node *node = NULL; + struct ulist_iterator uiter; int ret; tmp = ulist_alloc(GFP_NOFS); @@ -798,15 +1041,16 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, return -ENOMEM; } + ULIST_ITER_INIT(&uiter); while (1) { - ret = find_parent_nodes(trans, fs_info, bytenr, seq, - tmp, *roots); + ret = find_parent_nodes(trans, fs_info, bytenr, delayed_ref_seq, + time_seq, tmp, *roots, NULL); if (ret < 0 && ret != -ENOENT) { ulist_free(tmp); ulist_free(*roots); return ret; } - node = ulist_next(tmp, node); + node = ulist_next(tmp, &uiter); if (!node) break; bytenr = node->val; @@ -893,18 +1137,22 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, s64 bytes_left = size - 1; struct extent_buffer *eb = eb_in; struct btrfs_key found_key; + int leave_spinning = path->leave_spinning; if (bytes_left >= 0) dest[bytes_left] = '\0'; + path->leave_spinning = 1; while (1) { len = btrfs_inode_ref_name_len(eb, iref); bytes_left -= len; if (bytes_left >= 0) read_extent_buffer(eb, dest + bytes_left, (unsigned long)(iref + 1), len); - if (eb != eb_in) + if (eb != eb_in) { + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); + } ret = inode_ref_info(parent, 0, fs_root, path, &found_key); if (ret > 0) ret = -ENOENT; @@ -919,8 +1167,11 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, slot = path->slots[0]; eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ - if (eb != eb_in) + if (eb != eb_in) { atomic_inc(&eb->refs); + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); @@ -931,6 +1182,7 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, } btrfs_release_path(path); + path->leave_spinning = leave_spinning; if (ret) return ERR_PTR(ret); @@ -1084,67 +1336,25 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, return 0; } -static int iterate_leaf_refs(struct btrfs_fs_info *fs_info, u64 logical, - u64 orig_extent_item_objectid, - u64 extent_item_pos, u64 root, +static int iterate_leaf_refs(struct extent_inode_elem *inode_list, + u64 root, u64 extent_item_objectid, iterate_extent_inodes_t *iterate, void *ctx) { - u64 disk_byte; - struct btrfs_key key; - struct btrfs_file_extent_item *fi; - struct extent_buffer *eb; - int slot; - int nritems; + struct extent_inode_elem *eie; int ret = 0; - int extent_type; - u64 data_offset; - u64 data_len; - - eb = read_tree_block(fs_info->tree_root, logical, - fs_info->tree_root->leafsize, 0); - if (!eb) - return -EIO; - - /* - * from the shared data ref, we only have the leaf but we need - * the key. thus, we must look into all items and see that we - * find one (some) with a reference to our extent item. - */ - nritems = btrfs_header_nritems(eb); - for (slot = 0; slot < nritems; ++slot) { - btrfs_item_key_to_cpu(eb, &key, slot); - if (key.type != BTRFS_EXTENT_DATA_KEY) - continue; - fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); - extent_type = btrfs_file_extent_type(eb, fi); - if (extent_type == BTRFS_FILE_EXTENT_INLINE) - continue; - /* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */ - disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); - if (disk_byte != orig_extent_item_objectid) - continue; - - data_offset = btrfs_file_extent_offset(eb, fi); - data_len = btrfs_file_extent_num_bytes(eb, fi); - - if (extent_item_pos < data_offset || - extent_item_pos >= data_offset + data_len) - continue; + for (eie = inode_list; eie; eie = eie->next) { pr_debug("ref for %llu resolved, key (%llu EXTEND_DATA %llu), " - "root %llu\n", orig_extent_item_objectid, - key.objectid, key.offset, root); - ret = iterate(key.objectid, - key.offset + (extent_item_pos - data_offset), - root, ctx); + "root %llu\n", extent_item_objectid, + eie->inum, eie->offset, root); + ret = iterate(eie->inum, eie->offset, root, ctx); if (ret) { - pr_debug("stopping iteration because ret=%d\n", ret); + pr_debug("stopping iteration for %llu due to ret=%d\n", + extent_item_objectid, ret); break; } } - free_extent_buffer(eb); - return ret; } @@ -1166,7 +1376,10 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, struct ulist *roots = NULL; struct ulist_node *ref_node = NULL; struct ulist_node *root_node = NULL; - struct seq_list seq_elem; + struct seq_list seq_elem = {}; + struct seq_list tree_mod_seq_elem = {}; + struct ulist_iterator ref_uiter; + struct ulist_iterator root_uiter; struct btrfs_delayed_ref_root *delayed_refs = NULL; pr_debug("resolving all inodes for extent %llu\n", @@ -1183,34 +1396,41 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, spin_lock(&delayed_refs->lock); btrfs_get_delayed_seq(delayed_refs, &seq_elem); spin_unlock(&delayed_refs->lock); + btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, - extent_item_pos, seq_elem.seq, - &refs); - + seq_elem.seq, tree_mod_seq_elem.seq, &refs, + &extent_item_pos); if (ret) goto out; - while (!ret && (ref_node = ulist_next(refs, ref_node))) { - ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, -1, - seq_elem.seq, &roots); + ULIST_ITER_INIT(&ref_uiter); + while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) { + ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, + seq_elem.seq, + tree_mod_seq_elem.seq, &roots); if (ret) break; - while (!ret && (root_node = ulist_next(roots, root_node))) { - pr_debug("root %llu references leaf %llu\n", - root_node->val, ref_node->val); - ret = iterate_leaf_refs(fs_info, ref_node->val, - extent_item_objectid, - extent_item_pos, root_node->val, - iterate, ctx); + ULIST_ITER_INIT(&root_uiter); + while (!ret && (root_node = ulist_next(roots, &root_uiter))) { + pr_debug("root %llu references leaf %llu, data list " + "%#lx\n", root_node->val, ref_node->val, + ref_node->aux); + ret = iterate_leaf_refs( + (struct extent_inode_elem *)ref_node->aux, + root_node->val, extent_item_objectid, + iterate, ctx); } + ulist_free(roots); + roots = NULL; } - ulist_free(refs); + free_leaf_list(refs); ulist_free(roots); out: if (!search_commit_root) { + btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_put_delayed_seq(delayed_refs, &seq_elem); btrfs_end_transaction(trans, fs_info->extent_root); } @@ -1247,7 +1467,7 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, struct btrfs_path *path, iterate_irefs_t *iterate, void *ctx) { - int ret; + int ret = 0; int slot; u32 cur; u32 len; @@ -1259,7 +1479,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, struct btrfs_inode_ref *iref; struct btrfs_key found_key; - while (1) { + while (!ret) { + path->leave_spinning = 1; ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path, &found_key); if (ret < 0) @@ -1275,6 +1496,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ atomic_inc(&eb->refs); + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); btrfs_release_path(path); item = btrfs_item_nr(eb, slot); @@ -1288,13 +1511,12 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, (unsigned long long)found_key.objectid, (unsigned long long)fs_root->objectid); ret = iterate(parent, iref, eb, ctx); - if (ret) { - free_extent_buffer(eb); + if (ret) break; - } len = sizeof(*iref) + name_len; iref = (struct btrfs_inode_ref *)((char *)iref + len); } + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } @@ -1414,6 +1636,8 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, void free_ipath(struct inode_fs_paths *ipath) { + if (!ipath) + return; kfree(ipath->fspath); kfree(ipath); } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 57ea2e959e4..c18d8ac7b79 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -58,7 +58,8 @@ int paths_from_inode(u64 inum, struct inode_fs_paths *ipath); int btrfs_find_all_roots(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 bytenr, - u64 num_bytes, u64 seq, struct ulist **roots); + u64 delayed_ref_seq, u64 time_seq, + struct ulist **roots); struct btrfs_data_container *init_data_container(u32 total_bytes); struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 9b9b15fd520..12394a90d60 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -24,6 +24,21 @@ #include "ordered-data.h" #include "delayed-inode.h" +/* + * ordered_data_close is set by truncate when a file that used + * to have good data has been truncated to zero. When it is set + * the btrfs file release call will add this inode to the + * ordered operations list so that we make sure to flush out any + * new data the application may have written before commit. + */ +#define BTRFS_INODE_ORDERED_DATA_CLOSE 0 +#define BTRFS_INODE_ORPHAN_META_RESERVED 1 +#define BTRFS_INODE_DUMMY 2 +#define BTRFS_INODE_IN_DEFRAG 3 +#define BTRFS_INODE_DELALLOC_META_RESERVED 4 +#define BTRFS_INODE_HAS_ORPHAN_ITEM 5 +#define BTRFS_INODE_HAS_ASYNC_EXTENT 6 + /* in memory btrfs inode */ struct btrfs_inode { /* which subvolume this inode belongs to */ @@ -57,9 +72,6 @@ struct btrfs_inode { /* used to order data wrt metadata */ struct btrfs_ordered_inode_tree ordered_tree; - /* for keeping track of orphaned inodes */ - struct list_head i_orphan; - /* list of all the delalloc inodes in the FS. There are times we need * to write all the delalloc pages to disk, and this list is used * to walk them all. @@ -78,14 +90,13 @@ struct btrfs_inode { /* the space_info for where this inode's data allocations are done */ struct btrfs_space_info *space_info; + unsigned long runtime_flags; + /* full 64 bit generation number, struct vfs_inode doesn't have a big * enough field for this. */ u64 generation; - /* sequence number for NFS changes */ - u64 sequence; - /* * transid of the trans_handle that last modified this inode */ @@ -145,22 +156,9 @@ struct btrfs_inode { unsigned reserved_extents; /* - * ordered_data_close is set by truncate when a file that used - * to have good data has been truncated to zero. When it is set - * the btrfs file release call will add this inode to the - * ordered operations list so that we make sure to flush out any - * new data the application may have written before commit. - */ - unsigned ordered_data_close:1; - unsigned orphan_meta_reserved:1; - unsigned dummy_inode:1; - unsigned in_defrag:1; - unsigned delalloc_meta_reserved:1; - - /* * always compress this one file */ - unsigned force_compress:4; + unsigned force_compress; struct btrfs_delayed_node *delayed_node; @@ -202,4 +200,17 @@ static inline bool btrfs_is_free_space_inode(struct btrfs_root *root, return false; } +static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) +{ + struct btrfs_root *root = BTRFS_I(inode)->root; + int ret = 0; + + mutex_lock(&root->log_mutex); + if (BTRFS_I(inode)->logged_trans == generation && + BTRFS_I(inode)->last_sub_trans <= root->last_log_commit) + ret = 1; + mutex_unlock(&root->log_mutex); + return ret; +} + #endif diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index c053e90f200..da6e9364a5e 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -93,6 +93,7 @@ #include "print-tree.h" #include "locking.h" #include "check-integrity.h" +#include "rcu-string.h" #define BTRFSIC_BLOCK_HASHTABLE_SIZE 0x10000 #define BTRFSIC_BLOCK_LINK_HASHTABLE_SIZE 0x10000 @@ -103,8 +104,6 @@ #define BTRFSIC_BLOCK_STACK_FRAME_MAGIC_NUMBER 20111300 #define BTRFSIC_TREE_DUMP_MAX_INDENT_LEVEL (200 - 6) /* in characters, * excluding " [...]" */ -#define BTRFSIC_BLOCK_SIZE PAGE_SIZE - #define BTRFSIC_GENERATION_UNKNOWN ((u64)-1) /* @@ -210,8 +209,9 @@ struct btrfsic_block_data_ctx { u64 dev_bytenr; /* physical bytenr on device */ u32 len; struct btrfsic_dev_state *dev; - char *data; - struct buffer_head *bh; /* do not use if set to NULL */ + char **datav; + struct page **pagev; + void *mem_to_free; }; /* This structure is used to implement recursion without occupying @@ -243,6 +243,8 @@ struct btrfsic_state { struct btrfs_root *root; u64 max_superblock_generation; struct btrfsic_block *latest_superblock; + u32 metablock_size; + u32 datablock_size; }; static void btrfsic_block_init(struct btrfsic_block *b); @@ -290,8 +292,10 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, static int btrfsic_process_metablock(struct btrfsic_state *state, struct btrfsic_block *block, struct btrfsic_block_data_ctx *block_ctx, - struct btrfs_header *hdr, int limit_nesting, int force_iodone_flag); +static void btrfsic_read_from_block_data( + struct btrfsic_block_data_ctx *block_ctx, + void *dst, u32 offset, size_t len); static int btrfsic_create_link_to_next_block( struct btrfsic_state *state, struct btrfsic_block *block, @@ -318,12 +322,13 @@ static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx); static int btrfsic_read_block(struct btrfsic_state *state, struct btrfsic_block_data_ctx *block_ctx); static void btrfsic_dump_database(struct btrfsic_state *state); +static void btrfsic_complete_bio_end_io(struct bio *bio, int err); static int btrfsic_test_for_metadata(struct btrfsic_state *state, - const u8 *data, unsigned int size); + char **datav, unsigned int num_pages); static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, - u64 dev_bytenr, u8 *mapped_data, - unsigned int len, struct bio *bio, - int *bio_is_patched, + u64 dev_bytenr, char **mapped_datav, + unsigned int num_pages, + struct bio *bio, int *bio_is_patched, struct buffer_head *bh, int submit_bio_bh_rw); static int btrfsic_process_written_superblock( @@ -375,7 +380,7 @@ static struct btrfsic_dev_state *btrfsic_dev_state_lookup( static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, u64 bytenr, struct btrfsic_dev_state *dev_state, - u64 dev_bytenr, char *data); + u64 dev_bytenr); static struct mutex btrfsic_mutex; static int btrfsic_is_initialized; @@ -651,7 +656,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, int pass; BUG_ON(NULL == state); - selected_super = kmalloc(sizeof(*selected_super), GFP_NOFS); + selected_super = kzalloc(sizeof(*selected_super), GFP_NOFS); if (NULL == selected_super) { printk(KERN_INFO "btrfsic: error, kmalloc failed!\n"); return -1; @@ -718,7 +723,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, num_copies = btrfs_num_copies(&state->root->fs_info->mapping_tree, - next_bytenr, PAGE_SIZE); + next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", (unsigned long long)next_bytenr, num_copies); @@ -727,9 +732,9 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, struct btrfsic_block *next_block; struct btrfsic_block_data_ctx tmp_next_block_ctx; struct btrfsic_block_link *l; - struct btrfs_header *hdr; - ret = btrfsic_map_block(state, next_bytenr, PAGE_SIZE, + ret = btrfsic_map_block(state, next_bytenr, + state->metablock_size, &tmp_next_block_ctx, mirror_num); if (ret) { @@ -758,7 +763,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, BUG_ON(NULL == l); ret = btrfsic_read_block(state, &tmp_next_block_ctx); - if (ret < (int)BTRFSIC_BLOCK_SIZE) { + if (ret < (int)PAGE_CACHE_SIZE) { printk(KERN_INFO "btrfsic: read @logical %llu failed!\n", (unsigned long long) @@ -768,11 +773,9 @@ static int btrfsic_process_superblock(struct btrfsic_state *state, return -1; } - hdr = (struct btrfs_header *)tmp_next_block_ctx.data; ret = btrfsic_process_metablock(state, next_block, &tmp_next_block_ctx, - hdr, BTRFS_MAX_LEVEL + 3, 1); btrfsic_release_block_ctx(&tmp_next_block_ctx); } @@ -799,7 +802,10 @@ static int btrfsic_process_superblock_dev_mirror( /* super block bytenr is always the unmapped device bytenr */ dev_bytenr = btrfs_sb_offset(superblock_mirror_num); - bh = __bread(superblock_bdev, dev_bytenr / 4096, 4096); + if (dev_bytenr + BTRFS_SUPER_INFO_SIZE > device->total_bytes) + return -1; + bh = __bread(superblock_bdev, dev_bytenr / 4096, + BTRFS_SUPER_INFO_SIZE); if (NULL == bh) return -1; super_tmp = (struct btrfs_super_block *) @@ -808,7 +814,10 @@ static int btrfsic_process_superblock_dev_mirror( if (btrfs_super_bytenr(super_tmp) != dev_bytenr || strncmp((char *)(&(super_tmp->magic)), BTRFS_MAGIC, sizeof(super_tmp->magic)) || - memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE)) { + memcmp(device->uuid, super_tmp->dev_item.uuid, BTRFS_UUID_SIZE) || + btrfs_super_nodesize(super_tmp) != state->metablock_size || + btrfs_super_leafsize(super_tmp) != state->metablock_size || + btrfs_super_sectorsize(super_tmp) != state->datablock_size) { brelse(bh); return 0; } @@ -835,13 +844,14 @@ static int btrfsic_process_superblock_dev_mirror( superblock_tmp->never_written = 0; superblock_tmp->mirror_num = 1 + superblock_mirror_num; if (state->print_mask & BTRFSIC_PRINT_MASK_SUPERBLOCK_WRITE) - printk(KERN_INFO "New initial S-block (bdev %p, %s)" - " @%llu (%s/%llu/%d)\n", - superblock_bdev, device->name, - (unsigned long long)dev_bytenr, - dev_state->name, - (unsigned long long)dev_bytenr, - superblock_mirror_num); + printk_in_rcu(KERN_INFO "New initial S-block (bdev %p, %s)" + " @%llu (%s/%llu/%d)\n", + superblock_bdev, + rcu_str_deref(device->name), + (unsigned long long)dev_bytenr, + dev_state->name, + (unsigned long long)dev_bytenr, + superblock_mirror_num); list_add(&superblock_tmp->all_blocks_node, &state->all_blocks_list); btrfsic_block_hashtable_add(superblock_tmp, @@ -893,7 +903,7 @@ static int btrfsic_process_superblock_dev_mirror( num_copies = btrfs_num_copies(&state->root->fs_info->mapping_tree, - next_bytenr, PAGE_SIZE); + next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", (unsigned long long)next_bytenr, num_copies); @@ -902,7 +912,8 @@ static int btrfsic_process_superblock_dev_mirror( struct btrfsic_block_data_ctx tmp_next_block_ctx; struct btrfsic_block_link *l; - if (btrfsic_map_block(state, next_bytenr, PAGE_SIZE, + if (btrfsic_map_block(state, next_bytenr, + state->metablock_size, &tmp_next_block_ctx, mirror_num)) { printk(KERN_INFO "btrfsic: btrfsic_map_block(" @@ -966,13 +977,15 @@ static int btrfsic_process_metablock( struct btrfsic_state *state, struct btrfsic_block *const first_block, struct btrfsic_block_data_ctx *const first_block_ctx, - struct btrfs_header *const first_hdr, int first_limit_nesting, int force_iodone_flag) { struct btrfsic_stack_frame initial_stack_frame = { 0 }; struct btrfsic_stack_frame *sf; struct btrfsic_stack_frame *next_stack; + struct btrfs_header *const first_hdr = + (struct btrfs_header *)first_block_ctx->datav[0]; + BUG_ON(!first_hdr); sf = &initial_stack_frame; sf->error = 0; sf->i = -1; @@ -1012,21 +1025,47 @@ continue_with_current_leaf_stack_frame: } if (sf->i < sf->nr) { - struct btrfs_item *disk_item = leafhdr->items + sf->i; - struct btrfs_disk_key *disk_key = &disk_item->key; + struct btrfs_item disk_item; + u32 disk_item_offset = + (uintptr_t)(leafhdr->items + sf->i) - + (uintptr_t)leafhdr; + struct btrfs_disk_key *disk_key; u8 type; - const u32 item_offset = le32_to_cpu(disk_item->offset); + u32 item_offset; + if (disk_item_offset + sizeof(struct btrfs_item) > + sf->block_ctx->len) { +leaf_item_out_of_bounce_error: + printk(KERN_INFO + "btrfsic: leaf item out of bounce at logical %llu, dev %s\n", + sf->block_ctx->start, + sf->block_ctx->dev->name); + goto one_stack_frame_backwards; + } + btrfsic_read_from_block_data(sf->block_ctx, + &disk_item, + disk_item_offset, + sizeof(struct btrfs_item)); + item_offset = le32_to_cpu(disk_item.offset); + disk_key = &disk_item.key; type = disk_key->type; if (BTRFS_ROOT_ITEM_KEY == type) { - const struct btrfs_root_item *const root_item = - (struct btrfs_root_item *) - (sf->block_ctx->data + - offsetof(struct btrfs_leaf, items) + - item_offset); - const u64 next_bytenr = - le64_to_cpu(root_item->bytenr); + struct btrfs_root_item root_item; + u32 root_item_offset; + u64 next_bytenr; + + root_item_offset = item_offset + + offsetof(struct btrfs_leaf, items); + if (root_item_offset + + sizeof(struct btrfs_root_item) > + sf->block_ctx->len) + goto leaf_item_out_of_bounce_error; + btrfsic_read_from_block_data( + sf->block_ctx, &root_item, + root_item_offset, + sizeof(struct btrfs_root_item)); + next_bytenr = le64_to_cpu(root_item.bytenr); sf->error = btrfsic_create_link_to_next_block( @@ -1041,7 +1080,7 @@ continue_with_current_leaf_stack_frame: &sf->num_copies, &sf->mirror_num, disk_key, - le64_to_cpu(root_item-> + le64_to_cpu(root_item. generation)); if (sf->error) goto one_stack_frame_backwards; @@ -1049,7 +1088,7 @@ continue_with_current_leaf_stack_frame: if (NULL != sf->next_block) { struct btrfs_header *const next_hdr = (struct btrfs_header *) - sf->next_block_ctx.data; + sf->next_block_ctx.datav[0]; next_stack = btrfsic_stack_frame_alloc(); @@ -1111,10 +1150,24 @@ continue_with_current_node_stack_frame: } if (sf->i < sf->nr) { - struct btrfs_key_ptr *disk_key_ptr = - nodehdr->ptrs + sf->i; - const u64 next_bytenr = - le64_to_cpu(disk_key_ptr->blockptr); + struct btrfs_key_ptr key_ptr; + u32 key_ptr_offset; + u64 next_bytenr; + + key_ptr_offset = (uintptr_t)(nodehdr->ptrs + sf->i) - + (uintptr_t)nodehdr; + if (key_ptr_offset + sizeof(struct btrfs_key_ptr) > + sf->block_ctx->len) { + printk(KERN_INFO + "btrfsic: node item out of bounce at logical %llu, dev %s\n", + sf->block_ctx->start, + sf->block_ctx->dev->name); + goto one_stack_frame_backwards; + } + btrfsic_read_from_block_data( + sf->block_ctx, &key_ptr, key_ptr_offset, + sizeof(struct btrfs_key_ptr)); + next_bytenr = le64_to_cpu(key_ptr.blockptr); sf->error = btrfsic_create_link_to_next_block( state, @@ -1127,15 +1180,15 @@ continue_with_current_node_stack_frame: force_iodone_flag, &sf->num_copies, &sf->mirror_num, - &disk_key_ptr->key, - le64_to_cpu(disk_key_ptr->generation)); + &key_ptr.key, + le64_to_cpu(key_ptr.generation)); if (sf->error) goto one_stack_frame_backwards; if (NULL != sf->next_block) { struct btrfs_header *const next_hdr = (struct btrfs_header *) - sf->next_block_ctx.data; + sf->next_block_ctx.datav[0]; next_stack = btrfsic_stack_frame_alloc(); if (NULL == next_stack) @@ -1181,6 +1234,35 @@ one_stack_frame_backwards: return sf->error; } +static void btrfsic_read_from_block_data( + struct btrfsic_block_data_ctx *block_ctx, + void *dstv, u32 offset, size_t len) +{ + size_t cur; + size_t offset_in_page; + char *kaddr; + char *dst = (char *)dstv; + size_t start_offset = block_ctx->start & ((u64)PAGE_CACHE_SIZE - 1); + unsigned long i = (start_offset + offset) >> PAGE_CACHE_SHIFT; + + WARN_ON(offset + len > block_ctx->len); + offset_in_page = (start_offset + offset) & + ((unsigned long)PAGE_CACHE_SIZE - 1); + + while (len > 0) { + cur = min(len, ((size_t)PAGE_CACHE_SIZE - offset_in_page)); + BUG_ON(i >= (block_ctx->len + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT); + kaddr = block_ctx->datav[i]; + memcpy(dst, kaddr + offset_in_page, cur); + + dst += cur; + len -= cur; + offset_in_page = 0; + i++; + } +} + static int btrfsic_create_link_to_next_block( struct btrfsic_state *state, struct btrfsic_block *block, @@ -1204,7 +1286,7 @@ static int btrfsic_create_link_to_next_block( if (0 == *num_copiesp) { *num_copiesp = btrfs_num_copies(&state->root->fs_info->mapping_tree, - next_bytenr, PAGE_SIZE); + next_bytenr, state->metablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", (unsigned long long)next_bytenr, *num_copiesp); @@ -1219,7 +1301,7 @@ static int btrfsic_create_link_to_next_block( "btrfsic_create_link_to_next_block(mirror_num=%d)\n", *mirror_nump); ret = btrfsic_map_block(state, next_bytenr, - BTRFSIC_BLOCK_SIZE, + state->metablock_size, next_block_ctx, *mirror_nump); if (ret) { printk(KERN_INFO @@ -1314,7 +1396,7 @@ static int btrfsic_create_link_to_next_block( if (limit_nesting > 0 && did_alloc_block_link) { ret = btrfsic_read_block(state, next_block_ctx); - if (ret < (int)BTRFSIC_BLOCK_SIZE) { + if (ret < (int)next_block_ctx->len) { printk(KERN_INFO "btrfsic: read block @logical %llu failed!\n", (unsigned long long)next_bytenr); @@ -1339,43 +1421,74 @@ static int btrfsic_handle_extent_data( u32 item_offset, int force_iodone_flag) { int ret; - struct btrfs_file_extent_item *file_extent_item = - (struct btrfs_file_extent_item *)(block_ctx->data + - offsetof(struct btrfs_leaf, - items) + item_offset); - u64 next_bytenr = - le64_to_cpu(file_extent_item->disk_bytenr) + - le64_to_cpu(file_extent_item->offset); - u64 num_bytes = le64_to_cpu(file_extent_item->num_bytes); - u64 generation = le64_to_cpu(file_extent_item->generation); + struct btrfs_file_extent_item file_extent_item; + u64 file_extent_item_offset; + u64 next_bytenr; + u64 num_bytes; + u64 generation; struct btrfsic_block_link *l; + file_extent_item_offset = offsetof(struct btrfs_leaf, items) + + item_offset; + if (file_extent_item_offset + + offsetof(struct btrfs_file_extent_item, disk_num_bytes) > + block_ctx->len) { + printk(KERN_INFO + "btrfsic: file item out of bounce at logical %llu, dev %s\n", + block_ctx->start, block_ctx->dev->name); + return -1; + } + + btrfsic_read_from_block_data(block_ctx, &file_extent_item, + file_extent_item_offset, + offsetof(struct btrfs_file_extent_item, disk_num_bytes)); + if (BTRFS_FILE_EXTENT_REG != file_extent_item.type || + ((u64)0) == le64_to_cpu(file_extent_item.disk_bytenr)) { + if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE) + printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu\n", + file_extent_item.type, + (unsigned long long) + le64_to_cpu(file_extent_item.disk_bytenr)); + return 0; + } + + if (file_extent_item_offset + sizeof(struct btrfs_file_extent_item) > + block_ctx->len) { + printk(KERN_INFO + "btrfsic: file item out of bounce at logical %llu, dev %s\n", + block_ctx->start, block_ctx->dev->name); + return -1; + } + btrfsic_read_from_block_data(block_ctx, &file_extent_item, + file_extent_item_offset, + sizeof(struct btrfs_file_extent_item)); + next_bytenr = le64_to_cpu(file_extent_item.disk_bytenr) + + le64_to_cpu(file_extent_item.offset); + generation = le64_to_cpu(file_extent_item.generation); + num_bytes = le64_to_cpu(file_extent_item.num_bytes); + generation = le64_to_cpu(file_extent_item.generation); + if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE) printk(KERN_INFO "extent_data: type %u, disk_bytenr = %llu," " offset = %llu, num_bytes = %llu\n", - file_extent_item->type, - (unsigned long long) - le64_to_cpu(file_extent_item->disk_bytenr), + file_extent_item.type, (unsigned long long) - le64_to_cpu(file_extent_item->offset), - (unsigned long long) - le64_to_cpu(file_extent_item->num_bytes)); - if (BTRFS_FILE_EXTENT_REG != file_extent_item->type || - ((u64)0) == le64_to_cpu(file_extent_item->disk_bytenr)) - return 0; + le64_to_cpu(file_extent_item.disk_bytenr), + (unsigned long long)le64_to_cpu(file_extent_item.offset), + (unsigned long long)num_bytes); while (num_bytes > 0) { u32 chunk_len; int num_copies; int mirror_num; - if (num_bytes > BTRFSIC_BLOCK_SIZE) - chunk_len = BTRFSIC_BLOCK_SIZE; + if (num_bytes > state->datablock_size) + chunk_len = state->datablock_size; else chunk_len = num_bytes; num_copies = btrfs_num_copies(&state->root->fs_info->mapping_tree, - next_bytenr, PAGE_SIZE); + next_bytenr, state->datablock_size); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", (unsigned long long)next_bytenr, num_copies); @@ -1475,8 +1588,9 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, block_ctx_out->dev_bytenr = multi->stripes[0].physical; block_ctx_out->start = bytenr; block_ctx_out->len = len; - block_ctx_out->data = NULL; - block_ctx_out->bh = NULL; + block_ctx_out->datav = NULL; + block_ctx_out->pagev = NULL; + block_ctx_out->mem_to_free = NULL; if (0 == ret) kfree(multi); @@ -1496,8 +1610,9 @@ static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr, block_ctx_out->dev_bytenr = bytenr; block_ctx_out->start = bytenr; block_ctx_out->len = len; - block_ctx_out->data = NULL; - block_ctx_out->bh = NULL; + block_ctx_out->datav = NULL; + block_ctx_out->pagev = NULL; + block_ctx_out->mem_to_free = NULL; if (NULL != block_ctx_out->dev) { return 0; } else { @@ -1508,38 +1623,127 @@ static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr, static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx) { - if (NULL != block_ctx->bh) { - brelse(block_ctx->bh); - block_ctx->bh = NULL; + if (block_ctx->mem_to_free) { + unsigned int num_pages; + + BUG_ON(!block_ctx->datav); + BUG_ON(!block_ctx->pagev); + num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; + while (num_pages > 0) { + num_pages--; + if (block_ctx->datav[num_pages]) { + kunmap(block_ctx->pagev[num_pages]); + block_ctx->datav[num_pages] = NULL; + } + if (block_ctx->pagev[num_pages]) { + __free_page(block_ctx->pagev[num_pages]); + block_ctx->pagev[num_pages] = NULL; + } + } + + kfree(block_ctx->mem_to_free); + block_ctx->mem_to_free = NULL; + block_ctx->pagev = NULL; + block_ctx->datav = NULL; } } static int btrfsic_read_block(struct btrfsic_state *state, struct btrfsic_block_data_ctx *block_ctx) { - block_ctx->bh = NULL; - if (block_ctx->dev_bytenr & 4095) { + unsigned int num_pages; + unsigned int i; + u64 dev_bytenr; + int ret; + + BUG_ON(block_ctx->datav); + BUG_ON(block_ctx->pagev); + BUG_ON(block_ctx->mem_to_free); + if (block_ctx->dev_bytenr & ((u64)PAGE_CACHE_SIZE - 1)) { printk(KERN_INFO "btrfsic: read_block() with unaligned bytenr %llu\n", (unsigned long long)block_ctx->dev_bytenr); return -1; } - if (block_ctx->len > 4096) { - printk(KERN_INFO - "btrfsic: read_block() with too huge size %d\n", - block_ctx->len); + + num_pages = (block_ctx->len + (u64)PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; + block_ctx->mem_to_free = kzalloc((sizeof(*block_ctx->datav) + + sizeof(*block_ctx->pagev)) * + num_pages, GFP_NOFS); + if (!block_ctx->mem_to_free) return -1; + block_ctx->datav = block_ctx->mem_to_free; + block_ctx->pagev = (struct page **)(block_ctx->datav + num_pages); + for (i = 0; i < num_pages; i++) { + block_ctx->pagev[i] = alloc_page(GFP_NOFS); + if (!block_ctx->pagev[i]) + return -1; } - block_ctx->bh = __bread(block_ctx->dev->bdev, - block_ctx->dev_bytenr >> 12, 4096); - if (NULL == block_ctx->bh) - return -1; - block_ctx->data = block_ctx->bh->b_data; + dev_bytenr = block_ctx->dev_bytenr; + for (i = 0; i < num_pages;) { + struct bio *bio; + unsigned int j; + DECLARE_COMPLETION_ONSTACK(complete); + + bio = bio_alloc(GFP_NOFS, num_pages - i); + if (!bio) { + printk(KERN_INFO + "btrfsic: bio_alloc() for %u pages failed!\n", + num_pages - i); + return -1; + } + bio->bi_bdev = block_ctx->dev->bdev; + bio->bi_sector = dev_bytenr >> 9; + bio->bi_end_io = btrfsic_complete_bio_end_io; + bio->bi_private = &complete; + + for (j = i; j < num_pages; j++) { + ret = bio_add_page(bio, block_ctx->pagev[j], + PAGE_CACHE_SIZE, 0); + if (PAGE_CACHE_SIZE != ret) + break; + } + if (j == i) { + printk(KERN_INFO + "btrfsic: error, failed to add a single page!\n"); + return -1; + } + submit_bio(READ, bio); + + /* this will also unplug the queue */ + wait_for_completion(&complete); + + if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { + printk(KERN_INFO + "btrfsic: read error at logical %llu dev %s!\n", + block_ctx->start, block_ctx->dev->name); + bio_put(bio); + return -1; + } + bio_put(bio); + dev_bytenr += (j - i) * PAGE_CACHE_SIZE; + i = j; + } + for (i = 0; i < num_pages; i++) { + block_ctx->datav[i] = kmap(block_ctx->pagev[i]); + if (!block_ctx->datav[i]) { + printk(KERN_INFO "btrfsic: kmap() failed (dev %s)!\n", + block_ctx->dev->name); + return -1; + } + } return block_ctx->len; } +static void btrfsic_complete_bio_end_io(struct bio *bio, int err) +{ + complete((struct completion *)bio->bi_private); +} + static void btrfsic_dump_database(struct btrfsic_state *state) { struct list_head *elem_all; @@ -1617,32 +1821,39 @@ static void btrfsic_dump_database(struct btrfsic_state *state) * (note that this test fails for the super block) */ static int btrfsic_test_for_metadata(struct btrfsic_state *state, - const u8 *data, unsigned int size) + char **datav, unsigned int num_pages) { struct btrfs_header *h; u8 csum[BTRFS_CSUM_SIZE]; u32 crc = ~(u32)0; - int fail = 0; - int crc_fail = 0; + unsigned int i; - h = (struct btrfs_header *)data; + if (num_pages * PAGE_CACHE_SIZE < state->metablock_size) + return 1; /* not metadata */ + num_pages = state->metablock_size >> PAGE_CACHE_SHIFT; + h = (struct btrfs_header *)datav[0]; if (memcmp(h->fsid, state->root->fs_info->fsid, BTRFS_UUID_SIZE)) - fail++; + return 1; + + for (i = 0; i < num_pages; i++) { + u8 *data = i ? datav[i] : (datav[i] + BTRFS_CSUM_SIZE); + size_t sublen = i ? PAGE_CACHE_SIZE : + (PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE); - crc = crc32c(crc, data + BTRFS_CSUM_SIZE, PAGE_SIZE - BTRFS_CSUM_SIZE); + crc = crc32c(crc, data, sublen); + } btrfs_csum_final(crc, csum); if (memcmp(csum, h->csum, state->csum_size)) - crc_fail++; + return 1; - return fail || crc_fail; + return 0; /* is metadata */ } static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, - u64 dev_bytenr, - u8 *mapped_data, unsigned int len, - struct bio *bio, - int *bio_is_patched, + u64 dev_bytenr, char **mapped_datav, + unsigned int num_pages, + struct bio *bio, int *bio_is_patched, struct buffer_head *bh, int submit_bio_bh_rw) { @@ -1652,12 +1863,19 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, int ret; struct btrfsic_state *state = dev_state->state; struct block_device *bdev = dev_state->bdev; + unsigned int processed_len; - WARN_ON(len > PAGE_SIZE); - is_metadata = (0 == btrfsic_test_for_metadata(state, mapped_data, len)); if (NULL != bio_is_patched) *bio_is_patched = 0; +again: + if (num_pages == 0) + return; + + processed_len = 0; + is_metadata = (0 == btrfsic_test_for_metadata(state, mapped_datav, + num_pages)); + block = btrfsic_block_hashtable_lookup(bdev, dev_bytenr, &state->block_hashtable); if (NULL != block) { @@ -1667,8 +1885,16 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, if (block->is_superblock) { bytenr = le64_to_cpu(((struct btrfs_super_block *) - mapped_data)->bytenr); + mapped_datav[0])->bytenr); + if (num_pages * PAGE_CACHE_SIZE < + BTRFS_SUPER_INFO_SIZE) { + printk(KERN_INFO + "btrfsic: cannot work with too short bios!\n"); + return; + } is_metadata = 1; + BUG_ON(BTRFS_SUPER_INFO_SIZE & (PAGE_CACHE_SIZE - 1)); + processed_len = BTRFS_SUPER_INFO_SIZE; if (state->print_mask & BTRFSIC_PRINT_MASK_TREE_BEFORE_SB_WRITE) { printk(KERN_INFO @@ -1678,12 +1904,18 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, } if (is_metadata) { if (!block->is_superblock) { + if (num_pages * PAGE_CACHE_SIZE < + state->metablock_size) { + printk(KERN_INFO + "btrfsic: cannot work with too short bios!\n"); + return; + } + processed_len = state->metablock_size; bytenr = le64_to_cpu(((struct btrfs_header *) - mapped_data)->bytenr); + mapped_datav[0])->bytenr); btrfsic_cmp_log_and_dev_bytenr(state, bytenr, dev_state, - dev_bytenr, - mapped_data); + dev_bytenr); } if (block->logical_bytenr != bytenr) { printk(KERN_INFO @@ -1710,6 +1942,13 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, block->mirror_num, btrfsic_get_block_type(state, block)); } else { + if (num_pages * PAGE_CACHE_SIZE < + state->datablock_size) { + printk(KERN_INFO + "btrfsic: cannot work with too short bios!\n"); + return; + } + processed_len = state->datablock_size; bytenr = block->logical_bytenr; if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO @@ -1747,7 +1986,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, le64_to_cpu(block->disk_key.offset), (unsigned long long) le64_to_cpu(((struct btrfs_header *) - mapped_data)->generation), + mapped_datav[0])->generation), (unsigned long long) state->max_superblock_generation); btrfsic_dump_tree(state); @@ -1765,10 +2004,10 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, (unsigned long long)block->generation, (unsigned long long) le64_to_cpu(((struct btrfs_header *) - mapped_data)->generation)); + mapped_datav[0])->generation)); /* it would not be safe to go on */ btrfsic_dump_tree(state); - return; + goto continue_loop; } /* @@ -1796,18 +2035,19 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, } if (block->is_superblock) - ret = btrfsic_map_superblock(state, bytenr, len, + ret = btrfsic_map_superblock(state, bytenr, + processed_len, bdev, &block_ctx); else - ret = btrfsic_map_block(state, bytenr, len, + ret = btrfsic_map_block(state, bytenr, processed_len, &block_ctx, 0); if (ret) { printk(KERN_INFO "btrfsic: btrfsic_map_block(root @%llu)" " failed!\n", (unsigned long long)bytenr); - return; + goto continue_loop; } - block_ctx.data = mapped_data; + block_ctx.datav = mapped_datav; /* the following is required in case of writes to mirrors, * use the same that was used for the lookup */ block_ctx.dev = dev_state; @@ -1863,11 +2103,13 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, block->logical_bytenr = bytenr; block->is_metadata = 1; if (block->is_superblock) { + BUG_ON(PAGE_CACHE_SIZE != + BTRFS_SUPER_INFO_SIZE); ret = btrfsic_process_written_superblock( state, block, (struct btrfs_super_block *) - mapped_data); + mapped_datav[0]); if (state->print_mask & BTRFSIC_PRINT_MASK_TREE_AFTER_SB_WRITE) { printk(KERN_INFO @@ -1880,8 +2122,6 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, state, block, &block_ctx, - (struct btrfs_header *) - block_ctx.data, 0, 0); } if (ret) @@ -1912,26 +2152,30 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, u64 bytenr; if (!is_metadata) { + processed_len = state->datablock_size; if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "Written block (%s/%llu/?)" " !found in hash table, D.\n", dev_state->name, (unsigned long long)dev_bytenr); - if (!state->include_extent_data) - return; /* ignore that written D block */ + if (!state->include_extent_data) { + /* ignore that written D block */ + goto continue_loop; + } /* this is getting ugly for the * include_extent_data case... */ bytenr = 0; /* unknown */ block_ctx.start = bytenr; - block_ctx.len = len; - block_ctx.bh = NULL; + block_ctx.len = processed_len; + block_ctx.mem_to_free = NULL; + block_ctx.pagev = NULL; } else { + processed_len = state->metablock_size; bytenr = le64_to_cpu(((struct btrfs_header *) - mapped_data)->bytenr); + mapped_datav[0])->bytenr); btrfsic_cmp_log_and_dev_bytenr(state, bytenr, dev_state, - dev_bytenr, - mapped_data); + dev_bytenr); if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) printk(KERN_INFO "Written block @%llu (%s/%llu/?)" @@ -1940,17 +2184,17 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, dev_state->name, (unsigned long long)dev_bytenr); - ret = btrfsic_map_block(state, bytenr, len, &block_ctx, - 0); + ret = btrfsic_map_block(state, bytenr, processed_len, + &block_ctx, 0); if (ret) { printk(KERN_INFO "btrfsic: btrfsic_map_block(root @%llu)" " failed!\n", (unsigned long long)dev_bytenr); - return; + goto continue_loop; } } - block_ctx.data = mapped_data; + block_ctx.datav = mapped_datav; /* the following is required in case of writes to mirrors, * use the same that was used for the lookup */ block_ctx.dev = dev_state; @@ -1960,7 +2204,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, if (NULL == block) { printk(KERN_INFO "btrfsic: error, kmalloc failed!\n"); btrfsic_release_block_ctx(&block_ctx); - return; + goto continue_loop; } block->dev_state = dev_state; block->dev_bytenr = dev_bytenr; @@ -2020,9 +2264,7 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, if (is_metadata) { ret = btrfsic_process_metablock(state, block, - &block_ctx, - (struct btrfs_header *) - block_ctx.data, 0, 0); + &block_ctx, 0, 0); if (ret) printk(KERN_INFO "btrfsic: process_metablock(root @%llu)" @@ -2031,6 +2273,13 @@ static void btrfsic_process_written_block(struct btrfsic_dev_state *dev_state, } btrfsic_release_block_ctx(&block_ctx); } + +continue_loop: + BUG_ON(!processed_len); + dev_bytenr += processed_len; + mapped_datav += processed_len >> PAGE_CACHE_SHIFT; + num_pages -= processed_len >> PAGE_CACHE_SHIFT; + goto again; } static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) @@ -2213,7 +2462,7 @@ static int btrfsic_process_written_superblock( num_copies = btrfs_num_copies(&state->root->fs_info->mapping_tree, - next_bytenr, PAGE_SIZE); + next_bytenr, BTRFS_SUPER_INFO_SIZE); if (state->print_mask & BTRFSIC_PRINT_MASK_NUM_COPIES) printk(KERN_INFO "num_copies(log_bytenr=%llu) = %d\n", (unsigned long long)next_bytenr, num_copies); @@ -2224,7 +2473,8 @@ static int btrfsic_process_written_superblock( printk(KERN_INFO "btrfsic_process_written_superblock(" "mirror_num=%d)\n", mirror_num); - ret = btrfsic_map_block(state, next_bytenr, PAGE_SIZE, + ret = btrfsic_map_block(state, next_bytenr, + BTRFS_SUPER_INFO_SIZE, &tmp_next_block_ctx, mirror_num); if (ret) { @@ -2689,7 +2939,7 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add( static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, u64 bytenr, struct btrfsic_dev_state *dev_state, - u64 dev_bytenr, char *data) + u64 dev_bytenr) { int num_copies; int mirror_num; @@ -2698,10 +2948,10 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, int match = 0; num_copies = btrfs_num_copies(&state->root->fs_info->mapping_tree, - bytenr, PAGE_SIZE); + bytenr, state->metablock_size); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { - ret = btrfsic_map_block(state, bytenr, PAGE_SIZE, + ret = btrfsic_map_block(state, bytenr, state->metablock_size, &block_ctx, mirror_num); if (ret) { printk(KERN_INFO "btrfsic:" @@ -2727,7 +2977,8 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state, (unsigned long long)bytenr, dev_state->name, (unsigned long long)dev_bytenr); for (mirror_num = 1; mirror_num <= num_copies; mirror_num++) { - ret = btrfsic_map_block(state, bytenr, PAGE_SIZE, + ret = btrfsic_map_block(state, bytenr, + state->metablock_size, &block_ctx, mirror_num); if (ret) continue; @@ -2781,13 +3032,13 @@ int btrfsic_submit_bh(int rw, struct buffer_head *bh) (unsigned long)bh->b_size, bh->b_data, bh->b_bdev); btrfsic_process_written_block(dev_state, dev_bytenr, - bh->b_data, bh->b_size, NULL, + &bh->b_data, 1, NULL, NULL, bh, rw); } else if (NULL != dev_state && (rw & REQ_FLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) printk(KERN_INFO - "submit_bh(rw=0x%x) FLUSH, bdev=%p)\n", + "submit_bh(rw=0x%x FLUSH, bdev=%p)\n", rw, bh->b_bdev); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & @@ -2836,6 +3087,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio) unsigned int i; u64 dev_bytenr; int bio_is_patched; + char **mapped_datav; dev_bytenr = 512 * bio->bi_sector; bio_is_patched = 0; @@ -2848,35 +3100,46 @@ void btrfsic_submit_bio(int rw, struct bio *bio) (unsigned long long)dev_bytenr, bio->bi_bdev); + mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt, + GFP_NOFS); + if (!mapped_datav) + goto leave; for (i = 0; i < bio->bi_vcnt; i++) { - u8 *mapped_data; - - mapped_data = kmap(bio->bi_io_vec[i].bv_page); + BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_CACHE_SIZE); + mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page); + if (!mapped_datav[i]) { + while (i > 0) { + i--; + kunmap(bio->bi_io_vec[i].bv_page); + } + kfree(mapped_datav); + goto leave; + } if ((BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | BTRFSIC_PRINT_MASK_VERBOSE) == (dev_state->state->print_mask & (BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH | BTRFSIC_PRINT_MASK_VERBOSE))) printk(KERN_INFO - "#%u: page=%p, mapped=%p, len=%u," - " offset=%u\n", + "#%u: page=%p, len=%u, offset=%u\n", i, bio->bi_io_vec[i].bv_page, - mapped_data, bio->bi_io_vec[i].bv_len, bio->bi_io_vec[i].bv_offset); - btrfsic_process_written_block(dev_state, dev_bytenr, - mapped_data, - bio->bi_io_vec[i].bv_len, - bio, &bio_is_patched, - NULL, rw); + } + btrfsic_process_written_block(dev_state, dev_bytenr, + mapped_datav, bio->bi_vcnt, + bio, &bio_is_patched, + NULL, rw); + while (i > 0) { + i--; kunmap(bio->bi_io_vec[i].bv_page); - dev_bytenr += bio->bi_io_vec[i].bv_len; } + kfree(mapped_datav); } else if (NULL != dev_state && (rw & REQ_FLUSH)) { if (dev_state->state->print_mask & BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH) printk(KERN_INFO - "submit_bio(rw=0x%x) FLUSH, bdev=%p)\n", + "submit_bio(rw=0x%x FLUSH, bdev=%p)\n", rw, bio->bi_bdev); if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) { if ((dev_state->state->print_mask & @@ -2903,6 +3166,7 @@ void btrfsic_submit_bio(int rw, struct bio *bio) bio->bi_end_io = btrfsic_bio_end_io; } } +leave: mutex_unlock(&btrfsic_mutex); submit_bio(rw, bio); @@ -2917,6 +3181,30 @@ int btrfsic_mount(struct btrfs_root *root, struct list_head *dev_head = &fs_devices->devices; struct btrfs_device *device; + if (root->nodesize != root->leafsize) { + printk(KERN_INFO + "btrfsic: cannot handle nodesize %d != leafsize %d!\n", + root->nodesize, root->leafsize); + return -1; + } + if (root->nodesize & ((u64)PAGE_CACHE_SIZE - 1)) { + printk(KERN_INFO + "btrfsic: cannot handle nodesize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", + root->nodesize, (unsigned long)PAGE_CACHE_SIZE); + return -1; + } + if (root->leafsize & ((u64)PAGE_CACHE_SIZE - 1)) { + printk(KERN_INFO + "btrfsic: cannot handle leafsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", + root->leafsize, (unsigned long)PAGE_CACHE_SIZE); + return -1; + } + if (root->sectorsize & ((u64)PAGE_CACHE_SIZE - 1)) { + printk(KERN_INFO + "btrfsic: cannot handle sectorsize %d not being a multiple of PAGE_CACHE_SIZE %ld!\n", + root->sectorsize, (unsigned long)PAGE_CACHE_SIZE); + return -1; + } state = kzalloc(sizeof(*state), GFP_NOFS); if (NULL == state) { printk(KERN_INFO "btrfs check-integrity: kmalloc() failed!\n"); @@ -2933,6 +3221,8 @@ int btrfsic_mount(struct btrfs_root *root, state->print_mask = print_mask; state->include_extent_data = including_extent_data; state->csum_size = 0; + state->metablock_size = root->nodesize; + state->datablock_size = root->sectorsize; INIT_LIST_HEAD(&state->all_blocks_list); btrfsic_block_hashtable_init(&state->block_hashtable); btrfsic_block_link_hashtable_init(&state->block_link_hashtable); @@ -3049,7 +3339,7 @@ void btrfsic_unmount(struct btrfs_root *root, btrfsic_block_link_free(l); } - if (b_all->is_iodone) + if (b_all->is_iodone || b_all->never_written) btrfsic_block_free(b_all); else printk(KERN_INFO "btrfs: attempt to free %c-block" diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index e801f226d7e..8206b390058 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/slab.h> +#include <linux/rbtree.h> #include "ctree.h" #include "disk-io.h" #include "transaction.h" @@ -37,7 +38,16 @@ static int balance_node_right(struct btrfs_trans_handle *trans, struct extent_buffer *dst_buf, struct extent_buffer *src_buf); static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_path *path, int level, int slot); + struct btrfs_path *path, int level, int slot, + int tree_mod_log); +static void tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb); +struct extent_buffer *read_old_tree_block(struct btrfs_root *root, u64 bytenr, + u32 blocksize, u64 parent_transid, + u64 time_seq); +struct extent_buffer *btrfs_find_old_tree_block(struct btrfs_root *root, + u64 bytenr, u32 blocksize, + u64 time_seq); struct btrfs_path *btrfs_alloc_path(void) { @@ -220,10 +230,12 @@ struct extent_buffer *btrfs_read_lock_root_node(struct btrfs_root *root) */ static void add_root_to_dirty_list(struct btrfs_root *root) { + spin_lock(&root->fs_info->trans_lock); if (root->track_dirty && list_empty(&root->dirty_list)) { list_add(&root->dirty_list, &root->fs_info->dirty_cowonly_roots); } + spin_unlock(&root->fs_info->trans_lock); } /* @@ -253,7 +265,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, 0, new_root_objectid, &disk_key, level, - buf->start, 0, 1); + buf->start, 0); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -286,6 +298,449 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, return 0; } +enum mod_log_op { + MOD_LOG_KEY_REPLACE, + MOD_LOG_KEY_ADD, + MOD_LOG_KEY_REMOVE, + MOD_LOG_KEY_REMOVE_WHILE_FREEING, + MOD_LOG_KEY_REMOVE_WHILE_MOVING, + MOD_LOG_MOVE_KEYS, + MOD_LOG_ROOT_REPLACE, +}; + +struct tree_mod_move { + int dst_slot; + int nr_items; +}; + +struct tree_mod_root { + u64 logical; + u8 level; +}; + +struct tree_mod_elem { + struct rb_node node; + u64 index; /* shifted logical */ + struct seq_list elem; + enum mod_log_op op; + + /* this is used for MOD_LOG_KEY_* and MOD_LOG_MOVE_KEYS operations */ + int slot; + + /* this is used for MOD_LOG_KEY* and MOD_LOG_ROOT_REPLACE */ + u64 generation; + + /* those are used for op == MOD_LOG_KEY_{REPLACE,REMOVE} */ + struct btrfs_disk_key key; + u64 blockptr; + + /* this is used for op == MOD_LOG_MOVE_KEYS */ + struct tree_mod_move move; + + /* this is used for op == MOD_LOG_ROOT_REPLACE */ + struct tree_mod_root old_root; +}; + +static inline void +__get_tree_mod_seq(struct btrfs_fs_info *fs_info, struct seq_list *elem) +{ + elem->seq = atomic_inc_return(&fs_info->tree_mod_seq); + list_add_tail(&elem->list, &fs_info->tree_mod_seq_list); +} + +void btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info, + struct seq_list *elem) +{ + elem->flags = 1; + spin_lock(&fs_info->tree_mod_seq_lock); + __get_tree_mod_seq(fs_info, elem); + spin_unlock(&fs_info->tree_mod_seq_lock); +} + +void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, + struct seq_list *elem) +{ + struct rb_root *tm_root; + struct rb_node *node; + struct rb_node *next; + struct seq_list *cur_elem; + struct tree_mod_elem *tm; + u64 min_seq = (u64)-1; + u64 seq_putting = elem->seq; + + if (!seq_putting) + return; + + BUG_ON(!(elem->flags & 1)); + spin_lock(&fs_info->tree_mod_seq_lock); + list_del(&elem->list); + + list_for_each_entry(cur_elem, &fs_info->tree_mod_seq_list, list) { + if ((cur_elem->flags & 1) && cur_elem->seq < min_seq) { + if (seq_putting > cur_elem->seq) { + /* + * blocker with lower sequence number exists, we + * cannot remove anything from the log + */ + goto out; + } + min_seq = cur_elem->seq; + } + } + + /* + * anything that's lower than the lowest existing (read: blocked) + * sequence number can be removed from the tree. + */ + write_lock(&fs_info->tree_mod_log_lock); + tm_root = &fs_info->tree_mod_log; + for (node = rb_first(tm_root); node; node = next) { + next = rb_next(node); + tm = container_of(node, struct tree_mod_elem, node); + if (tm->elem.seq > min_seq) + continue; + rb_erase(node, tm_root); + list_del(&tm->elem.list); + kfree(tm); + } + write_unlock(&fs_info->tree_mod_log_lock); +out: + spin_unlock(&fs_info->tree_mod_seq_lock); +} + +/* + * key order of the log: + * index -> sequence + * + * the index is the shifted logical of the *new* root node for root replace + * operations, or the shifted logical of the affected block for all other + * operations. + */ +static noinline int +__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm) +{ + struct rb_root *tm_root; + struct rb_node **new; + struct rb_node *parent = NULL; + struct tree_mod_elem *cur; + int ret = 0; + + BUG_ON(!tm || !tm->elem.seq); + + write_lock(&fs_info->tree_mod_log_lock); + tm_root = &fs_info->tree_mod_log; + new = &tm_root->rb_node; + while (*new) { + cur = container_of(*new, struct tree_mod_elem, node); + parent = *new; + if (cur->index < tm->index) + new = &((*new)->rb_left); + else if (cur->index > tm->index) + new = &((*new)->rb_right); + else if (cur->elem.seq < tm->elem.seq) + new = &((*new)->rb_left); + else if (cur->elem.seq > tm->elem.seq) + new = &((*new)->rb_right); + else { + kfree(tm); + ret = -EEXIST; + goto unlock; + } + } + + rb_link_node(&tm->node, parent, new); + rb_insert_color(&tm->node, tm_root); +unlock: + write_unlock(&fs_info->tree_mod_log_lock); + return ret; +} + +static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb) { + smp_mb(); + if (list_empty(&(fs_info)->tree_mod_seq_list)) + return 1; + if (!eb) + return 0; + if (btrfs_header_level(eb) == 0) + return 1; + return 0; +} + +/* + * This allocates memory and gets a tree modification sequence number when + * needed. + * + * Returns 0 when no sequence number is needed, < 0 on error. + * Returns 1 when a sequence number was added. In this case, + * fs_info->tree_mod_seq_lock was acquired and must be released by the caller + * after inserting into the rb tree. + */ +static inline int tree_mod_alloc(struct btrfs_fs_info *fs_info, gfp_t flags, + struct tree_mod_elem **tm_ret) +{ + struct tree_mod_elem *tm; + int seq; + + if (tree_mod_dont_log(fs_info, NULL)) + return 0; + + tm = *tm_ret = kzalloc(sizeof(*tm), flags); + if (!tm) + return -ENOMEM; + + tm->elem.flags = 0; + spin_lock(&fs_info->tree_mod_seq_lock); + if (list_empty(&fs_info->tree_mod_seq_list)) { + /* + * someone emptied the list while we were waiting for the lock. + * we must not add to the list, because no blocker exists. items + * are removed from the list only when the existing blocker is + * removed from the list. + */ + kfree(tm); + seq = 0; + spin_unlock(&fs_info->tree_mod_seq_lock); + } else { + __get_tree_mod_seq(fs_info, &tm->elem); + seq = tm->elem.seq; + } + + return seq; +} + +static noinline int +tree_mod_log_insert_key_mask(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int slot, + enum mod_log_op op, gfp_t flags) +{ + struct tree_mod_elem *tm; + int ret; + + ret = tree_mod_alloc(fs_info, flags, &tm); + if (ret <= 0) + return ret; + + tm->index = eb->start >> PAGE_CACHE_SHIFT; + if (op != MOD_LOG_KEY_ADD) { + btrfs_node_key(eb, &tm->key, slot); + tm->blockptr = btrfs_node_blockptr(eb, slot); + } + tm->op = op; + tm->slot = slot; + tm->generation = btrfs_node_ptr_generation(eb, slot); + + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; +} + +static noinline int +tree_mod_log_insert_key(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, + int slot, enum mod_log_op op) +{ + return tree_mod_log_insert_key_mask(fs_info, eb, slot, op, GFP_NOFS); +} + +static noinline int +tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, int dst_slot, int src_slot, + int nr_items, gfp_t flags) +{ + struct tree_mod_elem *tm; + int ret; + int i; + + if (tree_mod_dont_log(fs_info, eb)) + return 0; + + for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { + ret = tree_mod_log_insert_key(fs_info, eb, i + dst_slot, + MOD_LOG_KEY_REMOVE_WHILE_MOVING); + BUG_ON(ret < 0); + } + + ret = tree_mod_alloc(fs_info, flags, &tm); + if (ret <= 0) + return ret; + + tm->index = eb->start >> PAGE_CACHE_SHIFT; + tm->slot = src_slot; + tm->move.dst_slot = dst_slot; + tm->move.nr_items = nr_items; + tm->op = MOD_LOG_MOVE_KEYS; + + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; +} + +static noinline int +tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, + struct extent_buffer *old_root, + struct extent_buffer *new_root, gfp_t flags) +{ + struct tree_mod_elem *tm; + int ret; + + ret = tree_mod_alloc(fs_info, flags, &tm); + if (ret <= 0) + return ret; + + tm->index = new_root->start >> PAGE_CACHE_SHIFT; + tm->old_root.logical = old_root->start; + tm->old_root.level = btrfs_header_level(old_root); + tm->generation = btrfs_header_generation(old_root); + tm->op = MOD_LOG_ROOT_REPLACE; + + ret = __tree_mod_log_insert(fs_info, tm); + spin_unlock(&fs_info->tree_mod_seq_lock); + return ret; +} + +static struct tree_mod_elem * +__tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq, + int smallest) +{ + struct rb_root *tm_root; + struct rb_node *node; + struct tree_mod_elem *cur = NULL; + struct tree_mod_elem *found = NULL; + u64 index = start >> PAGE_CACHE_SHIFT; + + read_lock(&fs_info->tree_mod_log_lock); + tm_root = &fs_info->tree_mod_log; + node = tm_root->rb_node; + while (node) { + cur = container_of(node, struct tree_mod_elem, node); + if (cur->index < index) { + node = node->rb_left; + } else if (cur->index > index) { + node = node->rb_right; + } else if (cur->elem.seq < min_seq) { + node = node->rb_left; + } else if (!smallest) { + /* we want the node with the highest seq */ + if (found) + BUG_ON(found->elem.seq > cur->elem.seq); + found = cur; + node = node->rb_left; + } else if (cur->elem.seq > min_seq) { + /* we want the node with the smallest seq */ + if (found) + BUG_ON(found->elem.seq < cur->elem.seq); + found = cur; + node = node->rb_right; + } else { + found = cur; + break; + } + } + read_unlock(&fs_info->tree_mod_log_lock); + + return found; +} + +/* + * this returns the element from the log with the smallest time sequence + * value that's in the log (the oldest log item). any element with a time + * sequence lower than min_seq will be ignored. + */ +static struct tree_mod_elem * +tree_mod_log_search_oldest(struct btrfs_fs_info *fs_info, u64 start, + u64 min_seq) +{ + return __tree_mod_log_search(fs_info, start, min_seq, 1); +} + +/* + * this returns the element from the log with the largest time sequence + * value that's in the log (the most recent log item). any element with + * a time sequence lower than min_seq will be ignored. + */ +static struct tree_mod_elem * +tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq) +{ + return __tree_mod_log_search(fs_info, start, min_seq, 0); +} + +static inline void +tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, + struct extent_buffer *src, unsigned long dst_offset, + unsigned long src_offset, int nr_items) +{ + int ret; + int i; + + if (tree_mod_dont_log(fs_info, NULL)) + return; + + if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0) + return; + + /* speed this up by single seq for all operations? */ + for (i = 0; i < nr_items; i++) { + ret = tree_mod_log_insert_key(fs_info, src, i + src_offset, + MOD_LOG_KEY_REMOVE); + BUG_ON(ret < 0); + ret = tree_mod_log_insert_key(fs_info, dst, i + dst_offset, + MOD_LOG_KEY_ADD); + BUG_ON(ret < 0); + } +} + +static inline void +tree_mod_log_eb_move(struct btrfs_fs_info *fs_info, struct extent_buffer *dst, + int dst_offset, int src_offset, int nr_items) +{ + int ret; + ret = tree_mod_log_insert_move(fs_info, dst, dst_offset, src_offset, + nr_items, GFP_NOFS); + BUG_ON(ret < 0); +} + +static inline void +tree_mod_log_set_node_key(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb, + struct btrfs_disk_key *disk_key, int slot, int atomic) +{ + int ret; + + ret = tree_mod_log_insert_key_mask(fs_info, eb, slot, + MOD_LOG_KEY_REPLACE, + atomic ? GFP_ATOMIC : GFP_NOFS); + BUG_ON(ret < 0); +} + +static void tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, + struct extent_buffer *eb) +{ + int i; + int ret; + u32 nritems; + + if (tree_mod_dont_log(fs_info, eb)) + return; + + nritems = btrfs_header_nritems(eb); + for (i = nritems - 1; i >= 0; i--) { + ret = tree_mod_log_insert_key(fs_info, eb, i, + MOD_LOG_KEY_REMOVE_WHILE_FREEING); + BUG_ON(ret < 0); + } +} + +static inline void +tree_mod_log_set_root_pointer(struct btrfs_root *root, + struct extent_buffer *new_root_node) +{ + int ret; + tree_mod_log_free_eb(root->fs_info, root->node); + ret = tree_mod_log_insert_root(root->fs_info, root->node, + new_root_node, GFP_NOFS); + BUG_ON(ret < 0); +} + /* * check if the tree block can be shared by multiple trees */ @@ -407,6 +862,12 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, buf, 1, 1); BUG_ON(ret); /* -ENOMEM */ } + /* + * don't log freeing in case we're freeing the root node, this + * is done by tree_mod_log_set_root_pointer later + */ + if (buf != root->node && btrfs_header_level(buf) != 0) + tree_mod_log_free_eb(root->fs_info, buf); clean_tree_block(trans, root, buf); *last_ref = 1; } @@ -465,7 +926,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start, root->root_key.objectid, &disk_key, - level, search_start, empty_size, 1); + level, search_start, empty_size); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -504,10 +965,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, parent_start = 0; extent_buffer_get(cow); + tree_mod_log_set_root_pointer(root, cow); rcu_assign_pointer(root->node, cow); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref, 1); + last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -517,13 +979,15 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, parent_start = 0; WARN_ON(trans->transid != btrfs_header_generation(parent)); + tree_mod_log_insert_key(root->fs_info, parent, parent_slot, + MOD_LOG_KEY_REPLACE); btrfs_set_node_blockptr(parent, parent_slot, cow->start); btrfs_set_node_ptr_generation(parent, parent_slot, trans->transid); btrfs_mark_buffer_dirty(parent); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref, 1); + last_ref); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -533,6 +997,229 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return 0; } +/* + * returns the logical address of the oldest predecessor of the given root. + * entries older than time_seq are ignored. + */ +static struct tree_mod_elem * +__tree_mod_log_oldest_root(struct btrfs_fs_info *fs_info, + struct btrfs_root *root, u64 time_seq) +{ + struct tree_mod_elem *tm; + struct tree_mod_elem *found = NULL; + u64 root_logical = root->node->start; + int looped = 0; + + if (!time_seq) + return 0; + + /* + * the very last operation that's logged for a root is the replacement + * operation (if it is replaced at all). this has the index of the *new* + * root, making it the very first operation that's logged for this root. + */ + while (1) { + tm = tree_mod_log_search_oldest(fs_info, root_logical, + time_seq); + if (!looped && !tm) + return 0; + /* + * if there are no tree operation for the oldest root, we simply + * return it. this should only happen if that (old) root is at + * level 0. + */ + if (!tm) + break; + + /* + * if there's an operation that's not a root replacement, we + * found the oldest version of our root. normally, we'll find a + * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here. + */ + if (tm->op != MOD_LOG_ROOT_REPLACE) + break; + + found = tm; + root_logical = tm->old_root.logical; + BUG_ON(root_logical == root->node->start); + looped = 1; + } + + /* if there's no old root to return, return what we found instead */ + if (!found) + found = tm; + + return found; +} + +/* + * tm is a pointer to the first operation to rewind within eb. then, all + * previous operations will be rewinded (until we reach something older than + * time_seq). + */ +static void +__tree_mod_log_rewind(struct extent_buffer *eb, u64 time_seq, + struct tree_mod_elem *first_tm) +{ + u32 n; + struct rb_node *next; + struct tree_mod_elem *tm = first_tm; + unsigned long o_dst; + unsigned long o_src; + unsigned long p_size = sizeof(struct btrfs_key_ptr); + + n = btrfs_header_nritems(eb); + while (tm && tm->elem.seq >= time_seq) { + /* + * all the operations are recorded with the operator used for + * the modification. as we're going backwards, we do the + * opposite of each operation here. + */ + switch (tm->op) { + case MOD_LOG_KEY_REMOVE_WHILE_FREEING: + BUG_ON(tm->slot < n); + case MOD_LOG_KEY_REMOVE_WHILE_MOVING: + case MOD_LOG_KEY_REMOVE: + btrfs_set_node_key(eb, &tm->key, tm->slot); + btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr); + btrfs_set_node_ptr_generation(eb, tm->slot, + tm->generation); + n++; + break; + case MOD_LOG_KEY_REPLACE: + BUG_ON(tm->slot >= n); + btrfs_set_node_key(eb, &tm->key, tm->slot); + btrfs_set_node_blockptr(eb, tm->slot, tm->blockptr); + btrfs_set_node_ptr_generation(eb, tm->slot, + tm->generation); + break; + case MOD_LOG_KEY_ADD: + /* if a move operation is needed it's in the log */ + n--; + break; + case MOD_LOG_MOVE_KEYS: + o_dst = btrfs_node_key_ptr_offset(tm->slot); + o_src = btrfs_node_key_ptr_offset(tm->move.dst_slot); + memmove_extent_buffer(eb, o_dst, o_src, + tm->move.nr_items * p_size); + break; + case MOD_LOG_ROOT_REPLACE: + /* + * this operation is special. for roots, this must be + * handled explicitly before rewinding. + * for non-roots, this operation may exist if the node + * was a root: root A -> child B; then A gets empty and + * B is promoted to the new root. in the mod log, we'll + * have a root-replace operation for B, a tree block + * that is no root. we simply ignore that operation. + */ + break; + } + next = rb_next(&tm->node); + if (!next) + break; + tm = container_of(next, struct tree_mod_elem, node); + if (tm->index != first_tm->index) + break; + } + btrfs_set_header_nritems(eb, n); +} + +static struct extent_buffer * +tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, + u64 time_seq) +{ + struct extent_buffer *eb_rewin; + struct tree_mod_elem *tm; + + if (!time_seq) + return eb; + + if (btrfs_header_level(eb) == 0) + return eb; + + tm = tree_mod_log_search(fs_info, eb->start, time_seq); + if (!tm) + return eb; + + if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) { + BUG_ON(tm->slot != 0); + eb_rewin = alloc_dummy_extent_buffer(eb->start, + fs_info->tree_root->nodesize); + BUG_ON(!eb_rewin); + btrfs_set_header_bytenr(eb_rewin, eb->start); + btrfs_set_header_backref_rev(eb_rewin, + btrfs_header_backref_rev(eb)); + btrfs_set_header_owner(eb_rewin, btrfs_header_owner(eb)); + btrfs_set_header_level(eb_rewin, btrfs_header_level(eb)); + } else { + eb_rewin = btrfs_clone_extent_buffer(eb); + BUG_ON(!eb_rewin); + } + + extent_buffer_get(eb_rewin); + free_extent_buffer(eb); + + __tree_mod_log_rewind(eb_rewin, time_seq, tm); + + return eb_rewin; +} + +/* + * get_old_root() rewinds the state of @root's root node to the given @time_seq + * value. If there are no changes, the current root->root_node is returned. If + * anything changed in between, there's a fresh buffer allocated on which the + * rewind operations are done. In any case, the returned buffer is read locked. + * Returns NULL on error (with no locks held). + */ +static inline struct extent_buffer * +get_old_root(struct btrfs_root *root, u64 time_seq) +{ + struct tree_mod_elem *tm; + struct extent_buffer *eb; + struct tree_mod_root *old_root = NULL; + u64 old_generation = 0; + u64 logical; + + eb = btrfs_read_lock_root_node(root); + tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq); + if (!tm) + return root->node; + + if (tm->op == MOD_LOG_ROOT_REPLACE) { + old_root = &tm->old_root; + old_generation = tm->generation; + logical = old_root->logical; + } else { + logical = root->node->start; + } + + tm = tree_mod_log_search(root->fs_info, logical, time_seq); + if (old_root) + eb = alloc_dummy_extent_buffer(logical, root->nodesize); + else + eb = btrfs_clone_extent_buffer(root->node); + btrfs_tree_read_unlock(root->node); + free_extent_buffer(root->node); + if (!eb) + return NULL; + btrfs_tree_read_lock(eb); + if (old_root) { + btrfs_set_header_bytenr(eb, eb->start); + btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); + btrfs_set_header_owner(eb, root->root_key.objectid); + btrfs_set_header_level(eb, old_root->level); + btrfs_set_header_generation(eb, old_generation); + } + if (tm) + __tree_mod_log_rewind(eb, time_seq, tm); + else + WARN_ON(btrfs_header_level(eb) != 0); + extent_buffer_get(eb); + + return eb; +} + static inline int should_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf) @@ -723,7 +1410,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, cur = btrfs_find_tree_block(root, blocknr, blocksize); if (cur) - uptodate = btrfs_buffer_uptodate(cur, gen); + uptodate = btrfs_buffer_uptodate(cur, gen, 0); else uptodate = 0; if (!cur || !uptodate) { @@ -737,7 +1424,11 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans, if (!cur) return -EIO; } else if (!uptodate) { - btrfs_read_buffer(cur, gen); + err = btrfs_read_buffer(cur, gen); + if (err) { + free_extent_buffer(cur); + return err; + } } } if (search_start == 0) @@ -852,20 +1543,18 @@ static noinline int generic_bin_search(struct extent_buffer *eb, static int bin_search(struct extent_buffer *eb, struct btrfs_key *key, int level, int *slot) { - if (level == 0) { + if (level == 0) return generic_bin_search(eb, offsetof(struct btrfs_leaf, items), sizeof(struct btrfs_item), key, btrfs_header_nritems(eb), slot); - } else { + else return generic_bin_search(eb, offsetof(struct btrfs_node, ptrs), sizeof(struct btrfs_key_ptr), key, btrfs_header_nritems(eb), slot); - } - return -1; } int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key, @@ -972,6 +1661,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, goto enospc; } + tree_mod_log_set_root_pointer(root, child); rcu_assign_pointer(root->node, child); add_root_to_dirty_list(root); @@ -985,7 +1675,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1, 0); + btrfs_free_tree_block(trans, root, mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); return 0; @@ -994,8 +1684,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, BTRFS_NODEPTRS_PER_BLOCK(root) / 4) return 0; - btrfs_header_nritems(mid); - left = read_node_slot(root, parent, pslot - 1); if (left) { btrfs_tree_lock(left); @@ -1025,7 +1713,6 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, wret = push_node_left(trans, root, left, mid, 1); if (wret < 0) ret = wret; - btrfs_header_nritems(mid); } /* @@ -1038,14 +1725,16 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (btrfs_header_nritems(right) == 0) { clean_tree_block(trans, root, right); btrfs_tree_unlock(right); - del_ptr(trans, root, path, level + 1, pslot + 1); + del_ptr(trans, root, path, level + 1, pslot + 1, 1); root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1, 0); + btrfs_free_tree_block(trans, root, right, 0, 1); free_extent_buffer_stale(right); right = NULL; } else { struct btrfs_disk_key right_key; btrfs_node_key(right, &right_key, 0); + tree_mod_log_set_node_key(root->fs_info, parent, + &right_key, pslot + 1, 0); btrfs_set_node_key(parent, &right_key, pslot + 1); btrfs_mark_buffer_dirty(parent); } @@ -1080,15 +1769,17 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (btrfs_header_nritems(mid) == 0) { clean_tree_block(trans, root, mid); btrfs_tree_unlock(mid); - del_ptr(trans, root, path, level + 1, pslot); + del_ptr(trans, root, path, level + 1, pslot, 1); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1, 0); + btrfs_free_tree_block(trans, root, mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; } else { /* update the parent key to reflect our changes */ struct btrfs_disk_key mid_key; btrfs_node_key(mid, &mid_key, 0); + tree_mod_log_set_node_key(root->fs_info, parent, &mid_key, + pslot, 0); btrfs_set_node_key(parent, &mid_key, pslot); btrfs_mark_buffer_dirty(parent); } @@ -1186,6 +1877,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, struct btrfs_disk_key disk_key; orig_slot += left_nr; btrfs_node_key(mid, &disk_key, 0); + tree_mod_log_set_node_key(root->fs_info, parent, + &disk_key, pslot, 0); btrfs_set_node_key(parent, &disk_key, pslot); btrfs_mark_buffer_dirty(parent); if (btrfs_header_nritems(left) > orig_slot) { @@ -1237,6 +1930,8 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans, struct btrfs_disk_key disk_key; btrfs_node_key(right, &disk_key, 0); + tree_mod_log_set_node_key(root->fs_info, parent, + &disk_key, pslot + 1, 0); btrfs_set_node_key(parent, &disk_key, pslot + 1); btrfs_mark_buffer_dirty(parent); @@ -1358,7 +2053,12 @@ static noinline int reada_for_balance(struct btrfs_root *root, block1 = btrfs_node_blockptr(parent, slot - 1); gen = btrfs_node_ptr_generation(parent, slot - 1); eb = btrfs_find_tree_block(root, block1, blocksize); - if (eb && btrfs_buffer_uptodate(eb, gen)) + /* + * if we get -eagain from btrfs_buffer_uptodate, we + * don't want to return eagain here. That will loop + * forever + */ + if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) block1 = 0; free_extent_buffer(eb); } @@ -1366,7 +2066,7 @@ static noinline int reada_for_balance(struct btrfs_root *root, block2 = btrfs_node_blockptr(parent, slot + 1); gen = btrfs_node_ptr_generation(parent, slot + 1); eb = btrfs_find_tree_block(root, block2, blocksize); - if (eb && btrfs_buffer_uptodate(eb, gen)) + if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0) block2 = 0; free_extent_buffer(eb); } @@ -1489,7 +2189,7 @@ static int read_block_for_search(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *p, struct extent_buffer **eb_ret, int level, int slot, - struct btrfs_key *key) + struct btrfs_key *key, u64 time_seq) { u64 blocknr; u64 gen; @@ -1504,8 +2204,9 @@ read_block_for_search(struct btrfs_trans_handle *trans, tmp = btrfs_find_tree_block(root, blocknr, blocksize); if (tmp) { - if (btrfs_buffer_uptodate(tmp, 0)) { - if (btrfs_buffer_uptodate(tmp, gen)) { + /* first we do an atomic uptodate check */ + if (btrfs_buffer_uptodate(tmp, 0, 1) > 0) { + if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) { /* * we found an up to date block without * sleeping, return @@ -1523,8 +2224,9 @@ read_block_for_search(struct btrfs_trans_handle *trans, free_extent_buffer(tmp); btrfs_set_path_blocking(p); + /* now we're allowed to do a blocking uptodate check */ tmp = read_tree_block(root, blocknr, blocksize, gen); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + if (tmp && btrfs_buffer_uptodate(tmp, gen, 0) > 0) { *eb_ret = tmp; return 0; } @@ -1559,7 +2261,7 @@ read_block_for_search(struct btrfs_trans_handle *trans, * and give up so that our caller doesn't loop forever * on our EAGAINs. */ - if (!btrfs_buffer_uptodate(tmp, 0)) + if (!btrfs_buffer_uptodate(tmp, 0, 0)) ret = -EIO; free_extent_buffer(tmp); } @@ -1841,7 +2543,7 @@ cow_done: } err = read_block_for_search(trans, root, p, - &b, level, slot, key); + &b, level, slot, key, 0); if (err == -EAGAIN) goto again; if (err) { @@ -1913,6 +2615,113 @@ done: } /* + * Like btrfs_search_slot, this looks for a key in the given tree. It uses the + * current state of the tree together with the operations recorded in the tree + * modification log to search for the key in a previous version of this tree, as + * denoted by the time_seq parameter. + * + * Naturally, there is no support for insert, delete or cow operations. + * + * The resulting path and return value will be set up as if we called + * btrfs_search_slot at that point in time with ins_len and cow both set to 0. + */ +int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, + struct btrfs_path *p, u64 time_seq) +{ + struct extent_buffer *b; + int slot; + int ret; + int err; + int level; + int lowest_unlock = 1; + u8 lowest_level = 0; + + lowest_level = p->lowest_level; + WARN_ON(p->nodes[0] != NULL); + + if (p->search_commit_root) { + BUG_ON(time_seq); + return btrfs_search_slot(NULL, root, key, p, 0, 0); + } + +again: + b = get_old_root(root, time_seq); + level = btrfs_header_level(b); + p->locks[level] = BTRFS_READ_LOCK; + + while (b) { + level = btrfs_header_level(b); + p->nodes[level] = b; + btrfs_clear_path_blocking(p, NULL, 0); + + /* + * we have a lock on b and as long as we aren't changing + * the tree, there is no way to for the items in b to change. + * It is safe to drop the lock on our parent before we + * go through the expensive btree search on b. + */ + btrfs_unlock_up_safe(p, level + 1); + + ret = bin_search(b, key, level, &slot); + + if (level != 0) { + int dec = 0; + if (ret && slot > 0) { + dec = 1; + slot -= 1; + } + p->slots[level] = slot; + unlock_up(p, level, lowest_unlock, 0, NULL); + + if (level == lowest_level) { + if (dec) + p->slots[level]++; + goto done; + } + + err = read_block_for_search(NULL, root, p, &b, level, + slot, key, time_seq); + if (err == -EAGAIN) + goto again; + if (err) { + ret = err; + goto done; + } + + level = btrfs_header_level(b); + err = btrfs_try_tree_read_lock(b); + if (!err) { + btrfs_set_path_blocking(p); + btrfs_tree_read_lock(b); + btrfs_clear_path_blocking(p, b, + BTRFS_READ_LOCK); + } + p->locks[level] = BTRFS_READ_LOCK; + p->nodes[level] = b; + b = tree_mod_log_rewind(root->fs_info, b, time_seq); + if (b != p->nodes[level]) { + btrfs_tree_unlock_rw(p->nodes[level], + p->locks[level]); + p->locks[level] = 0; + p->nodes[level] = b; + } + } else { + p->slots[level] = slot; + unlock_up(p, level, lowest_unlock, 0, NULL); + goto done; + } + } + ret = 1; +done: + if (!p->leave_spinning) + btrfs_set_path_blocking(p); + if (ret < 0) + btrfs_release_path(p); + + return ret; +} + +/* * adjust the pointers going up the tree, starting at level * making sure the right key of each node is points to 'key'. * This is used after shifting pointers to the left, so it stops @@ -1932,6 +2741,7 @@ static void fixup_low_keys(struct btrfs_trans_handle *trans, if (!path->nodes[i]) break; t = path->nodes[i]; + tree_mod_log_set_node_key(root->fs_info, t, key, tslot, 1); btrfs_set_node_key(t, key, tslot); btrfs_mark_buffer_dirty(path->nodes[i]); if (tslot != 0) @@ -2014,12 +2824,16 @@ static int push_node_left(struct btrfs_trans_handle *trans, } else push_items = min(src_nritems - 8, push_items); + tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0, + push_items); copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(dst_nritems), btrfs_node_key_ptr_offset(0), push_items * sizeof(struct btrfs_key_ptr)); if (push_items < src_nritems) { + tree_mod_log_eb_move(root->fs_info, src, 0, push_items, + src_nritems - push_items); memmove_extent_buffer(src, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(push_items), (src_nritems - push_items) * @@ -2073,11 +2887,14 @@ static int balance_node_right(struct btrfs_trans_handle *trans, if (max_push < push_items) push_items = max_push; + tree_mod_log_eb_move(root->fs_info, dst, push_items, 0, dst_nritems); memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(push_items), btrfs_node_key_ptr_offset(0), (dst_nritems) * sizeof(struct btrfs_key_ptr)); + tree_mod_log_eb_copy(root->fs_info, dst, src, 0, + src_nritems - push_items, push_items); copy_extent_buffer(dst, src, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(src_nritems - push_items), @@ -2120,7 +2937,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, c = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, &lower_key, - level, root->node->start, 0, 0); + level, root->node->start, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -2152,6 +2969,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, btrfs_mark_buffer_dirty(c); old = root->node; + tree_mod_log_set_root_pointer(root, c); rcu_assign_pointer(root->node, c); /* the super has an extra ref to root->node */ @@ -2179,6 +2997,7 @@ static void insert_ptr(struct btrfs_trans_handle *trans, { struct extent_buffer *lower; int nritems; + int ret; BUG_ON(!path->nodes[level]); btrfs_assert_tree_locked(path->nodes[level]); @@ -2187,11 +3006,19 @@ static void insert_ptr(struct btrfs_trans_handle *trans, BUG_ON(slot > nritems); BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root)); if (slot != nritems) { + if (level) + tree_mod_log_eb_move(root->fs_info, lower, slot + 1, + slot, nritems - slot); memmove_extent_buffer(lower, btrfs_node_key_ptr_offset(slot + 1), btrfs_node_key_ptr_offset(slot), (nritems - slot) * sizeof(struct btrfs_key_ptr)); } + if (level) { + ret = tree_mod_log_insert_key(root->fs_info, lower, slot, + MOD_LOG_KEY_ADD); + BUG_ON(ret < 0); + } btrfs_set_node_key(lower, key, slot); btrfs_set_node_blockptr(lower, slot, bytenr); WARN_ON(trans->transid == 0); @@ -2243,7 +3070,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, split = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, - &disk_key, level, c->start, 0, 0); + &disk_key, level, c->start, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -2262,7 +3089,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, (unsigned long)btrfs_header_chunk_tree_uuid(split), BTRFS_UUID_SIZE); - + tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid); copy_extent_buffer(split, c, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(mid), @@ -2995,7 +3822,7 @@ again: right = btrfs_alloc_free_block(trans, root, root->leafsize, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0, 0); + &disk_key, 0, l->start, 0); if (IS_ERR(right)) return PTR_ERR(right); @@ -3740,19 +4567,29 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root * empty a node. */ static void del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct btrfs_path *path, int level, int slot) + struct btrfs_path *path, int level, int slot, + int tree_mod_log) { struct extent_buffer *parent = path->nodes[level]; u32 nritems; + int ret; nritems = btrfs_header_nritems(parent); if (slot != nritems - 1) { + if (tree_mod_log && level) + tree_mod_log_eb_move(root->fs_info, parent, slot, + slot + 1, nritems - slot - 1); memmove_extent_buffer(parent, btrfs_node_key_ptr_offset(slot), btrfs_node_key_ptr_offset(slot + 1), sizeof(struct btrfs_key_ptr) * (nritems - slot - 1)); + } else if (tree_mod_log && level) { + ret = tree_mod_log_insert_key(root->fs_info, parent, slot, + MOD_LOG_KEY_REMOVE); + BUG_ON(ret < 0); } + nritems--; btrfs_set_header_nritems(parent, nritems); if (nritems == 0 && parent == root->node) { @@ -3784,7 +4621,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, struct extent_buffer *leaf) { WARN_ON(btrfs_header_generation(leaf) != trans->transid); - del_ptr(trans, root, path, 1, path->slots[1]); + del_ptr(trans, root, path, 1, path->slots[1], 1); /* * btrfs_free_extent is expensive, we want to make sure we @@ -3795,7 +4632,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); extent_buffer_get(leaf); - btrfs_free_tree_block(trans, root, leaf, 0, 1, 0); + btrfs_free_tree_block(trans, root, leaf, 0, 1); free_extent_buffer_stale(leaf); } /* @@ -4043,7 +4880,7 @@ again: tmp = btrfs_find_tree_block(root, blockptr, btrfs_level_size(root, level - 1)); - if (tmp && btrfs_buffer_uptodate(tmp, gen)) { + if (tmp && btrfs_buffer_uptodate(tmp, gen, 1) > 0) { free_extent_buffer(tmp); break; } @@ -4166,7 +5003,8 @@ next: struct extent_buffer *cur; cur = btrfs_find_tree_block(root, blockptr, btrfs_level_size(root, level - 1)); - if (!cur || !btrfs_buffer_uptodate(cur, gen)) { + if (!cur || + btrfs_buffer_uptodate(cur, gen, 1) <= 0) { slot++; if (cur) free_extent_buffer(cur); @@ -4192,6 +5030,12 @@ next: */ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path) { + return btrfs_next_old_leaf(root, path, 0); +} + +int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, + u64 time_seq) +{ int slot; int level; struct extent_buffer *c; @@ -4216,7 +5060,10 @@ again: path->keep_locks = 1; path->leave_spinning = 1; - ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); + if (time_seq) + ret = btrfs_search_old_slot(root, &key, path, time_seq); + else + ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); path->keep_locks = 0; if (ret < 0) @@ -4261,7 +5108,7 @@ again: next = c; next_rw_lock = path->locks[level]; ret = read_block_for_search(NULL, root, path, &next, level, - slot, &key); + slot, &key, 0); if (ret == -EAGAIN) goto again; @@ -4272,6 +5119,18 @@ again: if (!path->skip_locking) { ret = btrfs_try_tree_read_lock(next); + if (!ret && time_seq) { + /* + * If we don't get the lock, we may be racing + * with push_leaf_left, holding that lock while + * itself waiting for the leaf we've currently + * locked. To solve this situation, we give up + * on our lock and cycle. + */ + btrfs_release_path(path); + cond_resched(); + goto again; + } if (!ret) { btrfs_set_path_blocking(path); btrfs_tree_read_lock(next); @@ -4298,7 +5157,7 @@ again: break; ret = read_block_for_search(NULL, root, path, &next, level, - 0, &key); + 0, &key, 0); if (ret == -EAGAIN) goto again; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3f65a812e28..fa5c45b3907 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -173,6 +173,9 @@ static int btrfs_csum_sizes[] = { 4, 0 }; #define BTRFS_FT_XATTR 8 #define BTRFS_FT_MAX 9 +/* ioprio of readahead is set to idle */ +#define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)) + /* * The key defines the order in the tree, and so it also defines (optimal) * block layout. @@ -823,6 +826,14 @@ struct btrfs_csum_item { u8 csum; } __attribute__ ((__packed__)); +struct btrfs_dev_stats_item { + /* + * grow this item struct at the end for future enhancements and keep + * the existing values unchanged + */ + __le64 values[BTRFS_DEV_STAT_VALUES_MAX]; +} __attribute__ ((__packed__)); + /* different types of block groups (and chunks) */ #define BTRFS_BLOCK_GROUP_DATA (1ULL << 0) #define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1) @@ -1078,7 +1089,7 @@ struct btrfs_fs_info { * is required instead of the faster short fsync log commits */ u64 last_trans_log_full_commit; - unsigned long mount_opt:21; + unsigned long mount_opt; unsigned long compress_type:4; u64 max_inline; u64 alloc_start; @@ -1129,6 +1140,15 @@ struct btrfs_fs_info { spinlock_t delayed_iput_lock; struct list_head delayed_iputs; + /* this protects tree_mod_seq_list */ + spinlock_t tree_mod_seq_lock; + atomic_t tree_mod_seq; + struct list_head tree_mod_seq_list; + + /* this protects tree_mod_log */ + rwlock_t tree_mod_log_lock; + struct rb_root tree_mod_log; + atomic_t nr_async_submits; atomic_t async_submit_draining; atomic_t nr_async_bios; @@ -1375,7 +1395,7 @@ struct btrfs_root { struct list_head root_list; spinlock_t orphan_lock; - struct list_head orphan_list; + atomic_t orphan_inodes; struct btrfs_block_rsv *orphan_block_rsv; int orphan_item_inserted; int orphan_cleanup_state; @@ -1508,6 +1528,12 @@ struct btrfs_ioctl_defrag_range_args { #define BTRFS_BALANCE_ITEM_KEY 248 /* + * Persistantly stores the io stats in the device tree. + * One key for all stats, (0, BTRFS_DEV_STATS_KEY, devid). + */ +#define BTRFS_DEV_STATS_KEY 249 + +/* * string items are for debugging. They just store a short string of * data in the FS */ @@ -2415,6 +2441,30 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, return btrfs_item_size(eb, e) - offset; } +/* btrfs_dev_stats_item */ +static inline u64 btrfs_dev_stats_value(struct extent_buffer *eb, + struct btrfs_dev_stats_item *ptr, + int index) +{ + u64 val; + + read_extent_buffer(eb, &val, + offsetof(struct btrfs_dev_stats_item, values) + + ((unsigned long)ptr) + (index * sizeof(u64)), + sizeof(val)); + return val; +} + +static inline void btrfs_set_dev_stats_value(struct extent_buffer *eb, + struct btrfs_dev_stats_item *ptr, + int index, u64 val) +{ + write_extent_buffer(eb, &val, + offsetof(struct btrfs_dev_stats_item, values) + + ((unsigned long)ptr) + (index * sizeof(u64)), + sizeof(val)); +} + static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb) { return sb->s_fs_info; @@ -2496,11 +2546,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size, int for_cow); + u64 hint, u64 empty_size); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref, int for_cow); + u64 parent, int last_ref); struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u32 blocksize, @@ -2659,6 +2709,8 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans, int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_key *key, struct btrfs_path *p, int ins_len, int cow); +int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key, + struct btrfs_path *p, u64 time_seq); int btrfs_realloc_node(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *parent, int start_slot, int cache_only, u64 *last_ret, @@ -2701,13 +2753,20 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, } int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); -static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path, + u64 time_seq); +static inline int btrfs_next_old_item(struct btrfs_root *root, + struct btrfs_path *p, u64 time_seq) { ++p->slots[0]; if (p->slots[0] >= btrfs_header_nritems(p->nodes[0])) - return btrfs_next_leaf(root, p); + return btrfs_next_old_leaf(root, p, time_seq); return 0; } +static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) +{ + return btrfs_next_old_item(root, p, 0); +} int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); int __must_check btrfs_drop_snapshot(struct btrfs_root *root, @@ -2922,7 +2981,6 @@ int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); int btrfs_dirty_inode(struct inode *inode); -int btrfs_update_time(struct file *file); struct inode *btrfs_alloc_inode(struct super_block *sb); void btrfs_destroy_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); @@ -3098,4 +3156,23 @@ void btrfs_reada_detach(void *handle); int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb, u64 start, int err); +/* delayed seq elem */ +struct seq_list { + struct list_head list; + u64 seq; + u32 flags; +}; + +void btrfs_get_tree_mod_seq(struct btrfs_fs_info *fs_info, + struct seq_list *elem); +void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, + struct seq_list *elem); + +static inline int is_fstree(u64 rootid) +{ + if (rootid == BTRFS_FS_TREE_OBJECTID || + (s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID) + return 1; + return 0; +} #endif diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 03e3748d84d..2399f408691 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -669,8 +669,8 @@ static int btrfs_delayed_inode_reserve_metadata( return ret; } else if (src_rsv == &root->fs_info->delalloc_block_rsv) { spin_lock(&BTRFS_I(inode)->lock); - if (BTRFS_I(inode)->delalloc_meta_reserved) { - BTRFS_I(inode)->delalloc_meta_reserved = 0; + if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED, + &BTRFS_I(inode)->runtime_flags)) { spin_unlock(&BTRFS_I(inode)->lock); release = true; goto migrate; @@ -1706,7 +1706,7 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, btrfs_set_stack_inode_nbytes(inode_item, inode_get_bytes(inode)); btrfs_set_stack_inode_generation(inode_item, BTRFS_I(inode)->generation); - btrfs_set_stack_inode_sequence(inode_item, BTRFS_I(inode)->sequence); + btrfs_set_stack_inode_sequence(inode_item, inode->i_version); btrfs_set_stack_inode_transid(inode_item, trans->transid); btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev); btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags); @@ -1754,7 +1754,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) set_nlink(inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); - BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item); + inode->i_version = btrfs_stack_inode_sequence(inode_item); inode->i_rdev = 0; *rdev = btrfs_stack_inode_rdev(inode_item); BTRFS_I(inode)->flags = btrfs_stack_inode_flags(inode_item); @@ -1879,3 +1879,21 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) } } } + +void btrfs_destroy_delayed_inodes(struct btrfs_root *root) +{ + struct btrfs_delayed_root *delayed_root; + struct btrfs_delayed_node *curr_node, *prev_node; + + delayed_root = btrfs_get_delayed_root(root); + + curr_node = btrfs_first_delayed_node(delayed_root); + while (curr_node) { + __btrfs_kill_delayed_node(curr_node); + + prev_node = curr_node; + curr_node = btrfs_next_delayed_node(curr_node); + btrfs_release_delayed_node(prev_node); + } +} + diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 7083d08b2a2..f5aa4023d3e 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -124,6 +124,9 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev); /* Used for drop dead root */ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root); +/* Used for clean the transaction */ +void btrfs_destroy_delayed_inodes(struct btrfs_root *root); + /* Used for readdir() */ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list, struct list_head *del_list); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 69f22e3ab3b..13ae7b04790 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -525,7 +525,7 @@ static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info, ref->is_head = 0; ref->in_tree = 1; - if (need_ref_seq(for_cow, ref_root)) + if (is_fstree(ref_root)) seq = inc_delayed_seq(delayed_refs); ref->seq = seq; @@ -584,7 +584,7 @@ static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info, ref->is_head = 0; ref->in_tree = 1; - if (need_ref_seq(for_cow, ref_root)) + if (is_fstree(ref_root)) seq = inc_delayed_seq(delayed_refs); ref->seq = seq; @@ -658,10 +658,11 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, level, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && + if (!is_fstree(ref_root) && waitqueue_active(&delayed_refs->seq_wait)) wake_up(&delayed_refs->seq_wait); spin_unlock(&delayed_refs->lock); + return 0; } @@ -706,10 +707,11 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, add_delayed_data_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && + if (!is_fstree(ref_root) && waitqueue_active(&delayed_refs->seq_wait)) wake_up(&delayed_refs->seq_wait); spin_unlock(&delayed_refs->lock); + return 0; } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index d8f244d9492..413927fb995 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -195,11 +195,6 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans, struct list_head *cluster, u64 search_start); -struct seq_list { - struct list_head list; - u64 seq; -}; - static inline u64 inc_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs) { assert_spin_locked(&delayed_refs->lock); @@ -230,25 +225,6 @@ int btrfs_check_delayed_seq(struct btrfs_delayed_ref_root *delayed_refs, u64 seq); /* - * delayed refs with a ref_seq > 0 must be held back during backref walking. - * this only applies to items in one of the fs-trees. for_cow items never need - * to be held back, so they won't get a ref_seq number. - */ -static inline int need_ref_seq(int for_cow, u64 rootid) -{ - if (for_cow) - return 0; - - if (rootid == BTRFS_FS_TREE_OBJECTID) - return 1; - - if ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID) - return 1; - - return 0; -} - -/* * a node might live in a head or a regular ref, this lets you * test for the proper type to use. */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 20196f41120..2936ca49b3b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -44,6 +44,7 @@ #include "free-space-cache.h" #include "inode-map.h" #include "check-integrity.h" +#include "rcu-string.h" static struct extent_io_ops btree_extent_io_ops; static void end_workqueue_fn(struct btrfs_work *work); @@ -323,7 +324,8 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf, * in the wrong place. */ static int verify_parent_transid(struct extent_io_tree *io_tree, - struct extent_buffer *eb, u64 parent_transid) + struct extent_buffer *eb, u64 parent_transid, + int atomic) { struct extent_state *cached_state = NULL; int ret; @@ -331,6 +333,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; + if (atomic) + return -EAGAIN; + lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, 0, &cached_state); if (extent_buffer_uptodate(eb) && @@ -372,7 +377,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, ret = read_extent_buffer_pages(io_tree, eb, start, WAIT_COMPLETE, btree_get_extent, mirror_num); - if (!ret && !verify_parent_transid(io_tree, eb, parent_transid)) + if (!ret && !verify_parent_transid(io_tree, eb, + parent_transid, 0)) break; /* @@ -383,17 +389,16 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) break; - if (!failed_mirror) { - failed = 1; - printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror); - failed_mirror = eb->failed_mirror; - } - num_copies = btrfs_num_copies(&root->fs_info->mapping_tree, eb->start, eb->len); if (num_copies == 1) break; + if (!failed_mirror) { + failed = 1; + failed_mirror = eb->read_mirror; + } + mirror_num++; if (mirror_num == failed_mirror) mirror_num++; @@ -564,7 +569,7 @@ struct extent_buffer *find_eb_for_page(struct extent_io_tree *tree, } static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state) + struct extent_state *state, int mirror) { struct extent_io_tree *tree; u64 found_start; @@ -589,6 +594,7 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end, if (!reads_done) goto err; + eb->read_mirror = mirror; if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) { ret = -EIO; goto err; @@ -652,7 +658,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror) eb = (struct extent_buffer *)page->private; set_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->failed_mirror = failed_mirror; + eb->read_mirror = failed_mirror; if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags)) btree_readahead_hook(root, eb, eb->start, -EIO); return -EIO; /* we fixed nothing */ @@ -1148,7 +1154,6 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, root->orphan_block_rsv = NULL; INIT_LIST_HEAD(&root->dirty_list); - INIT_LIST_HEAD(&root->orphan_list); INIT_LIST_HEAD(&root->root_list); spin_lock_init(&root->orphan_lock); spin_lock_init(&root->inode_lock); @@ -1161,6 +1166,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize, atomic_set(&root->log_commit[0], 0); atomic_set(&root->log_commit[1], 0); atomic_set(&root->log_writers, 0); + atomic_set(&root->orphan_inodes, 0); root->log_batch = 0; root->log_transid = 0; root->last_log_commit = 0; @@ -1202,7 +1208,7 @@ static int __must_check find_and_setup_root(struct btrfs_root *tree_root, root->commit_root = NULL; root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item), blocksize, generation); - if (!root->node || !btrfs_buffer_uptodate(root->node, generation)) { + if (!root->node || !btrfs_buffer_uptodate(root->node, generation, 0)) { free_extent_buffer(root->node); root->node = NULL; return -EIO; @@ -1247,7 +1253,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, BTRFS_TREE_LOG_OBJECTID, NULL, - 0, 0, 0, 0); + 0, 0, 0); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); @@ -1909,11 +1915,14 @@ int open_ctree(struct super_block *sb, spin_lock_init(&fs_info->delayed_iput_lock); spin_lock_init(&fs_info->defrag_inodes_lock); spin_lock_init(&fs_info->free_chunk_lock); + spin_lock_init(&fs_info->tree_mod_seq_lock); + rwlock_init(&fs_info->tree_mod_log_lock); mutex_init(&fs_info->reloc_mutex); init_completion(&fs_info->kobj_unregister); INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots); INIT_LIST_HEAD(&fs_info->space_info); + INIT_LIST_HEAD(&fs_info->tree_mod_seq_list); btrfs_mapping_init(&fs_info->mapping_tree); btrfs_init_block_rsv(&fs_info->global_block_rsv); btrfs_init_block_rsv(&fs_info->delalloc_block_rsv); @@ -1926,12 +1935,14 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->async_submit_draining, 0); atomic_set(&fs_info->nr_async_bios, 0); atomic_set(&fs_info->defrag_running, 0); + atomic_set(&fs_info->tree_mod_seq, 0); fs_info->sb = sb; fs_info->max_inline = 8192 * 1024; fs_info->metadata_ratio = 0; fs_info->defrag_inodes = RB_ROOT; fs_info->trans_no_join = 0; fs_info->free_chunk_space = 0; + fs_info->tree_mod_log = RB_ROOT; /* readahead state */ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); @@ -1996,7 +2007,8 @@ int open_ctree(struct super_block *sb, BTRFS_I(fs_info->btree_inode)->root = tree_root; memset(&BTRFS_I(fs_info->btree_inode)->location, 0, sizeof(struct btrfs_key)); - BTRFS_I(fs_info->btree_inode)->dummy_inode = 1; + set_bit(BTRFS_INODE_DUMMY, + &BTRFS_I(fs_info->btree_inode)->runtime_flags); insert_inode_hash(fs_info->btree_inode); spin_lock_init(&fs_info->block_group_cache_lock); @@ -2107,7 +2119,7 @@ int open_ctree(struct super_block *sb, features = btrfs_super_incompat_flags(disk_super); features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF; - if (tree_root->fs_info->compress_type & BTRFS_COMPRESS_LZO) + if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO) features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO; /* @@ -2254,9 +2266,9 @@ int open_ctree(struct super_block *sb, goto fail_sb_buffer; } - if (sectorsize < PAGE_SIZE) { - printk(KERN_WARNING "btrfs: Incompatible sector size " - "found on %s\n", sb->s_id); + if (sectorsize != PAGE_SIZE) { + printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) " + "found on %s\n", (unsigned long)sectorsize, sb->s_id); goto fail_sb_buffer; } @@ -2342,12 +2354,24 @@ retry_root_backup: BTRFS_CSUM_TREE_OBJECTID, csum_root); if (ret) goto recovery_tree_root; - csum_root->track_dirty = 1; fs_info->generation = generation; fs_info->last_trans_committed = generation; + ret = btrfs_recover_balance(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to recover balance\n"); + goto fail_block_groups; + } + + ret = btrfs_init_dev_stats(fs_info); + if (ret) { + printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n", + ret); + goto fail_block_groups; + } + ret = btrfs_init_space_info(fs_info); if (ret) { printk(KERN_ERR "Failed to initial space info: %d\n", ret); @@ -2466,20 +2490,23 @@ retry_root_backup: goto fail_trans_kthread; } - if (!(sb->s_flags & MS_RDONLY)) { - down_read(&fs_info->cleanup_work_sem); - err = btrfs_orphan_cleanup(fs_info->fs_root); - if (!err) - err = btrfs_orphan_cleanup(fs_info->tree_root); - up_read(&fs_info->cleanup_work_sem); + if (sb->s_flags & MS_RDONLY) + return 0; - if (!err) - err = btrfs_recover_balance(fs_info->tree_root); + down_read(&fs_info->cleanup_work_sem); + if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) || + (ret = btrfs_orphan_cleanup(fs_info->tree_root))) { + up_read(&fs_info->cleanup_work_sem); + close_ctree(tree_root); + return ret; + } + up_read(&fs_info->cleanup_work_sem); - if (err) { - close_ctree(tree_root); - return err; - } + ret = btrfs_resume_balance_async(fs_info); + if (ret) { + printk(KERN_WARNING "btrfs: failed to resume balance\n"); + close_ctree(tree_root); + return ret; } return 0; @@ -2551,18 +2578,20 @@ recovery_tree_root: static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) { - char b[BDEVNAME_SIZE]; - if (uptodate) { set_buffer_uptodate(bh); } else { - printk_ratelimited(KERN_WARNING "lost page write due to " - "I/O error on %s\n", - bdevname(bh->b_bdev, b)); + struct btrfs_device *device = (struct btrfs_device *) + bh->b_private; + + printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to " + "I/O error on %s\n", + rcu_str_deref(device->name)); /* note, we dont' set_buffer_write_io_error because we have * our own ways of dealing with the IO errors */ clear_buffer_uptodate(bh); + btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_WRITE_ERRS); } unlock_buffer(bh); put_bh(bh); @@ -2677,6 +2706,7 @@ static int write_dev_supers(struct btrfs_device *device, set_buffer_uptodate(bh); lock_buffer(bh); bh->b_end_io = btrfs_end_buffer_write_sync; + bh->b_private = device; } /* @@ -2729,12 +2759,15 @@ static int write_dev_flush(struct btrfs_device *device, int wait) wait_for_completion(&device->flush_wait); if (bio_flagged(bio, BIO_EOPNOTSUPP)) { - printk("btrfs: disabling barriers on dev %s\n", - device->name); + printk_in_rcu("btrfs: disabling barriers on dev %s\n", + rcu_str_deref(device->name)); device->nobarriers = 1; } if (!bio_flagged(bio, BIO_UPTODATE)) { ret = -EIO; + if (!bio_flagged(bio, BIO_EOPNOTSUPP)) + btrfs_dev_stat_inc_and_print(device, + BTRFS_DEV_STAT_FLUSH_ERRS); } /* drop the reference from the wait == 0 run */ @@ -2748,7 +2781,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) * one reference for us, and we leave it for the * caller */ - device->flush_bio = NULL;; + device->flush_bio = NULL; bio = bio_alloc(GFP_NOFS, 0); if (!bio) return -ENOMEM; @@ -2897,19 +2930,6 @@ int write_ctree_super(struct btrfs_trans_handle *trans, return ret; } -/* Kill all outstanding I/O */ -void btrfs_abort_devices(struct btrfs_root *root) -{ - struct list_head *head; - struct btrfs_device *dev; - mutex_lock(&root->fs_info->fs_devices->device_list_mutex); - head = &root->fs_info->fs_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - blk_abort_queue(dev->bdev->bd_disk->queue); - } - mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); -} - void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root) { spin_lock(&fs_info->fs_roots_radix_lock); @@ -3143,7 +3163,8 @@ int close_ctree(struct btrfs_root *root) return 0; } -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, + int atomic) { int ret; struct inode *btree_inode = buf->pages[0]->mapping->host; @@ -3153,7 +3174,9 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid) return ret; ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf, - parent_transid); + parent_transid, atomic); + if (ret == -EAGAIN) + return ret; return !ret; } @@ -3387,7 +3410,6 @@ int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, delayed_refs = &trans->delayed_refs; -again: spin_lock(&delayed_refs->lock); if (delayed_refs->num_entries == 0) { spin_unlock(&delayed_refs->lock); @@ -3395,31 +3417,37 @@ again: return ret; } - node = rb_first(&delayed_refs->root); - while (node) { + while ((node = rb_first(&delayed_refs->root)) != NULL) { ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node); - node = rb_next(node); - - ref->in_tree = 0; - rb_erase(&ref->rb_node, &delayed_refs->root); - delayed_refs->num_entries--; atomic_set(&ref->refs, 1); if (btrfs_delayed_ref_is_head(ref)) { struct btrfs_delayed_ref_head *head; head = btrfs_delayed_node_to_head(ref); - spin_unlock(&delayed_refs->lock); - mutex_lock(&head->mutex); + if (!mutex_trylock(&head->mutex)) { + atomic_inc(&ref->refs); + spin_unlock(&delayed_refs->lock); + + /* Need to wait for the delayed ref to run */ + mutex_lock(&head->mutex); + mutex_unlock(&head->mutex); + btrfs_put_delayed_ref(ref); + + spin_lock(&delayed_refs->lock); + continue; + } + kfree(head->extent_op); delayed_refs->num_heads--; if (list_empty(&head->cluster)) delayed_refs->num_heads_ready--; list_del_init(&head->cluster); - mutex_unlock(&head->mutex); - btrfs_put_delayed_ref(ref); - goto again; } + ref->in_tree = 0; + rb_erase(&ref->rb_node, &delayed_refs->root); + delayed_refs->num_entries--; + spin_unlock(&delayed_refs->lock); btrfs_put_delayed_ref(ref); @@ -3507,11 +3535,9 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, &(&BTRFS_I(page->mapping->host)->io_tree)->buffer, offset >> PAGE_CACHE_SHIFT); spin_unlock(&dirty_pages->buffer_lock); - if (eb) { + if (eb) ret = test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); - atomic_set(&eb->refs, 1); - } if (PageWriteback(page)) end_page_writeback(page); @@ -3525,8 +3551,8 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, spin_unlock_irq(&page->mapping->tree_lock); } - page->mapping->a_ops->invalidatepage(page, 0); unlock_page(page); + page_cache_release(page); } } @@ -3540,8 +3566,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, u64 start; u64 end; int ret; + bool loop = true; unpin = pinned_extents; +again: while (1) { ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY); @@ -3559,6 +3587,15 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, cond_resched(); } + if (loop) { + if (unpin == &root->fs_info->freed_extents[0]) + unpin = &root->fs_info->freed_extents[1]; + else + unpin = &root->fs_info->freed_extents[0]; + loop = false; + goto again; + } + return 0; } @@ -3572,21 +3609,23 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, /* FIXME: cleanup wait for commit */ cur_trans->in_commit = 1; cur_trans->blocked = 1; - if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) - wake_up(&root->fs_info->transaction_blocked_wait); + wake_up(&root->fs_info->transaction_blocked_wait); cur_trans->blocked = 0; - if (waitqueue_active(&root->fs_info->transaction_wait)) - wake_up(&root->fs_info->transaction_wait); + wake_up(&root->fs_info->transaction_wait); cur_trans->commit_done = 1; - if (waitqueue_active(&cur_trans->commit_wait)) - wake_up(&cur_trans->commit_wait); + wake_up(&cur_trans->commit_wait); + + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); btrfs_destroy_pending_snapshots(cur_trans); btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages, EXTENT_DIRTY); + btrfs_destroy_pinned_extent(root, + root->fs_info->pinned_extents); /* memset(cur_trans, 0, sizeof(*cur_trans)); @@ -3635,6 +3674,9 @@ int btrfs_cleanup_transaction(struct btrfs_root *root) if (waitqueue_active(&t->commit_wait)) wake_up(&t->commit_wait); + btrfs_destroy_delayed_inodes(root); + btrfs_assert_delayed_root_empty(root); + btrfs_destroy_pending_snapshots(t); btrfs_destroy_delalloc_inodes(root); @@ -3663,17 +3705,6 @@ int btrfs_cleanup_transaction(struct btrfs_root *root) return 0; } -static int btree_writepage_io_failed_hook(struct bio *bio, struct page *page, - u64 start, u64 end, - struct extent_state *state) -{ - struct super_block *sb = page->mapping->host->i_sb; - struct btrfs_fs_info *fs_info = btrfs_sb(sb); - btrfs_error(fs_info, -EIO, - "Error occured while writing out btree at %llu", start); - return -EIO; -} - static struct extent_io_ops btree_extent_io_ops = { .write_cache_pages_lock_hook = btree_lock_page_hook, .readpage_end_io_hook = btree_readpage_end_io_hook, @@ -3681,5 +3712,4 @@ static struct extent_io_ops btree_extent_io_ops = { .submit_bio_hook = btree_submit_bio_hook, /* note we're sharing with inode.c for the merge bio hook */ .merge_bio_hook = btrfs_merge_bio_hook, - .writepage_io_failed_hook = btree_writepage_io_failed_hook, }; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index a7ace1a2dd1..05b3fab39f7 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -66,7 +66,8 @@ void btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr); void __btrfs_btree_balance_dirty(struct btrfs_root *root, unsigned long nr); void btrfs_free_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_mark_buffer_dirty(struct extent_buffer *buf); -int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid); +int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid, + int atomic); int btrfs_set_buffer_uptodate(struct extent_buffer *buf); int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); u32 btrfs_csum_data(struct btrfs_root *root, char *data, u32 seed, size_t len); @@ -88,7 +89,6 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans, int btrfs_cleanup_transaction(struct btrfs_root *root); void btrfs_cleanup_one_transaction(struct btrfs_transaction *trans, struct btrfs_root *root); -void btrfs_abort_devices(struct btrfs_root *root); #ifdef CONFIG_DEBUG_LOCK_ALLOC void btrfs_init_lockdep(void); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index e887ee62b6d..614f34a899c 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -13,15 +13,14 @@ parent_root_objectid) / 4) #define BTRFS_FID_SIZE_CONNECTABLE_ROOT (sizeof(struct btrfs_fid) / 4) -static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, - int connectable) +static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, + struct inode *parent) { struct btrfs_fid *fid = (struct btrfs_fid *)fh; - struct inode *inode = dentry->d_inode; int len = *max_len; int type; - if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) { + if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) { *max_len = BTRFS_FID_SIZE_CONNECTABLE; return 255; } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) { @@ -36,19 +35,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, fid->root_objectid = BTRFS_I(inode)->root->objectid; fid->gen = inode->i_generation; - if (connectable && !S_ISDIR(inode->i_mode)) { - struct inode *parent; + if (parent) { u64 parent_root_id; - spin_lock(&dentry->d_lock); - - parent = dentry->d_parent->d_inode; fid->parent_objectid = BTRFS_I(parent)->location.objectid; fid->parent_gen = parent->i_generation; parent_root_id = BTRFS_I(parent)->root->objectid; - spin_unlock(&dentry->d_lock); - if (parent_root_id != fid->root_objectid) { fid->parent_root_objectid = parent_root_id; len = BTRFS_FID_SIZE_CONNECTABLE_ROOT; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2b35f8d14bb..6e1d36702ff 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2301,6 +2301,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, if (ret) { printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret); + spin_lock(&delayed_refs->lock); return ret; } @@ -2331,6 +2332,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, if (ret) { printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret); + spin_lock(&delayed_refs->lock); return ret; } @@ -2345,12 +2347,10 @@ next: return count; } - static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs) + unsigned long num_refs, + struct list_head *first_seq) { - struct list_head *first_seq = delayed_refs->seq_head.next; - spin_unlock(&delayed_refs->lock); pr_debug("waiting for more refs (num %ld, first %p)\n", num_refs, first_seq); @@ -2379,6 +2379,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; + struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; @@ -2434,8 +2435,10 @@ again: */ consider_waiting = 1; num_refs = delayed_refs->num_entries; + first_seq = root->fs_info->tree_mod_seq_list.next; } else { - wait_for_more_refs(delayed_refs, num_refs); + wait_for_more_refs(delayed_refs, + num_refs, first_seq); /* * after waiting, things have changed. we * dropped the lock and someone else might have @@ -3576,7 +3579,7 @@ again: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); out: - mutex_unlock(&extent_root->fs_info->chunk_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } @@ -3769,13 +3772,10 @@ again: */ if (current->journal_info) return -EAGAIN; - ret = wait_event_interruptible(space_info->wait, - !space_info->flush); - /* Must have been interrupted, return */ - if (ret) { - printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__); + ret = wait_event_killable(space_info->wait, !space_info->flush); + /* Must have been killed, return */ + if (ret) return -EINTR; - } spin_lock(&space_info->lock); } @@ -4215,8 +4215,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) num_bytes = calc_global_metadata_size(fs_info); - spin_lock(&block_rsv->lock); spin_lock(&sinfo->lock); + spin_lock(&block_rsv->lock); block_rsv->size = num_bytes; @@ -4242,8 +4242,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) block_rsv->full = 1; } - spin_unlock(&sinfo->lock); spin_unlock(&block_rsv->lock); + spin_unlock(&sinfo->lock); } static void init_global_block_rsv(struct btrfs_fs_info *fs_info) @@ -4356,10 +4356,9 @@ static unsigned drop_outstanding_extent(struct inode *inode) BTRFS_I(inode)->outstanding_extents--; if (BTRFS_I(inode)->outstanding_extents == 0 && - BTRFS_I(inode)->delalloc_meta_reserved) { + test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED, + &BTRFS_I(inode)->runtime_flags)) drop_inode_space = 1; - BTRFS_I(inode)->delalloc_meta_reserved = 0; - } /* * If we have more or the same amount of outsanding extents than we have @@ -4466,7 +4465,8 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) * Add an item to reserve for updating the inode when we complete the * delalloc io. */ - if (!BTRFS_I(inode)->delalloc_meta_reserved) { + if (!test_bit(BTRFS_INODE_DELALLOC_META_RESERVED, + &BTRFS_I(inode)->runtime_flags)) { nr_extents++; extra_reserve = 1; } @@ -4512,7 +4512,8 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) spin_lock(&BTRFS_I(inode)->lock); if (extra_reserve) { - BTRFS_I(inode)->delalloc_meta_reserved = 1; + set_bit(BTRFS_INODE_DELALLOC_META_RESERVED, + &BTRFS_I(inode)->runtime_flags); nr_extents--; } BTRFS_I(inode)->reserved_extents += nr_extents; @@ -5218,7 +5219,7 @@ out: void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref, int for_cow) + u64 parent, int last_ref) { struct btrfs_block_group_cache *cache = NULL; int ret; @@ -5228,7 +5229,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, buf->start, buf->len, parent, root->root_key.objectid, btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL, for_cow); + BTRFS_DROP_DELAYED_REF, NULL, 0); BUG_ON(ret); /* -ENOMEM */ } @@ -6250,7 +6251,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size, int for_cow) + u64 hint, u64 empty_size) { struct btrfs_key ins; struct btrfs_block_rsv *block_rsv; @@ -6298,7 +6299,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, ins.objectid, ins.offset, parent, root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op, for_cow); + extent_op, 0); BUG_ON(ret); /* -ENOMEM */ } return buf; @@ -6569,7 +6570,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, goto skip; } - if (!btrfs_buffer_uptodate(next, generation)) { + if (!btrfs_buffer_uptodate(next, generation, 0)) { btrfs_tree_unlock(next); free_extent_buffer(next); next = NULL; @@ -6716,7 +6717,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, btrfs_header_owner(path->nodes[level + 1])); } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1, 0); + btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); out: wc->refs[level] = 0; wc->flags[level] = 0; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cd4b5e40022..01c21b6c6d4 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -20,6 +20,7 @@ #include "volumes.h" #include "check-integrity.h" #include "locking.h" +#include "rcu-string.h" static struct kmem_cache *extent_state_cache; static struct kmem_cache *extent_buffer_cache; @@ -186,7 +187,6 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 offset, return parent; } - entry = rb_entry(node, struct tree_entry, rb_node); rb_link_node(node, parent, p); rb_insert_color(node, root); return NULL; @@ -402,20 +402,28 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig, return 0; } +static struct extent_state *next_state(struct extent_state *state) +{ + struct rb_node *next = rb_next(&state->rb_node); + if (next) + return rb_entry(next, struct extent_state, rb_node); + else + return NULL; +} + /* * utility function to clear some bits in an extent state struct. - * it will optionally wake up any one waiting on this state (wake == 1), or - * forcibly remove the state from the tree (delete == 1). + * it will optionally wake up any one waiting on this state (wake == 1). * * If no bits are set on the state struct after clearing things, the * struct is freed and removed from the tree */ -static int clear_state_bit(struct extent_io_tree *tree, - struct extent_state *state, - int *bits, int wake) +static struct extent_state *clear_state_bit(struct extent_io_tree *tree, + struct extent_state *state, + int *bits, int wake) { + struct extent_state *next; int bits_to_clear = *bits & ~EXTENT_CTLBITS; - int ret = state->state & bits_to_clear; if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) { u64 range = state->end - state->start + 1; @@ -427,6 +435,7 @@ static int clear_state_bit(struct extent_io_tree *tree, if (wake) wake_up(&state->wq); if (state->state == 0) { + next = next_state(state); if (state->tree) { rb_erase(&state->rb_node, &tree->state); state->tree = NULL; @@ -436,8 +445,9 @@ static int clear_state_bit(struct extent_io_tree *tree, } } else { merge_state(tree, state); + next = next_state(state); } - return ret; + return next; } static struct extent_state * @@ -476,7 +486,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state *state; struct extent_state *cached; struct extent_state *prealloc = NULL; - struct rb_node *next_node; struct rb_node *node; u64 last_end; int err; @@ -528,14 +537,11 @@ hit_next: WARN_ON(state->end < start); last_end = state->end; - if (state->end < end && !need_resched()) - next_node = rb_next(&state->rb_node); - else - next_node = NULL; - /* the state doesn't have the wanted bits, go ahead */ - if (!(state->state & bits)) + if (!(state->state & bits)) { + state = next_state(state); goto next; + } /* * | ---- desired range ---- | @@ -564,10 +570,8 @@ hit_next: if (err) goto out; if (state->end <= end) { - clear_state_bit(tree, state, &bits, wake); - if (last_end == (u64)-1) - goto out; - start = last_end + 1; + state = clear_state_bit(tree, state, &bits, wake); + goto next; } goto search_again; } @@ -593,16 +597,13 @@ hit_next: goto out; } - clear_state_bit(tree, state, &bits, wake); + state = clear_state_bit(tree, state, &bits, wake); next: if (last_end == (u64)-1) goto out; start = last_end + 1; - if (start <= end && next_node) { - state = rb_entry(next_node, struct extent_state, - rb_node); + if (start <= end && state && !need_resched()) goto hit_next; - } goto search_again; out: @@ -778,7 +779,6 @@ hit_next: * Just lock what we found and keep going */ if (state->start == start && state->end <= end) { - struct rb_node *next_node; if (state->state & exclusive_bits) { *failed_start = state->start; err = -EEXIST; @@ -786,20 +786,15 @@ hit_next: } set_state_bits(tree, state, &bits); - cache_state(state, cached_state); merge_state(tree, state); if (last_end == (u64)-1) goto out; - start = last_end + 1; - next_node = rb_next(&state->rb_node); - if (next_node && start < end && prealloc && !need_resched()) { - state = rb_entry(next_node, struct extent_state, - rb_node); - if (state->start == start) - goto hit_next; - } + state = next_state(state); + if (start < end && state && state->start == start && + !need_resched()) + goto hit_next; goto search_again; } @@ -842,6 +837,10 @@ hit_next: if (last_end == (u64)-1) goto out; start = last_end + 1; + state = next_state(state); + if (start < end && state && state->start == start && + !need_resched()) + goto hit_next; } goto search_again; } @@ -991,21 +990,14 @@ hit_next: * Just lock what we found and keep going */ if (state->start == start && state->end <= end) { - struct rb_node *next_node; - set_state_bits(tree, state, &bits); - clear_state_bit(tree, state, &clear_bits, 0); + state = clear_state_bit(tree, state, &clear_bits, 0); if (last_end == (u64)-1) goto out; - start = last_end + 1; - next_node = rb_next(&state->rb_node); - if (next_node && start < end && prealloc && !need_resched()) { - state = rb_entry(next_node, struct extent_state, - rb_node); - if (state->start == start) - goto hit_next; - } + if (start < end && state && state->start == start && + !need_resched()) + goto hit_next; goto search_again; } @@ -1039,10 +1031,13 @@ hit_next: goto out; if (state->end <= end) { set_state_bits(tree, state, &bits); - clear_state_bit(tree, state, &clear_bits, 0); + state = clear_state_bit(tree, state, &clear_bits, 0); if (last_end == (u64)-1) goto out; start = last_end + 1; + if (start < end && state && state->start == start && + !need_resched()) + goto hit_next; } goto search_again; } @@ -1170,9 +1165,8 @@ int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, cached_state, mask); } -static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, - u64 end, struct extent_state **cached_state, - gfp_t mask) +int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, + struct extent_state **cached_state, gfp_t mask) { return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0, cached_state, mask); @@ -1290,7 +1284,7 @@ out: * returned if we find something, and *start_ret and *end_ret are * set to reflect the state struct that was found. * - * If nothing was found, 1 is returned, < 0 on error + * If nothing was found, 1 is returned. If found something, return 0. */ int find_first_extent_bit(struct extent_io_tree *tree, u64 start, u64 *start_ret, u64 *end_ret, int bits) @@ -1920,12 +1914,13 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start, if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { /* try to remap that extent elsewhere? */ bio_put(bio); + btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS); return -EIO; } - printk(KERN_INFO "btrfs read error corrected: ino %lu off %llu (dev %s " - "sector %llu)\n", page->mapping->host->i_ino, start, - dev->name, sector); + printk_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu " + "(dev %s sector %llu)\n", page->mapping->host->i_ino, + start, rcu_str_deref(dev->name), sector); bio_put(bio); return 0; @@ -2219,17 +2214,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) uptodate = 0; } - if (!uptodate && tree->ops && - tree->ops->writepage_io_failed_hook) { - ret = tree->ops->writepage_io_failed_hook(NULL, page, - start, end, NULL); - /* Writeback already completed */ - if (ret == 0) - return 1; - } - if (!uptodate) { - clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS); ClearPageUptodate(page); SetPageError(page); } @@ -2301,7 +2286,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) u64 start; u64 end; int whole_page; - int failed_mirror; + int mirror; int ret; if (err) @@ -2340,20 +2325,31 @@ static void end_bio_extent_readpage(struct bio *bio, int err) } spin_unlock(&tree->lock); + mirror = (int)(unsigned long)bio->bi_bdev; if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, - state); - if (ret) + state, mirror); + if (ret) { + /* no IO indicated but software detected errors + * in the block, either checksum errors or + * issues with the contents */ + struct btrfs_root *root = + BTRFS_I(page->mapping->host)->root; + struct btrfs_device *device; + uptodate = 0; - else + device = btrfs_find_device_for_logical( + root, start, mirror); + if (device) + btrfs_dev_stat_inc_and_print(device, + BTRFS_DEV_STAT_CORRUPTION_ERRS); + } else { clean_io_failure(start, page); + } } - if (!uptodate) - failed_mirror = (int)(unsigned long)bio->bi_bdev; - if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { - ret = tree->ops->readpage_io_failed_hook(page, failed_mirror); + ret = tree->ops->readpage_io_failed_hook(page, mirror); if (!ret && !err && test_bit(BIO_UPTODATE, &bio->bi_flags)) uptodate = 1; @@ -2368,8 +2364,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) * can't handle the error it will return -EIO and we * remain responsible for that page. */ - ret = bio_readpage_error(bio, page, start, end, - failed_mirror, NULL); + ret = bio_readpage_error(bio, page, start, end, mirror, NULL); if (ret == 0) { uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); @@ -3164,7 +3159,7 @@ static int write_one_eb(struct extent_buffer *eb, u64 offset = eb->start; unsigned long i, num_pages; int rw = (epd->sync_io ? WRITE_SYNC : WRITE); - int ret; + int ret = 0; clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags); num_pages = num_extent_pages(eb->start, eb->len); @@ -3329,6 +3324,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, writepage_t writepage, void *data, void (*flush_fn)(void *)) { + struct inode *inode = mapping->host; int ret = 0; int done = 0; int nr_to_write_done = 0; @@ -3339,6 +3335,18 @@ static int extent_write_cache_pages(struct extent_io_tree *tree, int scanned = 0; int tag; + /* + * We have to hold onto the inode so that ordered extents can do their + * work when the IO finishes. The alternative to this is failing to add + * an ordered extent if the igrab() fails there and that is a huge pain + * to deal with, so instead just hold onto the inode throughout the + * writepages operation. If it fails here we are freeing up the inode + * anyway and we'd rather not waste our time writing out stuff that is + * going to be truncated anyway. + */ + if (!igrab(inode)) + return 0; + pagevec_init(&pvec, 0); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ @@ -3433,6 +3441,7 @@ retry: index = 0; goto retry; } + btrfs_add_delayed_iput(inode); return ret; } @@ -3930,6 +3939,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree, eb->start = start; eb->len = len; eb->tree = tree; + eb->bflags = 0; rwlock_init(&eb->lock); atomic_set(&eb->write_locks, 0); atomic_set(&eb->read_locks, 0); @@ -3967,6 +3977,60 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree, return eb; } +struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src) +{ + unsigned long i; + struct page *p; + struct extent_buffer *new; + unsigned long num_pages = num_extent_pages(src->start, src->len); + + new = __alloc_extent_buffer(NULL, src->start, src->len, GFP_ATOMIC); + if (new == NULL) + return NULL; + + for (i = 0; i < num_pages; i++) { + p = alloc_page(GFP_ATOMIC); + BUG_ON(!p); + attach_extent_buffer_page(new, p); + WARN_ON(PageDirty(p)); + SetPageUptodate(p); + new->pages[i] = p; + } + + copy_extent_buffer(new, src, 0, 0, src->len); + set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags); + set_bit(EXTENT_BUFFER_DUMMY, &new->bflags); + + return new; +} + +struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len) +{ + struct extent_buffer *eb; + unsigned long num_pages = num_extent_pages(0, len); + unsigned long i; + + eb = __alloc_extent_buffer(NULL, start, len, GFP_ATOMIC); + if (!eb) + return NULL; + + for (i = 0; i < num_pages; i++) { + eb->pages[i] = alloc_page(GFP_ATOMIC); + if (!eb->pages[i]) + goto err; + } + set_extent_buffer_uptodate(eb); + btrfs_set_header_nritems(eb, 0); + set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); + + return eb; +err: + for (i--; i > 0; i--) + __free_page(eb->pages[i]); + __free_extent_buffer(eb); + return NULL; +} + static int extent_buffer_under_io(struct extent_buffer *eb) { return (atomic_read(&eb->io_pages) || @@ -3981,18 +4045,21 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, unsigned long start_idx) { unsigned long index; + unsigned long num_pages; struct page *page; + int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags); BUG_ON(extent_buffer_under_io(eb)); - index = num_extent_pages(eb->start, eb->len); + num_pages = num_extent_pages(eb->start, eb->len); + index = start_idx + num_pages; if (start_idx >= index) return; do { index--; page = extent_buffer_page(eb, index); - if (page) { + if (page && mapped) { spin_lock(&page->mapping->private_lock); /* * We do this since we'll remove the pages after we've @@ -4017,6 +4084,8 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb, } spin_unlock(&page->mapping->private_lock); + } + if (page) { /* One for when we alloced the page */ page_cache_release(page); } @@ -4120,6 +4189,7 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, if (atomic_inc_not_zero(&exists->refs)) { spin_unlock(&mapping->private_lock); unlock_page(p); + page_cache_release(p); mark_extent_buffer_accessed(exists); goto free_eb; } @@ -4199,8 +4269,7 @@ free_eb: unlock_page(eb->pages[i]); } - if (!atomic_dec_and_test(&eb->refs)) - return exists; + WARN_ON(!atomic_dec_and_test(&eb->refs)); btrfs_release_extent_buffer(eb); return exists; } @@ -4235,14 +4304,18 @@ static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask) { WARN_ON(atomic_read(&eb->refs) == 0); if (atomic_dec_and_test(&eb->refs)) { - struct extent_io_tree *tree = eb->tree; + if (test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) { + spin_unlock(&eb->refs_lock); + } else { + struct extent_io_tree *tree = eb->tree; - spin_unlock(&eb->refs_lock); + spin_unlock(&eb->refs_lock); - spin_lock(&tree->buffer_lock); - radix_tree_delete(&tree->buffer, - eb->start >> PAGE_CACHE_SHIFT); - spin_unlock(&tree->buffer_lock); + spin_lock(&tree->buffer_lock); + radix_tree_delete(&tree->buffer, + eb->start >> PAGE_CACHE_SHIFT); + spin_unlock(&tree->buffer_lock); + } /* Should be safe to release our pages at this point */ btrfs_release_extent_buffer_page(eb, 0); @@ -4260,6 +4333,10 @@ void free_extent_buffer(struct extent_buffer *eb) spin_lock(&eb->refs_lock); if (atomic_read(&eb->refs) == 2 && + test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) + atomic_dec(&eb->refs); + + if (atomic_read(&eb->refs) == 2 && test_bit(EXTENT_BUFFER_STALE, &eb->bflags) && !extent_buffer_under_io(eb) && test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) @@ -4462,7 +4539,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree, } clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags); - eb->failed_mirror = 0; + eb->read_mirror = 0; atomic_set(&eb->io_pages, num_reads); for (i = start_i; i < num_pages; i++) { page = extent_buffer_page(eb, i); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index faf10eb57f7..25900af5b15 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -39,6 +39,7 @@ #define EXTENT_BUFFER_STALE 6 #define EXTENT_BUFFER_WRITEBACK 7 #define EXTENT_BUFFER_IOERR 8 +#define EXTENT_BUFFER_DUMMY 9 /* these are flags for extent_clear_unlock_delalloc */ #define EXTENT_CLEAR_UNLOCK_PAGE 0x1 @@ -75,11 +76,8 @@ struct extent_io_ops { unsigned long bio_flags); int (*readpage_io_hook)(struct page *page, u64 start, u64 end); int (*readpage_io_failed_hook)(struct page *page, int failed_mirror); - int (*writepage_io_failed_hook)(struct bio *bio, struct page *page, - u64 start, u64 end, - struct extent_state *state); int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end, - struct extent_state *state); + struct extent_state *state, int mirror); int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate); void (*set_bit_hook)(struct inode *inode, struct extent_state *state, @@ -135,7 +133,7 @@ struct extent_buffer { spinlock_t refs_lock; atomic_t refs; atomic_t io_pages; - int failed_mirror; + int read_mirror; struct list_head leak_list; struct rcu_head rcu_head; pid_t lock_owner; @@ -225,6 +223,8 @@ int set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached_state, gfp_t mask); +int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end, + struct extent_state **cached_state, gfp_t mask); int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask); int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, @@ -265,6 +265,8 @@ void set_page_extent_mapped(struct page *page); struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree, u64 start, unsigned long len); +struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len); +struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src); struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree, u64 start, unsigned long len); void free_extent_buffer(struct extent_buffer *eb); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index d83260d7498..9aa01ec2138 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -65,6 +65,21 @@ struct inode_defrag { int cycled; }; +static int __compare_inode_defrag(struct inode_defrag *defrag1, + struct inode_defrag *defrag2) +{ + if (defrag1->root > defrag2->root) + return 1; + else if (defrag1->root < defrag2->root) + return -1; + else if (defrag1->ino > defrag2->ino) + return 1; + else if (defrag1->ino < defrag2->ino) + return -1; + else + return 0; +} + /* pop a record for an inode into the defrag tree. The lock * must be held already * @@ -81,15 +96,17 @@ static void __btrfs_add_inode_defrag(struct inode *inode, struct inode_defrag *entry; struct rb_node **p; struct rb_node *parent = NULL; + int ret; p = &root->fs_info->defrag_inodes.rb_node; while (*p) { parent = *p; entry = rb_entry(parent, struct inode_defrag, rb_node); - if (defrag->ino < entry->ino) + ret = __compare_inode_defrag(defrag, entry); + if (ret < 0) p = &parent->rb_left; - else if (defrag->ino > entry->ino) + else if (ret > 0) p = &parent->rb_right; else { /* if we're reinserting an entry for @@ -103,7 +120,7 @@ static void __btrfs_add_inode_defrag(struct inode *inode, goto exists; } } - BTRFS_I(inode)->in_defrag = 1; + set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); rb_link_node(&defrag->rb_node, parent, p); rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes); return; @@ -131,7 +148,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, if (btrfs_fs_closing(root->fs_info)) return 0; - if (BTRFS_I(inode)->in_defrag) + if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) return 0; if (trans) @@ -148,7 +165,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, defrag->root = root->root_key.objectid; spin_lock(&root->fs_info->defrag_inodes_lock); - if (!BTRFS_I(inode)->in_defrag) + if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) __btrfs_add_inode_defrag(inode, defrag); else kfree(defrag); @@ -159,28 +176,35 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, /* * must be called with the defrag_inodes lock held */ -struct inode_defrag *btrfs_find_defrag_inode(struct btrfs_fs_info *info, u64 ino, +struct inode_defrag *btrfs_find_defrag_inode(struct btrfs_fs_info *info, + u64 root, u64 ino, struct rb_node **next) { struct inode_defrag *entry = NULL; + struct inode_defrag tmp; struct rb_node *p; struct rb_node *parent = NULL; + int ret; + + tmp.ino = ino; + tmp.root = root; p = info->defrag_inodes.rb_node; while (p) { parent = p; entry = rb_entry(parent, struct inode_defrag, rb_node); - if (ino < entry->ino) + ret = __compare_inode_defrag(&tmp, entry); + if (ret < 0) p = parent->rb_left; - else if (ino > entry->ino) + else if (ret > 0) p = parent->rb_right; else return entry; } if (next) { - while (parent && ino > entry->ino) { + while (parent && __compare_inode_defrag(&tmp, entry) > 0) { parent = rb_next(parent); entry = rb_entry(parent, struct inode_defrag, rb_node); } @@ -202,6 +226,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) struct btrfs_key key; struct btrfs_ioctl_defrag_range_args range; u64 first_ino = 0; + u64 root_objectid = 0; int num_defrag; int defrag_batch = 1024; @@ -214,11 +239,14 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) n = NULL; /* find an inode to defrag */ - defrag = btrfs_find_defrag_inode(fs_info, first_ino, &n); + defrag = btrfs_find_defrag_inode(fs_info, root_objectid, + first_ino, &n); if (!defrag) { - if (n) - defrag = rb_entry(n, struct inode_defrag, rb_node); - else if (first_ino) { + if (n) { + defrag = rb_entry(n, struct inode_defrag, + rb_node); + } else if (root_objectid || first_ino) { + root_objectid = 0; first_ino = 0; continue; } else { @@ -228,6 +256,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) /* remove it from the rbtree */ first_ino = defrag->ino + 1; + root_objectid = defrag->root; rb_erase(&defrag->rb_node, &fs_info->defrag_inodes); if (btrfs_fs_closing(fs_info)) @@ -252,7 +281,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info) goto next; /* do a chunk of defrag */ - BTRFS_I(inode)->in_defrag = 0; + clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); range.start = defrag->last_offset; num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid, defrag_batch); @@ -567,6 +596,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode, int extent_type; int recow; int ret; + int modify_tree = -1; if (drop_cache) btrfs_drop_extent_cache(inode, start, end - 1, 0); @@ -575,10 +605,13 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans, struct inode *inode, if (!path) return -ENOMEM; + if (start >= BTRFS_I(inode)->disk_i_size) + modify_tree = 0; + while (1) { recow = 0; ret = btrfs_lookup_file_extent(trans, root, path, ino, - search_start, -1); + search_start, modify_tree); if (ret < 0) break; if (ret > 0 && path->slots[0] > 0 && search_start == start) { @@ -634,7 +667,8 @@ next_slot: } search_start = max(key.offset, start); - if (recow) { + if (recow || !modify_tree) { + modify_tree = -1; btrfs_release_path(path); continue; } @@ -1300,7 +1334,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t *ppos, size_t count, size_t ocount) { struct file *file = iocb->ki_filp; - struct inode *inode = fdentry(file)->d_inode; struct iov_iter i; ssize_t written; ssize_t written_buffered; @@ -1310,18 +1343,6 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos, count, ocount); - /* - * the generic O_DIRECT will update in-memory i_size after the - * DIOs are done. But our endio handlers that update the on - * disk i_size never update past the in memory i_size. So we - * need one more update here to catch any additions to the - * file - */ - if (inode->i_size != BTRFS_I(inode)->disk_i_size) { - btrfs_ordered_update_i_size(inode, inode->i_size, NULL); - mark_inode_dirty(inode); - } - if (written < 0 || written == count) return written; @@ -1399,12 +1420,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, goto out; } - err = btrfs_update_time(file); + err = file_update_time(file); if (err) { mutex_unlock(&inode->i_mutex); goto out; } - BTRFS_I(inode)->sequence++; start_pos = round_down(pos, root->sectorsize); if (start_pos > i_size_read(inode)) { @@ -1461,8 +1481,8 @@ int btrfs_release_file(struct inode *inode, struct file *filp) * flush down new bytes that may have been written if the * application were using truncate to replace a file in place. */ - if (BTRFS_I(inode)->ordered_data_close) { - BTRFS_I(inode)->ordered_data_close = 0; + if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, + &BTRFS_I(inode)->runtime_flags)) { btrfs_add_ordered_operation(NULL, BTRFS_I(inode)->root, inode); if (inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT) filemap_flush(inode->i_mapping); @@ -1493,14 +1513,15 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) trace_btrfs_sync_file(file, datasync); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); - if (ret) - return ret; mutex_lock(&inode->i_mutex); - /* we wait first, since the writeback may change the inode */ + /* + * we wait first, since the writeback may change the inode, also wait + * ordered range does a filemape_write_and_wait_range which is why we + * don't do it above like other file systems. + */ root->log_batch++; - btrfs_wait_ordered_range(inode, 0, (u64)-1); + btrfs_wait_ordered_range(inode, start, end); root->log_batch++; /* @@ -1518,7 +1539,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * syncing */ smp_mb(); - if (BTRFS_I(inode)->last_trans <= + if (btrfs_inode_in_log(inode, root->fs_info->generation) || + BTRFS_I(inode)->last_trans <= root->fs_info->last_trans_committed) { BTRFS_I(inode)->last_trans = 0; mutex_unlock(&inode->i_mutex); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 202008ec367..6c4e2baa929 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -33,6 +33,8 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); +static void unlink_free_space(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info); static struct inode *__lookup_free_space_inode(struct btrfs_root *root, struct btrfs_path *path, @@ -75,7 +77,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, return ERR_PTR(-ENOENT); } - inode->i_mapping->flags &= ~__GFP_FS; + mapping_set_gfp_mask(inode->i_mapping, + mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS); return inode; } @@ -365,7 +368,7 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode, static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation) { - u64 *val; + __le64 *val; io_ctl_map_page(io_ctl, 1); @@ -388,7 +391,7 @@ static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation) static int io_ctl_check_generation(struct io_ctl *io_ctl, u64 generation) { - u64 *gen; + __le64 *gen; /* * Skip the crc area. If we don't check crcs then we just have a 64bit @@ -584,6 +587,44 @@ static int io_ctl_read_bitmap(struct io_ctl *io_ctl, return 0; } +/* + * Since we attach pinned extents after the fact we can have contiguous sections + * of free space that are split up in entries. This poses a problem with the + * tree logging stuff since it could have allocated across what appears to be 2 + * entries since we would have merged the entries when adding the pinned extents + * back to the free space cache. So run through the space cache that we just + * loaded and merge contiguous entries. This will make the log replay stuff not + * blow up and it will make for nicer allocator behavior. + */ +static void merge_space_tree(struct btrfs_free_space_ctl *ctl) +{ + struct btrfs_free_space *e, *prev = NULL; + struct rb_node *n; + +again: + spin_lock(&ctl->tree_lock); + for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { + e = rb_entry(n, struct btrfs_free_space, offset_index); + if (!prev) + goto next; + if (e->bitmap || prev->bitmap) + goto next; + if (prev->offset + prev->bytes == e->offset) { + unlink_free_space(ctl, prev); + unlink_free_space(ctl, e); + prev->bytes += e->bytes; + kmem_cache_free(btrfs_free_space_cachep, e); + link_free_space(ctl, prev); + prev = NULL; + spin_unlock(&ctl->tree_lock); + goto again; + } +next: + prev = e; + } + spin_unlock(&ctl->tree_lock); +} + int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, struct btrfs_path *path, u64 offset) @@ -726,6 +767,7 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, } io_ctl_drop_pages(&io_ctl); + merge_space_tree(ctl); ret = 1; out: io_ctl_free(&io_ctl); @@ -972,9 +1014,7 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, goto out; - ret = filemap_write_and_wait(inode->i_mapping); - if (ret) - goto out; + btrfs_wait_ordered_range(inode, 0, (u64)-1); key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; @@ -1503,29 +1543,26 @@ again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1; /* - * XXX - this can go away after a few releases. - * - * since the only user of btrfs_remove_free_space is the tree logging - * stuff, and the only way to test that is under crash conditions, we - * want to have this debug stuff here just in case somethings not - * working. Search the bitmap for the space we are trying to use to - * make sure its actually there. If its not there then we need to stop - * because something has gone wrong. + * We need to search for bits in this bitmap. We could only cover some + * of the extent in this bitmap thanks to how we add space, so we need + * to search for as much as it as we can and clear that amount, and then + * go searching for the next bit. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); BUG_ON(ret < 0 || search_start != *offset); - if (*offset > bitmap_info->offset && *offset + *bytes > end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1); - *bytes -= end - *offset + 1; - *offset = end + 1; - } else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) { - bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes); - *bytes = 0; - } + /* We may have found more bits than what we need */ + search_bytes = min(search_bytes, *bytes); + + /* Cannot clear past the end of the bitmap */ + search_bytes = min(search_bytes, end - search_start + 1); + + bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes); + *offset += search_bytes; + *bytes -= search_bytes; if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); @@ -1556,7 +1593,7 @@ again: * everything over again. */ search_start = *offset; - search_bytes = *bytes; + search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes); if (ret < 0 || search_start != *offset) @@ -1839,12 +1876,14 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group, { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; - struct btrfs_free_space *next_info = NULL; int ret = 0; spin_lock(&ctl->tree_lock); again: + if (!bytes) + goto out_lock; + info = tree_search_offset(ctl, offset, 0, 0); if (!info) { /* @@ -1865,88 +1904,48 @@ again: } } - if (info->bytes < bytes && rb_next(&info->offset_index)) { - u64 end; - next_info = rb_entry(rb_next(&info->offset_index), - struct btrfs_free_space, - offset_index); - - if (next_info->bitmap) - end = next_info->offset + - BITS_PER_BITMAP * ctl->unit - 1; - else - end = next_info->offset + next_info->bytes; - - if (next_info->bytes < bytes || - next_info->offset > offset || offset > end) { - printk(KERN_CRIT "Found free space at %llu, size %llu," - " trying to use %llu\n", - (unsigned long long)info->offset, - (unsigned long long)info->bytes, - (unsigned long long)bytes); - WARN_ON(1); - ret = -EINVAL; - goto out_lock; - } - - info = next_info; - } - - if (info->bytes == bytes) { - unlink_free_space(ctl, info); - if (info->bitmap) { - kfree(info->bitmap); - ctl->total_bitmaps--; - } - kmem_cache_free(btrfs_free_space_cachep, info); - ret = 0; - goto out_lock; - } - - if (!info->bitmap && info->offset == offset) { + if (!info->bitmap) { unlink_free_space(ctl, info); - info->offset += bytes; - info->bytes -= bytes; - ret = link_free_space(ctl, info); - WARN_ON(ret); - goto out_lock; - } + if (offset == info->offset) { + u64 to_free = min(bytes, info->bytes); + + info->bytes -= to_free; + info->offset += to_free; + if (info->bytes) { + ret = link_free_space(ctl, info); + WARN_ON(ret); + } else { + kmem_cache_free(btrfs_free_space_cachep, info); + } - if (!info->bitmap && info->offset <= offset && - info->offset + info->bytes >= offset + bytes) { - u64 old_start = info->offset; - /* - * we're freeing space in the middle of the info, - * this can happen during tree log replay - * - * first unlink the old info and then - * insert it again after the hole we're creating - */ - unlink_free_space(ctl, info); - if (offset + bytes < info->offset + info->bytes) { - u64 old_end = info->offset + info->bytes; + offset += to_free; + bytes -= to_free; + goto again; + } else { + u64 old_end = info->bytes + info->offset; - info->offset = offset + bytes; - info->bytes = old_end - info->offset; + info->bytes = offset - info->offset; ret = link_free_space(ctl, info); WARN_ON(ret); if (ret) goto out_lock; - } else { - /* the hole we're creating ends at the end - * of the info struct, just free the info - */ - kmem_cache_free(btrfs_free_space_cachep, info); - } - spin_unlock(&ctl->tree_lock); - /* step two, insert a new info struct to cover - * anything before the hole - */ - ret = btrfs_add_free_space(block_group, old_start, - offset - old_start); - WARN_ON(ret); /* -ENOMEM */ - goto out; + /* Not enough bytes in this entry to satisfy us */ + if (old_end < offset + bytes) { + bytes -= old_end - offset; + offset = old_end; + goto again; + } else if (old_end == offset + bytes) { + /* all done */ + goto out_lock; + } + spin_unlock(&ctl->tree_lock); + + ret = btrfs_add_free_space(block_group, offset + bytes, + old_end - (offset + bytes)); + WARN_ON(ret); + goto out; + } } ret = remove_from_bitmap(ctl, info, &offset, &bytes); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 115bc05e42b..a7d1921ac76 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -89,7 +89,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = { static int btrfs_setsize(struct inode *inode, loff_t newsize); static int btrfs_truncate(struct inode *inode); -static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end); +static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent); static noinline int cow_file_range(struct inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, @@ -257,10 +257,13 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans, ret = insert_inline_extent(trans, root, inode, start, inline_len, compressed_size, compress_type, compressed_pages); - if (ret) { + if (ret && ret != -ENOSPC) { btrfs_abort_transaction(trans, root, ret); return ret; + } else if (ret == -ENOSPC) { + return 1; } + btrfs_delalloc_release_metadata(inode, end + 1 - start); btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0); return 0; @@ -827,7 +830,7 @@ static noinline int cow_file_range(struct inode *inode, if (IS_ERR(trans)) { extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, end, NULL, + start, end, locked_page, EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | @@ -960,7 +963,7 @@ out: out_unlock: extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree, - start, end, NULL, + start, end, locked_page, EXTENT_CLEAR_UNLOCK_PAGE | EXTENT_CLEAR_UNLOCK | EXTENT_CLEAR_DELALLOC | @@ -983,8 +986,10 @@ static noinline void async_cow_start(struct btrfs_work *work) compress_file_range(async_cow->inode, async_cow->locked_page, async_cow->start, async_cow->end, async_cow, &num_added); - if (num_added == 0) + if (num_added == 0) { + btrfs_add_delayed_iput(async_cow->inode); async_cow->inode = NULL; + } } /* @@ -1017,6 +1022,8 @@ static noinline void async_cow_free(struct btrfs_work *work) { struct async_cow *async_cow; async_cow = container_of(work, struct async_cow, work); + if (async_cow->inode) + btrfs_add_delayed_iput(async_cow->inode); kfree(async_cow); } @@ -1035,7 +1042,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page, while (start < end) { async_cow = kmalloc(sizeof(*async_cow), GFP_NOFS); BUG_ON(!async_cow); /* -ENOMEM */ - async_cow->inode = inode; + async_cow->inode = igrab(inode); async_cow->root = root; async_cow->locked_page = locked_page; async_cow->start = start; @@ -1133,8 +1140,18 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 ino = btrfs_ino(inode); path = btrfs_alloc_path(); - if (!path) + if (!path) { + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + start, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); return -ENOMEM; + } nolock = btrfs_is_free_space_inode(root, inode); @@ -1144,6 +1161,15 @@ static noinline int run_delalloc_nocow(struct inode *inode, trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + start, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); btrfs_free_path(path); return PTR_ERR(trans); } @@ -1324,8 +1350,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) + if (cur_offset <= end && cow_start == (u64)-1) { cow_start = cur_offset; + cur_offset = end; + } + if (cow_start != (u64)-1) { ret = cow_file_range(inode, locked_page, cow_start, end, page_started, nr_written, 1); @@ -1344,6 +1373,17 @@ error: if (!ret) ret = err; + if (ret && cur_offset < end) + extent_clear_unlock_delalloc(inode, + &BTRFS_I(inode)->io_tree, + cur_offset, end, locked_page, + EXTENT_CLEAR_UNLOCK_PAGE | + EXTENT_CLEAR_UNLOCK | + EXTENT_CLEAR_DELALLOC | + EXTENT_CLEAR_DIRTY | + EXTENT_SET_WRITEBACK | + EXTENT_END_WRITEBACK); + btrfs_free_path(path); return ret; } @@ -1358,20 +1398,23 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page, int ret; struct btrfs_root *root = BTRFS_I(inode)->root; - if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); - else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) + } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - else if (!btrfs_test_opt(root, COMPRESS) && - !(BTRFS_I(inode)->force_compress) && - !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) + } else if (!btrfs_test_opt(root, COMPRESS) && + !(BTRFS_I(inode)->force_compress) && + !(BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS)) { ret = cow_file_range(inode, locked_page, start, end, page_started, nr_written, 1); - else + } else { + set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags); ret = cow_file_range_async(inode, locked_page, start, end, page_started, nr_written); + } return ret; } @@ -1572,11 +1615,11 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, if (btrfs_is_free_space_inode(root, inode)) metadata = 2; - ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata); - if (ret) - return ret; - if (!(rw & REQ_WRITE)) { + ret = btrfs_bio_wq_end_io(root->fs_info, bio, metadata); + if (ret) + return ret; + if (bio_flags & EXTENT_BIO_COMPRESSED) { return btrfs_submit_compressed_read(inode, bio, mirror_num, bio_flags); @@ -1815,25 +1858,24 @@ out: * an ordered extent if the range of bytes in the file it covers are * fully written. */ -static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) +static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) { + struct inode *inode = ordered_extent->inode; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_trans_handle *trans = NULL; - struct btrfs_ordered_extent *ordered_extent = NULL; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; struct extent_state *cached_state = NULL; int compress_type = 0; int ret; bool nolock; - ret = btrfs_dec_test_ordered_pending(inode, &ordered_extent, start, - end - start + 1); - if (!ret) - return 0; - BUG_ON(!ordered_extent); /* Logic error */ - nolock = btrfs_is_free_space_inode(root, inode); + if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) { + ret = -EIO; + goto out; + } + if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) { BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */ ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent); @@ -1889,12 +1931,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ordered_extent->file_offset, ordered_extent->len); } - unlock_extent_cached(io_tree, ordered_extent->file_offset, - ordered_extent->file_offset + - ordered_extent->len - 1, &cached_state, GFP_NOFS); + if (ret < 0) { btrfs_abort_transaction(trans, root, ret); - goto out; + goto out_unlock; } add_pending_csums(trans, inode, ordered_extent->file_offset, @@ -1905,10 +1945,14 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ret = btrfs_update_inode_fallback(trans, root, inode); if (ret) { /* -ENOMEM or corruption */ btrfs_abort_transaction(trans, root, ret); - goto out; + goto out_unlock; } } ret = 0; +out_unlock: + unlock_extent_cached(io_tree, ordered_extent->file_offset, + ordered_extent->file_offset + + ordered_extent->len - 1, &cached_state, GFP_NOFS); out: if (root != root->fs_info->tree_root) btrfs_delalloc_release_metadata(inode, ordered_extent->len); @@ -1919,26 +1963,57 @@ out: btrfs_end_transaction(trans, root); } + if (ret) + clear_extent_uptodate(io_tree, ordered_extent->file_offset, + ordered_extent->file_offset + + ordered_extent->len - 1, NULL, GFP_NOFS); + + /* + * This needs to be dont to make sure anybody waiting knows we are done + * upating everything for this ordered extent. + */ + btrfs_remove_ordered_extent(inode, ordered_extent); + /* once for us */ btrfs_put_ordered_extent(ordered_extent); /* once for the tree */ btrfs_put_ordered_extent(ordered_extent); - return 0; -out_unlock: - unlock_extent_cached(io_tree, ordered_extent->file_offset, - ordered_extent->file_offset + - ordered_extent->len - 1, &cached_state, GFP_NOFS); - goto out; + return ret; +} + +static void finish_ordered_fn(struct btrfs_work *work) +{ + struct btrfs_ordered_extent *ordered_extent; + ordered_extent = container_of(work, struct btrfs_ordered_extent, work); + btrfs_finish_ordered_io(ordered_extent); } static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, struct extent_state *state, int uptodate) { + struct inode *inode = page->mapping->host; + struct btrfs_root *root = BTRFS_I(inode)->root; + struct btrfs_ordered_extent *ordered_extent = NULL; + struct btrfs_workers *workers; + trace_btrfs_writepage_end_io_hook(page, start, end, uptodate); ClearPagePrivate2(page); - return btrfs_finish_ordered_io(page->mapping->host, start, end); + if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start, + end - start + 1, uptodate)) + return 0; + + ordered_extent->work.func = finish_ordered_fn; + ordered_extent->work.flags = 0; + + if (btrfs_is_free_space_inode(root, inode)) + workers = &root->fs_info->endio_freespace_worker; + else + workers = &root->fs_info->endio_write_workers; + btrfs_queue_worker(workers, &ordered_extent->work); + + return 0; } /* @@ -1947,7 +2022,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end, * extent_io.c will try to find good copies for us. */ static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end, - struct extent_state *state) + struct extent_state *state, int mirror) { size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT); struct inode *inode = page->mapping->host; @@ -2072,12 +2147,12 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, struct btrfs_block_rsv *block_rsv; int ret; - if (!list_empty(&root->orphan_list) || + if (atomic_read(&root->orphan_inodes) || root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) return; spin_lock(&root->orphan_lock); - if (!list_empty(&root->orphan_list)) { + if (atomic_read(&root->orphan_inodes)) { spin_unlock(&root->orphan_lock); return; } @@ -2134,8 +2209,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) block_rsv = NULL; } - if (list_empty(&BTRFS_I(inode)->i_orphan)) { - list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list); + if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags)) { #if 0 /* * For proper ENOSPC handling, we should do orphan @@ -2148,12 +2223,12 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) insert = 1; #endif insert = 1; + atomic_dec(&root->orphan_inodes); } - if (!BTRFS_I(inode)->orphan_meta_reserved) { - BTRFS_I(inode)->orphan_meta_reserved = 1; + if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED, + &BTRFS_I(inode)->runtime_flags)) reserve = 1; - } spin_unlock(&root->orphan_lock); /* grab metadata reservation from transaction handle */ @@ -2166,6 +2241,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode) if (insert >= 1) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret && ret != -EEXIST) { + clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags); btrfs_abort_transaction(trans, root, ret); return ret; } @@ -2196,15 +2273,13 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode) int ret = 0; spin_lock(&root->orphan_lock); - if (!list_empty(&BTRFS_I(inode)->i_orphan)) { - list_del_init(&BTRFS_I(inode)->i_orphan); + if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags)) delete_item = 1; - } - if (BTRFS_I(inode)->orphan_meta_reserved) { - BTRFS_I(inode)->orphan_meta_reserved = 0; + if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, + &BTRFS_I(inode)->runtime_flags)) release_rsv = 1; - } spin_unlock(&root->orphan_lock); if (trans && delete_item) { @@ -2212,8 +2287,10 @@ int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode) BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */ } - if (release_rsv) + if (release_rsv) { btrfs_orphan_release_metadata(inode); + atomic_dec(&root->orphan_inodes); + } return 0; } @@ -2341,6 +2418,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) ret = PTR_ERR(trans); goto out; } + printk(KERN_ERR "auto deleting %Lu\n", + found_key.objectid); ret = btrfs_del_orphan_item(trans, root, found_key.objectid); BUG_ON(ret); /* -ENOMEM or corruption (JDM: Recheck) */ @@ -2352,9 +2431,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * add this inode to the orphan list so btrfs_orphan_del does * the proper thing when we hit it */ - spin_lock(&root->orphan_lock); - list_add(&BTRFS_I(inode)->i_orphan, &root->orphan_list); - spin_unlock(&root->orphan_lock); + set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags); /* if we have links, this was a truncate, lets do that */ if (inode->i_nlink) { @@ -2510,7 +2588,7 @@ static void btrfs_read_locked_inode(struct inode *inode) inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item)); BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item); - BTRFS_I(inode)->sequence = btrfs_inode_sequence(leaf, inode_item); + inode->i_version = btrfs_inode_sequence(leaf, inode_item); inode->i_generation = BTRFS_I(inode)->generation; inode->i_rdev = 0; rdev = btrfs_inode_rdev(leaf, inode_item); @@ -2594,7 +2672,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, btrfs_set_inode_nbytes(leaf, item, inode_get_bytes(inode)); btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation); - btrfs_set_inode_sequence(leaf, item, BTRFS_I(inode)->sequence); + btrfs_set_inode_sequence(leaf, item, inode->i_version); btrfs_set_inode_transid(leaf, item, trans->transid); btrfs_set_inode_rdev(leaf, item, inode->i_rdev); btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags); @@ -2752,6 +2830,8 @@ err: goto out; btrfs_i_size_write(dir, dir->i_size - name_len * 2); + inode_inc_iversion(inode); + inode_inc_iversion(dir); inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME; btrfs_update_inode(trans, root, dir); out: @@ -3089,6 +3169,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, } btrfs_i_size_write(dir, dir->i_size - name_len * 2); + inode_inc_iversion(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, dir); if (ret) @@ -3607,7 +3688,8 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize) * any new writes get down to disk quickly. */ if (newsize == 0) - BTRFS_I(inode)->ordered_data_close = 1; + set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, + &BTRFS_I(inode)->runtime_flags); /* we don't support swapfiles, so vmtruncate shouldn't fail */ truncate_setsize(inode, newsize); @@ -3638,6 +3720,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr) if (attr->ia_valid) { setattr_copy(inode, attr); + inode_inc_iversion(inode); err = btrfs_dirty_inode(inode); if (!err && attr->ia_valid & ATTR_MODE) @@ -3671,7 +3754,8 @@ void btrfs_evict_inode(struct inode *inode) btrfs_wait_ordered_range(inode, 0, (u64)-1); if (root->fs_info->log_root_recovering) { - BUG_ON(!list_empty(&BTRFS_I(inode)->i_orphan)); + BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags)); goto no_delete; } @@ -3756,7 +3840,7 @@ void btrfs_evict_inode(struct inode *inode) btrfs_end_transaction(trans, root); btrfs_btree_balance_dirty(root, nr); no_delete: - end_writeback(inode); + clear_inode(inode); return; } @@ -4066,10 +4150,10 @@ static struct inode *new_simple_dir(struct super_block *s, BTRFS_I(inode)->root = root; memcpy(&BTRFS_I(inode)->location, key, sizeof(*key)); - BTRFS_I(inode)->dummy_inode = 1; + set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags); inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID; - inode->i_op = &simple_dir_inode_operations; + inode->i_op = &btrfs_dir_ro_inode_operations; inode->i_fop = &simple_dir_operations; inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; @@ -4140,14 +4224,18 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) static int btrfs_dentry_delete(const struct dentry *dentry) { struct btrfs_root *root; + struct inode *inode = dentry->d_inode; - if (!dentry->d_inode && !IS_ROOT(dentry)) - dentry = dentry->d_parent; + if (!inode && !IS_ROOT(dentry)) + inode = dentry->d_parent->d_inode; - if (dentry->d_inode) { - root = BTRFS_I(dentry->d_inode)->root; + if (inode) { + root = BTRFS_I(inode)->root; if (btrfs_root_refs(&root->root_item) == 0) return 1; + + if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) + return 1; } return 0; } @@ -4188,7 +4276,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, struct btrfs_path *path; struct list_head ins_list; struct list_head del_list; - struct qstr q; int ret; struct extent_buffer *leaf; int slot; @@ -4279,7 +4366,6 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, while (di_cur < di_total) { struct btrfs_key location; - struct dentry *tmp; if (verify_dir_item(root, leaf, di)) break; @@ -4300,35 +4386,15 @@ static int btrfs_real_readdir(struct file *filp, void *dirent, d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)]; btrfs_dir_item_key_to_cpu(leaf, di, &location); - q.name = name_ptr; - q.len = name_len; - q.hash = full_name_hash(q.name, q.len); - tmp = d_lookup(filp->f_dentry, &q); - if (!tmp) { - struct btrfs_key *newkey; - - newkey = kzalloc(sizeof(struct btrfs_key), - GFP_NOFS); - if (!newkey) - goto no_dentry; - tmp = d_alloc(filp->f_dentry, &q); - if (!tmp) { - kfree(newkey); - dput(tmp); - goto no_dentry; - } - memcpy(newkey, &location, - sizeof(struct btrfs_key)); - tmp->d_fsdata = newkey; - tmp->d_flags |= DCACHE_NEED_LOOKUP; - d_rehash(tmp); - dput(tmp); - } else { - dput(tmp); - } -no_dentry: + /* is this a reference to our own snapshot? If so - * skip it + * skip it. + * + * In contrast to old kernels, we insert the snapshot's + * dir item and dir index after it has been created, so + * we won't find a reference to our own snapshot. We + * still keep the following code for backward + * compatibility. */ if (location.type == BTRFS_ROOT_ITEM_KEY && location.objectid == root->root_key.objectid) { @@ -4388,7 +4454,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc) int ret = 0; bool nolock = false; - if (BTRFS_I(inode)->dummy_inode) + if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags)) return 0; if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(root, inode)) @@ -4421,7 +4487,7 @@ int btrfs_dirty_inode(struct inode *inode) struct btrfs_trans_handle *trans; int ret; - if (BTRFS_I(inode)->dummy_inode) + if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags)) return 0; trans = btrfs_join_transaction(root); @@ -4449,46 +4515,18 @@ int btrfs_dirty_inode(struct inode *inode) * This is a copy of file_update_time. We need this so we can return error on * ENOSPC for updating the inode in the case of file write and mmap writes. */ -int btrfs_update_time(struct file *file) +static int btrfs_update_time(struct inode *inode, struct timespec *now, + int flags) { - struct inode *inode = file->f_path.dentry->d_inode; - struct timespec now; - int ret; - enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0; - - /* First try to exhaust all avenues to not sync */ - if (IS_NOCMTIME(inode)) - return 0; - - now = current_fs_time(inode->i_sb); - if (!timespec_equal(&inode->i_mtime, &now)) - sync_it = S_MTIME; - - if (!timespec_equal(&inode->i_ctime, &now)) - sync_it |= S_CTIME; - - if (IS_I_VERSION(inode)) - sync_it |= S_VERSION; - - if (!sync_it) - return 0; - - /* Finally allowed to write? Takes lock. */ - if (mnt_want_write_file(file)) - return 0; - - /* Only change inode inside the lock region */ - if (sync_it & S_VERSION) + if (flags & S_VERSION) inode_inc_iversion(inode); - if (sync_it & S_CTIME) - inode->i_ctime = now; - if (sync_it & S_MTIME) - inode->i_mtime = now; - ret = btrfs_dirty_inode(inode); - if (!ret) - mark_inode_dirty_sync(inode); - mnt_drop_write(file->f_path.mnt); - return ret; + if (flags & S_CTIME) + inode->i_ctime = *now; + if (flags & S_MTIME) + inode->i_mtime = *now; + if (flags & S_ATIME) + inode->i_atime = *now; + return btrfs_dirty_inode(inode); } /* @@ -4748,6 +4786,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->i_size + name_len * 2); + inode_inc_iversion(parent_inode); parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, parent_inode); if (ret) @@ -4955,6 +4994,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, } btrfs_inc_nlink(inode); + inode_inc_iversion(inode); inode->i_ctime = CURRENT_TIME; ihold(inode); @@ -5836,8 +5876,17 @@ map: bh_result->b_size = len; bh_result->b_bdev = em->bdev; set_buffer_mapped(bh_result); - if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - set_buffer_new(bh_result); + if (create) { + if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + set_buffer_new(bh_result); + + /* + * Need to update the i_size under the extent lock so buffered + * readers will get the updated i_size when we unlock. + */ + if (start + len > i_size_read(inode)) + i_size_write(inode, start + len); + } free_extent_map(em); @@ -5921,9 +5970,7 @@ static void btrfs_endio_direct_write(struct bio *bio, int err) struct btrfs_dio_private *dip = bio->bi_private; struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_trans_handle *trans; struct btrfs_ordered_extent *ordered = NULL; - struct extent_state *cached_state = NULL; u64 ordered_offset = dip->logical_offset; u64 ordered_bytes = dip->bytes; int ret; @@ -5933,73 +5980,14 @@ static void btrfs_endio_direct_write(struct bio *bio, int err) again: ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, - ordered_bytes); + ordered_bytes, !err); if (!ret) goto out_test; - BUG_ON(!ordered); - - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - err = -ENOMEM; - goto out; - } - trans->block_rsv = &root->fs_info->delalloc_block_rsv; - - if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) { - ret = btrfs_ordered_update_i_size(inode, 0, ordered); - if (!ret) - err = btrfs_update_inode_fallback(trans, root, inode); - goto out; - } - - lock_extent_bits(&BTRFS_I(inode)->io_tree, ordered->file_offset, - ordered->file_offset + ordered->len - 1, 0, - &cached_state); - - if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags)) { - ret = btrfs_mark_extent_written(trans, inode, - ordered->file_offset, - ordered->file_offset + - ordered->len); - if (ret) { - err = ret; - goto out_unlock; - } - } else { - ret = insert_reserved_file_extent(trans, inode, - ordered->file_offset, - ordered->start, - ordered->disk_len, - ordered->len, - ordered->len, - 0, 0, 0, - BTRFS_FILE_EXTENT_REG); - unpin_extent_cache(&BTRFS_I(inode)->extent_tree, - ordered->file_offset, ordered->len); - if (ret) { - err = ret; - WARN_ON(1); - goto out_unlock; - } - } - - add_pending_csums(trans, inode, ordered->file_offset, &ordered->list); - ret = btrfs_ordered_update_i_size(inode, 0, ordered); - if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags)) - btrfs_update_inode_fallback(trans, root, inode); - ret = 0; -out_unlock: - unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset, - ordered->file_offset + ordered->len - 1, - &cached_state, GFP_NOFS); -out: - btrfs_delalloc_release_metadata(inode, ordered->len); - btrfs_end_transaction(trans, root); - ordered_offset = ordered->file_offset + ordered->len; - btrfs_put_ordered_extent(ordered); - btrfs_put_ordered_extent(ordered); - + ordered->work.func = finish_ordered_fn; + ordered->work.flags = 0; + btrfs_queue_worker(&root->fs_info->endio_write_workers, + &ordered->work); out_test: /* * our bio might span multiple ordered extents. If we haven't @@ -6008,12 +5996,12 @@ out_test: if (ordered_offset < dip->logical_offset + dip->bytes) { ordered_bytes = dip->logical_offset + dip->bytes - ordered_offset; + ordered = NULL; goto again; } out_done: bio->bi_private = dip->private; - kfree(dip->csums); kfree(dip); /* If we had an error make sure to clear the uptodate flag */ @@ -6081,9 +6069,12 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, int ret; bio_get(bio); - ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); - if (ret) - goto err; + + if (!write) { + ret = btrfs_bio_wq_end_io(root->fs_info, bio, 0); + if (ret) + goto err; + } if (skip_sum) goto map; @@ -6378,12 +6369,48 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, */ ordered = btrfs_lookup_ordered_range(inode, lockstart, lockend - lockstart + 1); - if (!ordered) + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + cached_state))) break; + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, &cached_state, GFP_NOFS); - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(file->f_mapping, + lockstart, + lockend); + if (ret) + goto out; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(file->f_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) { + if (ret == -EBUSY) + ret = 0; + goto out; + } + } + cond_resched(); } @@ -6503,13 +6530,13 @@ static int btrfs_releasepage(struct page *page, gfp_t gfp_flags) static void btrfs_invalidatepage(struct page *page, unsigned long offset) { + struct inode *inode = page->mapping->host; struct extent_io_tree *tree; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; u64 page_start = page_offset(page); u64 page_end = page_start + PAGE_CACHE_SIZE - 1; - /* * we have the page locked, so new writeback can't start, * and the dirty bit won't be cleared while we are here. @@ -6519,13 +6546,13 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) */ wait_on_page_writeback(page); - tree = &BTRFS_I(page->mapping->host)->io_tree; + tree = &BTRFS_I(inode)->io_tree; if (offset) { btrfs_releasepage(page, GFP_NOFS); return; } lock_extent_bits(tree, page_start, page_end, 0, &cached_state); - ordered = btrfs_lookup_ordered_extent(page->mapping->host, + ordered = btrfs_lookup_ordered_extent(inode, page_offset(page)); if (ordered) { /* @@ -6540,9 +6567,10 @@ static void btrfs_invalidatepage(struct page *page, unsigned long offset) * whoever cleared the private bit is responsible * for the finish_ordered_io */ - if (TestClearPagePrivate2(page)) { - btrfs_finish_ordered_io(page->mapping->host, - page_start, page_end); + if (TestClearPagePrivate2(page) && + btrfs_dec_test_ordered_pending(inode, &ordered, page_start, + PAGE_CACHE_SIZE, 1)) { + btrfs_finish_ordered_io(ordered); } btrfs_put_ordered_extent(ordered); cached_state = NULL; @@ -6594,7 +6622,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); if (!ret) { - ret = btrfs_update_time(vma->vm_file); + ret = file_update_time(vma->vm_file); reserved = 1; } if (ret) { @@ -6789,7 +6817,8 @@ static int btrfs_truncate(struct inode *inode) * using truncate to replace the contents of the file will * end up with a zero length file after a crash. */ - if (inode->i_size == 0 && BTRFS_I(inode)->ordered_data_close) + if (inode->i_size == 0 && test_bit(BTRFS_INODE_ORDERED_DATA_CLOSE, + &BTRFS_I(inode)->runtime_flags)) btrfs_add_ordered_operation(trans, root, inode); while (1) { @@ -6912,7 +6941,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->root = NULL; ei->space_info = NULL; ei->generation = 0; - ei->sequence = 0; ei->last_trans = 0; ei->last_sub_trans = 0; ei->logged_trans = 0; @@ -6927,11 +6955,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->outstanding_extents = 0; ei->reserved_extents = 0; - ei->ordered_data_close = 0; - ei->orphan_meta_reserved = 0; - ei->dummy_inode = 0; - ei->in_defrag = 0; - ei->delalloc_meta_reserved = 0; + ei->runtime_flags = 0; ei->force_compress = BTRFS_COMPRESS_NONE; ei->delayed_node = NULL; @@ -6945,7 +6969,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) mutex_init(&ei->log_mutex); mutex_init(&ei->delalloc_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); - INIT_LIST_HEAD(&ei->i_orphan); INIT_LIST_HEAD(&ei->delalloc_inodes); INIT_LIST_HEAD(&ei->ordered_operations); RB_CLEAR_NODE(&ei->rb_node); @@ -6990,13 +7013,12 @@ void btrfs_destroy_inode(struct inode *inode) spin_unlock(&root->fs_info->ordered_extent_lock); } - spin_lock(&root->orphan_lock); - if (!list_empty(&BTRFS_I(inode)->i_orphan)) { + if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, + &BTRFS_I(inode)->runtime_flags)) { printk(KERN_INFO "BTRFS: inode %llu still on the orphan list\n", (unsigned long long)btrfs_ino(inode)); - list_del_init(&BTRFS_I(inode)->i_orphan); + atomic_dec(&root->orphan_inodes); } - spin_unlock(&root->orphan_lock); while (1) { ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1); @@ -7117,10 +7139,13 @@ static void fixup_inode_flags(struct inode *dir, struct inode *inode) else b_inode->flags &= ~BTRFS_INODE_NODATACOW; - if (b_dir->flags & BTRFS_INODE_COMPRESS) + if (b_dir->flags & BTRFS_INODE_COMPRESS) { b_inode->flags |= BTRFS_INODE_COMPRESS; - else - b_inode->flags &= ~BTRFS_INODE_COMPRESS; + b_inode->flags &= ~BTRFS_INODE_NOCOMPRESS; + } else { + b_inode->flags &= ~(BTRFS_INODE_COMPRESS | + BTRFS_INODE_NOCOMPRESS); + } } static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, @@ -7211,6 +7236,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (new_inode && new_inode->i_size && S_ISREG(old_inode->i_mode)) btrfs_add_ordered_operation(trans, root, old_inode); + inode_inc_iversion(old_dir); + inode_inc_iversion(new_dir); + inode_inc_iversion(old_inode); old_dir->i_ctime = old_dir->i_mtime = ctime; new_dir->i_ctime = new_dir->i_mtime = ctime; old_inode->i_ctime = ctime; @@ -7237,6 +7265,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, } if (new_inode) { + inode_inc_iversion(new_inode); new_inode->i_ctime = CURRENT_TIME; if (unlikely(btrfs_ino(new_inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) { @@ -7508,6 +7537,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, cur_offset += ins.offset; *alloc_hint = ins.objectid + ins.offset; + inode_inc_iversion(inode); inode->i_ctime = CURRENT_TIME; BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC; if (!(mode & FALLOC_FL_KEEP_SIZE) && @@ -7665,6 +7695,7 @@ static const struct inode_operations btrfs_file_inode_operations = { .permission = btrfs_permission, .fiemap = btrfs_fiemap, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct inode_operations btrfs_special_inode_operations = { .getattr = btrfs_getattr, @@ -7675,6 +7706,7 @@ static const struct inode_operations btrfs_special_inode_operations = { .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct inode_operations btrfs_symlink_inode_operations = { .readlink = generic_readlink, @@ -7688,6 +7720,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = { .listxattr = btrfs_listxattr, .removexattr = btrfs_removexattr, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; const struct dentry_operations btrfs_dentry_operations = { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 18cc23d164a..0e92e576300 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -52,6 +52,7 @@ #include "locking.h" #include "inode-map.h" #include "backref.h" +#include "rcu-string.h" /* Mask out flags that are inappropriate for the given type of inode. */ static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags) @@ -261,6 +262,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } btrfs_update_iflags(inode); + inode_inc_iversion(inode); inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, inode); @@ -367,7 +369,7 @@ static noinline int create_subvol(struct btrfs_root *root, return PTR_ERR(trans); leaf = btrfs_alloc_free_block(trans, root, root->leafsize, - 0, objectid, NULL, 0, 0, 0, 0); + 0, objectid, NULL, 0, 0, 0); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); goto fail; @@ -784,39 +786,57 @@ none: return -ENOENT; } -/* - * Validaty check of prev em and next em: - * 1) no prev/next em - * 2) prev/next em is an hole/inline extent - */ -static int check_adjacent_extents(struct inode *inode, struct extent_map *em) +static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start) { struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; - struct extent_map *prev = NULL, *next = NULL; - int ret = 0; + struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; + struct extent_map *em; + u64 len = PAGE_CACHE_SIZE; + /* + * hopefully we have this extent in the tree already, try without + * the full extent lock + */ read_lock(&em_tree->lock); - prev = lookup_extent_mapping(em_tree, em->start - 1, (u64)-1); - next = lookup_extent_mapping(em_tree, em->start + em->len, (u64)-1); + em = lookup_extent_mapping(em_tree, start, len); read_unlock(&em_tree->lock); - if ((!prev || prev->block_start >= EXTENT_MAP_LAST_BYTE) && - (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)) - ret = 1; - free_extent_map(prev); - free_extent_map(next); + if (!em) { + /* get the big lock and read metadata off disk */ + lock_extent(io_tree, start, start + len - 1); + em = btrfs_get_extent(inode, NULL, 0, start, len, 0); + unlock_extent(io_tree, start, start + len - 1); + + if (IS_ERR(em)) + return NULL; + } + + return em; +} +static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em) +{ + struct extent_map *next; + bool ret = true; + + /* this is the last extent */ + if (em->start + em->len >= i_size_read(inode)) + return false; + + next = defrag_lookup_extent(inode, em->start + em->len); + if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) + ret = false; + + free_extent_map(next); return ret; } -static int should_defrag_range(struct inode *inode, u64 start, u64 len, - int thresh, u64 *last_len, u64 *skip, - u64 *defrag_end) +static int should_defrag_range(struct inode *inode, u64 start, int thresh, + u64 *last_len, u64 *skip, u64 *defrag_end) { - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; - struct extent_map *em = NULL; - struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; + struct extent_map *em; int ret = 1; + bool next_mergeable = true; /* * make sure that once we start defragging an extent, we keep on @@ -827,23 +847,9 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, *skip = 0; - /* - * hopefully we have this extent in the tree already, try without - * the full extent lock - */ - read_lock(&em_tree->lock); - em = lookup_extent_mapping(em_tree, start, len); - read_unlock(&em_tree->lock); - - if (!em) { - /* get the big lock and read metadata off disk */ - lock_extent(io_tree, start, start + len - 1); - em = btrfs_get_extent(inode, NULL, 0, start, len, 0); - unlock_extent(io_tree, start, start + len - 1); - - if (IS_ERR(em)) - return 0; - } + em = defrag_lookup_extent(inode, start); + if (!em) + return 0; /* this will cover holes, and inline extents */ if (em->block_start >= EXTENT_MAP_LAST_BYTE) { @@ -851,18 +857,15 @@ static int should_defrag_range(struct inode *inode, u64 start, u64 len, goto out; } - /* If we have nothing to merge with us, just skip. */ - if (check_adjacent_extents(inode, em)) { - ret = 0; - goto out; - } + next_mergeable = defrag_check_next_extent(inode, em); /* - * we hit a real extent, if it is big don't bother defragging it again + * we hit a real extent, if it is big or the next extent is not a + * real extent, don't bother defragging it */ - if ((*last_len == 0 || *last_len >= thresh) && em->len >= thresh) + if ((*last_len == 0 || *last_len >= thresh) && + (em->len >= thresh || !next_mergeable)) ret = 0; - out: /* * last_len ends up being a counter of how many bytes we've defragged. @@ -1141,8 +1144,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, break; if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT, - PAGE_CACHE_SIZE, extent_thresh, - &last_len, &skip, &defrag_end)) { + extent_thresh, &last_len, &skip, + &defrag_end)) { unsigned long next; /* * the should_defrag function tells us how much to skip @@ -1303,6 +1306,14 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, ret = -EINVAL; goto out_free; } + if (device->fs_devices && device->fs_devices->seeding) { + printk(KERN_INFO "btrfs: resizer unable to apply on " + "seeding device %llu\n", + (unsigned long long)devid); + ret = -EINVAL; + goto out_free; + } + if (!strcmp(sizestr, "max")) new_size = device->bdev->bd_inode->i_size; else { @@ -1344,8 +1355,9 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, do_div(new_size, root->sectorsize); new_size *= root->sectorsize; - printk(KERN_INFO "btrfs: new size for %s is %llu\n", - device->name, (unsigned long long)new_size); + printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n", + rcu_str_deref(device->name), + (unsigned long long)new_size); if (new_size > old_size) { trans = btrfs_start_transaction(root, 0); @@ -2262,7 +2274,17 @@ static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg) di_args->bytes_used = dev->bytes_used; di_args->total_bytes = dev->total_bytes; memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid)); - strncpy(di_args->path, dev->name, sizeof(di_args->path)); + if (dev->name) { + struct rcu_string *name; + + rcu_read_lock(); + name = rcu_dereference(dev->name); + strncpy(di_args->path, name->str, sizeof(di_args->path)); + rcu_read_unlock(); + di_args->path[sizeof(di_args->path) - 1] = 0; + } else { + di_args->path[0] = '\0'; + } out: if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args))) @@ -2619,6 +2641,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); + inode_inc_iversion(inode); inode->i_mtime = inode->i_ctime = CURRENT_TIME; /* @@ -2911,7 +2934,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) up_read(&info->groups_sem); } - user_dest = (struct btrfs_ioctl_space_info *) + user_dest = (struct btrfs_ioctl_space_info __user *) (arg + sizeof(struct btrfs_ioctl_space_args)); if (copy_to_user(user_dest, dest_orig, alloc_size)) @@ -3039,6 +3062,28 @@ static long btrfs_ioctl_scrub_progress(struct btrfs_root *root, return ret; } +static long btrfs_ioctl_get_dev_stats(struct btrfs_root *root, + void __user *arg, int reset_after_read) +{ + struct btrfs_ioctl_get_dev_stats *sa; + int ret; + + if (reset_after_read && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + sa = memdup_user(arg, sizeof(*sa)); + if (IS_ERR(sa)) + return PTR_ERR(sa); + + ret = btrfs_get_dev_stats(root, sa, reset_after_read); + + if (copy_to_user(arg, sa, sizeof(*sa))) + ret = -EFAULT; + + kfree(sa); + return ret; +} + static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg) { int ret = 0; @@ -3209,8 +3254,9 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, } } -static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) +static long btrfs_ioctl_balance(struct file *file, void __user *arg) { + struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_ioctl_balance_args *bargs; struct btrfs_balance_control *bctl; @@ -3222,6 +3268,10 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) if (fs_info->sb->s_flags & MS_RDONLY) return -EROFS; + ret = mnt_want_write(file->f_path.mnt); + if (ret) + return ret; + mutex_lock(&fs_info->volume_mutex); mutex_lock(&fs_info->balance_mutex); @@ -3288,6 +3338,7 @@ out_bargs: out: mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); + mnt_drop_write(file->f_path.mnt); return ret; } @@ -3383,7 +3434,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(root, argp); case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(root, NULL); + return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_CLONE: return btrfs_ioctl_clone(file, arg, 0, 0, 0); case BTRFS_IOC_CLONE_RANGE: @@ -3416,11 +3467,15 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SCRUB_PROGRESS: return btrfs_ioctl_scrub_progress(root, argp); case BTRFS_IOC_BALANCE_V2: - return btrfs_ioctl_balance(root, argp); + return btrfs_ioctl_balance(file, argp); case BTRFS_IOC_BALANCE_CTL: return btrfs_ioctl_balance_ctl(root, arg); case BTRFS_IOC_BALANCE_PROGRESS: return btrfs_ioctl_balance_progress(root, argp); + case BTRFS_IOC_GET_DEV_STATS: + return btrfs_ioctl_get_dev_stats(root, argp, 0); + case BTRFS_IOC_GET_AND_RESET_DEV_STATS: + return btrfs_ioctl_get_dev_stats(root, argp, 1); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 4f69028a68c..e440aa653c3 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -252,7 +252,7 @@ struct btrfs_data_container { struct btrfs_ioctl_ino_path_args { __u64 inum; /* in */ - __u32 size; /* in */ + __u64 size; /* in */ __u64 reserved[4]; /* struct btrfs_data_container *fspath; out */ __u64 fspath; /* out */ @@ -260,12 +260,41 @@ struct btrfs_ioctl_ino_path_args { struct btrfs_ioctl_logical_ino_args { __u64 logical; /* in */ - __u32 size; /* in */ + __u64 size; /* in */ __u64 reserved[4]; /* struct btrfs_data_container *inodes; out */ __u64 inodes; }; +enum btrfs_dev_stat_values { + /* disk I/O failure stats */ + BTRFS_DEV_STAT_WRITE_ERRS, /* EIO or EREMOTEIO from lower layers */ + BTRFS_DEV_STAT_READ_ERRS, /* EIO or EREMOTEIO from lower layers */ + BTRFS_DEV_STAT_FLUSH_ERRS, /* EIO or EREMOTEIO from lower layers */ + + /* stats for indirect indications for I/O failures */ + BTRFS_DEV_STAT_CORRUPTION_ERRS, /* checksum error, bytenr error or + * contents is illegal: this is an + * indication that the block was damaged + * during read or write, or written to + * wrong location or read from wrong + * location */ + BTRFS_DEV_STAT_GENERATION_ERRS, /* an indication that blocks have not + * been written */ + + BTRFS_DEV_STAT_VALUES_MAX +}; + +struct btrfs_ioctl_get_dev_stats { + __u64 devid; /* in */ + __u64 nr_items; /* in/out */ + + /* out values: */ + __u64 values[BTRFS_DEV_STAT_VALUES_MAX]; + + __u64 unused[128 - 2 - BTRFS_DEV_STAT_VALUES_MAX]; /* pad to 1k */ +}; + #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \ struct btrfs_ioctl_vol_args) #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \ @@ -310,7 +339,7 @@ struct btrfs_ioctl_logical_ino_args { #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ struct btrfs_ioctl_vol_args_v2) -#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64) +#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64) #define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64) #define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \ struct btrfs_ioctl_scrub_args) @@ -330,5 +359,9 @@ struct btrfs_ioctl_logical_ino_args { struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ struct btrfs_ioctl_ino_path_args) +#define BTRFS_IOC_GET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \ + struct btrfs_ioctl_get_dev_stats) +#define BTRFS_IOC_GET_AND_RESET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 53, \ + struct btrfs_ioctl_get_dev_stats) #endif diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index bbf6d0d9aeb..643335a4fe3 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -196,7 +196,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, entry->len = len; entry->disk_len = disk_len; entry->bytes_left = len; - entry->inode = inode; + entry->inode = igrab(inode); entry->compress_type = compress_type; if (type != BTRFS_ORDERED_IO_DONE && type != BTRFS_ORDERED_COMPLETE) set_bit(type, &entry->flags); @@ -212,12 +212,12 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, trace_btrfs_ordered_extent_add(inode, entry); - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); node = tree_insert(&tree->tree, file_offset, &entry->rb_node); if (node) ordered_data_tree_panic(inode, -EEXIST, file_offset); - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock); list_add_tail(&entry->root_extent_list, @@ -264,9 +264,9 @@ void btrfs_add_ordered_sum(struct inode *inode, struct btrfs_ordered_inode_tree *tree; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); list_add_tail(&sum->list, &entry->list); - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); } /* @@ -283,18 +283,19 @@ void btrfs_add_ordered_sum(struct inode *inode, */ int btrfs_dec_test_first_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, - u64 *file_offset, u64 io_size) + u64 *file_offset, u64 io_size, int uptodate) { struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; int ret; + unsigned long flags; u64 dec_end; u64 dec_start; u64 to_dec; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irqsave(&tree->lock, flags); node = tree_search(tree, *file_offset); if (!node) { ret = 1; @@ -323,6 +324,9 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode, (unsigned long long)to_dec); } entry->bytes_left -= to_dec; + if (!uptodate) + set_bit(BTRFS_ORDERED_IOERR, &entry->flags); + if (entry->bytes_left == 0) ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); else @@ -332,7 +336,7 @@ out: *cached = entry; atomic_inc(&entry->refs); } - spin_unlock(&tree->lock); + spin_unlock_irqrestore(&tree->lock, flags); return ret == 0; } @@ -347,15 +351,21 @@ out: */ int btrfs_dec_test_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size) + u64 file_offset, u64 io_size, int uptodate) { struct btrfs_ordered_inode_tree *tree; struct rb_node *node; struct btrfs_ordered_extent *entry = NULL; + unsigned long flags; int ret; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irqsave(&tree->lock, flags); + if (cached && *cached) { + entry = *cached; + goto have_entry; + } + node = tree_search(tree, file_offset); if (!node) { ret = 1; @@ -363,6 +373,7 @@ int btrfs_dec_test_ordered_pending(struct inode *inode, } entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); +have_entry: if (!offset_in_entry(entry, file_offset)) { ret = 1; goto out; @@ -374,6 +385,9 @@ int btrfs_dec_test_ordered_pending(struct inode *inode, (unsigned long long)io_size); } entry->bytes_left -= io_size; + if (!uptodate) + set_bit(BTRFS_ORDERED_IOERR, &entry->flags); + if (entry->bytes_left == 0) ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); else @@ -383,7 +397,7 @@ out: *cached = entry; atomic_inc(&entry->refs); } - spin_unlock(&tree->lock); + spin_unlock_irqrestore(&tree->lock, flags); return ret == 0; } @@ -399,6 +413,8 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) trace_btrfs_ordered_extent_put(entry->inode, entry); if (atomic_dec_and_test(&entry->refs)) { + if (entry->inode) + btrfs_add_delayed_iput(entry->inode); while (!list_empty(&entry->list)) { cur = entry->list.next; sum = list_entry(cur, struct btrfs_ordered_sum, list); @@ -411,21 +427,22 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry) /* * remove an ordered extent from the tree. No references are dropped - * and you must wake_up entry->wait. You must hold the tree lock - * while you call this function. + * and waiters are woken up. */ -static void __btrfs_remove_ordered_extent(struct inode *inode, - struct btrfs_ordered_extent *entry) +void btrfs_remove_ordered_extent(struct inode *inode, + struct btrfs_ordered_extent *entry) { struct btrfs_ordered_inode_tree *tree; struct btrfs_root *root = BTRFS_I(inode)->root; struct rb_node *node; tree = &BTRFS_I(inode)->ordered_tree; + spin_lock_irq(&tree->lock); node = &entry->rb_node; rb_erase(node, &tree->tree); tree->last = NULL; set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags); + spin_unlock_irq(&tree->lock); spin_lock(&root->fs_info->ordered_extent_lock); list_del_init(&entry->root_extent_list); @@ -442,21 +459,6 @@ static void __btrfs_remove_ordered_extent(struct inode *inode, list_del_init(&BTRFS_I(inode)->ordered_operations); } spin_unlock(&root->fs_info->ordered_extent_lock); -} - -/* - * remove an ordered extent from the tree. No references are dropped - * but any waiters are woken. - */ -void btrfs_remove_ordered_extent(struct inode *inode, - struct btrfs_ordered_extent *entry) -{ - struct btrfs_ordered_inode_tree *tree; - - tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); - __btrfs_remove_ordered_extent(inode, entry); - spin_unlock(&tree->lock); wake_up(&entry->wait); } @@ -621,17 +623,29 @@ void btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) if (orig_end > INT_LIMIT(loff_t)) orig_end = INT_LIMIT(loff_t); } -again: + /* start IO across the range first to instantiate any delalloc * extents */ filemap_fdatawrite_range(inode->i_mapping, start, orig_end); - /* The compression code will leave pages locked but return from - * writepage without setting the page writeback. Starting again - * with WB_SYNC_ALL will end up waiting for the IO to actually start. + /* + * So with compression we will find and lock a dirty page and clear the + * first one as dirty, setup an async extent, and immediately return + * with the entire range locked but with nobody actually marked with + * writeback. So we can't just filemap_write_and_wait_range() and + * expect it to work since it will just kick off a thread to do the + * actual work. So we need to call filemap_fdatawrite_range _again_ + * since it will wait on the page lock, which won't be unlocked until + * after the pages have been marked as writeback and so we're good to go + * from there. We have to do this otherwise we'll miss the ordered + * extents and that results in badness. Please Josef, do not think you + * know better and pull this out at some point in the future, it is + * right and you are wrong. */ - filemap_fdatawrite_range(inode->i_mapping, start, orig_end); + if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + filemap_fdatawrite_range(inode->i_mapping, start, orig_end); filemap_fdatawait_range(inode->i_mapping, start, orig_end); @@ -657,11 +671,6 @@ again: break; end--; } - if (found || test_range_bit(&BTRFS_I(inode)->io_tree, start, orig_end, - EXTENT_DELALLOC, 0, NULL)) { - schedule_timeout(1); - goto again; - } } /* @@ -676,7 +685,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, struct btrfs_ordered_extent *entry = NULL; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); node = tree_search(tree, file_offset); if (!node) goto out; @@ -687,7 +696,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode, if (entry) atomic_inc(&entry->refs); out: - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); return entry; } @@ -703,7 +712,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode, struct btrfs_ordered_extent *entry = NULL; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); node = tree_search(tree, file_offset); if (!node) { node = tree_search(tree, file_offset + len); @@ -728,7 +737,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode, out: if (entry) atomic_inc(&entry->refs); - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); return entry; } @@ -744,7 +753,7 @@ btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset) struct btrfs_ordered_extent *entry = NULL; tree = &BTRFS_I(inode)->ordered_tree; - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); node = tree_search(tree, file_offset); if (!node) goto out; @@ -752,7 +761,7 @@ btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset) entry = rb_entry(node, struct btrfs_ordered_extent, rb_node); atomic_inc(&entry->refs); out: - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); return entry; } @@ -764,7 +773,6 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, struct btrfs_ordered_extent *ordered) { struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; - struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; u64 disk_i_size; u64 new_i_size; u64 i_size_test; @@ -779,7 +787,7 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, else offset = ALIGN(offset, BTRFS_I(inode)->root->sectorsize); - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); disk_i_size = BTRFS_I(inode)->disk_i_size; /* truncate file */ @@ -798,14 +806,6 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, } /* - * we can't update the disk_isize if there are delalloc bytes - * between disk_i_size and this ordered extent - */ - if (test_range_bit(io_tree, disk_i_size, offset - 1, - EXTENT_DELALLOC, 0, NULL)) { - goto out; - } - /* * walk backward from this ordered extent to disk_i_size. * if we find an ordered extent then we can't update disk i_size * yet @@ -825,15 +825,18 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, } node = prev; } - while (node) { + for (; node; node = rb_prev(node)) { test = rb_entry(node, struct btrfs_ordered_extent, rb_node); + + /* We treat this entry as if it doesnt exist */ + if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags)) + continue; if (test->file_offset + test->len <= disk_i_size) break; if (test->file_offset >= i_size) break; if (test->file_offset >= disk_i_size) goto out; - node = rb_prev(node); } new_i_size = min_t(u64, offset, i_size); @@ -851,43 +854,49 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset, else node = rb_first(&tree->tree); } - i_size_test = 0; - if (node) { - /* - * do we have an area where IO might have finished - * between our ordered extent and the next one. - */ + + /* + * We are looking for an area between our current extent and the next + * ordered extent to update the i_size to. There are 3 cases here + * + * 1) We don't actually have anything and we can update to i_size. + * 2) We have stuff but they already did their i_size update so again we + * can just update to i_size. + * 3) We have an outstanding ordered extent so the most we can update + * our disk_i_size to is the start of the next offset. + */ + i_size_test = i_size; + for (; node; node = rb_next(node)) { test = rb_entry(node, struct btrfs_ordered_extent, rb_node); - if (test->file_offset > offset) + + if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags)) + continue; + if (test->file_offset > offset) { i_size_test = test->file_offset; - } else { - i_size_test = i_size; + break; + } } /* * i_size_test is the end of a region after this ordered - * extent where there are no ordered extents. As long as there - * are no delalloc bytes in this area, it is safe to update - * disk_i_size to the end of the region. + * extent where there are no ordered extents, we can safely set + * disk_i_size to this. */ - if (i_size_test > offset && - !test_range_bit(io_tree, offset, i_size_test - 1, - EXTENT_DELALLOC, 0, NULL)) { + if (i_size_test > offset) new_i_size = min_t(u64, i_size_test, i_size); - } BTRFS_I(inode)->disk_i_size = new_i_size; ret = 0; out: /* - * we need to remove the ordered extent with the tree lock held - * so that other people calling this function don't find our fully - * processed ordered entry and skip updating the i_size + * We need to do this because we can't remove ordered extents until + * after the i_disk_size has been updated and then the inode has been + * updated to reflect the change, so we need to tell anybody who finds + * this ordered extent that we've already done all the real work, we + * just haven't completed all the other work. */ if (ordered) - __btrfs_remove_ordered_extent(inode, ordered); - spin_unlock(&tree->lock); - if (ordered) - wake_up(&ordered->wait); + set_bit(BTRFS_ORDERED_UPDATED_ISIZE, &ordered->flags); + spin_unlock_irq(&tree->lock); return ret; } @@ -912,7 +921,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, if (!ordered) return 1; - spin_lock(&tree->lock); + spin_lock_irq(&tree->lock); list_for_each_entry_reverse(ordered_sum, &ordered->list, list) { if (disk_bytenr >= ordered_sum->bytenr) { num_sectors = ordered_sum->len / sectorsize; @@ -927,7 +936,7 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, } } out: - spin_unlock(&tree->lock); + spin_unlock_irq(&tree->lock); btrfs_put_ordered_extent(ordered); return ret; } diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index c355ad4dc1a..e03c560d299 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -74,6 +74,12 @@ struct btrfs_ordered_sum { #define BTRFS_ORDERED_DIRECT 5 /* set when we're doing DIO with this extent */ +#define BTRFS_ORDERED_IOERR 6 /* We had an io error when writing this out */ + +#define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates wether this ordered extent + * has done its due diligence in updating + * the isize. */ + struct btrfs_ordered_extent { /* logical offset in the file */ u64 file_offset; @@ -113,6 +119,8 @@ struct btrfs_ordered_extent { /* a per root list of all the pending ordered extents */ struct list_head root_extent_list; + + struct btrfs_work work; }; @@ -143,10 +151,11 @@ void btrfs_remove_ordered_extent(struct inode *inode, struct btrfs_ordered_extent *entry); int btrfs_dec_test_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, - u64 file_offset, u64 io_size); + u64 file_offset, u64 io_size, int uptodate); int btrfs_dec_test_first_ordered_pending(struct inode *inode, struct btrfs_ordered_extent **cached, - u64 *file_offset, u64 io_size); + u64 *file_offset, u64 io_size, + int uptodate); int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, u64 start, u64 len, u64 disk_len, int type); int btrfs_add_ordered_extent_dio(struct inode *inode, u64 file_offset, diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index f38e452486b..5e23684887e 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -294,6 +294,9 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) btrfs_dev_extent_chunk_offset(l, dev_extent), (unsigned long long) btrfs_dev_extent_length(l, dev_extent)); + case BTRFS_DEV_STATS_KEY: + printk(KERN_INFO "\t\tdevice stats\n"); + break; }; } } diff --git a/fs/btrfs/rcu-string.h b/fs/btrfs/rcu-string.h new file mode 100644 index 00000000000..9e111e4576d --- /dev/null +++ b/fs/btrfs/rcu-string.h @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 Red Hat. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public + * License v2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public + * License along with this program; if not, write to the + * Free Software Foundation, Inc., 59 Temple Place - Suite 330, + * Boston, MA 021110-1307, USA. + */ + +struct rcu_string { + struct rcu_head rcu; + char str[0]; +}; + +static inline struct rcu_string *rcu_string_strdup(const char *src, gfp_t mask) +{ + size_t len = strlen(src) + 1; + struct rcu_string *ret = kzalloc(sizeof(struct rcu_string) + + (len * sizeof(char)), mask); + if (!ret) + return ret; + strncpy(ret->str, src, len); + return ret; +} + +static inline void rcu_string_free(struct rcu_string *str) +{ + if (str) + kfree_rcu(str, rcu); +} + +#define printk_in_rcu(fmt, ...) do { \ + rcu_read_lock(); \ + printk(fmt, __VA_ARGS__); \ + rcu_read_unlock(); \ +} while (0) + +#define printk_ratelimited_in_rcu(fmt, ...) do { \ + rcu_read_lock(); \ + printk_ratelimited(fmt, __VA_ARGS__); \ + rcu_read_unlock(); \ +} while (0) + +#define rcu_str_deref(rcu_str) ({ \ + struct rcu_string *__str = rcu_dereference(rcu_str); \ + __str->str; \ +}) diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index dc5d33146fd..48a4882d8ad 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -250,14 +250,12 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info, struct btrfs_bio *bbio) { int ret; - int looped = 0; struct reada_zone *zone; struct btrfs_block_group_cache *cache = NULL; u64 start; u64 end; int i; -again: zone = NULL; spin_lock(&fs_info->reada_lock); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, @@ -274,9 +272,6 @@ again: spin_unlock(&fs_info->reada_lock); } - if (looped) - return NULL; - cache = btrfs_lookup_block_group(fs_info, logical); if (!cache) return NULL; @@ -307,13 +302,15 @@ again: ret = radix_tree_insert(&dev->reada_zones, (unsigned long)(zone->end >> PAGE_CACHE_SHIFT), zone); - spin_unlock(&fs_info->reada_lock); - if (ret) { + if (ret == -EEXIST) { kfree(zone); - looped = 1; - goto again; + ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, + logical >> PAGE_CACHE_SHIFT, 1); + if (ret == 1) + kref_get(&zone->refcnt); } + spin_unlock(&fs_info->reada_lock); return zone; } @@ -323,26 +320,26 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, struct btrfs_key *top, int level) { int ret; - int looped = 0; struct reada_extent *re = NULL; + struct reada_extent *re_exist = NULL; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree; struct btrfs_bio *bbio = NULL; struct btrfs_device *dev; + struct btrfs_device *prev_dev; u32 blocksize; u64 length; int nzones = 0; int i; unsigned long index = logical >> PAGE_CACHE_SHIFT; -again: spin_lock(&fs_info->reada_lock); re = radix_tree_lookup(&fs_info->reada_tree, index); if (re) kref_get(&re->refcnt); spin_unlock(&fs_info->reada_lock); - if (re || looped) + if (re) return re; re = kzalloc(sizeof(*re), GFP_NOFS); @@ -398,16 +395,31 @@ again: /* insert extent in reada_tree + all per-device trees, all or nothing */ spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&fs_info->reada_tree, index, re); + if (ret == -EEXIST) { + re_exist = radix_tree_lookup(&fs_info->reada_tree, index); + BUG_ON(!re_exist); + kref_get(&re_exist->refcnt); + spin_unlock(&fs_info->reada_lock); + goto error; + } if (ret) { spin_unlock(&fs_info->reada_lock); - if (ret != -ENOMEM) { - /* someone inserted the extent in the meantime */ - looped = 1; - } goto error; } + prev_dev = NULL; for (i = 0; i < nzones; ++i) { dev = bbio->stripes[i].dev; + if (dev == prev_dev) { + /* + * in case of DUP, just add the first zone. As both + * are on the same device, there's nothing to gain + * from adding both. + * Also, it wouldn't work, as the tree is per device + * and adding would fail with EEXIST + */ + continue; + } + prev_dev = dev; ret = radix_tree_insert(&dev->reada_extents, index, re); if (ret) { while (--i >= 0) { @@ -450,9 +462,7 @@ error: } kfree(bbio); kfree(re); - if (looped) - goto again; - return NULL; + return re_exist; } static void reada_kref_dummy(struct kref *kr) @@ -708,13 +718,18 @@ static void reada_start_machine_worker(struct btrfs_work *work) { struct reada_machine_work *rmw; struct btrfs_fs_info *fs_info; + int old_ioprio; rmw = container_of(work, struct reada_machine_work, work); fs_info = rmw->fs_info; kfree(rmw); + old_ioprio = IOPRIO_PRIO_VALUE(task_nice_ioclass(current), + task_nice_ioprio(current)); + set_task_ioprio(current, BTRFS_IOPRIO_READA); __reada_start_machine(fs_info); + set_task_ioprio(current, old_ioprio); } static void __reada_start_machine(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 017281dbb2a..646ee21bb03 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1279,7 +1279,9 @@ static int __update_reloc_root(struct btrfs_root *root, int del) if (rb_node) backref_tree_panic(rb_node, -EEXIST, node->bytenr); } else { + spin_lock(&root->fs_info->trans_lock); list_del_init(&root->root_list); + spin_unlock(&root->fs_info->trans_lock); kfree(node); } return 0; @@ -3811,7 +3813,7 @@ restart: ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 5); if (ret < 0) { - if (ret != -EAGAIN) { + if (ret != -ENOSPC) { err = ret; WARN_ON(1); break; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index bc015f77f3e..b223620cd5a 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -26,6 +26,7 @@ #include "backref.h" #include "extent_io.h" #include "check-integrity.h" +#include "rcu-string.h" /* * This is only the first step towards a full-features scrub. It reads all @@ -50,7 +51,7 @@ struct scrub_dev; struct scrub_page { struct scrub_block *sblock; struct page *page; - struct block_device *bdev; + struct btrfs_device *dev; u64 flags; /* extent flags */ u64 generation; u64 logical; @@ -86,6 +87,7 @@ struct scrub_block { unsigned int header_error:1; unsigned int checksum_error:1; unsigned int no_io_error_seen:1; + unsigned int generation_error:1; /* also sets header_error */ }; }; @@ -319,10 +321,10 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx) * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) - printk(KERN_WARNING "btrfs: %s at logical %llu on dev " + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu, " "length %llu, links %u (path: %s)\n", swarn->errstr, - swarn->logical, swarn->dev->name, + swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, min(isize - offset, (u64)PAGE_SIZE), nlink, (char *)(unsigned long)ipath->fspath->val[i]); @@ -331,10 +333,10 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx) return 0; err: - printk(KERN_WARNING "btrfs: %s at logical %llu on dev " + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev " "%s, sector %llu, root %llu, inode %llu, offset %llu: path " "resolving failed with ret=%d\n", swarn->errstr, - swarn->logical, swarn->dev->name, + swarn->logical, rcu_str_deref(swarn->dev->name), (unsigned long long)swarn->sector, root, inum, offset, ret); free_ipath(ipath); @@ -389,10 +391,11 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock) do { ret = tree_backref_for_extent(&ptr, eb, ei, item_size, &ref_root, &ref_level); - printk(KERN_WARNING + printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev %s, " "sector %llu: metadata %s (level %d) in tree " - "%llu\n", errstr, swarn.logical, dev->name, + "%llu\n", errstr, swarn.logical, + rcu_str_deref(dev->name), (unsigned long long)swarn.sector, ref_level ? "node" : "leaf", ret < 0 ? -1 : ref_level, @@ -579,9 +582,11 @@ out: spin_lock(&sdev->stat_lock); ++sdev->stat.uncorrectable_errors; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + + printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n", - (unsigned long long)fixup->logical, sdev->dev->name); + (unsigned long long)fixup->logical, + rcu_str_deref(sdev->dev->name)); } btrfs_free_path(path); @@ -675,6 +680,8 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sdev->stat.read_errors++; sdev->stat.uncorrectable_errors++; spin_unlock(&sdev->stat_lock); + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_READ_ERRS); goto out; } @@ -686,6 +693,8 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sdev->stat.read_errors++; sdev->stat.uncorrectable_errors++; spin_unlock(&sdev->stat_lock); + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_READ_ERRS); goto out; } BUG_ON(failed_mirror_index >= BTRFS_MAX_MIRRORS); @@ -699,6 +708,8 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) sdev->stat.read_errors++; sdev->stat.uncorrectable_errors++; spin_unlock(&sdev->stat_lock); + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_READ_ERRS); goto out; } @@ -725,12 +736,16 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) spin_unlock(&sdev->stat_lock); if (__ratelimit(&_rs)) scrub_print_warning("i/o error", sblock_to_check); + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_READ_ERRS); } else if (sblock_bad->checksum_error) { spin_lock(&sdev->stat_lock); sdev->stat.csum_errors++; spin_unlock(&sdev->stat_lock); if (__ratelimit(&_rs)) scrub_print_warning("checksum error", sblock_to_check); + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_CORRUPTION_ERRS); } else if (sblock_bad->header_error) { spin_lock(&sdev->stat_lock); sdev->stat.verify_errors++; @@ -738,6 +753,12 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check) if (__ratelimit(&_rs)) scrub_print_warning("checksum/header error", sblock_to_check); + if (sblock_bad->generation_error) + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_GENERATION_ERRS); + else + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_CORRUPTION_ERRS); } if (sdev->readonly) @@ -919,18 +940,20 @@ corrected_error: spin_lock(&sdev->stat_lock); sdev->stat.corrected_errors++; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + printk_ratelimited_in_rcu(KERN_ERR "btrfs: fixed up error at logical %llu on dev %s\n", - (unsigned long long)logical, sdev->dev->name); + (unsigned long long)logical, + rcu_str_deref(sdev->dev->name)); } } else { did_not_correct_error: spin_lock(&sdev->stat_lock); sdev->stat.uncorrectable_errors++; spin_unlock(&sdev->stat_lock); - printk_ratelimited(KERN_ERR + printk_ratelimited_in_rcu(KERN_ERR "btrfs: unable to fixup (regular) error at logical %llu on dev %s\n", - (unsigned long long)logical, sdev->dev->name); + (unsigned long long)logical, + rcu_str_deref(sdev->dev->name)); } out: @@ -998,7 +1021,8 @@ static int scrub_setup_recheck_block(struct scrub_dev *sdev, page = sblock->pagev + page_index; page->logical = logical; page->physical = bbio->stripes[mirror_index].physical; - page->bdev = bbio->stripes[mirror_index].dev->bdev; + /* for missing devices, dev->bdev is NULL */ + page->dev = bbio->stripes[mirror_index].dev; page->mirror_num = mirror_index + 1; page->page = alloc_page(GFP_NOFS); if (!page->page) { @@ -1042,11 +1066,17 @@ static int scrub_recheck_block(struct btrfs_fs_info *fs_info, struct scrub_page *page = sblock->pagev + page_num; DECLARE_COMPLETION_ONSTACK(complete); + if (page->dev->bdev == NULL) { + page->io_error = 1; + sblock->no_io_error_seen = 0; + continue; + } + BUG_ON(!page->page); bio = bio_alloc(GFP_NOFS, 1); if (!bio) return -EIO; - bio->bi_bdev = page->bdev; + bio->bi_bdev = page->dev->bdev; bio->bi_sector = page->physical >> 9; bio->bi_end_io = scrub_complete_bio_end_io; bio->bi_private = &complete; @@ -1095,11 +1125,14 @@ static void scrub_recheck_block_checksum(struct btrfs_fs_info *fs_info, h = (struct btrfs_header *)mapped_buffer; if (sblock->pagev[0].logical != le64_to_cpu(h->bytenr) || - generation != le64_to_cpu(h->generation) || memcmp(h->fsid, fs_info->fsid, BTRFS_UUID_SIZE) || memcmp(h->chunk_tree_uuid, fs_info->chunk_tree_uuid, - BTRFS_UUID_SIZE)) + BTRFS_UUID_SIZE)) { sblock->header_error = 1; + } else if (generation != le64_to_cpu(h->generation)) { + sblock->header_error = 1; + sblock->generation_error = 1; + } csum = h->csum; } else { if (!have_csum) @@ -1175,7 +1208,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, bio = bio_alloc(GFP_NOFS, 1); if (!bio) return -EIO; - bio->bi_bdev = page_bad->bdev; + bio->bi_bdev = page_bad->dev->bdev; bio->bi_sector = page_bad->physical >> 9; bio->bi_end_io = scrub_complete_bio_end_io; bio->bi_private = &complete; @@ -1189,6 +1222,12 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad, /* this will also unplug the queue */ wait_for_completion(&complete); + if (!bio_flagged(bio, BIO_UPTODATE)) { + btrfs_dev_stat_inc_and_print(page_bad->dev, + BTRFS_DEV_STAT_WRITE_ERRS); + bio_put(bio); + return -EIO; + } bio_put(bio); } @@ -1257,12 +1296,6 @@ static int scrub_checksum_data(struct scrub_block *sblock) if (memcmp(csum, on_disk_csum, sdev->csum_size)) fail = 1; - if (fail) { - spin_lock(&sdev->stat_lock); - ++sdev->stat.csum_errors; - spin_unlock(&sdev->stat_lock); - } - return fail; } @@ -1335,15 +1368,6 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock) if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size)) ++crc_fail; - if (crc_fail || fail) { - spin_lock(&sdev->stat_lock); - if (crc_fail) - ++sdev->stat.csum_errors; - if (fail) - ++sdev->stat.verify_errors; - spin_unlock(&sdev->stat_lock); - } - return fail || crc_fail; } @@ -1360,7 +1384,8 @@ static int scrub_checksum_super(struct scrub_block *sblock) u64 mapped_size; void *p; u32 crc = ~(u32)0; - int fail = 0; + int fail_gen = 0; + int fail_cor = 0; u64 len; int index; @@ -1371,13 +1396,13 @@ static int scrub_checksum_super(struct scrub_block *sblock) memcpy(on_disk_csum, s->csum, sdev->csum_size); if (sblock->pagev[0].logical != le64_to_cpu(s->bytenr)) - ++fail; + ++fail_cor; if (sblock->pagev[0].generation != le64_to_cpu(s->generation)) - ++fail; + ++fail_gen; if (memcmp(s->fsid, fs_info->fsid, BTRFS_UUID_SIZE)) - ++fail; + ++fail_cor; len = BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE; mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE; @@ -1402,9 +1427,9 @@ static int scrub_checksum_super(struct scrub_block *sblock) btrfs_csum_final(crc, calculated_csum); if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size)) - ++fail; + ++fail_cor; - if (fail) { + if (fail_cor + fail_gen) { /* * if we find an error in a super block, we just report it. * They will get written with the next transaction commit @@ -1413,9 +1438,15 @@ static int scrub_checksum_super(struct scrub_block *sblock) spin_lock(&sdev->stat_lock); ++sdev->stat.super_errors; spin_unlock(&sdev->stat_lock); + if (fail_cor) + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_CORRUPTION_ERRS); + else + btrfs_dev_stat_inc_and_print(sdev->dev, + BTRFS_DEV_STAT_GENERATION_ERRS); } - return fail; + return fail_cor + fail_gen; } static void scrub_block_get(struct scrub_block *sblock) @@ -1559,7 +1590,7 @@ static int scrub_pages(struct scrub_dev *sdev, u64 logical, u64 len, return -ENOMEM; } spage->sblock = sblock; - spage->bdev = sdev->dev->bdev; + spage->dev = sdev->dev; spage->flags = flags; spage->generation = gen; spage->logical = logical; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8d5d380f7bd..e23991574fd 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -54,6 +54,7 @@ #include "version.h" #include "export.h" #include "compression.h" +#include "rcu-string.h" #define CREATE_TRACE_POINTS #include <trace/events/btrfs.h> @@ -188,7 +189,8 @@ void btrfs_printk(struct btrfs_fs_info *fs_info, const char *fmt, ...) va_start(args, fmt); if (fmt[0] == '<' && isdigit(fmt[1]) && fmt[2] == '>') { - strncpy(lvl, fmt, 3); + memcpy(lvl, fmt, 3); + lvl[3] = '\0'; fmt += 3; type = logtypes[fmt[1] - '0']; } else @@ -435,11 +437,8 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_thread_pool: intarg = 0; match_int(&args[0], &intarg); - if (intarg) { + if (intarg) info->thread_pool_size = intarg; - printk(KERN_INFO "btrfs: thread pool %d\n", - info->thread_pool_size); - } break; case Opt_max_inline: num = match_strdup(&args[0]); @@ -769,7 +768,7 @@ static int btrfs_fill_super(struct super_block *sb, #ifdef CONFIG_BTRFS_FS_POSIX_ACL sb->s_flags |= MS_POSIXACL; #endif - + sb->s_flags |= MS_I_VERSION; err = open_ctree(sb, fs_devices, (char *)data); if (err) { printk("btrfs: open_ctree failed\n"); @@ -815,7 +814,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_start_delalloc_inodes(root, 0); btrfs_wait_ordered_extents(root, 0, 0); trans = btrfs_start_transaction(root, 0); @@ -926,63 +924,48 @@ static inline int is_subvolume_inode(struct inode *inode) */ static char *setup_root_args(char *args) { - unsigned copied = 0; - unsigned len = strlen(args) + 2; - char *pos; - char *ret; + unsigned len = strlen(args) + 2 + 1; + char *src, *dst, *buf; /* - * We need the same args as before, but minus - * - * subvol=a - * - * and add + * We need the same args as before, but with this substitution: + * s!subvol=[^,]+!subvolid=0! * - * subvolid=0 - * - * which is a difference of 2 characters, so we allocate strlen(args) + - * 2 characters. + * Since the replacement string is up to 2 bytes longer than the + * original, allocate strlen(args) + 2 + 1 bytes. */ - ret = kzalloc(len * sizeof(char), GFP_NOFS); - if (!ret) - return NULL; - pos = strstr(args, "subvol="); + src = strstr(args, "subvol="); /* This shouldn't happen, but just in case.. */ - if (!pos) { - kfree(ret); + if (!src) + return NULL; + + buf = dst = kmalloc(len, GFP_NOFS); + if (!buf) return NULL; - } /* - * The subvol=<> arg is not at the front of the string, copy everybody - * up to that into ret. + * If the subvol= arg is not at the start of the string, + * copy whatever precedes it into buf. */ - if (pos != args) { - *pos = '\0'; - strcpy(ret, args); - copied += strlen(args); - pos++; + if (src != args) { + *src++ = '\0'; + strcpy(buf, args); + dst += strlen(args); } - strncpy(ret + copied, "subvolid=0", len - copied); - - /* Length of subvolid=0 */ - copied += 10; + strcpy(dst, "subvolid=0"); + dst += strlen("subvolid=0"); /* - * If there is no , after the subvol= option then we know there's no - * other options and we can just return. + * If there is a "," after the original subvol=... string, + * copy that suffix into our buffer. Otherwise, we're done. */ - pos = strchr(pos, ','); - if (!pos) - return ret; - - /* Copy the rest of the arguments into our buffer */ - strncpy(ret + copied, pos, len - copied); - copied += strlen(pos); + src = strchr(src, ','); + if (src) + strcpy(dst, src); - return ret; + return buf; } static struct dentry *mount_subvol(const char *subvol_name, int flags, @@ -1119,6 +1102,40 @@ error_fs_info: return ERR_PTR(error); } +static void btrfs_set_max_workers(struct btrfs_workers *workers, int new_limit) +{ + spin_lock_irq(&workers->lock); + workers->max_workers = new_limit; + spin_unlock_irq(&workers->lock); +} + +static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, + int new_pool_size, int old_pool_size) +{ + if (new_pool_size == old_pool_size) + return; + + fs_info->thread_pool_size = new_pool_size; + + printk(KERN_INFO "btrfs: resize thread pool %d -> %d\n", + old_pool_size, new_pool_size); + + btrfs_set_max_workers(&fs_info->generic_worker, new_pool_size); + btrfs_set_max_workers(&fs_info->workers, new_pool_size); + btrfs_set_max_workers(&fs_info->delalloc_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->submit_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->caching_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->fixup_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->endio_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->endio_meta_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->endio_meta_write_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->endio_write_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->endio_freespace_worker, new_pool_size); + btrfs_set_max_workers(&fs_info->delayed_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->readahead_workers, new_pool_size); + btrfs_set_max_workers(&fs_info->scrub_workers, new_pool_size); +} + static int btrfs_remount(struct super_block *sb, int *flags, char *data) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); @@ -1138,6 +1155,9 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } + btrfs_resize_thread_pool(fs_info, + fs_info->thread_pool_size, old_thread_pool_size); + if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) return 0; @@ -1148,13 +1168,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; } else { - if (fs_info->fs_devices->rw_devices == 0) + if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; + } - if (btrfs_super_log_root(fs_info->super_copy) != 0) + if (btrfs_super_log_root(fs_info->super_copy) != 0) { ret = -EINVAL; goto restore; + } ret = btrfs_cleanup_fs_roots(fs_info); if (ret) @@ -1165,6 +1187,10 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; + ret = btrfs_resume_balance_async(fs_info); + if (ret) + goto restore; + sb->s_flags &= ~MS_RDONLY; } @@ -1179,7 +1205,8 @@ restore: fs_info->compress_type = old_compress_type; fs_info->max_inline = old_max_inline; fs_info->alloc_start = old_alloc_start; - fs_info->thread_pool_size = old_thread_pool_size; + btrfs_resize_thread_pool(fs_info, + old_thread_pool_size, fs_info->thread_pool_size); fs_info->metadata_ratio = old_metadata_ratio; return ret; } @@ -1460,12 +1487,44 @@ static void btrfs_fs_dirty_inode(struct inode *inode, int flags) "error %d\n", btrfs_ino(inode), ret); } +static int btrfs_show_devname(struct seq_file *m, struct dentry *root) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); + struct btrfs_fs_devices *cur_devices; + struct btrfs_device *dev, *first_dev = NULL; + struct list_head *head; + struct rcu_string *name; + + mutex_lock(&fs_info->fs_devices->device_list_mutex); + cur_devices = fs_info->fs_devices; + while (cur_devices) { + head = &cur_devices->devices; + list_for_each_entry(dev, head, dev_list) { + if (!first_dev || dev->devid < first_dev->devid) + first_dev = dev; + } + cur_devices = cur_devices->seed; + } + + if (first_dev) { + rcu_read_lock(); + name = rcu_dereference(first_dev->name); + seq_escape(m, name->str, " \t\n\\"); + rcu_read_unlock(); + } else { + WARN_ON(1); + } + mutex_unlock(&fs_info->fs_devices->device_list_mutex); + return 0; +} + static const struct super_operations btrfs_super_ops = { .drop_inode = btrfs_drop_inode, .evict_inode = btrfs_evict_inode, .put_super = btrfs_put_super, .sync_fs = btrfs_sync_fs, .show_options = btrfs_show_options, + .show_devname = btrfs_show_devname, .write_inode = btrfs_write_inode, .dirty_inode = btrfs_fs_dirty_inode, .alloc_inode = btrfs_alloc_inode, diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 11b77a59db6..b72b068183e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -28,6 +28,7 @@ #include "locking.h" #include "tree-log.h" #include "inode-map.h" +#include "volumes.h" #define BTRFS_ROOT_TRANS_TAG 0 @@ -55,47 +56,54 @@ static noinline void switch_commit_root(struct btrfs_root *root) static noinline int join_transaction(struct btrfs_root *root, int nofail) { struct btrfs_transaction *cur_trans; + struct btrfs_fs_info *fs_info = root->fs_info; - spin_lock(&root->fs_info->trans_lock); + spin_lock(&fs_info->trans_lock); loop: /* The file system has been taken offline. No new transactions. */ - if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { - spin_unlock(&root->fs_info->trans_lock); + if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { + spin_unlock(&fs_info->trans_lock); return -EROFS; } - if (root->fs_info->trans_no_join) { + if (fs_info->trans_no_join) { if (!nofail) { - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); return -EBUSY; } } - cur_trans = root->fs_info->running_transaction; + cur_trans = fs_info->running_transaction; if (cur_trans) { - if (cur_trans->aborted) + if (cur_trans->aborted) { + spin_unlock(&fs_info->trans_lock); return cur_trans->aborted; + } atomic_inc(&cur_trans->use_count); atomic_inc(&cur_trans->num_writers); cur_trans->num_joined++; - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); return 0; } - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS); if (!cur_trans) return -ENOMEM; - spin_lock(&root->fs_info->trans_lock); - if (root->fs_info->running_transaction) { + spin_lock(&fs_info->trans_lock); + if (fs_info->running_transaction) { /* * someone started a transaction after we unlocked. Make sure * to redo the trans_no_join checks above */ kmem_cache_free(btrfs_transaction_cachep, cur_trans); - cur_trans = root->fs_info->running_transaction; + cur_trans = fs_info->running_transaction; goto loop; + } else if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { + spin_unlock(&root->fs_info->trans_lock); + kmem_cache_free(btrfs_transaction_cachep, cur_trans); + return -EROFS; } atomic_set(&cur_trans->num_writers, 1); @@ -119,20 +127,38 @@ loop: cur_trans->delayed_refs.flushing = 0; cur_trans->delayed_refs.run_delayed_start = 0; cur_trans->delayed_refs.seq = 1; + + /* + * although the tree mod log is per file system and not per transaction, + * the log must never go across transaction boundaries. + */ + smp_mb(); + if (!list_empty(&fs_info->tree_mod_seq_list)) { + printk(KERN_ERR "btrfs: tree_mod_seq_list not empty when " + "creating a fresh transaction\n"); + WARN_ON(1); + } + if (!RB_EMPTY_ROOT(&fs_info->tree_mod_log)) { + printk(KERN_ERR "btrfs: tree_mod_log rb tree not empty when " + "creating a fresh transaction\n"); + WARN_ON(1); + } + atomic_set(&fs_info->tree_mod_seq, 0); + init_waitqueue_head(&cur_trans->delayed_refs.seq_wait); spin_lock_init(&cur_trans->commit_lock); spin_lock_init(&cur_trans->delayed_refs.lock); INIT_LIST_HEAD(&cur_trans->delayed_refs.seq_head); INIT_LIST_HEAD(&cur_trans->pending_snapshots); - list_add_tail(&cur_trans->list, &root->fs_info->trans_list); + list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, - root->fs_info->btree_inode->i_mapping); - root->fs_info->generation++; - cur_trans->transid = root->fs_info->generation; - root->fs_info->running_transaction = cur_trans; + fs_info->btree_inode->i_mapping); + fs_info->generation++; + cur_trans->transid = fs_info->generation; + fs_info->running_transaction = cur_trans; cur_trans->aborted = 0; - spin_unlock(&root->fs_info->trans_lock); + spin_unlock(&fs_info->trans_lock); return 0; } @@ -756,6 +782,9 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, if (ret) return ret; + ret = btrfs_run_dev_stats(trans, root->fs_info); + BUG_ON(ret); + while (!list_empty(&fs_info->dirty_cowonly_roots)) { next = fs_info->dirty_cowonly_roots.next; list_del_init(next); @@ -1188,14 +1217,20 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans, static void cleanup_transaction(struct btrfs_trans_handle *trans, - struct btrfs_root *root) + struct btrfs_root *root, int err) { struct btrfs_transaction *cur_trans = trans->transaction; WARN_ON(trans->use_count > 1); + btrfs_abort_transaction(trans, root, err); + spin_lock(&root->fs_info->trans_lock); list_del_init(&cur_trans->list); + if (cur_trans == root->fs_info->running_transaction) { + root->fs_info->running_transaction = NULL; + root->fs_info->trans_no_join = 0; + } spin_unlock(&root->fs_info->trans_lock); btrfs_cleanup_one_transaction(trans->transaction, root); @@ -1400,6 +1435,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = commit_fs_roots(trans, root); if (ret) { mutex_unlock(&root->fs_info->tree_log_mutex); + mutex_unlock(&root->fs_info->reloc_mutex); goto cleanup_transaction; } @@ -1411,6 +1447,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, ret = commit_cowonly_roots(trans, root); if (ret) { mutex_unlock(&root->fs_info->tree_log_mutex); + mutex_unlock(&root->fs_info->reloc_mutex); goto cleanup_transaction; } @@ -1499,7 +1536,7 @@ cleanup_transaction: // WARN_ON(1); if (current->journal_info == trans) current->journal_info = NULL; - cleanup_transaction(trans, root); + cleanup_transaction(trans, root, ret); return ret; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d017283ae6f..8abeae4224f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -279,7 +279,7 @@ static int process_one_buffer(struct btrfs_root *log, log->fs_info->extent_root, eb->start, eb->len); - if (btrfs_buffer_uptodate(eb, gen)) { + if (btrfs_buffer_uptodate(eb, gen, 0)) { if (wc->write) btrfs_write_tree_block(eb); if (wc->wait) @@ -690,6 +690,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans, kfree(name); iput(inode); + + btrfs_run_delayed_items(trans, root); return ret; } @@ -895,6 +897,7 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, victim_name, victim_name_len); + btrfs_run_delayed_items(trans, root); } kfree(victim_name); ptr = (unsigned long)(victim_ref + 1) + victim_name_len; @@ -1475,6 +1478,9 @@ again: ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len); BUG_ON(ret); + + btrfs_run_delayed_items(trans, root); + kfree(name); iput(inode); @@ -1628,7 +1634,9 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, int i; int ret; - btrfs_read_buffer(eb, gen); + ret = btrfs_read_buffer(eb, gen); + if (ret) + return ret; level = btrfs_header_level(eb); @@ -1749,7 +1757,11 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, path->slots[*level]++; if (wc->free) { - btrfs_read_buffer(next, ptr_gen); + ret = btrfs_read_buffer(next, ptr_gen); + if (ret) { + free_extent_buffer(next); + return ret; + } btrfs_tree_lock(next); btrfs_set_lock_blocking(next); @@ -1766,7 +1778,11 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans, free_extent_buffer(next); continue; } - btrfs_read_buffer(next, ptr_gen); + ret = btrfs_read_buffer(next, ptr_gen); + if (ret) { + free_extent_buffer(next); + return ret; + } WARN_ON(*level <= 0); if (path->nodes[*level-1]) @@ -2657,6 +2673,8 @@ static int drop_objectid_items(struct btrfs_trans_handle *trans, btrfs_release_path(path); } btrfs_release_path(path); + if (ret > 0) + ret = 0; return ret; } @@ -3028,21 +3046,6 @@ out: return ret; } -static int inode_in_log(struct btrfs_trans_handle *trans, - struct inode *inode) -{ - struct btrfs_root *root = BTRFS_I(inode)->root; - int ret = 0; - - mutex_lock(&root->log_mutex); - if (BTRFS_I(inode)->logged_trans == trans->transid && - BTRFS_I(inode)->last_sub_trans <= root->last_log_commit) - ret = 1; - mutex_unlock(&root->log_mutex); - return ret; -} - - /* * helper function around btrfs_log_inode to make sure newly created * parent directories also end up in the log. A minimal inode and backref @@ -3083,7 +3086,7 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans, if (ret) goto end_no_trans; - if (inode_in_log(trans, inode)) { + if (btrfs_inode_in_log(inode, trans->transid)) { ret = BTRFS_NO_LOG_SYNC; goto end_no_trans; } diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c index 12f5147bd2b..ab942f46b3d 100644 --- a/fs/btrfs/ulist.c +++ b/fs/btrfs/ulist.c @@ -23,9 +23,9 @@ * * ulist = ulist_alloc(); * ulist_add(ulist, root); - * elem = NULL; + * ULIST_ITER_INIT(&uiter); * - * while ((elem = ulist_next(ulist, elem)) { + * while ((elem = ulist_next(ulist, &uiter)) { * for (all child nodes n in elem) * ulist_add(ulist, n); * do something useful with the node; @@ -95,7 +95,7 @@ EXPORT_SYMBOL(ulist_reinit); * * The allocated ulist will be returned in an initialized state. */ -struct ulist *ulist_alloc(unsigned long gfp_mask) +struct ulist *ulist_alloc(gfp_t gfp_mask) { struct ulist *ulist = kmalloc(sizeof(*ulist), gfp_mask); @@ -144,13 +144,22 @@ EXPORT_SYMBOL(ulist_free); * unaltered. */ int ulist_add(struct ulist *ulist, u64 val, unsigned long aux, - unsigned long gfp_mask) + gfp_t gfp_mask) +{ + return ulist_add_merge(ulist, val, aux, NULL, gfp_mask); +} + +int ulist_add_merge(struct ulist *ulist, u64 val, unsigned long aux, + unsigned long *old_aux, gfp_t gfp_mask) { int i; for (i = 0; i < ulist->nnodes; ++i) { - if (ulist->nodes[i].val == val) + if (ulist->nodes[i].val == val) { + if (old_aux) + *old_aux = ulist->nodes[i].aux; return 0; + } } if (ulist->nnodes >= ulist->nodes_alloced) { @@ -188,33 +197,26 @@ EXPORT_SYMBOL(ulist_add); /** * ulist_next - iterate ulist * @ulist: ulist to iterate - * @prev: previously returned element or %NULL to start iteration + * @uiter: iterator variable, initialized with ULIST_ITER_INIT(&iterator) * * Note: locking must be provided by the caller. In case of rwlocks only read * locking is needed * - * This function is used to iterate an ulist. The iteration is started with - * @prev = %NULL. It returns the next element from the ulist or %NULL when the + * This function is used to iterate an ulist. + * It returns the next element from the ulist or %NULL when the * end is reached. No guarantee is made with respect to the order in which * the elements are returned. They might neither be returned in order of * addition nor in ascending order. * It is allowed to call ulist_add during an enumeration. Newly added items * are guaranteed to show up in the running enumeration. */ -struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_node *prev) +struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter) { - int next; - if (ulist->nnodes == 0) return NULL; - - if (!prev) - return &ulist->nodes[0]; - - next = (prev - ulist->nodes) + 1; - if (next < 0 || next >= ulist->nnodes) + if (uiter->i < 0 || uiter->i >= ulist->nnodes) return NULL; - return &ulist->nodes[next]; + return &ulist->nodes[uiter->i++]; } EXPORT_SYMBOL(ulist_next); diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h index 2e25dec58ec..21bdc8ec813 100644 --- a/fs/btrfs/ulist.h +++ b/fs/btrfs/ulist.h @@ -24,6 +24,10 @@ */ #define ULIST_SIZE 16 +struct ulist_iterator { + int i; +}; + /* * element of the list */ @@ -59,10 +63,15 @@ struct ulist { void ulist_init(struct ulist *ulist); void ulist_fini(struct ulist *ulist); void ulist_reinit(struct ulist *ulist); -struct ulist *ulist_alloc(unsigned long gfp_mask); +struct ulist *ulist_alloc(gfp_t gfp_mask); void ulist_free(struct ulist *ulist); int ulist_add(struct ulist *ulist, u64 val, unsigned long aux, - unsigned long gfp_mask); -struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_node *prev); + gfp_t gfp_mask); +int ulist_add_merge(struct ulist *ulist, u64 val, unsigned long aux, + unsigned long *old_aux, gfp_t gfp_mask); +struct ulist_node *ulist_next(struct ulist *ulist, + struct ulist_iterator *uiter); + +#define ULIST_ITER_INIT(uiter) ((uiter)->i = 0) #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 759d02486d7..ecaad40e7ef 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -23,6 +23,7 @@ #include <linux/random.h> #include <linux/iocontext.h> #include <linux/capability.h> +#include <linux/ratelimit.h> #include <linux/kthread.h> #include <asm/div64.h> #include "compat.h" @@ -34,11 +35,14 @@ #include "volumes.h" #include "async-thread.h" #include "check-integrity.h" +#include "rcu-string.h" static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_device *device); static int btrfs_relocate_sys_chunks(struct btrfs_root *root); +static void __btrfs_reset_dev_stats(struct btrfs_device *dev); +static void btrfs_dev_stat_print_on_load(struct btrfs_device *device); static DEFINE_MUTEX(uuid_mutex); static LIST_HEAD(fs_uuids); @@ -61,7 +65,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices) device = list_entry(fs_devices->devices.next, struct btrfs_device, dev_list); list_del(&device->dev_list); - kfree(device->name); + rcu_string_free(device->name); kfree(device); } kfree(fs_devices); @@ -331,8 +335,8 @@ static noinline int device_list_add(const char *path, { struct btrfs_device *device; struct btrfs_fs_devices *fs_devices; + struct rcu_string *name; u64 found_transid = btrfs_super_generation(disk_super); - char *name; fs_devices = find_fsid(disk_super->fsid); if (!fs_devices) { @@ -361,15 +365,18 @@ static noinline int device_list_add(const char *path, return -ENOMEM; } device->devid = devid; + device->dev_stats_valid = 0; device->work.func = pending_bios_fn; memcpy(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); spin_lock_init(&device->io_lock); - device->name = kstrdup(path, GFP_NOFS); - if (!device->name) { + + name = rcu_string_strdup(path, GFP_NOFS); + if (!name) { kfree(device); return -ENOMEM; } + rcu_assign_pointer(device->name, name); INIT_LIST_HEAD(&device->dev_alloc_list); /* init readahead state */ @@ -386,12 +393,12 @@ static noinline int device_list_add(const char *path, device->fs_devices = fs_devices; fs_devices->num_devices++; - } else if (!device->name || strcmp(device->name, path)) { - name = kstrdup(path, GFP_NOFS); + } else if (!device->name || strcmp(device->name->str, path)) { + name = rcu_string_strdup(path, GFP_NOFS); if (!name) return -ENOMEM; - kfree(device->name); - device->name = name; + rcu_string_free(device->name); + rcu_assign_pointer(device->name, name); if (device->missing) { fs_devices->missing_devices--; device->missing = 0; @@ -426,15 +433,22 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) /* We have held the volume lock, it is safe to get the devices. */ list_for_each_entry(orig_dev, &orig->devices, dev_list) { + struct rcu_string *name; + device = kzalloc(sizeof(*device), GFP_NOFS); if (!device) goto error; - device->name = kstrdup(orig_dev->name, GFP_NOFS); - if (!device->name) { + /* + * This is ok to do without rcu read locked because we hold the + * uuid mutex so nothing we touch in here is going to disappear. + */ + name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS); + if (!name) { kfree(device); goto error; } + rcu_assign_pointer(device->name, name); device->devid = orig_dev->devid; device->work.func = pending_bios_fn; @@ -487,7 +501,7 @@ again: } list_del_init(&device->dev_list); fs_devices->num_devices--; - kfree(device->name); + rcu_string_free(device->name); kfree(device); } @@ -512,7 +526,7 @@ static void __free_device(struct work_struct *work) if (device->bdev) blkdev_put(device->bdev, device->mode); - kfree(device->name); + rcu_string_free(device->name); kfree(device); } @@ -536,6 +550,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) mutex_lock(&fs_devices->device_list_mutex); list_for_each_entry(device, &fs_devices->devices, dev_list) { struct btrfs_device *new_device; + struct rcu_string *name; if (device->bdev) fs_devices->open_devices--; @@ -551,8 +566,11 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) new_device = kmalloc(sizeof(*new_device), GFP_NOFS); BUG_ON(!new_device); /* -ENOMEM */ memcpy(new_device, device, sizeof(*new_device)); - new_device->name = kstrdup(device->name, GFP_NOFS); - BUG_ON(device->name && !new_device->name); /* -ENOMEM */ + + /* Safe because we are under uuid_mutex */ + name = rcu_string_strdup(device->name->str, GFP_NOFS); + BUG_ON(device->name && !name); /* -ENOMEM */ + rcu_assign_pointer(new_device->name, name); new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; @@ -617,9 +635,9 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, if (!device->name) continue; - bdev = blkdev_get_by_path(device->name, flags, holder); + bdev = blkdev_get_by_path(device->name->str, flags, holder); if (IS_ERR(bdev)) { - printk(KERN_INFO "open %s failed\n", device->name); + printk(KERN_INFO "open %s failed\n", device->name->str); goto error; } filemap_write_and_wait(bdev->bd_inode->i_mapping); @@ -1628,12 +1646,13 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) struct block_device *bdev; struct list_head *devices; struct super_block *sb = root->fs_info->sb; + struct rcu_string *name; u64 total_bytes; int seeding_dev = 0; int ret = 0; if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding) - return -EINVAL; + return -EROFS; bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, root->fs_info->bdev_holder); @@ -1667,23 +1686,24 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) goto error; } - device->name = kstrdup(device_path, GFP_NOFS); - if (!device->name) { + name = rcu_string_strdup(device_path, GFP_NOFS); + if (!name) { kfree(device); ret = -ENOMEM; goto error; } + rcu_assign_pointer(device->name, name); ret = find_next_devid(root, &device->devid); if (ret) { - kfree(device->name); + rcu_string_free(device->name); kfree(device); goto error; } trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { - kfree(device->name); + rcu_string_free(device->name); kfree(device); ret = PTR_ERR(trans); goto error; @@ -1792,7 +1812,7 @@ error_trans: unlock_chunks(root); btrfs_abort_transaction(trans, root, ret); btrfs_end_transaction(trans, root); - kfree(device->name); + rcu_string_free(device->name); kfree(device); error: blkdev_put(bdev, FMODE_EXCL); @@ -2825,31 +2845,48 @@ out: static int balance_kthread(void *data) { - struct btrfs_balance_control *bctl = - (struct btrfs_balance_control *)data; - struct btrfs_fs_info *fs_info = bctl->fs_info; + struct btrfs_fs_info *fs_info = data; int ret = 0; mutex_lock(&fs_info->volume_mutex); mutex_lock(&fs_info->balance_mutex); - set_balance_control(bctl); - - if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { - printk(KERN_INFO "btrfs: force skipping balance\n"); - } else { + if (fs_info->balance_ctl) { printk(KERN_INFO "btrfs: continuing balance\n"); - ret = btrfs_balance(bctl, NULL); + ret = btrfs_balance(fs_info->balance_ctl, NULL); } mutex_unlock(&fs_info->balance_mutex); mutex_unlock(&fs_info->volume_mutex); + return ret; } -int btrfs_recover_balance(struct btrfs_root *tree_root) +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info) { struct task_struct *tsk; + + spin_lock(&fs_info->balance_lock); + if (!fs_info->balance_ctl) { + spin_unlock(&fs_info->balance_lock); + return 0; + } + spin_unlock(&fs_info->balance_lock); + + if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) { + printk(KERN_INFO "btrfs: force skipping balance\n"); + return 0; + } + + tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance"); + if (IS_ERR(tsk)) + return PTR_ERR(tsk); + + return 0; +} + +int btrfs_recover_balance(struct btrfs_fs_info *fs_info) +{ struct btrfs_balance_control *bctl; struct btrfs_balance_item *item; struct btrfs_disk_balance_args disk_bargs; @@ -2862,29 +2899,30 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) if (!path) return -ENOMEM; - bctl = kzalloc(sizeof(*bctl), GFP_NOFS); - if (!bctl) { - ret = -ENOMEM; - goto out; - } - key.objectid = BTRFS_BALANCE_OBJECTID; key.type = BTRFS_BALANCE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0); + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); if (ret < 0) - goto out_bctl; + goto out; if (ret > 0) { /* ret = -ENOENT; */ ret = 0; - goto out_bctl; + goto out; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out; } leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item); - bctl->fs_info = tree_root->fs_info; - bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME; + bctl->fs_info = fs_info; + bctl->flags = btrfs_balance_flags(leaf, item); + bctl->flags |= BTRFS_BALANCE_RESUME; btrfs_balance_data(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs); @@ -2893,14 +2931,13 @@ int btrfs_recover_balance(struct btrfs_root *tree_root) btrfs_balance_sys(leaf, item, &disk_bargs); btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs); - tsk = kthread_run(balance_kthread, bctl, "btrfs-balance"); - if (IS_ERR(tsk)) - ret = PTR_ERR(tsk); - else - goto out; + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); -out_bctl: - kfree(bctl); + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); out: btrfs_free_path(path); return ret; @@ -3324,12 +3361,14 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; num_stripes = ndevs * dev_stripes; - if (stripe_size * num_stripes > max_chunk_size * ncopies) { + if (stripe_size * ndevs > max_chunk_size * ncopies) { stripe_size = max_chunk_size * ncopies; - do_div(stripe_size, num_stripes); + do_div(stripe_size, ndevs); } do_div(stripe_size, dev_stripes); + + /* align to BTRFS_STRIPE_LEN */ do_div(stripe_size, BTRFS_STRIPE_LEN); stripe_size *= BTRFS_STRIPE_LEN; @@ -3805,10 +3844,11 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, else if (mirror_num) stripe_index += mirror_num - 1; else { + int old_stripe_index = stripe_index; stripe_index = find_live_mirror(map, stripe_index, map->sub_stripes, stripe_index + current->pid % map->sub_stripes); - mirror_num = stripe_index + 1; + mirror_num = stripe_index - old_stripe_index + 1; } } else { /* @@ -3998,13 +4038,60 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } +static void *merge_stripe_index_into_bio_private(void *bi_private, + unsigned int stripe_index) +{ + /* + * with single, dup, RAID0, RAID1 and RAID10, stripe_index is + * at most 1. + * The alternative solution (instead of stealing bits from the + * pointer) would be to allocate an intermediate structure + * that contains the old private pointer plus the stripe_index. + */ + BUG_ON((((uintptr_t)bi_private) & 3) != 0); + BUG_ON(stripe_index > 3); + return (void *)(((uintptr_t)bi_private) | stripe_index); +} + +static struct btrfs_bio *extract_bbio_from_bio_private(void *bi_private) +{ + return (struct btrfs_bio *)(((uintptr_t)bi_private) & ~((uintptr_t)3)); +} + +static unsigned int extract_stripe_index_from_bio_private(void *bi_private) +{ + return (unsigned int)((uintptr_t)bi_private) & 3; +} + static void btrfs_end_bio(struct bio *bio, int err) { - struct btrfs_bio *bbio = bio->bi_private; + struct btrfs_bio *bbio = extract_bbio_from_bio_private(bio->bi_private); int is_orig_bio = 0; - if (err) + if (err) { atomic_inc(&bbio->error); + if (err == -EIO || err == -EREMOTEIO) { + unsigned int stripe_index = + extract_stripe_index_from_bio_private( + bio->bi_private); + struct btrfs_device *dev; + + BUG_ON(stripe_index >= bbio->num_stripes); + dev = bbio->stripes[stripe_index].dev; + if (dev->bdev) { + if (bio->bi_rw & WRITE) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_WRITE_ERRS); + else + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_READ_ERRS); + if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); + btrfs_dev_stat_print_on_error(dev); + } + } + } if (bio == bbio->orig_bio) is_orig_bio = 1; @@ -4146,14 +4233,23 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, bio = first_bio; } bio->bi_private = bbio; + bio->bi_private = merge_stripe_index_into_bio_private( + bio->bi_private, (unsigned int)dev_nr); bio->bi_end_io = btrfs_end_bio; bio->bi_sector = bbio->stripes[dev_nr].physical >> 9; dev = bbio->stripes[dev_nr].dev; if (dev && dev->bdev && (rw != WRITE || dev->writeable)) { +#ifdef DEBUG + struct rcu_string *name; + + rcu_read_lock(); + name = rcu_dereference(dev->name); pr_debug("btrfs_map_bio: rw %d, secor=%llu, dev=%lu " "(%s id %llu), size=%u\n", rw, (u64)bio->bi_sector, (u_long)dev->bdev->bd_dev, - dev->name, dev->devid, bio->bi_size); + name->str, dev->devid, bio->bi_size); + rcu_read_unlock(); +#endif bio->bi_bdev = dev->bdev; if (async_submit) schedule_bio(root, dev, rw, bio); @@ -4350,8 +4446,10 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid) ret = __btrfs_open_devices(fs_devices, FMODE_READ, root->fs_info->bdev_holder); - if (ret) + if (ret) { + free_fs_devices(fs_devices); goto out; + } if (!fs_devices->seeding) { __btrfs_close_devices(fs_devices); @@ -4504,6 +4602,28 @@ int btrfs_read_sys_array(struct btrfs_root *root) return ret; } +struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, + u64 logical, int mirror_num) +{ + struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree; + int ret; + u64 map_length = 0; + struct btrfs_bio *bbio = NULL; + struct btrfs_device *device; + + BUG_ON(mirror_num == 0); + ret = btrfs_map_block(map_tree, WRITE, logical, &map_length, &bbio, + mirror_num); + if (ret) { + BUG_ON(bbio != NULL); + return NULL; + } + BUG_ON(mirror_num != bbio->mirror_num); + device = bbio->stripes[mirror_num - 1].dev; + kfree(bbio); + return device; +} + int btrfs_read_chunk_tree(struct btrfs_root *root) { struct btrfs_path *path; @@ -4578,3 +4698,231 @@ error: btrfs_free_path(path); return ret; } + +static void __btrfs_reset_dev_stats(struct btrfs_device *dev) +{ + int i; + + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + btrfs_dev_stat_reset(dev, i); +} + +int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info) +{ + struct btrfs_key key; + struct btrfs_key found_key; + struct btrfs_root *dev_root = fs_info->dev_root; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct extent_buffer *eb; + int slot; + int ret = 0; + struct btrfs_device *device; + struct btrfs_path *path = NULL; + int i; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + int item_size; + struct btrfs_dev_stats_item *ptr; + + key.objectid = 0; + key.type = BTRFS_DEV_STATS_KEY; + key.offset = device->devid; + ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); + if (ret) { + printk_in_rcu(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n", + rcu_str_deref(device->name), + (unsigned long long)device->devid); + __btrfs_reset_dev_stats(device); + device->dev_stats_valid = 1; + btrfs_release_path(path); + continue; + } + slot = path->slots[0]; + eb = path->nodes[0]; + btrfs_item_key_to_cpu(eb, &found_key, slot); + item_size = btrfs_item_size_nr(eb, slot); + + ptr = btrfs_item_ptr(eb, slot, + struct btrfs_dev_stats_item); + + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) { + if (item_size >= (1 + i) * sizeof(__le64)) + btrfs_dev_stat_set(device, i, + btrfs_dev_stats_value(eb, ptr, i)); + else + btrfs_dev_stat_reset(device, i); + } + + device->dev_stats_valid = 1; + btrfs_dev_stat_print_on_load(device); + btrfs_release_path(path); + } + mutex_unlock(&fs_devices->device_list_mutex); + +out: + btrfs_free_path(path); + return ret < 0 ? ret : 0; +} + +static int update_dev_stat_item(struct btrfs_trans_handle *trans, + struct btrfs_root *dev_root, + struct btrfs_device *device) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct extent_buffer *eb; + struct btrfs_dev_stats_item *ptr; + int ret; + int i; + + key.objectid = 0; + key.type = BTRFS_DEV_STATS_KEY; + key.offset = device->devid; + + path = btrfs_alloc_path(); + BUG_ON(!path); + ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); + if (ret < 0) { + printk_in_rcu(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n", + ret, rcu_str_deref(device->name)); + goto out; + } + + if (ret == 0 && + btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) { + /* need to delete old one and insert a new one */ + ret = btrfs_del_item(trans, dev_root, path); + if (ret != 0) { + printk_in_rcu(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n", + rcu_str_deref(device->name), ret); + goto out; + } + ret = 1; + } + + if (ret == 1) { + /* need to insert a new item */ + btrfs_release_path(path); + ret = btrfs_insert_empty_item(trans, dev_root, path, + &key, sizeof(*ptr)); + if (ret < 0) { + printk_in_rcu(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n", + rcu_str_deref(device->name), ret); + goto out; + } + } + + eb = path->nodes[0]; + ptr = btrfs_item_ptr(eb, path->slots[0], struct btrfs_dev_stats_item); + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + btrfs_set_dev_stats_value(eb, ptr, i, + btrfs_dev_stat_read(device, i)); + btrfs_mark_buffer_dirty(eb); + +out: + btrfs_free_path(path); + return ret; +} + +/* + * called from commit_transaction. Writes all changed device stats to disk. + */ +int btrfs_run_dev_stats(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *dev_root = fs_info->dev_root; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + int ret = 0; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->dev_stats_valid || !device->dev_stats_dirty) + continue; + + ret = update_dev_stat_item(trans, dev_root, device); + if (!ret) + device->dev_stats_dirty = 0; + } + mutex_unlock(&fs_devices->device_list_mutex); + + return ret; +} + +void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index) +{ + btrfs_dev_stat_inc(dev, index); + btrfs_dev_stat_print_on_error(dev); +} + +void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) +{ + if (!dev->dev_stats_valid) + return; + printk_ratelimited_in_rcu(KERN_ERR + "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + rcu_str_deref(dev->name), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), + btrfs_dev_stat_read(dev, + BTRFS_DEV_STAT_CORRUPTION_ERRS), + btrfs_dev_stat_read(dev, + BTRFS_DEV_STAT_GENERATION_ERRS)); +} + +static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev) +{ + printk_in_rcu(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + rcu_str_deref(dev->name), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS)); +} + +int btrfs_get_dev_stats(struct btrfs_root *root, + struct btrfs_ioctl_get_dev_stats *stats, + int reset_after_read) +{ + struct btrfs_device *dev; + struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; + int i; + + mutex_lock(&fs_devices->device_list_mutex); + dev = btrfs_find_device(root, stats->devid, NULL, NULL); + mutex_unlock(&fs_devices->device_list_mutex); + + if (!dev) { + printk(KERN_WARNING + "btrfs: get dev_stats failed, device not found\n"); + return -ENODEV; + } else if (!dev->dev_stats_valid) { + printk(KERN_WARNING + "btrfs: get dev_stats failed, not yet valid\n"); + return -ENODEV; + } else if (reset_after_read) { + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) { + if (stats->nr_items > i) + stats->values[i] = + btrfs_dev_stat_read_and_reset(dev, i); + else + btrfs_dev_stat_reset(dev, i); + } + } else { + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + if (stats->nr_items > i) + stats->values[i] = btrfs_dev_stat_read(dev, i); + } + if (stats->nr_items > BTRFS_DEV_STAT_VALUES_MAX) + stats->nr_items = BTRFS_DEV_STAT_VALUES_MAX; + return 0; +} diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index bb6b03f97aa..95f6637614d 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -22,6 +22,7 @@ #include <linux/bio.h> #include <linux/sort.h> #include "async-thread.h" +#include "ioctl.h" #define BTRFS_STRIPE_LEN (64 * 1024) @@ -57,7 +58,7 @@ struct btrfs_device { /* the mode sent to blkdev_get */ fmode_t mode; - char *name; + struct rcu_string *name; /* the internal btrfs device id */ u64 devid; @@ -106,6 +107,11 @@ struct btrfs_device { struct completion flush_wait; int nobarriers; + /* disk I/O failure stats. For detailed description refer to + * enum btrfs_dev_stat_values in ioctl.h */ + int dev_stats_valid; + int dev_stats_dirty; /* counters need to be written to disk */ + atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX]; }; struct btrfs_fs_devices { @@ -275,10 +281,57 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); -int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info); +int btrfs_recover_balance(struct btrfs_fs_info *fs_info); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *max_avail); +struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, + u64 logical, int mirror_num); +void btrfs_dev_stat_print_on_error(struct btrfs_device *device); +void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); +int btrfs_get_dev_stats(struct btrfs_root *root, + struct btrfs_ioctl_get_dev_stats *stats, + int reset_after_read); +int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info); +int btrfs_run_dev_stats(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info); + +static inline void btrfs_dev_stat_inc(struct btrfs_device *dev, + int index) +{ + atomic_inc(dev->dev_stat_values + index); + dev->dev_stats_dirty = 1; +} + +static inline int btrfs_dev_stat_read(struct btrfs_device *dev, + int index) +{ + return atomic_read(dev->dev_stat_values + index); +} + +static inline int btrfs_dev_stat_read_and_reset(struct btrfs_device *dev, + int index) +{ + int ret; + + ret = atomic_xchg(dev->dev_stat_values + index, 0); + dev->dev_stats_dirty = 1; + return ret; +} + +static inline void btrfs_dev_stat_set(struct btrfs_device *dev, + int index, unsigned long val) +{ + atomic_set(dev->dev_stat_values + index, val); + dev->dev_stats_dirty = 1; +} + +static inline void btrfs_dev_stat_reset(struct btrfs_device *dev, + int index) +{ + btrfs_dev_stat_set(dev, index, 0); +} #endif diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index e7a5659087e..3f4e2d69e83 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -196,6 +196,7 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans, if (ret) goto out; + inode_inc_iversion(inode); inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); diff --git a/fs/buffer.c b/fs/buffer.c index 36d66653b93..838a9cf246b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -921,6 +921,7 @@ init_page_buffers(struct page *page, struct block_device *bdev, struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); + sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode)); do { if (!buffer_mapped(bh)) { @@ -929,7 +930,8 @@ init_page_buffers(struct page *page, struct block_device *bdev, bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); - set_buffer_mapped(bh); + if (block < end_block) + set_buffer_mapped(bh); } block++; bh = bh->b_this_page; @@ -985,7 +987,6 @@ grow_dev_page(struct block_device *bdev, sector_t block, return page; failed: - BUG(); unlock_page(page); page_cache_release(page); return NULL; @@ -3151,7 +3152,7 @@ SYSCALL_DEFINE2(bdflush, int, func, long, data) /* * Buffer-head allocation */ -static struct kmem_cache *bh_cachep; +static struct kmem_cache *bh_cachep __read_mostly; /* * Once the number of bh's in the machine exceeds this level, we start diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 173b1d22e59..8b67304e4b8 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -54,7 +54,12 @@ (CONGESTION_ON_THRESH(congestion_kb) - \ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) - +static inline struct ceph_snap_context *page_snap_context(struct page *page) +{ + if (PagePrivate(page)) + return (void *)page->private; + return NULL; +} /* * Dirty a page. Optimistically adjust accounting, on the assumption @@ -142,10 +147,9 @@ static void ceph_invalidatepage(struct page *page, unsigned long offset) { struct inode *inode; struct ceph_inode_info *ci; - struct ceph_snap_context *snapc = (void *)page->private; + struct ceph_snap_context *snapc = page_snap_context(page); BUG_ON(!PageLocked(page)); - BUG_ON(!page->private); BUG_ON(!PagePrivate(page)); BUG_ON(!page->mapping); @@ -182,7 +186,6 @@ static int ceph_releasepage(struct page *page, gfp_t g) struct inode *inode = page->mapping ? page->mapping->host : NULL; dout("%p releasepage %p idx %lu\n", inode, page, page->index); WARN_ON(PageDirty(page)); - WARN_ON(page->private); WARN_ON(PagePrivate(page)); return 0; } @@ -443,7 +446,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) osdc = &fsc->client->osdc; /* verify this is a writeable snap context */ - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc == NULL) { dout("writepage %p page %p not dirty?\n", inode, page); goto out; @@ -451,7 +454,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) oldest = get_oldest_context(inode, &snap_size); if (snapc->seq > oldest->seq) { dout("writepage %p page %p snapc %p not writeable - noop\n", - inode, page, (void *)page->private); + inode, page, snapc); /* we should only noop if called by kswapd */ WARN_ON((current->flags & PF_MEMALLOC) == 0); ceph_put_snap_context(oldest); @@ -591,7 +594,7 @@ static void writepages_finish(struct ceph_osd_request *req, clear_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC); - ceph_put_snap_context((void *)page->private); + ceph_put_snap_context(page_snap_context(page)); page->private = 0; ClearPagePrivate(page); dout("unlocking %d %p\n", i, page); @@ -795,7 +798,7 @@ get_more_pages: } /* only if matching snap context */ - pgsnapc = (void *)page->private; + pgsnapc = page_snap_context(page); if (pgsnapc->seq > snapc->seq) { dout("page snapc %p %lld > oldest %p %lld\n", pgsnapc, pgsnapc->seq, snapc, snapc->seq); @@ -984,7 +987,7 @@ retry_locked: BUG_ON(!ci->i_snap_realm); down_read(&mdsc->snap_rwsem); BUG_ON(!ci->i_snap_realm->cached_context); - snapc = (void *)page->private; + snapc = page_snap_context(page); if (snapc && snapc != ci->i_head_snapc) { /* * this page is already dirty in another (older) snap diff --git a/fs/ceph/export.c b/fs/ceph/export.c index fbb2a643ef1..8e1b60e557b 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -40,38 +40,49 @@ struct ceph_nfs_confh { u32 parent_name_hash; } __attribute__ ((packed)); -static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len, - int connectable) +/* + * The presence of @parent_inode here tells us whether NFS wants a + * connectable file handle. However, we want to make a connectionable + * file handle unconditionally so that the MDS gets as much of a hint + * as possible. That means we only use @parent_dentry to indicate + * whether nfsd wants a connectable fh, and whether we should indicate + * failure from a too-small @max_len. + */ +static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, + struct inode *parent_inode) { int type; struct ceph_nfs_fh *fh = (void *)rawfh; struct ceph_nfs_confh *cfh = (void *)rawfh; - struct dentry *parent; - struct inode *inode = dentry->d_inode; int connected_handle_length = sizeof(*cfh)/4; int handle_length = sizeof(*fh)/4; + struct dentry *dentry = d_find_alias(inode); + struct dentry *parent; /* don't re-export snaps */ if (ceph_snap(inode) != CEPH_NOSNAP) return -EINVAL; - spin_lock(&dentry->d_lock); - parent = dentry->d_parent; - if (*max_len >= connected_handle_length) { + /* if we found an alias, generate a connectable fh */ + if (*max_len >= connected_handle_length && dentry) { dout("encode_fh %p connectable\n", dentry); - cfh->ino = ceph_ino(dentry->d_inode); + spin_lock(&dentry->d_lock); + parent = dentry->d_parent; + cfh->ino = ceph_ino(inode); cfh->parent_ino = ceph_ino(parent->d_inode); cfh->parent_name_hash = ceph_dentry_hash(parent->d_inode, dentry); *max_len = connected_handle_length; type = 2; + spin_unlock(&dentry->d_lock); } else if (*max_len >= handle_length) { - if (connectable) { + if (parent_inode) { + /* nfsd wants connectable */ *max_len = connected_handle_length; type = 255; } else { dout("encode_fh %p\n", dentry); - fh->ino = ceph_ino(dentry->d_inode); + fh->ino = ceph_ino(inode); *max_len = handle_length; type = 1; } @@ -79,7 +90,6 @@ static int ceph_encode_fh(struct dentry *dentry, u32 *rawfh, int *max_len, *max_len = handle_length; type = 255; } - spin_unlock(&dentry->d_lock); return type; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ed72428d9c7..988d4f302e4 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -54,7 +54,6 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode) req->r_fmode = ceph_flags_to_mode(flags); req->r_args.open.flags = cpu_to_le32(flags); req->r_args.open.mode = cpu_to_le32(create_mode); - req->r_args.open.preferred = cpu_to_le32(-1); out: return req; } diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 790914a598d..8e3fb69fbe6 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -26,8 +26,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg) l.stripe_count = ceph_file_layout_stripe_count(ci->i_layout); l.object_size = ceph_file_layout_object_size(ci->i_layout); l.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool); - l.preferred_osd = - (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred); + l.preferred_osd = (s32)-1; if (copy_to_user(arg, &l, sizeof(l))) return -EFAULT; } @@ -35,6 +34,32 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg) return err; } +static long __validate_layout(struct ceph_mds_client *mdsc, + struct ceph_ioctl_layout *l) +{ + int i, err; + + /* validate striping parameters */ + if ((l->object_size & ~PAGE_MASK) || + (l->stripe_unit & ~PAGE_MASK) || + ((unsigned)l->object_size % (unsigned)l->stripe_unit)) + return -EINVAL; + + /* make sure it's a valid data pool */ + mutex_lock(&mdsc->mutex); + err = -EINVAL; + for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++) + if (mdsc->mdsmap->m_data_pg_pools[i] == l->data_pool) { + err = 0; + break; + } + mutex_unlock(&mdsc->mutex); + if (err) + return err; + + return 0; +} + static long ceph_ioctl_set_layout(struct file *file, void __user *arg) { struct inode *inode = file->f_dentry->d_inode; @@ -44,52 +69,40 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) struct ceph_ioctl_layout l; struct ceph_inode_info *ci = ceph_inode(file->f_dentry->d_inode); struct ceph_ioctl_layout nl; - int err, i; + int err; if (copy_from_user(&l, arg, sizeof(l))) return -EFAULT; /* validate changed params against current layout */ err = ceph_do_getattr(file->f_dentry->d_inode, CEPH_STAT_CAP_LAYOUT); - if (!err) { - nl.stripe_unit = ceph_file_layout_su(ci->i_layout); - nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout); - nl.object_size = ceph_file_layout_object_size(ci->i_layout); - nl.data_pool = le32_to_cpu(ci->i_layout.fl_pg_pool); - nl.preferred_osd = - (s32)le32_to_cpu(ci->i_layout.fl_pg_preferred); - } else + if (err) return err; + memset(&nl, 0, sizeof(nl)); if (l.stripe_count) nl.stripe_count = l.stripe_count; + else + nl.stripe_count = ceph_file_layout_stripe_count(ci->i_layout); if (l.stripe_unit) nl.stripe_unit = l.stripe_unit; + else + nl.stripe_unit = ceph_file_layout_su(ci->i_layout); if (l.object_size) nl.object_size = l.object_size; + else + nl.object_size = ceph_file_layout_object_size(ci->i_layout); if (l.data_pool) nl.data_pool = l.data_pool; - if (l.preferred_osd) - nl.preferred_osd = l.preferred_osd; + else + nl.data_pool = ceph_file_layout_pg_pool(ci->i_layout); - if ((nl.object_size & ~PAGE_MASK) || - (nl.stripe_unit & ~PAGE_MASK) || - ((unsigned)nl.object_size % (unsigned)nl.stripe_unit)) - return -EINVAL; + /* this is obsolete, and always -1 */ + nl.preferred_osd = le64_to_cpu(-1); - /* make sure it's a valid data pool */ - if (l.data_pool > 0) { - mutex_lock(&mdsc->mutex); - err = -EINVAL; - for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++) - if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) { - err = 0; - break; - } - mutex_unlock(&mdsc->mutex); - if (err) - return err; - } + err = __validate_layout(mdsc, &nl); + if (err) + return err; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETLAYOUT, USE_AUTH_MDS); @@ -106,8 +119,6 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) req->r_args.setlayout.layout.fl_object_size = cpu_to_le32(l.object_size); req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool); - req->r_args.setlayout.layout.fl_pg_preferred = - cpu_to_le32(l.preferred_osd); parent_inode = ceph_get_dentry_parent_inode(file->f_dentry); err = ceph_mdsc_do_request(mdsc, parent_inode, req); @@ -127,33 +138,16 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg) struct inode *inode = file->f_dentry->d_inode; struct ceph_mds_request *req; struct ceph_ioctl_layout l; - int err, i; + int err; struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc; /* copy and validate */ if (copy_from_user(&l, arg, sizeof(l))) return -EFAULT; - if ((l.object_size & ~PAGE_MASK) || - (l.stripe_unit & ~PAGE_MASK) || - !l.stripe_unit || - (l.object_size && - (unsigned)l.object_size % (unsigned)l.stripe_unit)) - return -EINVAL; - - /* make sure it's a valid data pool */ - if (l.data_pool > 0) { - mutex_lock(&mdsc->mutex); - err = -EINVAL; - for (i = 0; i < mdsc->mdsmap->m_num_data_pg_pools; i++) - if (mdsc->mdsmap->m_data_pg_pools[i] == l.data_pool) { - err = 0; - break; - } - mutex_unlock(&mdsc->mutex); - if (err) - return err; - } + err = __validate_layout(mdsc, &l); + if (err) + return err; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETDIRLAYOUT, USE_AUTH_MDS); @@ -171,8 +165,6 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg) cpu_to_le32(l.object_size); req->r_args.setlayout.layout.fl_pg_pool = cpu_to_le32(l.data_pool); - req->r_args.setlayout.layout.fl_pg_preferred = - cpu_to_le32(l.preferred_osd); err = ceph_mdsc_do_request(mdsc, inode, req); ceph_mdsc_put_request(req); diff --git a/fs/ceph/ioctl.h b/fs/ceph/ioctl.h index be4a6048733..c77028afb1e 100644 --- a/fs/ceph/ioctl.h +++ b/fs/ceph/ioctl.h @@ -34,6 +34,8 @@ struct ceph_ioctl_layout { __u64 stripe_unit, stripe_count, object_size; __u64 data_pool; + + /* obsolete. new values ignored, always return -1 */ __s64 preferred_osd; }; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 89971e137aa..200bc87eceb 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -334,10 +334,10 @@ void ceph_put_mds_session(struct ceph_mds_session *s) dout("mdsc put_session %p %d -> %d\n", s, atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1); if (atomic_dec_and_test(&s->s_ref)) { - if (s->s_authorizer) + if (s->s_auth.authorizer) s->s_mdsc->fsc->client->monc.auth->ops->destroy_authorizer( s->s_mdsc->fsc->client->monc.auth, - s->s_authorizer); + s->s_auth.authorizer); kfree(s); } } @@ -3395,39 +3395,33 @@ out: /* * authentication */ -static int get_authorizer(struct ceph_connection *con, - void **buf, int *len, int *proto, - void **reply_buf, int *reply_len, int force_new) + +/* + * Note: returned pointer is the address of a structure that's + * managed separately. Caller must *not* attempt to free it. + */ +static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con, + int *proto, int force_new) { struct ceph_mds_session *s = con->private; struct ceph_mds_client *mdsc = s->s_mdsc; struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth; - int ret = 0; - - if (force_new && s->s_authorizer) { - ac->ops->destroy_authorizer(ac, s->s_authorizer); - s->s_authorizer = NULL; - } - if (s->s_authorizer == NULL) { - if (ac->ops->create_authorizer) { - ret = ac->ops->create_authorizer( - ac, CEPH_ENTITY_TYPE_MDS, - &s->s_authorizer, - &s->s_authorizer_buf, - &s->s_authorizer_buf_len, - &s->s_authorizer_reply_buf, - &s->s_authorizer_reply_buf_len); - if (ret) - return ret; - } - } + struct ceph_auth_handshake *auth = &s->s_auth; + if (force_new && auth->authorizer) { + if (ac->ops && ac->ops->destroy_authorizer) + ac->ops->destroy_authorizer(ac, auth->authorizer); + auth->authorizer = NULL; + } + if (!auth->authorizer && ac->ops && ac->ops->create_authorizer) { + int ret = ac->ops->create_authorizer(ac, CEPH_ENTITY_TYPE_MDS, + auth); + if (ret) + return ERR_PTR(ret); + } *proto = ac->protocol; - *buf = s->s_authorizer_buf; - *len = s->s_authorizer_buf_len; - *reply_buf = s->s_authorizer_reply_buf; - *reply_len = s->s_authorizer_reply_buf_len; - return 0; + + return auth; } @@ -3437,7 +3431,7 @@ static int verify_authorizer_reply(struct ceph_connection *con, int len) struct ceph_mds_client *mdsc = s->s_mdsc; struct ceph_auth_client *ac = mdsc->fsc->client->monc.auth; - return ac->ops->verify_authorizer_reply(ac, s->s_authorizer, len); + return ac->ops->verify_authorizer_reply(ac, s->s_auth.authorizer, len); } static int invalidate_authorizer(struct ceph_connection *con) diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 8c7c04ebb59..dd26846dd71 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -11,6 +11,7 @@ #include <linux/ceph/types.h> #include <linux/ceph/messenger.h> #include <linux/ceph/mdsmap.h> +#include <linux/ceph/auth.h> /* * Some lock dependencies: @@ -113,9 +114,7 @@ struct ceph_mds_session { struct ceph_connection s_con; - struct ceph_authorizer *s_authorizer; - void *s_authorizer_buf, *s_authorizer_reply_buf; - size_t s_authorizer_buf_len, s_authorizer_reply_buf_len; + struct ceph_auth_handshake s_auth; /* protected by s_gen_ttl_lock */ spinlock_t s_gen_ttl_lock; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index f04c0961f99..e5206fc7656 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -331,7 +331,7 @@ static int build_snap_context(struct ceph_snap_realm *realm) /* alloc new snap context */ err = -ENOMEM; - if (num > (ULONG_MAX - sizeof(*snapc)) / sizeof(u64)) + if (num > (SIZE_MAX - sizeof(*snapc)) / sizeof(u64)) goto fail; snapc = kzalloc(sizeof(*snapc) + num*sizeof(u64), GFP_NOFS); if (!snapc) diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 35b86331d8a..785cb3057c9 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -118,15 +118,6 @@ static size_t ceph_vxattrcb_file_layout(struct ceph_inode_info *ci, char *val, (unsigned long long)ceph_file_layout_su(ci->i_layout), (unsigned long long)ceph_file_layout_stripe_count(ci->i_layout), (unsigned long long)ceph_file_layout_object_size(ci->i_layout)); - - if (ceph_file_layout_pg_preferred(ci->i_layout) >= 0) { - val += ret; - size -= ret; - ret += snprintf(val, size, "preferred_osd=%lld\n", - (unsigned long long)ceph_file_layout_pg_preferred( - ci->i_layout)); - } - return ret; } diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 2b243af70aa..a08306a8bec 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -158,3 +158,23 @@ config CIFS_NFSD_EXPORT depends on CIFS && EXPERIMENTAL && BROKEN help Allows NFS server to export a CIFS mounted share (nfsd over cifs) + +config CIFS_SMB2 + bool "SMB2 network file system support (EXPERIMENTAL)" + depends on EXPERIMENTAL && INET && BROKEN + select NLS + select KEYS + select FSCACHE + select DNS_RESOLVER + + help + This enables experimental support for the SMB2 (Server Message Block + version 2) protocol. The SMB2 protocol is the successor to the + popular CIFS and SMB network file sharing protocols. SMB2 is the + native file sharing mechanism for recent versions of Windows + operating systems (since Vista). SMB2 enablement will eventually + allow users better performance, security and features, than would be + possible with cifs. Note that smb2 mount options also are simpler + (compared to cifs) due to protocol improvements. + + Unless you are a developer or tester, say N. diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 005d524c3a4..4b412754434 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -6,7 +6,7 @@ obj-$(CONFIG_CIFS) += cifs.o cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \ link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \ cifs_unicode.o nterr.o xattr.o cifsencrypt.o \ - readdir.o ioctl.o sess.o export.o + readdir.o ioctl.o sess.o export.o smb1ops.o cifs-$(CONFIG_CIFS_ACL) += cifsacl.o @@ -15,3 +15,5 @@ cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o + +cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o diff --git a/fs/cifs/README b/fs/cifs/README index b7d782bab79..22ab7b5b8da 100644 --- a/fs/cifs/README +++ b/fs/cifs/README @@ -608,11 +608,6 @@ Stats Lists summary resource usage information as well as per in the kernel configuration. Configuration pseudo-files: -MultiuserMount If set to one, more than one CIFS session to - the same server ip address can be established - if more than one uid accesses the same mount - point and if the uids user/password mapping - information is available. (default is 0) PacketSigningEnabled If set to one, cifs packet signing is enabled and will be used if the server requires it. If set to two, cifs packet signing is diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 27046462941..e8140528ca5 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -57,19 +57,21 @@ cifs_dump_mem(char *label, void *data, int length) } } -#ifdef CONFIG_CIFS_DEBUG2 void cifs_dump_detail(void *buf) { +#ifdef CONFIG_CIFS_DEBUG2 struct smb_hdr *smb = (struct smb_hdr *)buf; cERROR(1, "Cmd: %d Err: 0x%x Flags: 0x%x Flgs2: 0x%x Mid: %d Pid: %d", smb->Command, smb->Status.CifsError, smb->Flags, smb->Flags2, smb->Mid, smb->Pid); cERROR(1, "smb buf %p len %d", smb, smbCalcSize(smb)); +#endif /* CONFIG_CIFS_DEBUG2 */ } void cifs_dump_mids(struct TCP_Server_Info *server) { +#ifdef CONFIG_CIFS_DEBUG2 struct list_head *tmp; struct mid_q_entry *mid_entry; @@ -102,8 +104,8 @@ void cifs_dump_mids(struct TCP_Server_Info *server) } } spin_unlock(&GlobalMid_Lock); -} #endif /* CONFIG_CIFS_DEBUG2 */ +} #ifdef CONFIG_PROC_FS static int cifs_debug_data_proc_show(struct seq_file *m, void *v) @@ -420,7 +422,6 @@ static struct proc_dir_entry *proc_fs_cifs; static const struct file_operations cifsFYI_proc_fops; static const struct file_operations cifs_lookup_cache_proc_fops; static const struct file_operations traceSMB_proc_fops; -static const struct file_operations cifs_multiuser_mount_proc_fops; static const struct file_operations cifs_security_flags_proc_fops; static const struct file_operations cifs_linux_ext_proc_fops; @@ -440,8 +441,6 @@ cifs_proc_init(void) proc_create("traceSMB", 0, proc_fs_cifs, &traceSMB_proc_fops); proc_create("LinuxExtensionsEnabled", 0, proc_fs_cifs, &cifs_linux_ext_proc_fops); - proc_create("MultiuserMount", 0, proc_fs_cifs, - &cifs_multiuser_mount_proc_fops); proc_create("SecurityFlags", 0, proc_fs_cifs, &cifs_security_flags_proc_fops); proc_create("LookupCacheEnabled", 0, proc_fs_cifs, @@ -460,7 +459,6 @@ cifs_proc_clean(void) #ifdef CONFIG_CIFS_STATS remove_proc_entry("Stats", proc_fs_cifs); #endif - remove_proc_entry("MultiuserMount", proc_fs_cifs); remove_proc_entry("SecurityFlags", proc_fs_cifs); remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs); remove_proc_entry("LookupCacheEnabled", proc_fs_cifs); @@ -617,52 +615,6 @@ static const struct file_operations traceSMB_proc_fops = { .write = traceSMB_proc_write, }; -static int cifs_multiuser_mount_proc_show(struct seq_file *m, void *v) -{ - seq_printf(m, "%d\n", multiuser_mount); - return 0; -} - -static int cifs_multiuser_mount_proc_open(struct inode *inode, struct file *fh) -{ - return single_open(fh, cifs_multiuser_mount_proc_show, NULL); -} - -static ssize_t cifs_multiuser_mount_proc_write(struct file *file, - const char __user *buffer, size_t count, loff_t *ppos) -{ - char c; - int rc; - static bool warned; - - rc = get_user(c, buffer); - if (rc) - return rc; - if (c == '0' || c == 'n' || c == 'N') - multiuser_mount = 0; - else if (c == '1' || c == 'y' || c == 'Y') { - multiuser_mount = 1; - if (!warned) { - warned = true; - printk(KERN_WARNING "CIFS VFS: The legacy multiuser " - "mount code is scheduled to be deprecated in " - "3.5. Please switch to using the multiuser " - "mount option."); - } - } - - return count; -} - -static const struct file_operations cifs_multiuser_mount_proc_fops = { - .owner = THIS_MODULE, - .open = cifs_multiuser_mount_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = cifs_multiuser_mount_proc_write, -}; - static int cifs_security_flags_proc_show(struct seq_file *m, void *v) { seq_printf(m, "0x%x\n", global_secflags); diff --git a/fs/cifs/cifs_debug.h b/fs/cifs/cifs_debug.h index 566e0ae8dc2..c0c68bb492d 100644 --- a/fs/cifs/cifs_debug.h +++ b/fs/cifs/cifs_debug.h @@ -24,10 +24,10 @@ #define _H_CIFS_DEBUG void cifs_dump_mem(char *label, void *data, int length); -#ifdef CONFIG_CIFS_DEBUG2 -#define DBG2 2 void cifs_dump_detail(void *); void cifs_dump_mids(struct TCP_Server_Info *); +#ifdef CONFIG_CIFS_DEBUG2 +#define DBG2 2 #else #define DBG2 0 #endif diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d3421282244..8b6e344eb0b 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -56,7 +56,6 @@ int traceSMB = 0; bool enable_oplocks = true; unsigned int linuxExtEnabled = 1; unsigned int lookupCacheEnabled = 1; -unsigned int multiuser_mount = 0; unsigned int global_secflags = CIFSSEC_DEF; /* unsigned int ntlmv2_support = 0; */ unsigned int sign_CIFS_PDUs = 1; @@ -125,7 +124,7 @@ cifs_read_super(struct super_block *sb) goto out_no_root; } - /* do that *after* d_alloc_root() - we want NULL ->d_op for root here */ + /* do that *after* d_make_root() - we want NULL ->d_op for root here */ if (cifs_sb_master_tcon(cifs_sb)->nocase) sb->s_d_op = &cifs_ci_dentry_ops; else @@ -272,7 +271,7 @@ static void cifs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); cifs_fscache_release_inode_cookie(inode); } @@ -329,6 +328,19 @@ cifs_show_security(struct seq_file *s, struct TCP_Server_Info *server) seq_printf(s, "i"); } +static void +cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb) +{ + seq_printf(s, ",cache="); + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) + seq_printf(s, "strict"); + else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) + seq_printf(s, "none"); + else + seq_printf(s, "loose"); +} + /* * cifs_show_options() is for displaying mount options in /proc/mounts. * Not all settable options are displayed but most of the important @@ -342,7 +354,9 @@ cifs_show_options(struct seq_file *s, struct dentry *root) struct sockaddr *srcaddr; srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr; + seq_printf(s, ",vers=%s", tcon->ses->server->vals->version_string); cifs_show_security(s, tcon->ses->server); + cifs_show_cache_flavor(s, cifs_sb); seq_printf(s, ",unc=%s", tcon->treeName); @@ -370,13 +384,13 @@ cifs_show_options(struct seq_file *s, struct dentry *root) (int)(srcaddr->sa_family)); } - seq_printf(s, ",uid=%d", cifs_sb->mnt_uid); + seq_printf(s, ",uid=%u", cifs_sb->mnt_uid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) seq_printf(s, ",forceuid"); else seq_printf(s, ",noforceuid"); - seq_printf(s, ",gid=%d", cifs_sb->mnt_gid); + seq_printf(s, ",gid=%u", cifs_sb->mnt_gid); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) seq_printf(s, ",forcegid"); else @@ -408,8 +422,6 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",rwpidforward"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) seq_printf(s, ",forcemand"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) - seq_printf(s, ",directio"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) seq_printf(s, ",nouser_xattr"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) @@ -432,13 +444,15 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_printf(s, ",nostrictsync"); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) seq_printf(s, ",noperm"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) - seq_printf(s, ",strictcache"); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) + seq_printf(s, ",backupuid=%u", cifs_sb->mnt_backupuid); + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) + seq_printf(s, ",backupgid=%u", cifs_sb->mnt_backupgid); - seq_printf(s, ",rsize=%d", cifs_sb->rsize); - seq_printf(s, ",wsize=%d", cifs_sb->wsize); + seq_printf(s, ",rsize=%u", cifs_sb->rsize); + seq_printf(s, ",wsize=%u", cifs_sb->wsize); /* convert actimeo and display it in seconds */ - seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); + seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ); return 0; } @@ -695,7 +709,7 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin) * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length */ - if (origin != SEEK_SET || origin != SEEK_CUR) { + if (origin != SEEK_SET && origin != SEEK_CUR) { int rc; struct inode *inode = file->f_path.dentry->d_inode; @@ -941,7 +955,6 @@ cifs_init_once(void *inode) struct cifsInodeInfo *cifsi = inode; inode_init_once(&cifsi->vfs_inode); - INIT_LIST_HEAD(&cifsi->llist); mutex_init(&cifsi->lock_mutex); } diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d1389bb33ce..65365358c97 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "1.77" +#define CIFS_VERSION "1.78" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 4ff6313f0a9..6df0cbe1cbc 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -43,6 +43,7 @@ #define CIFS_MIN_RCV_POOL 4 +#define MAX_REOPEN_ATT 5 /* these many maximum attempts to reopen a file */ /* * default attribute cache timeout (jiffies) */ @@ -150,6 +151,58 @@ struct cifs_cred { ***************************************************************** */ +enum smb_version { + Smb_1 = 1, + Smb_21, +}; + +struct mid_q_entry; +struct TCP_Server_Info; +struct cifsFileInfo; +struct cifs_ses; + +struct smb_version_operations { + int (*send_cancel)(struct TCP_Server_Info *, void *, + struct mid_q_entry *); + bool (*compare_fids)(struct cifsFileInfo *, struct cifsFileInfo *); + /* setup request: allocate mid, sign message */ + int (*setup_request)(struct cifs_ses *, struct kvec *, unsigned int, + struct mid_q_entry **); + /* check response: verify signature, map error */ + int (*check_receive)(struct mid_q_entry *, struct TCP_Server_Info *, + bool); + void (*add_credits)(struct TCP_Server_Info *, const unsigned int); + void (*set_credits)(struct TCP_Server_Info *, const int); + int * (*get_credits_field)(struct TCP_Server_Info *); + __u64 (*get_next_mid)(struct TCP_Server_Info *); + /* data offset from read response message */ + unsigned int (*read_data_offset)(char *); + /* data length from read response message */ + unsigned int (*read_data_length)(char *); + /* map smb to linux error */ + int (*map_error)(char *, bool); + /* find mid corresponding to the response message */ + struct mid_q_entry * (*find_mid)(struct TCP_Server_Info *, char *); + void (*dump_detail)(void *); + /* verify the message */ + int (*check_message)(char *, unsigned int); + bool (*is_oplock_break)(char *, struct TCP_Server_Info *); +}; + +struct smb_version_values { + char *version_string; + __u32 large_lock_type; + __u32 exclusive_lock_type; + __u32 shared_lock_type; + __u32 unlock_lock_type; + size_t header_size; + size_t max_header_size; + size_t read_rsp_size; +}; + +#define HEADER_SIZE(server) (server->vals->header_size) +#define MAX_HEADER_SIZE(server) (server->vals->max_header_size) + struct smb_vol { char *username; char *password; @@ -205,6 +258,8 @@ struct smb_vol { bool sockopt_tcp_nodelay:1; unsigned short int port; unsigned long actimeo; /* attribute cache timeout (jiffies) */ + struct smb_version_operations *ops; + struct smb_version_values *vals; char *prepath; struct sockaddr_storage srcaddr; /* allow binding to a local IP */ struct nls_table *local_nls; @@ -242,6 +297,8 @@ struct TCP_Server_Info { int srv_count; /* reference counter */ /* 15 character server name + 0x20 16th byte indicating type = srv */ char server_RFC1001_name[RFC1001_NAME_LEN_WITH_NULL]; + struct smb_version_operations *ops; + struct smb_version_values *vals; enum statusEnum tcpStatus; /* what we think the status is */ char *hostname; /* hostname portion of UNC string */ struct socket *ssocket; @@ -321,16 +378,6 @@ in_flight(struct TCP_Server_Info *server) return num; } -static inline int* -get_credits_field(struct TCP_Server_Info *server) -{ - /* - * This will change to switch statement when we reserve slots for echos - * and oplock breaks. - */ - return &server->credits; -} - static inline bool has_credits(struct TCP_Server_Info *server, int *credits) { @@ -341,16 +388,22 @@ has_credits(struct TCP_Server_Info *server, int *credits) return num > 0; } -static inline size_t -header_size(void) +static inline void +add_credits(struct TCP_Server_Info *server, const unsigned int add) { - return sizeof(struct smb_hdr); + server->ops->add_credits(server, add); } -static inline size_t -max_header_size(void) +static inline void +set_credits(struct TCP_Server_Info *server, const int val) { - return MAX_CIFS_HDR_SIZE; + server->ops->set_credits(server, val); +} + +static inline __u64 +get_next_mid(struct TCP_Server_Info *server) +{ + return server->ops->get_next_mid(server); } /* @@ -547,8 +600,7 @@ struct cifsLockInfo { __u64 offset; __u64 length; __u32 pid; - __u8 type; - __u16 netfid; + __u32 type; }; /* @@ -573,6 +625,10 @@ struct cifs_search_info { struct cifsFileInfo { struct list_head tlist; /* pointer to next fid owned by tcon */ struct list_head flist; /* next fid (file instance) for this inode */ + struct list_head llist; /* + * brlocks held by this fid, protected by + * lock_mutex from cifsInodeInfo structure + */ unsigned int uid; /* allows finding which FileInfo structure */ __u32 pid; /* process id who opened file */ __u16 netfid; /* file id from remote */ @@ -615,9 +671,12 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file); */ struct cifsInodeInfo { - struct list_head llist; /* brlocks for this inode */ bool can_cache_brlcks; - struct mutex lock_mutex; /* protect two fields above */ + struct mutex lock_mutex; /* + * protect the field above and llist + * from every cifsFileInfo structure + * from openFileList + */ /* BB add in lists for dirty pages i.e. write caching info for oplock */ struct list_head openFileList; __u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */ @@ -703,7 +762,6 @@ static inline void cifs_stats_bytes_read(struct cifs_tcon *tcon, #endif -struct mid_q_entry; /* * This is the prototype for the mid receive function. This function is for @@ -1042,12 +1100,7 @@ GLOBAL_EXTERN atomic_t smBufAllocCount; GLOBAL_EXTERN atomic_t midCount; /* Misc globals */ -GLOBAL_EXTERN unsigned int multiuser_mount; /* if enabled allows new sessions - to be established on existing mount if we - have the uid/password or Kerberos credential - or equivalent for current user */ -/* enable or disable oplocks */ -GLOBAL_EXTERN bool enable_oplocks; +GLOBAL_EXTERN bool enable_oplocks; /* enable or disable oplocks */ GLOBAL_EXTERN unsigned int lookupCacheEnabled; GLOBAL_EXTERN unsigned int global_secflags; /* if on, session setup sent with more secure ntlmssp2 challenge/resp */ @@ -1074,4 +1127,11 @@ void cifs_oplock_break(struct work_struct *work); extern const struct slow_work_ops cifs_oplock_break_ops; extern struct workqueue_struct *cifsiod_wq; +/* Operations for different SMB versions */ +#define SMB1_VERSION_STRING "1.0" +extern struct smb_version_operations smb1_operations; +extern struct smb_version_values smb1_values; +#define SMB21_VERSION_STRING "2.1" +extern struct smb_version_operations smb21_operations; +extern struct smb_version_values smb21_values; #endif /* _CIFS_GLOB_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 96192c1e380..0a6cbfe2761 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -78,6 +78,8 @@ extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *, int * /* bytes returned */ , const int long_op); extern int SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses, char *in_buf, int flags); +extern int cifs_setup_request(struct cifs_ses *, struct kvec *, unsigned int, + struct mid_q_entry **); extern int cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server, bool log_error); extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *, @@ -88,9 +90,6 @@ extern int SendReceiveBlockingLock(const unsigned int xid, struct smb_hdr *in_buf , struct smb_hdr *out_buf, int *bytes_returned); -extern void cifs_add_credits(struct TCP_Server_Info *server, - const unsigned int add); -extern void cifs_set_credits(struct TCP_Server_Info *server, const int val); extern int checkSMB(char *buf, unsigned int length); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); @@ -115,7 +114,6 @@ extern int small_smb_init_no_tc(const int smb_cmd, const int wct, void **request_buf); extern int CIFS_SessSetup(unsigned int xid, struct cifs_ses *ses, const struct nls_table *nls_cp); -extern __u64 GetNextMid(struct TCP_Server_Info *server); extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601); extern u64 cifs_UnixTimeToNT(struct timespec); extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, @@ -192,11 +190,13 @@ extern int CIFSTCon(unsigned int xid, struct cifs_ses *ses, extern int CIFSFindFirst(const int xid, struct cifs_tcon *tcon, const char *searchName, const struct nls_table *nls_codepage, - __u16 *searchHandle, struct cifs_search_info *psrch_inf, + __u16 *searchHandle, __u16 search_flags, + struct cifs_search_info *psrch_inf, int map, const char dirsep); extern int CIFSFindNext(const int xid, struct cifs_tcon *tcon, - __u16 searchHandle, struct cifs_search_info *psrch_inf); + __u16 searchHandle, __u16 search_flags, + struct cifs_search_info *psrch_inf); extern int CIFSFindClose(const int, struct cifs_tcon *tcon, const __u16 search_handle); @@ -464,6 +464,9 @@ extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, /* asynchronous read support */ struct cifs_readdata { + struct kref refcount; + struct list_head list; + struct completion done; struct cifsFileInfo *cfile; struct address_space *mapping; __u64 offset; @@ -472,12 +475,13 @@ struct cifs_readdata { int result; struct list_head pages; struct work_struct work; + int (*marshal_iov) (struct cifs_readdata *rdata, + unsigned int remaining); unsigned int nr_iov; struct kvec iov[1]; }; -struct cifs_readdata *cifs_readdata_alloc(unsigned int nr_pages); -void cifs_readdata_free(struct cifs_readdata *rdata); +void cifs_readdata_release(struct kref *refcount); int cifs_async_readv(struct cifs_readdata *rdata); /* asynchronous write support */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index f52c5ab78f9..5b400730c21 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -87,7 +87,6 @@ static struct { #endif /* CIFS_POSIX */ /* Forward declarations */ -static void cifs_readv_complete(struct work_struct *work); /* Mark as invalid, all open files on tree connections since they were closed when session to server was lost */ @@ -269,7 +268,7 @@ small_smb_init_no_tc(const int smb_command, const int wct, return rc; buffer = (struct smb_hdr *)*request_buf; - buffer->Mid = GetNextMid(ses->server); + buffer->Mid = get_next_mid(ses->server); if (ses->capabilities & CAP_UNICODE) buffer->Flags2 |= SMBFLG2_UNICODE; if (ses->capabilities & CAP_STATUS32) @@ -403,7 +402,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses) cFYI(1, "secFlags 0x%x", secFlags); - pSMB->hdr.Mid = GetNextMid(server); + pSMB->hdr.Mid = get_next_mid(server); pSMB->hdr.Flags2 |= (SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS); if ((secFlags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5) @@ -461,7 +460,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses) server->maxReq = min_t(unsigned int, le16_to_cpu(rsp->MaxMpxCount), cifs_max_pending); - cifs_set_credits(server, server->maxReq); + set_credits(server, server->maxReq); server->maxBuf = le16_to_cpu(rsp->MaxBufSize); server->max_vcs = le16_to_cpu(rsp->MaxNumberVcs); /* even though we do not use raw we might as well set this @@ -569,7 +568,7 @@ CIFSSMBNegotiate(unsigned int xid, struct cifs_ses *ses) little endian */ server->maxReq = min_t(unsigned int, le16_to_cpu(pSMBr->MaxMpxCount), cifs_max_pending); - cifs_set_credits(server, server->maxReq); + set_credits(server, server->maxReq); /* probably no need to store and check maxvcs */ server->maxBuf = le32_to_cpu(pSMBr->MaxBufferSize); server->max_rw = le32_to_cpu(pSMBr->MaxRawSize); @@ -721,7 +720,7 @@ cifs_echo_callback(struct mid_q_entry *mid) struct TCP_Server_Info *server = mid->callback_data; DeleteMidQEntry(mid); - cifs_add_credits(server, 1); + add_credits(server, 1); } int @@ -783,7 +782,7 @@ CIFSSMBLogoff(const int xid, struct cifs_ses *ses) return rc; } - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); if (ses->server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) @@ -1385,28 +1384,6 @@ openRetry: return rc; } -struct cifs_readdata * -cifs_readdata_alloc(unsigned int nr_pages) -{ - struct cifs_readdata *rdata; - - /* readdata + 1 kvec for each page */ - rdata = kzalloc(sizeof(*rdata) + - sizeof(struct kvec) * nr_pages, GFP_KERNEL); - if (rdata != NULL) { - INIT_WORK(&rdata->work, cifs_readv_complete); - INIT_LIST_HEAD(&rdata->pages); - } - return rdata; -} - -void -cifs_readdata_free(struct cifs_readdata *rdata) -{ - cifsFileInfo_put(rdata->cfile); - kfree(rdata); -} - /* * Discard any remaining data in the current SMB. To do this, we borrow the * current bigbuf. @@ -1423,7 +1400,7 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) length = cifs_read_from_socket(server, server->bigbuf, min_t(unsigned int, remaining, - CIFSMaxBufSize + max_header_size())); + CIFSMaxBufSize + MAX_HEADER_SIZE(server))); if (length < 0) return length; server->total_read += length; @@ -1434,38 +1411,14 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid) return 0; } -static inline size_t -read_rsp_size(void) -{ - return sizeof(READ_RSP); -} - -static inline unsigned int -read_data_offset(char *buf) -{ - READ_RSP *rsp = (READ_RSP *)buf; - return le16_to_cpu(rsp->DataOffset); -} - -static inline unsigned int -read_data_length(char *buf) -{ - READ_RSP *rsp = (READ_RSP *)buf; - return (le16_to_cpu(rsp->DataLengthHigh) << 16) + - le16_to_cpu(rsp->DataLength); -} - static int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) { int length, len; - unsigned int data_offset, remaining, data_len; + unsigned int data_offset, data_len; struct cifs_readdata *rdata = mid->callback_data; char *buf = server->smallbuf; unsigned int buflen = get_rfc1002_length(buf) + 4; - u64 eof; - pgoff_t eof_index; - struct page *page, *tpage; cFYI(1, "%s: mid=%llu offset=%llu bytes=%u", __func__, mid->mid, rdata->offset, rdata->bytes); @@ -1475,9 +1428,10 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) * can if there's not enough data. At this point, we've read down to * the Mid. */ - len = min_t(unsigned int, buflen, read_rsp_size()) - header_size() + 1; + len = min_t(unsigned int, buflen, server->vals->read_rsp_size) - + HEADER_SIZE(server) + 1; - rdata->iov[0].iov_base = buf + header_size() - 1; + rdata->iov[0].iov_base = buf + HEADER_SIZE(server) - 1; rdata->iov[0].iov_len = len; length = cifs_readv_from_socket(server, rdata->iov, 1, len); @@ -1486,7 +1440,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) server->total_read += length; /* Was the SMB read successful? */ - rdata->result = map_smb_to_linux_error(buf, false); + rdata->result = server->ops->map_error(buf, false); if (rdata->result != 0) { cFYI(1, "%s: server returned error %d", __func__, rdata->result); @@ -1494,14 +1448,15 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* Is there enough to get to the rest of the READ_RSP header? */ - if (server->total_read < read_rsp_size()) { + if (server->total_read < server->vals->read_rsp_size) { cFYI(1, "%s: server returned short header. got=%u expected=%zu", - __func__, server->total_read, read_rsp_size()); + __func__, server->total_read, + server->vals->read_rsp_size); rdata->result = -EIO; return cifs_readv_discard(server, mid); } - data_offset = read_data_offset(buf) + 4; + data_offset = server->ops->read_data_offset(buf) + 4; if (data_offset < server->total_read) { /* * win2k8 sometimes sends an offset of 0 when the read @@ -1540,7 +1495,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) rdata->iov[0].iov_base, rdata->iov[0].iov_len); /* how much data is in the response? */ - data_len = read_data_length(buf); + data_len = server->ops->read_data_length(buf); if (data_offset + data_len > buflen) { /* data_len is corrupt -- discard frame */ rdata->result = -EIO; @@ -1548,64 +1503,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* marshal up the page array */ - len = 0; - remaining = data_len; - rdata->nr_iov = 1; - - /* determine the eof that the server (probably) has */ - eof = CIFS_I(rdata->mapping->host)->server_eof; - eof_index = eof ? (eof - 1) >> PAGE_CACHE_SHIFT : 0; - cFYI(1, "eof=%llu eof_index=%lu", eof, eof_index); - - list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { - if (remaining >= PAGE_CACHE_SIZE) { - /* enough data to fill the page */ - rdata->iov[rdata->nr_iov].iov_base = kmap(page); - rdata->iov[rdata->nr_iov].iov_len = PAGE_CACHE_SIZE; - cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", - rdata->nr_iov, page->index, - rdata->iov[rdata->nr_iov].iov_base, - rdata->iov[rdata->nr_iov].iov_len); - ++rdata->nr_iov; - len += PAGE_CACHE_SIZE; - remaining -= PAGE_CACHE_SIZE; - } else if (remaining > 0) { - /* enough for partial page, fill and zero the rest */ - rdata->iov[rdata->nr_iov].iov_base = kmap(page); - rdata->iov[rdata->nr_iov].iov_len = remaining; - cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", - rdata->nr_iov, page->index, - rdata->iov[rdata->nr_iov].iov_base, - rdata->iov[rdata->nr_iov].iov_len); - memset(rdata->iov[rdata->nr_iov].iov_base + remaining, - '\0', PAGE_CACHE_SIZE - remaining); - ++rdata->nr_iov; - len += remaining; - remaining = 0; - } else if (page->index > eof_index) { - /* - * The VFS will not try to do readahead past the - * i_size, but it's possible that we have outstanding - * writes with gaps in the middle and the i_size hasn't - * caught up yet. Populate those with zeroed out pages - * to prevent the VFS from repeatedly attempting to - * fill them until the writes are flushed. - */ - zero_user(page, 0, PAGE_CACHE_SIZE); - list_del(&page->lru); - lru_cache_add_file(page); - flush_dcache_page(page); - SetPageUptodate(page); - unlock_page(page); - page_cache_release(page); - } else { - /* no need to hold page hostage */ - list_del(&page->lru); - lru_cache_add_file(page); - unlock_page(page); - page_cache_release(page); - } - } + len = rdata->marshal_iov(rdata, data_len); + data_len -= len; /* issue the read if we have any iovecs left to fill */ if (rdata->nr_iov > 1) { @@ -1621,7 +1520,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) rdata->bytes = length; cFYI(1, "total_read=%u buflen=%u remaining=%u", server->total_read, - buflen, remaining); + buflen, data_len); /* discard anything left over */ if (server->total_read < buflen) @@ -1632,33 +1531,6 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) } static void -cifs_readv_complete(struct work_struct *work) -{ - struct cifs_readdata *rdata = container_of(work, - struct cifs_readdata, work); - struct page *page, *tpage; - - list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { - list_del(&page->lru); - lru_cache_add_file(page); - - if (rdata->result == 0) { - kunmap(page); - flush_dcache_page(page); - SetPageUptodate(page); - } - - unlock_page(page); - - if (rdata->result == 0) - cifs_readpage_to_fscache(rdata->mapping->host, page); - - page_cache_release(page); - } - cifs_readdata_free(rdata); -} - -static void cifs_readv_callback(struct mid_q_entry *mid) { struct cifs_readdata *rdata = mid->callback_data; @@ -1691,7 +1563,7 @@ cifs_readv_callback(struct mid_q_entry *mid) queue_work(cifsiod_wq, &rdata->work); DeleteMidQEntry(mid); - cifs_add_credits(server, 1); + add_credits(server, 1); } /* cifs_async_readv - send an async write, and set up mid to handle result */ @@ -1744,12 +1616,15 @@ cifs_async_readv(struct cifs_readdata *rdata) rdata->iov[0].iov_base = smb; rdata->iov[0].iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4; + kref_get(&rdata->refcount); rc = cifs_call_async(tcon->ses->server, rdata->iov, 1, cifs_readv_receive, cifs_readv_callback, rdata, false); if (rc == 0) cifs_stats_inc(&tcon->num_reads); + else + kref_put(&rdata->refcount, cifs_readdata_release); cifs_small_buf_release(smb); return rc; @@ -2135,7 +2010,7 @@ cifs_writev_callback(struct mid_q_entry *mid) queue_work(cifsiod_wq, &wdata->work); DeleteMidQEntry(mid); - cifs_add_credits(tcon->ses->server, 1); + add_credits(tcon->ses->server, 1); } /* cifs_async_writev - send an async write, and set up mid to handle result */ @@ -4344,7 +4219,7 @@ int CIFSFindFirst(const int xid, struct cifs_tcon *tcon, const char *searchName, const struct nls_table *nls_codepage, - __u16 *pnetfid, + __u16 *pnetfid, __u16 search_flags, struct cifs_search_info *psrch_inf, int remap, const char dirsep) { /* level 257 SMB_ */ @@ -4416,8 +4291,7 @@ findFirstRetry: cpu_to_le16(ATTR_READONLY | ATTR_HIDDEN | ATTR_SYSTEM | ATTR_DIRECTORY); pSMB->SearchCount = cpu_to_le16(CIFSMaxBufSize/sizeof(FILE_UNIX_INFO)); - pSMB->SearchFlags = cpu_to_le16(CIFS_SEARCH_CLOSE_AT_END | - CIFS_SEARCH_RETURN_RESUME); + pSMB->SearchFlags = cpu_to_le16(search_flags); pSMB->InformationLevel = cpu_to_le16(psrch_inf->info_level); /* BB what should we set StorageType to? Does it matter? BB */ @@ -4487,8 +4361,8 @@ findFirstRetry: return rc; } -int CIFSFindNext(const int xid, struct cifs_tcon *tcon, - __u16 searchHandle, struct cifs_search_info *psrch_inf) +int CIFSFindNext(const int xid, struct cifs_tcon *tcon, __u16 searchHandle, + __u16 search_flags, struct cifs_search_info *psrch_inf) { TRANSACTION2_FNEXT_REQ *pSMB = NULL; TRANSACTION2_FNEXT_RSP *pSMBr = NULL; @@ -4531,8 +4405,7 @@ int CIFSFindNext(const int xid, struct cifs_tcon *tcon, cpu_to_le16(CIFSMaxBufSize / sizeof(FILE_UNIX_INFO)); pSMB->InformationLevel = cpu_to_le16(psrch_inf->info_level); pSMB->ResumeKey = psrch_inf->resume_key; - pSMB->SearchFlags = - cpu_to_le16(CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME); + pSMB->SearchFlags = cpu_to_le16(search_flags); name_len = psrch_inf->resume_name_len; params += name_len; @@ -4844,8 +4717,12 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr, max_len = data_end - temp; node->node_name = cifs_strndup_from_utf16(temp, max_len, is_unicode, nls_codepage); - if (!node->node_name) + if (!node->node_name) { rc = -ENOMEM; + goto parse_DFS_referrals_exit; + } + + ref++; } parse_DFS_referrals_exit: @@ -4885,7 +4762,7 @@ getDFSRetry: /* server pointer checked in called function, but should never be null here anyway */ - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); pSMB->hdr.Tid = ses->ipc_tid; pSMB->hdr.Uid = ses->Suid; if (ses->capabilities & CAP_STATUS32) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index f31dc9ac37b..0ae86ddf221 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1,7 +1,7 @@ /* * fs/cifs/connect.c * - * Copyright (C) International Business Machines Corp., 2002,2009 + * Copyright (C) International Business Machines Corp., 2002,2011 * Author(s): Steve French (sfrench@us.ibm.com) * * This library is free software; you can redistribute it and/or modify @@ -102,7 +102,7 @@ enum { Opt_srcaddr, Opt_prefixpath, Opt_iocharset, Opt_sockopt, Opt_netbiosname, Opt_servern, - Opt_ver, Opt_sec, + Opt_ver, Opt_vers, Opt_sec, Opt_cache, /* Mount options to be ignored */ Opt_ignore, @@ -164,7 +164,8 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_sign, "sign" }, { Opt_seal, "seal" }, { Opt_direct, "direct" }, - { Opt_direct, "forceddirectio" }, + { Opt_direct, "directio" }, + { Opt_direct, "forcedirectio" }, { Opt_strictcache, "strictcache" }, { Opt_noac, "noac" }, { Opt_fsc, "fsc" }, @@ -209,12 +210,14 @@ static const match_table_t cifs_mount_option_tokens = { { Opt_netbiosname, "netbiosname=%s" }, { Opt_servern, "servern=%s" }, { Opt_ver, "ver=%s" }, - { Opt_ver, "vers=%s" }, - { Opt_ver, "version=%s" }, + { Opt_vers, "vers=%s" }, { Opt_sec, "sec=%s" }, + { Opt_cache, "cache=%s" }, { Opt_ignore, "cred" }, { Opt_ignore, "credentials" }, + { Opt_ignore, "cred=%s" }, + { Opt_ignore, "credentials=%s" }, { Opt_ignore, "guest" }, { Opt_ignore, "rw" }, { Opt_ignore, "ro" }, @@ -258,6 +261,26 @@ static const match_table_t cifs_secflavor_tokens = { { Opt_sec_err, NULL } }; +/* cache flavors */ +enum { + Opt_cache_loose, + Opt_cache_strict, + Opt_cache_none, + Opt_cache_err +}; + +static const match_table_t cifs_cacheflavor_tokens = { + { Opt_cache_loose, "loose" }, + { Opt_cache_strict, "strict" }, + { Opt_cache_none, "none" }, + { Opt_cache_err, NULL } +}; + +static const match_table_t cifs_smb_version_tokens = { + { Smb_1, SMB1_VERSION_STRING }, + { Smb_21, SMB21_VERSION_STRING }, +}; + static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); @@ -546,7 +569,7 @@ allocate_buffers(struct TCP_Server_Info *server) } } else if (server->large_buf) { /* we are reusing a dirty large buf, clear its start */ - memset(server->bigbuf, 0, header_size()); + memset(server->bigbuf, 0, HEADER_SIZE(server)); } if (!server->smallbuf) { @@ -560,7 +583,7 @@ allocate_buffers(struct TCP_Server_Info *server) /* beginning of smb buffer is cleared in our buf_get */ } else { /* if existing small buf clear beginning */ - memset(server->smallbuf, 0, header_size()); + memset(server->smallbuf, 0, HEADER_SIZE(server)); } return true; @@ -761,25 +784,6 @@ is_smb_response(struct TCP_Server_Info *server, unsigned char type) return false; } -static struct mid_q_entry * -find_mid(struct TCP_Server_Info *server, char *buffer) -{ - struct smb_hdr *buf = (struct smb_hdr *)buffer; - struct mid_q_entry *mid; - - spin_lock(&GlobalMid_Lock); - list_for_each_entry(mid, &server->pending_mid_q, qhead) { - if (mid->mid == buf->Mid && - mid->mid_state == MID_REQUEST_SUBMITTED && - le16_to_cpu(mid->command) == buf->Command) { - spin_unlock(&GlobalMid_Lock); - return mid; - } - } - spin_unlock(&GlobalMid_Lock); - return NULL; -} - void dequeue_mid(struct mid_q_entry *mid, bool malformed) { @@ -931,7 +935,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) unsigned int pdu_length = get_rfc1002_length(buf); /* make sure this will fit in a large buffer */ - if (pdu_length > CIFSMaxBufSize + max_header_size() - 4) { + if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server) - 4) { cERROR(1, "SMB response too long (%u bytes)", pdu_length); cifs_reconnect(server); @@ -947,8 +951,8 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* now read the rest */ - length = cifs_read_from_socket(server, buf + header_size() - 1, - pdu_length - header_size() + 1 + 4); + length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, + pdu_length - HEADER_SIZE(server) + 1 + 4); if (length < 0) return length; server->total_read += length; @@ -964,7 +968,7 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) * 48 bytes is enough to display the header and a little bit * into the payload for debugging purposes. */ - length = checkSMB(buf, server->total_read); + length = server->ops->check_message(buf, server->total_read); if (length != 0) cifs_dump_mem("Bad SMB: ", buf, min_t(unsigned int, server->total_read, 48)); @@ -1022,7 +1026,7 @@ cifs_demultiplex_thread(void *p) continue; /* make sure we have enough to get to the MID */ - if (pdu_length < header_size() - 1 - 4) { + if (pdu_length < HEADER_SIZE(server) - 1 - 4) { cERROR(1, "SMB response too short (%u bytes)", pdu_length); cifs_reconnect(server); @@ -1032,12 +1036,12 @@ cifs_demultiplex_thread(void *p) /* read down to the MID */ length = cifs_read_from_socket(server, buf + 4, - header_size() - 1 - 4); + HEADER_SIZE(server) - 1 - 4); if (length < 0) continue; server->total_read += length; - mid_entry = find_mid(server, buf); + mid_entry = server->ops->find_mid(server, buf); if (!mid_entry || !mid_entry->receive) length = standard_receive3(server, mid_entry); @@ -1054,12 +1058,15 @@ cifs_demultiplex_thread(void *p) if (mid_entry != NULL) { if (!mid_entry->multiRsp || mid_entry->multiEnd) mid_entry->callback(mid_entry); - } else if (!is_valid_oplock_break(buf, server)) { + } else if (!server->ops->is_oplock_break || + !server->ops->is_oplock_break(buf, server)) { cERROR(1, "No task to wake, unknown frame received! " "NumMids %d", atomic_read(&midCount)); - cifs_dump_mem("Received Data is: ", buf, header_size()); + cifs_dump_mem("Received Data is: ", buf, + HEADER_SIZE(server)); #ifdef CONFIG_CIFS_DEBUG2 - cifs_dump_detail(buf); + if (server->ops->dump_detail) + server->ops->dump_detail(buf); cifs_dump_mids(server); #endif /* CIFS_DEBUG2 */ @@ -1183,6 +1190,54 @@ static int cifs_parse_security_flavors(char *value, } static int +cifs_parse_cache_flavor(char *value, struct smb_vol *vol) +{ + substring_t args[MAX_OPT_ARGS]; + + switch (match_token(value, cifs_cacheflavor_tokens, args)) { + case Opt_cache_loose: + vol->direct_io = false; + vol->strict_io = false; + break; + case Opt_cache_strict: + vol->direct_io = false; + vol->strict_io = true; + break; + case Opt_cache_none: + vol->direct_io = true; + vol->strict_io = false; + break; + default: + cERROR(1, "bad cache= option: %s", value); + return 1; + } + return 0; +} + +static int +cifs_parse_smb_version(char *value, struct smb_vol *vol) +{ + substring_t args[MAX_OPT_ARGS]; + + switch (match_token(value, cifs_smb_version_tokens, args)) { + case Smb_1: + vol->ops = &smb1_operations; + vol->vals = &smb1_values; + break; +#ifdef CONFIG_CIFS_SMB2 + case Smb_21: + vol->ops = &smb21_operations; + vol->vals = &smb21_values; + break; +#endif + default: + cERROR(1, "Unknown vers= option specified: %s", value); + return 1; + } + return 0; +} + +static int cifs_parse_mount_options(const char *mountdata, const char *devname, struct smb_vol *vol) { @@ -1200,6 +1255,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, char *string = NULL; char *tmp_end, *value; char delim; + bool cache_specified = false; + static bool cache_warned = false; separator[0] = ','; separator[1] = 0; @@ -1233,6 +1290,10 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->actimeo = CIFS_DEF_ACTIMEO; + /* FIXME: add autonegotiation -- for now, SMB1 is default */ + vol->ops = &smb1_operations; + vol->vals = &smb1_values; + if (!mountdata) goto cifs_parse_mount_err; @@ -1411,10 +1472,20 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->seal = 1; break; case Opt_direct: - vol->direct_io = 1; + cache_specified = true; + vol->direct_io = true; + vol->strict_io = false; + cERROR(1, "The \"directio\" option will be removed in " + "3.7. Please switch to the \"cache=none\" " + "option."); break; case Opt_strictcache: - vol->strict_io = 1; + cache_specified = true; + vol->direct_io = false; + vol->strict_io = true; + cERROR(1, "The \"strictcache\" option will be removed " + "in 3.7. Please switch to the \"cache=strict\" " + "option."); break; case Opt_noac: printk(KERN_WARNING "CIFS: Mount option noac not " @@ -1582,24 +1653,26 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, * If yes, we have encountered a double deliminator * reset the NULL character to the deliminator */ - if (tmp_end < end && tmp_end[1] == delim) + if (tmp_end < end && tmp_end[1] == delim) { tmp_end[0] = delim; - /* Keep iterating until we get to a single deliminator - * OR the end - */ - while ((tmp_end = strchr(tmp_end, delim)) != NULL && - (tmp_end[1] == delim)) { - tmp_end = (char *) &tmp_end[2]; - } + /* Keep iterating until we get to a single + * deliminator OR the end + */ + while ((tmp_end = strchr(tmp_end, delim)) + != NULL && (tmp_end[1] == delim)) { + tmp_end = (char *) &tmp_end[2]; + } - /* Reset var options to point to next element */ - if (tmp_end) { - tmp_end[0] = '\0'; - options = (char *) &tmp_end[1]; - } else - /* Reached the end of the mount option string */ - options = end; + /* Reset var options to point to next element */ + if (tmp_end) { + tmp_end[0] = '\0'; + options = (char *) &tmp_end[1]; + } else + /* Reached the end of the mount option + * string */ + options = end; + } /* Now build new password string */ temp_len = strlen(value); @@ -1818,8 +1891,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (string == NULL) goto out_nomem; - if (strnicmp(string, "cifs", 4) == 0 || - strnicmp(string, "1", 1) == 0) { + if (strnicmp(string, "1", 1) == 0) { /* This is the default */ break; } @@ -1827,6 +1899,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, printk(KERN_WARNING "CIFS: Invalid version" " specified\n"); goto cifs_parse_mount_err; + case Opt_vers: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + + if (cifs_parse_smb_version(string, vol) != 0) + goto cifs_parse_mount_err; + break; case Opt_sec: string = match_strdup(args); if (string == NULL) @@ -1835,6 +1915,15 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, if (cifs_parse_security_flavors(string, vol) != 0) goto cifs_parse_mount_err; break; + case Opt_cache: + cache_specified = true; + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + + if (cifs_parse_cache_flavor(string, vol) != 0) + goto cifs_parse_mount_err; + break; default: /* * An option we don't recognize. Save it off for later @@ -1878,6 +1967,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, printk(KERN_NOTICE "CIFS: ignoring forcegid mount option " "specified with no gid= option.\n"); + /* FIXME: remove this block in 3.7 */ + if (!cache_specified && !cache_warned) { + cache_warned = true; + printk(KERN_NOTICE "CIFS: no cache= option specified, using " + "\"cache=loose\". This default will change " + "to \"cache=strict\" in 3.7.\n"); + } + kfree(mountdata_copy); return 0; @@ -2038,6 +2135,9 @@ match_security(struct TCP_Server_Info *server, struct smb_vol *vol) static int match_server(struct TCP_Server_Info *server, struct sockaddr *addr, struct smb_vol *vol) { + if ((server->vals != vol->vals) || (server->ops != vol->ops)) + return 0; + if (!net_eq(cifs_net_ns(server), current->nsproxy->net_ns)) return 0; @@ -2160,6 +2260,8 @@ cifs_get_tcp_session(struct smb_vol *volume_info) goto out_err; } + tcp_ses->ops = volume_info->ops; + tcp_ses->vals = volume_info->vals; cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); tcp_ses->hostname = extract_hostname(volume_info->UNC); if (IS_ERR(tcp_ses->hostname)) { @@ -2183,6 +2285,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info) tcp_ses->session_estab = false; tcp_ses->sequence_number = 0; tcp_ses->lstrp = jiffies; + spin_lock_init(&tcp_ses->req_lock); INIT_LIST_HEAD(&tcp_ses->tcp_ses_list); INIT_LIST_HEAD(&tcp_ses->smb_ses_list); INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request); @@ -3228,10 +3331,6 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_uid = pvolume_info->linux_uid; cifs_sb->mnt_gid = pvolume_info->linux_gid; - if (pvolume_info->backupuid_specified) - cifs_sb->mnt_backupuid = pvolume_info->backupuid; - if (pvolume_info->backupgid_specified) - cifs_sb->mnt_backupgid = pvolume_info->backupgid; cifs_sb->mnt_file_mode = pvolume_info->file_mode; cifs_sb->mnt_dir_mode = pvolume_info->dir_mode; cFYI(1, "file mode: 0x%hx dir mode: 0x%hx", @@ -3262,10 +3361,14 @@ void cifs_setup_cifs_sb(struct smb_vol *pvolume_info, cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD; if (pvolume_info->cifs_acl) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL; - if (pvolume_info->backupuid_specified) + if (pvolume_info->backupuid_specified) { cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID; - if (pvolume_info->backupgid_specified) + cifs_sb->mnt_backupuid = pvolume_info->backupuid; + } + if (pvolume_info->backupgid_specified) { cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID; + cifs_sb->mnt_backupgid = pvolume_info->backupgid; + } if (pvolume_info->override_uid) cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID; if (pvolume_info->override_gid) @@ -3392,18 +3495,15 @@ cifs_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *pvolume_info) * MS-CIFS indicates that servers are only limited by the client's * bufsize for reads, testing against win98se shows that it throws * INVALID_PARAMETER errors if you try to request too large a read. + * OS/2 just sends back short reads. * - * If the server advertises a MaxBufferSize of less than one page, - * assume that it also can't satisfy reads larger than that either. - * - * FIXME: Is there a better heuristic for this? + * If the server doesn't advertise CAP_LARGE_READ_X, then assume that + * it can't handle a read request larger than its MaxBufferSize either. */ if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_READ_CAP)) defsize = CIFS_DEFAULT_IOSIZE; else if (server->capabilities & CAP_LARGE_READ_X) defsize = CIFS_DEFAULT_NON_POSIX_RSIZE; - else if (server->maxBuf >= PAGE_CACHE_SIZE) - defsize = CIFSMaxBufSize; else defsize = server->maxBuf - sizeof(READ_RSP); @@ -3565,6 +3665,7 @@ cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, if (cifs_parse_mount_options(mount_data, devname, volume_info)) return -EINVAL; + if (volume_info->nullauth) { cFYI(1, "Anonymous login"); kfree(volume_info->username); @@ -3614,22 +3715,6 @@ cifs_get_volume_info(char *mount_data, const char *devname) return volume_info; } -/* make sure ra_pages is a multiple of rsize */ -static inline unsigned int -cifs_ra_pages(struct cifs_sb_info *cifs_sb) -{ - unsigned int reads; - unsigned int rsize_pages = cifs_sb->rsize / PAGE_CACHE_SIZE; - - if (rsize_pages >= default_backing_dev_info.ra_pages) - return default_backing_dev_info.ra_pages; - else if (rsize_pages == 0) - return rsize_pages; - - reads = default_backing_dev_info.ra_pages / rsize_pages; - return reads * rsize_pages; -} - int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) { @@ -3717,7 +3802,7 @@ try_mount_again: cifs_sb->rsize = cifs_negotiate_rsize(tcon, volume_info); /* tune readahead according to rsize */ - cifs_sb->bdi.ra_pages = cifs_ra_pages(cifs_sb); + cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_CACHE_SIZE; remote_path_check: #ifdef CONFIG_CIFS_DFS_UPCALL @@ -3854,7 +3939,7 @@ CIFSTCon(unsigned int xid, struct cifs_ses *ses, header_assemble(smb_buffer, SMB_COM_TREE_CONNECT_ANDX, NULL /*no tid */ , 4 /*wct */ ); - smb_buffer->Mid = GetNextMid(ses->server); + smb_buffer->Mid = get_next_mid(ses->server); smb_buffer->Uid = ses->Suid; pSMB = (TCONX_REQ *) smb_buffer; pSMBr = (TCONX_RSP *) smb_buffer_response; @@ -4022,11 +4107,11 @@ int cifs_negotiate_protocol(unsigned int xid, struct cifs_ses *ses) if (server->maxBuf != 0) return 0; - cifs_set_credits(server, 1); + set_credits(server, 1); rc = CIFSSMBNegotiate(xid, ses); if (rc == -EAGAIN) { /* retry only once on 1st time connection */ - cifs_set_credits(server, 1); + set_credits(server, 1); rc = CIFSSMBNegotiate(xid, ses); if (rc == -EAGAIN) rc = -EHOSTDOWN; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index d172c8ed901..ec4e9a2a12f 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -668,12 +668,19 @@ cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd) return 0; else { /* - * Forcibly invalidate automounting directory inodes - * (remote DFS directories) so to have them - * instantiated again for automount + * If the inode wasn't known to be a dfs entry when + * the dentry was instantiated, such as when created + * via ->readdir(), it needs to be set now since the + * attributes will have been updated by + * cifs_revalidate_dentry(). */ - if (IS_AUTOMOUNT(direntry->d_inode)) - return 0; + if (IS_AUTOMOUNT(direntry->d_inode) && + !(direntry->d_flags & DCACHE_NEED_AUTOMOUNT)) { + spin_lock(&direntry->d_lock); + direntry->d_flags |= DCACHE_NEED_AUTOMOUNT; + spin_unlock(&direntry->d_lock); + } + return 1; } } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index fae765dac93..513adbc211d 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -264,6 +264,7 @@ cifs_new_fileinfo(__u16 fileHandle, struct file *file, pCifsFile->tlink = cifs_get_tlink(tlink); mutex_init(&pCifsFile->fh_mutex); INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); + INIT_LIST_HEAD(&pCifsFile->llist); spin_lock(&cifs_file_list_lock); list_add(&pCifsFile->tlist, &(tlink_tcon(tlink)->openFileList)); @@ -334,9 +335,7 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file) * is closed anyway. */ mutex_lock(&cifsi->lock_mutex); - list_for_each_entry_safe(li, tmp, &cifsi->llist, llist) { - if (li->netfid != cifs_file->netfid) - continue; + list_for_each_entry_safe(li, tmp, &cifs_file->llist, llist) { list_del(&li->llist); cifs_del_lock_waiters(li); kfree(li); @@ -645,7 +644,7 @@ int cifs_closedir(struct inode *inode, struct file *file) } static struct cifsLockInfo * -cifs_lock_init(__u64 offset, __u64 length, __u8 type, __u16 netfid) +cifs_lock_init(__u64 offset, __u64 length, __u8 type) { struct cifsLockInfo *lock = kmalloc(sizeof(struct cifsLockInfo), GFP_KERNEL); @@ -654,7 +653,6 @@ cifs_lock_init(__u64 offset, __u64 length, __u8 type, __u16 netfid) lock->offset = offset; lock->length = length; lock->type = type; - lock->netfid = netfid; lock->pid = current->tgid; INIT_LIST_HEAD(&lock->blist); init_waitqueue_head(&lock->block_q); @@ -672,19 +670,20 @@ cifs_del_lock_waiters(struct cifsLockInfo *lock) } static bool -__cifs_find_lock_conflict(struct cifsInodeInfo *cinode, __u64 offset, - __u64 length, __u8 type, __u16 netfid, - struct cifsLockInfo **conf_lock) +cifs_find_fid_lock_conflict(struct cifsFileInfo *cfile, __u64 offset, + __u64 length, __u8 type, struct cifsFileInfo *cur, + struct cifsLockInfo **conf_lock) { - struct cifsLockInfo *li, *tmp; + struct cifsLockInfo *li; + struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; - list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { + list_for_each_entry(li, &cfile->llist, llist) { if (offset + length <= li->offset || offset >= li->offset + li->length) continue; - else if ((type & LOCKING_ANDX_SHARED_LOCK) && - ((netfid == li->netfid && current->tgid == li->pid) || - type == li->type)) + else if ((type & server->vals->shared_lock_type) && + ((server->ops->compare_fids(cur, cfile) && + current->tgid == li->pid) || type == li->type)) continue; else { *conf_lock = li; @@ -695,11 +694,23 @@ __cifs_find_lock_conflict(struct cifsInodeInfo *cinode, __u64 offset, } static bool -cifs_find_lock_conflict(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock, - struct cifsLockInfo **conf_lock) +cifs_find_lock_conflict(struct cifsFileInfo *cfile, __u64 offset, __u64 length, + __u8 type, struct cifsLockInfo **conf_lock) { - return __cifs_find_lock_conflict(cinode, lock->offset, lock->length, - lock->type, lock->netfid, conf_lock); + bool rc = false; + struct cifsFileInfo *fid, *tmp; + struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); + + spin_lock(&cifs_file_list_lock); + list_for_each_entry_safe(fid, tmp, &cinode->openFileList, flist) { + rc = cifs_find_fid_lock_conflict(fid, offset, length, type, + cfile, conf_lock); + if (rc) + break; + } + spin_unlock(&cifs_file_list_lock); + + return rc; } /* @@ -710,22 +721,24 @@ cifs_find_lock_conflict(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock, * the server or 1 otherwise. */ static int -cifs_lock_test(struct cifsInodeInfo *cinode, __u64 offset, __u64 length, - __u8 type, __u16 netfid, struct file_lock *flock) +cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length, + __u8 type, struct file_lock *flock) { int rc = 0; struct cifsLockInfo *conf_lock; + struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); + struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; bool exist; mutex_lock(&cinode->lock_mutex); - exist = __cifs_find_lock_conflict(cinode, offset, length, type, netfid, - &conf_lock); + exist = cifs_find_lock_conflict(cfile, offset, length, type, + &conf_lock); if (exist) { flock->fl_start = conf_lock->offset; flock->fl_end = conf_lock->offset + conf_lock->length - 1; flock->fl_pid = conf_lock->pid; - if (conf_lock->type & LOCKING_ANDX_SHARED_LOCK) + if (conf_lock->type & server->vals->shared_lock_type) flock->fl_type = F_RDLCK; else flock->fl_type = F_WRLCK; @@ -739,10 +752,11 @@ cifs_lock_test(struct cifsInodeInfo *cinode, __u64 offset, __u64 length, } static void -cifs_lock_add(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock) +cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock) { + struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); mutex_lock(&cinode->lock_mutex); - list_add_tail(&lock->llist, &cinode->llist); + list_add_tail(&lock->llist, &cfile->llist); mutex_unlock(&cinode->lock_mutex); } @@ -753,10 +767,11 @@ cifs_lock_add(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock) * 3) -EACCESS, if there is a lock that prevents us and wait is false. */ static int -cifs_lock_add_if(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock, +cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock, bool wait) { struct cifsLockInfo *conf_lock; + struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); bool exist; int rc = 0; @@ -764,9 +779,10 @@ try_again: exist = false; mutex_lock(&cinode->lock_mutex); - exist = cifs_find_lock_conflict(cinode, lock, &conf_lock); + exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length, + lock->type, &conf_lock); if (!exist && cinode->can_cache_brlcks) { - list_add_tail(&lock->llist, &cinode->llist); + list_add_tail(&lock->llist, &cfile->llist); mutex_unlock(&cinode->lock_mutex); return rc; } @@ -860,7 +876,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) struct cifsLockInfo *li, *tmp; struct cifs_tcon *tcon; struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); - unsigned int num, max_num; + unsigned int num, max_num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; int types[] = {LOCKING_ANDX_LARGE_FILES, LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; @@ -876,8 +892,19 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) return rc; } - max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / - sizeof(LOCKING_ANDX_RANGE); + /* + * Accessing maxBuf is racy with cifs_reconnect - need to store value + * and check it for zero before using. + */ + max_buf = tcon->ses->server->maxBuf; + if (!max_buf) { + mutex_unlock(&cinode->lock_mutex); + FreeXid(xid); + return -EINVAL; + } + + max_num = (max_buf - sizeof(struct smb_hdr)) / + sizeof(LOCKING_ANDX_RANGE); buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); if (!buf) { mutex_unlock(&cinode->lock_mutex); @@ -888,7 +915,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) for (i = 0; i < 2; i++) { cur = buf; num = 0; - list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { + list_for_each_entry_safe(li, tmp, &cfile->llist, llist) { if (li->type != types[i]) continue; cur->Pid = cpu_to_le16(li->pid); @@ -898,7 +925,8 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32)); if (++num == max_num) { stored_rc = cifs_lockv(xid, tcon, cfile->netfid, - li->type, 0, num, buf); + (__u8)li->type, 0, num, + buf); if (stored_rc) rc = stored_rc; cur = buf; @@ -909,7 +937,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) if (num) { stored_rc = cifs_lockv(xid, tcon, cfile->netfid, - types[i], 0, num, buf); + (__u8)types[i], 0, num, buf); if (stored_rc) rc = stored_rc; } @@ -1053,8 +1081,8 @@ cifs_push_locks(struct cifsFileInfo *cfile) } static void -cifs_read_flock(struct file_lock *flock, __u8 *type, int *lock, int *unlock, - bool *wait_flag) +cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock, + bool *wait_flag, struct TCP_Server_Info *server) { if (flock->fl_flags & FL_POSIX) cFYI(1, "Posix"); @@ -1073,38 +1101,50 @@ cifs_read_flock(struct file_lock *flock, __u8 *type, int *lock, int *unlock, (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE))) cFYI(1, "Unknown lock flags 0x%x", flock->fl_flags); - *type = LOCKING_ANDX_LARGE_FILES; + *type = server->vals->large_lock_type; if (flock->fl_type == F_WRLCK) { cFYI(1, "F_WRLCK "); + *type |= server->vals->exclusive_lock_type; *lock = 1; } else if (flock->fl_type == F_UNLCK) { cFYI(1, "F_UNLCK"); + *type |= server->vals->unlock_lock_type; *unlock = 1; /* Check if unlock includes more than one lock range */ } else if (flock->fl_type == F_RDLCK) { cFYI(1, "F_RDLCK"); - *type |= LOCKING_ANDX_SHARED_LOCK; + *type |= server->vals->shared_lock_type; *lock = 1; } else if (flock->fl_type == F_EXLCK) { cFYI(1, "F_EXLCK"); + *type |= server->vals->exclusive_lock_type; *lock = 1; } else if (flock->fl_type == F_SHLCK) { cFYI(1, "F_SHLCK"); - *type |= LOCKING_ANDX_SHARED_LOCK; + *type |= server->vals->shared_lock_type; *lock = 1; } else cFYI(1, "Unknown type of lock"); } static int -cifs_getlk(struct file *file, struct file_lock *flock, __u8 type, +cifs_mandatory_lock(int xid, struct cifsFileInfo *cfile, __u64 offset, + __u64 length, __u32 type, int lock, int unlock, bool wait) +{ + return CIFSSMBLock(xid, tlink_tcon(cfile->tlink), cfile->netfid, + current->tgid, length, offset, unlock, lock, + (__u8)type, wait, 0); +} + +static int +cifs_getlk(struct file *file, struct file_lock *flock, __u32 type, bool wait_flag, bool posix_lck, int xid) { int rc = 0; __u64 length = 1 + flock->fl_end - flock->fl_start; struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); + struct TCP_Server_Info *server = tcon->ses->server; __u16 netfid = cfile->netfid; if (posix_lck) { @@ -1114,7 +1154,7 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u8 type, if (!rc) return rc; - if (type & LOCKING_ANDX_SHARED_LOCK) + if (type & server->vals->shared_lock_type) posix_lock_type = CIFS_RDLCK; else posix_lock_type = CIFS_WRLCK; @@ -1124,38 +1164,35 @@ cifs_getlk(struct file *file, struct file_lock *flock, __u8 type, return rc; } - rc = cifs_lock_test(cinode, flock->fl_start, length, type, netfid, - flock); + rc = cifs_lock_test(cfile, flock->fl_start, length, type, flock); if (!rc) return rc; /* BB we could chain these into one lock request BB */ - rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, - flock->fl_start, 0, 1, type, 0, 0); + rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, type, + 1, 0, false); if (rc == 0) { - rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, - length, flock->fl_start, 1, 0, - type, 0, 0); + rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, + type, 0, 1, false); flock->fl_type = F_UNLCK; if (rc != 0) cERROR(1, "Error unlocking previously locked " - "range %d during test of lock", rc); + "range %d during test of lock", rc); return 0; } - if (type & LOCKING_ANDX_SHARED_LOCK) { + if (type & server->vals->shared_lock_type) { flock->fl_type = F_WRLCK; return 0; } - rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, - flock->fl_start, 0, 1, - type | LOCKING_ANDX_SHARED_LOCK, 0, 0); + rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, + type | server->vals->shared_lock_type, 1, 0, + false); if (rc == 0) { - rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, - length, flock->fl_start, 1, 0, - type | LOCKING_ANDX_SHARED_LOCK, - 0, 0); + rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, + type | server->vals->shared_lock_type, + 0, 1, false); flock->fl_type = F_RDLCK; if (rc != 0) cERROR(1, "Error unlocking previously locked " @@ -1192,7 +1229,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) int types[] = {LOCKING_ANDX_LARGE_FILES, LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; unsigned int i; - unsigned int max_num, num; + unsigned int max_num, num, max_buf; LOCKING_ANDX_RANGE *buf, *cur; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); @@ -1202,8 +1239,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) INIT_LIST_HEAD(&tmp_llist); - max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / - sizeof(LOCKING_ANDX_RANGE); + /* + * Accessing maxBuf is racy with cifs_reconnect - need to store value + * and check it for zero before using. + */ + max_buf = tcon->ses->server->maxBuf; + if (!max_buf) + return -EINVAL; + + max_num = (max_buf - sizeof(struct smb_hdr)) / + sizeof(LOCKING_ANDX_RANGE); buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); if (!buf) return -ENOMEM; @@ -1212,71 +1257,64 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) for (i = 0; i < 2; i++) { cur = buf; num = 0; - list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { + list_for_each_entry_safe(li, tmp, &cfile->llist, llist) { if (flock->fl_start > li->offset || (flock->fl_start + length) < (li->offset + li->length)) continue; if (current->tgid != li->pid) continue; - if (cfile->netfid != li->netfid) - continue; if (types[i] != li->type) continue; - if (!cinode->can_cache_brlcks) { - cur->Pid = cpu_to_le16(li->pid); - cur->LengthLow = cpu_to_le32((u32)li->length); - cur->LengthHigh = - cpu_to_le32((u32)(li->length>>32)); - cur->OffsetLow = cpu_to_le32((u32)li->offset); - cur->OffsetHigh = - cpu_to_le32((u32)(li->offset>>32)); - /* - * We need to save a lock here to let us add - * it again to the inode list if the unlock - * range request fails on the server. - */ - list_move(&li->llist, &tmp_llist); - if (++num == max_num) { - stored_rc = cifs_lockv(xid, tcon, - cfile->netfid, - li->type, num, - 0, buf); - if (stored_rc) { - /* - * We failed on the unlock range - * request - add all locks from - * the tmp list to the head of - * the inode list. - */ - cifs_move_llist(&tmp_llist, - &cinode->llist); - rc = stored_rc; - } else - /* - * The unlock range request - * succeed - free the tmp list. - */ - cifs_free_llist(&tmp_llist); - cur = buf; - num = 0; - } else - cur++; - } else { + if (cinode->can_cache_brlcks) { /* * We can cache brlock requests - simply remove - * a lock from the inode list. + * a lock from the file's list. */ list_del(&li->llist); cifs_del_lock_waiters(li); kfree(li); + continue; } + cur->Pid = cpu_to_le16(li->pid); + cur->LengthLow = cpu_to_le32((u32)li->length); + cur->LengthHigh = cpu_to_le32((u32)(li->length>>32)); + cur->OffsetLow = cpu_to_le32((u32)li->offset); + cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32)); + /* + * We need to save a lock here to let us add it again to + * the file's list if the unlock range request fails on + * the server. + */ + list_move(&li->llist, &tmp_llist); + if (++num == max_num) { + stored_rc = cifs_lockv(xid, tcon, cfile->netfid, + li->type, num, 0, buf); + if (stored_rc) { + /* + * We failed on the unlock range + * request - add all locks from the tmp + * list to the head of the file's list. + */ + cifs_move_llist(&tmp_llist, + &cfile->llist); + rc = stored_rc; + } else + /* + * The unlock range request succeed - + * free the tmp list. + */ + cifs_free_llist(&tmp_llist); + cur = buf; + num = 0; + } else + cur++; } if (num) { stored_rc = cifs_lockv(xid, tcon, cfile->netfid, types[i], num, 0, buf); if (stored_rc) { - cifs_move_llist(&tmp_llist, &cinode->llist); + cifs_move_llist(&tmp_llist, &cfile->llist); rc = stored_rc; } else cifs_free_llist(&tmp_llist); @@ -1289,14 +1327,14 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) } static int -cifs_setlk(struct file *file, struct file_lock *flock, __u8 type, +cifs_setlk(struct file *file, struct file_lock *flock, __u32 type, bool wait_flag, bool posix_lck, int lock, int unlock, int xid) { int rc = 0; __u64 length = 1 + flock->fl_end - flock->fl_start; struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); - struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode); + struct TCP_Server_Info *server = tcon->ses->server; __u16 netfid = cfile->netfid; if (posix_lck) { @@ -1306,7 +1344,7 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u8 type, if (!rc || rc < 0) return rc; - if (type & LOCKING_ANDX_SHARED_LOCK) + if (type & server->vals->shared_lock_type) posix_lock_type = CIFS_RDLCK; else posix_lock_type = CIFS_WRLCK; @@ -1323,24 +1361,24 @@ cifs_setlk(struct file *file, struct file_lock *flock, __u8 type, if (lock) { struct cifsLockInfo *lock; - lock = cifs_lock_init(flock->fl_start, length, type, netfid); + lock = cifs_lock_init(flock->fl_start, length, type); if (!lock) return -ENOMEM; - rc = cifs_lock_add_if(cinode, lock, wait_flag); + rc = cifs_lock_add_if(cfile, lock, wait_flag); if (rc < 0) kfree(lock); if (rc <= 0) goto out; - rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, - flock->fl_start, 0, 1, type, wait_flag, 0); + rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, + type, 1, 0, wait_flag); if (rc) { kfree(lock); goto out; } - cifs_lock_add(cinode, lock); + cifs_lock_add(cfile, lock); } else if (unlock) rc = cifs_unlock_range(cfile, flock, xid); @@ -1361,7 +1399,7 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) struct cifsInodeInfo *cinode; struct cifsFileInfo *cfile; __u16 netfid; - __u8 type; + __u32 type; rc = -EACCES; xid = GetXid(); @@ -1370,11 +1408,13 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) "end: %lld", cmd, flock->fl_flags, flock->fl_type, flock->fl_start, flock->fl_end); - cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag); - - cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); cfile = (struct cifsFileInfo *)file->private_data; tcon = tlink_tcon(cfile->tlink); + + cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag, + tcon->ses->server); + + cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); netfid = cfile->netfid; cinode = CIFS_I(file->f_path.dentry->d_inode); @@ -1539,10 +1579,11 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only) { - struct cifsFileInfo *open_file; + struct cifsFileInfo *open_file, *inv_file = NULL; struct cifs_sb_info *cifs_sb; bool any_available = false; int rc; + unsigned int refind = 0; /* Having a null inode here (because mapping->host was set to zero by the VFS or MM) should not happen but we had reports of on oops (due to @@ -1562,40 +1603,25 @@ struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, spin_lock(&cifs_file_list_lock); refind_writable: + if (refind > MAX_REOPEN_ATT) { + spin_unlock(&cifs_file_list_lock); + return NULL; + } list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { if (!any_available && open_file->pid != current->tgid) continue; if (fsuid_only && open_file->uid != current_fsuid()) continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { - cifsFileInfo_get(open_file); - if (!open_file->invalidHandle) { /* found a good writable file */ + cifsFileInfo_get(open_file); spin_unlock(&cifs_file_list_lock); return open_file; + } else { + if (!inv_file) + inv_file = open_file; } - - spin_unlock(&cifs_file_list_lock); - - /* Had to unlock since following call can block */ - rc = cifs_reopen_file(open_file, false); - if (!rc) - return open_file; - - /* if it fails, try another handle if possible */ - cFYI(1, "wp failed on reopen file"); - cifsFileInfo_put(open_file); - - spin_lock(&cifs_file_list_lock); - - /* else we simply continue to the next entry. Thus - we do not loop on reopen errors. If we - can not reopen the file, for example if we - reconnected to a server with another client - racing to delete or lock the file we would not - make progress if we restarted before the beginning - of the loop here. */ } } /* couldn't find useable FH with same pid, try any available */ @@ -1603,7 +1629,30 @@ refind_writable: any_available = true; goto refind_writable; } + + if (inv_file) { + any_available = false; + cifsFileInfo_get(inv_file); + } + spin_unlock(&cifs_file_list_lock); + + if (inv_file) { + rc = cifs_reopen_file(inv_file, false); + if (!rc) + return inv_file; + else { + spin_lock(&cifs_file_list_lock); + list_move_tail(&inv_file->flist, + &cifs_inode->openFileList); + spin_unlock(&cifs_file_list_lock); + cifsFileInfo_put(inv_file); + spin_lock(&cifs_file_list_lock); + ++refind; + goto refind_writable; + } + } + return NULL; } @@ -2178,7 +2227,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, unsigned long nr_pages, i; size_t copied, len, cur_len; ssize_t total_written = 0; - loff_t offset = *poffset; + loff_t offset; struct iov_iter it; struct cifsFileInfo *open_file; struct cifs_tcon *tcon; @@ -2200,6 +2249,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); open_file = file->private_data; tcon = tlink_tcon(open_file->tlink); + offset = *poffset; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; @@ -2338,24 +2388,224 @@ ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, return cifs_user_writev(iocb, iov, nr_segs, pos); } +static struct cifs_readdata * +cifs_readdata_alloc(unsigned int nr_vecs, work_func_t complete) +{ + struct cifs_readdata *rdata; + + rdata = kzalloc(sizeof(*rdata) + + sizeof(struct kvec) * nr_vecs, GFP_KERNEL); + if (rdata != NULL) { + kref_init(&rdata->refcount); + INIT_LIST_HEAD(&rdata->list); + init_completion(&rdata->done); + INIT_WORK(&rdata->work, complete); + INIT_LIST_HEAD(&rdata->pages); + } + return rdata; +} + +void +cifs_readdata_release(struct kref *refcount) +{ + struct cifs_readdata *rdata = container_of(refcount, + struct cifs_readdata, refcount); + + if (rdata->cfile) + cifsFileInfo_put(rdata->cfile); + + kfree(rdata); +} + +static int +cifs_read_allocate_pages(struct list_head *list, unsigned int npages) +{ + int rc = 0; + struct page *page, *tpage; + unsigned int i; + + for (i = 0; i < npages; i++) { + page = alloc_page(GFP_KERNEL|__GFP_HIGHMEM); + if (!page) { + rc = -ENOMEM; + break; + } + list_add(&page->lru, list); + } + + if (rc) { + list_for_each_entry_safe(page, tpage, list, lru) { + list_del(&page->lru); + put_page(page); + } + } + return rc; +} + +static void +cifs_uncached_readdata_release(struct kref *refcount) +{ + struct page *page, *tpage; + struct cifs_readdata *rdata = container_of(refcount, + struct cifs_readdata, refcount); + + list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { + list_del(&page->lru); + put_page(page); + } + cifs_readdata_release(refcount); +} + +static int +cifs_retry_async_readv(struct cifs_readdata *rdata) +{ + int rc; + + do { + if (rdata->cfile->invalidHandle) { + rc = cifs_reopen_file(rdata->cfile, true); + if (rc != 0) + continue; + } + rc = cifs_async_readv(rdata); + } while (rc == -EAGAIN); + + return rc; +} + +/** + * cifs_readdata_to_iov - copy data from pages in response to an iovec + * @rdata: the readdata response with list of pages holding data + * @iov: vector in which we should copy the data + * @nr_segs: number of segments in vector + * @offset: offset into file of the first iovec + * @copied: used to return the amount of data copied to the iov + * + * This function copies data from a list of pages in a readdata response into + * an array of iovecs. It will first calculate where the data should go + * based on the info in the readdata and then copy the data into that spot. + */ +static ssize_t +cifs_readdata_to_iov(struct cifs_readdata *rdata, const struct iovec *iov, + unsigned long nr_segs, loff_t offset, ssize_t *copied) +{ + int rc = 0; + struct iov_iter ii; + size_t pos = rdata->offset - offset; + struct page *page, *tpage; + ssize_t remaining = rdata->bytes; + unsigned char *pdata; + + /* set up iov_iter and advance to the correct offset */ + iov_iter_init(&ii, iov, nr_segs, iov_length(iov, nr_segs), 0); + iov_iter_advance(&ii, pos); + + *copied = 0; + list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { + ssize_t copy; + + /* copy a whole page or whatever's left */ + copy = min_t(ssize_t, remaining, PAGE_SIZE); + + /* ...but limit it to whatever space is left in the iov */ + copy = min_t(ssize_t, copy, iov_iter_count(&ii)); + + /* go while there's data to be copied and no errors */ + if (copy && !rc) { + pdata = kmap(page); + rc = memcpy_toiovecend(ii.iov, pdata, ii.iov_offset, + (int)copy); + kunmap(page); + if (!rc) { + *copied += copy; + remaining -= copy; + iov_iter_advance(&ii, copy); + } + } + + list_del(&page->lru); + put_page(page); + } + + return rc; +} + +static void +cifs_uncached_readv_complete(struct work_struct *work) +{ + struct cifs_readdata *rdata = container_of(work, + struct cifs_readdata, work); + + /* if the result is non-zero then the pages weren't kmapped */ + if (rdata->result == 0) { + struct page *page; + + list_for_each_entry(page, &rdata->pages, lru) + kunmap(page); + } + + complete(&rdata->done); + kref_put(&rdata->refcount, cifs_uncached_readdata_release); +} + +static int +cifs_uncached_read_marshal_iov(struct cifs_readdata *rdata, + unsigned int remaining) +{ + int len = 0; + struct page *page, *tpage; + + rdata->nr_iov = 1; + list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { + if (remaining >= PAGE_SIZE) { + /* enough data to fill the page */ + rdata->iov[rdata->nr_iov].iov_base = kmap(page); + rdata->iov[rdata->nr_iov].iov_len = PAGE_SIZE; + cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", + rdata->nr_iov, page->index, + rdata->iov[rdata->nr_iov].iov_base, + rdata->iov[rdata->nr_iov].iov_len); + ++rdata->nr_iov; + len += PAGE_SIZE; + remaining -= PAGE_SIZE; + } else if (remaining > 0) { + /* enough for partial page, fill and zero the rest */ + rdata->iov[rdata->nr_iov].iov_base = kmap(page); + rdata->iov[rdata->nr_iov].iov_len = remaining; + cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", + rdata->nr_iov, page->index, + rdata->iov[rdata->nr_iov].iov_base, + rdata->iov[rdata->nr_iov].iov_len); + memset(rdata->iov[rdata->nr_iov].iov_base + remaining, + '\0', PAGE_SIZE - remaining); + ++rdata->nr_iov; + len += remaining; + remaining = 0; + } else { + /* no need to hold page hostage */ + list_del(&page->lru); + put_page(page); + } + } + + return len; +} + static ssize_t cifs_iovec_read(struct file *file, const struct iovec *iov, unsigned long nr_segs, loff_t *poffset) { - int rc; - int xid; - ssize_t total_read; - unsigned int bytes_read = 0; + ssize_t rc; size_t len, cur_len; - int iov_offset = 0; + ssize_t total_read = 0; + loff_t offset = *poffset; + unsigned int npages; struct cifs_sb_info *cifs_sb; - struct cifs_tcon *pTcon; + struct cifs_tcon *tcon; struct cifsFileInfo *open_file; - struct smb_com_read_rsp *pSMBr; - struct cifs_io_parms io_parms; - char *read_data; - unsigned int rsize; - __u32 pid; + struct cifs_readdata *rdata, *tmp; + struct list_head rdata_list; + pid_t pid; if (!nr_segs) return 0; @@ -2364,14 +2614,10 @@ cifs_iovec_read(struct file *file, const struct iovec *iov, if (!len) return 0; - xid = GetXid(); + INIT_LIST_HEAD(&rdata_list); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); - - /* FIXME: set up handlers for larger reads and/or convert to async */ - rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize); - open_file = file->private_data; - pTcon = tlink_tcon(open_file->tlink); + tcon = tlink_tcon(open_file->tlink); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; @@ -2381,56 +2627,78 @@ cifs_iovec_read(struct file *file, const struct iovec *iov, if ((file->f_flags & O_ACCMODE) == O_WRONLY) cFYI(1, "attempting read on write only file instance"); - for (total_read = 0; total_read < len; total_read += bytes_read) { - cur_len = min_t(const size_t, len - total_read, rsize); - rc = -EAGAIN; - read_data = NULL; + do { + cur_len = min_t(const size_t, len - total_read, cifs_sb->rsize); + npages = DIV_ROUND_UP(cur_len, PAGE_SIZE); - while (rc == -EAGAIN) { - int buf_type = CIFS_NO_BUFFER; - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, true); - if (rc != 0) - break; - } - io_parms.netfid = open_file->netfid; - io_parms.pid = pid; - io_parms.tcon = pTcon; - io_parms.offset = *poffset; - io_parms.length = cur_len; - rc = CIFSSMBRead(xid, &io_parms, &bytes_read, - &read_data, &buf_type); - pSMBr = (struct smb_com_read_rsp *)read_data; - if (read_data) { - char *data_offset = read_data + 4 + - le16_to_cpu(pSMBr->DataOffset); - if (memcpy_toiovecend(iov, data_offset, - iov_offset, bytes_read)) - rc = -EFAULT; - if (buf_type == CIFS_SMALL_BUFFER) - cifs_small_buf_release(read_data); - else if (buf_type == CIFS_LARGE_BUFFER) - cifs_buf_release(read_data); - read_data = NULL; - iov_offset += bytes_read; - } + /* allocate a readdata struct */ + rdata = cifs_readdata_alloc(npages, + cifs_uncached_readv_complete); + if (!rdata) { + rc = -ENOMEM; + goto error; } - if (rc || (bytes_read == 0)) { - if (total_read) { - break; - } else { - FreeXid(xid); - return rc; + rc = cifs_read_allocate_pages(&rdata->pages, npages); + if (rc) + goto error; + + rdata->cfile = cifsFileInfo_get(open_file); + rdata->offset = offset; + rdata->bytes = cur_len; + rdata->pid = pid; + rdata->marshal_iov = cifs_uncached_read_marshal_iov; + + rc = cifs_retry_async_readv(rdata); +error: + if (rc) { + kref_put(&rdata->refcount, + cifs_uncached_readdata_release); + break; + } + + list_add_tail(&rdata->list, &rdata_list); + offset += cur_len; + len -= cur_len; + } while (len > 0); + + /* if at least one read request send succeeded, then reset rc */ + if (!list_empty(&rdata_list)) + rc = 0; + + /* the loop below should proceed in the order of increasing offsets */ +restart_loop: + list_for_each_entry_safe(rdata, tmp, &rdata_list, list) { + if (!rc) { + ssize_t copied; + + /* FIXME: freezable sleep too? */ + rc = wait_for_completion_killable(&rdata->done); + if (rc) + rc = -EINTR; + else if (rdata->result) + rc = rdata->result; + else { + rc = cifs_readdata_to_iov(rdata, iov, + nr_segs, *poffset, + &copied); + total_read += copied; + } + + /* resend call if it's a retryable error */ + if (rc == -EAGAIN) { + rc = cifs_retry_async_readv(rdata); + goto restart_loop; } - } else { - cifs_stats_bytes_read(pTcon, bytes_read); - *poffset += bytes_read; } + list_del_init(&rdata->list); + kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - FreeXid(xid); - return total_read; + cifs_stats_bytes_read(tcon, total_read); + *poffset += total_read; + + return total_read ? total_read : rc; } ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov, @@ -2605,6 +2873,100 @@ int cifs_file_mmap(struct file *file, struct vm_area_struct *vma) return rc; } +static void +cifs_readv_complete(struct work_struct *work) +{ + struct cifs_readdata *rdata = container_of(work, + struct cifs_readdata, work); + struct page *page, *tpage; + + list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { + list_del(&page->lru); + lru_cache_add_file(page); + + if (rdata->result == 0) { + kunmap(page); + flush_dcache_page(page); + SetPageUptodate(page); + } + + unlock_page(page); + + if (rdata->result == 0) + cifs_readpage_to_fscache(rdata->mapping->host, page); + + page_cache_release(page); + } + kref_put(&rdata->refcount, cifs_readdata_release); +} + +static int +cifs_readpages_marshal_iov(struct cifs_readdata *rdata, unsigned int remaining) +{ + int len = 0; + struct page *page, *tpage; + u64 eof; + pgoff_t eof_index; + + /* determine the eof that the server (probably) has */ + eof = CIFS_I(rdata->mapping->host)->server_eof; + eof_index = eof ? (eof - 1) >> PAGE_CACHE_SHIFT : 0; + cFYI(1, "eof=%llu eof_index=%lu", eof, eof_index); + + rdata->nr_iov = 1; + list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { + if (remaining >= PAGE_CACHE_SIZE) { + /* enough data to fill the page */ + rdata->iov[rdata->nr_iov].iov_base = kmap(page); + rdata->iov[rdata->nr_iov].iov_len = PAGE_CACHE_SIZE; + cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", + rdata->nr_iov, page->index, + rdata->iov[rdata->nr_iov].iov_base, + rdata->iov[rdata->nr_iov].iov_len); + ++rdata->nr_iov; + len += PAGE_CACHE_SIZE; + remaining -= PAGE_CACHE_SIZE; + } else if (remaining > 0) { + /* enough for partial page, fill and zero the rest */ + rdata->iov[rdata->nr_iov].iov_base = kmap(page); + rdata->iov[rdata->nr_iov].iov_len = remaining; + cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu", + rdata->nr_iov, page->index, + rdata->iov[rdata->nr_iov].iov_base, + rdata->iov[rdata->nr_iov].iov_len); + memset(rdata->iov[rdata->nr_iov].iov_base + remaining, + '\0', PAGE_CACHE_SIZE - remaining); + ++rdata->nr_iov; + len += remaining; + remaining = 0; + } else if (page->index > eof_index) { + /* + * The VFS will not try to do readahead past the + * i_size, but it's possible that we have outstanding + * writes with gaps in the middle and the i_size hasn't + * caught up yet. Populate those with zeroed out pages + * to prevent the VFS from repeatedly attempting to + * fill them until the writes are flushed. + */ + zero_user(page, 0, PAGE_CACHE_SIZE); + list_del(&page->lru); + lru_cache_add_file(page); + flush_dcache_page(page); + SetPageUptodate(page); + unlock_page(page); + page_cache_release(page); + } else { + /* no need to hold page hostage */ + list_del(&page->lru); + lru_cache_add_file(page); + unlock_page(page); + page_cache_release(page); + } + } + + return len; +} + static int cifs_readpages(struct file *file, struct address_space *mapping, struct list_head *page_list, unsigned num_pages) { @@ -2707,7 +3069,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, nr_pages++; } - rdata = cifs_readdata_alloc(nr_pages); + rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete); if (!rdata) { /* best to give up if we're out of mem */ list_for_each_entry_safe(page, tpage, &tmplist, lru) { @@ -2721,24 +3083,16 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, } spin_lock(&cifs_file_list_lock); - cifsFileInfo_get(open_file); spin_unlock(&cifs_file_list_lock); - rdata->cfile = open_file; + rdata->cfile = cifsFileInfo_get(open_file); rdata->mapping = mapping; rdata->offset = offset; rdata->bytes = bytes; rdata->pid = pid; + rdata->marshal_iov = cifs_readpages_marshal_iov; list_splice_init(&tmplist, &rdata->pages); - do { - if (open_file->invalidHandle) { - rc = cifs_reopen_file(open_file, true); - if (rc != 0) - continue; - } - rc = cifs_async_readv(rdata); - } while (rc == -EAGAIN); - + rc = cifs_retry_async_readv(rdata); if (rc != 0) { list_for_each_entry_safe(page, tpage, &rdata->pages, lru) { @@ -2747,9 +3101,11 @@ static int cifs_readpages(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); } - cifs_readdata_free(rdata); + kref_put(&rdata->refcount, cifs_readdata_release); break; } + + kref_put(&rdata->refcount, cifs_readdata_release); } return rc; diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 4221b5e48a4..6d2667f0c98 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -51,7 +51,15 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) cifs_sb = CIFS_SB(inode->i_sb); switch (command) { + static bool warned = false; case CIFS_IOC_CHECKUMOUNT: + if (!warned) { + warned = true; + cERROR(1, "the CIFS_IOC_CHECKMOUNT ioctl will " + "be deprecated in 3.7. Please " + "migrate away from the use of " + "umount.cifs"); + } cFYI(1, "User unmount attempted"); if (cifs_sb->mnt_uid == current_uid()) rc = 0; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index c29d1aa2c54..557506ae1e2 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -212,93 +212,6 @@ cifs_small_buf_release(void *buf_to_free) return; } -/* - * Find a free multiplex id (SMB mid). Otherwise there could be - * mid collisions which might cause problems, demultiplexing the - * wrong response to this request. Multiplex ids could collide if - * one of a series requests takes much longer than the others, or - * if a very large number of long lived requests (byte range - * locks or FindNotify requests) are pending. No more than - * 64K-1 requests can be outstanding at one time. If no - * mids are available, return zero. A future optimization - * could make the combination of mids and uid the key we use - * to demultiplex on (rather than mid alone). - * In addition to the above check, the cifs demultiplex - * code already used the command code as a secondary - * check of the frame and if signing is negotiated the - * response would be discarded if the mid were the same - * but the signature was wrong. Since the mid is not put in the - * pending queue until later (when it is about to be dispatched) - * we do have to limit the number of outstanding requests - * to somewhat less than 64K-1 although it is hard to imagine - * so many threads being in the vfs at one time. - */ -__u64 GetNextMid(struct TCP_Server_Info *server) -{ - __u64 mid = 0; - __u16 last_mid, cur_mid; - bool collision; - - spin_lock(&GlobalMid_Lock); - - /* mid is 16 bit only for CIFS/SMB */ - cur_mid = (__u16)((server->CurrentMid) & 0xffff); - /* we do not want to loop forever */ - last_mid = cur_mid; - cur_mid++; - - /* - * This nested loop looks more expensive than it is. - * In practice the list of pending requests is short, - * fewer than 50, and the mids are likely to be unique - * on the first pass through the loop unless some request - * takes longer than the 64 thousand requests before it - * (and it would also have to have been a request that - * did not time out). - */ - while (cur_mid != last_mid) { - struct mid_q_entry *mid_entry; - unsigned int num_mids; - - collision = false; - if (cur_mid == 0) - cur_mid++; - - num_mids = 0; - list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { - ++num_mids; - if (mid_entry->mid == cur_mid && - mid_entry->mid_state == MID_REQUEST_SUBMITTED) { - /* This mid is in use, try a different one */ - collision = true; - break; - } - } - - /* - * if we have more than 32k mids in the list, then something - * is very wrong. Possibly a local user is trying to DoS the - * box by issuing long-running calls and SIGKILL'ing them. If - * we get to 2^16 mids then we're in big trouble as this - * function could loop forever. - * - * Go ahead and assign out the mid in this situation, but force - * an eventual reconnect to clean out the pending_mid_q. - */ - if (num_mids > 32768) - server->tcpStatus = CifsNeedReconnect; - - if (!collision) { - mid = (__u64)cur_mid; - server->CurrentMid = mid; - break; - } - cur_mid++; - } - spin_unlock(&GlobalMid_Lock); - return mid; -} - /* NB: MID can not be set if treeCon not passed in, in that case it is responsbility of caller to set the mid */ void @@ -306,8 +219,6 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , const struct cifs_tcon *treeCon, int word_count /* length of fixed section (word count) in two byte units */) { - struct list_head *temp_item; - struct cifs_ses *ses; char *temp = (char *) buffer; memset(temp, 0, 256); /* bigger than MAX_CIFS_HDR_SIZE */ @@ -336,52 +247,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , /* Uid is not converted */ buffer->Uid = treeCon->ses->Suid; - buffer->Mid = GetNextMid(treeCon->ses->server); - if (multiuser_mount != 0) { - /* For the multiuser case, there are few obvious technically */ - /* possible mechanisms to match the local linux user (uid) */ - /* to a valid remote smb user (smb_uid): */ - /* 1) Query Winbind (or other local pam/nss daemon */ - /* for userid/password/logon_domain or credential */ - /* 2) Query Winbind for uid to sid to username mapping */ - /* and see if we have a matching password for existing*/ - /* session for that user perhas getting password by */ - /* adding a new pam_cifs module that stores passwords */ - /* so that the cifs vfs can get at that for all logged*/ - /* on users */ - /* 3) (Which is the mechanism we have chosen) */ - /* Search through sessions to the same server for a */ - /* a match on the uid that was passed in on mount */ - /* with the current processes uid (or euid?) and use */ - /* that smb uid. If no existing smb session for */ - /* that uid found, use the default smb session ie */ - /* the smb session for the volume mounted which is */ - /* the same as would be used if the multiuser mount */ - /* flag were disabled. */ - - /* BB Add support for establishing new tCon and SMB Session */ - /* with userid/password pairs found on the smb session */ - /* for other target tcp/ip addresses BB */ - if (current_fsuid() != treeCon->ses->linux_uid) { - cFYI(1, "Multiuser mode and UID " - "did not match tcon uid"); - spin_lock(&cifs_tcp_ses_lock); - list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) { - ses = list_entry(temp_item, struct cifs_ses, smb_ses_list); - if (ses->linux_uid == current_fsuid()) { - if (ses->server == treeCon->ses->server) { - cFYI(1, "found matching uid substitute right smb_uid"); - buffer->Uid = ses->Suid; - break; - } else { - /* BB eventually call cifs_setup_session here */ - cFYI(1, "local UID found but no smb sess with this server exists"); - } - } - } - spin_unlock(&cifs_tcp_ses_lock); - } - } + buffer->Mid = get_next_mid(treeCon->ses->server); } if (treeCon->Flags & SMB_SHARE_IS_IN_DFS) buffer->Flags2 |= SMBFLG2_DFS; @@ -700,22 +566,3 @@ backup_cred(struct cifs_sb_info *cifs_sb) return false; } - -void -cifs_add_credits(struct TCP_Server_Info *server, const unsigned int add) -{ - spin_lock(&server->req_lock); - server->credits += add; - server->in_flight--; - spin_unlock(&server->req_lock); - wake_up(&server->request_q); -} - -void -cifs_set_credits(struct TCP_Server_Info *server, const int val) -{ - spin_lock(&server->req_lock); - server->credits = val; - server->oplocks = val > 1 ? enable_oplocks : false; - spin_unlock(&server->req_lock); -} diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index e2bbc683e01..0a8224d1c4c 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -219,6 +219,7 @@ int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb, static int initiate_cifs_search(const int xid, struct file *file) { + __u16 search_flags; int rc = 0; char *full_path = NULL; struct cifsFileInfo *cifsFile; @@ -270,8 +271,12 @@ ffirst_retry: cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO; } + search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; + if (backup_cred(cifs_sb)) + search_flags |= CIFS_SEARCH_BACKUP_SEARCH; + rc = CIFSFindFirst(xid, pTcon, full_path, cifs_sb->local_nls, - &cifsFile->netfid, &cifsFile->srch_inf, + &cifsFile->netfid, search_flags, &cifsFile->srch_inf, cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR, CIFS_DIR_SEP(cifs_sb)); if (rc == 0) @@ -502,11 +507,13 @@ static int cifs_save_resume_key(const char *current_entry, static int find_cifs_entry(const int xid, struct cifs_tcon *pTcon, struct file *file, char **ppCurrentEntry, int *num_to_ret) { + __u16 search_flags; int rc = 0; int pos_in_buf = 0; loff_t first_entry_in_buffer; loff_t index_to_find = file->f_pos; struct cifsFileInfo *cifsFile = file->private_data; + struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); /* check if index in the buffer */ if ((cifsFile == NULL) || (ppCurrentEntry == NULL) || @@ -560,10 +567,14 @@ static int find_cifs_entry(const int xid, struct cifs_tcon *pTcon, cifsFile); } + search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; + if (backup_cred(cifs_sb)) + search_flags |= CIFS_SEARCH_BACKUP_SEARCH; + while ((index_to_find >= cifsFile->srch_inf.index_of_last_entry) && (rc == 0) && !cifsFile->srch_inf.endOfSearch) { cFYI(1, "calling findnext2"); - rc = CIFSFindNext(xid, pTcon, cifsFile->netfid, + rc = CIFSFindNext(xid, pTcon, cifsFile->netfid, search_flags, &cifsFile->srch_inf); /* FindFirst/Next set last_entry to NULL on malformed reply */ if (cifsFile->srch_inf.last_entry) diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c new file mode 100644 index 00000000000..6dec38f5522 --- /dev/null +++ b/fs/cifs/smb1ops.c @@ -0,0 +1,243 @@ +/* + * SMB1 (CIFS) version specific operations + * + * Copyright (c) 2012, Jeff Layton <jlayton@redhat.com> + * + * This library is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License v2 as published + * by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include "cifsglob.h" +#include "cifsproto.h" +#include "cifs_debug.h" +#include "cifspdu.h" + +/* + * An NT cancel request header looks just like the original request except: + * + * The Command is SMB_COM_NT_CANCEL + * The WordCount is zeroed out + * The ByteCount is zeroed out + * + * This function mangles an existing request buffer into a + * SMB_COM_NT_CANCEL request and then sends it. + */ +static int +send_nt_cancel(struct TCP_Server_Info *server, void *buf, + struct mid_q_entry *mid) +{ + int rc = 0; + struct smb_hdr *in_buf = (struct smb_hdr *)buf; + + /* -4 for RFC1001 length and +2 for BCC field */ + in_buf->smb_buf_length = cpu_to_be32(sizeof(struct smb_hdr) - 4 + 2); + in_buf->Command = SMB_COM_NT_CANCEL; + in_buf->WordCount = 0; + put_bcc(0, in_buf); + + mutex_lock(&server->srv_mutex); + rc = cifs_sign_smb(in_buf, server, &mid->sequence_number); + if (rc) { + mutex_unlock(&server->srv_mutex); + return rc; + } + rc = smb_send(server, in_buf, be32_to_cpu(in_buf->smb_buf_length)); + mutex_unlock(&server->srv_mutex); + + cFYI(1, "issued NT_CANCEL for mid %u, rc = %d", + in_buf->Mid, rc); + + return rc; +} + +static bool +cifs_compare_fids(struct cifsFileInfo *ob1, struct cifsFileInfo *ob2) +{ + return ob1->netfid == ob2->netfid; +} + +static unsigned int +cifs_read_data_offset(char *buf) +{ + READ_RSP *rsp = (READ_RSP *)buf; + return le16_to_cpu(rsp->DataOffset); +} + +static unsigned int +cifs_read_data_length(char *buf) +{ + READ_RSP *rsp = (READ_RSP *)buf; + return (le16_to_cpu(rsp->DataLengthHigh) << 16) + + le16_to_cpu(rsp->DataLength); +} + +static struct mid_q_entry * +cifs_find_mid(struct TCP_Server_Info *server, char *buffer) +{ + struct smb_hdr *buf = (struct smb_hdr *)buffer; + struct mid_q_entry *mid; + + spin_lock(&GlobalMid_Lock); + list_for_each_entry(mid, &server->pending_mid_q, qhead) { + if (mid->mid == buf->Mid && + mid->mid_state == MID_REQUEST_SUBMITTED && + le16_to_cpu(mid->command) == buf->Command) { + spin_unlock(&GlobalMid_Lock); + return mid; + } + } + spin_unlock(&GlobalMid_Lock); + return NULL; +} + +static void +cifs_add_credits(struct TCP_Server_Info *server, const unsigned int add) +{ + spin_lock(&server->req_lock); + server->credits += add; + server->in_flight--; + spin_unlock(&server->req_lock); + wake_up(&server->request_q); +} + +static void +cifs_set_credits(struct TCP_Server_Info *server, const int val) +{ + spin_lock(&server->req_lock); + server->credits = val; + server->oplocks = val > 1 ? enable_oplocks : false; + spin_unlock(&server->req_lock); +} + +static int * +cifs_get_credits_field(struct TCP_Server_Info *server) +{ + return &server->credits; +} + +/* + * Find a free multiplex id (SMB mid). Otherwise there could be + * mid collisions which might cause problems, demultiplexing the + * wrong response to this request. Multiplex ids could collide if + * one of a series requests takes much longer than the others, or + * if a very large number of long lived requests (byte range + * locks or FindNotify requests) are pending. No more than + * 64K-1 requests can be outstanding at one time. If no + * mids are available, return zero. A future optimization + * could make the combination of mids and uid the key we use + * to demultiplex on (rather than mid alone). + * In addition to the above check, the cifs demultiplex + * code already used the command code as a secondary + * check of the frame and if signing is negotiated the + * response would be discarded if the mid were the same + * but the signature was wrong. Since the mid is not put in the + * pending queue until later (when it is about to be dispatched) + * we do have to limit the number of outstanding requests + * to somewhat less than 64K-1 although it is hard to imagine + * so many threads being in the vfs at one time. + */ +static __u64 +cifs_get_next_mid(struct TCP_Server_Info *server) +{ + __u64 mid = 0; + __u16 last_mid, cur_mid; + bool collision; + + spin_lock(&GlobalMid_Lock); + + /* mid is 16 bit only for CIFS/SMB */ + cur_mid = (__u16)((server->CurrentMid) & 0xffff); + /* we do not want to loop forever */ + last_mid = cur_mid; + cur_mid++; + + /* + * This nested loop looks more expensive than it is. + * In practice the list of pending requests is short, + * fewer than 50, and the mids are likely to be unique + * on the first pass through the loop unless some request + * takes longer than the 64 thousand requests before it + * (and it would also have to have been a request that + * did not time out). + */ + while (cur_mid != last_mid) { + struct mid_q_entry *mid_entry; + unsigned int num_mids; + + collision = false; + if (cur_mid == 0) + cur_mid++; + + num_mids = 0; + list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) { + ++num_mids; + if (mid_entry->mid == cur_mid && + mid_entry->mid_state == MID_REQUEST_SUBMITTED) { + /* This mid is in use, try a different one */ + collision = true; + break; + } + } + + /* + * if we have more than 32k mids in the list, then something + * is very wrong. Possibly a local user is trying to DoS the + * box by issuing long-running calls and SIGKILL'ing them. If + * we get to 2^16 mids then we're in big trouble as this + * function could loop forever. + * + * Go ahead and assign out the mid in this situation, but force + * an eventual reconnect to clean out the pending_mid_q. + */ + if (num_mids > 32768) + server->tcpStatus = CifsNeedReconnect; + + if (!collision) { + mid = (__u64)cur_mid; + server->CurrentMid = mid; + break; + } + cur_mid++; + } + spin_unlock(&GlobalMid_Lock); + return mid; +} + +struct smb_version_operations smb1_operations = { + .send_cancel = send_nt_cancel, + .compare_fids = cifs_compare_fids, + .setup_request = cifs_setup_request, + .check_receive = cifs_check_receive, + .add_credits = cifs_add_credits, + .set_credits = cifs_set_credits, + .get_credits_field = cifs_get_credits_field, + .get_next_mid = cifs_get_next_mid, + .read_data_offset = cifs_read_data_offset, + .read_data_length = cifs_read_data_length, + .map_error = map_smb_to_linux_error, + .find_mid = cifs_find_mid, + .check_message = checkSMB, + .dump_detail = cifs_dump_detail, + .is_oplock_break = is_valid_oplock_break, +}; + +struct smb_version_values smb1_values = { + .version_string = SMB1_VERSION_STRING, + .large_lock_type = LOCKING_ANDX_LARGE_FILES, + .exclusive_lock_type = 0, + .shared_lock_type = LOCKING_ANDX_SHARED_LOCK, + .unlock_lock_type = 0, + .header_size = sizeof(struct smb_hdr), + .max_header_size = MAX_CIFS_HDR_SIZE, + .read_rsp_size = sizeof(READ_RSP), +}; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c new file mode 100644 index 00000000000..f065e89756a --- /dev/null +++ b/fs/cifs/smb2ops.c @@ -0,0 +1,27 @@ +/* + * SMB2 version specific operations + * + * Copyright (c) 2012, Jeff Layton <jlayton@redhat.com> + * + * This library is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License v2 as published + * by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See + * the GNU Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with this library; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include "cifsglob.h" + +struct smb_version_operations smb21_operations = { +}; + +struct smb_version_values smb21_values = { + .version_string = SMB21_VERSION_STRING, +}; diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 0961336513d..3097ee58fd7 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -304,7 +304,8 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int optype, static int wait_for_free_request(struct TCP_Server_Info *server, const int optype) { - return wait_for_free_credits(server, optype, get_credits_field(server)); + return wait_for_free_credits(server, optype, + server->ops->get_credits_field(server)); } static int allocate_mid(struct cifs_ses *ses, struct smb_hdr *in_buf, @@ -396,7 +397,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, rc = cifs_setup_async_request(server, iov, nvec, &mid); if (rc) { mutex_unlock(&server->srv_mutex); - cifs_add_credits(server, 1); + add_credits(server, 1); wake_up(&server->request_q); return rc; } @@ -418,7 +419,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct kvec *iov, return rc; out_err: delete_mid(mid); - cifs_add_credits(server, 1); + add_credits(server, 1); wake_up(&server->request_q); return rc; } @@ -483,41 +484,11 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server) return rc; } -/* - * An NT cancel request header looks just like the original request except: - * - * The Command is SMB_COM_NT_CANCEL - * The WordCount is zeroed out - * The ByteCount is zeroed out - * - * This function mangles an existing request buffer into a - * SMB_COM_NT_CANCEL request and then sends it. - */ -static int -send_nt_cancel(struct TCP_Server_Info *server, struct smb_hdr *in_buf, - struct mid_q_entry *mid) +static inline int +send_cancel(struct TCP_Server_Info *server, void *buf, struct mid_q_entry *mid) { - int rc = 0; - - /* -4 for RFC1001 length and +2 for BCC field */ - in_buf->smb_buf_length = cpu_to_be32(sizeof(struct smb_hdr) - 4 + 2); - in_buf->Command = SMB_COM_NT_CANCEL; - in_buf->WordCount = 0; - put_bcc(0, in_buf); - - mutex_lock(&server->srv_mutex); - rc = cifs_sign_smb(in_buf, server, &mid->sequence_number); - if (rc) { - mutex_unlock(&server->srv_mutex); - return rc; - } - rc = smb_send(server, in_buf, be32_to_cpu(in_buf->smb_buf_length)); - mutex_unlock(&server->srv_mutex); - - cFYI(1, "issued NT_CANCEL for mid %u, rc = %d", - in_buf->Mid, rc); - - return rc; + return server->ops->send_cancel ? + server->ops->send_cancel(server, buf, mid) : 0; } int @@ -544,7 +515,7 @@ cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server, return map_smb_to_linux_error(mid->resp_buf, log_error); } -static int +int cifs_setup_request(struct cifs_ses *ses, struct kvec *iov, unsigned int nvec, struct mid_q_entry **ret_mid) { @@ -607,12 +578,12 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, mutex_lock(&ses->server->srv_mutex); - rc = cifs_setup_request(ses, iov, n_vec, &midQ); + rc = ses->server->ops->setup_request(ses, iov, n_vec, &midQ); if (rc) { mutex_unlock(&ses->server->srv_mutex); cifs_small_buf_release(buf); /* Update # of requests on wire to server */ - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -636,13 +607,13 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(ses->server, midQ); if (rc != 0) { - send_nt_cancel(ses->server, (struct smb_hdr *)buf, midQ); + send_cancel(ses->server, buf, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { midQ->callback = DeleteMidQEntry; spin_unlock(&GlobalMid_Lock); cifs_small_buf_release(buf); - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } spin_unlock(&GlobalMid_Lock); @@ -652,7 +623,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, rc = cifs_sync_mid_result(midQ, ses->server); if (rc != 0) { - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -670,14 +641,15 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, else *pRespBufType = CIFS_SMALL_BUFFER; - rc = cifs_check_receive(midQ, ses->server, flags & CIFS_LOG_ERROR); + rc = ses->server->ops->check_receive(midQ, ses->server, + flags & CIFS_LOG_ERROR); /* mark it so buf will not be freed by delete_mid */ if ((flags & CIFS_NO_RESP) == 0) midQ->resp_buf = NULL; out: delete_mid(midQ); - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -727,7 +699,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, if (rc) { mutex_unlock(&ses->server->srv_mutex); /* Update # of requests on wire to server */ - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -753,13 +725,13 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = wait_for_response(ses->server, midQ); if (rc != 0) { - send_nt_cancel(ses->server, in_buf, midQ); + send_cancel(ses->server, in_buf, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { /* no longer considered to be "in-flight" */ midQ->callback = DeleteMidQEntry; spin_unlock(&GlobalMid_Lock); - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } spin_unlock(&GlobalMid_Lock); @@ -767,7 +739,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = cifs_sync_mid_result(midQ, ses->server); if (rc != 0) { - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -783,7 +755,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses, rc = cifs_check_receive(midQ, ses->server, 0); out: delete_mid(midQ); - cifs_add_credits(ses->server, 1); + add_credits(ses->server, 1); return rc; } @@ -807,7 +779,7 @@ send_lock_cancel(const unsigned int xid, struct cifs_tcon *tcon, pSMB->LockType = LOCKING_ANDX_CANCEL_LOCK|LOCKING_ANDX_LARGE_FILES; pSMB->Timeout = 0; - pSMB->hdr.Mid = GetNextMid(ses->server); + pSMB->hdr.Mid = get_next_mid(ses->server); return SendReceive(xid, ses, in_buf, out_buf, &bytes_returned, 0); @@ -898,7 +870,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, if (in_buf->Command == SMB_COM_TRANSACTION2) { /* POSIX lock. We send a NT_CANCEL SMB to cause the blocking lock to return. */ - rc = send_nt_cancel(ses->server, in_buf, midQ); + rc = send_cancel(ses->server, in_buf, midQ); if (rc) { delete_mid(midQ); return rc; @@ -919,7 +891,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon, rc = wait_for_response(ses->server, midQ); if (rc) { - send_nt_cancel(ses->server, in_buf, midQ); + send_cancel(ses->server, in_buf, midQ); spin_lock(&GlobalMid_Lock); if (midQ->mid_state == MID_REQUEST_SUBMITTED) { /* no longer considered to be "in-flight" */ diff --git a/fs/coda/inode.c b/fs/coda/inode.c index 2870597b5c9..f1813120d75 100644 --- a/fs/coda/inode.c +++ b/fs/coda/inode.c @@ -244,7 +244,7 @@ static void coda_put_super(struct super_block *sb) static void coda_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); coda_cache_clear_inode(inode); } diff --git a/fs/compat.c b/fs/compat.c index f2944ace7a7..6161255fac4 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -144,8 +144,8 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; @@ -532,7 +532,7 @@ out: ssize_t compat_rw_copy_check_uvector(int type, const struct compat_iovec __user *uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, int check_access) + struct iovec **ret_pointer) { compat_ssize_t tot_len; struct iovec *iov = *ret_pointer = fast_pointer; @@ -579,7 +579,7 @@ ssize_t compat_rw_copy_check_uvector(int type, } if (len < 0) /* size_t not fitting in compat_ssize_t .. */ goto out; - if (check_access && + if (type >= 0 && !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { ret = -EFAULT; goto out; @@ -871,12 +871,12 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, { int error; struct file *file; + int fput_needed; struct compat_readdir_callback buf; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.result = 0; buf.dirent = dirent; @@ -885,8 +885,7 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, if (buf.result) error = buf.result; - fput(file); -out: + fput_light(file, fput_needed); return error; } @@ -953,16 +952,15 @@ asmlinkage long compat_sys_getdents(unsigned int fd, struct file * file; struct compat_linux_dirent __user * lastdirent; struct compat_getdents_callback buf; + int fput_needed; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; + return -EFAULT; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.current_dir = dirent; buf.previous = NULL; @@ -979,8 +977,7 @@ asmlinkage long compat_sys_getdents(unsigned int fd, else error = count - buf.count; } - fput(file); -out: + fput_light(file, fput_needed); return error; } @@ -1041,16 +1038,15 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, struct file * file; struct linux_dirent64 __user * lastdirent; struct compat_getdents_callback64 buf; + int fput_needed; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; + return -EFAULT; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.current_dir = dirent; buf.previous = NULL; @@ -1068,8 +1064,7 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, else error = count - buf.count; } - fput(file); -out: + fput_light(file, fput_needed); return error; } #endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */ @@ -1094,7 +1089,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, goto out; tot_len = compat_rw_copy_check_uvector(type, uvector, nr_segs, - UIO_FASTIOV, iovstack, &iov, 1); + UIO_FASTIOV, iovstack, &iov); if (tot_len == 0) { ret = 0; goto out; @@ -1547,7 +1542,6 @@ asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg) compat_ptr(a.exp), compat_ptr(a.tvp)); } -#ifdef HAVE_SET_RESTORE_SIGMASK static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, @@ -1670,11 +1664,9 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, return ret; } -#endif /* HAVE_SET_RESTORE_SIGMASK */ #ifdef CONFIG_EPOLL -#ifdef HAVE_SET_RESTORE_SIGMASK asmlinkage long compat_sys_epoll_pwait(int epfd, struct compat_epoll_event __user *events, int maxevents, int timeout, @@ -1718,7 +1710,6 @@ asmlinkage long compat_sys_epoll_pwait(int epfd, return err; } -#endif /* HAVE_SET_RESTORE_SIGMASK */ #endif /* CONFIG_EPOLL */ diff --git a/fs/dcache.c b/fs/dcache.c index b60ddc41d78..40469044088 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -141,18 +141,25 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, * Compare 2 name strings, return 0 if they match, otherwise non-zero. * The strings are both count bytes long, and count is non-zero. */ -static inline int dentry_cmp(const unsigned char *cs, size_t scount, - const unsigned char *ct, size_t tcount) -{ #ifdef CONFIG_DCACHE_WORD_ACCESS - unsigned long a,b,mask; - if (unlikely(scount != tcount)) - return 1; +#include <asm/word-at-a-time.h> +/* + * NOTE! 'cs' and 'scount' come from a dentry, so it has a + * aligned allocation for this particular component. We don't + * strictly need the load_unaligned_zeropad() safety, but it + * doesn't hurt either. + * + * In contrast, 'ct' and 'tcount' can be from a pathname, and do + * need the careful unaligned handling. + */ +static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) +{ + unsigned long a,b,mask; for (;;) { a = *(unsigned long *)cs; - b = *(unsigned long *)ct; + b = load_unaligned_zeropad(ct); if (tcount < sizeof(unsigned long)) break; if (unlikely(a != b)) @@ -165,10 +172,12 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount, } mask = ~(~0ul << tcount*8); return unlikely(!!((a ^ b) & mask)); +} + #else - if (scount != tcount) - return 1; +static inline int dentry_string_cmp(const unsigned char *cs, const unsigned char *ct, unsigned tcount) +{ do { if (*cs != *ct) return 1; @@ -177,7 +186,32 @@ static inline int dentry_cmp(const unsigned char *cs, size_t scount, tcount--; } while (tcount); return 0; +} + #endif + +static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *ct, unsigned tcount) +{ + const unsigned char *cs; + /* + * Be careful about RCU walk racing with rename: + * use ACCESS_ONCE to fetch the name pointer. + * + * NOTE! Even if a rename will mean that the length + * was not loaded atomically, we don't care. The + * RCU walk will check the sequence count eventually, + * and catch it. And we won't overrun the buffer, + * because we're reading the name pointer atomically, + * and a dentry name is guaranteed to be properly + * terminated with a NUL byte. + * + * End result: even if 'len' is wrong, we'll exit + * early because the data cannot match (there can + * be no NUL in the ct/tcount data) + */ + cs = ACCESS_ONCE(dentry->d_name.name); + smp_read_barrier_depends(); + return dentry_string_cmp(cs, ct, tcount); } static void __d_free(struct rcu_head *head) @@ -1240,6 +1274,13 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) if (!dentry) return NULL; + /* + * We guarantee that the inline name is always NUL-terminated. + * This way the memcpy() done by the name switching in rename + * will still always have a NUL at the end, even if we might + * be overwriting an internal NUL character + */ + dentry->d_iname[DNAME_INLINE_LEN-1] = 0; if (name->len > DNAME_INLINE_LEN-1) { dname = kmalloc(name->len + 1, GFP_KERNEL); if (!dname) { @@ -1249,13 +1290,16 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) } else { dname = dentry->d_iname; } - dentry->d_name.name = dname; dentry->d_name.len = name->len; dentry->d_name.hash = name->hash; memcpy(dname, name->name, name->len); dname[name->len] = 0; + /* Make sure we always see the terminating NUL character */ + smp_wmb(); + dentry->d_name.name = dname; + dentry->d_count = 1; dentry->d_flags = 0; spin_lock_init(&dentry->d_lock); @@ -1421,18 +1465,18 @@ static struct dentry *__d_instantiate_unique(struct dentry *entry, } list_for_each_entry(alias, &inode->i_dentry, d_alias) { - struct qstr *qstr = &alias->d_name; - /* * Don't need alias->d_lock here, because aliases with * d_parent == entry->d_parent are not subject to name or * parent changes, because the parent inode i_mutex is held. */ - if (qstr->hash != hash) + if (alias->d_name.hash != hash) continue; if (alias->d_parent != entry->d_parent) continue; - if (dentry_cmp(qstr->name, qstr->len, name, len)) + if (alias->d_name.len != len) + continue; + if (dentry_cmp(alias, name, len)) continue; __dget(alias); return alias; @@ -1471,7 +1515,7 @@ struct dentry *d_make_root(struct inode *root_inode) struct dentry *res = NULL; if (root_inode) { - static const struct qstr name = { .name = "/", .len = 1 }; + static const struct qstr name = QSTR_INIT("/", 1); res = __d_alloc(root_inode->i_sb, &name); if (res) @@ -1709,6 +1753,48 @@ err_out: } EXPORT_SYMBOL(d_add_ci); +/* + * Do the slow-case of the dentry name compare. + * + * Unlike the dentry_cmp() function, we need to atomically + * load the name, length and inode information, so that the + * filesystem can rely on them, and can use the 'name' and + * 'len' information without worrying about walking off the + * end of memory etc. + * + * Thus the read_seqcount_retry() and the "duplicate" info + * in arguments (the low-level filesystem should not look + * at the dentry inode or name contents directly, since + * rename can change them while we're in RCU mode). + */ +enum slow_d_compare { + D_COMP_OK, + D_COMP_NOMATCH, + D_COMP_SEQRETRY, +}; + +static noinline enum slow_d_compare slow_dentry_cmp( + const struct dentry *parent, + struct inode *inode, + struct dentry *dentry, + unsigned int seq, + const struct qstr *name) +{ + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; + struct inode *i = dentry->d_inode; + + if (read_seqcount_retry(&dentry->d_seq, seq)) { + cpu_relax(); + return D_COMP_SEQRETRY; + } + if (parent->d_op->d_compare(parent, inode, + dentry, i, + tlen, tname, name)) + return D_COMP_NOMATCH; + return D_COMP_OK; +} + /** * __d_lookup_rcu - search for a dentry (racy, store-free) * @parent: parent dentry @@ -1735,15 +1821,17 @@ EXPORT_SYMBOL(d_add_ci); * the returned dentry, so long as its parent's seqlock is checked after the * child is looked up. Thus, an interlocking stepping of sequence lock checks * is formed, giving integrity down the path walk. + * + * NOTE! The caller *has* to check the resulting dentry against the sequence + * number we've returned before using any of the resulting dentry state! */ struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, - unsigned *seqp, struct inode **inode) + unsigned *seqp, struct inode *inode) { - unsigned int len = name->len; - unsigned int hash = name->hash; + u64 hashlen = name->hash_len; const unsigned char *str = name->name; - struct hlist_bl_head *b = d_hash(parent, hash); + struct hlist_bl_head *b = d_hash(parent, hashlen_hash(hashlen)); struct hlist_bl_node *node; struct dentry *dentry; @@ -1769,49 +1857,47 @@ struct dentry *__d_lookup_rcu(const struct dentry *parent, */ hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { unsigned seq; - struct inode *i; - const char *tname; - int tlen; - - if (dentry->d_name.hash != hash) - continue; seqretry: - seq = read_seqcount_begin(&dentry->d_seq); + /* + * The dentry sequence count protects us from concurrent + * renames, and thus protects inode, parent and name fields. + * + * The caller must perform a seqcount check in order + * to do anything useful with the returned dentry, + * including using the 'd_inode' pointer. + * + * NOTE! We do a "raw" seqcount_begin here. That means that + * we don't wait for the sequence count to stabilize if it + * is in the middle of a sequence change. If we do the slow + * dentry compare, we will do seqretries until it is stable, + * and if we end up with a successful lookup, we actually + * want to exit RCU lookup anyway. + */ + seq = raw_seqcount_begin(&dentry->d_seq); if (dentry->d_parent != parent) continue; if (d_unhashed(dentry)) continue; - tlen = dentry->d_name.len; - tname = dentry->d_name.name; - i = dentry->d_inode; - prefetch(tname); - /* - * This seqcount check is required to ensure name and - * len are loaded atomically, so as not to walk off the - * edge of memory when walking. If we could load this - * atomically some other way, we could drop this check. - */ - if (read_seqcount_retry(&dentry->d_seq, seq)) - goto seqretry; + *seqp = seq; + if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) { - if (parent->d_op->d_compare(parent, *inode, - dentry, i, - tlen, tname, name)) + if (dentry->d_name.hash != hashlen_hash(hashlen)) continue; - } else { - if (dentry_cmp(tname, tlen, str, len)) + switch (slow_dentry_cmp(parent, inode, dentry, seq, name)) { + case D_COMP_OK: + return dentry; + case D_COMP_NOMATCH: continue; + default: + goto seqretry; + } } - /* - * No extra seqcount check is required after the name - * compare. The caller must perform a seqcount check in - * order to do anything useful with the returned dentry - * anyway. - */ - *seqp = seq; - *inode = i; - return dentry; + + if (dentry->d_name.hash_len != hashlen) + continue; + if (!dentry_cmp(dentry, str, hashlen_len(hashlen))) + return dentry; } return NULL; } @@ -1890,8 +1976,6 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name) rcu_read_lock(); hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) { - const char *tname; - int tlen; if (dentry->d_name.hash != hash) continue; @@ -1906,15 +1990,17 @@ struct dentry *__d_lookup(struct dentry *parent, struct qstr *name) * It is safe to compare names since d_move() cannot * change the qstr (protected by d_lock). */ - tlen = dentry->d_name.len; - tname = dentry->d_name.name; if (parent->d_flags & DCACHE_OP_COMPARE) { + int tlen = dentry->d_name.len; + const char *tname = dentry->d_name.name; if (parent->d_op->d_compare(parent, parent->d_inode, dentry, dentry->d_inode, tlen, tname, name)) goto next; } else { - if (dentry_cmp(tname, tlen, str, len)) + if (dentry->d_name.len != len) + goto next; + if (dentry_cmp(dentry, str, len)) goto next; } @@ -2489,7 +2575,7 @@ static int prepend_path(const struct path *path, bool slash = false; int error = 0; - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); while (dentry != root->dentry || vfsmnt != root->mnt) { struct dentry * parent; @@ -2520,7 +2606,7 @@ static int prepend_path(const struct path *path, error = prepend(buffer, buflen, "/", 1); out: - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return error; global_root: @@ -3007,6 +3093,7 @@ static void __init dcache_init_early(void) HASH_EARLY, &d_hash_shift, &d_hash_mask, + 0, 0); for (loop = 0; loop < (1U << d_hash_shift); loop++) @@ -3037,6 +3124,7 @@ static void __init dcache_init(void) 0, &d_hash_shift, &d_hash_mask, + 0, 0); for (loop = 0; loop < (1U << d_hash_shift); loop++) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 5dfafdd1dbd..2340f6978d6 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -20,6 +20,7 @@ #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/io.h> +#include <linux/slab.h> static ssize_t default_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) @@ -520,6 +521,133 @@ struct dentry *debugfs_create_blob(const char *name, umode_t mode, } EXPORT_SYMBOL_GPL(debugfs_create_blob); +struct array_data { + void *array; + u32 elements; +}; + +static int u32_array_open(struct inode *inode, struct file *file) +{ + file->private_data = NULL; + return nonseekable_open(inode, file); +} + +static size_t format_array(char *buf, size_t bufsize, const char *fmt, + u32 *array, u32 array_size) +{ + size_t ret = 0; + u32 i; + + for (i = 0; i < array_size; i++) { + size_t len; + + len = snprintf(buf, bufsize, fmt, array[i]); + len++; /* ' ' or '\n' */ + ret += len; + + if (buf) { + buf += len; + bufsize -= len; + buf[-1] = (i == array_size-1) ? '\n' : ' '; + } + } + + ret++; /* \0 */ + if (buf) + *buf = '\0'; + + return ret; +} + +static char *format_array_alloc(const char *fmt, u32 *array, + u32 array_size) +{ + size_t len = format_array(NULL, 0, fmt, array, array_size); + char *ret; + + ret = kmalloc(len, GFP_KERNEL); + if (ret == NULL) + return NULL; + + format_array(ret, len, fmt, array, array_size); + return ret; +} + +static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len, + loff_t *ppos) +{ + struct inode *inode = file->f_path.dentry->d_inode; + struct array_data *data = inode->i_private; + size_t size; + + if (*ppos == 0) { + if (file->private_data) { + kfree(file->private_data); + file->private_data = NULL; + } + + file->private_data = format_array_alloc("%u", data->array, + data->elements); + } + + size = 0; + if (file->private_data) + size = strlen(file->private_data); + + return simple_read_from_buffer(buf, len, ppos, + file->private_data, size); +} + +static int u32_array_release(struct inode *inode, struct file *file) +{ + kfree(file->private_data); + + return 0; +} + +static const struct file_operations u32_array_fops = { + .owner = THIS_MODULE, + .open = u32_array_open, + .release = u32_array_release, + .read = u32_array_read, + .llseek = no_llseek, +}; + +/** + * debugfs_create_u32_array - create a debugfs file that is used to read u32 + * array. + * @name: a pointer to a string containing the name of the file to create. + * @mode: the permission that the file should have. + * @parent: a pointer to the parent dentry for this file. This should be a + * directory dentry if set. If this parameter is %NULL, then the + * file will be created in the root of the debugfs filesystem. + * @array: u32 array that provides data. + * @elements: total number of elements in the array. + * + * This function creates a file in debugfs with the given name that exports + * @array as data. If the @mode variable is so set it can be read from. + * Writing is not supported. Seek within the file is also not supported. + * Once array is created its size can not be changed. + * + * The function returns a pointer to dentry on success. If debugfs is not + * enabled in the kernel, the value -%ENODEV will be returned. + */ +struct dentry *debugfs_create_u32_array(const char *name, umode_t mode, + struct dentry *parent, + u32 *array, u32 elements) +{ + struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL); + + if (data == NULL) + return NULL; + + data->array = array; + data->elements = elements; + + return debugfs_create_file(name, mode, parent, data, &u32_array_fops); +} +EXPORT_SYMBOL_GPL(debugfs_create_u32_array); + #ifdef CONFIG_HAS_IOMEM /* diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 10f5e0b484d..979c1e309c7 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -98,8 +98,8 @@ static struct vfsmount *devpts_mnt; struct pts_mount_opts { int setuid; int setgid; - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; umode_t mode; umode_t ptmxmode; int newinstance; @@ -158,11 +158,13 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode) static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) { char *p; + kuid_t uid; + kgid_t gid; opts->setuid = 0; opts->setgid = 0; - opts->uid = 0; - opts->gid = 0; + opts->uid = GLOBAL_ROOT_UID; + opts->gid = GLOBAL_ROOT_GID; opts->mode = DEVPTS_DEFAULT_MODE; opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; opts->max = NR_UNIX98_PTY_MAX; @@ -184,13 +186,19 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) case Opt_uid: if (match_int(&args[0], &option)) return -EINVAL; - opts->uid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) + return -EINVAL; + opts->uid = uid; opts->setuid = 1; break; case Opt_gid: if (match_int(&args[0], &option)) return -EINVAL; - opts->gid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) + return -EINVAL; + opts->gid = gid; opts->setgid = 1; break; case Opt_mode: @@ -315,9 +323,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root) struct pts_mount_opts *opts = &fsi->mount_opts; if (opts->setuid) - seq_printf(seq, ",uid=%u", opts->uid); + seq_printf(seq, ",uid=%u", from_kuid_munged(&init_user_ns, opts->uid)); if (opts->setgid) - seq_printf(seq, ",gid=%u", opts->gid); + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid)); seq_printf(seq, ",mode=%03o", opts->mode); #ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode); diff --git a/fs/direct-io.c b/fs/direct-io.c index f4aadd15b61..0c85fae3766 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -145,50 +145,6 @@ struct dio { static struct kmem_cache *dio_cache __read_mostly; -static void __inode_dio_wait(struct inode *inode) -{ - wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); - DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); - - do { - prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE); - if (atomic_read(&inode->i_dio_count)) - schedule(); - } while (atomic_read(&inode->i_dio_count)); - finish_wait(wq, &q.wait); -} - -/** - * inode_dio_wait - wait for outstanding DIO requests to finish - * @inode: inode to wait for - * - * Waits for all pending direct I/O requests to finish so that we can - * proceed with a truncate or equivalent operation. - * - * Must be called under a lock that serializes taking new references - * to i_dio_count, usually by inode->i_mutex. - */ -void inode_dio_wait(struct inode *inode) -{ - if (atomic_read(&inode->i_dio_count)) - __inode_dio_wait(inode); -} -EXPORT_SYMBOL(inode_dio_wait); - -/* - * inode_dio_done - signal finish of a direct I/O requests - * @inode: inode the direct I/O happens on - * - * This is called once we've finished processing a direct I/O request, - * and is used to wake up callers waiting for direct I/O to be quiesced. - */ -void inode_dio_done(struct inode *inode) -{ - if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); -} -EXPORT_SYMBOL(inode_dio_done); - /* * How many pages are in the queue? */ diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index 90e5997262e..63dc19c54d5 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -310,6 +310,7 @@ void dlm_callback_resume(struct dlm_ls *ls) } mutex_unlock(&ls->ls_cb_mutex); - log_debug(ls, "dlm_callback_resume %d", count); + if (count) + log_debug(ls, "dlm_callback_resume %d", count); } diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h index 3a564d197e9..bc342f7ac3a 100644 --- a/fs/dlm/dlm_internal.h +++ b/fs/dlm/dlm_internal.h @@ -38,6 +38,7 @@ #include <linux/miscdevice.h> #include <linux/mutex.h> #include <linux/idr.h> +#include <linux/ratelimit.h> #include <asm/uaccess.h> #include <linux/dlm.h> @@ -74,6 +75,13 @@ do { \ (ls)->ls_name , ##args); \ } while (0) +#define log_limit(ls, fmt, args...) \ +do { \ + if (dlm_config.ci_log_debug) \ + printk_ratelimited(KERN_DEBUG "dlm: %s: " fmt "\n", \ + (ls)->ls_name , ##args); \ +} while (0) + #define DLM_ASSERT(x, do) \ { \ if (!(x)) \ @@ -263,6 +271,8 @@ struct dlm_lkb { ktime_t lkb_last_cast_time; /* for debugging */ ktime_t lkb_last_bast_time; /* for debugging */ + uint64_t lkb_recover_seq; /* from ls_recover_seq */ + char *lkb_lvbptr; struct dlm_lksb *lkb_lksb; /* caller's status block */ void (*lkb_astfn) (void *astparam); @@ -317,7 +327,7 @@ enum rsb_flags { RSB_NEW_MASTER, RSB_NEW_MASTER2, RSB_RECOVER_CONVERT, - RSB_LOCKS_PURGED, + RSB_RECOVER_GRANT, }; static inline void rsb_set_flag(struct dlm_rsb *r, enum rsb_flags flag) @@ -563,6 +573,7 @@ struct dlm_ls { struct mutex ls_requestqueue_mutex; struct dlm_rcom *ls_recover_buf; int ls_recover_nodeid; /* for debugging */ + unsigned int ls_recover_locks_in; /* for log info */ uint64_t ls_rcom_seq; spinlock_t ls_rcom_spin; struct list_head ls_recover_list; @@ -589,6 +600,7 @@ struct dlm_ls { #define LSFL_UEVENT_WAIT 5 #define LSFL_TIMEWARN 6 #define LSFL_CB_DELAY 7 +#define LSFL_NODIR 8 /* much of this is just saving user space pointers associated with the lock that we pass back to the user lib with an ast */ @@ -636,7 +648,7 @@ static inline int dlm_recovery_stopped(struct dlm_ls *ls) static inline int dlm_no_directory(struct dlm_ls *ls) { - return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0; + return test_bit(LSFL_NODIR, &ls->ls_flags); } int dlm_netlink_init(void); diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index fa5c07d51dc..bdafb65a523 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -160,11 +160,12 @@ static const int __quecvt_compat_matrix[8][8] = { void dlm_print_lkb(struct dlm_lkb *lkb) { - printk(KERN_ERR "lkb: nodeid %d id %x remid %x exflags %x flags %x\n" - " status %d rqmode %d grmode %d wait_type %d\n", + printk(KERN_ERR "lkb: nodeid %d id %x remid %x exflags %x flags %x " + "sts %d rq %d gr %d wait_type %d wait_nodeid %d seq %llu\n", lkb->lkb_nodeid, lkb->lkb_id, lkb->lkb_remid, lkb->lkb_exflags, lkb->lkb_flags, lkb->lkb_status, lkb->lkb_rqmode, - lkb->lkb_grmode, lkb->lkb_wait_type); + lkb->lkb_grmode, lkb->lkb_wait_type, lkb->lkb_wait_nodeid, + (unsigned long long)lkb->lkb_recover_seq); } static void dlm_print_rsb(struct dlm_rsb *r) @@ -251,8 +252,6 @@ static inline int is_process_copy(struct dlm_lkb *lkb) static inline int is_master_copy(struct dlm_lkb *lkb) { - if (lkb->lkb_flags & DLM_IFL_MSTCPY) - DLM_ASSERT(lkb->lkb_nodeid, dlm_print_lkb(lkb);); return (lkb->lkb_flags & DLM_IFL_MSTCPY) ? 1 : 0; } @@ -479,6 +478,9 @@ static int _search_rsb(struct dlm_ls *ls, char *name, int len, int b, kref_get(&r->res_ref); goto out; } + if (error == -ENOTBLK) + goto out; + error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, flags, &r); if (error) goto out; @@ -586,6 +588,23 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen, return error; } +static void dlm_dump_rsb_hash(struct dlm_ls *ls, uint32_t hash) +{ + struct rb_node *n; + struct dlm_rsb *r; + int i; + + for (i = 0; i < ls->ls_rsbtbl_size; i++) { + spin_lock(&ls->ls_rsbtbl[i].lock); + for (n = rb_first(&ls->ls_rsbtbl[i].keep); n; n = rb_next(n)) { + r = rb_entry(n, struct dlm_rsb, res_hashnode); + if (r->res_hash == hash) + dlm_dump_rsb(r); + } + spin_unlock(&ls->ls_rsbtbl[i].lock); + } +} + /* This is only called to add a reference when the code already holds a valid reference to the rsb, so there's no need for locking. */ @@ -1064,8 +1083,9 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype, goto out_del; } - log_error(ls, "remwait error %x reply %d flags %x no wait_type", - lkb->lkb_id, mstype, lkb->lkb_flags); + log_error(ls, "remwait error %x remote %d %x msg %d flags %x no wait", + lkb->lkb_id, ms ? ms->m_header.h_nodeid : 0, lkb->lkb_remid, + mstype, lkb->lkb_flags); return -1; out_del: @@ -1498,13 +1518,13 @@ static void _grant_lock(struct dlm_rsb *r, struct dlm_lkb *lkb) } lkb->lkb_rqmode = DLM_LOCK_IV; + lkb->lkb_highbast = 0; } static void grant_lock(struct dlm_rsb *r, struct dlm_lkb *lkb) { set_lvb_lock(r, lkb); _grant_lock(r, lkb); - lkb->lkb_highbast = 0; } static void grant_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb, @@ -1737,6 +1757,18 @@ static int _can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now) return 1; /* + * Even if the convert is compat with all granted locks, + * QUECVT forces it behind other locks on the convert queue. + */ + + if (now && conv && (lkb->lkb_exflags & DLM_LKF_QUECVT)) { + if (list_empty(&r->res_convertqueue)) + return 1; + else + goto out; + } + + /* * The NOORDER flag is set to avoid the standard vms rules on grant * order. */ @@ -1854,7 +1886,8 @@ static int can_be_granted(struct dlm_rsb *r, struct dlm_lkb *lkb, int now, /* Returns the highest requested mode of all blocked conversions; sets cw if there's a blocked conversion to DLM_LOCK_CW. */ -static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw) +static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw, + unsigned int *count) { struct dlm_lkb *lkb, *s; int hi, demoted, quit, grant_restart, demote_restart; @@ -1873,6 +1906,8 @@ static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw) if (can_be_granted(r, lkb, 0, &deadlk)) { grant_lock_pending(r, lkb); grant_restart = 1; + if (count) + (*count)++; continue; } @@ -1906,14 +1941,17 @@ static int grant_pending_convert(struct dlm_rsb *r, int high, int *cw) return max_t(int, high, hi); } -static int grant_pending_wait(struct dlm_rsb *r, int high, int *cw) +static int grant_pending_wait(struct dlm_rsb *r, int high, int *cw, + unsigned int *count) { struct dlm_lkb *lkb, *s; list_for_each_entry_safe(lkb, s, &r->res_waitqueue, lkb_statequeue) { - if (can_be_granted(r, lkb, 0, NULL)) + if (can_be_granted(r, lkb, 0, NULL)) { grant_lock_pending(r, lkb); - else { + if (count) + (*count)++; + } else { high = max_t(int, lkb->lkb_rqmode, high); if (lkb->lkb_rqmode == DLM_LOCK_CW) *cw = 1; @@ -1942,16 +1980,20 @@ static int lock_requires_bast(struct dlm_lkb *gr, int high, int cw) return 0; } -static void grant_pending_locks(struct dlm_rsb *r) +static void grant_pending_locks(struct dlm_rsb *r, unsigned int *count) { struct dlm_lkb *lkb, *s; int high = DLM_LOCK_IV; int cw = 0; - DLM_ASSERT(is_master(r), dlm_dump_rsb(r);); + if (!is_master(r)) { + log_print("grant_pending_locks r nodeid %d", r->res_nodeid); + dlm_dump_rsb(r); + return; + } - high = grant_pending_convert(r, high, &cw); - high = grant_pending_wait(r, high, &cw); + high = grant_pending_convert(r, high, &cw, count); + high = grant_pending_wait(r, high, &cw, count); if (high == DLM_LOCK_IV) return; @@ -2487,7 +2529,7 @@ static int do_convert(struct dlm_rsb *r, struct dlm_lkb *lkb) before we try again to grant this one. */ if (is_demoted(lkb)) { - grant_pending_convert(r, DLM_LOCK_IV, NULL); + grant_pending_convert(r, DLM_LOCK_IV, NULL, NULL); if (_can_be_granted(r, lkb, 1)) { grant_lock(r, lkb); queue_cast(r, lkb, 0); @@ -2515,7 +2557,7 @@ static void do_convert_effects(struct dlm_rsb *r, struct dlm_lkb *lkb, { switch (error) { case 0: - grant_pending_locks(r); + grant_pending_locks(r, NULL); /* grant_pending_locks also sends basts */ break; case -EAGAIN: @@ -2538,7 +2580,7 @@ static int do_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb) static void do_unlock_effects(struct dlm_rsb *r, struct dlm_lkb *lkb, int error) { - grant_pending_locks(r); + grant_pending_locks(r, NULL); } /* returns: 0 did nothing, -DLM_ECANCEL canceled lock */ @@ -2559,7 +2601,7 @@ static void do_cancel_effects(struct dlm_rsb *r, struct dlm_lkb *lkb, int error) { if (error) - grant_pending_locks(r); + grant_pending_locks(r, NULL); } /* @@ -3360,7 +3402,7 @@ static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms) return error; } -static void receive_request(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_request(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; @@ -3400,14 +3442,15 @@ static void receive_request(struct dlm_ls *ls, struct dlm_message *ms) error = 0; if (error) dlm_put_lkb(lkb); - return; + return 0; fail: setup_stub_lkb(ls, ms); send_request_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error); + return error; } -static void receive_convert(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; @@ -3417,6 +3460,15 @@ static void receive_convert(struct dlm_ls *ls, struct dlm_message *ms) if (error) goto fail; + if (lkb->lkb_remid != ms->m_lkid) { + log_error(ls, "receive_convert %x remid %x recover_seq %llu " + "remote %d %x", lkb->lkb_id, lkb->lkb_remid, + (unsigned long long)lkb->lkb_recover_seq, + ms->m_header.h_nodeid, ms->m_lkid); + error = -ENOENT; + goto fail; + } + r = lkb->lkb_resource; hold_rsb(r); @@ -3444,14 +3496,15 @@ static void receive_convert(struct dlm_ls *ls, struct dlm_message *ms) unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); - return; + return 0; fail: setup_stub_lkb(ls, ms); send_convert_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error); + return error; } -static void receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; @@ -3461,6 +3514,14 @@ static void receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) if (error) goto fail; + if (lkb->lkb_remid != ms->m_lkid) { + log_error(ls, "receive_unlock %x remid %x remote %d %x", + lkb->lkb_id, lkb->lkb_remid, + ms->m_header.h_nodeid, ms->m_lkid); + error = -ENOENT; + goto fail; + } + r = lkb->lkb_resource; hold_rsb(r); @@ -3485,14 +3546,15 @@ static void receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); - return; + return 0; fail: setup_stub_lkb(ls, ms); send_unlock_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error); + return error; } -static void receive_cancel(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_cancel(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; @@ -3520,25 +3582,23 @@ static void receive_cancel(struct dlm_ls *ls, struct dlm_message *ms) unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); - return; + return 0; fail: setup_stub_lkb(ls, ms); send_cancel_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error); + return error; } -static void receive_grant(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_grant(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; int error; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_grant from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; r = lkb->lkb_resource; @@ -3558,20 +3618,18 @@ static void receive_grant(struct dlm_ls *ls, struct dlm_message *ms) unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); + return 0; } -static void receive_bast(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; int error; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_bast from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; r = lkb->lkb_resource; @@ -3583,10 +3641,12 @@ static void receive_bast(struct dlm_ls *ls, struct dlm_message *ms) goto out; queue_bast(r, lkb, ms->m_bastmode); + lkb->lkb_highbast = ms->m_bastmode; out: unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); + return 0; } static void receive_lookup(struct dlm_ls *ls, struct dlm_message *ms) @@ -3641,18 +3701,15 @@ static void receive_purge(struct dlm_ls *ls, struct dlm_message *ms) do_purge(ls, ms->m_nodeid, ms->m_pid); } -static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; struct dlm_rsb *r; int error, mstype, result; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_request_reply from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; r = lkb->lkb_resource; hold_rsb(r); @@ -3664,8 +3721,13 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) mstype = lkb->lkb_wait_type; error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY); - if (error) + if (error) { + log_error(ls, "receive_request_reply %x remote %d %x result %d", + lkb->lkb_id, ms->m_header.h_nodeid, ms->m_lkid, + ms->m_result); + dlm_dump_rsb(r); goto out; + } /* Optimization: the dir node was also the master, so it took our lookup as a request and sent request reply instead of lookup reply */ @@ -3743,6 +3805,7 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms) unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); + return 0; } static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, @@ -3781,8 +3844,11 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb, break; default: - log_error(r->res_ls, "receive_convert_reply %x error %d", - lkb->lkb_id, ms->m_result); + log_error(r->res_ls, "receive_convert_reply %x remote %d %x %d", + lkb->lkb_id, ms->m_header.h_nodeid, ms->m_lkid, + ms->m_result); + dlm_print_rsb(r); + dlm_print_lkb(lkb); } } @@ -3809,20 +3875,18 @@ static void _receive_convert_reply(struct dlm_lkb *lkb, struct dlm_message *ms) put_rsb(r); } -static void receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; int error; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_convert_reply from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; _receive_convert_reply(lkb, ms); dlm_put_lkb(lkb); + return 0; } static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms) @@ -3861,20 +3925,18 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms) put_rsb(r); } -static void receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; int error; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_unlock_reply from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; _receive_unlock_reply(lkb, ms); dlm_put_lkb(lkb); + return 0; } static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) @@ -3913,20 +3975,18 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms) put_rsb(r); } -static void receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms) +static int receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms) { struct dlm_lkb *lkb; int error; error = find_lkb(ls, ms->m_remid, &lkb); - if (error) { - log_debug(ls, "receive_cancel_reply from %d no lkb %x", - ms->m_header.h_nodeid, ms->m_remid); - return; - } + if (error) + return error; _receive_cancel_reply(lkb, ms); dlm_put_lkb(lkb); + return 0; } static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) @@ -3937,7 +3997,7 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) error = find_lkb(ls, ms->m_lkid, &lkb); if (error) { - log_error(ls, "receive_lookup_reply no lkb"); + log_error(ls, "receive_lookup_reply no lkid %x", ms->m_lkid); return; } @@ -3981,8 +4041,11 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms) dlm_put_lkb(lkb); } -static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) +static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms, + uint32_t saved_seq) { + int error = 0, noent = 0; + if (!dlm_is_member(ls, ms->m_header.h_nodeid)) { log_debug(ls, "ignore non-member message %d from %d %x %x %d", ms->m_type, ms->m_header.h_nodeid, ms->m_lkid, @@ -3995,47 +4058,50 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) /* messages sent to a master node */ case DLM_MSG_REQUEST: - receive_request(ls, ms); + error = receive_request(ls, ms); break; case DLM_MSG_CONVERT: - receive_convert(ls, ms); + error = receive_convert(ls, ms); break; case DLM_MSG_UNLOCK: - receive_unlock(ls, ms); + error = receive_unlock(ls, ms); break; case DLM_MSG_CANCEL: - receive_cancel(ls, ms); + noent = 1; + error = receive_cancel(ls, ms); break; /* messages sent from a master node (replies to above) */ case DLM_MSG_REQUEST_REPLY: - receive_request_reply(ls, ms); + error = receive_request_reply(ls, ms); break; case DLM_MSG_CONVERT_REPLY: - receive_convert_reply(ls, ms); + error = receive_convert_reply(ls, ms); break; case DLM_MSG_UNLOCK_REPLY: - receive_unlock_reply(ls, ms); + error = receive_unlock_reply(ls, ms); break; case DLM_MSG_CANCEL_REPLY: - receive_cancel_reply(ls, ms); + error = receive_cancel_reply(ls, ms); break; /* messages sent from a master node (only two types of async msg) */ case DLM_MSG_GRANT: - receive_grant(ls, ms); + noent = 1; + error = receive_grant(ls, ms); break; case DLM_MSG_BAST: - receive_bast(ls, ms); + noent = 1; + error = receive_bast(ls, ms); break; /* messages sent to a dir node */ @@ -4063,6 +4129,37 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms) default: log_error(ls, "unknown message type %d", ms->m_type); } + + /* + * When checking for ENOENT, we're checking the result of + * find_lkb(m_remid): + * + * The lock id referenced in the message wasn't found. This may + * happen in normal usage for the async messages and cancel, so + * only use log_debug for them. + * + * Some errors are expected and normal. + */ + + if (error == -ENOENT && noent) { + log_debug(ls, "receive %d no %x remote %d %x saved_seq %u", + ms->m_type, ms->m_remid, ms->m_header.h_nodeid, + ms->m_lkid, saved_seq); + } else if (error == -ENOENT) { + log_error(ls, "receive %d no %x remote %d %x saved_seq %u", + ms->m_type, ms->m_remid, ms->m_header.h_nodeid, + ms->m_lkid, saved_seq); + + if (ms->m_type == DLM_MSG_CONVERT) + dlm_dump_rsb_hash(ls, ms->m_hash); + } + + if (error == -EINVAL) { + log_error(ls, "receive %d inval from %d lkid %x remid %x " + "saved_seq %u", + ms->m_type, ms->m_header.h_nodeid, + ms->m_lkid, ms->m_remid, saved_seq); + } } /* If the lockspace is in recovery mode (locking stopped), then normal @@ -4080,16 +4177,17 @@ static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms, dlm_add_requestqueue(ls, nodeid, ms); } else { dlm_wait_requestqueue(ls); - _receive_message(ls, ms); + _receive_message(ls, ms, 0); } } /* This is called by dlm_recoverd to process messages that were saved on the requestqueue. */ -void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms) +void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms, + uint32_t saved_seq) { - _receive_message(ls, ms); + _receive_message(ls, ms, saved_seq); } /* This is called by the midcomms layer when something is received for @@ -4125,9 +4223,11 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid) ls = dlm_find_lockspace_global(hd->h_lockspace); if (!ls) { - if (dlm_config.ci_log_debug) - log_print("invalid lockspace %x from %d cmd %d type %d", - hd->h_lockspace, nodeid, hd->h_cmd, type); + if (dlm_config.ci_log_debug) { + printk_ratelimited(KERN_DEBUG "dlm: invalid lockspace " + "%u from %d cmd %d type %d\n", + hd->h_lockspace, nodeid, hd->h_cmd, type); + } if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS) dlm_send_ls_not_ready(nodeid, &p->rcom); @@ -4175,15 +4275,13 @@ static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb, /* A waiting lkb needs recovery if the master node has failed, or the master node is changing (only when no directory is used) */ -static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb) +static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb, + int dir_nodeid) { - if (dlm_is_removed(ls, lkb->lkb_nodeid)) + if (dlm_no_directory(ls)) return 1; - if (!dlm_no_directory(ls)) - return 0; - - if (dlm_dir_nodeid(lkb->lkb_resource) != lkb->lkb_nodeid) + if (dlm_is_removed(ls, lkb->lkb_wait_nodeid)) return 1; return 0; @@ -4200,6 +4298,7 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) struct dlm_lkb *lkb, *safe; struct dlm_message *ms_stub; int wait_type, stub_unlock_result, stub_cancel_result; + int dir_nodeid; ms_stub = kmalloc(sizeof(struct dlm_message), GFP_KERNEL); if (!ms_stub) { @@ -4211,13 +4310,21 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) list_for_each_entry_safe(lkb, safe, &ls->ls_waiters, lkb_wait_reply) { + dir_nodeid = dlm_dir_nodeid(lkb->lkb_resource); + /* exclude debug messages about unlocks because there can be so many and they aren't very interesting */ if (lkb->lkb_wait_type != DLM_MSG_UNLOCK) { - log_debug(ls, "recover_waiter %x nodeid %d " - "msg %d to %d", lkb->lkb_id, lkb->lkb_nodeid, - lkb->lkb_wait_type, lkb->lkb_wait_nodeid); + log_debug(ls, "waiter %x remote %x msg %d r_nodeid %d " + "lkb_nodeid %d wait_nodeid %d dir_nodeid %d", + lkb->lkb_id, + lkb->lkb_remid, + lkb->lkb_wait_type, + lkb->lkb_resource->res_nodeid, + lkb->lkb_nodeid, + lkb->lkb_wait_nodeid, + dir_nodeid); } /* all outstanding lookups, regardless of destination will be @@ -4228,7 +4335,7 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls) continue; } - if (!waiter_needs_recovery(ls, lkb)) + if (!waiter_needs_recovery(ls, lkb, dir_nodeid)) continue; wait_type = lkb->lkb_wait_type; @@ -4361,8 +4468,11 @@ int dlm_recover_waiters_post(struct dlm_ls *ls) ou = is_overlap_unlock(lkb); err = 0; - log_debug(ls, "recover_waiter %x nodeid %d msg %d r_nodeid %d", - lkb->lkb_id, lkb->lkb_nodeid, mstype, r->res_nodeid); + log_debug(ls, "waiter %x remote %x msg %d r_nodeid %d " + "lkb_nodeid %d wait_nodeid %d dir_nodeid %d " + "overlap %d %d", lkb->lkb_id, lkb->lkb_remid, mstype, + r->res_nodeid, lkb->lkb_nodeid, lkb->lkb_wait_nodeid, + dlm_dir_nodeid(r), oc, ou); /* At this point we assume that we won't get a reply to any previous op or overlap op on this lock. First, do a big @@ -4414,9 +4524,12 @@ int dlm_recover_waiters_post(struct dlm_ls *ls) } } - if (err) - log_error(ls, "recover_waiters_post %x %d %x %d %d", - lkb->lkb_id, mstype, lkb->lkb_flags, oc, ou); + if (err) { + log_error(ls, "waiter %x msg %d r_nodeid %d " + "dir_nodeid %d overlap %d %d", + lkb->lkb_id, mstype, r->res_nodeid, + dlm_dir_nodeid(r), oc, ou); + } unlock_rsb(r); put_rsb(r); dlm_put_lkb(lkb); @@ -4425,112 +4538,177 @@ int dlm_recover_waiters_post(struct dlm_ls *ls) return error; } -static void purge_queue(struct dlm_rsb *r, struct list_head *queue, - int (*test)(struct dlm_ls *ls, struct dlm_lkb *lkb)) +static void purge_mstcpy_list(struct dlm_ls *ls, struct dlm_rsb *r, + struct list_head *list) { - struct dlm_ls *ls = r->res_ls; struct dlm_lkb *lkb, *safe; - list_for_each_entry_safe(lkb, safe, queue, lkb_statequeue) { - if (test(ls, lkb)) { - rsb_set_flag(r, RSB_LOCKS_PURGED); - del_lkb(r, lkb); - /* this put should free the lkb */ - if (!dlm_put_lkb(lkb)) - log_error(ls, "purged lkb not released"); - } + list_for_each_entry_safe(lkb, safe, list, lkb_statequeue) { + if (!is_master_copy(lkb)) + continue; + + /* don't purge lkbs we've added in recover_master_copy for + the current recovery seq */ + + if (lkb->lkb_recover_seq == ls->ls_recover_seq) + continue; + + del_lkb(r, lkb); + + /* this put should free the lkb */ + if (!dlm_put_lkb(lkb)) + log_error(ls, "purged mstcpy lkb not released"); } } -static int purge_dead_test(struct dlm_ls *ls, struct dlm_lkb *lkb) +void dlm_purge_mstcpy_locks(struct dlm_rsb *r) { - return (is_master_copy(lkb) && dlm_is_removed(ls, lkb->lkb_nodeid)); -} + struct dlm_ls *ls = r->res_ls; -static int purge_mstcpy_test(struct dlm_ls *ls, struct dlm_lkb *lkb) -{ - return is_master_copy(lkb); + purge_mstcpy_list(ls, r, &r->res_grantqueue); + purge_mstcpy_list(ls, r, &r->res_convertqueue); + purge_mstcpy_list(ls, r, &r->res_waitqueue); } -static void purge_dead_locks(struct dlm_rsb *r) +static void purge_dead_list(struct dlm_ls *ls, struct dlm_rsb *r, + struct list_head *list, + int nodeid_gone, unsigned int *count) { - purge_queue(r, &r->res_grantqueue, &purge_dead_test); - purge_queue(r, &r->res_convertqueue, &purge_dead_test); - purge_queue(r, &r->res_waitqueue, &purge_dead_test); -} + struct dlm_lkb *lkb, *safe; -void dlm_purge_mstcpy_locks(struct dlm_rsb *r) -{ - purge_queue(r, &r->res_grantqueue, &purge_mstcpy_test); - purge_queue(r, &r->res_convertqueue, &purge_mstcpy_test); - purge_queue(r, &r->res_waitqueue, &purge_mstcpy_test); + list_for_each_entry_safe(lkb, safe, list, lkb_statequeue) { + if (!is_master_copy(lkb)) + continue; + + if ((lkb->lkb_nodeid == nodeid_gone) || + dlm_is_removed(ls, lkb->lkb_nodeid)) { + + del_lkb(r, lkb); + + /* this put should free the lkb */ + if (!dlm_put_lkb(lkb)) + log_error(ls, "purged dead lkb not released"); + + rsb_set_flag(r, RSB_RECOVER_GRANT); + + (*count)++; + } + } } /* Get rid of locks held by nodes that are gone. */ -int dlm_purge_locks(struct dlm_ls *ls) +void dlm_recover_purge(struct dlm_ls *ls) { struct dlm_rsb *r; + struct dlm_member *memb; + int nodes_count = 0; + int nodeid_gone = 0; + unsigned int lkb_count = 0; + + /* cache one removed nodeid to optimize the common + case of a single node removed */ - log_debug(ls, "dlm_purge_locks"); + list_for_each_entry(memb, &ls->ls_nodes_gone, list) { + nodes_count++; + nodeid_gone = memb->nodeid; + } + + if (!nodes_count) + return; down_write(&ls->ls_root_sem); list_for_each_entry(r, &ls->ls_root_list, res_root_list) { hold_rsb(r); lock_rsb(r); - if (is_master(r)) - purge_dead_locks(r); + if (is_master(r)) { + purge_dead_list(ls, r, &r->res_grantqueue, + nodeid_gone, &lkb_count); + purge_dead_list(ls, r, &r->res_convertqueue, + nodeid_gone, &lkb_count); + purge_dead_list(ls, r, &r->res_waitqueue, + nodeid_gone, &lkb_count); + } unlock_rsb(r); unhold_rsb(r); - - schedule(); + cond_resched(); } up_write(&ls->ls_root_sem); - return 0; + if (lkb_count) + log_debug(ls, "dlm_recover_purge %u locks for %u nodes", + lkb_count, nodes_count); } -static struct dlm_rsb *find_purged_rsb(struct dlm_ls *ls, int bucket) +static struct dlm_rsb *find_grant_rsb(struct dlm_ls *ls, int bucket) { struct rb_node *n; - struct dlm_rsb *r, *r_ret = NULL; + struct dlm_rsb *r; spin_lock(&ls->ls_rsbtbl[bucket].lock); for (n = rb_first(&ls->ls_rsbtbl[bucket].keep); n; n = rb_next(n)) { r = rb_entry(n, struct dlm_rsb, res_hashnode); - if (!rsb_flag(r, RSB_LOCKS_PURGED)) + + if (!rsb_flag(r, RSB_RECOVER_GRANT)) + continue; + rsb_clear_flag(r, RSB_RECOVER_GRANT); + if (!is_master(r)) continue; hold_rsb(r); - rsb_clear_flag(r, RSB_LOCKS_PURGED); - r_ret = r; - break; + spin_unlock(&ls->ls_rsbtbl[bucket].lock); + return r; } spin_unlock(&ls->ls_rsbtbl[bucket].lock); - return r_ret; + return NULL; } -void dlm_grant_after_purge(struct dlm_ls *ls) +/* + * Attempt to grant locks on resources that we are the master of. + * Locks may have become grantable during recovery because locks + * from departed nodes have been purged (or not rebuilt), allowing + * previously blocked locks to now be granted. The subset of rsb's + * we are interested in are those with lkb's on either the convert or + * waiting queues. + * + * Simplest would be to go through each master rsb and check for non-empty + * convert or waiting queues, and attempt to grant on those rsbs. + * Checking the queues requires lock_rsb, though, for which we'd need + * to release the rsbtbl lock. This would make iterating through all + * rsb's very inefficient. So, we rely on earlier recovery routines + * to set RECOVER_GRANT on any rsb's that we should attempt to grant + * locks for. + */ + +void dlm_recover_grant(struct dlm_ls *ls) { struct dlm_rsb *r; int bucket = 0; + unsigned int count = 0; + unsigned int rsb_count = 0; + unsigned int lkb_count = 0; while (1) { - r = find_purged_rsb(ls, bucket); + r = find_grant_rsb(ls, bucket); if (!r) { if (bucket == ls->ls_rsbtbl_size - 1) break; bucket++; continue; } + rsb_count++; + count = 0; lock_rsb(r); - if (is_master(r)) { - grant_pending_locks(r); - confirm_master(r, 0); - } + grant_pending_locks(r, &count); + lkb_count += count; + confirm_master(r, 0); unlock_rsb(r); put_rsb(r); - schedule(); + cond_resched(); } + + if (lkb_count) + log_debug(ls, "dlm_recover_grant %u locks on %u resources", + lkb_count, rsb_count); } static struct dlm_lkb *search_remid_list(struct list_head *head, int nodeid, @@ -4619,6 +4797,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf; struct dlm_rsb *r; struct dlm_lkb *lkb; + uint32_t remid = 0; int error; if (rl->rl_parent_lkid) { @@ -4626,14 +4805,31 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) goto out; } - error = find_rsb(ls, rl->rl_name, le16_to_cpu(rl->rl_namelen), - R_MASTER, &r); + remid = le32_to_cpu(rl->rl_lkid); + + /* In general we expect the rsb returned to be R_MASTER, but we don't + have to require it. Recovery of masters on one node can overlap + recovery of locks on another node, so one node can send us MSTCPY + locks before we've made ourselves master of this rsb. We can still + add new MSTCPY locks that we receive here without any harm; when + we make ourselves master, dlm_recover_masters() won't touch the + MSTCPY locks we've received early. */ + + error = find_rsb(ls, rl->rl_name, le16_to_cpu(rl->rl_namelen), 0, &r); if (error) goto out; + if (dlm_no_directory(ls) && (dlm_dir_nodeid(r) != dlm_our_nodeid())) { + log_error(ls, "dlm_recover_master_copy remote %d %x not dir", + rc->rc_header.h_nodeid, remid); + error = -EBADR; + put_rsb(r); + goto out; + } + lock_rsb(r); - lkb = search_remid(r, rc->rc_header.h_nodeid, le32_to_cpu(rl->rl_lkid)); + lkb = search_remid(r, rc->rc_header.h_nodeid, remid); if (lkb) { error = -EEXIST; goto out_remid; @@ -4652,19 +4848,25 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc) attach_lkb(r, lkb); add_lkb(r, lkb, rl->rl_status); error = 0; + ls->ls_recover_locks_in++; + + if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue)) + rsb_set_flag(r, RSB_RECOVER_GRANT); out_remid: /* this is the new value returned to the lock holder for saving in its process-copy lkb */ rl->rl_remid = cpu_to_le32(lkb->lkb_id); + lkb->lkb_recover_seq = ls->ls_recover_seq; + out_unlock: unlock_rsb(r); put_rsb(r); out: - if (error) - log_debug(ls, "recover_master_copy %d %x", error, - le32_to_cpu(rl->rl_lkid)); + if (error && error != -EEXIST) + log_debug(ls, "dlm_recover_master_copy remote %d %x error %d", + rc->rc_header.h_nodeid, remid, error); rl->rl_result = cpu_to_le32(error); return error; } @@ -4675,41 +4877,52 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc) struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf; struct dlm_rsb *r; struct dlm_lkb *lkb; - int error; + uint32_t lkid, remid; + int error, result; - error = find_lkb(ls, le32_to_cpu(rl->rl_lkid), &lkb); + lkid = le32_to_cpu(rl->rl_lkid); + remid = le32_to_cpu(rl->rl_remid); + result = le32_to_cpu(rl->rl_result); + + error = find_lkb(ls, lkid, &lkb); if (error) { - log_error(ls, "recover_process_copy no lkid %x", - le32_to_cpu(rl->rl_lkid)); + log_error(ls, "dlm_recover_process_copy no %x remote %d %x %d", + lkid, rc->rc_header.h_nodeid, remid, result); return error; } - DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb);); - - error = le32_to_cpu(rl->rl_result); - r = lkb->lkb_resource; hold_rsb(r); lock_rsb(r); - switch (error) { + if (!is_process_copy(lkb)) { + log_error(ls, "dlm_recover_process_copy bad %x remote %d %x %d", + lkid, rc->rc_header.h_nodeid, remid, result); + dlm_dump_rsb(r); + unlock_rsb(r); + put_rsb(r); + dlm_put_lkb(lkb); + return -EINVAL; + } + + switch (result) { case -EBADR: /* There's a chance the new master received our lock before dlm_recover_master_reply(), this wouldn't happen if we did a barrier between recover_masters and recover_locks. */ - log_debug(ls, "master copy not ready %x r %lx %s", lkb->lkb_id, - (unsigned long)r, r->res_name); + + log_debug(ls, "dlm_recover_process_copy %x remote %d %x %d", + lkid, rc->rc_header.h_nodeid, remid, result); + dlm_send_rcom_lock(r, lkb); goto out; case -EEXIST: - log_debug(ls, "master copy exists %x", lkb->lkb_id); - /* fall through */ case 0: - lkb->lkb_remid = le32_to_cpu(rl->rl_remid); + lkb->lkb_remid = remid; break; default: - log_error(ls, "dlm_recover_process_copy unknown error %d %x", - error, lkb->lkb_id); + log_error(ls, "dlm_recover_process_copy %x remote %d %x %d unk", + lkid, rc->rc_header.h_nodeid, remid, result); } /* an ack for dlm_recover_locks() which waits for replies from diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h index 1a255307f6f..c8b226c6280 100644 --- a/fs/dlm/lock.h +++ b/fs/dlm/lock.h @@ -15,7 +15,8 @@ void dlm_dump_rsb(struct dlm_rsb *r); void dlm_print_lkb(struct dlm_lkb *lkb); -void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms); +void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms, + uint32_t saved_seq); void dlm_receive_buffer(union dlm_packet *p, int nodeid); int dlm_modes_compat(int mode1, int mode2); void dlm_put_rsb(struct dlm_rsb *r); @@ -31,9 +32,9 @@ void dlm_adjust_timeouts(struct dlm_ls *ls); int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len, unsigned int flags, struct dlm_rsb **r_ret); -int dlm_purge_locks(struct dlm_ls *ls); +void dlm_recover_purge(struct dlm_ls *ls); void dlm_purge_mstcpy_locks(struct dlm_rsb *r); -void dlm_grant_after_purge(struct dlm_ls *ls); +void dlm_recover_grant(struct dlm_ls *ls); int dlm_recover_waiters_post(struct dlm_ls *ls); void dlm_recover_waiters_pre(struct dlm_ls *ls); int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc); diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index a1ea25face8..ca506abbdd3 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -74,6 +74,19 @@ static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len) return len; } +static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", dlm_no_directory(ls)); +} + +static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len) +{ + int val = simple_strtoul(buf, NULL, 0); + if (val == 1) + set_bit(LSFL_NODIR, &ls->ls_flags); + return len; +} + static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf) { uint32_t status = dlm_recover_status(ls); @@ -107,6 +120,12 @@ static struct dlm_attr dlm_attr_id = { .store = dlm_id_store }; +static struct dlm_attr dlm_attr_nodir = { + .attr = {.name = "nodir", .mode = S_IRUGO | S_IWUSR}, + .show = dlm_nodir_show, + .store = dlm_nodir_store +}; + static struct dlm_attr dlm_attr_recover_status = { .attr = {.name = "recover_status", .mode = S_IRUGO}, .show = dlm_recover_status_show @@ -121,6 +140,7 @@ static struct attribute *dlm_attrs[] = { &dlm_attr_control.attr, &dlm_attr_event.attr, &dlm_attr_id.attr, + &dlm_attr_nodir.attr, &dlm_attr_recover_status.attr, &dlm_attr_recover_nodeid.attr, NULL, diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 133ef6dc7cb..5c1b0e38c7a 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -142,6 +142,7 @@ struct writequeue_entry { static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; +static int dlm_allow_conn; /* Work queues */ static struct workqueue_struct *recv_workqueue; @@ -710,6 +711,13 @@ static int tcp_accept_from_sock(struct connection *con) struct connection *newcon; struct connection *addcon; + mutex_lock(&connections_lock); + if (!dlm_allow_conn) { + mutex_unlock(&connections_lock); + return -1; + } + mutex_unlock(&connections_lock); + memset(&peeraddr, 0, sizeof(peeraddr)); result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_TCP, &newsock); @@ -1503,6 +1511,7 @@ void dlm_lowcomms_stop(void) socket activity. */ mutex_lock(&connections_lock); + dlm_allow_conn = 0; foreach_conn(stop_conn); mutex_unlock(&connections_lock); @@ -1530,7 +1539,7 @@ int dlm_lowcomms_start(void) if (!dlm_local_count) { error = -ENOTCONN; log_print("no local IP address has been set"); - goto out; + goto fail; } error = -ENOMEM; @@ -1538,7 +1547,13 @@ int dlm_lowcomms_start(void) __alignof__(struct connection), 0, NULL); if (!con_cache) - goto out; + goto fail; + + error = work_start(); + if (error) + goto fail_destroy; + + dlm_allow_conn = 1; /* Start listening */ if (dlm_config.ci_protocol == 0) @@ -1548,20 +1563,17 @@ int dlm_lowcomms_start(void) if (error) goto fail_unlisten; - error = work_start(); - if (error) - goto fail_unlisten; - return 0; fail_unlisten: + dlm_allow_conn = 0; con = nodeid2con(0,0); if (con) { close_connection(con, false); kmem_cache_free(con_cache, con); } +fail_destroy: kmem_cache_destroy(con_cache); - -out: +fail: return error; } diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c index da64df7576e..7cd24bccd4f 100644 --- a/fs/dlm/memory.c +++ b/fs/dlm/memory.c @@ -21,21 +21,19 @@ static struct kmem_cache *rsb_cache; int __init dlm_memory_init(void) { - int ret = 0; - lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb), __alignof__(struct dlm_lkb), 0, NULL); if (!lkb_cache) - ret = -ENOMEM; + return -ENOMEM; rsb_cache = kmem_cache_create("dlm_rsb", sizeof(struct dlm_rsb), __alignof__(struct dlm_rsb), 0, NULL); if (!rsb_cache) { kmem_cache_destroy(lkb_cache); - ret = -ENOMEM; + return -ENOMEM; } - return ret; + return 0; } void dlm_memory_exit(void) diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c index ac5c616c969..64d3e2b958c 100644 --- a/fs/dlm/rcom.c +++ b/fs/dlm/rcom.c @@ -486,47 +486,50 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in) return 0; } -static int is_old_reply(struct dlm_ls *ls, struct dlm_rcom *rc) +/* Called by dlm_recv; corresponds to dlm_receive_message() but special + recovery-only comms are sent through here. */ + +void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) { + int lock_size = sizeof(struct dlm_rcom) + sizeof(struct rcom_lock); + int stop, reply = 0, lock = 0; + uint32_t status; uint64_t seq; - int rv = 0; switch (rc->rc_type) { + case DLM_RCOM_LOCK: + lock = 1; + break; + case DLM_RCOM_LOCK_REPLY: + lock = 1; + reply = 1; + break; case DLM_RCOM_STATUS_REPLY: case DLM_RCOM_NAMES_REPLY: case DLM_RCOM_LOOKUP_REPLY: - case DLM_RCOM_LOCK_REPLY: - spin_lock(&ls->ls_recover_lock); - seq = ls->ls_recover_seq; - spin_unlock(&ls->ls_recover_lock); - if (rc->rc_seq_reply != seq) { - log_debug(ls, "ignoring old reply %x from %d " - "seq_reply %llx expect %llx", - rc->rc_type, rc->rc_header.h_nodeid, - (unsigned long long)rc->rc_seq_reply, - (unsigned long long)seq); - rv = 1; - } - } - return rv; -} - -/* Called by dlm_recv; corresponds to dlm_receive_message() but special - recovery-only comms are sent through here. */ + reply = 1; + }; -void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid) -{ - int lock_size = sizeof(struct dlm_rcom) + sizeof(struct rcom_lock); + spin_lock(&ls->ls_recover_lock); + status = ls->ls_recover_status; + stop = test_bit(LSFL_RECOVERY_STOP, &ls->ls_flags); + seq = ls->ls_recover_seq; + spin_unlock(&ls->ls_recover_lock); - if (dlm_recovery_stopped(ls) && (rc->rc_type != DLM_RCOM_STATUS)) { - log_debug(ls, "ignoring recovery message %x from %d", - rc->rc_type, nodeid); + if ((stop && (rc->rc_type != DLM_RCOM_STATUS)) || + (reply && (rc->rc_seq_reply != seq)) || + (lock && !(status & DLM_RS_DIR))) { + log_limit(ls, "dlm_receive_rcom ignore msg %d " + "from %d %llu %llu recover seq %llu sts %x gen %u", + rc->rc_type, + nodeid, + (unsigned long long)rc->rc_seq, + (unsigned long long)rc->rc_seq_reply, + (unsigned long long)seq, + status, ls->ls_generation); goto out; } - if (is_old_reply(ls, rc)) - goto out; - switch (rc->rc_type) { case DLM_RCOM_STATUS: receive_rcom_status(ls, rc); diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c index 34d5adf1fce..7554e4dac6b 100644 --- a/fs/dlm/recover.c +++ b/fs/dlm/recover.c @@ -339,9 +339,12 @@ static void set_lock_master(struct list_head *queue, int nodeid) { struct dlm_lkb *lkb; - list_for_each_entry(lkb, queue, lkb_statequeue) - if (!(lkb->lkb_flags & DLM_IFL_MSTCPY)) + list_for_each_entry(lkb, queue, lkb_statequeue) { + if (!(lkb->lkb_flags & DLM_IFL_MSTCPY)) { lkb->lkb_nodeid = nodeid; + lkb->lkb_remid = 0; + } + } } static void set_master_lkbs(struct dlm_rsb *r) @@ -354,18 +357,16 @@ static void set_master_lkbs(struct dlm_rsb *r) /* * Propagate the new master nodeid to locks * The NEW_MASTER flag tells dlm_recover_locks() which rsb's to consider. - * The NEW_MASTER2 flag tells recover_lvb() and set_locks_purged() which + * The NEW_MASTER2 flag tells recover_lvb() and recover_grant() which * rsb's to consider. */ static void set_new_master(struct dlm_rsb *r, int nodeid) { - lock_rsb(r); r->res_nodeid = nodeid; set_master_lkbs(r); rsb_set_flag(r, RSB_NEW_MASTER); rsb_set_flag(r, RSB_NEW_MASTER2); - unlock_rsb(r); } /* @@ -376,9 +377,9 @@ static void set_new_master(struct dlm_rsb *r, int nodeid) static int recover_master(struct dlm_rsb *r) { struct dlm_ls *ls = r->res_ls; - int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid(); - - dir_nodeid = dlm_dir_nodeid(r); + int error, ret_nodeid; + int our_nodeid = dlm_our_nodeid(); + int dir_nodeid = dlm_dir_nodeid(r); if (dir_nodeid == our_nodeid) { error = dlm_dir_lookup(ls, our_nodeid, r->res_name, @@ -388,7 +389,9 @@ static int recover_master(struct dlm_rsb *r) if (ret_nodeid == our_nodeid) ret_nodeid = 0; + lock_rsb(r); set_new_master(r, ret_nodeid); + unlock_rsb(r); } else { recover_list_add(r); error = dlm_send_rcom_lookup(r, dir_nodeid); @@ -398,24 +401,33 @@ static int recover_master(struct dlm_rsb *r) } /* - * When not using a directory, most resource names will hash to a new static - * master nodeid and the resource will need to be remastered. + * All MSTCPY locks are purged and rebuilt, even if the master stayed the same. + * This is necessary because recovery can be started, aborted and restarted, + * causing the master nodeid to briefly change during the aborted recovery, and + * change back to the original value in the second recovery. The MSTCPY locks + * may or may not have been purged during the aborted recovery. Another node + * with an outstanding request in waiters list and a request reply saved in the + * requestqueue, cannot know whether it should ignore the reply and resend the + * request, or accept the reply and complete the request. It must do the + * former if the remote node purged MSTCPY locks, and it must do the later if + * the remote node did not. This is solved by always purging MSTCPY locks, in + * which case, the request reply would always be ignored and the request + * resent. */ static int recover_master_static(struct dlm_rsb *r) { - int master = dlm_dir_nodeid(r); + int dir_nodeid = dlm_dir_nodeid(r); + int new_master = dir_nodeid; - if (master == dlm_our_nodeid()) - master = 0; + if (dir_nodeid == dlm_our_nodeid()) + new_master = 0; - if (r->res_nodeid != master) { - if (is_master(r)) - dlm_purge_mstcpy_locks(r); - set_new_master(r, master); - return 1; - } - return 0; + lock_rsb(r); + dlm_purge_mstcpy_locks(r); + set_new_master(r, new_master); + unlock_rsb(r); + return 1; } /* @@ -481,7 +493,9 @@ int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc) if (nodeid == dlm_our_nodeid()) nodeid = 0; + lock_rsb(r); set_new_master(r, nodeid); + unlock_rsb(r); recover_list_del(r); if (recover_list_empty(ls)) @@ -556,8 +570,6 @@ int dlm_recover_locks(struct dlm_ls *ls) struct dlm_rsb *r; int error, count = 0; - log_debug(ls, "dlm_recover_locks"); - down_read(&ls->ls_root_sem); list_for_each_entry(r, &ls->ls_root_list, res_root_list) { if (is_master(r)) { @@ -584,7 +596,7 @@ int dlm_recover_locks(struct dlm_ls *ls) } up_read(&ls->ls_root_sem); - log_debug(ls, "dlm_recover_locks %d locks", count); + log_debug(ls, "dlm_recover_locks %d out", count); error = dlm_wait_function(ls, &recover_list_empty); out: @@ -721,21 +733,19 @@ static void recover_conversion(struct dlm_rsb *r) } /* We've become the new master for this rsb and waiting/converting locks may - need to be granted in dlm_grant_after_purge() due to locks that may have + need to be granted in dlm_recover_grant() due to locks that may have existed from a removed node. */ -static void set_locks_purged(struct dlm_rsb *r) +static void recover_grant(struct dlm_rsb *r) { if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue)) - rsb_set_flag(r, RSB_LOCKS_PURGED); + rsb_set_flag(r, RSB_RECOVER_GRANT); } void dlm_recover_rsbs(struct dlm_ls *ls) { struct dlm_rsb *r; - int count = 0; - - log_debug(ls, "dlm_recover_rsbs"); + unsigned int count = 0; down_read(&ls->ls_root_sem); list_for_each_entry(r, &ls->ls_root_list, res_root_list) { @@ -744,7 +754,7 @@ void dlm_recover_rsbs(struct dlm_ls *ls) if (rsb_flag(r, RSB_RECOVER_CONVERT)) recover_conversion(r); if (rsb_flag(r, RSB_NEW_MASTER2)) - set_locks_purged(r); + recover_grant(r); recover_lvb(r); count++; } @@ -754,7 +764,8 @@ void dlm_recover_rsbs(struct dlm_ls *ls) } up_read(&ls->ls_root_sem); - log_debug(ls, "dlm_recover_rsbs %d rsbs", count); + if (count) + log_debug(ls, "dlm_recover_rsbs %d done", count); } /* Create a single list of all root rsb's to be used during recovery */ diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c index 3780caf7ae0..f1a9073c083 100644 --- a/fs/dlm/recoverd.c +++ b/fs/dlm/recoverd.c @@ -54,7 +54,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) unsigned long start; int error, neg = 0; - log_debug(ls, "dlm_recover %llx", (unsigned long long)rv->seq); + log_debug(ls, "dlm_recover %llu", (unsigned long long)rv->seq); mutex_lock(&ls->ls_recoverd_active); @@ -84,6 +84,8 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } + ls->ls_recover_locks_in = 0; + dlm_set_recover_status(ls, DLM_RS_NODES); error = dlm_recover_members_wait(ls); @@ -130,7 +132,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) * Clear lkb's for departed nodes. */ - dlm_purge_locks(ls); + dlm_recover_purge(ls); /* * Get new master nodeid's for rsb's that were mastered on @@ -161,6 +163,9 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } + log_debug(ls, "dlm_recover_locks %u in", + ls->ls_recover_locks_in); + /* * Finalize state in master rsb's now that all locks can be * checked. This includes conversion resolution and lvb @@ -225,9 +230,9 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) goto fail; } - dlm_grant_after_purge(ls); + dlm_recover_grant(ls); - log_debug(ls, "dlm_recover %llx generation %u done: %u ms", + log_debug(ls, "dlm_recover %llu generation %u done: %u ms", (unsigned long long)rv->seq, ls->ls_generation, jiffies_to_msecs(jiffies - start)); mutex_unlock(&ls->ls_recoverd_active); @@ -237,7 +242,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv) fail: dlm_release_root_list(ls); - log_debug(ls, "dlm_recover %llx error %d", + log_debug(ls, "dlm_recover %llu error %d", (unsigned long long)rv->seq, error); mutex_unlock(&ls->ls_recoverd_active); return error; diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c index a44fa22890e..1695f1b0dd4 100644 --- a/fs/dlm/requestqueue.c +++ b/fs/dlm/requestqueue.c @@ -19,6 +19,7 @@ struct rq_entry { struct list_head list; + uint32_t recover_seq; int nodeid; struct dlm_message request; }; @@ -41,6 +42,7 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms) return; } + e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF; e->nodeid = nodeid; memcpy(&e->request, ms, ms->m_header.h_length); @@ -63,6 +65,7 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms) int dlm_process_requestqueue(struct dlm_ls *ls) { struct rq_entry *e; + struct dlm_message *ms; int error = 0; mutex_lock(&ls->ls_requestqueue_mutex); @@ -76,7 +79,15 @@ int dlm_process_requestqueue(struct dlm_ls *ls) e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list); mutex_unlock(&ls->ls_requestqueue_mutex); - dlm_receive_message_saved(ls, &e->request); + ms = &e->request; + + log_limit(ls, "dlm_process_requestqueue msg %d from %d " + "lkid %x remid %x result %d seq %u", + ms->m_type, ms->m_header.h_nodeid, + ms->m_lkid, ms->m_remid, ms->m_result, + e->recover_seq); + + dlm_receive_message_saved(ls, &e->request, e->recover_seq); mutex_lock(&ls->ls_requestqueue_mutex); list_del(&e->list); @@ -138,35 +149,7 @@ static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid) if (!dlm_no_directory(ls)) return 0; - /* with no directory, the master is likely to change as a part of - recovery; requests to/from the defunct master need to be purged */ - - switch (type) { - case DLM_MSG_REQUEST: - case DLM_MSG_CONVERT: - case DLM_MSG_UNLOCK: - case DLM_MSG_CANCEL: - /* we're no longer the master of this resource, the sender - will resend to the new master (see waiter_needs_recovery) */ - - if (dlm_hash2nodeid(ls, ms->m_hash) != dlm_our_nodeid()) - return 1; - break; - - case DLM_MSG_REQUEST_REPLY: - case DLM_MSG_CONVERT_REPLY: - case DLM_MSG_UNLOCK_REPLY: - case DLM_MSG_CANCEL_REPLY: - case DLM_MSG_GRANT: - /* this reply is from the former master of the resource, - we'll resend to the new master if needed */ - - if (dlm_hash2nodeid(ls, ms->m_hash) != nodeid) - return 1; - break; - } - - return 0; + return 1; } void dlm_purge_requestqueue(struct dlm_ls *ls) diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index ab35b113003..a07441a0a87 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -660,11 +660,10 @@ static int ecryptfs_readlink_lower(struct dentry *dentry, char **buf, { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); char *lower_buf; - size_t lower_bufsiz = PATH_MAX; mm_segment_t old_fs; int rc; - lower_buf = kmalloc(lower_bufsiz, GFP_KERNEL); + lower_buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!lower_buf) { rc = -ENOMEM; goto out; @@ -673,58 +672,29 @@ static int ecryptfs_readlink_lower(struct dentry *dentry, char **buf, set_fs(get_ds()); rc = lower_dentry->d_inode->i_op->readlink(lower_dentry, (char __user *)lower_buf, - lower_bufsiz); + PATH_MAX); set_fs(old_fs); if (rc < 0) goto out; - lower_bufsiz = rc; rc = ecryptfs_decode_and_decrypt_filename(buf, bufsiz, dentry, - lower_buf, lower_bufsiz); + lower_buf, rc); out: kfree(lower_buf); return rc; } -static int -ecryptfs_readlink(struct dentry *dentry, char __user *buf, int bufsiz) +static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd) { - char *kbuf; - size_t kbufsiz, copied; + char *buf; + size_t len = PATH_MAX; int rc; - rc = ecryptfs_readlink_lower(dentry, &kbuf, &kbufsiz); + rc = ecryptfs_readlink_lower(dentry, &buf, &len); if (rc) goto out; - copied = min_t(size_t, bufsiz, kbufsiz); - rc = copy_to_user(buf, kbuf, copied) ? -EFAULT : copied; - kfree(kbuf); fsstack_copy_attr_atime(dentry->d_inode, ecryptfs_dentry_to_lower(dentry)->d_inode); -out: - return rc; -} - -static void *ecryptfs_follow_link(struct dentry *dentry, struct nameidata *nd) -{ - char *buf; - int len = PAGE_SIZE, rc; - mm_segment_t old_fs; - - /* Released in ecryptfs_put_link(); only release here on error */ - buf = kmalloc(len, GFP_KERNEL); - if (!buf) { - buf = ERR_PTR(-ENOMEM); - goto out; - } - old_fs = get_fs(); - set_fs(get_ds()); - rc = dentry->d_inode->i_op->readlink(dentry, (char __user *)buf, len); - set_fs(old_fs); - if (rc < 0) { - kfree(buf); - buf = ERR_PTR(rc); - } else - buf[rc] = '\0'; + buf[len] = '\0'; out: nd_set_link(nd, buf); return NULL; @@ -1153,7 +1123,7 @@ out: } const struct inode_operations ecryptfs_symlink_iops = { - .readlink = ecryptfs_readlink, + .readlink = generic_readlink, .follow_link = ecryptfs_follow_link, .put_link = ecryptfs_put_link, .permission = ecryptfs_permission, diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index 69f994a7d52..0dbe58a8b17 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -149,7 +149,7 @@ int ecryptfs_privileged_open(struct file **lower_file, (*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred); if (!IS_ERR(*lower_file)) goto out; - if (flags & O_RDONLY) { + if ((flags & O_ACCMODE) == O_RDONLY) { rc = PTR_ERR((*lower_file)); goto out; } diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index ab224809051..a750f957b14 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -303,7 +303,7 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid, mutex_unlock(&ecryptfs_daemon_hash_mux); goto wake_up; } - tsk_user_ns = __task_cred(msg_ctx->task)->user->user_ns; + tsk_user_ns = __task_cred(msg_ctx->task)->user_ns; ctx_euid = task_euid(msg_ctx->task); rc = ecryptfs_find_daemon_by_euid(&daemon, ctx_euid, tsk_user_ns); rcu_read_unlock(); diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 3a06f4043df..c0038f6566d 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -49,7 +49,10 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -122,6 +125,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) goto out_unlock_daemon; } daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN; + file->private_data = daemon; atomic_inc(&ecryptfs_num_miscdev_opens); out_unlock_daemon: mutex_unlock(&daemon->mux); @@ -152,9 +156,9 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file) mutex_lock(&ecryptfs_daemon_hash_mux); rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) + daemon = file->private_data; mutex_lock(&daemon->mux); - BUG_ON(daemon->pid != task_pid(current)); BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN)); daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN; atomic_dec(&ecryptfs_num_miscdev_opens); @@ -191,31 +195,32 @@ int ecryptfs_send_miscdev(char *data, size_t data_size, struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type, u16 msg_flags, struct ecryptfs_daemon *daemon) { - int rc = 0; + struct ecryptfs_message *msg; - mutex_lock(&msg_ctx->mux); - msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size), - GFP_KERNEL); - if (!msg_ctx->msg) { - rc = -ENOMEM; + msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL); + if (!msg) { printk(KERN_ERR "%s: Out of memory whilst attempting " "to kmalloc(%zd, GFP_KERNEL)\n", __func__, - (sizeof(*msg_ctx->msg) + data_size)); - goto out_unlock; + (sizeof(*msg) + data_size)); + return -ENOMEM; } + + mutex_lock(&msg_ctx->mux); + msg_ctx->msg = msg; msg_ctx->msg->index = msg_ctx->index; msg_ctx->msg->data_len = data_size; msg_ctx->type = msg_type; memcpy(msg_ctx->msg->data, data, data_size); msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size); - mutex_lock(&daemon->mux); list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue); + mutex_unlock(&msg_ctx->mux); + + mutex_lock(&daemon->mux); daemon->num_queued_msg_ctx++; wake_up_interruptible(&daemon->wait); mutex_unlock(&daemon->mux); -out_unlock: - mutex_unlock(&msg_ctx->mux); - return rc; + + return 0; } /* @@ -269,8 +274,16 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); - BUG_ON(rc || !daemon); + if (rc || !daemon) { + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EINVAL; + } mutex_lock(&daemon->mux); + if (task_pid(current) != daemon->pid) { + mutex_unlock(&daemon->mux); + mutex_unlock(&ecryptfs_daemon_hash_mux); + return -EPERM; + } if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { rc = 0; mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -307,9 +320,6 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(euid != daemon->euid); - BUG_ON(current_user_ns() != daemon->user_ns); - BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); BUG_ON(!msg_ctx); diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 2dd946b636d..e879cf8ff0b 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -133,7 +133,7 @@ static int ecryptfs_statfs(struct dentry *dentry, struct kstatfs *buf) static void ecryptfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); iput(ecryptfs_inode_to_lower(inode)); } diff --git a/fs/eventfd.c b/fs/eventfd.c index dba15fecf23..d81b9f65408 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -46,20 +46,16 @@ struct eventfd_ctx { * value, and we signal this as overflow condition by returining a POLLERR * to poll(2). * - * Returns @n in case of success, a non-negative number lower than @n in case - * of overflow, or the following error codes: - * - * -EINVAL : The value of @n is negative. + * Returns the amount by which the counter was incrememnted. This will be less + * than @n if the counter has overflowed. */ -int eventfd_signal(struct eventfd_ctx *ctx, int n) +__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) { unsigned long flags; - if (n < 0) - return -EINVAL; spin_lock_irqsave(&ctx->wqh.lock, flags); if (ULLONG_MAX - ctx->count < n) - n = (int) (ULLONG_MAX - ctx->count); + n = ULLONG_MAX - ctx->count; ctx->count += n; if (waitqueue_active(&ctx->wqh)) wake_up_locked_poll(&ctx->wqh, POLLIN); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 739b0985b39..74598f67efe 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -33,6 +33,7 @@ #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> +#include <linux/device.h> #include <asm/uaccess.h> #include <asm/io.h> #include <asm/mman.h> @@ -87,7 +88,7 @@ */ /* Epoll private bits inside the event mask */ -#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET) +#define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 @@ -154,6 +155,9 @@ struct epitem { /* List header used to link this item to the "struct file" items list */ struct list_head fllink; + /* wakeup_source used when EPOLLWAKEUP is set */ + struct wakeup_source *ws; + /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; @@ -194,6 +198,9 @@ struct eventpoll { */ struct epitem *ovflist; + /* wakeup_source used when ep_scan_ready_list is running */ + struct wakeup_source *ws; + /* The user that created the eventpoll descriptor */ struct user_struct *user; @@ -588,8 +595,10 @@ static int ep_scan_ready_list(struct eventpoll *ep, * queued into ->ovflist but the "txlist" might already * contain them, and the list_splice() below takes care of them. */ - if (!ep_is_linked(&epi->rdllink)) + if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); + __pm_stay_awake(epi->ws); + } } /* * We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after @@ -602,6 +611,7 @@ static int ep_scan_ready_list(struct eventpoll *ep, * Quickly re-inject items left on "txlist". */ list_splice(&txlist, &ep->rdllist); + __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { /* @@ -656,6 +666,8 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); + wakeup_source_unregister(epi->ws); + /* At this point it is safe to free the eventpoll item */ kmem_cache_free(epi_cache, epi); @@ -706,6 +718,7 @@ static void ep_free(struct eventpoll *ep) mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); free_uid(ep->user); + wakeup_source_unregister(ep->ws); kfree(ep); } @@ -737,6 +750,7 @@ static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head, * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ + __pm_relax(epi->ws); list_del_init(&epi->rdllink); } } @@ -927,13 +941,23 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k if (epi->next == EP_UNACTIVE_PTR) { epi->next = ep->ovflist; ep->ovflist = epi; + if (epi->ws) { + /* + * Activate ep->ws since epi->ws may get + * deactivated at any time. + */ + __pm_stay_awake(ep->ws); + } + } goto out_unlock; } /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(&epi->rdllink)) + if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); + __pm_stay_awake(epi->ws); + } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() @@ -1091,6 +1115,30 @@ static int reverse_path_check(void) return error; } +static int ep_create_wakeup_source(struct epitem *epi) +{ + const char *name; + + if (!epi->ep->ws) { + epi->ep->ws = wakeup_source_register("eventpoll"); + if (!epi->ep->ws) + return -ENOMEM; + } + + name = epi->ffd.file->f_path.dentry->d_name.name; + epi->ws = wakeup_source_register(name); + if (!epi->ws) + return -ENOMEM; + + return 0; +} + +static void ep_destroy_wakeup_source(struct epitem *epi) +{ + wakeup_source_unregister(epi->ws); + epi->ws = NULL; +} + /* * Must be called with "mtx" held. */ @@ -1118,6 +1166,13 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, epi->event = *event; epi->nwait = 0; epi->next = EP_UNACTIVE_PTR; + if (epi->event.events & EPOLLWAKEUP) { + error = ep_create_wakeup_source(epi); + if (error) + goto error_create_wakeup_source; + } else { + epi->ws = NULL; + } /* Initialize the poll table using the queue callback */ epq.epi = epi; @@ -1164,6 +1219,7 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event, /* If the file is already "ready" we drop it inside the ready list */ if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); + __pm_stay_awake(epi->ws); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1204,6 +1260,9 @@ error_unregister: list_del_init(&epi->rdllink); spin_unlock_irqrestore(&ep->lock, flags); + wakeup_source_unregister(epi->ws); + +error_create_wakeup_source: kmem_cache_free(epi_cache, epi); return error; @@ -1229,6 +1288,12 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even epi->event.events = event->events; pt._key = event->events; epi->event.data = event->data; /* protected by mtx */ + if (epi->event.events & EPOLLWAKEUP) { + if (!epi->ws) + ep_create_wakeup_source(epi); + } else if (epi->ws) { + ep_destroy_wakeup_source(epi); + } /* * Get current event bits. We can safely use the file* here because @@ -1244,6 +1309,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even spin_lock_irq(&ep->lock); if (!ep_is_linked(&epi->rdllink)) { list_add_tail(&epi->rdllink, &ep->rdllist); + __pm_stay_awake(epi->ws); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) @@ -1282,6 +1348,18 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, !list_empty(head) && eventcnt < esed->maxevents;) { epi = list_first_entry(head, struct epitem, rdllink); + /* + * Activate ep->ws before deactivating epi->ws to prevent + * triggering auto-suspend here (in case we reactive epi->ws + * below). + * + * This could be rearranged to delay the deactivation of epi->ws + * instead, but then epi->ws would temporarily be out of sync + * with ep_is_linked(). + */ + if (epi->ws && epi->ws->active) + __pm_stay_awake(ep->ws); + __pm_relax(epi->ws); list_del_init(&epi->rdllink); pt._key = epi->event.events; @@ -1298,6 +1376,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, if (__put_user(revents, &uevent->events) || __put_user(epi->event.data, &uevent->data)) { list_add(&epi->rdllink, head); + __pm_stay_awake(epi->ws); return eventcnt ? eventcnt : -EFAULT; } eventcnt++; @@ -1317,6 +1396,7 @@ static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head, * poll callback will queue them in ep->ovflist. */ list_add_tail(&epi->rdllink, &ep->rdllist); + __pm_stay_awake(epi->ws); } } } @@ -1629,6 +1709,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, if (!tfile->f_op || !tfile->f_op->poll) goto error_tgt_fput; + /* Check if EPOLLWAKEUP is allowed */ + if ((epds.events & EPOLLWAKEUP) && !capable(CAP_EPOLLWAKEUP)) + epds.events &= ~EPOLLWAKEUP; + /* * We have to check that the file structure underneath the file descriptor * the user passed to us _is_ an eventpoll file. And also we do not permit @@ -1663,8 +1747,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, if (op == EPOLL_CTL_ADD) { if (is_file_epoll(tfile)) { error = -ELOOP; - if (ep_loop_check(ep, tfile) != 0) + if (ep_loop_check(ep, tfile) != 0) { + clear_tfile_check_list(); goto error_tgt_fput; + } } else list_add(&tfile->f_tfile_llink, &tfile_check_list); } @@ -1767,8 +1853,6 @@ error_return: return error; } -#ifdef HAVE_SET_RESTORE_SIGMASK - /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). @@ -1813,8 +1897,6 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, return error; } -#endif /* HAVE_SET_RESTORE_SIGMASK */ - static int __init eventpoll_init(void) { struct sysinfo si; diff --git a/fs/exec.c b/fs/exec.c index b1fd2025e59..da27b91ff1e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -280,10 +280,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm) vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); INIT_LIST_HEAD(&vma->anon_vma_chain); - err = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1); - if (err) - goto err; - err = insert_vm_struct(mm, vma); if (err) goto err; @@ -823,10 +819,10 @@ static int exec_mmap(struct mm_struct *mm) /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; - sync_mm_rss(old_mm); mm_release(tsk, old_mm); if (old_mm) { + sync_mm_rss(old_mm); /* * Make sure that if there is a core dump in progress * for the old mm, we get out and die instead of going @@ -1139,7 +1135,7 @@ void setup_new_exec(struct linux_binprm * bprm) /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; - if (current_euid() == current_uid() && current_egid() == current_gid()) + if (uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid())) set_dumpable(current->mm, 1); else set_dumpable(current->mm, suid_dumpable); @@ -1153,8 +1149,8 @@ void setup_new_exec(struct linux_binprm * bprm) current->mm->task_size = TASK_SIZE; /* install the new credentials */ - if (bprm->cred->uid != current_euid() || - bprm->cred->gid != current_egid()) { + if (!uid_eq(bprm->cred->uid, current_euid()) || + !gid_eq(bprm->cred->gid, current_egid())) { current->pdeath_signal = 0; } else { would_dump(bprm, bprm->file); @@ -1245,6 +1241,13 @@ static int check_unsafe_exec(struct linux_binprm *bprm) bprm->unsafe |= LSM_UNSAFE_PTRACE; } + /* + * This isn't strictly necessary, but it makes it harder for LSMs to + * mess up. + */ + if (current->no_new_privs) + bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; + n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); @@ -1288,11 +1291,15 @@ int prepare_binprm(struct linux_binprm *bprm) bprm->cred->euid = current_euid(); bprm->cred->egid = current_egid(); - if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { + if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) && + !current->no_new_privs) { /* Set-uid? */ if (mode & S_ISUID) { + if (!kuid_has_mapping(bprm->cred->user_ns, inode->i_uid)) + return -EPERM; bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = inode->i_uid; + } /* Set-gid? */ @@ -1302,6 +1309,8 @@ int prepare_binprm(struct linux_binprm *bprm) * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + if (!kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) + return -EPERM; bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = inode->i_gid; } @@ -1930,8 +1939,21 @@ static int coredump_wait(int exit_code, struct core_state *core_state) core_waiters = zap_threads(tsk, mm, core_state, exit_code); up_write(&mm->mmap_sem); - if (core_waiters > 0) + if (core_waiters > 0) { + struct core_thread *ptr; + wait_for_completion(&core_state->startup); + /* + * Wait for all the threads to become inactive, so that + * all the thread context (extended register state, like + * fpu etc) gets copied to the memory. + */ + ptr = core_state->dumper.next; + while (ptr != NULL) { + wait_task_inactive(ptr->task, 0); + ptr = ptr->next; + } + } return core_waiters; } @@ -2121,7 +2143,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) if (__get_dumpable(cprm.mm_flags) == 2) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ - cred->fsuid = 0; /* Dump root private */ + cred->fsuid = GLOBAL_ROOT_UID; /* Dump root private */ } retval = coredump_wait(exit_code, &core_state); @@ -2222,7 +2244,7 @@ void do_coredump(long signr, int exit_code, struct pt_regs *regs) * Dont allow local users get cute and trick others to coredump * into their pre-created files. */ - if (inode->i_uid != current_fsuid()) + if (!uid_eq(inode->i_uid, current_fsuid())) goto close_fail; if (!cprm.file->f_op || !cprm.file->f_op->write) goto close_fail; diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild index 352ba149d23..389ba8312d5 100644 --- a/fs/exofs/Kbuild +++ b/fs/exofs/Kbuild @@ -16,5 +16,5 @@ libore-y := ore.o ore_raid.o obj-$(CONFIG_ORE) += libore.o -exofs-y := inode.o file.o symlink.o namei.o dir.o super.o +exofs-y := inode.o file.o symlink.o namei.o dir.o super.o sys.o obj-$(CONFIG_EXOFS_FS) += exofs.o diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h index ca9d49665ef..fffe86fd7a4 100644 --- a/fs/exofs/exofs.h +++ b/fs/exofs/exofs.h @@ -56,6 +56,9 @@ struct exofs_dev { struct ore_dev ored; unsigned did; + unsigned urilen; + uint8_t *uri; + struct kobject ed_kobj; }; /* * our extension to the in-memory superblock @@ -73,6 +76,7 @@ struct exofs_sb_info { struct ore_layout layout; /* Default files layout */ struct ore_comp one_comp; /* id & cred of partition id=0*/ struct ore_components oc; /* comps for the partition */ + struct kobject s_kobj; /* holds per-sbi kobject */ }; /* @@ -176,6 +180,16 @@ void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj); int exofs_sbi_write_stats(struct exofs_sb_info *sbi); +/* sys.c */ +int exofs_sysfs_init(void); +void exofs_sysfs_uninit(void); +int exofs_sysfs_sb_add(struct exofs_sb_info *sbi, + struct exofs_dt_device_info *dt_dev); +void exofs_sysfs_sb_del(struct exofs_sb_info *sbi); +int exofs_sysfs_odev_add(struct exofs_dev *edev, + struct exofs_sb_info *sbi); +void exofs_sysfs_dbg_print(void); + /********************* * operation vectors * *********************/ diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index ea5e1f97806..5badb0c039d 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -1473,7 +1473,7 @@ void exofs_evict_inode(struct inode *inode) goto no_delete; inode->i_size = 0; - end_writeback(inode); + clear_inode(inode); /* if we are deleting an obj that hasn't been created yet, wait. * This also makes sure that create_done cannot be called with an @@ -1503,5 +1503,5 @@ void exofs_evict_inode(struct inode *inode) return; no_delete: - end_writeback(inode); + clear_inode(inode); } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 735ca06430a..433783624d1 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -472,6 +472,7 @@ static void exofs_put_super(struct super_block *sb) _exofs_print_device("Unmounting", NULL, ore_comp_dev(&sbi->oc, 0), sbi->one_comp.obj.partition); + exofs_sysfs_sb_del(sbi); bdi_destroy(&sbi->bdi); exofs_free_sbi(sbi); sb->s_fs_info = NULL; @@ -632,6 +633,12 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi, memcpy(&sbi->oc.ods[numdevs], &sbi->oc.ods[0], (numdevs - 1) * sizeof(sbi->oc.ods[0])); + /* create sysfs subdir under which we put the device table + * And cluster layout. A Superblock is identified by the string: + * "dev[0].osdname"_"pid" + */ + exofs_sysfs_sb_add(sbi, &dt->dt_dev_table[0]); + for (i = 0; i < numdevs; i++) { struct exofs_fscb fscb; struct osd_dev_info odi; @@ -657,6 +664,7 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi, eds[i].ored.od = fscb_od; ++sbi->oc.numdevs; fscb_od = NULL; + exofs_sysfs_odev_add(&eds[i], sbi); continue; } @@ -682,6 +690,7 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi, odi.osdname); goto out; } + exofs_sysfs_odev_add(&eds[i], sbi); /* TODO: verify other information is correct and FS-uuid * matches. Benny what did you say about device table @@ -745,7 +754,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) sbi->one_comp.obj.partition = opts->pid; sbi->one_comp.obj.id = 0; exofs_make_credential(sbi->one_comp.cred, &sbi->one_comp.obj); - sbi->oc.numdevs = 1; sbi->oc.single_comp = EC_SINGLE_COMP; sbi->oc.comps = &sbi->one_comp; @@ -804,6 +812,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) goto free_sbi; ore_comp_set_dev(&sbi->oc, 0, od); + sbi->oc.numdevs = 1; } __sbi_read_stats(sbi); @@ -844,6 +853,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent) goto free_sbi; } + exofs_sysfs_dbg_print(); _exofs_print_device("Mounting", opts->dev_name, ore_comp_dev(&sbi->oc, 0), sbi->one_comp.obj.partition); @@ -1023,6 +1033,9 @@ static int __init init_exofs(void) if (err) goto out_d; + /* We don't fail if sysfs creation failed */ + exofs_sysfs_init(); + return 0; out_d: destroy_inodecache(); @@ -1032,6 +1045,7 @@ out: static void __exit exit_exofs(void) { + exofs_sysfs_uninit(); unregister_filesystem(&exofs_type); destroy_inodecache(); } diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c new file mode 100644 index 00000000000..5a7b691e748 --- /dev/null +++ b/fs/exofs/sys.c @@ -0,0 +1,200 @@ +/* + * Copyright (C) 2012 + * Sachin Bhamare <sbhamare@panasas.com> + * Boaz Harrosh <bharrosh@panasas.com> + * + * This file is part of exofs. + * + * exofs is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License 2 as published by + * the Free Software Foundation. + * + * exofs is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with exofs; if not, write to the: + * Free Software Foundation <licensing@fsf.org> + */ + +#include <linux/kobject.h> +#include <linux/device.h> + +#include "exofs.h" + +struct odev_attr { + struct attribute attr; + ssize_t (*show)(struct exofs_dev *, char *); + ssize_t (*store)(struct exofs_dev *, const char *, size_t); +}; + +static ssize_t odev_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj); + struct odev_attr *a = container_of(attr, struct odev_attr, attr); + + return a->show ? a->show(edp, buf) : 0; +} + +static ssize_t odev_attr_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t len) +{ + struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj); + struct odev_attr *a = container_of(attr, struct odev_attr, attr); + + return a->store ? a->store(edp, buf, len) : len; +} + +static const struct sysfs_ops odev_attr_ops = { + .show = odev_attr_show, + .store = odev_attr_store, +}; + + +static struct kset *exofs_kset; + +static ssize_t osdname_show(struct exofs_dev *edp, char *buf) +{ + struct osd_dev *odev = edp->ored.od; + const struct osd_dev_info *odi = osduld_device_info(odev); + + return snprintf(buf, odi->osdname_len + 1, "%s", odi->osdname); +} + +static ssize_t systemid_show(struct exofs_dev *edp, char *buf) +{ + struct osd_dev *odev = edp->ored.od; + const struct osd_dev_info *odi = osduld_device_info(odev); + + memcpy(buf, odi->systemid, odi->systemid_len); + return odi->systemid_len; +} + +static ssize_t uri_show(struct exofs_dev *edp, char *buf) +{ + return snprintf(buf, edp->urilen, "%s", edp->uri); +} + +static ssize_t uri_store(struct exofs_dev *edp, const char *buf, size_t len) +{ + edp->urilen = strlen(buf) + 1; + edp->uri = krealloc(edp->uri, edp->urilen, GFP_KERNEL); + strncpy(edp->uri, buf, edp->urilen); + return edp->urilen; +} + +#define OSD_ATTR(name, mode, show, store) \ + static struct odev_attr odev_attr_##name = \ + __ATTR(name, mode, show, store) + +OSD_ATTR(osdname, S_IRUGO, osdname_show, NULL); +OSD_ATTR(systemid, S_IRUGO, systemid_show, NULL); +OSD_ATTR(uri, S_IRWXU, uri_show, uri_store); + +static struct attribute *odev_attrs[] = { + &odev_attr_osdname.attr, + &odev_attr_systemid.attr, + &odev_attr_uri.attr, + NULL, +}; + +static struct kobj_type odev_ktype = { + .default_attrs = odev_attrs, + .sysfs_ops = &odev_attr_ops, +}; + +static struct kobj_type uuid_ktype = { +}; + +void exofs_sysfs_dbg_print(void) +{ +#ifdef CONFIG_EXOFS_DEBUG + struct kobject *k_name, *k_tmp; + + list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) { + printk(KERN_INFO "%s: name %s ref %d\n", + __func__, kobject_name(k_name), + (int)atomic_read(&k_name->kref.refcount)); + } +#endif +} +/* + * This function removes all kobjects under exofs_kset + * At the end of it, exofs_kset kobject will have a refcount + * of 1 which gets decremented only on exofs module unload + */ +void exofs_sysfs_sb_del(struct exofs_sb_info *sbi) +{ + struct kobject *k_name, *k_tmp; + struct kobject *s_kobj = &sbi->s_kobj; + + list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) { + /* Remove all that are children of this SBI */ + if (k_name->parent == s_kobj) + kobject_put(k_name); + } + kobject_put(s_kobj); +} + +/* + * This function creates sysfs entries to hold the current exofs cluster + * instance (uniquely identified by osdname,pid tuple). + * This function gets called once per exofs mount instance. + */ +int exofs_sysfs_sb_add(struct exofs_sb_info *sbi, + struct exofs_dt_device_info *dt_dev) +{ + struct kobject *s_kobj; + int retval = 0; + uint64_t pid = sbi->one_comp.obj.partition; + + /* allocate new uuid dirent */ + s_kobj = &sbi->s_kobj; + s_kobj->kset = exofs_kset; + retval = kobject_init_and_add(s_kobj, &uuid_ktype, + &exofs_kset->kobj, "%s_%llx", dt_dev->osdname, pid); + if (retval) { + EXOFS_ERR("ERROR: Failed to create sysfs entry for " + "uuid-%s_%llx => %d\n", dt_dev->osdname, pid, retval); + return -ENOMEM; + } + return 0; +} + +int exofs_sysfs_odev_add(struct exofs_dev *edev, struct exofs_sb_info *sbi) +{ + struct kobject *d_kobj; + int retval = 0; + + /* create osd device group which contains following attributes + * osdname, systemid & uri + */ + d_kobj = &edev->ed_kobj; + d_kobj->kset = exofs_kset; + retval = kobject_init_and_add(d_kobj, &odev_ktype, + &sbi->s_kobj, "dev%u", edev->did); + if (retval) { + EXOFS_ERR("ERROR: Failed to create sysfs entry for " + "device dev%u\n", edev->did); + return retval; + } + return 0; +} + +int exofs_sysfs_init(void) +{ + exofs_kset = kset_create_and_add("exofs", NULL, fs_kobj); + if (!exofs_kset) { + EXOFS_ERR("ERROR: kset_create_and_add exofs failed\n"); + return -ENOMEM; + } + return 0; +} + +void exofs_sysfs_uninit(void) +{ + kset_unregister(exofs_kset); +} diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index b05acb79613..b0201ca6e9c 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -304,24 +304,23 @@ out: /** * export_encode_fh - default export_operations->encode_fh function - * @dentry: the dentry to encode + * @inode: the object to encode * @fh: where to store the file handle fragment * @max_len: maximum length to store there - * @connectable: whether to store parent information + * @parent: parent directory inode, if wanted * * This default encode_fh function assumes that the 32 inode number * is suitable for locating an inode, and that the generation number * can be used to check that it is still valid. It places them in the * filehandle fragment where export_decode_fh expects to find them. */ -static int export_encode_fh(struct dentry *dentry, struct fid *fid, - int *max_len, int connectable) +static int export_encode_fh(struct inode *inode, struct fid *fid, + int *max_len, struct inode *parent) { - struct inode * inode = dentry->d_inode; int len = *max_len; int type = FILEID_INO32_GEN; - if (connectable && (len < 4)) { + if (parent && (len < 4)) { *max_len = 4; return 255; } else if (len < 2) { @@ -332,14 +331,9 @@ static int export_encode_fh(struct dentry *dentry, struct fid *fid, len = 2; fid->i32.ino = inode->i_ino; fid->i32.gen = inode->i_generation; - if (connectable && !S_ISDIR(inode->i_mode)) { - struct inode *parent; - - spin_lock(&dentry->d_lock); - parent = dentry->d_parent->d_inode; + if (parent) { fid->i32.parent_ino = parent->i_ino; fid->i32.parent_gen = parent->i_generation; - spin_unlock(&dentry->d_lock); len = 4; type = FILEID_INO32_GEN_PARENT; } @@ -352,11 +346,22 @@ int exportfs_encode_fh(struct dentry *dentry, struct fid *fid, int *max_len, { const struct export_operations *nop = dentry->d_sb->s_export_op; int error; + struct dentry *p = NULL; + struct inode *inode = dentry->d_inode, *parent = NULL; + if (connectable && !S_ISDIR(inode->i_mode)) { + p = dget_parent(dentry); + /* + * note that while p might've ceased to be our parent already, + * it's still pinned by and still positive. + */ + parent = p->d_inode; + } if (nop->encode_fh) - error = nop->encode_fh(dentry, fid->raw, max_len, connectable); + error = nop->encode_fh(inode, fid->raw, max_len, parent); else - error = export_encode_fh(dentry, fid, max_len, connectable); + error = export_encode_fh(inode, fid, max_len, parent); + dput(p); return error; } diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index a8cbe1bc6ad..1c361399886 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -165,7 +165,6 @@ static void release_blocks(struct super_block *sb, int count) struct ext2_sb_info *sbi = EXT2_SB(sb); percpu_counter_add(&sbi->s_freeblocks_counter, count); - sb->s_dirt = 1; } } @@ -180,7 +179,6 @@ static void group_adjust_blocks(struct super_block *sb, int group_no, free_blocks = le16_to_cpu(desc->bg_free_blocks_count); desc->bg_free_blocks_count = cpu_to_le16(free_blocks + count); spin_unlock(sb_bgl_lock(sbi, group_no)); - sb->s_dirt = 1; mark_buffer_dirty(bh); } } @@ -479,7 +477,7 @@ void ext2_discard_reservation(struct inode *inode) } /** - * ext2_free_blocks_sb() -- Free given blocks and update quota and i_blocks + * ext2_free_blocks() -- Free given blocks and update quota and i_blocks * @inode: inode * @block: start physcial block to free * @count: number of blocks to free @@ -1193,8 +1191,9 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - sbi->s_resuid != current_fsuid() && - (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { + !uid_eq(sbi->s_resuid, current_fsuid()) && + (gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) || + !in_group_p (sbi->s_resgid))) { return 0; } return 1; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 0b2b4db5bdc..d9a17d0b124 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -82,8 +82,8 @@ struct ext2_sb_info { struct buffer_head ** s_group_desc; unsigned long s_mount_opt; unsigned long s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; @@ -637,8 +637,8 @@ static inline void verify_offsets(void) */ struct ext2_mount_options { unsigned long s_mount_opt; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; }; /* diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index 8b15cf8cef3..c13eb7b91a1 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -81,7 +81,6 @@ static void ext2_release_inode(struct super_block *sb, int group, int dir) spin_unlock(sb_bgl_lock(EXT2_SB(sb), group)); if (dir) percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter); - sb->s_dirt = 1; mark_buffer_dirty(bh); } @@ -543,7 +542,6 @@ got: } spin_unlock(sb_bgl_lock(sbi, group)); - sb->s_dirt = 1; mark_buffer_dirty(bh2); if (test_opt(sb, GRPID)) { inode->i_mode = mode; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 740cad8dcd8..264d315f6c4 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -90,7 +90,7 @@ void ext2_evict_inode(struct inode * inode) } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); ext2_discard_reservation(inode); rsv = EXT2_I(inode)->i_block_alloc_info; @@ -1293,6 +1293,8 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) struct inode *inode; long ret = -EIO; int n; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -1310,12 +1312,14 @@ struct inode *ext2_iget (struct super_block *sb, unsigned long ino) } inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (!(test_opt (inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); @@ -1413,8 +1417,8 @@ static int __ext2_write_inode(struct inode *inode, int do_sync) struct ext2_inode_info *ei = EXT2_I(inode); struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; - uid_t uid = inode->i_uid; - gid_t gid = inode->i_gid; + uid_t uid = i_uid_read(inode); + gid_t gid = i_gid_read(inode); struct buffer_head * bh; struct ext2_inode * raw_inode = ext2_get_inode(sb, ino, &bh); int n; @@ -1529,8 +1533,8 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) if (is_quota_modification(inode, iattr)) dquot_initialize(inode); - if ((iattr->ia_valid & ATTR_UID && iattr->ia_uid != inode->i_uid) || - (iattr->ia_valid & ATTR_GID && iattr->ia_gid != inode->i_gid)) { + if ((iattr->ia_valid & ATTR_UID && !uid_eq(iattr->ia_uid, inode->i_uid)) || + (iattr->ia_valid & ATTR_GID && !gid_eq(iattr->ia_gid, inode->i_gid))) { error = dquot_transfer(inode, iattr); if (error) return error; diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c index dffb8653628..f663a67d7bf 100644 --- a/fs/ext2/namei.c +++ b/fs/ext2/namei.c @@ -79,7 +79,7 @@ static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext2_get_parent(struct dentry *child) { - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); unsigned long ino = ext2_inode_by_name(child->d_inode, &dotdot); if (!ino) return ERR_PTR(-ENOENT); diff --git a/fs/ext2/super.c b/fs/ext2/super.c index e1025c7a437..b3621cb7ea3 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -130,9 +130,6 @@ static void ext2_put_super (struct super_block * sb) dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - if (sb->s_dirt) - ext2_write_super(sb); - ext2_xattr_put_super(sb); if (!(sb->s_flags & MS_RDONLY)) { struct ext2_super_block *es = sbi->s_es; @@ -228,13 +225,15 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",grpid"); if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS)) seq_puts(seq, ",nogrpid"); - if (sbi->s_resuid != EXT2_DEF_RESUID || + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) { - seq_printf(seq, ",resuid=%u", sbi->s_resuid); + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); } - if (sbi->s_resgid != EXT2_DEF_RESGID || + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) { - seq_printf(seq, ",resgid=%u", sbi->s_resgid); + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); } if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); @@ -305,7 +304,6 @@ static const struct super_operations ext2_sops = { .write_inode = ext2_write_inode, .evict_inode = ext2_evict_inode, .put_super = ext2_put_super, - .write_super = ext2_write_super, .sync_fs = ext2_sync_fs, .statfs = ext2_statfs, .remount_fs = ext2_remount, @@ -356,11 +354,6 @@ static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid, ext2_nfs_get_inode); } -/* Yes, most of these are left as NULL!! - * A NULL value implies the default, which works with ext2-like file - * systems, but can be improved upon. - * Currently only get_parent is required. - */ static const struct export_operations ext2_export_ops = { .fh_to_dentry = ext2_fh_to_dentry, .fh_to_parent = ext2_fh_to_parent, @@ -436,6 +429,8 @@ static int parse_options(char *options, struct super_block *sb) struct ext2_sb_info *sbi = EXT2_SB(sb); substring_t args[MAX_OPT_ARGS]; int option; + kuid_t uid; + kgid_t gid; if (!options) return 1; @@ -462,12 +457,23 @@ static int parse_options(char *options, struct super_block *sb) case Opt_resuid: if (match_int(&args[0], &option)) return 0; - sbi->s_resuid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return -1; + + } + sbi->s_resuid = uid; break; case Opt_resgid: if (match_int(&args[0], &option)) return 0; - sbi->s_resgid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return -1; + } + sbi->s_resgid = gid; break; case Opt_sb: /* handled by get_sb_block() instead of here */ @@ -841,8 +847,8 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) else set_opt(sbi->s_mount_opt, ERRORS_RO); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); set_opt(sbi->s_mount_opt, RESERVATION); @@ -1161,7 +1167,6 @@ static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es, mark_buffer_dirty(EXT2_SB(sb)->s_sbh); if (wait) sync_dirty_buffer(EXT2_SB(sb)->s_sbh); - sb->s_dirt = 0; } /* @@ -1194,8 +1199,6 @@ void ext2_write_super(struct super_block *sb) { if (!(sb->s_flags & MS_RDONLY)) ext2_sync_fs(sb, 1); - else - sb->s_dirt = 0; } static int ext2_remount (struct super_block * sb, int * flags, char * data) @@ -1441,7 +1444,6 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, struct buffer_head tmp_bh; struct buffer_head *bh; - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); while (towrite > 0) { tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; @@ -1471,16 +1473,13 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) { - mutex_unlock(&inode->i_mutex); + if (len == towrite) return err; - } if (inode->i_size < off+len-towrite) i_size_write(inode, off+len-towrite); inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - mutex_unlock(&inode->i_mutex); return len - towrite; } diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 6dcafc7efdf..b6754dbbce3 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -339,7 +339,6 @@ static void ext2_xattr_update_super_block(struct super_block *sb) spin_lock(&EXT2_SB(sb)->s_lock); EXT2_SET_COMPAT_FEATURE(sb, EXT2_FEATURE_COMPAT_EXT_ATTR); spin_unlock(&EXT2_SB(sb)->s_lock); - sb->s_dirt = 1; mark_buffer_dirty(EXT2_SB(sb)->s_sbh); } diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index baac1b129fb..25cd6089211 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -1439,8 +1439,9 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi, int use_reservation) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - !use_reservation && sbi->s_resuid != current_fsuid() && - (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { + !use_reservation && !uid_eq(sbi->s_resuid, current_fsuid()) && + (gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) || + !in_group_p (sbi->s_resgid))) { return 0; } return 1; diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c index cc761ad8fa5..92490e9f85c 100644 --- a/fs/ext3/dir.c +++ b/fs/ext3/dir.c @@ -21,30 +21,15 @@ * */ +#include <linux/compat.h> #include "ext3.h" static unsigned char ext3_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; -static int ext3_readdir(struct file *, void *, filldir_t); static int ext3_dx_readdir(struct file * filp, void * dirent, filldir_t filldir); -static int ext3_release_dir (struct inode * inode, - struct file * filp); - -const struct file_operations ext3_dir_operations = { - .llseek = generic_file_llseek, - .read = generic_read_dir, - .readdir = ext3_readdir, /* we take BKL. needed?*/ - .unlocked_ioctl = ext3_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = ext3_compat_ioctl, -#endif - .fsync = ext3_sync_file, /* BKL held */ - .release = ext3_release_dir, -}; - static unsigned char get_dtype(struct super_block *sb, int filetype) { @@ -55,6 +40,25 @@ static unsigned char get_dtype(struct super_block *sb, int filetype) return (ext3_filetype_table[filetype]); } +/** + * Check if the given dir-inode refers to an htree-indexed directory + * (or a directory which chould potentially get coverted to use htree + * indexing). + * + * Return 1 if it is a dx dir, 0 if not + */ +static int is_dx_dir(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + + if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb, + EXT3_FEATURE_COMPAT_DIR_INDEX) && + ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) || + ((inode->i_size >> sb->s_blocksize_bits) == 1))) + return 1; + + return 0; +} int ext3_check_dir_entry (const char * function, struct inode * dir, struct ext3_dir_entry_2 * de, @@ -94,18 +98,13 @@ static int ext3_readdir(struct file * filp, unsigned long offset; int i, stored; struct ext3_dir_entry_2 *de; - struct super_block *sb; int err; struct inode *inode = filp->f_path.dentry->d_inode; + struct super_block *sb = inode->i_sb; int ret = 0; int dir_has_error = 0; - sb = inode->i_sb; - - if (EXT3_HAS_COMPAT_FEATURE(inode->i_sb, - EXT3_FEATURE_COMPAT_DIR_INDEX) && - ((EXT3_I(inode)->i_flags & EXT3_INDEX_FL) || - ((inode->i_size >> sb->s_blocksize_bits) == 1))) { + if (is_dx_dir(inode)) { err = ext3_dx_readdir(filp, dirent, filldir); if (err != ERR_BAD_DX_DIR) { ret = err; @@ -227,22 +226,87 @@ out: return ret; } +static inline int is_32bit_api(void) +{ +#ifdef CONFIG_COMPAT + return is_compat_task(); +#else + return (BITS_PER_LONG == 32); +#endif +} + /* * These functions convert from the major/minor hash to an f_pos - * value. + * value for dx directories * - * Currently we only use major hash numer. This is unfortunate, but - * on 32-bit machines, the same VFS interface is used for lseek and - * llseek, so if we use the 64 bit offset, then the 32-bit versions of - * lseek/telldir/seekdir will blow out spectacularly, and from within - * the ext2 low-level routine, we don't know if we're being called by - * a 64-bit version of the system call or the 32-bit version of the - * system call. Worse yet, NFSv2 only allows for a 32-bit readdir - * cookie. Sigh. + * Upper layer (for example NFS) should specify FMODE_32BITHASH or + * FMODE_64BITHASH explicitly. On the other hand, we allow ext3 to be mounted + * directly on both 32-bit and 64-bit nodes, under such case, neither + * FMODE_32BITHASH nor FMODE_64BITHASH is specified. */ -#define hash2pos(major, minor) (major >> 1) -#define pos2maj_hash(pos) ((pos << 1) & 0xffffffff) -#define pos2min_hash(pos) (0) +static inline loff_t hash2pos(struct file *filp, __u32 major, __u32 minor) +{ + if ((filp->f_mode & FMODE_32BITHASH) || + (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) + return major >> 1; + else + return ((__u64)(major >> 1) << 32) | (__u64)minor; +} + +static inline __u32 pos2maj_hash(struct file *filp, loff_t pos) +{ + if ((filp->f_mode & FMODE_32BITHASH) || + (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) + return (pos << 1) & 0xffffffff; + else + return ((pos >> 32) << 1) & 0xffffffff; +} + +static inline __u32 pos2min_hash(struct file *filp, loff_t pos) +{ + if ((filp->f_mode & FMODE_32BITHASH) || + (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) + return 0; + else + return pos & 0xffffffff; +} + +/* + * Return 32- or 64-bit end-of-file for dx directories + */ +static inline loff_t ext3_get_htree_eof(struct file *filp) +{ + if ((filp->f_mode & FMODE_32BITHASH) || + (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api())) + return EXT3_HTREE_EOF_32BIT; + else + return EXT3_HTREE_EOF_64BIT; +} + + +/* + * ext3_dir_llseek() calls generic_file_llseek[_size]() to handle both + * non-htree and htree directories, where the "offset" is in terms + * of the filename hash value instead of the byte offset. + * + * Because we may return a 64-bit hash that is well beyond s_maxbytes, + * we need to pass the max hash as the maximum allowable offset in + * the htree directory case. + * + * NOTE: offsets obtained *before* ext3_set_inode_flag(dir, EXT3_INODE_INDEX) + * will be invalid once the directory was converted into a dx directory + */ +loff_t ext3_dir_llseek(struct file *file, loff_t offset, int origin) +{ + struct inode *inode = file->f_mapping->host; + int dx_dir = is_dx_dir(inode); + + if (likely(dx_dir)) + return generic_file_llseek_size(file, offset, origin, + ext3_get_htree_eof(file)); + else + return generic_file_llseek(file, offset, origin); +} /* * This structure holds the nodes of the red-black tree used to store @@ -303,15 +367,16 @@ static void free_rb_tree_fname(struct rb_root *root) } -static struct dir_private_info *ext3_htree_create_dir_info(loff_t pos) +static struct dir_private_info *ext3_htree_create_dir_info(struct file *filp, + loff_t pos) { struct dir_private_info *p; p = kzalloc(sizeof(struct dir_private_info), GFP_KERNEL); if (!p) return NULL; - p->curr_hash = pos2maj_hash(pos); - p->curr_minor_hash = pos2min_hash(pos); + p->curr_hash = pos2maj_hash(filp, pos); + p->curr_minor_hash = pos2min_hash(filp, pos); return p; } @@ -401,7 +466,7 @@ static int call_filldir(struct file * filp, void * dirent, printk("call_filldir: called with null fname?!?\n"); return 0; } - curr_pos = hash2pos(fname->hash, fname->minor_hash); + curr_pos = hash2pos(filp, fname->hash, fname->minor_hash); while (fname) { error = filldir(dirent, fname->name, fname->name_len, curr_pos, @@ -426,13 +491,13 @@ static int ext3_dx_readdir(struct file * filp, int ret; if (!info) { - info = ext3_htree_create_dir_info(filp->f_pos); + info = ext3_htree_create_dir_info(filp, filp->f_pos); if (!info) return -ENOMEM; filp->private_data = info; } - if (filp->f_pos == EXT3_HTREE_EOF) + if (filp->f_pos == ext3_get_htree_eof(filp)) return 0; /* EOF */ /* Some one has messed with f_pos; reset the world */ @@ -440,8 +505,8 @@ static int ext3_dx_readdir(struct file * filp, free_rb_tree_fname(&info->root); info->curr_node = NULL; info->extra_fname = NULL; - info->curr_hash = pos2maj_hash(filp->f_pos); - info->curr_minor_hash = pos2min_hash(filp->f_pos); + info->curr_hash = pos2maj_hash(filp, filp->f_pos); + info->curr_minor_hash = pos2min_hash(filp, filp->f_pos); } /* @@ -473,7 +538,7 @@ static int ext3_dx_readdir(struct file * filp, if (ret < 0) return ret; if (ret == 0) { - filp->f_pos = EXT3_HTREE_EOF; + filp->f_pos = ext3_get_htree_eof(filp); break; } info->curr_node = rb_first(&info->root); @@ -493,7 +558,7 @@ static int ext3_dx_readdir(struct file * filp, info->curr_minor_hash = fname->minor_hash; } else { if (info->next_hash == ~0) { - filp->f_pos = EXT3_HTREE_EOF; + filp->f_pos = ext3_get_htree_eof(filp); break; } info->curr_hash = info->next_hash; @@ -512,3 +577,15 @@ static int ext3_release_dir (struct inode * inode, struct file * filp) return 0; } + +const struct file_operations ext3_dir_operations = { + .llseek = ext3_dir_llseek, + .read = generic_read_dir, + .readdir = ext3_readdir, + .unlocked_ioctl = ext3_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = ext3_compat_ioctl, +#endif + .fsync = ext3_sync_file, + .release = ext3_release_dir, +}; diff --git a/fs/ext3/ext3.h b/fs/ext3/ext3.h index b6515fd7e56..e85ff15a060 100644 --- a/fs/ext3/ext3.h +++ b/fs/ext3/ext3.h @@ -243,8 +243,8 @@ struct ext3_new_group_data { */ struct ext3_mount_options { unsigned long s_mount_opt; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned long s_commit_interval; #ifdef CONFIG_QUOTA int s_jquota_fmt; @@ -637,8 +637,8 @@ struct ext3_sb_info { struct buffer_head ** s_group_desc; unsigned long s_mount_opt; ext3_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; @@ -920,7 +920,11 @@ struct dx_hash_info u32 *seed; }; -#define EXT3_HTREE_EOF 0x7fffffff + +/* 32 and 64 bit signed EOF for dx directories */ +#define EXT3_HTREE_EOF_32BIT ((1UL << (32 - 1)) - 1) +#define EXT3_HTREE_EOF_64BIT ((1ULL << (64 - 1)) - 1) + /* * Control parameters used by ext3_htree_next_block diff --git a/fs/ext3/hash.c b/fs/ext3/hash.c index d10231ddcf8..ede315cdf12 100644 --- a/fs/ext3/hash.c +++ b/fs/ext3/hash.c @@ -198,8 +198,8 @@ int ext3fs_dirhash(const char *name, int len, struct dx_hash_info *hinfo) return -1; } hash = hash & ~1; - if (hash == (EXT3_HTREE_EOF << 1)) - hash = (EXT3_HTREE_EOF-1) << 1; + if (hash == (EXT3_HTREE_EOF_32BIT << 1)) + hash = (EXT3_HTREE_EOF_32BIT - 1) << 1; hinfo->hash = hash; hinfo->minor_hash = minor_hash; return 0; diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index e3c39e4cec1..082afd78b10 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -180,8 +180,7 @@ error_return: * It's OK to put directory into a group unless * it has too many directories already (max_dirs) or * it has too few free inodes left (min_inodes) or - * it has too few free blocks left (min_blocks) or - * it's already running too large debt (max_debt). + * it has too few free blocks left (min_blocks). * Parent's group is preferred, if it doesn't satisfy these * conditions we search cyclically through the rest. If none * of the groups look good we just look for a group with more @@ -191,21 +190,16 @@ error_return: * when we allocate an inode, within 0--255. */ -#define INODE_COST 64 -#define BLOCK_COST 256 - static int find_group_orlov(struct super_block *sb, struct inode *parent) { int parent_group = EXT3_I(parent)->i_block_group; struct ext3_sb_info *sbi = EXT3_SB(sb); - struct ext3_super_block *es = sbi->s_es; int ngroups = sbi->s_groups_count; int inodes_per_group = EXT3_INODES_PER_GROUP(sb); unsigned int freei, avefreei; ext3_fsblk_t freeb, avefreeb; - ext3_fsblk_t blocks_per_dir; unsigned int ndirs; - int max_debt, max_dirs, min_inodes; + int max_dirs, min_inodes; ext3_grpblk_t min_blocks; int group = -1, i; struct ext3_group_desc *desc; @@ -242,20 +236,10 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent) goto fallback; } - blocks_per_dir = (le32_to_cpu(es->s_blocks_count) - freeb) / ndirs; - max_dirs = ndirs / ngroups + inodes_per_group / 16; min_inodes = avefreei - inodes_per_group / 4; min_blocks = avefreeb - EXT3_BLOCKS_PER_GROUP(sb) / 4; - max_debt = EXT3_BLOCKS_PER_GROUP(sb) / max(blocks_per_dir, (ext3_fsblk_t)BLOCK_COST); - if (max_debt * INODE_COST > inodes_per_group) - max_debt = inodes_per_group / INODE_COST; - if (max_debt > 255) - max_debt = 255; - if (max_debt == 0) - max_debt = 1; - for (i = 0; i < ngroups; i++) { group = (parent_group + i) % ngroups; desc = ext3_get_group_desc (sb, group, NULL); diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 10d7812f602..9a4a5c48b1c 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -272,18 +272,18 @@ void ext3_evict_inode (struct inode *inode) if (ext3_mark_inode_dirty(handle, inode)) { /* If that failed, just dquot_drop() and be done with that */ dquot_drop(inode); - end_writeback(inode); + clear_inode(inode); } else { ext3_xattr_delete_inode(handle, inode); dquot_free_inode(inode); dquot_drop(inode); - end_writeback(inode); + clear_inode(inode); ext3_free_inode(handle, inode); } ext3_journal_stop(handle); return; no_delete: - end_writeback(inode); + clear_inode(inode); dquot_drop(inode); } @@ -2891,6 +2891,8 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) transaction_t *transaction; long ret; int block; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -2907,12 +2909,14 @@ struct inode *ext3_iget(struct super_block *sb, unsigned long ino) bh = iloc.bh; raw_inode = ext3_raw_inode(&iloc); inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if(!(test_opt (inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); inode->i_size = le32_to_cpu(raw_inode->i_size); inode->i_atime.tv_sec = (signed)le32_to_cpu(raw_inode->i_atime); @@ -3068,6 +3072,8 @@ static int ext3_do_update_inode(handle_t *handle, struct ext3_inode_info *ei = EXT3_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + uid_t i_uid; + gid_t i_gid; again: /* we can't allow multiple procs in here at once, its a bit racey */ @@ -3080,27 +3086,29 @@ again: ext3_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); if(!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if(!ei->i_dtime) { raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(inode->i_uid)); + cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(inode->i_gid)); + cpu_to_le16(high_16_bits(i_gid)); } else { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } } else { raw_inode->i_uid_low = - cpu_to_le16(fs_high2lowuid(inode->i_uid)); + cpu_to_le16(fs_high2lowuid(i_uid)); raw_inode->i_gid_low = - cpu_to_le16(fs_high2lowgid(inode->i_gid)); + cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } @@ -3262,8 +3270,8 @@ int ext3_setattr(struct dentry *dentry, struct iattr *attr) if (is_quota_modification(inode, attr)) dquot_initialize(inode); - if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || - (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || + (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c index d7940b24cf6..eeb63dfc5d2 100644 --- a/fs/ext3/namei.c +++ b/fs/ext3/namei.c @@ -1045,7 +1045,7 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str struct dentry *ext3_get_parent(struct dentry *child) { unsigned long ino; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct ext3_dir_entry_2 * de; struct buffer_head *bh; diff --git a/fs/ext3/super.c b/fs/ext3/super.c index cf0b5921cf0..8c3a44b7c37 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -617,13 +617,15 @@ static int ext3_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",grpid"); if (!test_opt(sb, GRPID) && (def_mount_opts & EXT3_DEFM_BSDGROUPS)) seq_puts(seq, ",nogrpid"); - if (sbi->s_resuid != EXT3_DEF_RESUID || + if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT3_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT3_DEF_RESUID) { - seq_printf(seq, ",resuid=%u", sbi->s_resuid); + seq_printf(seq, ",resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); } - if (sbi->s_resgid != EXT3_DEF_RESGID || + if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT3_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT3_DEF_RESGID) { - seq_printf(seq, ",resgid=%u", sbi->s_resgid); + seq_printf(seq, ",resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); } if (test_opt(sb, ERRORS_RO)) { int def_errors = le16_to_cpu(es->s_errors); @@ -967,6 +969,8 @@ static int parse_options (char *options, struct super_block *sb, substring_t args[MAX_OPT_ARGS]; int data_opt = 0; int option; + kuid_t uid; + kgid_t gid; #ifdef CONFIG_QUOTA int qfmt; #endif @@ -1000,12 +1004,23 @@ static int parse_options (char *options, struct super_block *sb, case Opt_resuid: if (match_int(&args[0], &option)) return 0; - sbi->s_resuid = option; + uid = make_kuid(current_user_ns(), option); + if (!uid_valid(uid)) { + ext3_msg(sb, KERN_ERR, "Invalid uid value %d", option); + return -1; + + } + sbi->s_resuid = uid; break; case Opt_resgid: if (match_int(&args[0], &option)) return 0; - sbi->s_resgid = option; + gid = make_kgid(current_user_ns(), option); + if (!gid_valid(gid)) { + ext3_msg(sb, KERN_ERR, "Invalid gid value %d", option); + return -1; + } + sbi->s_resgid = gid; break; case Opt_sb: /* handled by get_sb_block() instead of here */ @@ -1651,8 +1666,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_mount_opt = 0; - sbi->s_resuid = EXT3_DEF_RESUID; - sbi->s_resgid = EXT3_DEF_RESGID; + sbi->s_resuid = make_kuid(&init_user_ns, EXT3_DEF_RESUID); + sbi->s_resgid = make_kgid(&init_user_ns, EXT3_DEF_RESGID); sbi->s_sb_block = sb_block; blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE); @@ -1716,8 +1731,8 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent) else set_opt(sbi->s_mount_opt, ERRORS_RO); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); /* enable barriers by default */ set_opt(sbi->s_mount_opt, BARRIER); @@ -3000,7 +3015,6 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, (unsigned long long)off, (unsigned long long)len); return -EIO; } - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); bh = ext3_bread(handle, inode, blk, 1, &err); if (!bh) goto out; @@ -3024,10 +3038,8 @@ static ssize_t ext3_quota_write(struct super_block *sb, int type, } brelse(bh); out: - if (err) { - mutex_unlock(&inode->i_mutex); + if (err) return err; - } if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT3_I(inode)->i_disksize = inode->i_size; @@ -3035,7 +3047,6 @@ out: inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; ext3_mark_inode_dirty(handle, inode); - mutex_unlock(&inode->i_mutex); return len; } diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 9ed1bb1f319..c22f17021b6 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -2,6 +2,8 @@ config EXT4_FS tristate "The Extended 4 (ext4) filesystem" select JBD2 select CRC16 + select CRYPTO + select CRYPTO_CRC32C help This is the next generation of the ext3 filesystem. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 4bbd07a6fa1..cee7812cc3c 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -90,8 +90,8 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, * unusual file system layouts. */ if (ext4_block_in_group(sb, ext4_block_bitmap(sb, gdp), block_group)) { - block_cluster = EXT4_B2C(sbi, (start - - ext4_block_bitmap(sb, gdp))); + block_cluster = EXT4_B2C(sbi, + ext4_block_bitmap(sb, gdp) - start); if (block_cluster < num_clusters) block_cluster = -1; else if (block_cluster == num_clusters) { @@ -102,7 +102,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, if (ext4_block_in_group(sb, ext4_inode_bitmap(sb, gdp), block_group)) { inode_cluster = EXT4_B2C(sbi, - start - ext4_inode_bitmap(sb, gdp)); + ext4_inode_bitmap(sb, gdp) - start); if (inode_cluster < num_clusters) inode_cluster = -1; else if (inode_cluster == num_clusters) { @@ -114,7 +114,7 @@ unsigned ext4_num_overhead_clusters(struct super_block *sb, itbl_blk = ext4_inode_table(sb, gdp); for (i = 0; i < sbi->s_itb_per_group; i++) { if (ext4_block_in_group(sb, itbl_blk + i, block_group)) { - c = EXT4_B2C(sbi, start - itbl_blk + i); + c = EXT4_B2C(sbi, itbl_blk + i - start); if ((c < num_clusters) || (c == inode_cluster) || (c == block_cluster) || (c == itbl_cluster)) continue; @@ -168,12 +168,14 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ - if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); ext4_free_group_clusters_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); return; } memset(bh->b_data, 0, sb->s_blocksize); @@ -210,6 +212,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh, */ ext4_mark_bitmap_end(num_clusters_in_group(sb, block_group), sb->s_blocksize * 8, bh->b_data); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, gdp); } /* Return the number of free blocks in a block group. It is used when @@ -276,9 +281,9 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, } static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; @@ -325,6 +330,23 @@ err_out: block_group, bitmap_blk); return 0; } + +void ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) +{ + if (buffer_verified(bh)) + return; + + ext4_lock_group(sb, block_group); + if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && + ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8)) + set_buffer_verified(bh); + ext4_unlock_group(sb, block_group); +} + /** * ext4_read_block_bitmap() * @sb: super block @@ -355,12 +377,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } if (bitmap_uptodate(bh)) - return bh; + goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); - return bh; + goto verify; } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -379,7 +401,7 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) */ set_bitmap_uptodate(bh); unlock_buffer(bh); - return bh; + goto verify; } /* * submit the buffer_head for reading @@ -390,6 +412,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) get_bh(bh); submit_bh(READ, bh); return bh; +verify: + ext4_validate_block_bitmap(sb, desc, block_group, bh); + return bh; } /* Returns 0 on success, 1 on error */ @@ -412,7 +437,7 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, } clear_buffer_new(bh); /* Panic or remount fs read-only if block bitmap is invalid */ - ext4_valid_block_bitmap(sb, desc, block_group, bh); + ext4_validate_block_bitmap(sb, desc, block_group, bh); return 0; } @@ -461,8 +486,8 @@ static int ext4_has_free_clusters(struct ext4_sb_info *sbi, return 1; /* Hm, nope. Are (enough) root reserved clusters available? */ - if (sbi->s_resuid == current_fsuid() || - ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || + if (uid_eq(sbi->s_resuid, current_fsuid()) || + (!gid_eq(sbi->s_resgid, GLOBAL_ROOT_GID) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE) || (flags & EXT4_MB_USE_ROOT_BLOCKS)) { diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index fa3af81ac56..b319721da26 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -29,3 +29,86 @@ unsigned int ext4_count_free(struct buffer_head *map, unsigned int numchars) #endif /* EXT4FS_DEBUG */ +int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 hi; + __u32 provided, calculated; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + provided = le16_to_cpu(gdp->bg_inode_bitmap_csum_lo); + calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) { + hi = le16_to_cpu(gdp->bg_inode_bitmap_csum_hi); + provided |= (hi << 16); + } else + calculated &= 0xFFFF; + + return provided == calculated; +} + +void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 csum; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + gdp->bg_inode_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); + if (sbi->s_desc_size >= EXT4_BG_INODE_BITMAP_CSUM_HI_END) + gdp->bg_inode_bitmap_csum_hi = cpu_to_le16(csum >> 16); +} + +int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 hi; + __u32 provided, calculated; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + provided = le16_to_cpu(gdp->bg_block_bitmap_csum_lo); + calculated = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) { + hi = le16_to_cpu(gdp->bg_block_bitmap_csum_hi); + provided |= (hi << 16); + } else + calculated &= 0xFFFF; + + if (provided == calculated) + return 1; + + ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); + return 0; +} + +void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz) +{ + __u32 csum; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)bh->b_data, sz); + gdp->bg_block_bitmap_csum_lo = cpu_to_le16(csum & 0xFFFF); + if (sbi->s_desc_size >= EXT4_BG_BLOCK_BITMAP_CSUM_HI_END) + gdp->bg_block_bitmap_csum_hi = cpu_to_le16(csum >> 16); +} diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index b8678620264..aa39e600d15 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -179,6 +179,18 @@ static int ext4_readdir(struct file *filp, continue; } + /* Check the checksum */ + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(inode, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_FILE(filp, 0, "directory fails checksum " + "at offset %llu", + (unsigned long long)filp->f_pos); + filp->f_pos += sb->s_blocksize - offset; + continue; + } + set_buffer_verified(bh); + revalidate: /* If the dir block has changed since the last call to * readdir(2), then we might be pointing to an invalid diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0e01e90add8..cfc4e01b3c8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -29,6 +29,7 @@ #include <linux/wait.h> #include <linux/blockgroup_lock.h> #include <linux/percpu_counter.h> +#include <crypto/hash.h> #ifdef __KERNEL__ #include <linux/compat.h> #endif @@ -298,7 +299,9 @@ struct ext4_group_desc __le16 bg_free_inodes_count_lo;/* Free inodes count */ __le16 bg_used_dirs_count_lo; /* Directories count */ __le16 bg_flags; /* EXT4_BG_flags (INODE_UNINIT, etc) */ - __u32 bg_reserved[2]; /* Likely block/inode bitmap checksum */ + __le32 bg_exclude_bitmap_lo; /* Exclude bitmap for snapshots */ + __le16 bg_block_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+bbitmap) LE */ + __le16 bg_inode_bitmap_csum_lo;/* crc32c(s_uuid+grp_num+ibitmap) LE */ __le16 bg_itable_unused_lo; /* Unused inodes count */ __le16 bg_checksum; /* crc16(sb_uuid+group+desc) */ __le32 bg_block_bitmap_hi; /* Blocks bitmap block MSB */ @@ -308,9 +311,19 @@ struct ext4_group_desc __le16 bg_free_inodes_count_hi;/* Free inodes count MSB */ __le16 bg_used_dirs_count_hi; /* Directories count MSB */ __le16 bg_itable_unused_hi; /* Unused inodes count MSB */ - __u32 bg_reserved2[3]; + __le32 bg_exclude_bitmap_hi; /* Exclude bitmap block MSB */ + __le16 bg_block_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+bbitmap) BE */ + __le16 bg_inode_bitmap_csum_hi;/* crc32c(s_uuid+grp_num+ibitmap) BE */ + __u32 bg_reserved; }; +#define EXT4_BG_INODE_BITMAP_CSUM_HI_END \ + (offsetof(struct ext4_group_desc, bg_inode_bitmap_csum_hi) + \ + sizeof(__le16)) +#define EXT4_BG_BLOCK_BITMAP_CSUM_HI_END \ + (offsetof(struct ext4_group_desc, bg_block_bitmap_csum_hi) + \ + sizeof(__le16)) + /* * Structure of a flex block group info */ @@ -650,7 +663,8 @@ struct ext4_inode { __le16 l_i_file_acl_high; __le16 l_i_uid_high; /* these 2 fields */ __le16 l_i_gid_high; /* were reserved2[0] */ - __u32 l_i_reserved2; + __le16 l_i_checksum_lo;/* crc32c(uuid+inum+inode) LE */ + __le16 l_i_reserved; } linux2; struct { __le16 h_i_reserved1; /* Obsoleted fragment number/size which are removed in ext4 */ @@ -666,7 +680,7 @@ struct ext4_inode { } masix2; } osd2; /* OS dependent 2 */ __le16 i_extra_isize; - __le16 i_pad1; + __le16 i_checksum_hi; /* crc32c(uuid+inum+inode) BE */ __le32 i_ctime_extra; /* extra Change time (nsec << 2 | epoch) */ __le32 i_mtime_extra; /* extra Modification time(nsec << 2 | epoch) */ __le32 i_atime_extra; /* extra Access time (nsec << 2 | epoch) */ @@ -768,7 +782,7 @@ do { \ #define i_gid_low i_gid #define i_uid_high osd2.linux2.l_i_uid_high #define i_gid_high osd2.linux2.l_i_gid_high -#define i_reserved2 osd2.linux2.l_i_reserved2 +#define i_checksum_lo osd2.linux2.l_i_checksum_lo #elif defined(__GNU__) @@ -908,6 +922,9 @@ struct ext4_inode_info { */ tid_t i_sync_tid; tid_t i_datasync_tid; + + /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ + __u32 i_csum_seed; }; /* @@ -1001,6 +1018,9 @@ extern void ext4_set_bits(void *bm, int cur, int len); #define EXT4_ERRORS_PANIC 3 /* Panic */ #define EXT4_ERRORS_DEFAULT EXT4_ERRORS_CONTINUE +/* Metadata checksum algorithm codes */ +#define EXT4_CRC32C_CHKSUM 1 + /* * Structure of the super block */ @@ -1087,7 +1107,7 @@ struct ext4_super_block { __le64 s_mmp_block; /* Block for multi-mount protection */ __le32 s_raid_stripe_width; /* blocks on all data disks (N*stride)*/ __u8 s_log_groups_per_flex; /* FLEX_BG group size */ - __u8 s_reserved_char_pad; + __u8 s_checksum_type; /* metadata checksum algorithm used */ __le16 s_reserved_pad; __le64 s_kbytes_written; /* nr of lifetime kilobytes written */ __le32 s_snapshot_inum; /* Inode number of active snapshot */ @@ -1113,7 +1133,8 @@ struct ext4_super_block { __le32 s_usr_quota_inum; /* inode for tracking user quota */ __le32 s_grp_quota_inum; /* inode for tracking group quota */ __le32 s_overhead_clusters; /* overhead blocks/clusters in fs */ - __le32 s_reserved[109]; /* Padding to the end of the block */ + __le32 s_reserved[108]; /* Padding to the end of the block */ + __le32 s_checksum; /* crc32c(superblock) */ }; #define EXT4_S_ERR_LEN (EXT4_S_ERR_END - EXT4_S_ERR_START) @@ -1153,8 +1174,8 @@ struct ext4_sb_info { unsigned int s_mount_flags; unsigned int s_def_mount_opt; ext4_fsblk_t s_sb_block; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned short s_mount_state; unsigned short s_pad; int s_addr_per_block_bits; @@ -1176,6 +1197,7 @@ struct ext4_sb_info { struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; + struct super_block *s_sb; /* Journaling */ struct journal_s *s_journal; @@ -1266,6 +1288,12 @@ struct ext4_sb_info { /* record the last minlen when FITRIM is called. */ atomic_t s_last_trim_minblks; + + /* Reference to checksum algorithm driver via cryptoapi */ + struct crypto_shash *s_chksum_driver; + + /* Precomputed FS UUID checksum for seeding other checksums */ + __u32 s_csum_seed; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -1414,6 +1442,12 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) #define EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE 0x0040 #define EXT4_FEATURE_RO_COMPAT_QUOTA 0x0100 #define EXT4_FEATURE_RO_COMPAT_BIGALLOC 0x0200 +/* + * METADATA_CSUM also enables group descriptor checksums (GDT_CSUM). When + * METADATA_CSUM is set, group descriptor checksums use the same algorithm as + * all other data structures' checksums. However, the METADATA_CSUM and + * GDT_CSUM bits are mutually exclusive. + */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 @@ -1461,7 +1495,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei) EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE | \ EXT4_FEATURE_RO_COMPAT_BTREE_DIR |\ EXT4_FEATURE_RO_COMPAT_HUGE_FILE |\ - EXT4_FEATURE_RO_COMPAT_BIGALLOC) + EXT4_FEATURE_RO_COMPAT_BIGALLOC |\ + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) /* * Default values for user and/or group using reserved blocks @@ -1527,6 +1562,18 @@ struct ext4_dir_entry_2 { }; /* + * This is a bogus directory entry at the end of each leaf block that + * records checksums. + */ +struct ext4_dir_entry_tail { + __le32 det_reserved_zero1; /* Pretend to be unused */ + __le16 det_rec_len; /* 12 */ + __u8 det_reserved_zero2; /* Zero name length */ + __u8 det_reserved_ft; /* 0xDE, fake file type */ + __le32 det_checksum; /* crc32c(uuid+inum+dirblock) */ +}; + +/* * Ext4 directory file types. Only the low 3 bits are used. The * other bits are reserved for now. */ @@ -1541,6 +1588,8 @@ struct ext4_dir_entry_2 { #define EXT4_FT_MAX 8 +#define EXT4_FT_DIR_CSUM 0xDE + /* * EXT4_DIR_PAD defines the directory entries boundaries * @@ -1609,6 +1658,25 @@ static inline __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize) #define DX_HASH_HALF_MD4_UNSIGNED 4 #define DX_HASH_TEA_UNSIGNED 5 +static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc, + const void *address, unsigned int length) +{ + struct { + struct shash_desc shash; + char ctx[crypto_shash_descsize(sbi->s_chksum_driver)]; + } desc; + int err; + + desc.shash.tfm = sbi->s_chksum_driver; + desc.shash.flags = 0; + *(u32 *)desc.ctx = crc; + + err = crypto_shash_update(&desc.shash, address, length); + BUG_ON(err); + + return *(u32 *)desc.ctx; +} + #ifdef __KERNEL__ /* hash info structure used by the directory hash */ @@ -1741,7 +1809,8 @@ struct mmp_struct { __le16 mmp_check_interval; __le16 mmp_pad1; - __le32 mmp_pad2[227]; + __le32 mmp_pad2[226]; + __le32 mmp_checksum; /* crc32c(uuid+mmp_block) */ }; /* arguments passed to the mmp thread */ @@ -1784,8 +1853,24 @@ struct mmpd_data { /* bitmap.c */ extern unsigned int ext4_count_free(struct buffer_head *, unsigned); +void ext4_inode_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +int ext4_inode_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +void ext4_block_bitmap_csum_set(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); +int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, + struct ext4_group_desc *gdp, + struct buffer_head *bh, int sz); /* balloc.c */ +extern void ext4_validate_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh); extern unsigned int ext4_block_group(struct super_block *sb, ext4_fsblk_t blocknr); extern ext4_grpblk_t ext4_block_group_offset(struct super_block *sb, @@ -1864,7 +1949,7 @@ extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate); /* mballoc.c */ extern long ext4_mb_stats; extern long ext4_mb_max_to_scan; -extern int ext4_mb_init(struct super_block *, int); +extern int ext4_mb_init(struct super_block *); extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); @@ -1936,6 +2021,8 @@ extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long); extern int ext4_ext_migrate(struct inode *); /* namei.c */ +extern int ext4_dirent_csum_verify(struct inode *inode, + struct ext4_dir_entry *dirent); extern int ext4_orphan_add(handle_t *, struct inode *); extern int ext4_orphan_del(handle_t *, struct inode *); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, @@ -1950,6 +2037,10 @@ extern int ext4_group_extend(struct super_block *sb, extern int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count); /* super.c */ +extern int ext4_superblock_csum_verify(struct super_block *sb, + struct ext4_super_block *es); +extern void ext4_superblock_csum_set(struct super_block *sb, + struct ext4_super_block *es); extern void *ext4_kvmalloc(size_t size, gfp_t flags); extern void *ext4_kvzalloc(size_t size, gfp_t flags); extern void ext4_kvfree(void *ptr); @@ -2025,10 +2116,17 @@ extern void ext4_used_dirs_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); extern void ext4_itable_unused_set(struct super_block *sb, struct ext4_group_desc *bg, __u32 count); -extern __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 group, - struct ext4_group_desc *gdp); -extern int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 group, +extern int ext4_group_desc_csum_verify(struct super_block *sb, __u32 group, struct ext4_group_desc *gdp); +extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group, + struct ext4_group_desc *gdp); + +static inline int ext4_has_group_desc_csum(struct super_block *sb) +{ + return EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_GDT_CSUM | + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM); +} static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es) { @@ -2225,6 +2323,9 @@ static inline void ext4_unlock_group(struct super_block *sb, static inline void ext4_mark_super_dirty(struct super_block *sb) { + struct ext4_super_block *es = EXT4_SB(sb)->s_es; + + ext4_superblock_csum_set(sb, es); if (EXT4_SB(sb)->s_journal == NULL) sb->s_dirt =1; } @@ -2314,6 +2415,9 @@ extern int ext4_bio_write_page(struct ext4_io_submit *io, /* mmp.c */ extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t); +extern void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp); +extern int ext4_mmp_csum_verify(struct super_block *sb, + struct mmp_struct *mmp); /* BH_Uninit flag: blocks are allocated but uninitialized on disk */ enum ext4_state_bits { diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index 0f58b86e3a0..cb1b2c91996 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -63,9 +63,22 @@ * ext4_inode has i_block array (60 bytes total). * The first 12 bytes store ext4_extent_header; * the remainder stores an array of ext4_extent. + * For non-inode extent blocks, ext4_extent_tail + * follows the array. */ /* + * This is the extent tail on-disk structure. + * All other extent structures are 12 bytes long. It turns out that + * block_size % 12 >= 4 for at least all powers of 2 greater than 512, which + * covers all valid ext4 block sizes. Therefore, this tail structure can be + * crammed into the end of the block without having to rebalance the tree. + */ +struct ext4_extent_tail { + __le32 et_checksum; /* crc32c(uuid+inum+extent_block) */ +}; + +/* * This is the extent on-disk structure. * It's used at the bottom of the tree. */ @@ -101,6 +114,17 @@ struct ext4_extent_header { #define EXT4_EXT_MAGIC cpu_to_le16(0xf30a) +#define EXT4_EXTENT_TAIL_OFFSET(hdr) \ + (sizeof(struct ext4_extent_header) + \ + (sizeof(struct ext4_extent) * le16_to_cpu((hdr)->eh_max))) + +static inline struct ext4_extent_tail * +find_ext4_extent_tail(struct ext4_extent_header *eh) +{ + return (struct ext4_extent_tail *)(((void *)eh) + + EXT4_EXTENT_TAIL_OFFSET(eh)); +} + /* * Array of ext4_ext_path contains path to some extent. * Creation/lookup routines use it for traversal/splitting/etc. diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index aca17901758..90f7c2e84db 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -138,16 +138,23 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb) + handle_t *handle, struct super_block *sb, + int now) { struct buffer_head *bh = EXT4_SB(sb)->s_sbh; int err = 0; if (ext4_handle_valid(handle)) { + ext4_superblock_csum_set(sb, + (struct ext4_super_block *)bh->b_data); err = jbd2_journal_dirty_metadata(handle, bh); if (err) ext4_journal_abort_handle(where, line, __func__, bh, handle, err); + } else if (now) { + ext4_superblock_csum_set(sb, + (struct ext4_super_block *)bh->b_data); + mark_buffer_dirty(bh); } else sb->s_dirt = 1; return err; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 83b20fcf940..f440e8f1841 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -213,7 +213,8 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, struct buffer_head *bh); int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb); + handle_t *handle, struct super_block *sb, + int now); #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) @@ -225,8 +226,10 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) +#define ext4_handle_dirty_super_now(handle, sb) \ + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 1) #define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) + __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb), 0) handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks); int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index abcdeab67f5..91341ec6e06 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -52,6 +52,46 @@ #define EXT4_EXT_MARK_UNINIT1 0x2 /* mark first half uninitialized */ #define EXT4_EXT_MARK_UNINIT2 0x4 /* mark second half uninitialized */ +static __le32 ext4_extent_block_csum(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __u32 csum; + + csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)eh, + EXT4_EXTENT_TAIL_OFFSET(eh)); + return cpu_to_le32(csum); +} + +static int ext4_extent_block_csum_verify(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent_tail *et; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + et = find_ext4_extent_tail(eh); + if (et->et_checksum != ext4_extent_block_csum(inode, eh)) + return 0; + return 1; +} + +static void ext4_extent_block_csum_set(struct inode *inode, + struct ext4_extent_header *eh) +{ + struct ext4_extent_tail *et; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + et = find_ext4_extent_tail(eh); + et->et_checksum = ext4_extent_block_csum(inode, eh); +} + static int ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, @@ -117,6 +157,7 @@ static int __ext4_ext_dirty(const char *where, unsigned int line, { int err; if (path->p_bh) { + ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); @@ -391,6 +432,12 @@ static int __ext4_ext_check(const char *function, unsigned int line, error_msg = "invalid extent entries"; goto corrupted; } + /* Verify checksum on non-root extent tree nodes */ + if (ext_depth(inode) != depth && + !ext4_extent_block_csum_verify(inode, eh)) { + error_msg = "extent tree corrupted"; + goto corrupted; + } return 0; corrupted: @@ -412,6 +459,26 @@ int ext4_ext_check_inode(struct inode *inode) return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode)); } +static int __ext4_ext_check_block(const char *function, unsigned int line, + struct inode *inode, + struct ext4_extent_header *eh, + int depth, + struct buffer_head *bh) +{ + int ret; + + if (buffer_verified(bh)) + return 0; + ret = ext4_ext_check(inode, eh, depth); + if (ret) + return ret; + set_buffer_verified(bh); + return ret; +} + +#define ext4_ext_check_block(inode, eh, depth, bh) \ + __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh) + #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { @@ -536,7 +603,7 @@ ext4_ext_binsearch_idx(struct inode *inode, } path->p_idx = l - 1; - ext_debug(" -> %d->%lld ", le32_to_cpu(path->p_idx->ei_block), + ext_debug(" -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH @@ -668,8 +735,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, i = depth; /* walk through the tree */ while (i) { - int need_to_validate = 0; - ext_debug("depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); @@ -688,8 +753,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, put_bh(bh); goto err; } - /* validate the extent entries */ - need_to_validate = 1; } eh = ext_block_hdr(bh); ppos++; @@ -703,7 +766,7 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block, path[ppos].p_hdr = eh; i--; - if (need_to_validate && ext4_ext_check(inode, eh, i)) + if (ext4_ext_check_block(inode, eh, i, bh)) goto err; } @@ -914,6 +977,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, le16_add_cpu(&neh->eh_entries, m); } + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -992,6 +1056,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1089,6 +1154,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; + ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); @@ -1344,7 +1410,8 @@ got_index: return -EIO; eh = ext_block_hdr(bh); /* subtract from p_depth to get proper eh_depth */ - if (ext4_ext_check(inode, eh, path->p_depth - depth)) { + if (ext4_ext_check_block(inode, eh, + path->p_depth - depth, bh)) { put_bh(bh); return -EIO; } @@ -1357,7 +1424,7 @@ got_index: if (bh == NULL) return -EIO; eh = ext_block_hdr(bh); - if (ext4_ext_check(inode, eh, path->p_depth - depth)) { + if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) { put_bh(bh); return -EIO; } @@ -2644,8 +2711,8 @@ cont: err = -EIO; break; } - if (ext4_ext_check(inode, ext_block_hdr(bh), - depth - i - 1)) { + if (ext4_ext_check_block(inode, ext_block_hdr(bh), + depth - i - 1, bh)) { err = -EIO; break; } @@ -4722,8 +4789,8 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) /* Now release the pages */ if (last_page_offset > first_page_offset) { - truncate_inode_pages_range(mapping, first_page_offset, - last_page_offset-1); + truncate_pagecache_range(inode, first_page_offset, + last_page_offset - 1); } /* finish any pending end_io work */ diff --git a/fs/ext4/file.c b/fs/ext4/file.c index cb70f1812a7..8c7642a0005 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -95,7 +95,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; int unaligned_aio = 0; - int ret; + ssize_t ret; /* * If we have encountered a bitmap-format file, the size limit diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 409c2ee7750..d48e8b14928 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -70,24 +70,27 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, ext4_group_t block_group, struct ext4_group_desc *gdp) { - struct ext4_sb_info *sbi = EXT4_SB(sb); - J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ - if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) { + if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); ext4_free_group_clusters_set(sb, gdp, 0); ext4_free_inodes_set(sb, gdp, 0); ext4_itable_unused_set(sb, gdp, 0); memset(bh->b_data, 0xff, sb->s_blocksize); + ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_INODES_PER_GROUP(sb) / 8); return 0; } memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8); ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); + ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh, + EXT4_INODES_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, gdp); return EXT4_INODES_PER_GROUP(sb); } @@ -128,12 +131,12 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) return NULL; } if (bitmap_uptodate(bh)) - return bh; + goto verify; lock_buffer(bh); if (bitmap_uptodate(bh)) { unlock_buffer(bh); - return bh; + goto verify; } ext4_lock_group(sb, block_group); @@ -141,6 +144,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) ext4_init_inode_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); + set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); return bh; @@ -154,7 +158,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) */ set_bitmap_uptodate(bh); unlock_buffer(bh); - return bh; + goto verify; } /* * submit the buffer_head for reading @@ -171,6 +175,20 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) block_group, bitmap_blk); return NULL; } + +verify: + ext4_lock_group(sb, block_group); + if (!buffer_verified(bh) && + !ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh, + EXT4_INODES_PER_GROUP(sb) / 8)) { + ext4_unlock_group(sb, block_group); + put_bh(bh); + ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " + "inode_bitmap = %llu", block_group, bitmap_blk); + return NULL; + } + ext4_unlock_group(sb, block_group); + set_buffer_verified(bh); return bh; } @@ -276,7 +294,9 @@ void ext4_free_inode(handle_t *handle, struct inode *inode) ext4_used_dirs_set(sb, gdp, count); percpu_counter_dec(&sbi->s_dirs_counter); } - gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); + ext4_inode_bitmap_csum_set(sb, block_group, gdp, bitmap_bh, + EXT4_INODES_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); percpu_counter_inc(&sbi->s_freeinodes_counter); @@ -488,10 +508,12 @@ fallback_retry: for (i = 0; i < ngroups; i++) { grp = (parent_group + i) % ngroups; desc = ext4_get_group_desc(sb, grp, NULL); - grp_free = ext4_free_inodes_count(sb, desc); - if (desc && grp_free && grp_free >= avefreei) { - *group = grp; - return 0; + if (desc) { + grp_free = ext4_free_inodes_count(sb, desc); + if (grp_free && grp_free >= avefreei) { + *group = grp; + return 0; + } } } @@ -709,7 +731,7 @@ repeat_in_this_group: got: /* We may have to initialize the block bitmap if it isn't already */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) && + if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { struct buffer_head *block_bitmap_bh; @@ -731,8 +753,11 @@ got: gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT); ext4_free_group_clusters_set(sb, gdp, ext4_free_clusters_after_init(sb, group, gdp)); - gdp->bg_checksum = ext4_group_desc_csum(sbi, group, - gdp); + ext4_block_bitmap_csum_set(sb, group, gdp, + block_bitmap_bh, + EXT4_BLOCKS_PER_GROUP(sb) / + 8); + ext4_group_desc_csum_set(sb, group, gdp); } ext4_unlock_group(sb, group); @@ -751,7 +776,7 @@ got: goto fail; /* Update the relevant bg descriptor fields */ - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { + if (ext4_has_group_desc_csum(sb)) { int free; struct ext4_group_info *grp = ext4_get_group_info(sb, group); @@ -772,7 +797,10 @@ got: ext4_itable_unused_set(sb, gdp, (EXT4_INODES_PER_GROUP(sb) - ino)); up_read(&grp->alloc_sem); + } else { + ext4_lock_group(sb, group); } + ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1); if (S_ISDIR(mode)) { ext4_used_dirs_set(sb, gdp, ext4_used_dirs_count(sb, gdp) + 1); @@ -782,10 +810,12 @@ got: atomic_inc(&sbi->s_flex_groups[f].used_dirs); } } - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { - gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); - ext4_unlock_group(sb, group); + if (ext4_has_group_desc_csum(sb)) { + ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh, + EXT4_INODES_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, group, gdp); } + ext4_unlock_group(sb, group); BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); @@ -808,8 +838,8 @@ got: } if (owner) { inode->i_mode = mode; - inode->i_uid = owner[0]; - inode->i_gid = owner[1]; + i_uid_write(inode, owner[0]); + i_gid_write(inode, owner[1]); } else if (test_opt(sb, GRPID)) { inode->i_mode = mode; inode->i_uid = current_fsuid(); @@ -850,6 +880,19 @@ got: inode->i_generation = sbi->s_next_generation++; spin_unlock(&sbi->s_next_gen_lock); + /* Precompute checksum seed for inode metadata */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + __u32 csum; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __le32 inum = cpu_to_le32(inode->i_ino); + __le32 gen = cpu_to_le32(inode->i_generation); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, + sizeof(inum)); + ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, + sizeof(gen)); + } + ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ext4_set_inode_state(inode, EXT4_STATE_NEW); @@ -1140,7 +1183,7 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group, skip_zeroout: ext4_lock_group(sb, group); gdp->bg_flags |= cpu_to_le16(EXT4_BG_INODE_ZEROED); - gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); + ext4_group_desc_csum_set(sb, group, gdp); ext4_unlock_group(sb, group); BUFFER_TRACE(group_desc_bh, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c77b0bd2c71..02bc8cbe728 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -47,6 +47,73 @@ #define MPAGE_DA_EXTENT_TAIL 0x01 +static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, + struct ext4_inode_info *ei) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __u16 csum_lo; + __u16 csum_hi = 0; + __u32 csum; + + csum_lo = raw->i_checksum_lo; + raw->i_checksum_lo = 0; + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { + csum_hi = raw->i_checksum_hi; + raw->i_checksum_hi = 0; + } + + csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)raw, + EXT4_INODE_SIZE(inode->i_sb)); + + raw->i_checksum_lo = csum_lo; + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) + raw->i_checksum_hi = csum_hi; + + return csum; +} + +static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, + struct ext4_inode_info *ei) +{ + __u32 provided, calculated; + + if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != + cpu_to_le32(EXT4_OS_LINUX) || + !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + provided = le16_to_cpu(raw->i_checksum_lo); + calculated = ext4_inode_csum(inode, raw, ei); + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) + provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16; + else + calculated &= 0xFFFF; + + return provided == calculated; +} + +static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, + struct ext4_inode_info *ei) +{ + __u32 csum; + + if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != + cpu_to_le32(EXT4_OS_LINUX) || + !EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + csum = ext4_inode_csum(inode, raw, ei); + raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF); + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && + EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) + raw->i_checksum_hi = cpu_to_le16(csum >> 16); +} + static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { @@ -3517,8 +3584,7 @@ make_io: b = table; end = b + EXT4_SB(sb)->s_inode_readahead_blks; num = EXT4_INODES_PER_GROUP(sb); - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) + if (ext4_has_group_desc_csum(sb)) num -= ext4_itable_unused_count(sb, gdp); table += num / inodes_per_block; if (end > table) @@ -3630,6 +3696,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) journal_t *journal = EXT4_SB(sb)->s_journal; long ret; int block; + uid_t i_uid; + gid_t i_gid; inode = iget_locked(sb, ino); if (!inode) @@ -3644,13 +3712,48 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (ret < 0) goto bad_inode; raw_inode = ext4_raw_inode(&iloc); + + if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { + ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); + if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > + EXT4_INODE_SIZE(inode->i_sb)) { + EXT4_ERROR_INODE(inode, "bad extra_isize (%u != %u)", + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize, + EXT4_INODE_SIZE(inode->i_sb)); + ret = -EIO; + goto bad_inode; + } + } else + ei->i_extra_isize = 0; + + /* Precompute checksum seed for inode metadata */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + __u32 csum; + __le32 inum = cpu_to_le32(inode->i_ino); + __le32 gen = raw_inode->i_generation; + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&inum, + sizeof(inum)); + ei->i_csum_seed = ext4_chksum(sbi, csum, (__u8 *)&gen, + sizeof(gen)); + } + + if (!ext4_inode_csum_verify(inode, raw_inode, ei)) { + EXT4_ERROR_INODE(inode, "checksum invalid"); + ret = -EIO; + goto bad_inode; + } + inode->i_mode = le16_to_cpu(raw_inode->i_mode); - inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); - inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); + i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); + i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (!(test_opt(inode->i_sb, NO_UID32))) { - inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; - inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; + i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; + i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } + i_uid_write(inode, i_uid); + i_gid_write(inode, i_gid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ @@ -3721,12 +3824,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) } if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { - ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); - if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > - EXT4_INODE_SIZE(inode->i_sb)) { - ret = -EIO; - goto bad_inode; - } if (ei->i_extra_isize == 0) { /* The extra space is currently unused. Use it. */ ei->i_extra_isize = sizeof(struct ext4_inode) - @@ -3738,8 +3835,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) ext4_set_inode_state(inode, EXT4_STATE_XATTR); } - } else - ei->i_extra_isize = 0; + } EXT4_INODE_GET_XTIME(i_ctime, inode, raw_inode); EXT4_INODE_GET_XTIME(i_mtime, inode, raw_inode); @@ -3870,6 +3966,8 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; int err = 0, rc, block; + uid_t i_uid; + gid_t i_gid; /* For fields not not tracking in the in-memory inode, * initialise them to zero for new inodes. */ @@ -3878,27 +3976,27 @@ static int ext4_do_update_inode(handle_t *handle, ext4_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); + i_uid = i_uid_read(inode); + i_gid = i_gid_read(inode); if (!(test_opt(inode->i_sb, NO_UID32))) { - raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); - raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ if (!ei->i_dtime) { raw_inode->i_uid_high = - cpu_to_le16(high_16_bits(inode->i_uid)); + cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = - cpu_to_le16(high_16_bits(inode->i_gid)); + cpu_to_le16(high_16_bits(i_gid)); } else { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } } else { - raw_inode->i_uid_low = - cpu_to_le16(fs_high2lowuid(inode->i_uid)); - raw_inode->i_gid_low = - cpu_to_le16(fs_high2lowgid(inode->i_gid)); + raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); + raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } @@ -3936,7 +4034,7 @@ static int ext4_do_update_inode(handle_t *handle, EXT4_SET_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_LARGE_FILE); ext4_handle_sync(handle); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_super_now(handle, sb); } } raw_inode->i_generation = cpu_to_le32(inode->i_generation); @@ -3963,6 +4061,8 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); } + ext4_inode_csum_set(inode, raw_inode, ei); + BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); rc = ext4_handle_dirty_metadata(handle, NULL, bh); if (!err) @@ -4084,8 +4184,8 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) if (is_quota_modification(inode, attr)) dquot_initialize(inode); - if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) || - (ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) { + if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || + (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, @@ -4207,7 +4307,8 @@ int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, * will return the blocks that include the delayed allocation * blocks for this file. */ - delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks; + delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb), + EXT4_I(inode)->i_reserved_data_blocks); stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9; return 0; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 6eee25591b8..e34deac3f36 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -38,7 +38,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) handle_t *handle = NULL; int err, migrate = 0; struct ext4_iloc iloc; - unsigned int oldflags; + unsigned int oldflags, mask, i; unsigned int jflag; if (!inode_owner_or_capable(inode)) @@ -115,9 +115,14 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (err) goto flags_err; - flags = flags & EXT4_FL_USER_MODIFIABLE; - flags |= oldflags & ~EXT4_FL_USER_MODIFIABLE; - ei->i_flags = flags; + for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { + if (!(mask & EXT4_FL_USER_MODIFIABLE)) + continue; + if (mask & flags) + ext4_set_inode_flag(inode, i); + else + ext4_clear_inode_flag(inode, i); + } ext4_set_inode_flags(inode); inode->i_ctime = ext4_current_time(inode); @@ -152,6 +157,13 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + ext4_warning(sb, "Setting inode version is not " + "supported with metadata_csum enabled."); + return -ENOTTY; + } + err = mnt_want_write_file(filp); if (err) return err; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 99ab428bcfa..1cd6994fc44 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -788,7 +788,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore) int first_block; struct super_block *sb; struct buffer_head *bhs; - struct buffer_head **bh; + struct buffer_head **bh = NULL; struct inode *inode; char *data; char *bitmap; @@ -2375,7 +2375,7 @@ static int ext4_groupinfo_create_slab(size_t size) return 0; } -int ext4_mb_init(struct super_block *sb, int needs_recovery) +int ext4_mb_init(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned i, j; @@ -2517,6 +2517,9 @@ int ext4_mb_release(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); + if (sbi->s_proc) + remove_proc_entry("mb_groups", sbi->s_proc); + if (sbi->s_group_info) { for (i = 0; i < ngroups; i++) { grinfo = ext4_get_group_info(sb, i); @@ -2564,8 +2567,6 @@ int ext4_mb_release(struct super_block *sb) } free_percpu(sbi->s_locality_groups); - if (sbi->s_proc) - remove_proc_entry("mb_groups", sbi->s_proc); return 0; } @@ -2797,7 +2798,9 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, } len = ext4_free_group_clusters(sb, gdp) - ac->ac_b_ex.fe_len; ext4_free_group_clusters_set(sb, gdp, len); - gdp->bg_checksum = ext4_group_desc_csum(sbi, ac->ac_b_ex.fe_group, gdp); + ext4_block_bitmap_csum_set(sb, ac->ac_b_ex.fe_group, gdp, bitmap_bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, ac->ac_b_ex.fe_group, gdp); ext4_unlock_group(sb, ac->ac_b_ex.fe_group); percpu_counter_sub(&sbi->s_freeclusters_counter, ac->ac_b_ex.fe_len); @@ -3071,13 +3074,9 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) { struct ext4_prealloc_space *pa = ac->ac_pa; - int len; - - if (pa && pa->pa_type == MB_INODE_PA) { - len = ac->ac_b_ex.fe_len; - pa->pa_free += len; - } + if (pa && pa->pa_type == MB_INODE_PA) + pa->pa_free += ac->ac_b_ex.fe_len; } /* @@ -4636,6 +4635,7 @@ do_more: */ new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS); if (!new_entry) { + ext4_mb_unload_buddy(&e4b); err = -ENOMEM; goto error_return; } @@ -4659,7 +4659,9 @@ do_more: ret = ext4_free_group_clusters(sb, gdp) + count_clusters; ext4_free_group_clusters_set(sb, gdp, ret); - gdp->bg_checksum = ext4_group_desc_csum(sbi, block_group, gdp); + ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, gdp); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters); @@ -4803,7 +4805,9 @@ int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, mb_free_blocks(NULL, &e4b, bit, count); blk_free_count = blocks_freed + ext4_free_group_clusters(sb, desc); ext4_free_group_clusters_set(sb, desc, blk_free_count); - desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc); + ext4_block_bitmap_csum_set(sb, block_group, desc, bitmap_bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + ext4_group_desc_csum_set(sb, block_group, desc); ext4_unlock_group(sb, block_group); percpu_counter_add(&sbi->s_freeclusters_counter, EXT4_B2C(sbi, blocks_freed)); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index f39f80f8f2c..f1bb32ec016 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -466,8 +466,8 @@ int ext4_ext_migrate(struct inode *inode) } goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) * EXT4_INODES_PER_GROUP(inode->i_sb)) + 1; - owner[0] = inode->i_uid; - owner[1] = inode->i_gid; + owner[0] = i_uid_read(inode); + owner[1] = i_gid_read(inode); tmp_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG, NULL, goal, owner); if (IS_ERR(tmp_inode)) { diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index ed6548d8916..f99a1311e84 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -6,12 +6,45 @@ #include "ext4.h" +/* Checksumming functions */ +static __u32 ext4_mmp_csum(struct super_block *sb, struct mmp_struct *mmp) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int offset = offsetof(struct mmp_struct, mmp_checksum); + __u32 csum; + + csum = ext4_chksum(sbi, sbi->s_csum_seed, (char *)mmp, offset); + + return cpu_to_le32(csum); +} + +int ext4_mmp_csum_verify(struct super_block *sb, struct mmp_struct *mmp) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + return mmp->mmp_checksum == ext4_mmp_csum(sb, mmp); +} + +void ext4_mmp_csum_set(struct super_block *sb, struct mmp_struct *mmp) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + mmp->mmp_checksum = ext4_mmp_csum(sb, mmp); +} + /* * Write the MMP block using WRITE_SYNC to try to get the block on-disk * faster. */ -static int write_mmp_block(struct buffer_head *bh) +static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) { + struct mmp_struct *mmp = (struct mmp_struct *)(bh->b_data); + + ext4_mmp_csum_set(sb, mmp); mark_buffer_dirty(bh); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; @@ -59,7 +92,8 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh, } mmp = (struct mmp_struct *)((*bh)->b_data); - if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) + if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC || + !ext4_mmp_csum_verify(sb, mmp)) return -EINVAL; return 0; @@ -120,7 +154,7 @@ static int kmmpd(void *data) mmp->mmp_time = cpu_to_le64(get_seconds()); last_update_time = jiffies; - retval = write_mmp_block(bh); + retval = write_mmp_block(sb, bh); /* * Don't spew too many error messages. Print one every * (s_mmp_update_interval * 60) seconds. @@ -200,7 +234,7 @@ static int kmmpd(void *data) mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN); mmp->mmp_time = cpu_to_le64(get_seconds()); - retval = write_mmp_block(bh); + retval = write_mmp_block(sb, bh); failed: kfree(data); @@ -299,7 +333,7 @@ skip: seq = mmp_new_seq(); mmp->mmp_seq = cpu_to_le32(seq); - retval = write_mmp_block(bh); + retval = write_mmp_block(sb, bh); if (retval) goto failed; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 349d7b3671c..5845cd97bf8 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -145,6 +145,14 @@ struct dx_map_entry u16 size; }; +/* + * This goes at the end of each htree block. + */ +struct dx_tail { + u32 dt_reserved; + __le32 dt_checksum; /* crc32c(uuid+inum+dirblock) */ +}; + static inline ext4_lblk_t dx_get_block(struct dx_entry *entry); static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value); static inline unsigned dx_get_hash(struct dx_entry *entry); @@ -180,6 +188,230 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, struct inode *inode); +/* checksumming functions */ +#define EXT4_DIRENT_TAIL(block, blocksize) \ + ((struct ext4_dir_entry_tail *)(((void *)(block)) + \ + ((blocksize) - \ + sizeof(struct ext4_dir_entry_tail)))) + +static void initialize_dirent_tail(struct ext4_dir_entry_tail *t, + unsigned int blocksize) +{ + memset(t, 0, sizeof(struct ext4_dir_entry_tail)); + t->det_rec_len = ext4_rec_len_to_disk( + sizeof(struct ext4_dir_entry_tail), blocksize); + t->det_reserved_ft = EXT4_FT_DIR_CSUM; +} + +/* Walk through a dirent block to find a checksum "dirent" at the tail */ +static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, + struct ext4_dir_entry *de) +{ + struct ext4_dir_entry_tail *t; + +#ifdef PARANOID + struct ext4_dir_entry *d, *top; + + d = de; + top = (struct ext4_dir_entry *)(((void *)de) + + (EXT4_BLOCK_SIZE(inode->i_sb) - + sizeof(struct ext4_dir_entry_tail))); + while (d < top && d->rec_len) + d = (struct ext4_dir_entry *)(((void *)d) + + le16_to_cpu(d->rec_len)); + + if (d != top) + return NULL; + + t = (struct ext4_dir_entry_tail *)d; +#else + t = EXT4_DIRENT_TAIL(de, EXT4_BLOCK_SIZE(inode->i_sb)); +#endif + + if (t->det_reserved_zero1 || + le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) || + t->det_reserved_zero2 || + t->det_reserved_ft != EXT4_FT_DIR_CSUM) + return NULL; + + return t; +} + +static __le32 ext4_dirent_csum(struct inode *inode, + struct ext4_dir_entry *dirent, int size) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + __u32 csum; + + csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size); + return cpu_to_le32(csum); +} + +int ext4_dirent_csum_verify(struct inode *inode, struct ext4_dir_entry *dirent) +{ + struct ext4_dir_entry_tail *t; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + t = get_dirent_tail(inode, dirent); + if (!t) { + EXT4_ERROR_INODE(inode, "metadata_csum set but no space in dir " + "leaf for checksum. Please run e2fsck -D."); + return 0; + } + + if (t->det_checksum != ext4_dirent_csum(inode, dirent, + (void *)t - (void *)dirent)) + return 0; + + return 1; +} + +static void ext4_dirent_csum_set(struct inode *inode, + struct ext4_dir_entry *dirent) +{ + struct ext4_dir_entry_tail *t; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + t = get_dirent_tail(inode, dirent); + if (!t) { + EXT4_ERROR_INODE(inode, "metadata_csum set but no space in dir " + "leaf for checksum. Please run e2fsck -D."); + return; + } + + t->det_checksum = ext4_dirent_csum(inode, dirent, + (void *)t - (void *)dirent); +} + +static inline int ext4_handle_dirty_dirent_node(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) +{ + ext4_dirent_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); + return ext4_handle_dirty_metadata(handle, inode, bh); +} + +static struct dx_countlimit *get_dx_countlimit(struct inode *inode, + struct ext4_dir_entry *dirent, + int *offset) +{ + struct ext4_dir_entry *dp; + struct dx_root_info *root; + int count_offset; + + if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) + count_offset = 8; + else if (le16_to_cpu(dirent->rec_len) == 12) { + dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); + if (le16_to_cpu(dp->rec_len) != + EXT4_BLOCK_SIZE(inode->i_sb) - 12) + return NULL; + root = (struct dx_root_info *)(((void *)dp + 12)); + if (root->reserved_zero || + root->info_length != sizeof(struct dx_root_info)) + return NULL; + count_offset = 32; + } else + return NULL; + + if (offset) + *offset = count_offset; + return (struct dx_countlimit *)(((void *)dirent) + count_offset); +} + +static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, + int count_offset, int count, struct dx_tail *t) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + __u32 csum, old_csum; + int size; + + size = count_offset + (count * sizeof(struct dx_entry)); + old_csum = t->dt_checksum; + t->dt_checksum = 0; + csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size); + csum = ext4_chksum(sbi, csum, (__u8 *)t, sizeof(struct dx_tail)); + t->dt_checksum = old_csum; + + return cpu_to_le32(csum); +} + +static int ext4_dx_csum_verify(struct inode *inode, + struct ext4_dir_entry *dirent) +{ + struct dx_countlimit *c; + struct dx_tail *t; + int count_offset, limit, count; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + c = get_dx_countlimit(inode, dirent, &count_offset); + if (!c) { + EXT4_ERROR_INODE(inode, "dir seems corrupt? Run e2fsck -D."); + return 1; + } + limit = le16_to_cpu(c->limit); + count = le16_to_cpu(c->count); + if (count_offset + (limit * sizeof(struct dx_entry)) > + EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) { + EXT4_ERROR_INODE(inode, "metadata_csum set but no space for " + "tree checksum found. Run e2fsck -D."); + return 1; + } + t = (struct dx_tail *)(((struct dx_entry *)c) + limit); + + if (t->dt_checksum != ext4_dx_csum(inode, dirent, count_offset, + count, t)) + return 0; + return 1; +} + +static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) +{ + struct dx_countlimit *c; + struct dx_tail *t; + int count_offset, limit, count; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + c = get_dx_countlimit(inode, dirent, &count_offset); + if (!c) { + EXT4_ERROR_INODE(inode, "dir seems corrupt? Run e2fsck -D."); + return; + } + limit = le16_to_cpu(c->limit); + count = le16_to_cpu(c->count); + if (count_offset + (limit * sizeof(struct dx_entry)) > + EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) { + EXT4_ERROR_INODE(inode, "metadata_csum set but no space for " + "tree checksum. Run e2fsck -D."); + return; + } + t = (struct dx_tail *)(((struct dx_entry *)c) + limit); + + t->dt_checksum = ext4_dx_csum(inode, dirent, count_offset, count, t); +} + +static inline int ext4_handle_dirty_dx_node(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) +{ + ext4_dx_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); + return ext4_handle_dirty_metadata(handle, inode, bh); +} + /* * p is at least 6 bytes before the end of page */ @@ -239,12 +471,20 @@ static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - EXT4_DIR_REC_LEN(2) - infosize; + + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } static inline unsigned dx_node_limit(struct inode *dir) { unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0); + + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + entry_space -= sizeof(struct dx_tail); return entry_space / sizeof(struct dx_entry); } @@ -390,6 +630,15 @@ dx_probe(const struct qstr *d_name, struct inode *dir, goto fail; } + if (!buffer_verified(bh) && + !ext4_dx_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) { + ext4_warning(dir->i_sb, "Root failed checksum"); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + set_buffer_verified(bh); + entries = (struct dx_entry *) (((char *)&root->info) + root->info.info_length); @@ -450,6 +699,17 @@ dx_probe(const struct qstr *d_name, struct inode *dir, if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err))) goto fail2; at = entries = ((struct dx_node *) bh->b_data)->entries; + + if (!buffer_verified(bh) && + !ext4_dx_csum_verify(dir, + (struct ext4_dir_entry *)bh->b_data)) { + ext4_warning(dir->i_sb, "Node failed checksum"); + brelse(bh); + *err = ERR_BAD_DX_DIR; + goto fail; + } + set_buffer_verified(bh); + if (dx_get_limit(entries) != dx_node_limit (dir)) { ext4_warning(dir->i_sb, "dx entry: limit != node limit"); @@ -549,6 +809,15 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at), 0, &err))) return err; /* Failure */ + + if (!buffer_verified(bh) && + !ext4_dx_csum_verify(dir, + (struct ext4_dir_entry *)bh->b_data)) { + ext4_warning(dir->i_sb, "Node failed checksum"); + return -EIO; + } + set_buffer_verified(bh); + p++; brelse(p->bh); p->bh = bh; @@ -577,6 +846,11 @@ static int htree_dirblock_to_tree(struct file *dir_file, if (!(bh = ext4_bread (NULL, dir, block, 0, &err))) return err; + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) + return -EIO; + set_buffer_verified(bh); + de = (struct ext4_dir_entry_2 *) bh->b_data; top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - @@ -936,6 +1210,15 @@ restart: brelse(bh); goto next; } + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(dir, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_INODE(dir, "checksumming directory " + "block %lu", (unsigned long)block); + brelse(bh); + goto next; + } + set_buffer_verified(bh); i = search_dirblock(bh, dir, d_name, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { @@ -987,6 +1270,16 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q if (!(bh = ext4_bread(NULL, dir, block, 0, err))) goto errout; + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(dir, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_INODE(dir, "checksumming directory " + "block %lu", (unsigned long)block); + brelse(bh); + *err = -EIO; + goto errout; + } + set_buffer_verified(bh); retval = search_dirblock(bh, dir, d_name, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); @@ -1037,6 +1330,12 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru EXT4_ERROR_INODE(dir, "bad inode number: %u", ino); return ERR_PTR(-EIO); } + if (unlikely(ino == dir->i_ino)) { + EXT4_ERROR_INODE(dir, "'%.*s' linked to parent dir", + dentry->d_name.len, + dentry->d_name.name); + return ERR_PTR(-EIO); + } inode = ext4_iget(dir->i_sb, ino); if (inode == ERR_PTR(-ESTALE)) { EXT4_ERROR_INODE(dir, @@ -1052,10 +1351,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, stru struct dentry *ext4_get_parent(struct dentry *child) { __u32 ino; - static const struct qstr dotdot = { - .name = "..", - .len = 2, - }; + static const struct qstr dotdot = QSTR_INIT("..", 2); struct ext4_dir_entry_2 * de; struct buffer_head *bh; @@ -1159,8 +1455,14 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, char *data1 = (*bh)->b_data, *data2; unsigned split, move, size; struct ext4_dir_entry_2 *de = NULL, *de2; + struct ext4_dir_entry_tail *t; + int csum_size = 0; int err = 0, i; + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); + bh2 = ext4_append (handle, dir, &newblock, &err); if (!(bh2)) { brelse(*bh); @@ -1207,10 +1509,20 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, /* Fancy dance to stay within two buffers */ de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize); de = dx_pack_dirents(data1, blocksize); - de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de, + de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - + (char *) de, blocksize); - de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2, + de2->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - + (char *) de2, blocksize); + if (csum_size) { + t = EXT4_DIRENT_TAIL(data2, blocksize); + initialize_dirent_tail(t, blocksize); + + t = EXT4_DIRENT_TAIL(data1, blocksize); + initialize_dirent_tail(t, blocksize); + } + dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1)); dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1)); @@ -1221,10 +1533,10 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, de = de2; } dx_insert_block(frame, hash2 + continued, newblock); - err = ext4_handle_dirty_metadata(handle, dir, bh2); + err = ext4_handle_dirty_dirent_node(handle, dir, bh2); if (err) goto journal_error; - err = ext4_handle_dirty_metadata(handle, dir, frame->bh); + err = ext4_handle_dirty_dx_node(handle, dir, frame->bh); if (err) goto journal_error; brelse(bh2); @@ -1261,11 +1573,16 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, unsigned short reclen; int nlen, rlen, err; char *top; + int csum_size = 0; + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); reclen = EXT4_DIR_REC_LEN(namelen); if (!de) { de = (struct ext4_dir_entry_2 *)bh->b_data; - top = bh->b_data + blocksize - reclen; + top = bh->b_data + (blocksize - csum_size) - reclen; while ((char *) de <= top) { if (ext4_check_dir_entry(dir, NULL, de, bh, offset)) return -EIO; @@ -1298,11 +1615,8 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, de = de1; } de->file_type = EXT4_FT_UNKNOWN; - if (inode) { - de->inode = cpu_to_le32(inode->i_ino); - ext4_set_de_type(dir->i_sb, de, inode->i_mode); - } else - de->inode = 0; + de->inode = cpu_to_le32(inode->i_ino); + ext4_set_de_type(dir->i_sb, de, inode->i_mode); de->name_len = namelen; memcpy(de->name, name, namelen); /* @@ -1321,7 +1635,7 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry, dir->i_version++; ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, dir, bh); + err = ext4_handle_dirty_dirent_node(handle, dir, bh); if (err) ext4_std_error(dir->i_sb, err); return 0; @@ -1342,6 +1656,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct dx_frame frames[2], *frame; struct dx_entry *entries; struct ext4_dir_entry_2 *de, *de2; + struct ext4_dir_entry_tail *t; char *data1, *top; unsigned len; int retval; @@ -1349,6 +1664,11 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, struct dx_hash_info hinfo; ext4_lblk_t block; struct fake_dirent *fde; + int csum_size = 0; + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); blocksize = dir->i_sb->s_blocksize; dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino)); @@ -1369,7 +1689,7 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, brelse(bh); return -EIO; } - len = ((char *) root) + blocksize - (char *) de; + len = ((char *) root) + (blocksize - csum_size) - (char *) de; /* Allocate new block for the 0th block's dirents */ bh2 = ext4_append(handle, dir, &block, &retval); @@ -1385,8 +1705,15 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, top = data1 + len; while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) de = de2; - de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de, + de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) - + (char *) de, blocksize); + + if (csum_size) { + t = EXT4_DIRENT_TAIL(data1, blocksize); + initialize_dirent_tail(t, blocksize); + } + /* Initialize the root; the dot dirents already exist */ de = (struct ext4_dir_entry_2 *) (&root->dotdot); de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(2), @@ -1411,8 +1738,8 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry, frame->bh = bh; bh = bh2; - ext4_handle_dirty_metadata(handle, dir, frame->bh); - ext4_handle_dirty_metadata(handle, dir, bh); + ext4_handle_dirty_dx_node(handle, dir, frame->bh); + ext4_handle_dirty_dirent_node(handle, dir, bh); de = do_split(handle,dir, &bh, frame, &hinfo, &retval); if (!de) { @@ -1448,11 +1775,17 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, struct inode *dir = dentry->d_parent->d_inode; struct buffer_head *bh; struct ext4_dir_entry_2 *de; + struct ext4_dir_entry_tail *t; struct super_block *sb; int retval; int dx_fallback=0; unsigned blocksize; ext4_lblk_t block, blocks; + int csum_size = 0; + + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); sb = dir->i_sb; blocksize = sb->s_blocksize; @@ -1471,6 +1804,11 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, bh = ext4_bread(handle, dir, block, 0, &retval); if(!bh) return retval; + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(dir, + (struct ext4_dir_entry *)bh->b_data)) + return -EIO; + set_buffer_verified(bh); retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh); if (retval != -ENOSPC) { brelse(bh); @@ -1487,7 +1825,13 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, return retval; de = (struct ext4_dir_entry_2 *) bh->b_data; de->inode = 0; - de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize); + de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize); + + if (csum_size) { + t = EXT4_DIRENT_TAIL(bh->b_data, blocksize); + initialize_dirent_tail(t, blocksize); + } + retval = add_dirent_to_buf(handle, dentry, inode, de, bh); brelse(bh); if (retval == 0) @@ -1519,6 +1863,11 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err))) goto cleanup; + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) + goto journal_error; + set_buffer_verified(bh); + BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); if (err) @@ -1586,7 +1935,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, dxtrace(dx_show_index("node", frames[1].entries)); dxtrace(dx_show_index("node", ((struct dx_node *) bh2->b_data)->entries)); - err = ext4_handle_dirty_metadata(handle, dir, bh2); + err = ext4_handle_dirty_dx_node(handle, dir, bh2); if (err) goto journal_error; brelse (bh2); @@ -1612,7 +1961,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, if (err) goto journal_error; } - err = ext4_handle_dirty_metadata(handle, dir, frames[0].bh); + err = ext4_handle_dirty_dx_node(handle, dir, frames[0].bh); if (err) { ext4_std_error(inode->i_sb, err); goto cleanup; @@ -1644,12 +1993,17 @@ static int ext4_delete_entry(handle_t *handle, { struct ext4_dir_entry_2 *de, *pde; unsigned int blocksize = dir->i_sb->s_blocksize; + int csum_size = 0; int i, err; + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); + i = 0; pde = NULL; de = (struct ext4_dir_entry_2 *) bh->b_data; - while (i < bh->b_size) { + while (i < bh->b_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, i)) return -EIO; if (de == de_del) { @@ -1670,7 +2024,7 @@ static int ext4_delete_entry(handle_t *handle, de->inode = 0; dir->i_version++; BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, dir, bh); + err = ext4_handle_dirty_dirent_node(handle, dir, bh); if (unlikely(err)) { ext4_std_error(dir->i_sb, err); return err; @@ -1812,9 +2166,15 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct inode *inode; struct buffer_head *dir_block = NULL; struct ext4_dir_entry_2 *de; + struct ext4_dir_entry_tail *t; unsigned int blocksize = dir->i_sb->s_blocksize; + int csum_size = 0; int err, retries = 0; + if (EXT4_HAS_RO_COMPAT_FEATURE(dir->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + csum_size = sizeof(struct ext4_dir_entry_tail); + if (EXT4_DIR_LINK_MAX(dir)) return -EMLINK; @@ -1855,16 +2215,24 @@ retry: ext4_set_de_type(dir->i_sb, de, S_IFDIR); de = ext4_next_entry(de, blocksize); de->inode = cpu_to_le32(dir->i_ino); - de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(1), + de->rec_len = ext4_rec_len_to_disk(blocksize - + (csum_size + EXT4_DIR_REC_LEN(1)), blocksize); de->name_len = 2; strcpy(de->name, ".."); ext4_set_de_type(dir->i_sb, de, S_IFDIR); set_nlink(inode, 2); + + if (csum_size) { + t = EXT4_DIRENT_TAIL(dir_block->b_data, blocksize); + initialize_dirent_tail(t, blocksize); + } + BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, inode, dir_block); + err = ext4_handle_dirty_dirent_node(handle, inode, dir_block); if (err) goto out_clear_inode; + set_buffer_verified(dir_block); err = ext4_mark_inode_dirty(handle, inode); if (!err) err = ext4_add_entry(handle, dentry, inode); @@ -1914,6 +2282,14 @@ static int empty_dir(struct inode *inode) inode->i_ino); return 1; } + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(inode, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_INODE(inode, "checksum error reading directory " + "lblock 0"); + return -EIO; + } + set_buffer_verified(bh); de = (struct ext4_dir_entry_2 *) bh->b_data; de1 = ext4_next_entry(de, sb->s_blocksize); if (le32_to_cpu(de->inode) != inode->i_ino || @@ -1945,6 +2321,14 @@ static int empty_dir(struct inode *inode) offset += sb->s_blocksize; continue; } + if (!buffer_verified(bh) && + !ext4_dirent_csum_verify(inode, + (struct ext4_dir_entry *)bh->b_data)) { + EXT4_ERROR_INODE(inode, "checksum error " + "reading directory lblock 0"); + return -EIO; + } + set_buffer_verified(bh); de = (struct ext4_dir_entry_2 *) bh->b_data; } if (ext4_check_dir_entry(inode, NULL, de, bh, offset)) { @@ -2013,7 +2397,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) /* Insert this inode at the head of the on-disk orphan list... */ NEXT_ORPHAN(inode) = le32_to_cpu(EXT4_SB(sb)->s_es->s_last_orphan); EXT4_SB(sb)->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); - err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_super_now(handle, sb); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -2086,7 +2470,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) if (err) goto out_brelse; sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); - err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); + err = ext4_handle_dirty_super_now(handle, inode->i_sb); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -2445,6 +2829,11 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval); if (!dir_bh) goto end_rename; + if (!buffer_verified(dir_bh) && + !ext4_dirent_csum_verify(old_inode, + (struct ext4_dir_entry *)dir_bh->b_data)) + goto end_rename; + set_buffer_verified(dir_bh); if (le32_to_cpu(PARENT_INO(dir_bh->b_data, old_dir->i_sb->s_blocksize)) != old_dir->i_ino) goto end_rename; @@ -2475,7 +2864,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, ext4_current_time(new_dir); ext4_mark_inode_dirty(handle, new_dir); BUFFER_TRACE(new_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_metadata(handle, new_dir, new_bh); + retval = ext4_handle_dirty_dirent_node(handle, new_dir, new_bh); if (unlikely(retval)) { ext4_std_error(new_dir->i_sb, retval); goto end_rename; @@ -2529,7 +2918,8 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) = cpu_to_le32(new_dir->i_ino); BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata"); - retval = ext4_handle_dirty_metadata(handle, old_inode, dir_bh); + retval = ext4_handle_dirty_dirent_node(handle, old_inode, + dir_bh); if (retval) { ext4_std_error(old_dir->i_sb, retval); goto end_rename; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 59fa0be2725..7ea6cbb4412 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -161,6 +161,8 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + goto out2; flex_gd->count = flexbg_size; flex_gd->groups = kmalloc(sizeof(struct ext4_new_group_data) * @@ -796,7 +798,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, ext4_kvfree(o_group_desc); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_super_now(handle, sb); if (err) ext4_std_error(sb, err); @@ -968,6 +970,8 @@ static void update_backups(struct super_block *sb, goto exit_err; } + ext4_superblock_csum_set(sb, (struct ext4_super_block *)data); + while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) { struct buffer_head *bh; @@ -1067,6 +1071,54 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, return err; } +static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block) +{ + struct buffer_head *bh = sb_getblk(sb, block); + if (!bh) + return NULL; + + if (bitmap_uptodate(bh)) + return bh; + + lock_buffer(bh); + if (bh_submit_read(bh) < 0) { + unlock_buffer(bh); + brelse(bh); + return NULL; + } + unlock_buffer(bh); + + return bh; +} + +static int ext4_set_bitmap_checksums(struct super_block *sb, + ext4_group_t group, + struct ext4_group_desc *gdp, + struct ext4_new_group_data *group_data) +{ + struct buffer_head *bh; + + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 0; + + bh = ext4_get_bitmap(sb, group_data->inode_bitmap); + if (!bh) + return -EIO; + ext4_inode_bitmap_csum_set(sb, group, gdp, bh, + EXT4_INODES_PER_GROUP(sb) / 8); + brelse(bh); + + bh = ext4_get_bitmap(sb, group_data->block_bitmap); + if (!bh) + return -EIO; + ext4_block_bitmap_csum_set(sb, group, gdp, bh, + EXT4_BLOCKS_PER_GROUP(sb) / 8); + brelse(bh); + + return 0; +} + /* * ext4_setup_new_descs() will set up the group descriptor descriptors of a flex bg */ @@ -1093,18 +1145,24 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, */ gdb_bh = sbi->s_group_desc[gdb_num]; /* Update group descriptor block for new group */ - gdp = (struct ext4_group_desc *)((char *)gdb_bh->b_data + + gdp = (struct ext4_group_desc *)(gdb_bh->b_data + gdb_off * EXT4_DESC_SIZE(sb)); memset(gdp, 0, EXT4_DESC_SIZE(sb)); ext4_block_bitmap_set(sb, gdp, group_data->block_bitmap); ext4_inode_bitmap_set(sb, gdp, group_data->inode_bitmap); + err = ext4_set_bitmap_checksums(sb, group, gdp, group_data); + if (err) { + ext4_std_error(sb, err); + break; + } + ext4_inode_table_set(sb, gdp, group_data->inode_table); ext4_free_group_clusters_set(sb, gdp, EXT4_B2C(sbi, group_data->free_blocks_count)); ext4_free_inodes_set(sb, gdp, EXT4_INODES_PER_GROUP(sb)); gdp->bg_flags = cpu_to_le16(*bg_flags); - gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp); + ext4_group_desc_csum_set(sb, group, gdp); err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { @@ -1343,17 +1401,14 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, (1 + ext4_bg_num_gdb(sb, group + i) + le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; group_data[i].free_blocks_count = blocks_per_group - overhead; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) + if (ext4_has_group_desc_csum(sb)) flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT | EXT4_BG_INODE_UNINIT; else flex_gd->bg_flags[i] = EXT4_BG_INODE_ZEROED; } - if (last_group == n_group && - EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) + if (last_group == n_group && ext4_has_group_desc_csum(sb)) /* We need to initialize block bitmap of last group. */ flex_gd->bg_flags[i - 1] &= ~EXT4_BG_BLOCK_UNINIT; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6da193564e4..eb7aa3e4ef0 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -112,6 +112,48 @@ static struct file_system_type ext3_fs_type = { #define IS_EXT3_SB(sb) (0) #endif +static int ext4_verify_csum_type(struct super_block *sb, + struct ext4_super_block *es) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + return es->s_checksum_type == EXT4_CRC32C_CHKSUM; +} + +static __le32 ext4_superblock_csum(struct super_block *sb, + struct ext4_super_block *es) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + int offset = offsetof(struct ext4_super_block, s_checksum); + __u32 csum; + + csum = ext4_chksum(sbi, ~0, (char *)es, offset); + + return cpu_to_le32(csum); +} + +int ext4_superblock_csum_verify(struct super_block *sb, + struct ext4_super_block *es) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return 1; + + return es->s_checksum == ext4_superblock_csum(sb, es); +} + +void ext4_superblock_csum_set(struct super_block *sb, + struct ext4_super_block *es) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + es->s_checksum = ext4_superblock_csum(sb, es); +} + void *ext4_kvmalloc(size_t size, gfp_t flags) { void *ret; @@ -497,6 +539,7 @@ void __ext4_error(struct super_block *sb, const char *function, printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: comm %s: %pV\n", sb->s_id, function, line, current->comm, &vaf); va_end(args); + save_error_info(sb, function, line); ext4_handle_error(sb); } @@ -905,6 +948,8 @@ static void ext4_put_super(struct super_block *sb) unlock_super(sb); kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); + if (sbi->s_chksum_driver) + crypto_free_shash(sbi->s_chksum_driver); kfree(sbi->s_blockgroup_lock); kfree(sbi); } @@ -1007,7 +1052,7 @@ static void destroy_inodecache(void) void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); dquot_drop(inode); ext4_discard_preallocations(inode); if (EXT4_I(inode)->jinode) { @@ -1448,6 +1493,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, { struct ext4_sb_info *sbi = EXT4_SB(sb); const struct mount_opts *m; + kuid_t uid; + kgid_t gid; int arg = 0; #ifdef CONFIG_QUOTA @@ -1474,10 +1521,20 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, "Ignoring removed %s option", opt); return 1; case Opt_resuid: - sbi->s_resuid = arg; + uid = make_kuid(current_user_ns(), arg); + if (!uid_valid(uid)) { + ext4_msg(sb, KERN_ERR, "Invalid uid value %d", arg); + return -1; + } + sbi->s_resuid = uid; return 1; case Opt_resgid: - sbi->s_resgid = arg; + gid = make_kgid(current_user_ns(), arg); + if (!gid_valid(gid)) { + ext4_msg(sb, KERN_ERR, "Invalid gid value %d", arg); + return -1; + } + sbi->s_resgid = gid; return 1; case Opt_abort: sbi->s_mount_flags |= EXT4_MF_FS_ABORTED; @@ -1597,7 +1654,9 @@ static int parse_options(char *options, struct super_block *sb, unsigned int *journal_ioprio, int is_remount) { +#ifdef CONFIG_QUOTA struct ext4_sb_info *sbi = EXT4_SB(sb); +#endif char *p; substring_t args[MAX_OPT_ARGS]; int token; @@ -1730,12 +1789,14 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("%s", token2str(m->token)); } - if (nodefs || sbi->s_resuid != EXT4_DEF_RESUID || + if (nodefs || !uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT4_DEF_RESUID)) || le16_to_cpu(es->s_def_resuid) != EXT4_DEF_RESUID) - SEQ_OPTS_PRINT("resuid=%u", sbi->s_resuid); - if (nodefs || sbi->s_resgid != EXT4_DEF_RESGID || + SEQ_OPTS_PRINT("resuid=%u", + from_kuid_munged(&init_user_ns, sbi->s_resuid)); + if (nodefs || !gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT4_DEF_RESGID)) || le16_to_cpu(es->s_def_resgid) != EXT4_DEF_RESGID) - SEQ_OPTS_PRINT("resgid=%u", sbi->s_resgid); + SEQ_OPTS_PRINT("resgid=%u", + from_kgid_munged(&init_user_ns, sbi->s_resgid)); def_errors = nodefs ? -1 : le16_to_cpu(es->s_errors); if (test_opt(sb, ERRORS_RO) && def_errors != EXT4_ERRORS_RO) SEQ_OPTS_PUTS("errors=remount-ro"); @@ -1906,43 +1967,69 @@ failed: return 0; } -__le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, - struct ext4_group_desc *gdp) +static __le16 ext4_group_desc_csum(struct ext4_sb_info *sbi, __u32 block_group, + struct ext4_group_desc *gdp) { + int offset; __u16 crc = 0; + __le32 le_group = cpu_to_le32(block_group); - if (sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) { - int offset = offsetof(struct ext4_group_desc, bg_checksum); - __le32 le_group = cpu_to_le32(block_group); - - crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); - crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); - crc = crc16(crc, (__u8 *)gdp, offset); - offset += sizeof(gdp->bg_checksum); /* skip checksum */ - /* for checksum of struct ext4_group_desc do the rest...*/ - if ((sbi->s_es->s_feature_incompat & - cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && - offset < le16_to_cpu(sbi->s_es->s_desc_size)) - crc = crc16(crc, (__u8 *)gdp + offset, - le16_to_cpu(sbi->s_es->s_desc_size) - - offset); + if ((sbi->s_es->s_feature_ro_compat & + cpu_to_le32(EXT4_FEATURE_RO_COMPAT_METADATA_CSUM))) { + /* Use new metadata_csum algorithm */ + __u16 old_csum; + __u32 csum32; + + old_csum = gdp->bg_checksum; + gdp->bg_checksum = 0; + csum32 = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&le_group, + sizeof(le_group)); + csum32 = ext4_chksum(sbi, csum32, (__u8 *)gdp, + sbi->s_desc_size); + gdp->bg_checksum = old_csum; + + crc = csum32 & 0xFFFF; + goto out; } + /* old crc16 code */ + offset = offsetof(struct ext4_group_desc, bg_checksum); + + crc = crc16(~0, sbi->s_es->s_uuid, sizeof(sbi->s_es->s_uuid)); + crc = crc16(crc, (__u8 *)&le_group, sizeof(le_group)); + crc = crc16(crc, (__u8 *)gdp, offset); + offset += sizeof(gdp->bg_checksum); /* skip checksum */ + /* for checksum of struct ext4_group_desc do the rest...*/ + if ((sbi->s_es->s_feature_incompat & + cpu_to_le32(EXT4_FEATURE_INCOMPAT_64BIT)) && + offset < le16_to_cpu(sbi->s_es->s_desc_size)) + crc = crc16(crc, (__u8 *)gdp + offset, + le16_to_cpu(sbi->s_es->s_desc_size) - + offset); + +out: return cpu_to_le16(crc); } -int ext4_group_desc_csum_verify(struct ext4_sb_info *sbi, __u32 block_group, +int ext4_group_desc_csum_verify(struct super_block *sb, __u32 block_group, struct ext4_group_desc *gdp) { - if ((sbi->s_es->s_feature_ro_compat & - cpu_to_le32(EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) && - (gdp->bg_checksum != ext4_group_desc_csum(sbi, block_group, gdp))) + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_checksum != ext4_group_desc_csum(EXT4_SB(sb), + block_group, gdp))) return 0; return 1; } +void ext4_group_desc_csum_set(struct super_block *sb, __u32 block_group, + struct ext4_group_desc *gdp) +{ + if (!ext4_has_group_desc_csum(sb)) + return; + gdp->bg_checksum = ext4_group_desc_csum(EXT4_SB(sb), block_group, gdp); +} + /* Called at mount-time, super-block is locked */ static int ext4_check_descriptors(struct super_block *sb, ext4_group_t *first_not_zeroed) @@ -1997,7 +2084,7 @@ static int ext4_check_descriptors(struct super_block *sb, return 0; } ext4_lock_group(sb, i); - if (!ext4_group_desc_csum_verify(sbi, i, gdp)) { + if (!ext4_group_desc_csum_verify(sb, i, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: " "Checksum for group %u failed (%u!=%u)", i, le16_to_cpu(ext4_group_desc_csum(sbi, i, @@ -2401,6 +2488,23 @@ static ssize_t sbi_ui_store(struct ext4_attr *a, return count; } +static ssize_t trigger_test_error(struct ext4_attr *a, + struct ext4_sb_info *sbi, + const char *buf, size_t count) +{ + int len = count; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (len && buf[len-1] == '\n') + len--; + + if (len) + ext4_error(sbi->s_sb, "%.*s", len, buf); + return count; +} + #define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ @@ -2431,6 +2535,7 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump); +EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error); static struct attribute *ext4_attrs[] = { ATTR_LIST(delayed_allocation_blocks), @@ -2445,6 +2550,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), ATTR_LIST(max_writeback_mb_bump), + ATTR_LIST(trigger_fs_error), NULL, }; @@ -2941,6 +3047,44 @@ static void ext4_destroy_lazyinit_thread(void) kthread_stop(ext4_lazyinit_task); } +static int set_journal_csum_feature_set(struct super_block *sb) +{ + int ret = 1; + int compat, incompat; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + /* journal checksum v2 */ + compat = 0; + incompat = JBD2_FEATURE_INCOMPAT_CSUM_V2; + } else { + /* journal checksum v1 */ + compat = JBD2_FEATURE_COMPAT_CHECKSUM; + incompat = 0; + } + + if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { + ret = jbd2_journal_set_features(sbi->s_journal, + compat, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | + incompat); + } else if (test_opt(sb, JOURNAL_CHECKSUM)) { + ret = jbd2_journal_set_features(sbi->s_journal, + compat, 0, + incompat); + jbd2_journal_clear_features(sbi->s_journal, 0, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + } else { + jbd2_journal_clear_features(sbi->s_journal, + JBD2_FEATURE_COMPAT_CHECKSUM, 0, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | + JBD2_FEATURE_INCOMPAT_CSUM_V2); + } + + return ret; +} + static int ext4_fill_super(struct super_block *sb, void *data, int silent) { char *orig_data = kstrdup(data, GFP_KERNEL); @@ -2977,9 +3121,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto out_free_orig; } sb->s_fs_info = sbi; + sbi->s_sb = sb; sbi->s_mount_opt = 0; - sbi->s_resuid = EXT4_DEF_RESUID; - sbi->s_resgid = EXT4_DEF_RESGID; + sbi->s_resuid = make_kuid(&init_user_ns, EXT4_DEF_RESUID); + sbi->s_resgid = make_kgid(&init_user_ns, EXT4_DEF_RESGID); sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; sbi->s_sb_block = sb_block; if (sb->s_bdev->bd_part) @@ -3016,13 +3161,54 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * Note: s_es must be initialized as soon as possible because * some ext4 macro-instructions depend on its value */ - es = (struct ext4_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext4_super_block *) (bh->b_data + offset); sbi->s_es = es; sb->s_magic = le16_to_cpu(es->s_magic); if (sb->s_magic != EXT4_SUPER_MAGIC) goto cantfind_ext4; sbi->s_kbytes_written = le64_to_cpu(es->s_kbytes_written); + /* Warn if metadata_csum and gdt_csum are both set. */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) + ext4_warning(sb, KERN_INFO "metadata_csum and uninit_bg are " + "redundant flags; please run fsck."); + + /* Check for a known checksum algorithm */ + if (!ext4_verify_csum_type(sb, es)) { + ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " + "unknown checksum algorithm."); + silent = 1; + goto cantfind_ext4; + } + + /* Load the checksum driver */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) { + sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(sbi->s_chksum_driver)) { + ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver."); + ret = PTR_ERR(sbi->s_chksum_driver); + sbi->s_chksum_driver = NULL; + goto failed_mount; + } + } + + /* Check superblock checksum */ + if (!ext4_superblock_csum_verify(sb, es)) { + ext4_msg(sb, KERN_ERR, "VFS: Found ext4 filesystem with " + "invalid superblock checksum. Run e2fsck?"); + silent = 1; + goto cantfind_ext4; + } + + /* Precompute checksum seed for all metadata */ + if (EXT4_HAS_RO_COMPAT_FEATURE(sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid, + sizeof(es->s_uuid)); + /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); set_opt(sb, INIT_INODE_TABLE); @@ -3058,8 +3244,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (def_mount_opts & EXT4_DEFM_DISCARD) set_opt(sb, DISCARD); - sbi->s_resuid = le16_to_cpu(es->s_def_resuid); - sbi->s_resgid = le16_to_cpu(es->s_def_resgid); + sbi->s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid)); + sbi->s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid)); sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; @@ -3184,7 +3370,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "Can't read superblock on 2nd try"); goto failed_mount; } - es = (struct ext4_super_block *)(((char *)bh->b_data) + offset); + es = (struct ext4_super_block *)(bh->b_data + offset); sbi->s_es = es; if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) { ext4_msg(sb, KERN_ERR, @@ -3376,6 +3562,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) GFP_KERNEL); if (sbi->s_group_desc == NULL) { ext4_msg(sb, KERN_ERR, "not enough memory"); + ret = -ENOMEM; goto failed_mount; } @@ -3433,6 +3620,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (err) { ext4_msg(sb, KERN_ERR, "insufficient memory"); + ret = err; goto failed_mount3; } @@ -3490,26 +3678,17 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto no_journal; } - if (ext4_blocks_count(es) > 0xffffffffULL && + if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT) && !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_64BIT)) { ext4_msg(sb, KERN_ERR, "Failed to set 64-bit journal feature"); goto failed_mount_wq; } - if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else if (test_opt(sb, JOURNAL_CHECKSUM)) { - jbd2_journal_set_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0); - jbd2_journal_clear_features(sbi->s_journal, 0, 0, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); - } else { - jbd2_journal_clear_features(sbi->s_journal, - JBD2_FEATURE_COMPAT_CHECKSUM, 0, - JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT); + if (!set_journal_csum_feature_set(sb)) { + ext4_msg(sb, KERN_ERR, "Failed to set journal checksum " + "feature set"); + goto failed_mount_wq; } /* We have now updated the journal if required, so we can @@ -3590,7 +3769,8 @@ no_journal: goto failed_mount4; } - ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY); + if (ext4_setup_super(sb, es, sb->s_flags & MS_RDONLY)) + sb->s_flags |= MS_RDONLY; /* determine the minimum size of new large inodes, if present */ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) { @@ -3625,7 +3805,7 @@ no_journal: } ext4_ext_init(sb); - err = ext4_mb_init(sb, needs_recovery); + err = ext4_mb_init(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", err); @@ -3708,6 +3888,8 @@ failed_mount2: brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); failed_mount: + if (sbi->s_chksum_driver) + crypto_free_shash(sbi->s_chksum_driver); if (sbi->s_proc) { remove_proc_entry("options", sbi->s_proc); remove_proc_entry(sb->s_id, ext4_proc_root); @@ -3831,7 +4013,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, goto out_bdev; } - es = (struct ext4_super_block *) (((char *)bh->b_data) + offset); + es = (struct ext4_super_block *) (bh->b_data + offset); if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) || !(le32_to_cpu(es->s_feature_incompat) & EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) { @@ -4023,6 +4205,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) &EXT4_SB(sb)->s_freeinodes_counter)); sb->s_dirt = 0; BUFFER_TRACE(sbh, "marking dirty"); + ext4_superblock_csum_set(sb, es); mark_buffer_dirty(sbh); if (sync) { error = sync_dirty_buffer(sbh); @@ -4211,8 +4394,8 @@ static int ext4_unfreeze(struct super_block *sb) struct ext4_mount_options { unsigned long s_mount_opt; unsigned long s_mount_opt2; - uid_t s_resuid; - gid_t s_resgid; + kuid_t s_resuid; + kgid_t s_resgid; unsigned long s_commit_interval; u32 s_min_batch_time, s_max_batch_time; #ifdef CONFIG_QUOTA @@ -4317,7 +4500,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) struct ext4_group_desc *gdp = ext4_get_group_desc(sb, g, NULL); - if (!ext4_group_desc_csum_verify(sbi, g, gdp)) { + if (!ext4_group_desc_csum_verify(sb, g, gdp)) { ext4_msg(sb, KERN_ERR, "ext4_remount: Checksum for group %u failed (%u!=%u)", g, le16_to_cpu(ext4_group_desc_csum(sbi, g, gdp)), @@ -4742,7 +4925,6 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, return -EIO; } - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); bh = ext4_bread(handle, inode, blk, 1, &err); if (!bh) goto out; @@ -4758,16 +4940,13 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, err = ext4_handle_dirty_metadata(handle, NULL, bh); brelse(bh); out: - if (err) { - mutex_unlock(&inode->i_mutex); + if (err) return err; - } if (inode->i_size < off + len) { i_size_write(inode, off + len); EXT4_I(inode)->i_disksize = inode->i_size; ext4_mark_inode_dirty(handle, inode); } - mutex_unlock(&inode->i_mutex); return len; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index e88748e55c0..e56c9ed7d6e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -122,6 +122,58 @@ const struct xattr_handler *ext4_xattr_handlers[] = { NULL }; +static __le32 ext4_xattr_block_csum(struct inode *inode, + sector_t block_nr, + struct ext4_xattr_header *hdr) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + struct ext4_inode_info *ei = EXT4_I(inode); + __u32 csum, old; + + old = hdr->h_checksum; + hdr->h_checksum = 0; + if (le32_to_cpu(hdr->h_refcount) != 1) { + block_nr = cpu_to_le64(block_nr); + csum = ext4_chksum(sbi, sbi->s_csum_seed, (__u8 *)&block_nr, + sizeof(block_nr)); + } else + csum = ei->i_csum_seed; + csum = ext4_chksum(sbi, csum, (__u8 *)hdr, + EXT4_BLOCK_SIZE(inode->i_sb)); + hdr->h_checksum = old; + return cpu_to_le32(csum); +} + +static int ext4_xattr_block_csum_verify(struct inode *inode, + sector_t block_nr, + struct ext4_xattr_header *hdr) +{ + if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM) && + (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr))) + return 0; + return 1; +} + +static void ext4_xattr_block_csum_set(struct inode *inode, + sector_t block_nr, + struct ext4_xattr_header *hdr) +{ + if (!EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb, + EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) + return; + + hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr); +} + +static inline int ext4_handle_dirty_xattr_block(handle_t *handle, + struct inode *inode, + struct buffer_head *bh) +{ + ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh)); + return ext4_handle_dirty_metadata(handle, inode, bh); +} + static inline const struct xattr_handler * ext4_xattr_handler(int name_index) { @@ -156,12 +208,22 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end) } static inline int -ext4_xattr_check_block(struct buffer_head *bh) +ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) { + int error; + + if (buffer_verified(bh)) + return 0; + if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) return -EIO; - return ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) + return -EIO; + error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size); + if (!error) + set_buffer_verified(bh); + return error; } static inline int @@ -224,7 +286,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, goto cleanup; ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); - if (ext4_xattr_check_block(bh)) { + if (ext4_xattr_check_block(inode, bh)) { bad_block: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); @@ -369,7 +431,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) goto cleanup; ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); - if (ext4_xattr_check_block(bh)) { + if (ext4_xattr_check_block(inode, bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); error = -EIO; @@ -492,7 +554,7 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode, if (ce) mb_cache_entry_release(ce); unlock_buffer(bh); - error = ext4_handle_dirty_metadata(handle, inode, bh); + error = ext4_handle_dirty_xattr_block(handle, inode, bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, 1); @@ -662,7 +724,7 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); - if (ext4_xattr_check_block(bs->bh)) { + if (ext4_xattr_check_block(inode, bs->bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); error = -EIO; @@ -725,9 +787,9 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, if (error == -EIO) goto bad_block; if (!error) - error = ext4_handle_dirty_metadata(handle, - inode, - bs->bh); + error = ext4_handle_dirty_xattr_block(handle, + inode, + bs->bh); if (error) goto cleanup; goto inserted; @@ -796,9 +858,9 @@ inserted: ea_bdebug(new_bh, "reusing; refcount now=%d", le32_to_cpu(BHDR(new_bh)->h_refcount)); unlock_buffer(new_bh); - error = ext4_handle_dirty_metadata(handle, - inode, - new_bh); + error = ext4_handle_dirty_xattr_block(handle, + inode, + new_bh); if (error) goto cleanup_dquot; } @@ -855,8 +917,8 @@ getblk_failed: set_buffer_uptodate(new_bh); unlock_buffer(new_bh); ext4_xattr_cache_insert(new_bh); - error = ext4_handle_dirty_metadata(handle, - inode, new_bh); + error = ext4_handle_dirty_xattr_block(handle, + inode, new_bh); if (error) goto cleanup; } @@ -1193,7 +1255,7 @@ retry: error = -EIO; if (!bh) goto cleanup; - if (ext4_xattr_check_block(bh)) { + if (ext4_xattr_check_block(inode, bh)) { EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); error = -EIO; diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h index 25b7387ff18..91f31ca7d9a 100644 --- a/fs/ext4/xattr.h +++ b/fs/ext4/xattr.h @@ -27,7 +27,9 @@ struct ext4_xattr_header { __le32 h_refcount; /* reference count */ __le32 h_blocks; /* number of disk blocks used */ __le32 h_hash; /* hash value of all attributes */ - __u32 h_reserved[4]; /* zero right now */ + __le32 h_checksum; /* crc32c(uuid+id+xattrblock) */ + /* id = inum if refcount=1, blknum otherwise */ + __u32 h_reserved[3]; /* zero right now */ }; struct ext4_xattr_ibody_header { diff --git a/fs/fat/dir.c b/fs/fat/dir.c index aca191bd5f8..6eaa28c98ad 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -98,8 +98,8 @@ next: *bh = sb_bread(sb, phys); if (*bh == NULL) { - fat_msg(sb, KERN_ERR, "Directory bread(block %llu) failed", - (llu)phys); + fat_msg_ratelimit(sb, KERN_ERR, + "Directory bread(block %llu) failed", (llu)phys); /* skip this block */ *pos = (iblock + 1) << sb->s_blocksize_bits; goto next; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 66994f316e1..fc35c5c6913 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -82,6 +82,7 @@ struct msdos_sb_info { int fatent_shift; struct fatent_operations *fatent_ops; struct inode *fat_inode; + struct inode *fsinfo_inode; struct ratelimit_state ratelimit; @@ -334,6 +335,11 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); __fat_fs_error(sb, __ratelimit(&MSDOS_SB(sb)->ratelimit), fmt , ## args) __printf(3, 4) __cold void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...); +#define fat_msg_ratelimit(sb, level, fmt, args...) \ + do { \ + if (__ratelimit(&MSDOS_SB(sb)->ratelimit)) \ + fat_msg(sb, level, fmt, ## args); \ + } while (0) extern int fat_clusters_flush(struct super_block *sb); extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 2e81ac0df7e..31f08ab62c5 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -308,6 +308,16 @@ void fat_ent_access_init(struct super_block *sb) } } +static void mark_fsinfo_dirty(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + if (sb->s_flags & MS_RDONLY || sbi->fat_bits != 32) + return; + + __mark_inode_dirty(sbi->fsinfo_inode, I_DIRTY_SYNC); +} + static inline int fat_ent_update_ptr(struct super_block *sb, struct fat_entry *fatent, int offset, sector_t blocknr) @@ -498,7 +508,6 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) sbi->prev_free = entry; if (sbi->free_clusters != -1) sbi->free_clusters--; - sb->s_dirt = 1; cluster[idx_clus] = entry; idx_clus++; @@ -520,11 +529,11 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) /* Couldn't allocate the free entries */ sbi->free_clusters = 0; sbi->free_clus_valid = 1; - sb->s_dirt = 1; err = -ENOSPC; out: unlock_fat(sbi); + mark_fsinfo_dirty(sb); fatent_brelse(&fatent); if (!err) { if (inode_needs_sync(inode)) @@ -549,7 +558,7 @@ int fat_free_clusters(struct inode *inode, int cluster) struct fat_entry fatent; struct buffer_head *bhs[MAX_BUF_PER_PAGE]; int i, err, nr_bhs; - int first_cl = cluster; + int first_cl = cluster, dirty_fsinfo = 0; nr_bhs = 0; fatent_init(&fatent); @@ -587,7 +596,7 @@ int fat_free_clusters(struct inode *inode, int cluster) ops->ent_put(&fatent, FAT_ENT_FREE); if (sbi->free_clusters != -1) { sbi->free_clusters++; - sb->s_dirt = 1; + dirty_fsinfo = 1; } if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) { @@ -617,6 +626,8 @@ error: for (i = 0; i < nr_bhs; i++) brelse(bhs[i]); unlock_fat(sbi); + if (dirty_fsinfo) + mark_fsinfo_dirty(sb); return err; } @@ -677,7 +688,7 @@ int fat_count_free_clusters(struct super_block *sb) } sbi->free_clusters = free; sbi->free_clus_valid = 1; - sb->s_dirt = 1; + mark_fsinfo_dirty(sb); fatent_brelse(&fatent); out: unlock_fat(sbi); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 21687e31acc..0038b32cb36 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -454,42 +454,16 @@ static void fat_evict_inode(struct inode *inode) fat_truncate_blocks(inode, 0); } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); fat_cache_inval_inode(inode); fat_detach(inode); } -static void fat_write_super(struct super_block *sb) -{ - lock_super(sb); - sb->s_dirt = 0; - - if (!(sb->s_flags & MS_RDONLY)) - fat_clusters_flush(sb); - unlock_super(sb); -} - -static int fat_sync_fs(struct super_block *sb, int wait) -{ - int err = 0; - - if (sb->s_dirt) { - lock_super(sb); - sb->s_dirt = 0; - err = fat_clusters_flush(sb); - unlock_super(sb); - } - - return err; -} - static void fat_put_super(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); - if (sb->s_dirt) - fat_write_super(sb); - + iput(sbi->fsinfo_inode); iput(sbi->fat_inode); unload_nls(sbi->nls_disk); @@ -661,7 +635,18 @@ retry: static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) { - return __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); + int err; + + if (inode->i_ino == MSDOS_FSINFO_INO) { + struct super_block *sb = inode->i_sb; + + lock_super(sb); + err = fat_clusters_flush(sb); + unlock_super(sb); + } else + err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); + + return err; } int fat_sync_inode(struct inode *inode) @@ -678,8 +663,6 @@ static const struct super_operations fat_sops = { .write_inode = fat_write_inode, .evict_inode = fat_evict_inode, .put_super = fat_put_super, - .write_super = fat_write_super, - .sync_fs = fat_sync_fs, .statfs = fat_statfs, .remount_fs = fat_remount, @@ -752,28 +735,26 @@ static struct dentry *fat_fh_to_dentry(struct super_block *sb, } static int -fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable) +fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { int len = *lenp; - struct inode *inode = de->d_inode; - u32 ipos_h, ipos_m, ipos_l; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + loff_t i_pos; if (len < 5) { *lenp = 5; return 255; /* no room */ } - ipos_h = MSDOS_I(inode)->i_pos >> 8; - ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24; - ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28; + i_pos = fat_i_pos_read(sbi, inode); *lenp = 5; fh[0] = inode->i_ino; fh[1] = inode->i_generation; - fh[2] = ipos_h; - fh[3] = ipos_m | MSDOS_I(inode)->i_logstart; - spin_lock(&de->d_lock); - fh[4] = ipos_l | MSDOS_I(de->d_parent->d_inode)->i_logstart; - spin_unlock(&de->d_lock); + fh[2] = i_pos >> 8; + fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart; + fh[4] = (i_pos & 0x0f) << 28; + if (parent) + fh[4] |= MSDOS_I(parent)->i_logstart; return 3; } @@ -1244,6 +1225,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, void (*setup)(struct super_block *)) { struct inode *root_inode = NULL, *fat_inode = NULL; + struct inode *fsinfo_inode = NULL; struct buffer_head *bh; struct fat_boot_sector *b; struct msdos_sb_info *sbi; @@ -1490,6 +1472,14 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; MSDOS_I(fat_inode)->i_pos = 0; sbi->fat_inode = fat_inode; + + fsinfo_inode = new_inode(sb); + if (!fsinfo_inode) + goto out_fail; + fsinfo_inode->i_ino = MSDOS_FSINFO_INO; + sbi->fsinfo_inode = fsinfo_inode; + insert_inode_hash(fsinfo_inode); + root_inode = new_inode(sb); if (!root_inode) goto out_fail; @@ -1516,6 +1506,8 @@ out_invalid: fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: + if (fsinfo_inode) + iput(fsinfo_inode); if (fat_inode) iput(fat_inode); unload_nls(sbi->nls_io); diff --git a/fs/fcntl.c b/fs/fcntl.c index 75e7c1f3a08..81b70e665bf 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -442,28 +442,24 @@ static int check_fcntl_cmd(unsigned cmd) SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct file *filp; + int fput_needed; long err = -EBADF; - filp = fget_raw(fd); + filp = fget_raw_light(fd, &fput_needed); if (!filp) goto out; if (unlikely(filp->f_mode & FMODE_PATH)) { - if (!check_fcntl_cmd(cmd)) { - fput(filp); - goto out; - } + if (!check_fcntl_cmd(cmd)) + goto out1; } err = security_file_fcntl(filp, cmd, arg); - if (err) { - fput(filp); - return err; - } + if (!err) + err = do_fcntl(fd, cmd, arg, filp); - err = do_fcntl(fd, cmd, arg, filp); - - fput(filp); +out1: + fput_light(filp, fput_needed); out: return err; } @@ -473,26 +469,21 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct file * filp; - long err; + long err = -EBADF; + int fput_needed; - err = -EBADF; - filp = fget_raw(fd); + filp = fget_raw_light(fd, &fput_needed); if (!filp) goto out; if (unlikely(filp->f_mode & FMODE_PATH)) { - if (!check_fcntl_cmd(cmd)) { - fput(filp); - goto out; - } + if (!check_fcntl_cmd(cmd)) + goto out1; } err = security_file_fcntl(filp, cmd, arg); - if (err) { - fput(filp); - return err; - } - err = -EBADF; + if (err) + goto out1; switch (cmd) { case F_GETLK64: @@ -507,7 +498,8 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, err = do_fcntl(fd, cmd, arg, filp); break; } - fput(filp); +out1: + fput_light(filp, fput_needed); out: return err; } @@ -532,9 +524,9 @@ static inline int sigio_perm(struct task_struct *p, rcu_read_lock(); cred = __task_cred(p); - ret = ((fown->euid == 0 || - fown->euid == cred->suid || fown->euid == cred->uid || - fown->uid == cred->suid || fown->uid == cred->uid) && + ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || + uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || + uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; diff --git a/fs/file_table.c b/fs/file_table.c index 70f2a0fd6ae..a305d9e2d1b 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -34,7 +34,6 @@ struct files_stat_struct files_stat = { .max_files = NR_FILE }; -DECLARE_LGLOCK(files_lglock); DEFINE_LGLOCK(files_lglock); /* SLAB cache for file structures */ @@ -421,9 +420,9 @@ static inline void __file_sb_list_add(struct file *file, struct super_block *sb) */ void file_sb_list_add(struct file *file, struct super_block *sb) { - lg_local_lock(files_lglock); + lg_local_lock(&files_lglock); __file_sb_list_add(file, sb); - lg_local_unlock(files_lglock); + lg_local_unlock(&files_lglock); } /** @@ -436,9 +435,9 @@ void file_sb_list_add(struct file *file, struct super_block *sb) void file_sb_list_del(struct file *file) { if (!list_empty(&file->f_u.fu_list)) { - lg_local_lock_cpu(files_lglock, file_list_cpu(file)); + lg_local_lock_cpu(&files_lglock, file_list_cpu(file)); list_del_init(&file->f_u.fu_list); - lg_local_unlock_cpu(files_lglock, file_list_cpu(file)); + lg_local_unlock_cpu(&files_lglock, file_list_cpu(file)); } } @@ -485,7 +484,7 @@ void mark_files_ro(struct super_block *sb) struct file *f; retry: - lg_global_lock(files_lglock); + lg_global_lock(&files_lglock); do_file_list_for_each_entry(sb, f) { struct vfsmount *mnt; if (!S_ISREG(f->f_path.dentry->d_inode->i_mode)) @@ -502,12 +501,12 @@ retry: file_release_write(f); mnt = mntget(f->f_path.mnt); /* This can sleep, so we can't hold the spinlock. */ - lg_global_unlock(files_lglock); + lg_global_unlock(&files_lglock); mnt_drop_write(mnt); mntput(mnt); goto retry; } while_file_list_for_each_entry; - lg_global_unlock(files_lglock); + lg_global_unlock(&files_lglock); } void __init files_init(unsigned long mempages) @@ -525,6 +524,6 @@ void __init files_init(unsigned long mempages) n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); files_defer_init(); - lg_lock_init(files_lglock); + lg_lock_init(&files_lglock, "files_lglock"); percpu_counter_init(&nr_files, 0); } diff --git a/fs/freevxfs/vxfs_inode.c b/fs/freevxfs/vxfs_inode.c index cf9ef918a2a..ef67c95f12d 100644 --- a/fs/freevxfs/vxfs_inode.c +++ b/fs/freevxfs/vxfs_inode.c @@ -355,6 +355,6 @@ void vxfs_evict_inode(struct inode *ip) { truncate_inode_pages(&ip->i_data, 0); - end_writeback(ip); + clear_inode(ip); call_rcu(&ip->i_rcu, vxfs_i_callback); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 539f36cf3e4..41a3ccff18d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -231,11 +231,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) static void inode_sync_complete(struct inode *inode) { - /* - * Prevent speculative execution through - * spin_unlock(&wb->list_lock); - */ - + inode->i_state &= ~I_SYNC; + /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } @@ -329,10 +326,12 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc) } /* - * Wait for writeback on an inode to complete. + * Wait for writeback on an inode to complete. Called with i_lock held. + * Caller must make sure inode cannot go away when we drop i_lock. */ -static void inode_wait_for_writeback(struct inode *inode, - struct bdi_writeback *wb) +static void __inode_wait_for_writeback(struct inode *inode) + __releases(inode->i_lock) + __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; @@ -340,70 +339,119 @@ static void inode_wait_for_writeback(struct inode *inode, wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); - spin_unlock(&wb->list_lock); __wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE); - spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); } } /* - * Write out an inode's dirty pages. Called under wb->list_lock and - * inode->i_lock. Either the caller has an active reference on the inode or - * the inode has I_WILL_FREE set. - * - * If `wait' is set, wait on the writeout. - * - * The whole writeout design is quite complex and fragile. We want to avoid - * starvation of particular inodes when others are being redirtied, prevent - * livelocks, etc. + * Wait for writeback on an inode to complete. Caller must have inode pinned. */ -static int -writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, - struct writeback_control *wbc) +void inode_wait_for_writeback(struct inode *inode) { - struct address_space *mapping = inode->i_mapping; - long nr_to_write = wbc->nr_to_write; - unsigned dirty; - int ret; + spin_lock(&inode->i_lock); + __inode_wait_for_writeback(inode); + spin_unlock(&inode->i_lock); +} - assert_spin_locked(&wb->list_lock); - assert_spin_locked(&inode->i_lock); +/* + * Sleep until I_SYNC is cleared. This function must be called with i_lock + * held and drops it. It is aimed for callers not holding any inode reference + * so once i_lock is dropped, inode can go away. + */ +static void inode_sleep_on_writeback(struct inode *inode) + __releases(inode->i_lock) +{ + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); + int sleep; - if (!atomic_read(&inode->i_count)) - WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); - else - WARN_ON(inode->i_state & I_WILL_FREE); + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + sleep = inode->i_state & I_SYNC; + spin_unlock(&inode->i_lock); + if (sleep) + schedule(); + finish_wait(wqh, &wait); +} - if (inode->i_state & I_SYNC) { +/* + * Find proper writeback list for the inode depending on its current state and + * possibly also change of its state while we were doing writeback. Here we + * handle things such as livelock prevention or fairness of writeback among + * inodes. This function can be called only by flusher thread - noone else + * processes all inodes in writeback lists and requeueing inodes behind flusher + * thread's back can have unexpected consequences. + */ +static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, + struct writeback_control *wbc) +{ + if (inode->i_state & I_FREEING) + return; + + /* + * Sync livelock prevention. Each inode is tagged and synced in one + * shot. If still dirty, it will be redirty_tail()'ed below. Update + * the dirty time to prevent enqueue and sync it again. + */ + if ((inode->i_state & I_DIRTY) && + (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) + inode->dirtied_when = jiffies; + + if (wbc->pages_skipped) { /* - * If this inode is locked for writeback and we are not doing - * writeback-for-data-integrity, move it to b_more_io so that - * writeback can proceed with the other inodes on s_io. - * - * We'll have another go at writing back this inode when we - * completed a full scan of b_io. + * writeback is not making progress due to locked + * buffers. Skip this inode for now. */ - if (wbc->sync_mode != WB_SYNC_ALL) { + redirty_tail(inode, wb); + return; + } + + if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { + /* + * We didn't write back all the pages. nfs_writepages() + * sometimes bales out without doing anything. + */ + if (wbc->nr_to_write <= 0) { + /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); - trace_writeback_single_inode_requeue(inode, wbc, - nr_to_write); - return 0; + } else { + /* + * Writeback blocked by something other than + * congestion. Delay the inode for some time to + * avoid spinning on the CPU (100% iowait) + * retrying writeback of the dirty page/inode + * that cannot be performed immediately. + */ + redirty_tail(inode, wb); } - + } else if (inode->i_state & I_DIRTY) { /* - * It's a data-integrity sync. We must wait. + * Filesystems can dirty the inode during writeback operations, + * such as delayed allocation during submission or metadata + * updates after data IO completion. */ - inode_wait_for_writeback(inode, wb); + redirty_tail(inode, wb); + } else { + /* The inode is clean. Remove from writeback lists. */ + list_del_init(&inode->i_wb_list); } +} - BUG_ON(inode->i_state & I_SYNC); +/* + * Write out an inode and its dirty pages. Do not update the writeback list + * linkage. That is left to the caller. The caller is also responsible for + * setting I_SYNC flag and calling inode_sync_complete() to clear it. + */ +static int +__writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, + struct writeback_control *wbc) +{ + struct address_space *mapping = inode->i_mapping; + long nr_to_write = wbc->nr_to_write; + unsigned dirty; + int ret; - /* Set I_SYNC, reset I_DIRTY_PAGES */ - inode->i_state |= I_SYNC; - inode->i_state &= ~I_DIRTY_PAGES; - spin_unlock(&inode->i_lock); - spin_unlock(&wb->list_lock); + WARN_ON(!(inode->i_state & I_SYNC)); ret = do_writepages(mapping, wbc); @@ -424,6 +472,9 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, * write_inode() */ spin_lock(&inode->i_lock); + /* Clear I_DIRTY_PAGES if we've written out all dirty pages */ + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + inode->i_state &= ~I_DIRTY_PAGES; dirty = inode->i_state & I_DIRTY; inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC); spin_unlock(&inode->i_lock); @@ -433,60 +484,67 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, if (ret == 0) ret = err; } + trace_writeback_single_inode(inode, wbc, nr_to_write); + return ret; +} + +/* + * Write out an inode's dirty pages. Either the caller has an active reference + * on the inode or the inode has I_WILL_FREE set. + * + * This function is designed to be called for writing back one inode which + * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() + * and does more profound writeback list handling in writeback_sb_inodes(). + */ +static int +writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, + struct writeback_control *wbc) +{ + int ret = 0; - spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); - inode->i_state &= ~I_SYNC; - if (!(inode->i_state & I_FREEING)) { + if (!atomic_read(&inode->i_count)) + WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); + else + WARN_ON(inode->i_state & I_WILL_FREE); + + if (inode->i_state & I_SYNC) { + if (wbc->sync_mode != WB_SYNC_ALL) + goto out; /* - * Sync livelock prevention. Each inode is tagged and synced in - * one shot. If still dirty, it will be redirty_tail()'ed below. - * Update the dirty time to prevent enqueue and sync it again. + * It's a data-integrity sync. We must wait. Since callers hold + * inode reference or inode has I_WILL_FREE set, it cannot go + * away under us. */ - if ((inode->i_state & I_DIRTY) && - (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) - inode->dirtied_when = jiffies; - - if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - /* - * We didn't write back all the pages. nfs_writepages() - * sometimes bales out without doing anything. - */ - inode->i_state |= I_DIRTY_PAGES; - if (wbc->nr_to_write <= 0) { - /* - * slice used up: queue for next turn - */ - requeue_io(inode, wb); - } else { - /* - * Writeback blocked by something other than - * congestion. Delay the inode for some time to - * avoid spinning on the CPU (100% iowait) - * retrying writeback of the dirty page/inode - * that cannot be performed immediately. - */ - redirty_tail(inode, wb); - } - } else if (inode->i_state & I_DIRTY) { - /* - * Filesystems can dirty the inode during writeback - * operations, such as delayed allocation during - * submission or metadata updates after data IO - * completion. - */ - redirty_tail(inode, wb); - } else { - /* - * The inode is clean. At this point we either have - * a reference to the inode or it's on it's way out. - * No need to add it back to the LRU. - */ - list_del_init(&inode->i_wb_list); - } + __inode_wait_for_writeback(inode); } + WARN_ON(inode->i_state & I_SYNC); + /* + * Skip inode if it is clean. We don't want to mess with writeback + * lists in this function since flusher thread may be doing for example + * sync in parallel and if we move the inode, it could get skipped. So + * here we make sure inode is on some writeback list and leave it there + * unless we have completely cleaned the inode. + */ + if (!(inode->i_state & I_DIRTY)) + goto out; + inode->i_state |= I_SYNC; + spin_unlock(&inode->i_lock); + + ret = __writeback_single_inode(inode, wb, wbc); + + spin_lock(&wb->list_lock); + spin_lock(&inode->i_lock); + /* + * If inode is clean, remove it from writeback lists. Otherwise don't + * touch it. See comment above for explanation. + */ + if (!(inode->i_state & I_DIRTY)) + list_del_init(&inode->i_wb_list); + spin_unlock(&wb->list_lock); inode_sync_complete(inode); - trace_writeback_single_inode(inode, wbc, nr_to_write); +out: + spin_unlock(&inode->i_lock); return ret; } @@ -580,29 +638,58 @@ static long writeback_sb_inodes(struct super_block *sb, redirty_tail(inode, wb); continue; } - __iget(inode); + if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { + /* + * If this inode is locked for writeback and we are not + * doing writeback-for-data-integrity, move it to + * b_more_io so that writeback can proceed with the + * other inodes on s_io. + * + * We'll have another go at writing back this inode + * when we completed a full scan of b_io. + */ + spin_unlock(&inode->i_lock); + requeue_io(inode, wb); + trace_writeback_sb_inodes_requeue(inode); + continue; + } + spin_unlock(&wb->list_lock); + + /* + * We already requeued the inode if it had I_SYNC set and we + * are doing WB_SYNC_NONE writeback. So this catches only the + * WB_SYNC_ALL case. + */ + if (inode->i_state & I_SYNC) { + /* Wait for I_SYNC. This function drops i_lock... */ + inode_sleep_on_writeback(inode); + /* Inode may be gone, start again */ + spin_lock(&wb->list_lock); + continue; + } + inode->i_state |= I_SYNC; + spin_unlock(&inode->i_lock); + write_chunk = writeback_chunk_size(wb->bdi, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; - writeback_single_inode(inode, wb, &wbc); + /* + * We use I_SYNC to pin the inode in memory. While it is set + * evict_inode() will wait so the inode cannot be freed. + */ + __writeback_single_inode(inode, wb, &wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; + spin_lock(&wb->list_lock); + spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY)) wrote++; - if (wbc.pages_skipped) { - /* - * writeback is not making progress due to locked - * buffers. Skip this inode for now. - */ - redirty_tail(inode, wb); - } + requeue_inode(inode, wb, &wbc); + inode_sync_complete(inode); spin_unlock(&inode->i_lock); - spin_unlock(&wb->list_lock); - iput(inode); - cond_resched(); - spin_lock(&wb->list_lock); + cond_resched_lock(&wb->list_lock); /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. @@ -796,8 +883,10 @@ static long wb_writeback(struct bdi_writeback *wb, trace_writeback_wait(wb->bdi, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); - inode_wait_for_writeback(inode, wb); - spin_unlock(&inode->i_lock); + spin_unlock(&wb->list_lock); + /* This function drops i_lock... */ + inode_sleep_on_writeback(inode); + spin_lock(&wb->list_lock); } } spin_unlock(&wb->list_lock); @@ -1331,7 +1420,6 @@ EXPORT_SYMBOL(sync_inodes_sb); int write_inode_now(struct inode *inode, int sync) { struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - int ret; struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, @@ -1343,12 +1431,7 @@ int write_inode_now(struct inode *inode, int sync) wbc.nr_to_write = 0; might_sleep(); - spin_lock(&wb->list_lock); - spin_lock(&inode->i_lock); - ret = writeback_single_inode(inode, wb, &wbc); - spin_unlock(&inode->i_lock); - spin_unlock(&wb->list_lock); - return ret; + return writeback_single_inode(inode, wb, &wbc); } EXPORT_SYMBOL(write_inode_now); @@ -1365,15 +1448,7 @@ EXPORT_SYMBOL(write_inode_now); */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { - struct bdi_writeback *wb = &inode_to_bdi(inode)->wb; - int ret; - - spin_lock(&wb->list_lock); - spin_lock(&inode->i_lock); - ret = writeback_single_inode(inode, wb, wbc); - spin_unlock(&inode->i_lock); - spin_unlock(&wb->list_lock); - return ret; + return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc); } EXPORT_SYMBOL(sync_inode); diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 42593c587d4..03ff5b1eba9 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -75,19 +75,13 @@ static ssize_t fuse_conn_limit_write(struct file *file, const char __user *buf, unsigned global_limit) { unsigned long t; - char tmp[32]; unsigned limit = (1 << 16) - 1; int err; - if (*ppos || count >= sizeof(tmp) - 1) - return -EINVAL; - - if (copy_from_user(tmp, buf, count)) + if (*ppos) return -EINVAL; - tmp[count] = '\0'; - - err = strict_strtoul(tmp, 0, &t); + err = kstrtoul_from_user(buf, count, 0, &t); if (err) return err; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index df5ac048dc7..334e0b18a01 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -775,6 +775,8 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, struct kstat *stat) { + unsigned int blkbits; + stat->dev = inode->i_sb->s_dev; stat->ino = attr->ino; stat->mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); @@ -790,7 +792,13 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, stat->ctime.tv_nsec = attr->ctimensec; stat->size = attr->size; stat->blocks = attr->blocks; - stat->blksize = (1 << inode->i_blkbits); + + if (attr->blksize != 0) + blkbits = ilog2(attr->blksize); + else + blkbits = inode->i_sb->s_blocksize_bits; + + stat->blksize = 1 << blkbits; } static int fuse_do_getattr(struct inode *inode, struct kstat *stat, @@ -863,6 +871,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, if (stat) { generic_fillattr(inode, stat); stat->mode = fi->orig_i_mode; + stat->ino = fi->orig_ino; } } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 504e61b7fd7..b321a688cde 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -962,7 +962,9 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) goto out; - file_update_time(file); + err = file_update_time(file); + if (err) + goto out; if (file->f_flags & O_DIRECT) { written = generic_file_direct_write(iocb, iov, &nr_segs, @@ -2171,6 +2173,44 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, return ret; } +long fuse_file_fallocate(struct file *file, int mode, loff_t offset, + loff_t length) +{ + struct fuse_file *ff = file->private_data; + struct fuse_conn *fc = ff->fc; + struct fuse_req *req; + struct fuse_fallocate_in inarg = { + .fh = ff->fh, + .offset = offset, + .length = length, + .mode = mode + }; + int err; + + if (fc->no_fallocate) + return -EOPNOTSUPP; + + req = fuse_get_req(fc); + if (IS_ERR(req)) + return PTR_ERR(req); + + req->in.h.opcode = FUSE_FALLOCATE; + req->in.h.nodeid = ff->nodeid; + req->in.numargs = 1; + req->in.args[0].size = sizeof(inarg); + req->in.args[0].value = &inarg; + fuse_request_send(fc, req); + err = req->out.h.error; + if (err == -ENOSYS) { + fc->no_fallocate = 1; + err = -EOPNOTSUPP; + } + fuse_put_request(fc, req); + + return err; +} +EXPORT_SYMBOL_GPL(fuse_file_fallocate); + static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, .read = do_sync_read, @@ -2188,6 +2228,7 @@ static const struct file_operations fuse_file_operations = { .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, + .fallocate = fuse_file_fallocate, }; static const struct file_operations fuse_direct_io_file_operations = { @@ -2204,6 +2245,7 @@ static const struct file_operations fuse_direct_io_file_operations = { .unlocked_ioctl = fuse_file_ioctl, .compat_ioctl = fuse_file_compat_ioctl, .poll = fuse_file_poll, + .fallocate = fuse_file_fallocate, /* no splice_read */ }; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 572cefc7801..771fb6322c0 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -82,6 +82,9 @@ struct fuse_inode { preserve the original mode */ umode_t orig_i_mode; + /** 64 bit inode number */ + u64 orig_ino; + /** Version of last attribute change */ u64 attr_version; @@ -478,6 +481,9 @@ struct fuse_conn { /** Are BSD file locking primitives not implemented by fs? */ unsigned no_flock:1; + /** Is fallocate not implemented by fs? */ + unsigned no_fallocate:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 26783eb2b1f..1cd61652018 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -91,6 +91,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb) fi->nlookup = 0; fi->attr_version = 0; fi->writectr = 0; + fi->orig_ino = 0; INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); INIT_LIST_HEAD(&fi->writepages); @@ -122,7 +123,7 @@ static void fuse_destroy_inode(struct inode *inode) static void fuse_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (inode->i_sb->s_flags & MS_ACTIVE) { struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); @@ -139,6 +140,18 @@ static int fuse_remount_fs(struct super_block *sb, int *flags, char *data) return 0; } +/* + * ino_t is 32-bits on 32-bit arch. We have to squash the 64-bit value down + * so that it will fit. + */ +static ino_t fuse_squash_ino(u64 ino64) +{ + ino_t ino = (ino_t) ino64; + if (sizeof(ino_t) < sizeof(u64)) + ino ^= ino64 >> (sizeof(u64) - sizeof(ino_t)) * 8; + return ino; +} + void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, u64 attr_valid) { @@ -148,7 +161,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, fi->attr_version = ++fc->attr_version; fi->i_time = attr_valid; - inode->i_ino = attr->ino; + inode->i_ino = fuse_squash_ino(attr->ino); inode->i_mode = (inode->i_mode & S_IFMT) | (attr->mode & 07777); set_nlink(inode, attr->nlink); inode->i_uid = attr->uid; @@ -174,6 +187,8 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, fi->orig_i_mode = inode->i_mode; if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) inode->i_mode &= ~S_ISVTX; + + fi->orig_ino = attr->ino; } void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, @@ -627,12 +642,10 @@ static struct dentry *fuse_get_dentry(struct super_block *sb, return ERR_PTR(err); } -static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, - int connectable) +static int fuse_encode_fh(struct inode *inode, u32 *fh, int *max_len, + struct inode *parent) { - struct inode *inode = dentry->d_inode; - bool encode_parent = connectable && !S_ISDIR(inode->i_mode); - int len = encode_parent ? 6 : 3; + int len = parent ? 6 : 3; u64 nodeid; u32 generation; @@ -648,14 +661,9 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, fh[1] = (u32)(nodeid & 0xffffffff); fh[2] = generation; - if (encode_parent) { - struct inode *parent; - - spin_lock(&dentry->d_lock); - parent = dentry->d_parent->d_inode; + if (parent) { nodeid = get_fuse_inode(parent)->nodeid; generation = parent->i_generation; - spin_unlock(&dentry->d_lock); fh[3] = (u32)(nodeid >> 32); fh[4] = (u32)(nodeid & 0xffffffff); @@ -663,7 +671,7 @@ static int fuse_encode_fh(struct dentry *dentry, u32 *fh, int *max_len, } *max_len = len; - return encode_parent ? 0x82 : 0x81; + return parent ? 0x82 : 0x81; } static struct dentry *fuse_fh_to_dentry(struct super_block *sb, diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c index 230eb0f005b..bd4a5892c93 100644 --- a/fs/gfs2/acl.c +++ b/fs/gfs2/acl.c @@ -73,12 +73,8 @@ static int gfs2_set_mode(struct inode *inode, umode_t mode) int error = 0; if (mode != inode->i_mode) { - struct iattr iattr; - - iattr.ia_valid = ATTR_MODE; - iattr.ia_mode = mode; - - error = gfs2_setattr_simple(inode, &iattr); + inode->i_mode = mode; + mark_inode_dirty(inode); } return error; @@ -126,9 +122,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode) return PTR_ERR(acl); if (!acl) { mode &= ~current_umask(); - if (mode != inode->i_mode) - error = gfs2_set_mode(inode, mode); - return error; + return gfs2_set_mode(inode, mode); } if (S_ISDIR(inode->i_mode)) { diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9b2ff0e851b..e80a464850c 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -36,8 +36,8 @@ #include "glops.h" -void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int to) +static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, + unsigned int from, unsigned int to) { struct buffer_head *head = page_buffers(page); unsigned int bsize = head->b_size; @@ -517,15 +517,14 @@ out: /** * gfs2_internal_read - read an internal file * @ip: The gfs2 inode - * @ra_state: The readahead state (or NULL for no readahead) * @buf: The buffer to fill * @pos: The file position * @size: The amount to read * */ -int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state, - char *buf, loff_t *pos, unsigned size) +int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, + unsigned size) { struct address_space *mapping = ip->i_inode.i_mapping; unsigned long index = *pos / PAGE_CACHE_SIZE; @@ -943,8 +942,8 @@ static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh) clear_buffer_dirty(bh); bd = bh->b_private; if (bd) { - if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh)) - list_del_init(&bd->bd_le.le_list); + if (!list_empty(&bd->bd_list) && !buffer_pinned(bh)) + list_del_init(&bd->bd_list); else gfs2_remove_from_journal(bh, current->journal_info, 0); } @@ -1084,10 +1083,9 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask) bd = bh->b_private; if (bd) { gfs2_assert_warn(sdp, bd->bd_bh == bh); - gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr)); - if (!list_empty(&bd->bd_le.le_list)) { + if (!list_empty(&bd->bd_list)) { if (!buffer_pinned(bh)) - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); else bd = NULL; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 03c04febe26..dab54099dd9 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -324,7 +324,7 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp) if (!dblock) return x + 1; - ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, 0, &mp->mp_bh[x+1]); + ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, &mp->mp_bh[x+1]); if (ret) return ret; } @@ -882,7 +882,7 @@ static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh, top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0]; bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs; } else { - error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh); + error = gfs2_meta_indirect_buffer(ip, height, block, &bh); if (error) return error; @@ -1169,6 +1169,7 @@ static int do_grow(struct inode *inode, u64 size) struct buffer_head *dibh; struct gfs2_qadata *qa = NULL; int error; + int unstuff = 0; if (gfs2_is_stuffed(ip) && (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) { @@ -1183,13 +1184,14 @@ static int do_grow(struct inode *inode, u64 size) error = gfs2_inplace_reserve(ip, 1); if (error) goto do_grow_qunlock; + unstuff = 1; } error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0); if (error) goto do_grow_release; - if (qa) { + if (unstuff) { error = gfs2_unstuff_dinode(ip, NULL); if (error) goto do_end_trans; @@ -1208,7 +1210,7 @@ static int do_grow(struct inode *inode, u64 size) do_end_trans: gfs2_trans_end(sdp); do_grow_release: - if (qa) { + if (unstuff) { gfs2_inplace_release(ip); do_grow_qunlock: gfs2_quota_unlock(ip); diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index a836056343f..8aaeb07a07b 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -821,7 +821,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct qstr name = { .name = "", .len = 0, .hash = 0 }; + struct qstr name = { .name = "" }; error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); if (error) diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c index 70ba891654f..e8ed6d4a618 100644 --- a/fs/gfs2/export.c +++ b/fs/gfs2/export.c @@ -28,15 +28,14 @@ #define GFS2_LARGE_FH_SIZE 8 #define GFS2_OLD_FH_SIZE 10 -static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, - int connectable) +static int gfs2_encode_fh(struct inode *inode, __u32 *p, int *len, + struct inode *parent) { __be32 *fh = (__force __be32 *)p; - struct inode *inode = dentry->d_inode; struct super_block *sb = inode->i_sb; struct gfs2_inode *ip = GFS2_I(inode); - if (connectable && (*len < GFS2_LARGE_FH_SIZE)) { + if (parent && (*len < GFS2_LARGE_FH_SIZE)) { *len = GFS2_LARGE_FH_SIZE; return 255; } else if (*len < GFS2_SMALL_FH_SIZE) { @@ -50,14 +49,10 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, fh[3] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_SMALL_FH_SIZE; - if (!connectable || inode == sb->s_root->d_inode) + if (!parent || inode == sb->s_root->d_inode) return *len; - spin_lock(&dentry->d_lock); - inode = dentry->d_parent->d_inode; - ip = GFS2_I(inode); - igrab(inode); - spin_unlock(&dentry->d_lock); + ip = GFS2_I(parent); fh[4] = cpu_to_be32(ip->i_no_formal_ino >> 32); fh[5] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF); @@ -65,8 +60,6 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len, fh[7] = cpu_to_be32(ip->i_no_addr & 0xFFFFFFFF); *len = GFS2_LARGE_FH_SIZE; - iput(inode); - return *len; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index a3d2c9ee8d6..31b199f6efc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -558,14 +558,14 @@ fail: } /** - * gfs2_close - called to close a struct file + * gfs2_release - called to close a struct file * @inode: the inode the struct file belongs to * @file: the struct file being closed * * Returns: errno */ -static int gfs2_close(struct inode *inode, struct file *file) +static int gfs2_release(struct inode *inode, struct file *file) { struct gfs2_sbd *sdp = inode->i_sb->s_fs_info; struct gfs2_file *fp; @@ -1005,7 +1005,7 @@ const struct file_operations gfs2_file_fops = { .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, @@ -1019,7 +1019,7 @@ const struct file_operations gfs2_dir_fops = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .lock = gfs2_lock, .flock = gfs2_flock, @@ -1037,7 +1037,7 @@ const struct file_operations gfs2_file_fops_nolock = { .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, @@ -1049,7 +1049,7 @@ const struct file_operations gfs2_dir_fops_nolock = { .readdir = gfs2_readdir, .unlocked_ioctl = gfs2_ioctl, .open = gfs2_open, - .release = gfs2_close, + .release = gfs2_release, .fsync = gfs2_fsync, .llseek = default_llseek, }; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 1656df7aacd..4bdcf378418 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -94,7 +94,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl) /* A shortened, inline version of gfs2_trans_begin() */ tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64)); tr.tr_ip = (unsigned long)__builtin_return_address(0); - INIT_LIST_HEAD(&tr.tr_list_buf); gfs2_log_reserve(sdp, tr.tr_reserved); BUG_ON(current->journal_info); current->journal_info = &tr; @@ -379,11 +378,6 @@ int gfs2_inode_refresh(struct gfs2_inode *ip) if (error) return error; - if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) { - brelse(dibh); - return -EIO; - } - error = gfs2_dinode_in(ip, dibh->b_data); brelse(dibh); clear_bit(GIF_INVALID, &ip->i_flags); diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 47d0bda5ac2..67fd6beffec 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -26,7 +26,7 @@ #define DIO_METADATA 0x00000020 struct gfs2_log_operations; -struct gfs2_log_element; +struct gfs2_bufdata; struct gfs2_holder; struct gfs2_glock; struct gfs2_quota_data; @@ -52,7 +52,7 @@ struct gfs2_log_header_host { */ struct gfs2_log_operations { - void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le); + void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_bufdata *bd); void (*lo_before_commit) (struct gfs2_sbd *sdp); void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai); void (*lo_before_scan) (struct gfs2_jdesc *jd, @@ -64,11 +64,6 @@ struct gfs2_log_operations { const char *lo_name; }; -struct gfs2_log_element { - struct list_head le_list; - const struct gfs2_log_operations *le_ops; -}; - #define GBF_FULL 1 struct gfs2_bitmap { @@ -118,15 +113,10 @@ TAS_BUFFER_FNS(Zeronew, zeronew) struct gfs2_bufdata { struct buffer_head *bd_bh; struct gfs2_glock *bd_gl; + u64 bd_blkno; - union { - struct list_head list_tr; - u64 blkno; - } u; -#define bd_list_tr u.list_tr -#define bd_blkno u.blkno - - struct gfs2_log_element bd_le; + struct list_head bd_list; + const struct gfs2_log_operations *bd_ops; struct gfs2_ail *bd_ail; struct list_head bd_ail_st_list; @@ -411,13 +401,10 @@ struct gfs2_trans { int tr_touched; - unsigned int tr_num_buf; unsigned int tr_num_buf_new; unsigned int tr_num_databuf_new; unsigned int tr_num_buf_rm; unsigned int tr_num_databuf_rm; - struct list_head tr_list_buf; - unsigned int tr_num_revoke; unsigned int tr_num_revoke_rm; }; @@ -556,7 +543,6 @@ struct gfs2_sb_host { struct lm_lockstruct { int ls_jid; unsigned int ls_first; - unsigned int ls_nodir; const struct lm_lockops *ls_ops; dlm_lockspace_t *ls_dlm; @@ -699,7 +685,6 @@ struct gfs2_sbd { struct list_head sd_log_le_buf; struct list_head sd_log_le_revoke; - struct list_head sd_log_le_rg; struct list_head sd_log_le_databuf; struct list_head sd_log_le_ordered; @@ -716,7 +701,9 @@ struct gfs2_sbd { struct rw_semaphore sd_log_flush_lock; atomic_t sd_log_in_flight; + struct bio *sd_log_bio; wait_queue_head_t sd_log_flush_wait; + int sd_log_error; unsigned int sd_log_flush_head; u64 sd_log_flush_wrapped; diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h index 276e7b52b65..c53c7477f6d 100644 --- a/fs/gfs2/inode.h +++ b/fs/gfs2/inode.h @@ -17,10 +17,7 @@ extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask); extern int gfs2_internal_read(struct gfs2_inode *ip, - struct file_ra_state *ra_state, char *buf, loff_t *pos, unsigned size); -extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page, - unsigned int from, unsigned int to); extern void gfs2_set_aops(struct inode *inode); static inline int gfs2_is_stuffed(const struct gfs2_inode *ip) diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index f8411bd1b80..4a38db739ca 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -200,10 +200,11 @@ static int make_mode(const unsigned int lmstate) return -1; } -static u32 make_flags(const u32 lkid, const unsigned int gfs_flags, +static u32 make_flags(struct gfs2_glock *gl, const unsigned int gfs_flags, const int req) { u32 lkf = DLM_LKF_VALBLK; + u32 lkid = gl->gl_lksb.sb_lkid; if (gfs_flags & LM_FLAG_TRY) lkf |= DLM_LKF_NOQUEUE; @@ -227,8 +228,11 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags, BUG(); } - if (lkid != 0) + if (lkid != 0) { lkf |= DLM_LKF_CONVERT; + if (test_bit(GLF_BLOCKING, &gl->gl_flags)) + lkf |= DLM_LKF_QUECVT; + } return lkf; } @@ -250,7 +254,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state, char strname[GDLM_STRNAME_BYTES] = ""; req = make_mode(req_state); - lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req); + lkf = make_flags(gl, flags, req); gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT); gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT); if (gl->gl_lksb.sb_lkid) { @@ -1205,8 +1209,6 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table) fsname++; flags = DLM_LSFL_FS | DLM_LSFL_NEWEXCL; - if (ls->ls_nodir) - flags |= DLM_LSFL_NODIR; /* * create/join lockspace diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 4752eadc7f6..f4beeb9c81c 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -32,8 +32,6 @@ #include "dir.h" #include "trace_gfs2.h" -#define PULL 1 - /** * gfs2_struct2blk - compute stuff * @sdp: the filesystem @@ -359,18 +357,6 @@ retry: return 0; } -u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn) -{ - struct gfs2_journal_extent *je; - - list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { - if (lbn >= je->lblock && lbn < je->lblock + je->blocks) - return je->dblock + lbn - je->lblock; - } - - return -1; -} - /** * log_distance - Compute distance between two journal blocks * @sdp: The GFS2 superblock @@ -466,17 +452,6 @@ static unsigned int current_tail(struct gfs2_sbd *sdp) return tail; } -void gfs2_log_incr_head(struct gfs2_sbd *sdp) -{ - BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && - (sdp->sd_log_flush_head != sdp->sd_log_head)); - - if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { - sdp->sd_log_flush_head = 0; - sdp->sd_log_flush_wrapped = 1; - } -} - static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail) { unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail); @@ -511,8 +486,8 @@ static int bd_cmp(void *priv, struct list_head *a, struct list_head *b) { struct gfs2_bufdata *bda, *bdb; - bda = list_entry(a, struct gfs2_bufdata, bd_le.le_list); - bdb = list_entry(b, struct gfs2_bufdata, bd_le.le_list); + bda = list_entry(a, struct gfs2_bufdata, bd_list); + bdb = list_entry(b, struct gfs2_bufdata, bd_list); if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr) return -1; @@ -530,8 +505,8 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp); while (!list_empty(&sdp->sd_log_le_ordered)) { - bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list); - list_move(&bd->bd_le.le_list, &written); + bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_list); + list_move(&bd->bd_list, &written); bh = bd->bd_bh; if (!buffer_dirty(bh)) continue; @@ -558,7 +533,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); while (!list_empty(&sdp->sd_log_le_ordered)) { - bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list); + bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_list); bh = bd->bd_bh; if (buffer_locked(bh)) { get_bh(bh); @@ -568,7 +543,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) gfs2_log_lock(sdp); continue; } - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); } gfs2_log_unlock(sdp); } @@ -580,25 +555,19 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp) * Returns: the initialized log buffer descriptor */ -static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) +static void log_write_header(struct gfs2_sbd *sdp, u32 flags) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; struct gfs2_log_header *lh; unsigned int tail; u32 hash; - - bh = sb_getblk(sdp->sd_vfs, blkno); - lock_buffer(bh); - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); + int rw = WRITE_FLUSH_FUA | REQ_META; + struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + lh = page_address(page); + clear_page(lh); gfs2_ail1_empty(sdp); tail = current_tail(sdp); - lh = (struct gfs2_log_header *)bh->b_data; - memset(lh, 0, sizeof(struct gfs2_log_header)); lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC); lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH); lh->lh_header.__pad0 = cpu_to_be64(0); @@ -608,31 +577,22 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull) lh->lh_flags = cpu_to_be32(flags); lh->lh_tail = cpu_to_be32(tail); lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head); - hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header)); + hash = gfs2_disk_hash(page_address(page), sizeof(struct gfs2_log_header)); lh->lh_hash = cpu_to_be32(hash); - bh->b_end_io = end_buffer_write_sync; - get_bh(bh); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) { gfs2_ordered_wait(sdp); log_flush_wait(sdp); - submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh); - } else { - submit_bh(WRITE_FLUSH_FUA | REQ_META, bh); + rw = WRITE_SYNC | REQ_META | REQ_PRIO; } - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) - gfs2_io_error_bh(sdp, bh); - brelse(bh); + sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); + gfs2_log_write_page(sdp, page); + gfs2_log_flush_bio(sdp, rw); + log_flush_wait(sdp); if (sdp->sd_log_tail != tail) log_pull_tail(sdp, tail); - else - gfs2_assert_withdraw(sdp, !pull); - - sdp->sd_log_idle = (tail == sdp->sd_log_flush_head); - gfs2_log_incr_head(sdp); } /** @@ -678,15 +638,14 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl) gfs2_ordered_write(sdp); lops_before_commit(sdp); + gfs2_log_flush_bio(sdp, WRITE); if (sdp->sd_log_head != sdp->sd_log_flush_head) { - log_write_header(sdp, 0, 0); + log_write_header(sdp, 0); } else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){ - gfs2_log_lock(sdp); atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */ trace_gfs2_log_blocks(sdp, -1); - gfs2_log_unlock(sdp); - log_write_header(sdp, 0, PULL); + log_write_header(sdp, 0); } lops_after_commit(sdp, ai); @@ -735,21 +694,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr) gfs2_log_unlock(sdp); } -static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) -{ - struct list_head *head = &tr->tr_list_buf; - struct gfs2_bufdata *bd; - - gfs2_log_lock(sdp); - while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr); - list_del_init(&bd->bd_list_tr); - tr->tr_num_buf--; - } - gfs2_log_unlock(sdp); - gfs2_assert_warn(sdp, !tr->tr_num_buf); -} - /** * gfs2_log_commit - Commit a transaction to the log * @sdp: the filesystem @@ -768,8 +712,6 @@ static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr) { log_refund(sdp, tr); - buf_lo_incore_commit(sdp, tr); - up_read(&sdp->sd_log_flush_lock); if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) || @@ -798,8 +740,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp) sdp->sd_log_flush_head = sdp->sd_log_head; sdp->sd_log_flush_wrapped = 0; - log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT, - (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL); + log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT); gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks); gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail); @@ -854,11 +795,9 @@ int gfs2_logd(void *data) struct gfs2_sbd *sdp = data; unsigned long t = 1; DEFINE_WAIT(wait); - unsigned preflush; while (!kthread_should_stop()) { - preflush = atomic_read(&sdp->sd_log_pinned); if (gfs2_jrnl_flush_reqd(sdp) || t == 0) { gfs2_ail1_empty(sdp); gfs2_log_flush(sdp, NULL); diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h index ff07454b582..3fd5215ea25 100644 --- a/fs/gfs2/log.h +++ b/fs/gfs2/log.h @@ -52,8 +52,6 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct, unsigned int ssize); extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks); -extern void gfs2_log_incr_head(struct gfs2_sbd *sdp); -extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn); extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl); extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans); extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 6b1efb594d9..852c1be1dd3 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -127,146 +127,277 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh, atomic_dec(&sdp->sd_log_pinned); } - -static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh) +static void gfs2_log_incr_head(struct gfs2_sbd *sdp) { - return (struct gfs2_log_descriptor *)bh->b_data; + BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) && + (sdp->sd_log_flush_head != sdp->sd_log_head)); + + if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) { + sdp->sd_log_flush_head = 0; + sdp->sd_log_flush_wrapped = 1; + } } -static inline __be64 *bh_log_ptr(struct buffer_head *bh) +static u64 gfs2_log_bmap(struct gfs2_sbd *sdp) { - struct gfs2_log_descriptor *ld = bh_log_desc(bh); - return (__force __be64 *)(ld + 1); + unsigned int lbn = sdp->sd_log_flush_head; + struct gfs2_journal_extent *je; + u64 block; + + list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) { + if (lbn >= je->lblock && lbn < je->lblock + je->blocks) { + block = je->dblock + lbn - je->lblock; + gfs2_log_incr_head(sdp); + return block; + } + } + + return -1; } -static inline __be64 *bh_ptr_end(struct buffer_head *bh) +/** + * gfs2_end_log_write_bh - end log write of pagecache data with buffers + * @sdp: The superblock + * @bvec: The bio_vec + * @error: The i/o status + * + * This finds the relavent buffers and unlocks then and sets the + * error flag according to the status of the i/o request. This is + * used when the log is writing data which has an in-place version + * that is pinned in the pagecache. + */ + +static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, + int error) { - return (__force __be64 *)(bh->b_data + bh->b_size); + struct buffer_head *bh, *next; + struct page *page = bvec->bv_page; + unsigned size; + + bh = page_buffers(page); + size = bvec->bv_len; + while (bh_offset(bh) < bvec->bv_offset) + bh = bh->b_this_page; + do { + if (error) + set_buffer_write_io_error(bh); + unlock_buffer(bh); + next = bh->b_this_page; + size -= bh->b_size; + brelse(bh); + bh = next; + } while(bh && size); } /** - * gfs2_log_write_endio - End of I/O for a log buffer - * @bh: The buffer head - * @uptodate: I/O Status + * gfs2_end_log_write - end of i/o to the log + * @bio: The bio + * @error: Status of i/o request + * + * Each bio_vec contains either data from the pagecache or data + * relating to the log itself. Here we iterate over the bio_vec + * array, processing both kinds of data. * */ -static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate) +static void gfs2_end_log_write(struct bio *bio, int error) { - struct gfs2_sbd *sdp = bh->b_private; - bh->b_private = NULL; + struct gfs2_sbd *sdp = bio->bi_private; + struct bio_vec *bvec; + struct page *page; + int i; - end_buffer_write_sync(bh, uptodate); + if (error) { + sdp->sd_log_error = error; + fs_err(sdp, "Error %d writing to log\n", error); + } + + bio_for_each_segment(bvec, bio, i) { + page = bvec->bv_page; + if (page_has_buffers(page)) + gfs2_end_log_write_bh(sdp, bvec, error); + else + mempool_free(page, gfs2_page_pool); + } + + bio_put(bio); if (atomic_dec_and_test(&sdp->sd_log_in_flight)) wake_up(&sdp->sd_log_flush_wait); } /** - * gfs2_log_get_buf - Get and initialize a buffer to use for log control data - * @sdp: The GFS2 superblock + * gfs2_log_flush_bio - Submit any pending log bio + * @sdp: The superblock + * @rw: The rw flags * - * tReturns: the buffer_head + * Submit any pending part-built or full bio to the block device. If + * there is no pending bio, then this is a no-op. */ -static struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp) +void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; + if (sdp->sd_log_bio) { + atomic_inc(&sdp->sd_log_in_flight); + submit_bio(rw, sdp->sd_log_bio); + sdp->sd_log_bio = NULL; + } +} - bh = sb_getblk(sdp->sd_vfs, blkno); - lock_buffer(bh); - memset(bh->b_data, 0, bh->b_size); - set_buffer_uptodate(bh); - clear_buffer_dirty(bh); - gfs2_log_incr_head(sdp); - atomic_inc(&sdp->sd_log_in_flight); - bh->b_private = sdp; - bh->b_end_io = gfs2_log_write_endio; +/** + * gfs2_log_alloc_bio - Allocate a new bio for log writing + * @sdp: The superblock + * @blkno: The next device block number we want to write to + * + * This should never be called when there is a cached bio in the + * super block. When it returns, there will be a cached bio in the + * super block which will have as many bio_vecs as the device is + * happy to handle. + * + * Returns: Newly allocated bio + */ - return bh; +static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno) +{ + struct super_block *sb = sdp->sd_vfs; + unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev); + struct bio *bio; + + BUG_ON(sdp->sd_log_bio); + + while (1) { + bio = bio_alloc(GFP_NOIO, nrvecs); + if (likely(bio)) + break; + nrvecs = max(nrvecs/2, 1U); + } + + bio->bi_sector = blkno * (sb->s_blocksize >> 9); + bio->bi_bdev = sb->s_bdev; + bio->bi_end_io = gfs2_end_log_write; + bio->bi_private = sdp; + + sdp->sd_log_bio = bio; + + return bio; } /** - * gfs2_fake_write_endio - - * @bh: The buffer head - * @uptodate: The I/O Status + * gfs2_log_get_bio - Get cached log bio, or allocate a new one + * @sdp: The superblock + * @blkno: The device block number we want to write to + * + * If there is a cached bio, then if the next block number is sequential + * with the previous one, return it, otherwise flush the bio to the + * device. If there is not a cached bio, or we just flushed it, then + * allocate a new one. * + * Returns: The bio to use for log writes */ -static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate) +static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno) { - struct buffer_head *real_bh = bh->b_private; - struct gfs2_bufdata *bd = real_bh->b_private; - struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd; + struct bio *bio = sdp->sd_log_bio; + u64 nblk; + + if (bio) { + nblk = bio->bi_sector + bio_sectors(bio); + nblk >>= sdp->sd_fsb2bb_shift; + if (blkno == nblk) + return bio; + gfs2_log_flush_bio(sdp, WRITE); + } - end_buffer_write_sync(bh, uptodate); - mempool_free(bh, gfs2_bh_pool); - unlock_buffer(real_bh); - brelse(real_bh); - if (atomic_dec_and_test(&sdp->sd_log_in_flight)) - wake_up(&sdp->sd_log_flush_wait); + return gfs2_log_alloc_bio(sdp, blkno); } + /** - * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log + * gfs2_log_write - write to log * @sdp: the filesystem - * @data: the data the buffer_head should point to + * @page: the page to write + * @size: the size of the data to write + * @offset: the offset within the page * - * Returns: the log buffer descriptor + * Try and add the page segment to the current bio. If that fails, + * submit the current bio to the device and create a new one, and + * then add the page segment to that. */ -static struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp, - struct buffer_head *real) +static void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, + unsigned size, unsigned offset) { - u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head); - struct buffer_head *bh; + u64 blkno = gfs2_log_bmap(sdp); + struct bio *bio; + int ret; + + bio = gfs2_log_get_bio(sdp, blkno); + ret = bio_add_page(bio, page, size, offset); + if (ret == 0) { + gfs2_log_flush_bio(sdp, WRITE); + bio = gfs2_log_alloc_bio(sdp, blkno); + ret = bio_add_page(bio, page, size, offset); + WARN_ON(ret == 0); + } +} + +/** + * gfs2_log_write_bh - write a buffer's content to the log + * @sdp: The super block + * @bh: The buffer pointing to the in-place location + * + * This writes the content of the buffer to the next available location + * in the log. The buffer will be unlocked once the i/o to the log has + * completed. + */ - bh = mempool_alloc(gfs2_bh_pool, GFP_NOFS); - atomic_set(&bh->b_count, 1); - bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock); - set_bh_page(bh, real->b_page, bh_offset(real)); - bh->b_blocknr = blkno; - bh->b_size = sdp->sd_sb.sb_bsize; - bh->b_bdev = sdp->sd_vfs->s_bdev; - bh->b_private = real; - bh->b_end_io = gfs2_fake_write_endio; +static void gfs2_log_write_bh(struct gfs2_sbd *sdp, struct buffer_head *bh) +{ + gfs2_log_write(sdp, bh->b_page, bh->b_size, bh_offset(bh)); +} - gfs2_log_incr_head(sdp); - atomic_inc(&sdp->sd_log_in_flight); +/** + * gfs2_log_write_page - write one block stored in a page, into the log + * @sdp: The superblock + * @page: The struct page + * + * This writes the first block-sized part of the page into the log. Note + * that the page must have been allocated from the gfs2_page_pool mempool + * and that after this has been called, ownership has been transferred and + * the page may be freed at any time. + */ - return bh; +void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) +{ + struct super_block *sb = sdp->sd_vfs; + gfs2_log_write(sdp, page, sb->s_blocksize, 0); } -static struct buffer_head *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type) +static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, + u32 ld_length, u32 ld_data1) { - struct buffer_head *bh = gfs2_log_get_buf(sdp); - struct gfs2_log_descriptor *ld = bh_log_desc(bh); + struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + struct gfs2_log_descriptor *ld = page_address(page); + clear_page(ld); ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC); ld->ld_header.mh_type = cpu_to_be32(GFS2_METATYPE_LD); ld->ld_header.mh_format = cpu_to_be32(GFS2_FORMAT_LD); ld->ld_type = cpu_to_be32(ld_type); - ld->ld_length = 0; - ld->ld_data1 = 0; + ld->ld_length = cpu_to_be32(ld_length); + ld->ld_data1 = cpu_to_be32(ld_data1); ld->ld_data2 = 0; - memset(ld->ld_reserved, 0, sizeof(ld->ld_reserved)); - return bh; + return page; } -static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_meta_header *mh; struct gfs2_trans *tr; lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (!list_empty(&bd->bd_list_tr)) - goto out; tr = current->journal_info; tr->tr_touched = 1; - tr->tr_num_buf++; - list_add(&bd->bd_list_tr, &tr->tr_list_buf); - if (!list_empty(&le->le_list)) + if (!list_empty(&bd->bd_list)) goto out; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); @@ -276,62 +407,86 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) mh->__pad0 = cpu_to_be64(0); mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid); sdp->sd_log_num_buf++; - list_add(&le->le_list, &sdp->sd_log_le_buf); + list_add(&bd->bd_list, &sdp->sd_log_le_buf); tr->tr_num_buf_new++; out: gfs2_log_unlock(sdp); unlock_buffer(bd->bd_bh); } -static void buf_lo_before_commit(struct gfs2_sbd *sdp) +static void gfs2_check_magic(struct buffer_head *bh) +{ + void *kaddr; + __be32 *ptr; + + clear_buffer_escaped(bh); + kaddr = kmap_atomic(bh->b_page); + ptr = kaddr + bh_offset(bh); + if (*ptr == cpu_to_be32(GFS2_MAGIC)) + set_buffer_escaped(bh); + kunmap_atomic(kaddr); +} + +static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit, + unsigned int total, struct list_head *blist, + bool is_databuf) { - struct buffer_head *bh; struct gfs2_log_descriptor *ld; struct gfs2_bufdata *bd1 = NULL, *bd2; - unsigned int total; - unsigned int limit; + struct page *page; unsigned int num; unsigned n; __be64 *ptr; - limit = buf_limit(sdp); - /* for 4k blocks, limit = 503 */ - gfs2_log_lock(sdp); - total = sdp->sd_log_num_buf; - bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list); + bd1 = bd2 = list_prepare_entry(bd1, blist, bd_list); while(total) { num = total; if (total > limit) num = limit; gfs2_log_unlock(sdp); - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA); + page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_METADATA, num + 1, num); + ld = page_address(page); gfs2_log_lock(sdp); - ld = bh_log_desc(bh); - ptr = bh_log_ptr(bh); - ld->ld_length = cpu_to_be32(num + 1); - ld->ld_data1 = cpu_to_be32(num); + ptr = (__be64 *)(ld + 1); n = 0; - list_for_each_entry_continue(bd1, &sdp->sd_log_le_buf, - bd_le.le_list) { + list_for_each_entry_continue(bd1, blist, bd_list) { *ptr++ = cpu_to_be64(bd1->bd_bh->b_blocknr); + if (is_databuf) { + gfs2_check_magic(bd1->bd_bh); + *ptr++ = cpu_to_be64(buffer_escaped(bd1->bd_bh) ? 1 : 0); + } if (++n >= num) break; } gfs2_log_unlock(sdp); - submit_bh(WRITE_SYNC, bh); + gfs2_log_write_page(sdp, page); gfs2_log_lock(sdp); n = 0; - list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf, - bd_le.le_list) { + list_for_each_entry_continue(bd2, blist, bd_list) { get_bh(bd2->bd_bh); gfs2_log_unlock(sdp); lock_buffer(bd2->bd_bh); - bh = gfs2_log_fake_buf(sdp, bd2->bd_bh); - submit_bh(WRITE_SYNC, bh); + + if (buffer_escaped(bd2->bd_bh)) { + void *kaddr; + page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + ptr = page_address(page); + kaddr = kmap_atomic(bd2->bd_bh->b_page); + memcpy(ptr, kaddr + bh_offset(bd2->bd_bh), + bd2->bd_bh->b_size); + kunmap_atomic(kaddr); + *(__be32 *)ptr = 0; + clear_buffer_escaped(bd2->bd_bh); + unlock_buffer(bd2->bd_bh); + brelse(bd2->bd_bh); + gfs2_log_write_page(sdp, page); + } else { + gfs2_log_write_bh(sdp, bd2->bd_bh); + } gfs2_log_lock(sdp); if (++n >= num) break; @@ -343,14 +498,22 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp) gfs2_log_unlock(sdp); } +static void buf_lo_before_commit(struct gfs2_sbd *sdp) +{ + unsigned int limit = buf_limit(sdp); /* 503 for 4k blocks */ + + gfs2_before_commit(sdp, limit, sdp->sd_log_num_buf, + &sdp->sd_log_le_buf, 0); +} + static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) { struct list_head *head = &sdp->sd_log_le_buf; struct gfs2_bufdata *bd; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); sdp->sd_log_num_buf--; gfs2_unpin(sdp, bd->bd_bh, ai); @@ -437,9 +600,8 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks); } -static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_glock *gl = bd->bd_gl; struct gfs2_trans *tr; @@ -449,48 +611,48 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) sdp->sd_log_num_revoke++; atomic_inc(&gl->gl_revokes); set_bit(GLF_LFLUSH, &gl->gl_flags); - list_add(&le->le_list, &sdp->sd_log_le_revoke); + list_add(&bd->bd_list, &sdp->sd_log_le_revoke); } static void revoke_lo_before_commit(struct gfs2_sbd *sdp) { struct gfs2_log_descriptor *ld; struct gfs2_meta_header *mh; - struct buffer_head *bh; unsigned int offset; struct list_head *head = &sdp->sd_log_le_revoke; struct gfs2_bufdata *bd; + struct page *page; + unsigned int length; if (!sdp->sd_log_num_revoke) return; - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE); - ld = bh_log_desc(bh); - ld->ld_length = cpu_to_be32(gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, - sizeof(u64))); - ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke); + length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64)); + page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke); + ld = page_address(page); offset = sizeof(struct gfs2_log_descriptor); - list_for_each_entry(bd, head, bd_le.le_list) { + list_for_each_entry(bd, head, bd_list) { sdp->sd_log_num_revoke--; if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) { - submit_bh(WRITE_SYNC, bh); - bh = gfs2_log_get_buf(sdp); - mh = (struct gfs2_meta_header *)bh->b_data; + gfs2_log_write_page(sdp, page); + page = mempool_alloc(gfs2_page_pool, GFP_NOIO); + mh = page_address(page); + clear_page(mh); mh->mh_magic = cpu_to_be32(GFS2_MAGIC); mh->mh_type = cpu_to_be32(GFS2_METATYPE_LB); mh->mh_format = cpu_to_be32(GFS2_FORMAT_LB); offset = sizeof(struct gfs2_meta_header); } - *(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno); + *(__be64 *)(page_address(page) + offset) = cpu_to_be64(bd->bd_blkno); offset += sizeof(u64); } gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke); - submit_bh(WRITE_SYNC, bh); + gfs2_log_write_page(sdp, page); } static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) @@ -500,8 +662,8 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) struct gfs2_glock *gl; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); gl = bd->bd_gl; atomic_dec(&gl->gl_revokes); clear_bit(GLF_LFLUSH, &gl->gl_flags); @@ -604,108 +766,33 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass) * blocks, which isn't an enormous overhead but twice as much as * for normal metadata blocks. */ -static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le); struct gfs2_trans *tr = current->journal_info; struct address_space *mapping = bd->bd_bh->b_page->mapping; struct gfs2_inode *ip = GFS2_I(mapping->host); lock_buffer(bd->bd_bh); gfs2_log_lock(sdp); - if (tr) { - if (!list_empty(&bd->bd_list_tr)) - goto out; + if (tr) tr->tr_touched = 1; - if (gfs2_is_jdata(ip)) { - tr->tr_num_buf++; - list_add(&bd->bd_list_tr, &tr->tr_list_buf); - } - } - if (!list_empty(&le->le_list)) + if (!list_empty(&bd->bd_list)) goto out; - set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); if (gfs2_is_jdata(ip)) { gfs2_pin(sdp, bd->bd_bh); tr->tr_num_databuf_new++; sdp->sd_log_num_databuf++; - list_add_tail(&le->le_list, &sdp->sd_log_le_databuf); + list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf); } else { - list_add_tail(&le->le_list, &sdp->sd_log_le_ordered); + list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered); } out: gfs2_log_unlock(sdp); unlock_buffer(bd->bd_bh); } -static void gfs2_check_magic(struct buffer_head *bh) -{ - void *kaddr; - __be32 *ptr; - - clear_buffer_escaped(bh); - kaddr = kmap_atomic(bh->b_page); - ptr = kaddr + bh_offset(bh); - if (*ptr == cpu_to_be32(GFS2_MAGIC)) - set_buffer_escaped(bh); - kunmap_atomic(kaddr); -} - -static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, - struct list_head *list, struct list_head *done, - unsigned int n) -{ - struct buffer_head *bh1; - struct gfs2_log_descriptor *ld; - struct gfs2_bufdata *bd; - __be64 *ptr; - - if (!bh) - return; - - ld = bh_log_desc(bh); - ld->ld_length = cpu_to_be32(n + 1); - ld->ld_data1 = cpu_to_be32(n); - - ptr = bh_log_ptr(bh); - - get_bh(bh); - submit_bh(WRITE_SYNC, bh); - gfs2_log_lock(sdp); - while(!list_empty(list)) { - bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list); - list_move_tail(&bd->bd_le.le_list, done); - get_bh(bd->bd_bh); - while (be64_to_cpu(*ptr) != bd->bd_bh->b_blocknr) { - gfs2_log_incr_head(sdp); - ptr += 2; - } - gfs2_log_unlock(sdp); - lock_buffer(bd->bd_bh); - if (buffer_escaped(bd->bd_bh)) { - void *kaddr; - bh1 = gfs2_log_get_buf(sdp); - kaddr = kmap_atomic(bd->bd_bh->b_page); - memcpy(bh1->b_data, kaddr + bh_offset(bd->bd_bh), - bh1->b_size); - kunmap_atomic(kaddr); - *(__be32 *)bh1->b_data = 0; - clear_buffer_escaped(bd->bd_bh); - unlock_buffer(bd->bd_bh); - brelse(bd->bd_bh); - } else { - bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh); - } - submit_bh(WRITE_SYNC, bh1); - gfs2_log_lock(sdp); - ptr += 2; - } - gfs2_log_unlock(sdp); - brelse(bh); -} - /** * databuf_lo_before_commit - Scan the data buffers, writing as we go * @@ -713,37 +800,10 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh, static void databuf_lo_before_commit(struct gfs2_sbd *sdp) { - struct gfs2_bufdata *bd = NULL; - struct buffer_head *bh = NULL; - unsigned int n = 0; - __be64 *ptr = NULL, *end = NULL; - LIST_HEAD(processed); - LIST_HEAD(in_progress); + unsigned int limit = buf_limit(sdp) / 2; - gfs2_log_lock(sdp); - while (!list_empty(&sdp->sd_log_le_databuf)) { - if (ptr == end) { - gfs2_log_unlock(sdp); - gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); - n = 0; - bh = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_JDATA); - ptr = bh_log_ptr(bh); - end = bh_ptr_end(bh) - 1; - gfs2_log_lock(sdp); - continue; - } - bd = list_entry(sdp->sd_log_le_databuf.next, struct gfs2_bufdata, bd_le.le_list); - list_move_tail(&bd->bd_le.le_list, &in_progress); - gfs2_check_magic(bd->bd_bh); - *ptr++ = cpu_to_be64(bd->bd_bh->b_blocknr); - *ptr++ = cpu_to_be64(buffer_escaped(bh) ? 1 : 0); - n++; - } - gfs2_log_unlock(sdp); - gfs2_write_blocks(sdp, bh, &in_progress, &processed, n); - gfs2_log_lock(sdp); - list_splice(&processed, &sdp->sd_log_le_databuf); - gfs2_log_unlock(sdp); + gfs2_before_commit(sdp, limit, sdp->sd_log_num_databuf, + &sdp->sd_log_le_databuf, 1); } static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start, @@ -822,8 +882,8 @@ static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai) struct gfs2_bufdata *bd; while (!list_empty(head)) { - bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list); - list_del_init(&bd->bd_le.le_list); + bd = list_entry(head->next, struct gfs2_bufdata, bd_list); + list_del_init(&bd->bd_list); sdp->sd_log_num_databuf--; gfs2_unpin(sdp, bd->bd_bh, ai); } diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 3c0b2737658..954a330585f 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -27,6 +27,8 @@ extern const struct gfs2_log_operations gfs2_rg_lops; extern const struct gfs2_log_operations gfs2_databuf_lops; extern const struct gfs2_log_operations *gfs2_log_ops[]; +extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); +extern void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { @@ -44,17 +46,17 @@ static inline unsigned int databuf_limit(struct gfs2_sbd *sdp) return limit; } -static inline void lops_init_le(struct gfs2_log_element *le, +static inline void lops_init_le(struct gfs2_bufdata *bd, const struct gfs2_log_operations *lops) { - INIT_LIST_HEAD(&le->le_list); - le->le_ops = lops; + INIT_LIST_HEAD(&bd->bd_list); + bd->bd_ops = lops; } -static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le) +static inline void lops_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - if (le->le_ops->lo_add) - le->le_ops->lo_add(sdp, le); + if (bd->bd_ops->lo_add) + bd->bd_ops->lo_add(sdp, bd); } static inline void lops_before_commit(struct gfs2_sbd *sdp) diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 754426b1e52..6cdb0f2a1b0 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -70,16 +70,6 @@ static void gfs2_init_gl_aspace_once(void *foo) address_space_init_once(mapping); } -static void *gfs2_bh_alloc(gfp_t mask, void *data) -{ - return alloc_buffer_head(mask); -} - -static void gfs2_bh_free(void *ptr, void *data) -{ - return free_buffer_head(ptr); -} - /** * init_gfs2_fs - Register GFS2 as a filesystem * @@ -143,6 +133,12 @@ static int __init init_gfs2_fs(void) if (!gfs2_quotad_cachep) goto fail; + gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk", + sizeof(struct gfs2_blkreserv), + 0, 0, NULL); + if (!gfs2_rsrv_cachep) + goto fail; + register_shrinker(&qd_shrinker); error = register_filesystem(&gfs2_fs_type); @@ -164,8 +160,8 @@ static int __init init_gfs2_fs(void) if (!gfs2_control_wq) goto fail_recovery; - gfs2_bh_pool = mempool_create(1024, gfs2_bh_alloc, gfs2_bh_free, NULL); - if (!gfs2_bh_pool) + gfs2_page_pool = mempool_create_page_pool(64, 0); + if (!gfs2_page_pool) goto fail_control; gfs2_register_debugfs(); @@ -186,6 +182,9 @@ fail: unregister_shrinker(&qd_shrinker); gfs2_glock_exit(); + if (gfs2_rsrv_cachep) + kmem_cache_destroy(gfs2_rsrv_cachep); + if (gfs2_quotad_cachep) kmem_cache_destroy(gfs2_quotad_cachep); @@ -225,7 +224,8 @@ static void __exit exit_gfs2_fs(void) rcu_barrier(); - mempool_destroy(gfs2_bh_pool); + mempool_destroy(gfs2_page_pool); + kmem_cache_destroy(gfs2_rsrv_cachep); kmem_cache_destroy(gfs2_quotad_cachep); kmem_cache_destroy(gfs2_rgrpd_cachep); kmem_cache_destroy(gfs2_bufdata_cachep); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 181586e673f..6c1e5d1c404 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -293,11 +293,10 @@ void gfs2_attach_bufdata(struct gfs2_glock *gl, struct buffer_head *bh, bd->bd_bh = bh; bd->bd_gl = gl; - INIT_LIST_HEAD(&bd->bd_list_tr); if (meta) - lops_init_le(&bd->bd_le, &gfs2_buf_lops); + lops_init_le(bd, &gfs2_buf_lops); else - lops_init_le(&bd->bd_le, &gfs2_databuf_lops); + lops_init_le(bd, &gfs2_databuf_lops); bh->b_private = bd; if (meta) @@ -313,7 +312,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int if (test_clear_buffer_pinned(bh)) { trace_gfs2_pin(bd, 0); atomic_dec(&sdp->sd_log_pinned); - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); if (meta) { gfs2_assert_warn(sdp, sdp->sd_log_num_buf); sdp->sd_log_num_buf--; @@ -375,33 +374,24 @@ void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen) * @ip: The GFS2 inode * @height: The level of this buf in the metadata (indir addr) tree (if any) * @num: The block number (device relative) of the buffer - * @new: Non-zero if we may create a new buffer * @bhp: the buffer is returned here * * Returns: errno */ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, - int new, struct buffer_head **bhp) + struct buffer_head **bhp) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_glock *gl = ip->i_gl; struct buffer_head *bh; int ret = 0; + u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; - if (new) { - BUG_ON(height == 0); - bh = gfs2_meta_new(gl, num); - gfs2_trans_add_bh(ip->i_gl, bh, 1); - gfs2_metatype_set(bh, GFS2_METATYPE_IN, GFS2_FORMAT_IN); - gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header)); - } else { - u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI; - ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); - if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { - brelse(bh); - ret = -EIO; - } + ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh); + if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) { + brelse(bh); + ret = -EIO; } *bhp = bh; return ret; diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h index 22c52659313..c30973b07a7 100644 --- a/fs/gfs2/meta_io.h +++ b/fs/gfs2/meta_io.h @@ -65,12 +65,12 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, void gfs2_meta_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen); int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num, - int new, struct buffer_head **bhp); + struct buffer_head **bhp); static inline int gfs2_meta_inode_buffer(struct gfs2_inode *ip, struct buffer_head **bhp) { - return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, 0, bhp); + return gfs2_meta_indirect_buffer(ip, 0, ip->i_no_addr, bhp); } struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 6f3a18f9e17..b8c250fc492 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -99,7 +99,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) atomic_set(&sdp->sd_log_pinned, 0); INIT_LIST_HEAD(&sdp->sd_log_le_buf); INIT_LIST_HEAD(&sdp->sd_log_le_revoke); - INIT_LIST_HEAD(&sdp->sd_log_le_rg); INIT_LIST_HEAD(&sdp->sd_log_le_databuf); INIT_LIST_HEAD(&sdp->sd_log_le_ordered); @@ -994,6 +993,7 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent) ls->ls_jid = option; break; case Opt_id: + case Opt_nodir: /* Obsolete, but left for backward compat purposes */ break; case Opt_first: @@ -1002,12 +1002,6 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent) goto hostdata_error; ls->ls_first = option; break; - case Opt_nodir: - ret = match_int(&tmp[0], &option); - if (ret || (option != 0 && option != 1)) - goto hostdata_error; - ls->ls_nodir = option; - break; case Opt_err: default: hostdata_error: diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 6019da3dcae..b97178e7d39 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -652,7 +652,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc, } memset(&q, 0, sizeof(struct gfs2_quota)); - err = gfs2_internal_read(ip, NULL, (char *)&q, &loc, sizeof(q)); + err = gfs2_internal_read(ip, (char *)&q, &loc, sizeof(q)); if (err < 0) return err; @@ -744,7 +744,7 @@ get_a_page: i_size_write(inode, size); inode->i_mtime = inode->i_atime = CURRENT_TIME; mark_inode_dirty(inode); - return err; + return 0; unlock_out: unlock_page(page); @@ -852,7 +852,7 @@ static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd) memset(&q, 0, sizeof(struct gfs2_quota)); pos = qd2offset(qd); - error = gfs2_internal_read(ip, NULL, (char *)&q, &pos, sizeof(q)); + error = gfs2_internal_read(ip, (char *)&q, &pos, sizeof(q)); if (error < 0) return error; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 3df65c9ab73..f74fb9bd197 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -70,15 +70,15 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, /** * gfs2_setbit - Set a bit in the bitmaps - * @buffer: the buffer that holds the bitmaps - * @buflen: the length (in bytes) of the buffer + * @rgd: the resource group descriptor + * @buf2: the clone buffer that holds the bitmaps + * @bi: the bitmap structure * @block: the block to set * @new_state: the new state of the block * */ -static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, - unsigned char *buf2, unsigned int offset, +static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf2, struct gfs2_bitmap *bi, u32 block, unsigned char new_state) { @@ -86,8 +86,8 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, unsigned int buflen = bi->bi_len; const unsigned int bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE; - byte1 = buf1 + offset + (block / GFS2_NBBY); - end = buf1 + offset + buflen; + byte1 = bi->bi_bh->b_data + bi->bi_offset + (block / GFS2_NBBY); + end = bi->bi_bh->b_data + bi->bi_offset + buflen; BUG_ON(byte1 >= end); @@ -110,7 +110,7 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, *byte1 ^= (cur_state ^ new_state) << bit; if (buf2) { - byte2 = buf2 + offset + (block / GFS2_NBBY); + byte2 = buf2 + bi->bi_offset + (block / GFS2_NBBY); cur_state = (*byte2 >> bit) & GFS2_BIT_MASK; *byte2 ^= (cur_state ^ new_state) << bit; } @@ -118,6 +118,7 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1, /** * gfs2_testbit - test a bit in the bitmaps + * @rgd: the resource group descriptor * @buffer: the buffer that holds the bitmaps * @buflen: the length (in bytes) of the buffer * @block: the block to read @@ -179,7 +180,7 @@ static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state) /** * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing * a block in a given allocation state. - * @buffer: the buffer that holds the bitmaps + * @buf: the buffer that holds the bitmaps * @len: the length (in bytes) of the buffer * @goal: start search at this block's bit-pair (within @buffer) * @state: GFS2_BLKST_XXX the state of the block we're looking for. @@ -231,6 +232,7 @@ static u32 gfs2_bitfit(const u8 *buf, const unsigned int len, /** * gfs2_bitcount - count the number of bits in a certain state + * @rgd: the resource group descriptor * @buffer: the buffer that holds the bitmaps * @buflen: the length (in bytes) of the buffer * @state: the state of the block we're looking for @@ -264,7 +266,6 @@ static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, const u8 *buffer, /** * gfs2_rgrp_verify - Verify that a resource group is consistent - * @sdp: the filesystem * @rgd: the rgrp * */ @@ -322,7 +323,8 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block) /** * gfs2_blk2rgrpd - Find resource group for a given data/meta block number * @sdp: The GFS2 superblock - * @n: The data block number + * @blk: The data block number + * @exact: True if this needs to be an exact match * * Returns: The resource group, or NULL if not found */ @@ -380,7 +382,7 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp) /** * gfs2_rgrpd_get_next - get the next RG - * @rgd: A RG + * @rgd: the resource group descriptor * * Returns: The next rgrp */ @@ -529,6 +531,7 @@ static int compute_bitstructs(struct gfs2_rgrpd *rgd) /** * gfs2_ri_total - Total up the file system space, according to the rindex. + * @sdp: the filesystem * */ u64 gfs2_ri_total(struct gfs2_sbd *sdp) @@ -537,16 +540,14 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp) struct inode *inode = sdp->sd_rindex; struct gfs2_inode *ip = GFS2_I(inode); char buf[sizeof(struct gfs2_rindex)]; - struct file_ra_state ra_state; int error, rgrps; - file_ra_state_init(&ra_state, inode->i_mapping); for (rgrps = 0;; rgrps++) { loff_t pos = rgrps * sizeof(struct gfs2_rindex); if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode)) break; - error = gfs2_internal_read(ip, &ra_state, buf, &pos, + error = gfs2_internal_read(ip, buf, &pos, sizeof(struct gfs2_rindex)); if (error != sizeof(struct gfs2_rindex)) break; @@ -582,13 +583,12 @@ static int rgd_insert(struct gfs2_rgrpd *rgd) /** * read_rindex_entry - Pull in a new resource index entry from the disk - * @gl: The glock covering the rindex inode + * @ip: Pointer to the rindex inode * * Returns: 0 on success, > 0 on EOF, error code otherwise */ -static int read_rindex_entry(struct gfs2_inode *ip, - struct file_ra_state *ra_state) +static int read_rindex_entry(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex); @@ -599,7 +599,7 @@ static int read_rindex_entry(struct gfs2_inode *ip, if (pos >= i_size_read(&ip->i_inode)) return 1; - error = gfs2_internal_read(ip, ra_state, (char *)&buf, &pos, + error = gfs2_internal_read(ip, (char *)&buf, &pos, sizeof(struct gfs2_rindex)); if (error != sizeof(struct gfs2_rindex)) @@ -655,13 +655,10 @@ fail: static int gfs2_ri_update(struct gfs2_inode *ip) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); - struct inode *inode = &ip->i_inode; - struct file_ra_state ra_state; int error; - file_ra_state_init(&ra_state, inode->i_mapping); do { - error = read_rindex_entry(ip, &ra_state); + error = read_rindex_entry(ip); } while (error == 0); if (error < 0) @@ -741,7 +738,7 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf) /** * gfs2_rgrp_go_lock - Read in a RG's header and bitmaps - * @rgd: the struct gfs2_rgrpd describing the RG to read in + * @gh: The glock holder for the resource group * * Read in all of a Resource Group's header and bitmap blocks. * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. @@ -801,7 +798,7 @@ fail: /** * gfs2_rgrp_go_unlock - Release RG bitmaps read in with gfs2_rgrp_bh_get() - * @rgd: the struct gfs2_rgrpd describing the RG to read in + * @gh: The glock holder for the resource group * */ @@ -1002,11 +999,13 @@ struct gfs2_qadata *gfs2_qadata_get(struct gfs2_inode *ip) * Returns: the struct gfs2_qadata */ -static struct gfs2_blkreserv *gfs2_blkrsv_get(struct gfs2_inode *ip) +static int gfs2_blkrsv_get(struct gfs2_inode *ip) { BUG_ON(ip->i_res != NULL); - ip->i_res = kzalloc(sizeof(struct gfs2_blkreserv), GFP_NOFS); - return ip->i_res; + ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); + if (!ip->i_res) + return -ENOMEM; + return 0; } /** @@ -1038,6 +1037,8 @@ static inline u32 gfs2_bi2rgd_blk(struct gfs2_bitmap *bi, u32 blk) /** * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes * @rgd: The rgrp + * @last_unlinked: block address of the last dinode we unlinked + * @skip: block address we should explicitly not unlink * * Returns: 0 if no error * The inode, if one has been found, in inode. @@ -1102,7 +1103,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip /** * get_local_rgrp - Choose and lock a rgrp for allocation * @ip: the inode to reserve space for - * @rgp: the chosen and locked rgrp + * @last_unlinked: the last unlinked block * * Try to acquire rgrp in way which avoids contending with others. * @@ -1164,13 +1165,14 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked) static void gfs2_blkrsv_put(struct gfs2_inode *ip) { BUG_ON(ip->i_res == NULL); - kfree(ip->i_res); + kmem_cache_free(gfs2_rsrv_cachep, ip->i_res); ip->i_res = NULL; } /** * gfs2_inplace_reserve - Reserve space in the filesystem * @ip: the inode to reserve space for + * @requested: the number of blocks to be reserved * * Returns: errno */ @@ -1179,14 +1181,15 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, u32 requested) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); struct gfs2_blkreserv *rs; - int error = 0; + int error; u64 last_unlinked = NO_BLOCK; int tries = 0; - rs = gfs2_blkrsv_get(ip); - if (!rs) - return -ENOMEM; + error = gfs2_blkrsv_get(ip); + if (error) + return error; + rs = ip->i_res; rs->rs_requested = requested; if (gfs2_assert_warn(sdp, requested)) { error = -EINVAL; @@ -1268,7 +1271,6 @@ static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) * @rgd: the resource group descriptor * @goal: the goal block within the RG (start here to search for avail block) * @state: GFS2_BLKST_XXX the before-allocation state to find - * @dinode: TRUE if the first block we allocate is for a dinode * @rbi: address of the pointer to the bitmap containing the block found * * Walk rgrp's bitmap to find bits that represent a block in @state. @@ -1282,13 +1284,12 @@ static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block) * Returns: the block number found relative to the bitmap rbi */ -static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, - unsigned char state, +static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal, unsigned char state, struct gfs2_bitmap **rbi) { struct gfs2_bitmap *bi = NULL; const u32 length = rgd->rd_length; - u32 blk = BFITNOENT; + u32 biblk = BFITNOENT; unsigned int buf, x; const u8 *buffer = NULL; @@ -1325,8 +1326,8 @@ do_search: if (state != GFS2_BLKST_UNLINKED && bi->bi_clone) buffer = bi->bi_clone + bi->bi_offset; - blk = gfs2_bitfit(buffer, bi->bi_len, goal, state); - if (blk != BFITNOENT) + biblk = gfs2_bitfit(buffer, bi->bi_len, goal, state); + if (biblk != BFITNOENT) break; if ((goal == 0) && (state == GFS2_BLKST_FREE)) @@ -1339,10 +1340,10 @@ skip: goal = 0; } - if (blk != BFITNOENT) + if (biblk != BFITNOENT) *rbi = bi; - return blk; + return biblk; } /** @@ -1367,8 +1368,8 @@ static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, *n = 0; buffer = bi->bi_bh->b_data + bi->bi_offset; gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi, blk, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); + gfs2_setbit(rgd, bi->bi_clone, bi, blk, + dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); (*n)++; goal = blk; while (*n < elen) { @@ -1378,8 +1379,7 @@ static u64 gfs2_alloc_extent(struct gfs2_rgrpd *rgd, struct gfs2_bitmap *bi, if (gfs2_testbit(rgd, buffer, bi->bi_len, goal) != GFS2_BLKST_FREE) break; - gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset, - bi, goal, GFS2_BLKST_USED); + gfs2_setbit(rgd, bi->bi_clone, bi, goal, GFS2_BLKST_USED); (*n)++; } blk = gfs2_bi2rgd_blk(bi, blk); @@ -1436,8 +1436,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart, bi->bi_len); } gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1); - gfs2_setbit(rgd, bi->bi_bh->b_data, NULL, bi->bi_offset, - bi, buf_blk, new_state); + gfs2_setbit(rgd, NULL, bi, buf_blk, new_state); } return rgd; @@ -1557,7 +1556,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks, ip->i_inode.i_gid); rgd->rd_free_clone -= *nblocks; - trace_gfs2_block_alloc(ip, block, *nblocks, + trace_gfs2_block_alloc(ip, rgd, block, *nblocks, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED); *bn = block; return 0; @@ -1584,7 +1583,7 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta) rgd = rgblk_free(sdp, bstart, blen, GFS2_BLKST_FREE); if (!rgd) return; - trace_gfs2_block_alloc(ip, bstart, blen, GFS2_BLKST_FREE); + trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE); rgd->rd_free += blen; rgd->rd_flags &= ~GFS2_RGF_TRIMMED; gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); @@ -1622,7 +1621,7 @@ void gfs2_unlink_di(struct inode *inode) rgd = rgblk_free(sdp, blkno, 1, GFS2_BLKST_UNLINKED); if (!rgd) return; - trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED); + trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED); gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1); gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); } @@ -1652,7 +1651,7 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno) void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) { gfs2_free_uninit_di(rgd, ip->i_no_addr); - trace_gfs2_block_alloc(ip, ip->i_no_addr, 1, GFS2_BLKST_FREE); + trace_gfs2_block_alloc(ip, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE); gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid); gfs2_meta_wipe(ip, ip->i_no_addr, 1); } @@ -1752,7 +1751,6 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist, * and initialize an array of glock holders for them * @rlist: the list of resource groups * @state: the lock state to acquire the RG lock in - * @flags: the modifier flags for the holder structures * * FIXME: Don't use NOFAIL * diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 6172fa77ad5..713e621c240 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1554,7 +1554,7 @@ out_unlock: out: /* Case 3 starts here */ truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); gfs2_dir_hash_inval(ip); ip->i_gl->gl_object = NULL; flush_delayed_work_sync(&ip->i_gl->gl_work); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index d33172c291b..9c2592b1d5f 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -368,10 +368,7 @@ int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid) struct gfs2_jdesc *jd; int rv; - rv = -ESHUTDOWN; spin_lock(&sdp->sd_jindex_spin); - if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) - goto out; rv = -EBUSY; if (sdp->sd_jdesc->jd_jid == jid) goto out; @@ -396,8 +393,13 @@ static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len) if (rv != 1) return -EINVAL; - rv = gfs2_recover_set(sdp, jid); + if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) { + rv = -ESHUTDOWN; + goto out; + } + rv = gfs2_recover_set(sdp, jid); +out: return rv ? rv : len; } diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h index dfa89cd7553..1b8b8158819 100644 --- a/fs/gfs2/trace_gfs2.h +++ b/fs/gfs2/trace_gfs2.h @@ -457,10 +457,10 @@ TRACE_EVENT(gfs2_bmap, /* Keep track of blocks as they are allocated/freed */ TRACE_EVENT(gfs2_block_alloc, - TP_PROTO(const struct gfs2_inode *ip, u64 block, unsigned len, - u8 block_state), + TP_PROTO(const struct gfs2_inode *ip, struct gfs2_rgrpd *rgd, + u64 block, unsigned len, u8 block_state), - TP_ARGS(ip, block, len, block_state), + TP_ARGS(ip, rgd, block, len, block_state), TP_STRUCT__entry( __field( dev_t, dev ) @@ -468,6 +468,8 @@ TRACE_EVENT(gfs2_block_alloc, __field( u64, inum ) __field( u32, len ) __field( u8, block_state ) + __field( u64, rd_addr ) + __field( u32, rd_free_clone ) ), TP_fast_assign( @@ -476,14 +478,18 @@ TRACE_EVENT(gfs2_block_alloc, __entry->inum = ip->i_no_addr; __entry->len = len; __entry->block_state = block_state; + __entry->rd_addr = rgd->rd_addr; + __entry->rd_free_clone = rgd->rd_free_clone; ), - TP_printk("%u,%u bmap %llu alloc %llu/%lu %s", + TP_printk("%u,%u bmap %llu alloc %llu/%lu %s rg:%llu rf:%u", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->inum, (unsigned long long)__entry->start, (unsigned long)__entry->len, - block_state_name(__entry->block_state)) + block_state_name(__entry->block_state), + (unsigned long long)__entry->rd_addr, + __entry->rd_free_clone) ); #endif /* _TRACE_GFS2_H */ diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 86ac75d99d3..ad3e2fb763d 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -50,8 +50,6 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks, if (revokes) tr->tr_reserved += gfs2_struct2blk(sdp, revokes, sizeof(u64)); - INIT_LIST_HEAD(&tr->tr_list_buf); - gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh); error = gfs2_glock_nq(&tr->tr_t_gh); @@ -93,10 +91,21 @@ static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks) up_read(&sdp->sd_log_flush_lock); } +static void gfs2_print_trans(const struct gfs2_trans *tr) +{ + print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); + printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n", + tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched); + printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n", + tr->tr_num_buf_new, tr->tr_num_buf_rm, + tr->tr_num_databuf_new, tr->tr_num_databuf_rm, + tr->tr_num_revoke, tr->tr_num_revoke_rm); +} + void gfs2_trans_end(struct gfs2_sbd *sdp) { struct gfs2_trans *tr = current->journal_info; - + s64 nbuf; BUG_ON(!tr); current->journal_info = NULL; @@ -110,16 +119,13 @@ void gfs2_trans_end(struct gfs2_sbd *sdp) return; } - if (gfs2_assert_withdraw(sdp, tr->tr_num_buf <= tr->tr_blocks)) { - fs_err(sdp, "tr_num_buf = %u, tr_blocks = %u ", - tr->tr_num_buf, tr->tr_blocks); - print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); - } - if (gfs2_assert_withdraw(sdp, tr->tr_num_revoke <= tr->tr_revokes)) { - fs_err(sdp, "tr_num_revoke = %u, tr_revokes = %u ", - tr->tr_num_revoke, tr->tr_revokes); - print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip); - } + nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new; + nbuf -= tr->tr_num_buf_rm; + nbuf -= tr->tr_num_databuf_rm; + + if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) && + (tr->tr_num_revoke <= tr->tr_revokes))) + gfs2_print_trans(tr); gfs2_log_commit(sdp, tr); if (tr->tr_t_gh.gh_gl) { @@ -152,16 +158,16 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta) gfs2_attach_bufdata(gl, bh, meta); bd = bh->b_private; } - lops_add(sdp, &bd->bd_le); + lops_add(sdp, bd); } void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) { - BUG_ON(!list_empty(&bd->bd_le.le_list)); + BUG_ON(!list_empty(&bd->bd_list)); BUG_ON(!list_empty(&bd->bd_ail_st_list)); BUG_ON(!list_empty(&bd->bd_ail_gl_list)); - lops_init_le(&bd->bd_le, &gfs2_revoke_lops); - lops_add(sdp, &bd->bd_le); + lops_init_le(bd, &gfs2_revoke_lops); + lops_add(sdp, bd); } void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) @@ -171,9 +177,9 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len) unsigned int n = len; gfs2_log_lock(sdp); - list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_le.le_list) { + list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) { if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) { - list_del_init(&bd->bd_le.le_list); + list_del_init(&bd->bd_list); gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke); sdp->sd_log_num_revoke--; kmem_cache_free(gfs2_bufdata_cachep, bd); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 9e7765e8e7b..f00d7c5744f 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -25,7 +25,8 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly; struct kmem_cache *gfs2_bufdata_cachep __read_mostly; struct kmem_cache *gfs2_rgrpd_cachep __read_mostly; struct kmem_cache *gfs2_quotad_cachep __read_mostly; -mempool_t *gfs2_bh_pool __read_mostly; +struct kmem_cache *gfs2_rsrv_cachep __read_mostly; +mempool_t *gfs2_page_pool __read_mostly; void gfs2_assert_i(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index a4ce76c67db..3586b0dd6aa 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -152,7 +152,8 @@ extern struct kmem_cache *gfs2_inode_cachep; extern struct kmem_cache *gfs2_bufdata_cachep; extern struct kmem_cache *gfs2_rgrpd_cachep; extern struct kmem_cache *gfs2_quotad_cachep; -extern mempool_t *gfs2_bh_pool; +extern struct kmem_cache *gfs2_rsrv_cachep; +extern mempool_t *gfs2_page_pool; static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt, unsigned int *p) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 737dbeb6432..761ec06354b 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -532,7 +532,7 @@ out: void hfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (HFS_IS_RSRC(inode) && HFS_I(inode)->rsrc_inode) { HFS_I(HFS_I(inode)->rsrc_inode)->rsrc_inode = NULL; iput(HFS_I(inode)->rsrc_inode); diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c index 4dfbfec357e..ec2a9c23f0c 100644 --- a/fs/hfsplus/catalog.c +++ b/fs/hfsplus/catalog.c @@ -366,6 +366,10 @@ int hfsplus_rename_cat(u32 cnid, err = hfs_brec_find(&src_fd); if (err) goto out; + if (src_fd.entrylength > sizeof(entry) || src_fd.entrylength < 0) { + err = -EIO; + goto out; + } hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset, src_fd.entrylength); diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c index 88e155f895c..26b53fb09f6 100644 --- a/fs/hfsplus/dir.c +++ b/fs/hfsplus/dir.c @@ -150,6 +150,11 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) filp->f_pos++; /* fall through */ case 1: + if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { + err = -EIO; + goto out; + } + hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); if (be16_to_cpu(entry.type) != HFSPLUS_FOLDER_THREAD) { @@ -181,6 +186,12 @@ static int hfsplus_readdir(struct file *filp, void *dirent, filldir_t filldir) err = -EIO; goto out; } + + if (fd.entrylength > sizeof(entry) || fd.entrylength < 0) { + err = -EIO; + goto out; + } + hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, fd.entrylength); type = be16_to_cpu(entry.type); diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index c640ba57074..09addc8615f 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -31,6 +31,7 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags) struct hfsplus_sb_info *sbi = HFSPLUS_SB(inode->i_sb); struct hfsplus_vh *vh = sbi->s_vhdr; struct hfsplus_vh *bvh = sbi->s_backup_vhdr; + u32 cnid = (unsigned long)dentry->d_fsdata; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -41,8 +42,12 @@ static int hfsplus_ioctl_bless(struct file *file, int __user *user_flags) vh->finder_info[0] = bvh->finder_info[0] = cpu_to_be32(parent_ino(dentry)); - /* Bootloader */ - vh->finder_info[1] = bvh->finder_info[1] = cpu_to_be32(inode->i_ino); + /* + * Bootloader. Just using the inode here breaks in the case of + * hard links - the firmware wants the ID of the hard link file, + * but the inode points at the indirect inode + */ + vh->finder_info[1] = bvh->finder_info[1] = cpu_to_be32(cnid); /* Per spec, the OS X system folder - same as finder_info[0] here */ vh->finder_info[5] = bvh->finder_info[5] = diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index ceb1c281eef..a9bca4b8768 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -154,7 +154,7 @@ static void hfsplus_evict_inode(struct inode *inode) { dprint(DBG_INODE, "hfsplus_evict_inode: %lu\n", inode->i_ino); truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (HFSPLUS_IS_RSRC(inode)) { HFSPLUS_I(HFSPLUS_I(inode)->rsrc_inode)->rsrc_inode = NULL; iput(HFSPLUS_I(inode)->rsrc_inode); diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 7daf4b852d1..90effcccca9 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -56,7 +56,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector, DECLARE_COMPLETION_ONSTACK(wait); struct bio *bio; int ret = 0; - unsigned int io_size; + u64 io_size; loff_t start; int offset; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 07c516bfea7..2afa5bbccf9 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -240,7 +240,7 @@ static struct inode *hostfs_alloc_inode(struct super_block *sb) static void hostfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (HOSTFS_I(inode)->fd != -1) { close_file(&HOSTFS_I(inode)->fd); HOSTFS_I(inode)->fd = -1; diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c index 7a5eb2c718c..cdb84a83806 100644 --- a/fs/hpfs/alloc.c +++ b/fs/hpfs/alloc.c @@ -16,9 +16,9 @@ static int chk_if_allocated(struct super_block *s, secno sec, char *msg) { struct quad_buffer_head qbh; - u32 *bmp; + __le32 *bmp; if (!(bmp = hpfs_map_bitmap(s, sec >> 14, &qbh, "chk"))) goto fail; - if ((cpu_to_le32(bmp[(sec & 0x3fff) >> 5]) >> (sec & 0x1f)) & 1) { + if ((le32_to_cpu(bmp[(sec & 0x3fff) >> 5]) >> (sec & 0x1f)) & 1) { hpfs_error(s, "sector '%s' - %08x not allocated in bitmap", msg, sec); goto fail1; } @@ -62,7 +62,7 @@ int hpfs_chk_sectors(struct super_block *s, secno start, int len, char *msg) static secno alloc_in_bmp(struct super_block *s, secno near, unsigned n, unsigned forward) { struct quad_buffer_head qbh; - unsigned *bmp; + __le32 *bmp; unsigned bs = near & ~0x3fff; unsigned nr = (near & 0x3fff) & ~(n - 1); /*unsigned mnr;*/ @@ -236,7 +236,7 @@ static secno alloc_in_dirband(struct super_block *s, secno near) int hpfs_alloc_if_possible(struct super_block *s, secno sec) { struct quad_buffer_head qbh; - u32 *bmp; + __le32 *bmp; if (!(bmp = hpfs_map_bitmap(s, sec >> 14, &qbh, "aip"))) goto end; if (le32_to_cpu(bmp[(sec & 0x3fff) >> 5]) & (1 << (sec & 0x1f))) { bmp[(sec & 0x3fff) >> 5] &= cpu_to_le32(~(1 << (sec & 0x1f))); @@ -254,7 +254,7 @@ int hpfs_alloc_if_possible(struct super_block *s, secno sec) void hpfs_free_sectors(struct super_block *s, secno sec, unsigned n) { struct quad_buffer_head qbh; - u32 *bmp; + __le32 *bmp; struct hpfs_sb_info *sbi = hpfs_sb(s); /*printk("2 - ");*/ if (!n) return; @@ -299,7 +299,7 @@ int hpfs_check_free_dnodes(struct super_block *s, int n) int n_bmps = (hpfs_sb(s)->sb_fs_size + 0x4000 - 1) >> 14; int b = hpfs_sb(s)->sb_c_bitmap & 0x0fffffff; int i, j; - u32 *bmp; + __le32 *bmp; struct quad_buffer_head qbh; if ((bmp = hpfs_map_dnode_bitmap(s, &qbh))) { for (j = 0; j < 512; j++) { @@ -351,7 +351,7 @@ void hpfs_free_dnode(struct super_block *s, dnode_secno dno) hpfs_free_sectors(s, dno, 4); } else { struct quad_buffer_head qbh; - u32 *bmp; + __le32 *bmp; unsigned ssec = (dno - hpfs_sb(s)->sb_dirband_start) / 4; if (!(bmp = hpfs_map_dnode_bitmap(s, &qbh))) { return; diff --git a/fs/hpfs/anode.c b/fs/hpfs/anode.c index 08b503e8ed2..4bae4a4a60b 100644 --- a/fs/hpfs/anode.c +++ b/fs/hpfs/anode.c @@ -20,7 +20,7 @@ secno hpfs_bplus_lookup(struct super_block *s, struct inode *inode, int c1, c2 = 0; go_down: if (hpfs_sb(s)->sb_chk) if (hpfs_stop_cycles(s, a, &c1, &c2, "hpfs_bplus_lookup")) return -1; - if (btree->internal) { + if (bp_internal(btree)) { for (i = 0; i < btree->n_used_nodes; i++) if (le32_to_cpu(btree->u.internal[i].file_secno) > sec) { a = le32_to_cpu(btree->u.internal[i].down); @@ -82,7 +82,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi brelse(bh); return -1; } - if (btree->internal) { + if (bp_internal(btree)) { a = le32_to_cpu(btree->u.internal[n].down); btree->u.internal[n].file_secno = cpu_to_le32(-1); mark_buffer_dirty(bh); @@ -129,12 +129,12 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } if (a == node && fnod) { anode->up = cpu_to_le32(node); - anode->btree.fnode_parent = 1; + anode->btree.flags |= BP_fnode_parent; anode->btree.n_used_nodes = btree->n_used_nodes; anode->btree.first_free = btree->first_free; anode->btree.n_free_nodes = 40 - anode->btree.n_used_nodes; memcpy(&anode->u, &btree->u, btree->n_used_nodes * 12); - btree->internal = 1; + btree->flags |= BP_internal; btree->n_free_nodes = 11; btree->n_used_nodes = 1; btree->first_free = cpu_to_le16((char *)&(btree->u.internal[1]) - (char *)btree); @@ -184,7 +184,10 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi hpfs_free_sectors(s, ra, 1); if ((anode = hpfs_map_anode(s, na, &bh))) { anode->up = cpu_to_le32(up); - anode->btree.fnode_parent = up == node && fnod; + if (up == node && fnod) + anode->btree.flags |= BP_fnode_parent; + else + anode->btree.flags &= ~BP_fnode_parent; mark_buffer_dirty(bh); brelse(bh); } @@ -198,7 +201,7 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi if ((new_anode = hpfs_alloc_anode(s, a, &na, &bh))) { anode = new_anode; /*anode->up = cpu_to_le32(up != -1 ? up : ra);*/ - anode->btree.internal = 1; + anode->btree.flags |= BP_internal; anode->btree.n_used_nodes = 1; anode->btree.n_free_nodes = 59; anode->btree.first_free = cpu_to_le16(16); @@ -215,7 +218,8 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } if ((anode = hpfs_map_anode(s, na, &bh))) { anode->up = cpu_to_le32(node); - if (fnod) anode->btree.fnode_parent = 1; + if (fnod) + anode->btree.flags |= BP_fnode_parent; mark_buffer_dirty(bh); brelse(bh); } @@ -234,18 +238,19 @@ secno hpfs_add_sector_to_btree(struct super_block *s, secno node, int fnod, unsi } ranode->up = cpu_to_le32(node); memcpy(&ranode->btree, btree, le16_to_cpu(btree->first_free)); - if (fnod) ranode->btree.fnode_parent = 1; - ranode->btree.n_free_nodes = (ranode->btree.internal ? 60 : 40) - ranode->btree.n_used_nodes; - if (ranode->btree.internal) for (n = 0; n < ranode->btree.n_used_nodes; n++) { + if (fnod) + ranode->btree.flags |= BP_fnode_parent; + ranode->btree.n_free_nodes = (bp_internal(&ranode->btree) ? 60 : 40) - ranode->btree.n_used_nodes; + if (bp_internal(&ranode->btree)) for (n = 0; n < ranode->btree.n_used_nodes; n++) { struct anode *unode; if ((unode = hpfs_map_anode(s, le32_to_cpu(ranode->u.internal[n].down), &bh1))) { unode->up = cpu_to_le32(ra); - unode->btree.fnode_parent = 0; + unode->btree.flags &= ~BP_fnode_parent; mark_buffer_dirty(bh1); brelse(bh1); } } - btree->internal = 1; + btree->flags |= BP_internal; btree->n_free_nodes = fnod ? 10 : 58; btree->n_used_nodes = 2; btree->first_free = cpu_to_le16((char *)&btree->u.internal[2] - (char *)btree); @@ -278,7 +283,7 @@ void hpfs_remove_btree(struct super_block *s, struct bplus_header *btree) int d1, d2; go_down: d2 = 0; - while (btree1->internal) { + while (bp_internal(btree1)) { ano = le32_to_cpu(btree1->u.internal[pos].down); if (level) brelse(bh); if (hpfs_sb(s)->sb_chk) @@ -412,13 +417,13 @@ void hpfs_truncate_btree(struct super_block *s, secno f, int fno, unsigned secs) btree->n_free_nodes = 8; btree->n_used_nodes = 0; btree->first_free = cpu_to_le16(8); - btree->internal = 0; + btree->flags &= ~BP_internal; mark_buffer_dirty(bh); } else hpfs_free_sectors(s, f, 1); brelse(bh); return; } - while (btree->internal) { + while (bp_internal(btree)) { nodes = btree->n_used_nodes + btree->n_free_nodes; for (i = 0; i < btree->n_used_nodes; i++) if (le32_to_cpu(btree->u.internal[i].file_secno) >= secs) goto f; @@ -479,13 +484,13 @@ void hpfs_remove_fnode(struct super_block *s, fnode_secno fno) struct extended_attribute *ea; struct extended_attribute *ea_end; if (!(fnode = hpfs_map_fnode(s, fno, &bh))) return; - if (!fnode->dirflag) hpfs_remove_btree(s, &fnode->btree); + if (!fnode_is_dir(fnode)) hpfs_remove_btree(s, &fnode->btree); else hpfs_remove_dtree(s, le32_to_cpu(fnode->u.external[0].disk_secno)); ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) - if (ea->indirect) - hpfs_ea_remove(s, ea_sec(ea), ea->anode, ea_len(ea)); - hpfs_ea_ext_remove(s, le32_to_cpu(fnode->ea_secno), fnode->ea_anode, le32_to_cpu(fnode->ea_size_l)); + if (ea_indirect(ea)) + hpfs_ea_remove(s, ea_sec(ea), ea_in_anode(ea), ea_len(ea)); + hpfs_ea_ext_remove(s, le32_to_cpu(fnode->ea_secno), fnode_in_anode(fnode), le32_to_cpu(fnode->ea_size_l)); brelse(bh); hpfs_free_sectors(s, fno, 1); } diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index 9ecde27d1e2..f49d1498aa2 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -156,7 +156,6 @@ void hpfs_brelse4(struct quad_buffer_head *qbh) void hpfs_mark_4buffers_dirty(struct quad_buffer_head *qbh) { - PRINTK(("hpfs_mark_4buffers_dirty\n")); memcpy(qbh->bh[0]->b_data, qbh->data, 512); memcpy(qbh->bh[1]->b_data, qbh->data + 512, 512); memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512); diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c index 2fa0089a02a..b8472f803f4 100644 --- a/fs/hpfs/dir.c +++ b/fs/hpfs/dir.c @@ -87,7 +87,7 @@ static int hpfs_readdir(struct file *filp, void *dirent, filldir_t filldir) ret = -EIOERROR; goto out; } - if (!fno->dirflag) { + if (!fnode_is_dir(fno)) { e = 1; hpfs_error(inode->i_sb, "not a directory, fnode %08lx", (unsigned long)inode->i_ino); diff --git a/fs/hpfs/dnode.c b/fs/hpfs/dnode.c index 1e0e2ac30fd..3228c524ebe 100644 --- a/fs/hpfs/dnode.c +++ b/fs/hpfs/dnode.c @@ -153,7 +153,7 @@ static void set_last_pointer(struct super_block *s, struct dnode *d, dnode_secno } de->length = cpu_to_le16(36); de->down = 1; - *(dnode_secno *)((char *)de + 32) = cpu_to_le32(ptr); + *(__le32 *)((char *)de + 32) = cpu_to_le32(ptr); } } @@ -177,7 +177,7 @@ struct hpfs_dirent *hpfs_add_de(struct super_block *s, struct dnode *d, memmove((char *)de + d_size, de, (char *)de_end - (char *)de); memset(de, 0, d_size); if (down_ptr) { - *(dnode_secno *)((char *)de + d_size - 4) = cpu_to_le32(down_ptr); + *(__le32 *)((char *)de + d_size - 4) = cpu_to_le32(down_ptr); de->down = 1; } de->length = cpu_to_le16(d_size); @@ -656,7 +656,7 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno) del->down = 0; d1->first_free = cpu_to_le32(le32_to_cpu(d1->first_free) - 4); } else if (down) - *(dnode_secno *) ((void *) del + le16_to_cpu(del->length) - 4) = cpu_to_le32(down); + *(__le32 *) ((void *) del + le16_to_cpu(del->length) - 4) = cpu_to_le32(down); } else goto endm; if (!(de_cp = kmalloc(le16_to_cpu(de_prev->length), GFP_NOFS))) { printk("HPFS: out of memory for dtree balancing\n"); @@ -672,7 +672,7 @@ static void delete_empty_dnode(struct inode *i, dnode_secno dno) de_prev->down = 1; dnode->first_free = cpu_to_le32(le32_to_cpu(dnode->first_free) + 4); } - *(dnode_secno *) ((void *) de_prev + le16_to_cpu(de_prev->length) - 4) = cpu_to_le32(ndown); + *(__le32 *) ((void *) de_prev + le16_to_cpu(de_prev->length) - 4) = cpu_to_le32(ndown); hpfs_mark_4buffers_dirty(&qbh); hpfs_brelse4(&qbh); for_all_poss(i, hpfs_pos_subst, ((loff_t)up << 4) | (p - 1), 4); @@ -1015,7 +1015,7 @@ struct hpfs_dirent *map_fnode_dirent(struct super_block *s, fnode_secno fno, kfree(name2); return NULL; } - if (!upf->dirflag) { + if (!fnode_is_dir(upf)) { brelse(bh); hpfs_error(s, "fnode %08x has non-directory parent %08x", fno, le32_to_cpu(f->up)); kfree(name2); diff --git a/fs/hpfs/ea.c b/fs/hpfs/ea.c index d8b84d113c8..bcaafcd2666 100644 --- a/fs/hpfs/ea.c +++ b/fs/hpfs/ea.c @@ -23,15 +23,15 @@ void hpfs_ea_ext_remove(struct super_block *s, secno a, int ano, unsigned len) return; } if (hpfs_ea_read(s, a, ano, pos, 4, ex)) return; - if (ea->indirect) { + if (ea_indirect(ea)) { if (ea_valuelen(ea) != 8) { - hpfs_error(s, "ea->indirect set while ea->valuelen!=8, %s %08x, pos %08x", + hpfs_error(s, "ea_indirect(ea) set while ea->valuelen!=8, %s %08x, pos %08x", ano ? "anode" : "sectors", a, pos); return; } if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 9, ex+4)) return; - hpfs_ea_remove(s, ea_sec(ea), ea->anode, ea_len(ea)); + hpfs_ea_remove(s, ea_sec(ea), ea_in_anode(ea), ea_len(ea)); } pos += ea->namelen + ea_valuelen(ea) + 5; } @@ -81,7 +81,7 @@ int hpfs_read_ea(struct super_block *s, struct fnode *fnode, char *key, struct extended_attribute *ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) if (!strcmp(ea->name, key)) { - if (ea->indirect) + if (ea_indirect(ea)) goto indirect; if (ea_valuelen(ea) >= size) return -EINVAL; @@ -91,7 +91,7 @@ int hpfs_read_ea(struct super_block *s, struct fnode *fnode, char *key, } a = le32_to_cpu(fnode->ea_secno); len = le32_to_cpu(fnode->ea_size_l); - ano = fnode->ea_anode; + ano = fnode_in_anode(fnode); pos = 0; while (pos < len) { ea = (struct extended_attribute *)ex; @@ -101,10 +101,10 @@ int hpfs_read_ea(struct super_block *s, struct fnode *fnode, char *key, return -EIO; } if (hpfs_ea_read(s, a, ano, pos, 4, ex)) return -EIO; - if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea->indirect ? 8 : 0), ex + 4)) + if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea_indirect(ea) ? 8 : 0), ex + 4)) return -EIO; if (!strcmp(ea->name, key)) { - if (ea->indirect) + if (ea_indirect(ea)) goto indirect; if (ea_valuelen(ea) >= size) return -EINVAL; @@ -119,7 +119,7 @@ int hpfs_read_ea(struct super_block *s, struct fnode *fnode, char *key, indirect: if (ea_len(ea) >= size) return -EINVAL; - if (hpfs_ea_read(s, ea_sec(ea), ea->anode, 0, ea_len(ea), buf)) + if (hpfs_ea_read(s, ea_sec(ea), ea_in_anode(ea), 0, ea_len(ea), buf)) return -EIO; buf[ea_len(ea)] = 0; return 0; @@ -136,8 +136,8 @@ char *hpfs_get_ea(struct super_block *s, struct fnode *fnode, char *key, int *si struct extended_attribute *ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) if (!strcmp(ea->name, key)) { - if (ea->indirect) - return get_indirect_ea(s, ea->anode, ea_sec(ea), *size = ea_len(ea)); + if (ea_indirect(ea)) + return get_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), *size = ea_len(ea)); if (!(ret = kmalloc((*size = ea_valuelen(ea)) + 1, GFP_NOFS))) { printk("HPFS: out of memory for EA\n"); return NULL; @@ -148,7 +148,7 @@ char *hpfs_get_ea(struct super_block *s, struct fnode *fnode, char *key, int *si } a = le32_to_cpu(fnode->ea_secno); len = le32_to_cpu(fnode->ea_size_l); - ano = fnode->ea_anode; + ano = fnode_in_anode(fnode); pos = 0; while (pos < len) { char ex[4 + 255 + 1 + 8]; @@ -159,11 +159,11 @@ char *hpfs_get_ea(struct super_block *s, struct fnode *fnode, char *key, int *si return NULL; } if (hpfs_ea_read(s, a, ano, pos, 4, ex)) return NULL; - if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea->indirect ? 8 : 0), ex + 4)) + if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea_indirect(ea) ? 8 : 0), ex + 4)) return NULL; if (!strcmp(ea->name, key)) { - if (ea->indirect) - return get_indirect_ea(s, ea->anode, ea_sec(ea), *size = ea_len(ea)); + if (ea_indirect(ea)) + return get_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), *size = ea_len(ea)); if (!(ret = kmalloc((*size = ea_valuelen(ea)) + 1, GFP_NOFS))) { printk("HPFS: out of memory for EA\n"); return NULL; @@ -199,9 +199,9 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, struct extended_attribute *ea_end = fnode_end_ea(fnode); for (ea = fnode_ea(fnode); ea < ea_end; ea = next_ea(ea)) if (!strcmp(ea->name, key)) { - if (ea->indirect) { + if (ea_indirect(ea)) { if (ea_len(ea) == size) - set_indirect_ea(s, ea->anode, ea_sec(ea), data, size); + set_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), data, size); } else if (ea_valuelen(ea) == size) { memcpy(ea_data(ea), data, size); } @@ -209,7 +209,7 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, } a = le32_to_cpu(fnode->ea_secno); len = le32_to_cpu(fnode->ea_size_l); - ano = fnode->ea_anode; + ano = fnode_in_anode(fnode); pos = 0; while (pos < len) { char ex[4 + 255 + 1 + 8]; @@ -220,12 +220,12 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, return; } if (hpfs_ea_read(s, a, ano, pos, 4, ex)) return; - if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea->indirect ? 8 : 0), ex + 4)) + if (hpfs_ea_read(s, a, ano, pos + 4, ea->namelen + 1 + (ea_indirect(ea) ? 8 : 0), ex + 4)) return; if (!strcmp(ea->name, key)) { - if (ea->indirect) { + if (ea_indirect(ea)) { if (ea_len(ea) == size) - set_indirect_ea(s, ea->anode, ea_sec(ea), data, size); + set_indirect_ea(s, ea_in_anode(ea), ea_sec(ea), data, size); } else { if (ea_valuelen(ea) == size) @@ -246,7 +246,7 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, if (le16_to_cpu(fnode->ea_offs) < 0xc4 || le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s) + le16_to_cpu(fnode->ea_size_s) > 0x200) { hpfs_error(s, "fnode %08lx: ea_offs == %03x, ea_size_s == %03x", (unsigned long)inode->i_ino, - le32_to_cpu(fnode->ea_offs), le16_to_cpu(fnode->ea_size_s)); + le16_to_cpu(fnode->ea_offs), le16_to_cpu(fnode->ea_size_s)); return; } if ((le16_to_cpu(fnode->ea_size_s) || !le32_to_cpu(fnode->ea_size_l)) && @@ -276,7 +276,7 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, fnode->ea_size_l = cpu_to_le32(le16_to_cpu(fnode->ea_size_s)); fnode->ea_size_s = cpu_to_le16(0); fnode->ea_secno = cpu_to_le32(n); - fnode->ea_anode = cpu_to_le32(0); + fnode->flags &= ~FNODE_anode; mark_buffer_dirty(bh); brelse(bh); } @@ -288,9 +288,9 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, secno q = hpfs_alloc_sector(s, fno, 1, 0); if (!q) goto bail; fnode->ea_secno = cpu_to_le32(q); - fnode->ea_anode = 0; + fnode->flags &= ~FNODE_anode; len++; - } else if (!fnode->ea_anode) { + } else if (!fnode_in_anode(fnode)) { if (hpfs_alloc_if_possible(s, le32_to_cpu(fnode->ea_secno) + len)) { len++; } else { @@ -310,7 +310,7 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, anode->u.external[0].length = cpu_to_le32(len); mark_buffer_dirty(bh); brelse(bh); - fnode->ea_anode = 1; + fnode->flags |= FNODE_anode; fnode->ea_secno = cpu_to_le32(a_s);*/ secno new_sec; int i; @@ -338,7 +338,7 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, len = (pos + 511) >> 9; } } - if (fnode->ea_anode) { + if (fnode_in_anode(fnode)) { if (hpfs_add_sector_to_btree(s, le32_to_cpu(fnode->ea_secno), 0, len) != -1) { len++; @@ -351,16 +351,16 @@ void hpfs_set_ea(struct inode *inode, struct fnode *fnode, const char *key, h[1] = strlen(key); h[2] = size & 0xff; h[3] = size >> 8; - if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode->ea_anode, le32_to_cpu(fnode->ea_size_l), 4, h)) goto bail; - if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode->ea_anode, le32_to_cpu(fnode->ea_size_l) + 4, h[1] + 1, key)) goto bail; - if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode->ea_anode, le32_to_cpu(fnode->ea_size_l) + 5 + h[1], size, data)) goto bail; + if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode_in_anode(fnode), le32_to_cpu(fnode->ea_size_l), 4, h)) goto bail; + if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode_in_anode(fnode), le32_to_cpu(fnode->ea_size_l) + 4, h[1] + 1, key)) goto bail; + if (hpfs_ea_write(s, le32_to_cpu(fnode->ea_secno), fnode_in_anode(fnode), le32_to_cpu(fnode->ea_size_l) + 5 + h[1], size, data)) goto bail; fnode->ea_size_l = cpu_to_le32(pos); ret: hpfs_i(inode)->i_ea_size += 5 + strlen(key) + size; return; bail: if (le32_to_cpu(fnode->ea_secno)) - if (fnode->ea_anode) hpfs_truncate_btree(s, le32_to_cpu(fnode->ea_secno), 1, (le32_to_cpu(fnode->ea_size_l) + 511) >> 9); + if (fnode_in_anode(fnode)) hpfs_truncate_btree(s, le32_to_cpu(fnode->ea_secno), 1, (le32_to_cpu(fnode->ea_size_l) + 511) >> 9); else hpfs_free_sectors(s, le32_to_cpu(fnode->ea_secno) + ((le32_to_cpu(fnode->ea_size_l) + 511) >> 9), len - ((le32_to_cpu(fnode->ea_size_l) + 511) >> 9)); else fnode->ea_secno = fnode->ea_size_l = cpu_to_le32(0); } diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h index 8b0650aae32..cce025aff1b 100644 --- a/fs/hpfs/hpfs.h +++ b/fs/hpfs/hpfs.h @@ -51,11 +51,11 @@ struct hpfs_boot_block u8 n_rootdir_entries[2]; u8 n_sectors_s[2]; u8 media_byte; - u16 sectors_per_fat; - u16 sectors_per_track; - u16 heads_per_cyl; - u32 n_hidden_sectors; - u32 n_sectors_l; /* size of partition */ + __le16 sectors_per_fat; + __le16 sectors_per_track; + __le16 heads_per_cyl; + __le32 n_hidden_sectors; + __le32 n_sectors_l; /* size of partition */ u8 drive_number; u8 mbz; u8 sig_28h; /* 28h */ @@ -63,7 +63,7 @@ struct hpfs_boot_block u8 vol_label[11]; u8 sig_hpfs[8]; /* "HPFS " */ u8 pad[448]; - u16 magic; /* aa55 */ + __le16 magic; /* aa55 */ }; @@ -75,28 +75,28 @@ struct hpfs_boot_block struct hpfs_super_block { - u32 magic; /* f995 e849 */ - u32 magic1; /* fa53 e9c5, more magic? */ + __le32 magic; /* f995 e849 */ + __le32 magic1; /* fa53 e9c5, more magic? */ u8 version; /* version of a filesystem usually 2 */ u8 funcversion; /* functional version - oldest version of filesystem that can understand this disk */ - u16 zero; /* 0 */ - fnode_secno root; /* fnode of root directory */ - secno n_sectors; /* size of filesystem */ - u32 n_badblocks; /* number of bad blocks */ - secno bitmaps; /* pointers to free space bit maps */ - u32 zero1; /* 0 */ - secno badblocks; /* bad block list */ - u32 zero3; /* 0 */ - time32_t last_chkdsk; /* date last checked, 0 if never */ - time32_t last_optimize; /* date last optimized, 0 if never */ - secno n_dir_band; /* number of sectors in dir band */ - secno dir_band_start; /* first sector in dir band */ - secno dir_band_end; /* last sector in dir band */ - secno dir_band_bitmap; /* free space map, 1 dnode per bit */ + __le16 zero; /* 0 */ + __le32 root; /* fnode of root directory */ + __le32 n_sectors; /* size of filesystem */ + __le32 n_badblocks; /* number of bad blocks */ + __le32 bitmaps; /* pointers to free space bit maps */ + __le32 zero1; /* 0 */ + __le32 badblocks; /* bad block list */ + __le32 zero3; /* 0 */ + __le32 last_chkdsk; /* date last checked, 0 if never */ + __le32 last_optimize; /* date last optimized, 0 if never */ + __le32 n_dir_band; /* number of sectors in dir band */ + __le32 dir_band_start; /* first sector in dir band */ + __le32 dir_band_end; /* last sector in dir band */ + __le32 dir_band_bitmap; /* free space map, 1 dnode per bit */ u8 volume_name[32]; /* not used */ - secno user_id_table; /* 8 preallocated sectors - user id */ + __le32 user_id_table; /* 8 preallocated sectors - user id */ u32 zero6[103]; /* 0 */ }; @@ -109,8 +109,8 @@ struct hpfs_super_block struct hpfs_spare_block { - u32 magic; /* f991 1849 */ - u32 magic1; /* fa52 29c5, more magic? */ + __le32 magic; /* f991 1849 */ + __le32 magic1; /* fa52 29c5, more magic? */ #ifdef __LITTLE_ENDIAN u8 dirty: 1; /* 0 clean, 1 "improperly stopped" */ @@ -153,21 +153,21 @@ struct hpfs_spare_block u8 mm_contlgulty; u8 unused; - secno hotfix_map; /* info about remapped bad sectors */ - u32 n_spares_used; /* number of hotfixes */ - u32 n_spares; /* number of spares in hotfix map */ - u32 n_dnode_spares_free; /* spare dnodes unused */ - u32 n_dnode_spares; /* length of spare_dnodes[] list, + __le32 hotfix_map; /* info about remapped bad sectors */ + __le32 n_spares_used; /* number of hotfixes */ + __le32 n_spares; /* number of spares in hotfix map */ + __le32 n_dnode_spares_free; /* spare dnodes unused */ + __le32 n_dnode_spares; /* length of spare_dnodes[] list, follows in this block*/ - secno code_page_dir; /* code page directory block */ - u32 n_code_pages; /* number of code pages */ - u32 super_crc; /* on HPFS386 and LAN Server this is + __le32 code_page_dir; /* code page directory block */ + __le32 n_code_pages; /* number of code pages */ + __le32 super_crc; /* on HPFS386 and LAN Server this is checksum of superblock, on normal OS/2 unused */ - u32 spare_crc; /* on HPFS386 checksum of spareblock */ - u32 zero1[15]; /* unused */ - dnode_secno spare_dnodes[100]; /* emergency free dnode list */ - u32 zero2[1]; /* room for more? */ + __le32 spare_crc; /* on HPFS386 checksum of spareblock */ + __le32 zero1[15]; /* unused */ + __le32 spare_dnodes[100]; /* emergency free dnode list */ + __le32 zero2[1]; /* room for more? */ }; /* The bad block list is 4 sectors long. The first word must be zero, @@ -202,18 +202,18 @@ struct hpfs_spare_block struct code_page_directory { - u32 magic; /* 4945 21f7 */ - u32 n_code_pages; /* number of pointers following */ - u32 zero1[2]; + __le32 magic; /* 4945 21f7 */ + __le32 n_code_pages; /* number of pointers following */ + __le32 zero1[2]; struct { - u16 ix; /* index */ - u16 code_page_number; /* code page number */ - u32 bounds; /* matches corresponding word + __le16 ix; /* index */ + __le16 code_page_number; /* code page number */ + __le32 bounds; /* matches corresponding word in data block */ - secno code_page_data; /* sector number of a code_page_data + __le32 code_page_data; /* sector number of a code_page_data containing c.p. array */ - u16 index; /* index in c.p. array in that sector*/ - u16 unknown; /* some unknown value; usually 0; + __le16 index; /* index in c.p. array in that sector*/ + __le16 unknown; /* some unknown value; usually 0; 2 in Japanese version */ } array[31]; /* unknown length */ }; @@ -224,19 +224,19 @@ struct code_page_directory struct code_page_data { - u32 magic; /* 8945 21f7 */ - u32 n_used; /* # elements used in c_p_data[] */ - u32 bounds[3]; /* looks a bit like + __le32 magic; /* 8945 21f7 */ + __le32 n_used; /* # elements used in c_p_data[] */ + __le32 bounds[3]; /* looks a bit like (beg1,end1), (beg2,end2) one byte each */ - u16 offs[3]; /* offsets from start of sector + __le16 offs[3]; /* offsets from start of sector to start of c_p_data[ix] */ struct { - u16 ix; /* index */ - u16 code_page_number; /* code page number */ - u16 unknown; /* the same as in cp directory */ + __le16 ix; /* index */ + __le16 code_page_number; /* code page number */ + __le16 unknown; /* the same as in cp directory */ u8 map[128]; /* upcase table for chars 80..ff */ - u16 zero2; + __le16 zero2; } code_page[3]; u8 incognita[78]; }; @@ -278,8 +278,8 @@ struct code_page_data #define DNODE_MAGIC 0x77e40aae struct dnode { - u32 magic; /* 77e4 0aae */ - u32 first_free; /* offset from start of dnode to + __le32 magic; /* 77e4 0aae */ + __le32 first_free; /* offset from start of dnode to first free dir entry */ #ifdef __LITTLE_ENDIAN u8 root_dnode: 1; /* Is it root dnode? */ @@ -293,14 +293,14 @@ struct dnode { u8 root_dnode: 1; /* Is it root dnode? */ #endif u8 increment_me2[3]; - secno up; /* (root dnode) directory's fnode + __le32 up; /* (root dnode) directory's fnode (nonroot) parent dnode */ - dnode_secno self; /* pointer to this dnode */ + __le32 self; /* pointer to this dnode */ u8 dirent[2028]; /* one or more dirents */ }; struct hpfs_dirent { - u16 length; /* offset to next dirent */ + __le16 length; /* offset to next dirent */ #ifdef __LITTLE_ENDIAN u8 first: 1; /* set on phony ^A^A (".") entry */ @@ -346,12 +346,12 @@ struct hpfs_dirent { u8 read_only: 1; /* dos attrib */ #endif - fnode_secno fnode; /* fnode giving allocation info */ - time32_t write_date; /* mtime */ - u32 file_size; /* file length, bytes */ - time32_t read_date; /* atime */ - time32_t creation_date; /* ctime */ - u32 ea_size; /* total EA length, bytes */ + __le32 fnode; /* fnode giving allocation info */ + __le32 write_date; /* mtime */ + __le32 file_size; /* file length, bytes */ + __le32 read_date; /* atime */ + __le32 creation_date; /* ctime */ + __le32 ea_size; /* total EA length, bytes */ u8 no_of_acls; /* number of ACL's (low 3 bits) */ u8 ix; /* code page index (of filename), see struct code_page_data */ @@ -375,50 +375,36 @@ struct hpfs_dirent { struct bplus_leaf_node { - u32 file_secno; /* first file sector in extent */ - u32 length; /* length, sectors */ - secno disk_secno; /* first corresponding disk sector */ + __le32 file_secno; /* first file sector in extent */ + __le32 length; /* length, sectors */ + __le32 disk_secno; /* first corresponding disk sector */ }; struct bplus_internal_node { - u32 file_secno; /* subtree maps sectors < this */ - anode_secno down; /* pointer to subtree */ + __le32 file_secno; /* subtree maps sectors < this */ + __le32 down; /* pointer to subtree */ }; +enum { + BP_hbff = 1, + BP_fnode_parent = 0x20, + BP_binary_search = 0x40, + BP_internal = 0x80 +}; struct bplus_header { -#ifdef __LITTLE_ENDIAN - u8 hbff: 1; /* high bit of first free entry offset */ - u8 flag1234: 4; - u8 fnode_parent: 1; /* ? we're pointed to by an fnode, - the data btree or some ea or the - main ea bootage pointer ea_secno */ - /* also can get set in fnodes, which - may be a chkdsk glitch or may mean - this bit is irrelevant in fnodes, - or this interpretation is all wet */ - u8 binary_search: 1; /* suggest binary search (unused) */ - u8 internal: 1; /* 1 -> (internal) tree of anodes - 0 -> (leaf) list of extents */ -#else - u8 internal: 1; /* 1 -> (internal) tree of anodes - 0 -> (leaf) list of extents */ - u8 binary_search: 1; /* suggest binary search (unused) */ - u8 fnode_parent: 1; /* ? we're pointed to by an fnode, + u8 flags; /* bit 0 - high bit of first free entry offset + bit 5 - we're pointed to by an fnode, the data btree or some ea or the - main ea bootage pointer ea_secno */ - /* also can get set in fnodes, which - may be a chkdsk glitch or may mean - this bit is irrelevant in fnodes, - or this interpretation is all wet */ - u8 flag1234: 4; - u8 hbff: 1; /* high bit of first free entry offset */ -#endif + main ea bootage pointer ea_secno + bit 6 - suggest binary search (unused) + bit 7 - 1 -> (internal) tree of anodes + 0 -> (leaf) list of extents */ u8 fill[3]; u8 n_free_nodes; /* free nodes in following array */ u8 n_used_nodes; /* used nodes in following array */ - u16 first_free; /* offset from start of header to + __le16 first_free; /* offset from start of header to first free node in array */ union { struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving @@ -428,6 +414,16 @@ struct bplus_header } u; }; +static inline bool bp_internal(struct bplus_header *bp) +{ + return bp->flags & BP_internal; +} + +static inline bool bp_fnode_parent(struct bplus_header *bp) +{ + return bp->flags & BP_fnode_parent; +} + /* fnode: root of allocation b+ tree, and EA's */ /* Every file and every directory has one fnode, pointed to by the directory @@ -436,62 +432,56 @@ struct bplus_header #define FNODE_MAGIC 0xf7e40aae +enum {FNODE_anode = cpu_to_le16(2), FNODE_dir = cpu_to_le16(256)}; struct fnode { - u32 magic; /* f7e4 0aae */ - u32 zero1[2]; /* read history */ + __le32 magic; /* f7e4 0aae */ + __le32 zero1[2]; /* read history */ u8 len, name[15]; /* true length, truncated name */ - fnode_secno up; /* pointer to file's directory fnode */ - secno acl_size_l; - secno acl_secno; - u16 acl_size_s; + __le32 up; /* pointer to file's directory fnode */ + __le32 acl_size_l; + __le32 acl_secno; + __le16 acl_size_s; u8 acl_anode; u8 zero2; /* history bit count */ - u32 ea_size_l; /* length of disk-resident ea's */ - secno ea_secno; /* first sector of disk-resident ea's*/ - u16 ea_size_s; /* length of fnode-resident ea's */ - -#ifdef __LITTLE_ENDIAN - u8 flag0: 1; - u8 ea_anode: 1; /* 1 -> ea_secno is an anode */ - u8 flag234567: 6; -#else - u8 flag234567: 6; - u8 ea_anode: 1; /* 1 -> ea_secno is an anode */ - u8 flag0: 1; -#endif + __le32 ea_size_l; /* length of disk-resident ea's */ + __le32 ea_secno; /* first sector of disk-resident ea's*/ + __le16 ea_size_s; /* length of fnode-resident ea's */ -#ifdef __LITTLE_ENDIAN - u8 dirflag: 1; /* 1 -> directory. first & only extent - points to dnode. */ - u8 flag9012345: 7; -#else - u8 flag9012345: 7; - u8 dirflag: 1; /* 1 -> directory. first & only extent + __le16 flags; /* bit 1 set -> ea_secno is an anode */ + /* bit 8 set -> directory. first & only extent points to dnode. */ -#endif - struct bplus_header btree; /* b+ tree, 8 extents or 12 subtrees */ union { struct bplus_leaf_node external[8]; struct bplus_internal_node internal[12]; } u; - u32 file_size; /* file length, bytes */ - u32 n_needea; /* number of EA's with NEEDEA set */ + __le32 file_size; /* file length, bytes */ + __le32 n_needea; /* number of EA's with NEEDEA set */ u8 user_id[16]; /* unused */ - u16 ea_offs; /* offset from start of fnode + __le16 ea_offs; /* offset from start of fnode to first fnode-resident ea */ u8 dasd_limit_treshhold; u8 dasd_limit_delta; - u32 dasd_limit; - u32 dasd_usage; + __le32 dasd_limit; + __le32 dasd_usage; u8 ea[316]; /* zero or more EA's, packed together with no alignment padding. (Do not use this name, get here via fnode + ea_offs. I think.) */ }; +static inline bool fnode_in_anode(struct fnode *p) +{ + return (p->flags & FNODE_anode) != 0; +} + +static inline bool fnode_is_dir(struct fnode *p) +{ + return (p->flags & FNODE_dir) != 0; +} + /* anode: 99.44% pure allocation tree */ @@ -499,9 +489,9 @@ struct fnode struct anode { - u32 magic; /* 37e4 0aae */ - anode_secno self; /* pointer to this anode */ - secno up; /* parent anode or fnode */ + __le32 magic; /* 37e4 0aae */ + __le32 self; /* pointer to this anode */ + __le32 up; /* parent anode or fnode */ struct bplus_header btree; /* b+tree, 40 extents or 60 subtrees */ union { @@ -509,7 +499,7 @@ struct anode struct bplus_internal_node internal[60]; } u; - u32 fill[3]; /* unused */ + __le32 fill[3]; /* unused */ }; @@ -528,32 +518,23 @@ struct anode run, or in multiple runs. Flags in the fnode tell whether the EA list is immediate, in a single run, or in multiple runs. */ +enum {EA_indirect = 1, EA_anode = 2, EA_needea = 128 }; struct extended_attribute { -#ifdef __LITTLE_ENDIAN - u8 indirect: 1; /* 1 -> value gives sector number + u8 flags; /* bit 0 set -> value gives sector number where real value starts */ - u8 anode: 1; /* 1 -> sector is an anode + /* bit 1 set -> sector is an anode that points to fragmented value */ - u8 flag23456: 5; - u8 needea: 1; /* required ea */ -#else - u8 needea: 1; /* required ea */ - u8 flag23456: 5; - u8 anode: 1; /* 1 -> sector is an anode - that points to fragmented value */ - u8 indirect: 1; /* 1 -> value gives sector number - where real value starts */ -#endif + /* bit 7 set -> required ea */ u8 namelen; /* length of name, bytes */ u8 valuelen_lo; /* length of value, bytes */ u8 valuelen_hi; /* length of value, bytes */ - u8 name[0]; + u8 name[]; /* u8 name[namelen]; ascii attrib name u8 nul; terminating '\0', not counted u8 value[valuelen]; value, arbitrary - if this.indirect, valuelen is 8 and the value is + if this.flags & 1, valuelen is 8 and the value is u32 length; real length of value, bytes secno secno; sector address where it starts if this.anode, the above sector number is the root of an anode tree @@ -561,6 +542,16 @@ struct extended_attribute */ }; +static inline bool ea_indirect(struct extended_attribute *ea) +{ + return ea->flags & EA_indirect; +} + +static inline bool ea_in_anode(struct extended_attribute *ea) +{ + return ea->flags & EA_anode; +} + /* Local Variables: comment-column: 40 diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index de946170ebb..c07ef1f1ced 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -35,13 +35,6 @@ #define CHKCOND(x,y) if (!(x)) printk y -#ifdef DBG -#define PRINTK(x) printk x -#else -#undef PRINTK -#define PRINTK(x) -#endif - struct hpfs_inode_info { loff_t mmu_private; ino_t i_parent_dir; /* (directories) gives fnode of parent dir */ @@ -82,7 +75,7 @@ struct hpfs_sb_info { unsigned char *sb_cp_table; /* code page tables: */ /* 128 bytes uppercasing table & */ /* 128 bytes lowercasing table */ - unsigned *sb_bmp_dir; /* main bitmap directory */ + __le32 *sb_bmp_dir; /* main bitmap directory */ unsigned sb_c_bitmap; /* current bitmap */ unsigned sb_max_fwd_alloc; /* max forwad allocation */ int sb_timeshift; @@ -100,7 +93,7 @@ struct quad_buffer_head { static inline dnode_secno de_down_pointer (struct hpfs_dirent *de) { CHKCOND(de->down,("HPFS: de_down_pointer: !de->down\n")); - return le32_to_cpu(*(dnode_secno *) ((void *) de + le16_to_cpu(de->length) - 4)); + return le32_to_cpu(*(__le32 *) ((void *) de + le16_to_cpu(de->length) - 4)); } /* The first dir entry in a dnode */ @@ -148,12 +141,12 @@ static inline struct extended_attribute *next_ea(struct extended_attribute *ea) static inline secno ea_sec(struct extended_attribute *ea) { - return le32_to_cpu(get_unaligned((secno *)((char *)ea + 9 + ea->namelen))); + return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 9 + ea->namelen))); } static inline secno ea_len(struct extended_attribute *ea) { - return le32_to_cpu(get_unaligned((secno *)((char *)ea + 5 + ea->namelen))); + return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 5 + ea->namelen))); } static inline char *ea_data(struct extended_attribute *ea) @@ -178,7 +171,7 @@ static inline void copy_de(struct hpfs_dirent *dst, struct hpfs_dirent *src) dst->not_8x3 = n; } -static inline unsigned tstbits(u32 *bmp, unsigned b, unsigned n) +static inline unsigned tstbits(__le32 *bmp, unsigned b, unsigned n) { int i; if ((b >= 0x4000) || (b + n - 1 >= 0x4000)) return n; @@ -275,10 +268,10 @@ void hpfs_evict_inode(struct inode *); /* map.c */ -unsigned *hpfs_map_dnode_bitmap(struct super_block *, struct quad_buffer_head *); -unsigned *hpfs_map_bitmap(struct super_block *, unsigned, struct quad_buffer_head *, char *); +__le32 *hpfs_map_dnode_bitmap(struct super_block *, struct quad_buffer_head *); +__le32 *hpfs_map_bitmap(struct super_block *, unsigned, struct quad_buffer_head *, char *); unsigned char *hpfs_load_code_page(struct super_block *, secno); -secno *hpfs_load_bitmap_directory(struct super_block *, secno bmp); +__le32 *hpfs_load_bitmap_directory(struct super_block *, secno bmp); struct fnode *hpfs_map_fnode(struct super_block *s, ino_t, struct buffer_head **); struct anode *hpfs_map_anode(struct super_block *s, anode_secno, struct buffer_head **); struct dnode *hpfs_map_dnode(struct super_block *s, dnode_secno, struct quad_buffer_head *); diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c index 3b2cec29972..ed671e0ea78 100644 --- a/fs/hpfs/inode.c +++ b/fs/hpfs/inode.c @@ -110,7 +110,7 @@ void hpfs_read_inode(struct inode *i) } } } - if (fnode->dirflag) { + if (fnode_is_dir(fnode)) { int n_dnodes, n_subdirs; i->i_mode |= S_IFDIR; i->i_op = &hpfs_dir_iops; @@ -299,7 +299,7 @@ void hpfs_write_if_changed(struct inode *inode) void hpfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (!inode->i_nlink) { hpfs_lock(inode->i_sb); hpfs_remove_fnode(inode->i_sb, inode->i_ino); diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index a790821366a..4acb19d7835 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -8,12 +8,12 @@ #include "hpfs_fn.h" -unsigned *hpfs_map_dnode_bitmap(struct super_block *s, struct quad_buffer_head *qbh) +__le32 *hpfs_map_dnode_bitmap(struct super_block *s, struct quad_buffer_head *qbh) { return hpfs_map_4sectors(s, hpfs_sb(s)->sb_dmap, qbh, 0); } -unsigned int *hpfs_map_bitmap(struct super_block *s, unsigned bmp_block, +__le32 *hpfs_map_bitmap(struct super_block *s, unsigned bmp_block, struct quad_buffer_head *qbh, char *id) { secno sec; @@ -89,18 +89,18 @@ unsigned char *hpfs_load_code_page(struct super_block *s, secno cps) return cp_table; } -secno *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) +__le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) { struct buffer_head *bh; int n = (hpfs_sb(s)->sb_fs_size + 0x200000 - 1) >> 21; int i; - secno *b; + __le32 *b; if (!(b = kmalloc(n * 512, GFP_KERNEL))) { printk("HPFS: can't allocate memory for bitmap directory\n"); return NULL; } for (i=0;i<n;i++) { - secno *d = hpfs_map_sector(s, bmp+i, &bh, n - i - 1); + __le32 *d = hpfs_map_sector(s, bmp+i, &bh, n - i - 1); if (!d) { kfree(b); return NULL; @@ -130,16 +130,16 @@ struct fnode *hpfs_map_fnode(struct super_block *s, ino_t ino, struct buffer_hea (unsigned long)ino); goto bail; } - if (!fnode->dirflag) { + if (!fnode_is_dir(fnode)) { if ((unsigned)fnode->btree.n_used_nodes + (unsigned)fnode->btree.n_free_nodes != - (fnode->btree.internal ? 12 : 8)) { + (bp_internal(&fnode->btree) ? 12 : 8)) { hpfs_error(s, "bad number of nodes in fnode %08lx", (unsigned long)ino); goto bail; } if (le16_to_cpu(fnode->btree.first_free) != - 8 + fnode->btree.n_used_nodes * (fnode->btree.internal ? 8 : 12)) { + 8 + fnode->btree.n_used_nodes * (bp_internal(&fnode->btree) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in fnode %08lx", (unsigned long)ino); @@ -187,12 +187,12 @@ struct anode *hpfs_map_anode(struct super_block *s, anode_secno ano, struct buff goto bail; } if ((unsigned)anode->btree.n_used_nodes + (unsigned)anode->btree.n_free_nodes != - (anode->btree.internal ? 60 : 40)) { + (bp_internal(&anode->btree) ? 60 : 40)) { hpfs_error(s, "bad number of nodes in anode %08x", ano); goto bail; } if (le16_to_cpu(anode->btree.first_free) != - 8 + anode->btree.n_used_nodes * (anode->btree.internal ? 8 : 12)) { + 8 + anode->btree.n_used_nodes * (bp_internal(&anode->btree) ? 8 : 12)) { hpfs_error(s, "bad first_free pointer in anode %08x", ano); goto bail; } diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 30dd7b10b50..9083ef8af58 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -70,7 +70,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) fnode->len = len; memcpy(fnode->name, name, len > 15 ? 15 : len); fnode->up = cpu_to_le32(dir->i_ino); - fnode->dirflag = 1; + fnode->flags |= FNODE_dir; fnode->btree.n_free_nodes = 7; fnode->btree.n_used_nodes = 1; fnode->btree.first_free = cpu_to_le16(0x14); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 54f6eccb79d..706a12c083e 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -572,7 +572,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) mark_buffer_dirty(bh2); } - if (le32_to_cpu(spareblock->hotfixes_used) || le32_to_cpu(spareblock->n_spares_used)) { + if (spareblock->hotfixes_used || spareblock->n_spares_used) { if (errs >= 2) { printk("HPFS: Hotfixes not supported here, try chkdsk\n"); mark_dirty(s, 0); @@ -645,7 +645,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) root->i_mtime.tv_nsec = 0; root->i_ctime.tv_sec = local_to_gmt(s, le32_to_cpu(de->creation_date)); root->i_ctime.tv_nsec = 0; - hpfs_i(root)->i_ea_size = le16_to_cpu(de->ea_size); + hpfs_i(root)->i_ea_size = le32_to_cpu(de->ea_size); hpfs_i(root)->i_parent_dir = root->i_ino; if (root->i_size == -1) root->i_size = 2048; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index a80e45a690a..d4f93b52cec 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -614,7 +614,7 @@ static struct inode *hppfs_alloc_inode(struct super_block *sb) void hppfs_evict_inode(struct inode *ino) { - end_writeback(ino); + clear_inode(ino); dput(HPPFS_I(ino)->proc_dentry); mntput(ino->i_sb->s_fs_info); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 28cf06e4ec8..cc9281b6c62 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -393,7 +393,7 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart) static void hugetlbfs_evict_inode(struct inode *inode) { truncate_hugepages(inode, 0); - end_writeback(inode); + clear_inode(inode); } static inline void @@ -485,6 +485,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); + lockdep_annotate_inode_mutex_key(inode); } return inode; } diff --git a/fs/inode.c b/fs/inode.c index 9f4f5fecc09..c99163b1b31 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -135,8 +135,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fop = &empty_fops; inode->__i_nlink = 1; inode->i_opflags = 0; - inode->i_uid = 0; - inode->i_gid = 0; + i_uid_write(inode, 0); + i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_blocks = 0; @@ -486,7 +486,7 @@ void __remove_inode_hash(struct inode *inode) } EXPORT_SYMBOL(__remove_inode_hash); -void end_writeback(struct inode *inode) +void clear_inode(struct inode *inode) { might_sleep(); /* @@ -500,11 +500,10 @@ void end_writeback(struct inode *inode) BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); - inode_sync_wait(inode); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } -EXPORT_SYMBOL(end_writeback); +EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected @@ -531,12 +530,20 @@ static void evict(struct inode *inode) inode_sb_list_del(inode); + /* + * Wait for flusher thread to be done with the inode so that filesystem + * does not start destroying it while writeback is still running. Since + * the inode has I_FREEING set, flusher thread won't start new work on + * the inode. We just have to wait for running writeback to finish. + */ + inode_wait_for_writeback(inode); + if (op->evict_inode) { op->evict_inode(inode); } else { if (inode->i_data.nrpages) truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); @@ -1480,10 +1487,30 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, return 0; } +/* + * This does the actual work of updating an inodes time or version. Must have + * had called mnt_want_write() before calling this. + */ +static int update_time(struct inode *inode, struct timespec *time, int flags) +{ + if (inode->i_op->update_time) + return inode->i_op->update_time(inode, time, flags); + + if (flags & S_ATIME) + inode->i_atime = *time; + if (flags & S_VERSION) + inode_inc_iversion(inode); + if (flags & S_CTIME) + inode->i_ctime = *time; + if (flags & S_MTIME) + inode->i_mtime = *time; + mark_inode_dirty_sync(inode); + return 0; +} + /** * touch_atime - update the access time - * @mnt: mount the inode is accessed on - * @dentry: dentry accessed + * @path: the &struct path to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, @@ -1518,12 +1545,83 @@ void touch_atime(struct path *path) if (mnt_want_write(mnt)) return; - inode->i_atime = now; - mark_inode_dirty_sync(inode); + /* + * File systems can error out when updating inodes if they need to + * allocate new space to modify an inode (such is the case for + * Btrfs), but since we touch atime while walking down the path we + * really don't care if we failed to update the atime of the file, + * so just ignore the return value. + */ + update_time(inode, &now, S_ATIME); mnt_drop_write(mnt); } EXPORT_SYMBOL(touch_atime); +/* + * The logic we want is + * + * if suid or (sgid and xgrp) + * remove privs + */ +int should_remove_suid(struct dentry *dentry) +{ + umode_t mode = dentry->d_inode->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) + return kill; + + return 0; +} +EXPORT_SYMBOL(should_remove_suid); + +static int __remove_suid(struct dentry *dentry, int kill) +{ + struct iattr newattrs; + + newattrs.ia_valid = ATTR_FORCE | kill; + return notify_change(dentry, &newattrs); +} + +int file_remove_suid(struct file *file) +{ + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = dentry->d_inode; + int killsuid; + int killpriv; + int error = 0; + + /* Fast path for nothing security related */ + if (IS_NOSEC(inode)) + return 0; + + killsuid = should_remove_suid(dentry); + killpriv = security_inode_need_killpriv(dentry); + + if (killpriv < 0) + return killpriv; + if (killpriv) + error = security_inode_killpriv(dentry); + if (!error && killsuid) + error = __remove_suid(dentry, killsuid); + if (!error && (inode->i_sb->s_flags & MS_NOSEC)) + inode->i_flags |= S_NOSEC; + + return error; +} +EXPORT_SYMBOL(file_remove_suid); + /** * file_update_time - update mtime and ctime time * @file: file accessed @@ -1533,18 +1631,20 @@ EXPORT_SYMBOL(touch_atime); * usage in the file write path of filesystems, and filesystems may * choose to explicitly ignore update via this function with the * S_NOCMTIME inode flag, e.g. for network filesystem where these - * timestamps are handled by the server. + * timestamps are handled by the server. This can return an error for + * file systems who need to allocate space in order to update an inode. */ -void file_update_time(struct file *file) +int file_update_time(struct file *file) { struct inode *inode = file->f_path.dentry->d_inode; struct timespec now; - enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0; + int sync_it = 0; + int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) - return; + return 0; now = current_fs_time(inode->i_sb); if (!timespec_equal(&inode->i_mtime, &now)) @@ -1557,21 +1657,16 @@ void file_update_time(struct file *file) sync_it |= S_VERSION; if (!sync_it) - return; + return 0; /* Finally allowed to write? Takes lock. */ if (mnt_want_write_file(file)) - return; + return 0; - /* Only change inode inside the lock region */ - if (sync_it & S_VERSION) - inode_inc_iversion(inode); - if (sync_it & S_CTIME) - inode->i_ctime = now; - if (sync_it & S_MTIME) - inode->i_mtime = now; - mark_inode_dirty_sync(inode); + ret = update_time(inode, &now, sync_it); mnt_drop_write_file(file); + + return ret; } EXPORT_SYMBOL(file_update_time); @@ -1647,6 +1742,7 @@ void __init inode_init_early(void) HASH_EARLY, &i_hash_shift, &i_hash_mask, + 0, 0); for (loop = 0; loop < (1U << i_hash_shift); loop++) @@ -1677,6 +1773,7 @@ void __init inode_init(void) 0, &i_hash_shift, &i_hash_mask, + 0, 0); for (loop = 0; loop < (1U << i_hash_shift); loop++) @@ -1732,12 +1829,57 @@ EXPORT_SYMBOL(inode_init_owner); */ bool inode_owner_or_capable(const struct inode *inode) { - struct user_namespace *ns = inode_userns(inode); - - if (current_user_ns() == ns && current_fsuid() == inode->i_uid) + if (uid_eq(current_fsuid(), inode->i_uid)) return true; - if (ns_capable(ns, CAP_FOWNER)) + if (inode_capable(inode, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); + +/* + * Direct i/o helper functions + */ +static void __inode_dio_wait(struct inode *inode) +{ + wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); + DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); + + do { + prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE); + if (atomic_read(&inode->i_dio_count)) + schedule(); + } while (atomic_read(&inode->i_dio_count)); + finish_wait(wq, &q.wait); +} + +/** + * inode_dio_wait - wait for outstanding DIO requests to finish + * @inode: inode to wait for + * + * Waits for all pending direct I/O requests to finish so that we can + * proceed with a truncate or equivalent operation. + * + * Must be called under a lock that serializes taking new references + * to i_dio_count, usually by inode->i_mutex. + */ +void inode_dio_wait(struct inode *inode) +{ + if (atomic_read(&inode->i_dio_count)) + __inode_dio_wait(inode); +} +EXPORT_SYMBOL(inode_dio_wait); + +/* + * inode_dio_done - signal finish of a direct I/O requests + * @inode: inode the direct I/O happens on + * + * This is called once we've finished processing a direct I/O request, + * and is used to wake up callers waiting for direct I/O to be quiesced. + */ +void inode_dio_done(struct inode *inode) +{ + if (atomic_dec_and_test(&inode->i_dio_count)) + wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); +} +EXPORT_SYMBOL(inode_dio_done); diff --git a/fs/internal.h b/fs/internal.h index 9962c59ba28..18bc216ea09 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -56,7 +56,7 @@ extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); -DECLARE_BRLOCK(vfsmount_lock); +extern struct lglock vfsmount_lock; /* @@ -100,6 +100,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *, extern long do_handle_open(int mountdirfd, struct file_handle __user *ufh, int open_flag); +extern int open_check_o_direct(struct file *f); /* * inode.c diff --git a/fs/ioprio.c b/fs/ioprio.c index 0f1b9515213..e50170ca7c3 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -37,8 +37,8 @@ int set_task_ioprio(struct task_struct *task, int ioprio) rcu_read_lock(); tcred = __task_cred(task); - if (tcred->uid != cred->euid && - tcred->uid != cred->uid && !capable(CAP_SYS_NICE)) { + if (!uid_eq(tcred->uid, cred->euid) && + !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); return -EPERM; } @@ -50,7 +50,7 @@ int set_task_ioprio(struct task_struct *task, int ioprio) ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE); if (ioc) { - ioc_ioprio_changed(ioc, ioprio); + ioc->ioprio = ioprio; put_io_context(ioc); } @@ -65,6 +65,7 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) struct task_struct *p, *g; struct user_struct *user; struct pid *pgrp; + kuid_t uid; int ret; switch (class) { @@ -110,16 +111,19 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: + uid = make_kuid(current_user_ns(), who); + if (!uid_valid(uid)) + break; if (!who) user = current_user(); else - user = find_user(who); + user = find_user(uid); if (!user) break; do_each_thread(g, p) { - if (__task_cred(p)->uid != who) + if (!uid_eq(task_uid(p), uid)) continue; ret = set_task_ioprio(p, ioprio); if (ret) @@ -174,6 +178,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) struct task_struct *g, *p; struct user_struct *user; struct pid *pgrp; + kuid_t uid; int ret = -ESRCH; int tmpio; @@ -203,16 +208,17 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: + uid = make_kuid(current_user_ns(), who); if (!who) user = current_user(); else - user = find_user(who); + user = find_user(uid); if (!user) break; do_each_thread(g, p) { - if (__task_cred(p)->uid != user->uid) + if (!uid_eq(task_uid(p), user->uid)) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/fs/isofs/export.c b/fs/isofs/export.c index dd4687ff30d..aa4356d09ee 100644 --- a/fs/isofs/export.c +++ b/fs/isofs/export.c @@ -107,12 +107,11 @@ static struct dentry *isofs_export_get_parent(struct dentry *child) } static int -isofs_export_encode_fh(struct dentry *dentry, +isofs_export_encode_fh(struct inode *inode, __u32 *fh32, int *max_len, - int connectable) + struct inode *parent) { - struct inode * inode = dentry->d_inode; struct iso_inode_info * ei = ISOFS_I(inode); int len = *max_len; int type = 1; @@ -124,7 +123,7 @@ isofs_export_encode_fh(struct dentry *dentry, * offset of the inode and the upper 16 bits of fh32[1] to * hold the offset of the parent. */ - if (connectable && (len < 5)) { + if (parent && (len < 5)) { *max_len = 5; return 255; } else if (len < 3) { @@ -136,16 +135,12 @@ isofs_export_encode_fh(struct dentry *dentry, fh32[0] = ei->i_iget5_block; fh16[2] = (__u16)ei->i_iget5_offset; /* fh16 [sic] */ fh32[2] = inode->i_generation; - if (connectable && !S_ISDIR(inode->i_mode)) { - struct inode *parent; + if (parent) { struct iso_inode_info *eparent; - spin_lock(&dentry->d_lock); - parent = dentry->d_parent->d_inode; eparent = ISOFS_I(parent); fh32[3] = eparent->i_iget5_block; fh16[3] = (__u16)eparent->i_iget5_offset; /* fh16 [sic] */ fh32[4] = parent->i_generation; - spin_unlock(&dentry->d_lock); len = 5; type = 2; } diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c index 05f0754f2b4..08c03044abd 100644 --- a/fs/jbd/checkpoint.c +++ b/fs/jbd/checkpoint.c @@ -508,20 +508,19 @@ int cleanup_journal_tail(journal_t *journal) /* * We need to make sure that any blocks that were recently written out * --- perhaps by log_do_checkpoint() --- are flushed out before we - * drop the transactions from the journal. It's unlikely this will be - * necessary, especially with an appropriately sized journal, but we - * need this to guarantee correctness. Fortunately - * cleanup_journal_tail() doesn't get called all that often. + * drop the transactions from the journal. Similarly we need to be sure + * superblock makes it to disk before next transaction starts reusing + * freed space (otherwise we could replay some blocks of the new + * transaction thinking they belong to the old one). So we use + * WRITE_FLUSH_FUA. It's unlikely this will be necessary, especially + * with an appropriately sized journal, but we need this to guarantee + * correctness. Fortunately cleanup_journal_tail() doesn't get called + * all that often. */ - if (journal->j_flags & JFS_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + journal_update_sb_log_tail(journal, first_tid, blocknr, + WRITE_FLUSH_FUA); spin_lock(&journal->j_state_lock); - if (!tid_gt(first_tid, journal->j_tail_sequence)) { - spin_unlock(&journal->j_state_lock); - /* Someone else cleaned up journal so return 0 */ - return 0; - } /* OK, update the superblock to recover the freed space. * Physical blocks come first: have we wrapped beyond the end of * the log? */ @@ -539,8 +538,6 @@ int cleanup_journal_tail(journal_t *journal) journal->j_tail_sequence = first_tid; journal->j_tail = blocknr; spin_unlock(&journal->j_state_lock); - if (!(journal->j_flags & JFS_ABORT)) - journal_update_superblock(journal, 1); return 0; } diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index f2b9a571f4c..52c15c77602 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -298,6 +298,7 @@ void journal_commit_transaction(journal_t *journal) int tag_flag; int i; struct blk_plug plug; + int write_op = WRITE; /* * First job: lock down the current transaction and wait for @@ -307,7 +308,16 @@ void journal_commit_transaction(journal_t *journal) /* Do we need to erase the effects of a prior journal_flush? */ if (journal->j_flags & JFS_FLUSHED) { jbd_debug(3, "super block updated\n"); - journal_update_superblock(journal, 1); + mutex_lock(&journal->j_checkpoint_mutex); + /* + * We hold j_checkpoint_mutex so tail cannot change under us. + * We don't need any special data guarantees for writing sb + * since journal is empty and it is ok for write to be + * flushed only with transaction commit. + */ + journal_update_sb_log_tail(journal, journal->j_tail_sequence, + journal->j_tail, WRITE_SYNC); + mutex_unlock(&journal->j_checkpoint_mutex); } else { jbd_debug(3, "superblock not updated\n"); } @@ -413,13 +423,16 @@ void journal_commit_transaction(journal_t *journal) jbd_debug (3, "JBD: commit phase 2\n"); + if (tid_geq(journal->j_commit_waited, commit_transaction->t_tid)) + write_op = WRITE_SYNC; + /* * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ blk_start_plug(&plug); err = journal_submit_data_buffers(journal, commit_transaction, - WRITE_SYNC); + write_op); blk_finish_plug(&plug); /* @@ -478,7 +491,7 @@ void journal_commit_transaction(journal_t *journal) blk_start_plug(&plug); - journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC); + journal_write_revoke_records(journal, commit_transaction, write_op); /* * If we found any dirty or locked buffers, then we should have @@ -649,7 +662,7 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(WRITE_SYNC, bh); + submit_bh(write_op, bh); } cond_resched(); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 0971e921780..425c2f2cf17 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -563,6 +563,8 @@ int log_wait_commit(journal_t *journal, tid_t tid) spin_unlock(&journal->j_state_lock); #endif spin_lock(&journal->j_state_lock); + if (!tid_geq(journal->j_commit_waited, tid)) + journal->j_commit_waited = tid; while (tid_gt(tid, journal->j_commit_sequence)) { jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n", tid, journal->j_commit_sequence); @@ -921,8 +923,33 @@ static int journal_reset(journal_t *journal) journal->j_max_transaction_buffers = journal->j_maxlen / 4; - /* Add the dynamic fields and write it to disk. */ - journal_update_superblock(journal, 1); + /* + * As a special case, if the on-disk copy is already marked as needing + * no recovery (s_start == 0), then we can safely defer the superblock + * update until the next commit by setting JFS_FLUSHED. This avoids + * attempting a write to a potential-readonly device. + */ + if (sb->s_start == 0) { + jbd_debug(1,"JBD: Skipping superblock update on recovered sb " + "(start %u, seq %d, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, + journal->j_errno); + journal->j_flags |= JFS_FLUSHED; + } else { + /* Lock here to make assertions happy... */ + mutex_lock(&journal->j_checkpoint_mutex); + /* + * Update log tail information. We use WRITE_FUA since new + * transaction will start reusing journal space and so we + * must make sure information about current log tail is on + * disk before that. + */ + journal_update_sb_log_tail(journal, + journal->j_tail_sequence, + journal->j_tail, + WRITE_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } return journal_start_thread(journal); } @@ -999,35 +1026,15 @@ int journal_create(journal_t *journal) return journal_reset(journal); } -/** - * void journal_update_superblock() - Update journal sb on disk. - * @journal: The journal to update. - * @wait: Set to '0' if you don't want to wait for IO completion. - * - * Update a journal's dynamic superblock fields and write it to disk, - * optionally waiting for the IO to complete. - */ -void journal_update_superblock(journal_t *journal, int wait) +static void journal_write_superblock(journal_t *journal, int write_op) { - journal_superblock_t *sb = journal->j_superblock; struct buffer_head *bh = journal->j_sb_buffer; + int ret; - /* - * As a special case, if the on-disk copy is already marked as needing - * no recovery (s_start == 0) and there are no outstanding transactions - * in the filesystem, then we can safely defer the superblock update - * until the next commit by setting JFS_FLUSHED. This avoids - * attempting a write to a potential-readonly device. - */ - if (sb->s_start == 0 && journal->j_tail_sequence == - journal->j_transaction_sequence) { - jbd_debug(1,"JBD: Skipping superblock update on recovered sb " - "(start %u, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, - journal->j_errno); - goto out; - } - + trace_journal_write_superblock(journal, write_op); + if (!(journal->j_flags & JFS_BARRIER)) + write_op &= ~(REQ_FUA | REQ_FLUSH); + lock_buffer(bh); if (buffer_write_io_error(bh)) { char b[BDEVNAME_SIZE]; /* @@ -1045,42 +1052,100 @@ void journal_update_superblock(journal_t *journal, int wait) set_buffer_uptodate(bh); } + get_bh(bh); + bh->b_end_io = end_buffer_write_sync; + ret = submit_bh(write_op, bh); + wait_on_buffer(bh); + if (buffer_write_io_error(bh)) { + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + ret = -EIO; + } + if (ret) { + char b[BDEVNAME_SIZE]; + printk(KERN_ERR "JBD: Error %d detected " + "when updating journal superblock for %s.\n", + ret, journal_dev_name(journal, b)); + } +} + +/** + * journal_update_sb_log_tail() - Update log tail in journal sb on disk. + * @journal: The journal to update. + * @tail_tid: TID of the new transaction at the tail of the log + * @tail_block: The first block of the transaction at the tail of the log + * @write_op: With which operation should we write the journal sb + * + * Update a journal's superblock information about log tail and write it to + * disk, waiting for the IO to complete. + */ +void journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, + unsigned int tail_block, int write_op) +{ + journal_superblock_t *sb = journal->j_superblock; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + jbd_debug(1,"JBD: updating superblock (start %u, seq %u)\n", + tail_block, tail_tid); + + sb->s_sequence = cpu_to_be32(tail_tid); + sb->s_start = cpu_to_be32(tail_block); + + journal_write_superblock(journal, write_op); + + /* Log is no longer empty */ + spin_lock(&journal->j_state_lock); + WARN_ON(!sb->s_sequence); + journal->j_flags &= ~JFS_FLUSHED; + spin_unlock(&journal->j_state_lock); +} + +/** + * mark_journal_empty() - Mark on disk journal as empty. + * @journal: The journal to update. + * + * Update a journal's dynamic superblock fields to show that journal is empty. + * Write updated superblock to disk waiting for IO to complete. + */ +static void mark_journal_empty(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); spin_lock(&journal->j_state_lock); - jbd_debug(1,"JBD: updating superblock (start %u, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, journal->j_errno); + jbd_debug(1, "JBD: Marking journal as empty (seq %d)\n", + journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); - sb->s_start = cpu_to_be32(journal->j_tail); - sb->s_errno = cpu_to_be32(journal->j_errno); + sb->s_start = cpu_to_be32(0); spin_unlock(&journal->j_state_lock); - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - if (wait) { - sync_dirty_buffer(bh); - if (buffer_write_io_error(bh)) { - char b[BDEVNAME_SIZE]; - printk(KERN_ERR "JBD: I/O error detected " - "when updating journal superblock for %s.\n", - journal_dev_name(journal, b)); - clear_buffer_write_io_error(bh); - set_buffer_uptodate(bh); - } - } else - write_dirty_buffer(bh, WRITE); + journal_write_superblock(journal, WRITE_FUA); - trace_jbd_update_superblock_end(journal, wait); -out: - /* If we have just flushed the log (by marking s_start==0), then - * any future commit will have to be careful to update the - * superblock again to re-record the true start of the log. */ + spin_lock(&journal->j_state_lock); + /* Log is empty */ + journal->j_flags |= JFS_FLUSHED; + spin_unlock(&journal->j_state_lock); +} + +/** + * journal_update_sb_errno() - Update error in the journal. + * @journal: The journal to update. + * + * Update a journal's errno. Write updated superblock to disk waiting for IO + * to complete. + */ +static void journal_update_sb_errno(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; spin_lock(&journal->j_state_lock); - if (sb->s_start) - journal->j_flags &= ~JFS_FLUSHED; - else - journal->j_flags |= JFS_FLUSHED; + jbd_debug(1, "JBD: updating superblock error (errno %d)\n", + journal->j_errno); + sb->s_errno = cpu_to_be32(journal->j_errno); spin_unlock(&journal->j_state_lock); + + journal_write_superblock(journal, WRITE_SYNC); } /* @@ -1251,6 +1316,8 @@ int journal_destroy(journal_t *journal) /* Force any old transactions to disk */ + /* We cannot race with anybody but must keep assertions happy */ + mutex_lock(&journal->j_checkpoint_mutex); /* Totally anal locking here... */ spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { @@ -1266,16 +1333,14 @@ int journal_destroy(journal_t *journal) if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { - /* We can now mark the journal as empty. */ - journal->j_tail = 0; journal->j_tail_sequence = ++journal->j_transaction_sequence; - journal_update_superblock(journal, 1); - } else { + mark_journal_empty(journal); + } else err = -EIO; - } brelse(journal->j_sb_buffer); } + mutex_unlock(&journal->j_checkpoint_mutex); if (journal->j_inode) iput(journal->j_inode); @@ -1455,7 +1520,6 @@ int journal_flush(journal_t *journal) { int err = 0; transaction_t *transaction = NULL; - unsigned int old_tail; spin_lock(&journal->j_state_lock); @@ -1490,6 +1554,7 @@ int journal_flush(journal_t *journal) if (is_journal_aborted(journal)) return -EIO; + mutex_lock(&journal->j_checkpoint_mutex); cleanup_journal_tail(journal); /* Finally, mark the journal as really needing no recovery. @@ -1497,14 +1562,9 @@ int journal_flush(journal_t *journal) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ + mark_journal_empty(journal); + mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_state_lock); - old_tail = journal->j_tail; - journal->j_tail = 0; - spin_unlock(&journal->j_state_lock); - journal_update_superblock(journal, 1); - spin_lock(&journal->j_state_lock); - journal->j_tail = old_tail; - J_ASSERT(!journal->j_running_transaction); J_ASSERT(!journal->j_committing_transaction); J_ASSERT(!journal->j_checkpoint_transactions); @@ -1544,8 +1604,12 @@ int journal_wipe(journal_t *journal, int write) write ? "Clearing" : "Ignoring"); err = journal_skip_recovery(journal); - if (write) - journal_update_superblock(journal, 1); + if (write) { + /* Lock to make assertions happy... */ + mutex_lock(&journal->j_checkpoint_mutex); + mark_journal_empty(journal); + mutex_unlock(&journal->j_checkpoint_mutex); + } no_recovery: return err; @@ -1613,7 +1677,7 @@ static void __journal_abort_soft (journal_t *journal, int errno) __journal_abort_hard(journal); if (errno) - journal_update_superblock(journal, 1); + journal_update_sb_errno(journal); } /** diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index b2a7e5244e3..febc10db5ce 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1433,8 +1433,6 @@ int journal_stop(handle_t *handle) } } - if (handle->h_sync) - transaction->t_synchronous_commit = 1; current->journal_info = NULL; spin_lock(&journal->j_state_lock); spin_lock(&transaction->t_handle_lock); diff --git a/fs/jbd2/Kconfig b/fs/jbd2/Kconfig index f32f346f4b0..69a48c2944d 100644 --- a/fs/jbd2/Kconfig +++ b/fs/jbd2/Kconfig @@ -1,6 +1,8 @@ config JBD2 tristate select CRC32 + select CRYPTO + select CRYPTO_CRC32C help This is a generic journaling layer for block devices that support both 32-bit and 64-bit block numbers. It is currently used by diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 806525a7269..216f4299f65 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -85,6 +85,24 @@ nope: __brelse(bh); } +static void jbd2_commit_block_csum_set(journal_t *j, + struct journal_head *descriptor) +{ + struct commit_header *h; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + h = (struct commit_header *)(jh2bh(descriptor)->b_data); + h->h_chksum_type = 0; + h->h_chksum_size = 0; + h->h_chksum[0] = 0; + csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, + j->j_blocksize); + h->h_chksum[0] = cpu_to_be32(csum); +} + /* * Done it all: now submit the commit record. We should have * cleaned up our previous buffers by now, so if we are in abort @@ -128,6 +146,7 @@ static int journal_submit_commit_record(journal_t *journal, tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); } + jbd2_commit_block_csum_set(journal, descriptor); JBUFFER_TRACE(descriptor, "submit commit block"); lock_buffer(bh); @@ -301,6 +320,44 @@ static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } +static void jbd2_descr_block_csum_set(journal_t *j, + struct journal_head *descriptor) +{ + struct jbd2_journal_block_tail *tail; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + tail = (struct jbd2_journal_block_tail *) + (jh2bh(descriptor)->b_data + j->j_blocksize - + sizeof(struct jbd2_journal_block_tail)); + tail->t_checksum = 0; + csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, + j->j_blocksize); + tail->t_checksum = cpu_to_be32(csum); +} + +static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag, + struct buffer_head *bh, __u32 sequence) +{ + struct page *page = bh->b_page; + __u8 *addr; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + sequence = cpu_to_be32(sequence); + addr = kmap_atomic(page, KM_USER0); + csum = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, + sizeof(sequence)); + csum = jbd2_chksum(j, csum, addr + offset_in_page(bh->b_data), + bh->b_size); + kunmap_atomic(addr, KM_USER0); + + tag->t_checksum = cpu_to_be32(csum); +} /* * jbd2_journal_commit_transaction * @@ -334,6 +391,10 @@ void jbd2_journal_commit_transaction(journal_t *journal) unsigned long first_block; tid_t first_tid; int update_tail; + int csum_size = 0; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + csum_size = sizeof(struct jbd2_journal_block_tail); /* * First job: lock down the current transaction and wait for @@ -627,7 +688,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) tag = (journal_block_tag_t *) tagp; write_tag_block(tag_bytes, tag, jh2bh(jh)->b_blocknr); - tag->t_flags = cpu_to_be32(tag_flag); + tag->t_flags = cpu_to_be16(tag_flag); + jbd2_block_tag_csum_set(journal, tag, jh2bh(new_jh), + commit_transaction->t_tid); tagp += tag_bytes; space_left -= tag_bytes; @@ -643,7 +706,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) if (bufs == journal->j_wbufsize || commit_transaction->t_buffers == NULL || - space_left < tag_bytes + 16) { + space_left < tag_bytes + 16 + csum_size) { jbd_debug(4, "JBD2: Submit %d IOs\n", bufs); @@ -651,8 +714,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) submitting the IOs. "tag" still points to the last tag we set up. */ - tag->t_flags |= cpu_to_be32(JBD2_FLAG_LAST_TAG); + tag->t_flags |= cpu_to_be16(JBD2_FLAG_LAST_TAG); + jbd2_descr_block_csum_set(journal, descriptor); start_journal_io: for (i = 0; i < bufs; i++) { struct buffer_head *bh = wbuf[i]; @@ -723,7 +787,7 @@ start_journal_io: if (commit_transaction->t_need_data_flush && (journal->j_fs_dev != journal->j_dev) && (journal->j_flags & JBD2_BARRIER)) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL); /* Done it all: now write the commit record asynchronously. */ if (JBD2_HAS_INCOMPAT_FEATURE(journal, @@ -859,7 +923,7 @@ wait_for_iobuf: if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT) && journal->j_flags & JBD2_BARRIER) { - blkdev_issue_flush(journal->j_dev, GFP_KERNEL, NULL); + blkdev_issue_flush(journal->j_dev, GFP_NOFS, NULL); } if (err) diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 1afb701622b..e9a3c4c8559 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -97,6 +97,43 @@ EXPORT_SYMBOL(jbd2_inode_cache); static void __journal_abort_soft (journal_t *journal, int errno); static int jbd2_journal_create_slab(size_t slab_size); +/* Checksumming functions */ +int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; +} + +static __u32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) +{ + __u32 csum, old_csum; + + old_csum = sb->s_checksum; + sb->s_checksum = 0; + csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t)); + sb->s_checksum = old_csum; + + return cpu_to_be32(csum); +} + +int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + return sb->s_checksum == jbd2_superblock_csum(j, sb); +} + +void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + sb->s_checksum = jbd2_superblock_csum(j, sb); +} + /* * Helper function used to manage commit timeouts */ @@ -1348,6 +1385,7 @@ static void jbd2_journal_update_sb_errno(journal_t *journal) jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", journal->j_errno); sb->s_errno = cpu_to_be32(journal->j_errno); + jbd2_superblock_csum_set(journal, sb); read_unlock(&journal->j_state_lock); jbd2_write_superblock(journal, WRITE_SYNC); @@ -1376,6 +1414,9 @@ static int journal_get_superblock(journal_t *journal) } } + if (buffer_verified(bh)) + return 0; + sb = journal->j_superblock; err = -EINVAL; @@ -1413,6 +1454,43 @@ static int journal_get_superblock(journal_t *journal) goto out; } + if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + /* Can't have checksum v1 and v2 on at the same time! */ + printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 " + "at the same time!\n"); + goto out; + } + + if (!jbd2_verify_csum_type(journal, sb)) { + printk(KERN_ERR "JBD: Unknown checksum type\n"); + goto out; + } + + /* Load the checksum driver */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD: Cannot load crc32c driver.\n"); + err = PTR_ERR(journal->j_chksum_driver); + journal->j_chksum_driver = NULL; + goto out; + } + } + + /* Check superblock checksum */ + if (!jbd2_superblock_csum_verify(journal, sb)) { + printk(KERN_ERR "JBD: journal checksum error\n"); + goto out; + } + + /* Precompute checksum seed for all metadata */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + + set_buffer_verified(bh); + return 0; out: @@ -1564,6 +1642,8 @@ int jbd2_journal_destroy(journal_t *journal) iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); + if (journal->j_chksum_driver) + crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); kfree(journal); @@ -1653,6 +1733,10 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com int jbd2_journal_set_features (journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { +#define INCOMPAT_FEATURE_ON(f) \ + ((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f))) +#define COMPAT_FEATURE_ON(f) \ + ((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f))) journal_superblock_t *sb; if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) @@ -1661,16 +1745,54 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; + /* Asking for checksumming v2 and v1? Only give them v2. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 && + compat & JBD2_FEATURE_COMPAT_CHECKSUM) + compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; + jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; + /* If enabling v2 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + sb->s_checksum_type = JBD2_CRC32C_CHKSUM; + sb->s_feature_compat &= + ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); + + /* Load the checksum driver */ + if (journal->j_chksum_driver == NULL) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", + 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD: Cannot load crc32c " + "driver.\n"); + journal->j_chksum_driver = NULL; + return 0; + } + } + + /* Precompute checksum seed for all metadata */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_CSUM_V2)) + journal->j_csum_seed = jbd2_chksum(journal, ~0, + sb->s_uuid, + sizeof(sb->s_uuid)); + } + + /* If enabling v1 checksums, downgrade superblock */ + if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) + sb->s_feature_incompat &= + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2); + sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); return 1; +#undef COMPAT_FEATURE_ON +#undef INCOMPAT_FEATURE_ON } /* @@ -1975,10 +2097,16 @@ int jbd2_journal_blocks_per_page(struct inode *inode) */ size_t journal_tag_bytes(journal_t *journal) { + journal_block_tag_t tag; + size_t x = 0; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + x += sizeof(tag.t_checksum); + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return JBD2_TAG_SIZE64; + return x + JBD2_TAG_SIZE64; else - return JBD2_TAG_SIZE32; + return x + JBD2_TAG_SIZE32; } /* diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index c1a03354a22..0131e436253 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -174,6 +174,25 @@ static int jread(struct buffer_head **bhp, journal_t *journal, return 0; } +static int jbd2_descr_block_csum_verify(journal_t *j, + void *buf) +{ + struct jbd2_journal_block_tail *tail; + __u32 provided, calculated; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + tail = (struct jbd2_journal_block_tail *)(buf + j->j_blocksize - + sizeof(struct jbd2_journal_block_tail)); + provided = tail->t_checksum; + tail->t_checksum = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); + tail->t_checksum = provided; + + provided = be32_to_cpu(provided); + return provided == calculated; +} /* * Count the number of in-use tags in a journal descriptor block. @@ -186,6 +205,9 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) int nr = 0, size = journal->j_blocksize; int tag_bytes = journal_tag_bytes(journal); + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + size -= sizeof(struct jbd2_journal_block_tail); + tagp = &bh->b_data[sizeof(journal_header_t)]; while ((tagp - bh->b_data + tag_bytes) <= size) { @@ -193,10 +215,10 @@ static int count_tags(journal_t *journal, struct buffer_head *bh) nr++; tagp += tag_bytes; - if (!(tag->t_flags & cpu_to_be32(JBD2_FLAG_SAME_UUID))) + if (!(tag->t_flags & cpu_to_be16(JBD2_FLAG_SAME_UUID))) tagp += 16; - if (tag->t_flags & cpu_to_be32(JBD2_FLAG_LAST_TAG)) + if (tag->t_flags & cpu_to_be16(JBD2_FLAG_LAST_TAG)) break; } @@ -353,6 +375,41 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh, return 0; } +static int jbd2_commit_block_csum_verify(journal_t *j, void *buf) +{ + struct commit_header *h; + __u32 provided, calculated; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + h = buf; + provided = h->h_chksum[0]; + h->h_chksum[0] = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); + h->h_chksum[0] = provided; + + provided = be32_to_cpu(provided); + return provided == calculated; +} + +static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag, + void *buf, __u32 sequence) +{ + __u32 provided, calculated; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + sequence = cpu_to_be32(sequence); + calculated = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence, + sizeof(sequence)); + calculated = jbd2_chksum(j, calculated, buf, j->j_blocksize); + provided = be32_to_cpu(tag->t_checksum); + + return provided == cpu_to_be32(calculated); +} + static int do_one_pass(journal_t *journal, struct recovery_info *info, enum passtype pass) { @@ -366,6 +423,7 @@ static int do_one_pass(journal_t *journal, int blocktype; int tag_bytes = journal_tag_bytes(journal); __u32 crc32_sum = ~0; /* Transactional Checksums */ + int descr_csum_size = 0; /* * First thing is to establish what we expect to find in the log @@ -451,6 +509,18 @@ static int do_one_pass(journal_t *journal, switch(blocktype) { case JBD2_DESCRIPTOR_BLOCK: + /* Verify checksum first */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_CSUM_V2)) + descr_csum_size = + sizeof(struct jbd2_journal_block_tail); + if (descr_csum_size > 0 && + !jbd2_descr_block_csum_verify(journal, + bh->b_data)) { + err = -EIO; + goto failed; + } + /* If it is a valid descriptor block, replay it * in pass REPLAY; if journal_checksums enabled, then * calculate checksums in PASS_SCAN, otherwise, @@ -481,11 +551,11 @@ static int do_one_pass(journal_t *journal, tagp = &bh->b_data[sizeof(journal_header_t)]; while ((tagp - bh->b_data + tag_bytes) - <= journal->j_blocksize) { + <= journal->j_blocksize - descr_csum_size) { unsigned long io_block; tag = (journal_block_tag_t *) tagp; - flags = be32_to_cpu(tag->t_flags); + flags = be16_to_cpu(tag->t_flags); io_block = next_log_block++; wrap(journal, next_log_block); @@ -516,6 +586,19 @@ static int do_one_pass(journal_t *journal, goto skip_write; } + /* Look for block corruption */ + if (!jbd2_block_tag_csum_verify( + journal, tag, obh->b_data, + be32_to_cpu(tmp->h_sequence))) { + brelse(obh); + success = -EIO; + printk(KERN_ERR "JBD: Invalid " + "checksum recovering " + "block %llu in log\n", + blocknr); + continue; + } + /* Find a buffer for the new * data being restored */ nbh = __getblk(journal->j_fs_dev, @@ -650,6 +733,19 @@ static int do_one_pass(journal_t *journal, } crc32_sum = ~0; } + if (pass == PASS_SCAN && + !jbd2_commit_block_csum_verify(journal, + bh->b_data)) { + info->end_transaction = next_commit_ID; + + if (!JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) { + journal->j_failed_commit = + next_commit_ID; + brelse(bh); + break; + } + } brelse(bh); next_commit_ID++; continue; @@ -706,6 +802,25 @@ static int do_one_pass(journal_t *journal, return err; } +static int jbd2_revoke_block_csum_verify(journal_t *j, + void *buf) +{ + struct jbd2_journal_revoke_tail *tail; + __u32 provided, calculated; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + tail = (struct jbd2_journal_revoke_tail *)(buf + j->j_blocksize - + sizeof(struct jbd2_journal_revoke_tail)); + provided = tail->r_checksum; + tail->r_checksum = 0; + calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize); + tail->r_checksum = provided; + + provided = be32_to_cpu(provided); + return provided == calculated; +} /* Scan a revoke record, marking all blocks mentioned as revoked. */ @@ -720,6 +835,9 @@ static int scan_revoke_records(journal_t *journal, struct buffer_head *bh, offset = sizeof(jbd2_journal_revoke_header_t); max = be32_to_cpu(header->r_count); + if (!jbd2_revoke_block_csum_verify(journal, header)) + return -EINVAL; + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) record_len = 8; diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 6973705d6a3..f30b80b4ce8 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -578,6 +578,7 @@ static void write_one_revoke_record(journal_t *journal, struct jbd2_revoke_record_s *record, int write_op) { + int csum_size = 0; struct journal_head *descriptor; int offset; journal_header_t *header; @@ -592,9 +593,13 @@ static void write_one_revoke_record(journal_t *journal, descriptor = *descriptorp; offset = *offsetp; + /* Do we need to leave space at the end for a checksum? */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + csum_size = sizeof(struct jbd2_journal_revoke_tail); + /* Make sure we have a descriptor with space left for the record */ if (descriptor) { - if (offset == journal->j_blocksize) { + if (offset >= journal->j_blocksize - csum_size) { flush_descriptor(journal, descriptor, offset, write_op); descriptor = NULL; } @@ -631,6 +636,24 @@ static void write_one_revoke_record(journal_t *journal, *offsetp = offset; } +static void jbd2_revoke_csum_set(journal_t *j, + struct journal_head *descriptor) +{ + struct jbd2_journal_revoke_tail *tail; + __u32 csum; + + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + tail = (struct jbd2_journal_revoke_tail *) + (jh2bh(descriptor)->b_data + j->j_blocksize - + sizeof(struct jbd2_journal_revoke_tail)); + tail->r_checksum = 0; + csum = jbd2_chksum(j, j->j_csum_seed, jh2bh(descriptor)->b_data, + j->j_blocksize); + tail->r_checksum = cpu_to_be32(csum); +} + /* * Flush a revoke descriptor out to the journal. If we are aborting, * this is a noop; otherwise we are generating a buffer which needs to @@ -652,6 +675,8 @@ static void flush_descriptor(journal_t *journal, header = (jbd2_journal_revoke_header_t *) jh2bh(descriptor)->b_data; header->r_count = cpu_to_be32(offset); + jbd2_revoke_csum_set(journal, descriptor); + set_buffer_jwrite(bh); BUFFER_TRACE(bh, "write"); set_buffer_dirty(bh); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ddcd3549c6c..fb1ab9533b6 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -162,8 +162,8 @@ static int start_this_handle(journal_t *journal, handle_t *handle, alloc_transaction: if (!journal->j_running_transaction) { - new_transaction = kmem_cache_alloc(transaction_cache, - gfp_mask | __GFP_ZERO); + new_transaction = kmem_cache_zalloc(transaction_cache, + gfp_mask); if (!new_transaction) { /* * If __GFP_FS is not present, then we may be diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index bb6f993ebca..3d3092eda81 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -240,7 +240,7 @@ void jffs2_evict_inode (struct inode *inode) jffs2_dbg(1, "%s(): ino #%lu mode %o\n", __func__, inode->i_ino, inode->i_mode); truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); jffs2_do_clear_inode(c, f); } diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c index ad271c70aa2..5a2dec2b064 100644 --- a/fs/jffs2/gc.c +++ b/fs/jffs2/gc.c @@ -234,8 +234,8 @@ int jffs2_garbage_collect_pass(struct jffs2_sb_info *c) return 0; jffs2_dbg(1, "No progress from erasing block; doing GC anyway\n"); - spin_lock(&c->erase_completion_lock); mutex_lock(&c->alloc_sem); + spin_lock(&c->erase_completion_lock); } /* First, work out which block we're garbage-collecting */ diff --git a/fs/jffs2/jffs2_fs_sb.h b/fs/jffs2/jffs2_fs_sb.h index 55a0c1dcead..413ef89c2d1 100644 --- a/fs/jffs2/jffs2_fs_sb.h +++ b/fs/jffs2/jffs2_fs_sb.h @@ -32,6 +32,13 @@ struct jffs2_inodirty; struct jffs2_mount_opts { bool override_compr; unsigned int compr; + + /* The size of the reserved pool. The reserved pool is the JFFS2 flash + * space which may only be used by root cannot be used by the other + * users. This is implemented simply by means of not allowing the + * latter users to write to the file system if the amount if the + * available space is less then 'rp_size'. */ + unsigned int rp_size; }; /* A struct for the overall file system control. Pointers to @@ -126,6 +133,10 @@ struct jffs2_sb_info { struct jffs2_inodirty *wbuf_inodes; struct rw_semaphore wbuf_sem; /* Protects the write buffer */ + struct delayed_work wbuf_dwork; /* write-buffer write-out work */ + int wbuf_queued; /* non-zero delayed work is queued */ + spinlock_t wbuf_dwork_lock; /* protects wbuf_dwork and and wbuf_queued */ + unsigned char *oobbuf; int oobavail; /* How many bytes are available for JFFS2 in OOB */ #endif diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c index 6784d1e7a7e..0c96eb52c79 100644 --- a/fs/jffs2/nodemgmt.c +++ b/fs/jffs2/nodemgmt.c @@ -18,6 +18,37 @@ #include "nodelist.h" #include "debug.h" +/* + * Check whether the user is allowed to write. + */ +static int jffs2_rp_can_write(struct jffs2_sb_info *c) +{ + uint32_t avail; + struct jffs2_mount_opts *opts = &c->mount_opts; + + avail = c->dirty_size + c->free_size + c->unchecked_size + + c->erasing_size - c->resv_blocks_write * c->sector_size + - c->nospc_dirty_size; + + if (avail < 2 * opts->rp_size) + jffs2_dbg(1, "rpsize %u, dirty_size %u, free_size %u, " + "erasing_size %u, unchecked_size %u, " + "nr_erasing_blocks %u, avail %u, resrv %u\n", + opts->rp_size, c->dirty_size, c->free_size, + c->erasing_size, c->unchecked_size, + c->nr_erasing_blocks, avail, c->nospc_dirty_size); + + if (avail > opts->rp_size) + return 1; + + /* Always allow root */ + if (capable(CAP_SYS_RESOURCE)) + return 1; + + jffs2_dbg(1, "forbid writing\n"); + return 0; +} + /** * jffs2_reserve_space - request physical space to write nodes to flash * @c: superblock info @@ -55,6 +86,15 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, spin_lock(&c->erase_completion_lock); + /* + * Check if the free space is greater then size of the reserved pool. + * If not, only allow root to proceed with writing. + */ + if (prio != ALLOC_DELETION && !jffs2_rp_can_write(c)) { + ret = -ENOSPC; + goto out; + } + /* this needs a little more thought (true <tglx> :)) */ while(ret == -EAGAIN) { while(c->nr_free_blocks + c->nr_erasing_blocks < blocksneeded) { @@ -158,6 +198,8 @@ int jffs2_reserve_space(struct jffs2_sb_info *c, uint32_t minsize, jffs2_dbg(1, "%s(): ret is %d\n", __func__, ret); } } + +out: spin_unlock(&c->erase_completion_lock); if (!ret) ret = jffs2_prealloc_raw_node_refs(c, c->nextblock, 1); diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 1cd3aec9d9a..bcd983d7e7f 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -95,6 +95,7 @@ static inline void jffs2_init_inode_info(struct jffs2_inode_info *f) #define jffs2_ubivol(c) (0) #define jffs2_ubivol_setup(c) (0) #define jffs2_ubivol_cleanup(c) do {} while (0) +#define jffs2_dirty_trigger(c) do {} while (0) #else /* NAND and/or ECC'd NOR support present */ @@ -135,14 +136,10 @@ void jffs2_ubivol_cleanup(struct jffs2_sb_info *c); #define jffs2_nor_wbuf_flash(c) (c->mtd->type == MTD_NORFLASH && ! (c->mtd->flags & MTD_BIT_WRITEABLE)) int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c); void jffs2_nor_wbuf_flash_cleanup(struct jffs2_sb_info *c); +void jffs2_dirty_trigger(struct jffs2_sb_info *c); #endif /* WRITEBUFFER */ -static inline void jffs2_dirty_trigger(struct jffs2_sb_info *c) -{ - OFNI_BS_2SFFJ(c)->s_dirt = 1; -} - /* background.c */ int jffs2_start_garbage_collect_thread(struct jffs2_sb_info *c); void jffs2_stop_garbage_collect_thread(struct jffs2_sb_info *c); diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index dc0437e8476..1ea349fff68 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -1266,19 +1266,25 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c, /* Symlink's inode data is the target path. Read it and * keep in RAM to facilitate quick follow symlink * operation. */ - f->target = kmalloc(je32_to_cpu(latest_node->csize) + 1, GFP_KERNEL); + uint32_t csize = je32_to_cpu(latest_node->csize); + if (csize > JFFS2_MAX_NAME_LEN) { + mutex_unlock(&f->sem); + jffs2_do_clear_inode(c, f); + return -ENAMETOOLONG; + } + f->target = kmalloc(csize + 1, GFP_KERNEL); if (!f->target) { - JFFS2_ERROR("can't allocate %d bytes of memory for the symlink target path cache\n", je32_to_cpu(latest_node->csize)); + JFFS2_ERROR("can't allocate %u bytes of memory for the symlink target path cache\n", csize); mutex_unlock(&f->sem); jffs2_do_clear_inode(c, f); return -ENOMEM; } ret = jffs2_flash_read(c, ref_offset(rii.latest_ref) + sizeof(*latest_node), - je32_to_cpu(latest_node->csize), &retlen, (char *)f->target); + csize, &retlen, (char *)f->target); - if (ret || retlen != je32_to_cpu(latest_node->csize)) { - if (retlen != je32_to_cpu(latest_node->csize)) + if (ret || retlen != csize) { + if (retlen != csize) ret = -EIO; kfree(f->target); f->target = NULL; @@ -1287,7 +1293,7 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c, return ret; } - f->target[je32_to_cpu(latest_node->csize)] = '\0'; + f->target[csize] = '\0'; dbg_readinode("symlink's target '%s' cached\n", f->target); } @@ -1415,6 +1421,7 @@ int jffs2_do_crccheck_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *i mutex_unlock(&f->sem); jffs2_do_clear_inode(c, f); } + jffs2_xattr_do_crccheck_inode(c, ic); kfree (f); return ret; } diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index f9916f312bd..61ea41389f9 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -63,21 +63,6 @@ static void jffs2_i_init_once(void *foo) inode_init_once(&f->vfs_inode); } -static void jffs2_write_super(struct super_block *sb) -{ - struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); - - lock_super(sb); - sb->s_dirt = 0; - - if (!(sb->s_flags & MS_RDONLY)) { - jffs2_dbg(1, "%s()\n", __func__); - jffs2_flush_wbuf_gc(c, 0); - } - - unlock_super(sb); -} - static const char *jffs2_compr_name(unsigned int compr) { switch (compr) { @@ -105,6 +90,8 @@ static int jffs2_show_options(struct seq_file *s, struct dentry *root) if (opts->override_compr) seq_printf(s, ",compr=%s", jffs2_compr_name(opts->compr)); + if (opts->rp_size) + seq_printf(s, ",rp_size=%u", opts->rp_size / 1024); return 0; } @@ -113,8 +100,6 @@ static int jffs2_sync_fs(struct super_block *sb, int wait) { struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); - jffs2_write_super(sb); - mutex_lock(&c->alloc_sem); jffs2_flush_wbuf_pad(c); mutex_unlock(&c->alloc_sem); @@ -171,15 +156,18 @@ static const struct export_operations jffs2_export_ops = { * JFFS2 mount options. * * Opt_override_compr: override default compressor + * Opt_rp_size: size of reserved pool in KiB * Opt_err: just end of array marker */ enum { Opt_override_compr, + Opt_rp_size, Opt_err, }; static const match_table_t tokens = { {Opt_override_compr, "compr=%s"}, + {Opt_rp_size, "rp_size=%u"}, {Opt_err, NULL}, }; @@ -187,6 +175,7 @@ static int jffs2_parse_options(struct jffs2_sb_info *c, char *data) { substring_t args[MAX_OPT_ARGS]; char *p, *name; + unsigned int opt; if (!data) return 0; @@ -224,6 +213,17 @@ static int jffs2_parse_options(struct jffs2_sb_info *c, char *data) kfree(name); c->mount_opts.override_compr = true; break; + case Opt_rp_size: + if (match_int(&args[0], &opt)) + return -EINVAL; + opt *= 1024; + if (opt > c->mtd->size) { + pr_warn("Too large reserve pool specified, max " + "is %llu KB\n", c->mtd->size / 1024); + return -EINVAL; + } + c->mount_opts.rp_size = opt; + break; default: pr_err("Error: unrecognized mount option '%s' or missing value\n", p); @@ -251,7 +251,6 @@ static const struct super_operations jffs2_super_operations = .alloc_inode = jffs2_alloc_inode, .destroy_inode =jffs2_destroy_inode, .put_super = jffs2_put_super, - .write_super = jffs2_write_super, .statfs = jffs2_statfs, .remount_fs = jffs2_remount_fs, .evict_inode = jffs2_evict_inode, @@ -319,9 +318,6 @@ static void jffs2_put_super (struct super_block *sb) jffs2_dbg(2, "%s()\n", __func__); - if (sb->s_dirt) - jffs2_write_super(sb); - mutex_lock(&c->alloc_sem); jffs2_flush_wbuf_pad(c); mutex_unlock(&c->alloc_sem); diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index 74d9be19df3..6f4529d3697 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -20,6 +20,7 @@ #include <linux/mtd/nand.h> #include <linux/jiffies.h> #include <linux/sched.h> +#include <linux/writeback.h> #include "nodelist.h" @@ -85,7 +86,7 @@ static void jffs2_wbuf_dirties_inode(struct jffs2_sb_info *c, uint32_t ino) { struct jffs2_inodirty *new; - /* Mark the superblock dirty so that kupdated will flush... */ + /* Schedule delayed write-buffer write-out */ jffs2_dirty_trigger(c); if (jffs2_wbuf_pending_for_ino(c, ino)) @@ -1148,6 +1149,47 @@ int jffs2_write_nand_badblock(struct jffs2_sb_info *c, struct jffs2_eraseblock * return 1; } +static struct jffs2_sb_info *work_to_sb(struct work_struct *work) +{ + struct delayed_work *dwork; + + dwork = container_of(work, struct delayed_work, work); + return container_of(dwork, struct jffs2_sb_info, wbuf_dwork); +} + +static void delayed_wbuf_sync(struct work_struct *work) +{ + struct jffs2_sb_info *c = work_to_sb(work); + struct super_block *sb = OFNI_BS_2SFFJ(c); + + spin_lock(&c->wbuf_dwork_lock); + c->wbuf_queued = 0; + spin_unlock(&c->wbuf_dwork_lock); + + if (!(sb->s_flags & MS_RDONLY)) { + jffs2_dbg(1, "%s()\n", __func__); + jffs2_flush_wbuf_gc(c, 0); + } +} + +void jffs2_dirty_trigger(struct jffs2_sb_info *c) +{ + struct super_block *sb = OFNI_BS_2SFFJ(c); + unsigned long delay; + + if (sb->s_flags & MS_RDONLY) + return; + + spin_lock(&c->wbuf_dwork_lock); + if (!c->wbuf_queued) { + jffs2_dbg(1, "%s()\n", __func__); + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &c->wbuf_dwork, delay); + c->wbuf_queued = 1; + } + spin_unlock(&c->wbuf_dwork_lock); +} + int jffs2_nand_flash_setup(struct jffs2_sb_info *c) { struct nand_ecclayout *oinfo = c->mtd->ecclayout; @@ -1169,6 +1211,8 @@ int jffs2_nand_flash_setup(struct jffs2_sb_info *c) /* Initialise write buffer */ init_rwsem(&c->wbuf_sem); + spin_lock_init(&c->wbuf_dwork_lock); + INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1207,8 +1251,8 @@ int jffs2_dataflash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); - - + spin_lock_init(&c->wbuf_dwork_lock); + INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->erasesize; /* Find a suitable c->sector_size @@ -1267,6 +1311,9 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) { /* Initialize write buffer */ init_rwsem(&c->wbuf_sem); + spin_lock_init(&c->wbuf_dwork_lock); + INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); + c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; @@ -1299,6 +1346,8 @@ int jffs2_ubivol_setup(struct jffs2_sb_info *c) { return 0; init_rwsem(&c->wbuf_sem); + spin_lock_init(&c->wbuf_dwork_lock); + INIT_DELAYED_WORK(&c->wbuf_dwork, delayed_wbuf_sync); c->wbuf_pagesize = c->mtd->writesize; c->wbuf_ofs = 0xFFFFFFFF; diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index b55b803eddc..3034e970eb9 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -11,6 +11,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define JFFS2_XATTR_IS_CORRUPTED 1 + #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> @@ -153,7 +155,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n", offset, je32_to_cpu(rx.hdr_crc), crc); xd->flags |= JFFS2_XFLAGS_INVALID; - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; } totlen = PAD(sizeof(rx) + rx.name_len + 1 + je16_to_cpu(rx.value_len)); if (je16_to_cpu(rx.magic) != JFFS2_MAGIC_BITMASK @@ -169,7 +171,7 @@ static int do_verify_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_dat je32_to_cpu(rx.xid), xd->xid, je32_to_cpu(rx.version), xd->version); xd->flags |= JFFS2_XFLAGS_INVALID; - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; } xd->xprefix = rx.xprefix; xd->name_len = rx.name_len; @@ -227,12 +229,12 @@ static int do_load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum data[xd->name_len] = '\0'; crc = crc32(0, data, length); if (crc != xd->data_crc) { - JFFS2_WARNING("node CRC failed (JFFS2_NODETYPE_XREF)" + JFFS2_WARNING("node CRC failed (JFFS2_NODETYPE_XATTR)" " at %#08x, read: 0x%08x calculated: 0x%08x\n", ref_offset(xd->node), xd->data_crc, crc); kfree(data); xd->flags |= JFFS2_XFLAGS_INVALID; - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; } xd->flags |= JFFS2_XFLAGS_HOT; @@ -270,7 +272,7 @@ static int load_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datum *x if (xd->xname) return 0; if (xd->flags & JFFS2_XFLAGS_INVALID) - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; if (unlikely(is_xattr_datum_unchecked(c, xd))) rc = do_verify_xattr_datum(c, xd); if (!rc) @@ -435,6 +437,8 @@ static void unrefer_xattr_datum(struct jffs2_sb_info *c, struct jffs2_xattr_datu * is called to release xattr related objects when unmounting. * check_xattr_ref_inode(c, ic) * is used to confirm inode does not have duplicate xattr name/value pair. + * jffs2_xattr_do_crccheck_inode(c, ic) + * is used to force xattr data integrity check during the initial gc scan. * -------------------------------------------------- */ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref) { @@ -462,7 +466,7 @@ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref if (crc != je32_to_cpu(rr.node_crc)) { JFFS2_ERROR("node CRC failed at %#08x, read=%#08x, calc=%#08x\n", offset, je32_to_cpu(rr.node_crc), crc); - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; } if (je16_to_cpu(rr.magic) != JFFS2_MAGIC_BITMASK || je16_to_cpu(rr.nodetype) != JFFS2_NODETYPE_XREF @@ -472,7 +476,7 @@ static int verify_xattr_ref(struct jffs2_sb_info *c, struct jffs2_xattr_ref *ref offset, je16_to_cpu(rr.magic), JFFS2_MAGIC_BITMASK, je16_to_cpu(rr.nodetype), JFFS2_NODETYPE_XREF, je32_to_cpu(rr.totlen), PAD(sizeof(rr))); - return -EIO; + return JFFS2_XATTR_IS_CORRUPTED; } ref->ino = je32_to_cpu(rr.ino); ref->xid = je32_to_cpu(rr.xid); @@ -682,6 +686,11 @@ static int check_xattr_ref_inode(struct jffs2_sb_info *c, struct jffs2_inode_cac return rc; } +void jffs2_xattr_do_crccheck_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic) +{ + check_xattr_ref_inode(c, ic); +} + /* -------- xattr subsystem functions --------------- * jffs2_init_xattr_subsystem(c) * is used to initialize semaphore and list_head, and some variables. diff --git a/fs/jffs2/xattr.h b/fs/jffs2/xattr.h index 7be4beb306f..467ff376ee2 100644 --- a/fs/jffs2/xattr.h +++ b/fs/jffs2/xattr.h @@ -77,6 +77,7 @@ extern void jffs2_clear_xattr_subsystem(struct jffs2_sb_info *c); extern struct jffs2_xattr_datum *jffs2_setup_xattr_datum(struct jffs2_sb_info *c, uint32_t xid, uint32_t version); +extern void jffs2_xattr_do_crccheck_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic); extern void jffs2_xattr_delete_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic); extern void jffs2_xattr_free_inode(struct jffs2_sb_info *c, struct jffs2_inode_cache *ic); @@ -108,6 +109,7 @@ extern ssize_t jffs2_listxattr(struct dentry *, char *, size_t); #define jffs2_build_xattr_subsystem(c) #define jffs2_clear_xattr_subsystem(c) +#define jffs2_xattr_do_crccheck_inode(c, ic) #define jffs2_xattr_delete_inode(c, ic) #define jffs2_xattr_free_inode(c, ic) #define jffs2_verify_xattr(c) (1) diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 77b69b27f82..4692bf3ca8c 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -169,7 +169,7 @@ void jfs_evict_inode(struct inode *inode) } else { truncate_inode_pages(&inode->i_data, 0); } - end_writeback(inode); + clear_inode(inode); dquot_drop(inode); } diff --git a/fs/libfs.c b/fs/libfs.c index 18d08f5db53..f86ec27a423 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -68,7 +68,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct na int dcache_dir_open(struct inode *inode, struct file *file) { - static struct qstr cursor_name = {.len = 1, .name = "."}; + static struct qstr cursor_name = QSTR_INIT(".", 1); file->private_data = d_alloc(file->f_path.dentry, &cursor_name); @@ -225,7 +225,7 @@ struct dentry *mount_pseudo(struct file_system_type *fs_type, char *name, struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL); struct dentry *dentry; struct inode *root; - struct qstr d_name = {.name = name, .len = strlen(name)}; + struct qstr d_name = QSTR_INIT(name, strlen(name)); if (IS_ERR(s)) return ERR_CAST(s); diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index ba1dc2eebd1..ca0a0800144 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -56,7 +56,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init) u32 nlm_version = (nlm_init->nfs_version == 2) ? 1 : 4; int status; - status = lockd_up(); + status = lockd_up(nlm_init->net); if (status < 0) return ERR_PTR(status); @@ -65,7 +65,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init) nlm_init->hostname, nlm_init->noresvport, nlm_init->net); if (host == NULL) { - lockd_down(); + lockd_down(nlm_init->net); return ERR_PTR(-ENOLCK); } @@ -80,8 +80,10 @@ EXPORT_SYMBOL_GPL(nlmclnt_init); */ void nlmclnt_done(struct nlm_host *host) { + struct net *net = host->net; + nlmclnt_release_host(host); - lockd_down(); + lockd_down(net); } EXPORT_SYMBOL_GPL(nlmclnt_done); @@ -220,11 +222,12 @@ reclaimer(void *ptr) struct nlm_wait *block; struct file_lock *fl, *next; u32 nsmstate; + struct net *net = host->net; allow_signal(SIGKILL); down_write(&host->h_rwsem); - lockd_up(); /* note: this cannot fail as lockd is already running */ + lockd_up(net); /* note: this cannot fail as lockd is already running */ dprintk("lockd: reclaiming locks for host %s\n", host->h_name); @@ -275,6 +278,6 @@ restart: /* Release host handle after use */ nlmclnt_release_host(host); - lockd_down(); + lockd_down(net); return 0; } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index f49b9afc443..80938fda67e 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -251,39 +251,40 @@ out_err: return err; } -static int lockd_up_net(struct net *net) +static int lockd_up_net(struct svc_serv *serv, struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); - struct svc_serv *serv = nlmsvc_rqst->rq_server; int error; - if (ln->nlmsvc_users) + if (ln->nlmsvc_users++) return 0; - error = svc_rpcb_setup(serv, net); + error = svc_bind(serv, net); if (error) - goto err_rpcb; + goto err_bind; error = make_socks(serv, net); if (error < 0) goto err_socks; + dprintk("lockd_up_net: per-net data created; net=%p\n", net); return 0; err_socks: svc_rpcb_cleanup(serv, net); -err_rpcb: +err_bind: + ln->nlmsvc_users--; return error; } -static void lockd_down_net(struct net *net) +static void lockd_down_net(struct svc_serv *serv, struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); - struct svc_serv *serv = nlmsvc_rqst->rq_server; if (ln->nlmsvc_users) { if (--ln->nlmsvc_users == 0) { nlm_shutdown_hosts_net(net); svc_shutdown_net(serv, net); + dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net); } } else { printk(KERN_ERR "lockd_down_net: no users! task=%p, net=%p\n", @@ -292,22 +293,60 @@ static void lockd_down_net(struct net *net) } } -/* - * Bring up the lockd process if it's not already up. - */ -int lockd_up(void) +static int lockd_start_svc(struct svc_serv *serv) +{ + int error; + + if (nlmsvc_rqst) + return 0; + + /* + * Create the kernel thread and wait for it to start. + */ + nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); + if (IS_ERR(nlmsvc_rqst)) { + error = PTR_ERR(nlmsvc_rqst); + printk(KERN_WARNING + "lockd_up: svc_rqst allocation failed, error=%d\n", + error); + goto out_rqst; + } + + svc_sock_update_bufs(serv); + serv->sv_maxconn = nlm_max_connections; + + nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name); + if (IS_ERR(nlmsvc_task)) { + error = PTR_ERR(nlmsvc_task); + printk(KERN_WARNING + "lockd_up: kthread_run failed, error=%d\n", error); + goto out_task; + } + dprintk("lockd_up: service started\n"); + return 0; + +out_task: + svc_exit_thread(nlmsvc_rqst); + nlmsvc_task = NULL; +out_rqst: + nlmsvc_rqst = NULL; + return error; +} + +static struct svc_serv *lockd_create_svc(void) { struct svc_serv *serv; - int error = 0; - struct net *net = current->nsproxy->net_ns; - mutex_lock(&nlmsvc_mutex); /* * Check whether we're already up and running. */ if (nlmsvc_rqst) { - error = lockd_up_net(net); - goto out; + /* + * Note: increase service usage, because later in case of error + * svc_destroy() will be called. + */ + svc_get(nlmsvc_rqst->rq_server); + return nlmsvc_rqst->rq_server; } /* @@ -318,59 +357,53 @@ int lockd_up(void) printk(KERN_WARNING "lockd_up: no pid, %d users??\n", nlmsvc_users); - error = -ENOMEM; serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); - goto out; + return ERR_PTR(-ENOMEM); } + dprintk("lockd_up: service created\n"); + return serv; +} - error = make_socks(serv, net); - if (error < 0) - goto destroy_and_out; +/* + * Bring up the lockd process if it's not already up. + */ +int lockd_up(struct net *net) +{ + struct svc_serv *serv; + int error; - /* - * Create the kernel thread and wait for it to start. - */ - nlmsvc_rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); - if (IS_ERR(nlmsvc_rqst)) { - error = PTR_ERR(nlmsvc_rqst); - nlmsvc_rqst = NULL; - printk(KERN_WARNING - "lockd_up: svc_rqst allocation failed, error=%d\n", - error); - goto destroy_and_out; + mutex_lock(&nlmsvc_mutex); + + serv = lockd_create_svc(); + if (IS_ERR(serv)) { + error = PTR_ERR(serv); + goto err_create; } - svc_sock_update_bufs(serv); - serv->sv_maxconn = nlm_max_connections; + error = lockd_up_net(serv, net); + if (error < 0) + goto err_net; - nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name); - if (IS_ERR(nlmsvc_task)) { - error = PTR_ERR(nlmsvc_task); - svc_exit_thread(nlmsvc_rqst); - nlmsvc_task = NULL; - nlmsvc_rqst = NULL; - printk(KERN_WARNING - "lockd_up: kthread_run failed, error=%d\n", error); - goto destroy_and_out; - } + error = lockd_start_svc(serv); + if (error < 0) + goto err_start; + nlmsvc_users++; /* * Note: svc_serv structures have an initial use count of 1, * so we exit through here on both success and failure. */ -destroy_and_out: +err_net: svc_destroy(serv); -out: - if (!error) { - struct lockd_net *ln = net_generic(net, lockd_net_id); - - ln->nlmsvc_users++; - nlmsvc_users++; - } +err_create: mutex_unlock(&nlmsvc_mutex); return error; + +err_start: + lockd_down_net(serv, net); + goto err_net; } EXPORT_SYMBOL_GPL(lockd_up); @@ -378,14 +411,13 @@ EXPORT_SYMBOL_GPL(lockd_up); * Decrement the user count and bring down lockd if we're the last. */ void -lockd_down(void) +lockd_down(struct net *net) { mutex_lock(&nlmsvc_mutex); + lockd_down_net(nlmsvc_rqst->rq_server, net); if (nlmsvc_users) { - if (--nlmsvc_users) { - lockd_down_net(current->nsproxy->net_ns); + if (--nlmsvc_users) goto out; - } } else { printk(KERN_ERR "lockd_down: no users! task=%p\n", nlmsvc_task); @@ -397,7 +429,9 @@ lockd_down(void) BUG(); } kthread_stop(nlmsvc_task); + dprintk("lockd_down: service stopped\n"); svc_exit_thread(nlmsvc_rqst); + dprintk("lockd_down: service destroyed\n"); nlmsvc_task = NULL; nlmsvc_rqst = NULL; out: diff --git a/fs/locks.c b/fs/locks.c index 0d68f1f8179..814c51d0de4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1446,7 +1446,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) struct inode *inode = dentry->d_inode; int error; - if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE)) + if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; @@ -1636,12 +1636,13 @@ EXPORT_SYMBOL(flock_lock_file_wait); SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { struct file *filp; + int fput_needed; struct file_lock *lock; int can_sleep, unlock; int error; error = -EBADF; - filp = fget(fd); + filp = fget_light(fd, &fput_needed); if (!filp) goto out; @@ -1674,7 +1675,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) locks_free_lock(lock); out_putf: - fput(filp); + fput_light(filp, fput_needed); out: return error; } diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index e3ab5e5a904..f1cb512c501 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -2175,7 +2175,7 @@ void logfs_evict_inode(struct inode *inode) } } truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); /* Cheaper version of write_inode. All changes are concealed in * aliases, which are moved back. No write to the medium happens. diff --git a/fs/minix/inode.c b/fs/minix/inode.c index fcb05d2c6b5..2a503ad020d 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -32,7 +32,7 @@ static void minix_evict_inode(struct inode *inode) minix_truncate(inode); } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); if (!inode->i_nlink) minix_free_inode(inode); } diff --git a/fs/namei.c b/fs/namei.c index 0062dd17eb5..7d694194024 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -16,6 +16,7 @@ #include <linux/init.h> #include <linux/export.h> +#include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/namei.h> @@ -116,47 +117,37 @@ * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ -static int do_getname(const char __user *filename, char *page) -{ - int retval; - unsigned long len = PATH_MAX; - - if (!segment_eq(get_fs(), KERNEL_DS)) { - if ((unsigned long) filename >= TASK_SIZE) - return -EFAULT; - if (TASK_SIZE - (unsigned long) filename < PATH_MAX) - len = TASK_SIZE - (unsigned long) filename; - } - - retval = strncpy_from_user(page, filename, len); - if (retval > 0) { - if (retval < len) - return 0; - return -ENAMETOOLONG; - } else if (!retval) - retval = -ENOENT; - return retval; -} - static char *getname_flags(const char __user *filename, int flags, int *empty) { - char *result = __getname(); - int retval; + char *result = __getname(), *err; + int len; - if (!result) + if (unlikely(!result)) return ERR_PTR(-ENOMEM); - retval = do_getname(filename, result); - if (retval < 0) { - if (retval == -ENOENT && empty) + len = strncpy_from_user(result, filename, PATH_MAX); + err = ERR_PTR(len); + if (unlikely(len < 0)) + goto error; + + /* The empty path is special. */ + if (unlikely(!len)) { + if (empty) *empty = 1; - if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) { - __putname(result); - return ERR_PTR(retval); - } + err = ERR_PTR(-ENOENT); + if (!(flags & LOOKUP_EMPTY)) + goto error; } - audit_getname(result); - return result; + + err = ERR_PTR(-ENAMETOOLONG); + if (likely(len < PATH_MAX)) { + audit_getname(result); + return result; + } + +error: + __putname(result); + return err; } char *getname(const char __user * filename) @@ -228,10 +219,7 @@ static int acl_permission_check(struct inode *inode, int mask) { unsigned int mode = inode->i_mode; - if (current_user_ns() != inode_userns(inode)) - goto other_perms; - - if (likely(current_fsuid() == inode->i_uid)) + if (likely(uid_eq(current_fsuid(), inode->i_uid))) mode >>= 6; else { if (IS_POSIXACL(inode) && (mode & S_IRWXG)) { @@ -244,7 +232,6 @@ static int acl_permission_check(struct inode *inode, int mask) mode >>= 3; } -other_perms: /* * If the DACs are ok we don't need any capability check. */ @@ -280,10 +267,10 @@ int generic_permission(struct inode *inode, int mask) if (S_ISDIR(inode->i_mode)) { /* DACs are overridable for directories */ - if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) + if (inode_capable(inode, CAP_DAC_OVERRIDE)) return 0; if (!(mask & MAY_WRITE)) - if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH)) + if (inode_capable(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; } @@ -293,7 +280,7 @@ int generic_permission(struct inode *inode, int mask) * at least one exec bit set. */ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO)) - if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE)) + if (inode_capable(inode, CAP_DAC_OVERRIDE)) return 0; /* @@ -301,7 +288,7 @@ int generic_permission(struct inode *inode, int mask) */ mask &= MAY_READ | MAY_WRITE | MAY_EXEC; if (mask == MAY_READ) - if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH)) + if (inode_capable(inode, CAP_DAC_READ_SEARCH)) return 0; return -EACCES; @@ -462,7 +449,7 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry) mntget(nd->path.mnt); rcu_read_unlock(); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); nd->flags &= ~LOOKUP_RCU; return 0; @@ -520,14 +507,14 @@ static int complete_walk(struct nameidata *nd) if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) { spin_unlock(&dentry->d_lock); rcu_read_unlock(); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return -ECHILD; } BUG_ON(nd->inode != dentry->d_inode); spin_unlock(&dentry->d_lock); mntget(nd->path.mnt); rcu_read_unlock(); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); } if (likely(!(nd->flags & LOOKUP_JUMPED))) @@ -694,15 +681,15 @@ int follow_up(struct path *path) struct mount *parent; struct dentry *mountpoint; - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); parent = mnt->mnt_parent; if (&parent->mnt == path->mnt) { - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return 0; } mntget(&parent->mnt); mountpoint = dget(mnt->mnt_mountpoint); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); dput(path->dentry); path->dentry = mountpoint; mntput(path->mnt); @@ -960,7 +947,7 @@ failed: if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; rcu_read_unlock(); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return -ECHILD; } @@ -1138,8 +1125,8 @@ static struct dentry *__lookup_hash(struct qstr *name, * small and for now I'd prefer to have fast path as straight as possible. * It _is_ time-critical. */ -static int do_lookup(struct nameidata *nd, struct qstr *name, - struct path *path, struct inode **inode) +static int lookup_fast(struct nameidata *nd, struct qstr *name, + struct path *path, struct inode **inode) { struct vfsmount *mnt = nd->path.mnt; struct dentry *dentry, *parent = nd->path.dentry; @@ -1154,12 +1141,25 @@ static int do_lookup(struct nameidata *nd, struct qstr *name, */ if (nd->flags & LOOKUP_RCU) { unsigned seq; - *inode = nd->inode; - dentry = __d_lookup_rcu(parent, name, &seq, inode); + dentry = __d_lookup_rcu(parent, name, &seq, nd->inode); if (!dentry) goto unlazy; - /* Memory barrier in read_seqcount_begin of child is enough */ + /* + * This sequence count validates that the inode matches + * the dentry name information from lookup. + */ + *inode = dentry->d_inode; + if (read_seqcount_retry(&dentry->d_seq, seq)) + return -ECHILD; + + /* + * This sequence count validates that the parent had no + * changes while we did the lookup of the dentry above. + * + * The memory barrier in read_seqcount_begin of child is + * enough, we can use __read_seqcount_retry here. + */ if (__read_seqcount_retry(&parent->d_seq, nd->seq)) return -ECHILD; nd->seq = seq; @@ -1208,7 +1208,7 @@ unlazy: goto need_lookup; } } -done: + path->mnt = mnt; path->dentry = dentry; err = follow_managed(path, nd->flags); @@ -1222,6 +1222,17 @@ done: return 0; need_lookup: + return 1; +} + +/* Fast lookup failed, do it the slow way */ +static int lookup_slow(struct nameidata *nd, struct qstr *name, + struct path *path) +{ + struct dentry *dentry, *parent; + int err; + + parent = nd->path.dentry; BUG_ON(nd->inode != parent->d_inode); mutex_lock(&parent->d_inode->i_mutex); @@ -1229,7 +1240,16 @@ need_lookup: mutex_unlock(&parent->d_inode->i_mutex); if (IS_ERR(dentry)) return PTR_ERR(dentry); - goto done; + path->mnt = nd->path.mnt; + path->dentry = dentry; + err = follow_managed(path, nd->flags); + if (unlikely(err < 0)) { + path_put_conditional(path, nd); + return err; + } + if (err) + nd->flags |= LOOKUP_JUMPED; + return 0; } static inline int may_lookup(struct nameidata *nd) @@ -1265,7 +1285,7 @@ static void terminate_walk(struct nameidata *nd) if (!(nd->flags & LOOKUP_ROOT)) nd->root.mnt = NULL; rcu_read_unlock(); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); } } @@ -1301,21 +1321,26 @@ static inline int walk_component(struct nameidata *nd, struct path *path, */ if (unlikely(type != LAST_NORM)) return handle_dots(nd, type); - err = do_lookup(nd, name, path, &inode); + err = lookup_fast(nd, name, path, &inode); if (unlikely(err)) { - terminate_walk(nd); - return err; - } - if (!inode) { - path_to_nameidata(path, nd); - terminate_walk(nd); - return -ENOENT; + if (err < 0) + goto out_err; + + err = lookup_slow(nd, name, path); + if (err < 0) + goto out_err; + + inode = path->dentry->d_inode; } + err = -ENOENT; + if (!inode) + goto out_path_put; + if (should_follow_link(inode, follow)) { if (nd->flags & LOOKUP_RCU) { if (unlikely(unlazy_walk(nd, path->dentry))) { - terminate_walk(nd); - return -ECHILD; + err = -ECHILD; + goto out_err; } } BUG_ON(inode != path->dentry->d_inode); @@ -1324,6 +1349,12 @@ static inline int walk_component(struct nameidata *nd, struct path *path, path_to_nameidata(path, nd); nd->inode = inode; return 0; + +out_path_put: + path_to_nameidata(path, nd); +out_err: + terminate_walk(nd); + return err; } /* @@ -1429,7 +1460,7 @@ unsigned int full_name_hash(const unsigned char *name, unsigned int len) unsigned long hash = 0; for (;;) { - a = *(unsigned long *)name; + a = load_unaligned_zeropad(name); if (len < sizeof(unsigned long)) break; hash += a; @@ -1452,25 +1483,27 @@ EXPORT_SYMBOL(full_name_hash); */ static inline unsigned long hash_name(const char *name, unsigned int *hashp) { - unsigned long a, mask, hash, len; + unsigned long a, b, adata, bdata, mask, hash, len; + const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; hash = a = 0; len = -sizeof(unsigned long); do { hash = (hash + a) * 9; len += sizeof(unsigned long); - a = *(unsigned long *)(name+len); - /* Do we have any NUL or '/' bytes in this word? */ - mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/')); - } while (!mask); - - /* The mask *below* the first high bit set */ - mask = (mask - 1) & ~mask; - mask >>= 7; - hash += a & mask; + a = load_unaligned_zeropad(name+len); + b = a ^ REPEAT_BYTE('/'); + } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants))); + + adata = prep_zero_mask(a, adata, &constants); + bdata = prep_zero_mask(b, bdata, &constants); + + mask = create_zero_mask(adata | bdata); + + hash += a & zero_bytemask(mask); *hashp = fold_hash(hash); - return len + count_masked_bytes(mask); + return len + find_zero(mask); } #else @@ -1618,7 +1651,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, nd->path = nd->root; nd->inode = inode; if (flags & LOOKUP_RCU) { - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); rcu_read_lock(); nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); } else { @@ -1631,7 +1664,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (*name=='/') { if (flags & LOOKUP_RCU) { - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); rcu_read_lock(); set_root_rcu(nd); } else { @@ -1644,7 +1677,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, struct fs_struct *fs = current->fs; unsigned seq; - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); rcu_read_lock(); do { @@ -1680,7 +1713,7 @@ static int path_init(int dfd, const char *name, unsigned int flags, if (fput_needed) *fp = file; nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq); - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); rcu_read_lock(); } else { path_get(&file->f_path); @@ -1931,19 +1964,15 @@ static int user_path_parent(int dfd, const char __user *path, */ static inline int check_sticky(struct inode *dir, struct inode *inode) { - uid_t fsuid = current_fsuid(); + kuid_t fsuid = current_fsuid(); if (!(dir->i_mode & S_ISVTX)) return 0; - if (current_user_ns() != inode_userns(inode)) - goto other_userns; - if (inode->i_uid == fsuid) + if (uid_eq(inode->i_uid, fsuid)) return 0; - if (dir->i_uid == fsuid) + if (uid_eq(dir->i_uid, fsuid)) return 0; - -other_userns: - return !ns_capable(inode_userns(inode), CAP_FOWNER); + return !inode_capable(inode, CAP_FOWNER); } /* @@ -2171,6 +2200,10 @@ static struct file *do_last(struct nameidata *nd, struct path *path, int want_write = 0; int acc_mode = op->acc_mode; struct file *filp; + struct inode *inode; + int symlink_ok = 0; + struct path save_parent = { .dentry = NULL, .mnt = NULL }; + bool retried = false; int error; nd->flags &= ~LOOKUP_PARENT; @@ -2202,30 +2235,23 @@ static struct file *do_last(struct nameidata *nd, struct path *path, } if (!(open_flag & O_CREAT)) { - int symlink_ok = 0; if (nd->last.name[nd->last.len]) nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW)) symlink_ok = 1; /* we _can_ be in RCU mode here */ - error = walk_component(nd, path, &nd->last, LAST_NORM, - !symlink_ok); - if (error < 0) - return ERR_PTR(error); - if (error) /* symlink */ - return NULL; - /* sayonara */ - error = complete_walk(nd); - if (error) - return ERR_PTR(error); + error = lookup_fast(nd, &nd->last, path, &inode); + if (unlikely(error)) { + if (error < 0) + goto exit; - error = -ENOTDIR; - if (nd->flags & LOOKUP_DIRECTORY) { - if (!nd->inode->i_op->lookup) + error = lookup_slow(nd, &nd->last, path); + if (error < 0) goto exit; + + inode = path->dentry->d_inode; } - audit_inode(pathname, nd->path.dentry); - goto ok; + goto finish_lookup; } /* create side of things */ @@ -2243,6 +2269,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path, if (nd->last.name[nd->last.len]) goto exit; +retry_lookup: mutex_lock(&dir->d_inode->i_mutex); dentry = lookup_hash(nd); @@ -2304,22 +2331,49 @@ static struct file *do_last(struct nameidata *nd, struct path *path, if (error) nd->flags |= LOOKUP_JUMPED; + BUG_ON(nd->flags & LOOKUP_RCU); + inode = path->dentry->d_inode; +finish_lookup: + /* we _can_ be in RCU mode here */ error = -ENOENT; - if (!path->dentry->d_inode) - goto exit_dput; + if (!inode) { + path_to_nameidata(path, nd); + goto exit; + } - if (path->dentry->d_inode->i_op->follow_link) + if (should_follow_link(inode, !symlink_ok)) { + if (nd->flags & LOOKUP_RCU) { + if (unlikely(unlazy_walk(nd, path->dentry))) { + error = -ECHILD; + goto exit; + } + } + BUG_ON(inode != path->dentry->d_inode); return NULL; + } - path_to_nameidata(path, nd); - nd->inode = path->dentry->d_inode; + if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) { + path_to_nameidata(path, nd); + } else { + save_parent.dentry = nd->path.dentry; + save_parent.mnt = mntget(path->mnt); + nd->path.dentry = path->dentry; + + } + nd->inode = inode; /* Why this, you ask? _Now_ we might have grown LOOKUP_JUMPED... */ error = complete_walk(nd); - if (error) + if (error) { + path_put(&save_parent); return ERR_PTR(error); + } error = -EISDIR; - if (S_ISDIR(nd->inode->i_mode)) + if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode)) + goto exit; + error = -ENOTDIR; + if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup) goto exit; + audit_inode(pathname, nd->path.dentry); ok: if (!S_ISREG(nd->inode->i_mode)) will_truncate = 0; @@ -2335,6 +2389,20 @@ common: if (error) goto exit; filp = nameidata_to_filp(nd); + if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) { + BUG_ON(save_parent.dentry != dir); + path_put(&nd->path); + nd->path = save_parent; + nd->inode = dir->d_inode; + save_parent.mnt = NULL; + save_parent.dentry = NULL; + if (want_write) { + mnt_drop_write(nd->path.mnt); + want_write = 0; + } + retried = true; + goto retry_lookup; + } if (!IS_ERR(filp)) { error = ima_file_check(filp, op->acc_mode); if (error) { @@ -2354,7 +2422,8 @@ common: out: if (want_write) mnt_drop_write(nd->path.mnt); - path_put(&nd->path); + path_put(&save_parent); + terminate_walk(nd); return filp; exit_mutex_unlock: @@ -2417,6 +2486,12 @@ out: if (base) fput(base); release_open_intent(nd); + if (filp == ERR_PTR(-EOPENSTALE)) { + if (flags & LOOKUP_RCU) + filp = ERR_PTR(-ECHILD); + else + filp = ERR_PTR(-ESTALE); + } return filp; out_filp: @@ -2531,8 +2606,7 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) if (error) return error; - if ((S_ISCHR(mode) || S_ISBLK(mode)) && - !ns_capable(inode_userns(dir), CAP_MKNOD)) + if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD)) return -EPERM; if (!dir->i_op->mknod) diff --git a/fs/namespace.c b/fs/namespace.c index e6081996c9a..1e4a5fe3d7b 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -397,7 +397,7 @@ static int mnt_make_readonly(struct mount *mnt) { int ret = 0; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; /* * After storing MNT_WRITE_HOLD, we'll read the counters. This store @@ -431,15 +431,15 @@ static int mnt_make_readonly(struct mount *mnt) */ smp_wmb(); mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return ret; } static void __mnt_unmake_readonly(struct mount *mnt) { - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); mnt->mnt.mnt_flags &= ~MNT_READONLY; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } int sb_prepare_remount_readonly(struct super_block *sb) @@ -451,7 +451,7 @@ int sb_prepare_remount_readonly(struct super_block *sb) if (atomic_long_read(&sb->s_remove_count)) return -EBUSY; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_for_each_entry(mnt, &sb->s_mounts, mnt_instance) { if (!(mnt->mnt.mnt_flags & MNT_READONLY)) { mnt->mnt.mnt_flags |= MNT_WRITE_HOLD; @@ -473,7 +473,7 @@ int sb_prepare_remount_readonly(struct super_block *sb) if (mnt->mnt.mnt_flags & MNT_WRITE_HOLD) mnt->mnt.mnt_flags &= ~MNT_WRITE_HOLD; } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return err; } @@ -522,14 +522,14 @@ struct vfsmount *lookup_mnt(struct path *path) { struct mount *child_mnt; - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); child_mnt = __lookup_mnt(path->mnt, path->dentry, 1); if (child_mnt) { mnt_add_count(child_mnt, 1); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return &child_mnt->mnt; } else { - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return NULL; } } @@ -714,9 +714,9 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void mnt->mnt.mnt_sb = root->d_sb; mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return &mnt->mnt; } EXPORT_SYMBOL_GPL(vfs_kern_mount); @@ -745,9 +745,9 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, mnt->mnt.mnt_root = dget(root); mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_add_tail(&mnt->mnt_instance, &sb->s_mounts); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); if (flag & CL_SLAVE) { list_add(&mnt->mnt_slave, &old->mnt_slave_list); @@ -803,35 +803,36 @@ static void mntput_no_expire(struct mount *mnt) { put_again: #ifdef CONFIG_SMP - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); if (likely(atomic_read(&mnt->mnt_longterm))) { mnt_add_count(mnt, -1); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return; } - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); mnt_add_count(mnt, -1); if (mnt_get_count(mnt)) { - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return; } #else mnt_add_count(mnt, -1); if (likely(mnt_get_count(mnt))) return; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); #endif if (unlikely(mnt->mnt_pinned)) { mnt_add_count(mnt, mnt->mnt_pinned + 1); mnt->mnt_pinned = 0; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); acct_auto_close_mnt(&mnt->mnt); goto put_again; } + list_del(&mnt->mnt_instance); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); mntfree(mnt); } @@ -857,21 +858,21 @@ EXPORT_SYMBOL(mntget); void mnt_pin(struct vfsmount *mnt) { - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); real_mount(mnt)->mnt_pinned++; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } EXPORT_SYMBOL(mnt_pin); void mnt_unpin(struct vfsmount *m) { struct mount *mnt = real_mount(m); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); if (mnt->mnt_pinned) { mnt_add_count(mnt, 1); mnt->mnt_pinned--; } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } EXPORT_SYMBOL(mnt_unpin); @@ -988,12 +989,12 @@ int may_umount_tree(struct vfsmount *m) BUG_ON(!m); /* write lock needed for mnt_get_count */ - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); for (p = mnt; p; p = next_mnt(p, mnt)) { actual_refs += mnt_get_count(p); minimum_refs += 2; } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); if (actual_refs > minimum_refs) return 0; @@ -1020,10 +1021,10 @@ int may_umount(struct vfsmount *mnt) { int ret = 1; down_read(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); if (propagate_mount_busy(real_mount(mnt), 2)) ret = 0; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_read(&namespace_sem); return ret; } @@ -1040,13 +1041,13 @@ void release_mounts(struct list_head *head) struct dentry *dentry; struct mount *m; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); dentry = mnt->mnt_mountpoint; m = mnt->mnt_parent; mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; m->mnt_ghosts--; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); dput(dentry); mntput(&m->mnt); } @@ -1073,8 +1074,9 @@ void umount_tree(struct mount *mnt, int propagate, struct list_head *kill) list_del_init(&p->mnt_expire); list_del_init(&p->mnt_list); __touch_mnt_namespace(p->mnt_ns); + if (p->mnt_ns) + __mnt_make_shortterm(p); p->mnt_ns = NULL; - __mnt_make_shortterm(p); list_del_init(&p->mnt_child); if (mnt_has_parent(p)) { p->mnt_parent->mnt_ghosts++; @@ -1112,12 +1114,12 @@ static int do_umount(struct mount *mnt, int flags) * probably don't strictly need the lock here if we examined * all race cases, but it's a slowpath. */ - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); if (mnt_get_count(mnt) != 2) { - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return -EBUSY; } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); if (!xchg(&mnt->mnt_expiry_mark, 1)) return -EAGAIN; @@ -1159,7 +1161,7 @@ static int do_umount(struct mount *mnt, int flags) } down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); event++; if (!(flags & MNT_DETACH)) @@ -1171,7 +1173,7 @@ static int do_umount(struct mount *mnt, int flags) umount_tree(mnt, 1, &umount_list); retval = 0; } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); return retval; @@ -1286,19 +1288,19 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, q = clone_mnt(p, p->mnt.mnt_root, flag); if (!q) goto Enomem; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_add_tail(&q->mnt_list, &res->mnt_list); attach_mnt(q, &path); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } } return res; Enomem: if (res) { LIST_HEAD(umount_list); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); umount_tree(res, 0, &umount_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); release_mounts(&umount_list); } return NULL; @@ -1318,9 +1320,9 @@ void drop_collected_mounts(struct vfsmount *mnt) { LIST_HEAD(umount_list); down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); umount_tree(real_mount(mnt), 0, &umount_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); } @@ -1448,7 +1450,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, if (err) goto out_cleanup_ids; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); if (IS_MNT_SHARED(dest_mnt)) { for (p = source_mnt; p; p = next_mnt(p, source_mnt)) @@ -1467,7 +1469,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, list_del_init(&child->mnt_hash); commit_tree(child); } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); return 0; @@ -1565,10 +1567,10 @@ static int do_change_type(struct path *path, int flag) goto out_unlock; } - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL)) change_mnt_propagation(m, type); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); out_unlock: up_write(&namespace_sem); @@ -1617,9 +1619,9 @@ static int do_loopback(struct path *path, char *old_name, err = graft_tree(mnt, path); if (err) { - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); umount_tree(mnt, 0, &umount_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } out2: unlock_mount(path); @@ -1677,16 +1679,16 @@ static int do_remount(struct path *path, int flags, int mnt_flags, else err = do_remount_sb(sb, flags, data, 0); if (!err) { - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); mnt_flags |= mnt->mnt.mnt_flags & MNT_PROPAGATION_MASK; mnt->mnt.mnt_flags = mnt_flags; - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } up_write(&sb->s_umount); if (!err) { - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); touch_mnt_namespace(mnt->mnt_ns); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); } return err; } @@ -1893,9 +1895,9 @@ fail: /* remove m from any expiration list it may be on */ if (!list_empty(&mnt->mnt_expire)) { down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_del_init(&mnt->mnt_expire); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); } mntput(m); @@ -1911,11 +1913,11 @@ fail: void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list) { down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_add_tail(&real_mount(mnt)->mnt_expire, expiry_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); } EXPORT_SYMBOL(mnt_set_expiry); @@ -1935,7 +1937,7 @@ void mark_mounts_for_expiry(struct list_head *mounts) return; down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); /* extract from the expiration list every vfsmount that matches the * following criteria: @@ -1954,7 +1956,7 @@ void mark_mounts_for_expiry(struct list_head *mounts) touch_mnt_namespace(mnt->mnt_ns); umount_tree(mnt, 1, &umounts); } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umounts); @@ -2218,9 +2220,9 @@ void mnt_make_shortterm(struct vfsmount *m) struct mount *mnt = real_mount(m); if (atomic_add_unless(&mnt->mnt_longterm, -1, 1)) return; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); atomic_dec(&mnt->mnt_longterm); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); #endif } @@ -2250,9 +2252,9 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns, return ERR_PTR(-ENOMEM); } new_ns->root = new; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); list_add_tail(&new_ns->list, &new->mnt_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); /* * Second pass: switch the tsk->fs->* elements and mark new vfsmounts @@ -2416,9 +2418,9 @@ bool is_path_reachable(struct mount *mnt, struct dentry *dentry, int path_is_under(struct path *path1, struct path *path2) { int res; - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); res = is_path_reachable(real_mount(path1->mnt), path1->dentry, path2); - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return res; } EXPORT_SYMBOL(path_is_under); @@ -2505,7 +2507,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make sure we can reach put_old from new_root */ if (!is_path_reachable(real_mount(old.mnt), old.dentry, &new)) goto out4; - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); detach_mnt(new_mnt, &parent_path); detach_mnt(root_mnt, &root_parent); /* mount old root on put_old */ @@ -2513,7 +2515,7 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* mount new_root on / */ attach_mnt(new_mnt, &root_parent); touch_mnt_namespace(current->nsproxy->mnt_ns); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); chroot_fs_refs(&root, &new); error = 0; out4: @@ -2576,7 +2578,7 @@ void __init mnt_init(void) for (u = 0; u < HASH_SIZE; u++) INIT_LIST_HEAD(&mount_hashtable[u]); - br_lock_init(vfsmount_lock); + br_lock_init(&vfsmount_lock); err = sysfs_init(); if (err) @@ -2596,9 +2598,9 @@ void put_mnt_ns(struct mnt_namespace *ns) if (!atomic_dec_and_test(&ns->count)) return; down_write(&namespace_sem); - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); umount_tree(ns->root, 0, &umount_list); - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); up_write(&namespace_sem); release_mounts(&umount_list); kfree(ns); diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index 3ff5fcc1528..122e260247f 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -221,6 +221,10 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * already_written = 0; + errno = file_update_time(file); + if (errno) + goto outrel; + bouncebuffer = vmalloc(bufsize); if (!bouncebuffer) { errno = -EIO; /* -ENOMEM */ @@ -252,8 +256,6 @@ ncp_file_write(struct file *file, const char __user *buf, size_t count, loff_t * } vfree(bouncebuffer); - file_update_time(file); - *ppos = pos; if (pos > i_size_read(inode)) { diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c index 87484fb8d17..333df07ae3b 100644 --- a/fs/ncpfs/inode.c +++ b/fs/ncpfs/inode.c @@ -292,7 +292,7 @@ static void ncp_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (S_ISDIR(inode->i_mode)) { DDPRINTK("ncp_evict_inode: put directory %ld\n", inode->i_ino); diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h index 4af803f1351..54cc0cdb3dc 100644 --- a/fs/ncpfs/ncp_fs_sb.h +++ b/fs/ncpfs/ncp_fs_sb.h @@ -23,17 +23,17 @@ struct ncp_mount_data_kernel { unsigned long flags; /* NCP_MOUNT_* flags */ unsigned int int_flags; /* internal flags */ #define NCP_IMOUNT_LOGGEDIN_POSSIBLE 0x0001 - __kernel_uid32_t mounted_uid; /* Who may umount() this filesystem? */ + uid_t mounted_uid; /* Who may umount() this filesystem? */ struct pid *wdog_pid; /* Who cares for our watchdog packets? */ unsigned int ncp_fd; /* The socket to the ncp port */ unsigned int time_out; /* How long should I wait after sending a NCP request? */ unsigned int retry_count; /* And how often should I retry? */ unsigned char mounted_vol[NCP_VOLNAME_LEN + 1]; - __kernel_uid32_t uid; - __kernel_gid32_t gid; - __kernel_mode_t file_mode; - __kernel_mode_t dir_mode; + uid_t uid; + gid_t gid; + umode_t file_mode; + umode_t dir_mode; int info_fd; }; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 2a0e6c59914..f90f4f5cd42 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -29,9 +29,20 @@ config NFS_FS If unsure, say N. +config NFS_V2 + bool "NFS client support for NFS version 2" + depends on NFS_FS + default y + help + This option enables support for version 2 of the NFS protocol + (RFC 1094) in the kernel's NFS client. + + If unsure, say Y. + config NFS_V3 bool "NFS client support for NFS version 3" depends on NFS_FS + default y help This option enables support for version 3 of the NFS protocol (RFC 1813) in the kernel's NFS client. diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index b58613d0abb..7ddd45d9f17 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -4,11 +4,12 @@ obj-$(CONFIG_NFS_FS) += nfs.o -nfs-y := client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \ - direct.o pagelist.o proc.o read.o symlink.o unlink.o \ +nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ + direct.o pagelist.o read.o symlink.o unlink.o \ write.o namespace.o mount_clnt.o \ dns_resolve.o cache_lib.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o +nfs-$(CONFIG_NFS_V2) += proc.o nfs2xdr.o nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \ diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 9c94297bb70..7ae8a608956 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -38,6 +38,8 @@ #include <linux/buffer_head.h> /* various write calls */ #include <linux/prefetch.h> +#include "../pnfs.h" +#include "../internal.h" #include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD @@ -185,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_read_data *rdata = (struct nfs_read_data *)par->data; do { struct page *page = bvec->bv_page; @@ -196,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err) SetPageUptodate(page); } while (bvec >= bio->bi_io_vec); if (!uptodate) { - if (!rdata->pnfs_error) - rdata->pnfs_error = -EIO; - pnfs_set_lo_fail(rdata->lseg); + struct nfs_read_data *rdata = par->data; + struct nfs_pgio_header *header = rdata->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -219,7 +223,7 @@ bl_end_par_io_read(void *data, int unused) { struct nfs_read_data *rdata = data; - rdata->task.tk_status = rdata->pnfs_error; + rdata->task.tk_status = rdata->header->pnfs_error; INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); schedule_work(&rdata->task.u.tk_work); } @@ -227,6 +231,7 @@ bl_end_par_io_read(void *data, int unused) static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *header = rdata->header; int i, hole; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -237,7 +242,7 @@ bl_read_pagelist(struct nfs_read_data *rdata) int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT; dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, - rdata->npages, f_offset, (unsigned int)rdata->args.count); + rdata->pages.npages, f_offset, (unsigned int)rdata->args.count); par = alloc_parallel(rdata); if (!par) @@ -247,17 +252,17 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect = (sector_t) (f_offset >> SECTOR_SHIFT); /* Code assumes extents are page-aligned */ - for (i = pg_index; i < rdata->npages; i++) { + for (i = pg_index; i < rdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); bl_put_extent(cow_read); bio = bl_submit_bio(READ, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be) { - rdata->pnfs_error = -EIO; + header->pnfs_error = -EIO; goto out; } extent_length = be->be_length - @@ -280,11 +285,12 @@ bl_read_pagelist(struct nfs_read_data *rdata) struct pnfs_block_extent *be_read; be_read = (hole && cow_read) ? cow_read : be; - bio = bl_add_page_to_bio(bio, rdata->npages - i, READ, + bio = bl_add_page_to_bio(bio, rdata->pages.npages - i, + READ, isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { - rdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -292,9 +298,9 @@ bl_read_pagelist(struct nfs_read_data *rdata) isect += PAGE_CACHE_SECTORS; extent_length -= PAGE_CACHE_SECTORS; } - if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) { + if ((isect << SECTOR_SHIFT) >= header->inode->i_size) { rdata->res.eof = 1; - rdata->res.count = rdata->inode->i_size - f_offset; + rdata->res.count = header->inode->i_size - f_offset; } else { rdata->res.count = (isect << SECTOR_SHIFT) - f_offset; } @@ -343,7 +349,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err) struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; do { struct page *page = bvec->bv_page; @@ -356,9 +361,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err) } while (bvec >= bio->bi_io_vec); if (unlikely(!uptodate)) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; + + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -368,12 +376,13 @@ static void bl_end_io_write(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; + struct nfs_write_data *data = par->data; + struct nfs_pgio_header *header = data->header; if (!uptodate) { - if (!wdata->pnfs_error) - wdata->pnfs_error = -EIO; - pnfs_set_lo_fail(wdata->lseg); + if (!header->pnfs_error) + header->pnfs_error = -EIO; + pnfs_set_lo_fail(header->lseg); } bio_put(bio); put_parallel(par); @@ -389,9 +398,9 @@ static void bl_write_cleanup(struct work_struct *work) dprintk("%s enter\n", __func__); task = container_of(work, struct rpc_task, u.tk_work); wdata = container_of(task, struct nfs_write_data, task); - if (likely(!wdata->pnfs_error)) { + if (likely(!wdata->header->pnfs_error)) { /* Marks for LAYOUTCOMMIT */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg), wdata->args.offset, wdata->args.count); } pnfs_ld_write_done(wdata); @@ -402,12 +411,12 @@ static void bl_end_par_io_write(void *data, int num_se) { struct nfs_write_data *wdata = data; - if (unlikely(wdata->pnfs_error)) { - bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval, + if (unlikely(wdata->header->pnfs_error)) { + bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval, num_se); } - wdata->task.tk_status = wdata->pnfs_error; + wdata->task.tk_status = wdata->header->pnfs_error; wdata->verf.committed = NFS_FILE_SYNC; INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup); schedule_work(&wdata->task.u.tk_work); @@ -538,6 +547,7 @@ check_page: static enum pnfs_try_status bl_write_pagelist(struct nfs_write_data *wdata, int sync) { + struct nfs_pgio_header *header = wdata->header; int i, ret, npg_zero, pg_index, last = 0; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; @@ -550,7 +560,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) pgoff_t index; u64 temp; int npg_per_block = - NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; + NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); /* At this point, wdata->pages is a (sequential) list of nfs_pages. @@ -564,7 +574,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) /* At this point, have to be more careful with error handling */ isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read); + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read); if (!be || !is_writable(be, isect)) { dprintk("%s no matching extents!\n", __func__); goto out_mds; @@ -595,10 +605,10 @@ fill_invalid_ext: dprintk("%s zero %dth page: index %lu isect %llu\n", __func__, npg_zero, index, (unsigned long long)isect); - page = bl_find_get_zeroing_page(wdata->inode, index, + page = bl_find_get_zeroing_page(header->inode, index, cow_read); if (unlikely(IS_ERR(page))) { - wdata->pnfs_error = PTR_ERR(page); + header->pnfs_error = PTR_ERR(page); goto out; } else if (page == NULL) goto next_page; @@ -610,7 +620,7 @@ fill_invalid_ext: __func__, ret); end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } if (likely(!bl_push_one_short_extent(be->be_inval))) @@ -618,11 +628,11 @@ fill_invalid_ext: else { end_page_writeback(page); page_cache_release(page); - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } /* FIXME: This should be done in bi_end_io */ - mark_extents_written(BLK_LSEG2EXT(wdata->lseg), + mark_extents_written(BLK_LSEG2EXT(header->lseg), page->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE); @@ -630,7 +640,7 @@ fill_invalid_ext: isect, page, be, bl_end_io_write_zero, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -645,16 +655,16 @@ next_page: /* Middle pages */ pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT; - for (i = pg_index; i < wdata->npages; i++) { + for (i = pg_index; i < wdata->pages.npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); bio = bl_submit_bio(WRITE, bio); /* Get the next one */ - be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), + be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, NULL); if (!be || !is_writable(be, isect)) { - wdata->pnfs_error = -EINVAL; + header->pnfs_error = -EINVAL; goto out; } if (be->be_state == PNFS_BLOCK_INVALID_DATA) { @@ -662,7 +672,7 @@ next_page: be->be_inval))) par->bse_count++; else { - wdata->pnfs_error = -ENOMEM; + header->pnfs_error = -ENOMEM; goto out; } } @@ -675,15 +685,15 @@ next_page: if (unlikely(ret)) { dprintk("%s bl_mark_sectors_init fail %d\n", __func__, ret); - wdata->pnfs_error = ret; + header->pnfs_error = ret; goto out; } } - bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE, + bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE, isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { - wdata->pnfs_error = PTR_ERR(bio); + header->pnfs_error = PTR_ERR(bio); bio = NULL; goto out; } @@ -868,7 +878,7 @@ nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, * GETDEVICEINFO's maxcount */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); dprintk("%s max_resp_sz %u max_pages %d\n", __func__, max_resp_sz, max_pages); diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c index a5c88a554d9..c96554245cc 100644 --- a/fs/nfs/blocklayout/blocklayoutdev.c +++ b/fs/nfs/blocklayout/blocklayoutdev.c @@ -123,7 +123,7 @@ nfs4_blk_decode_device(struct nfs_server *server, uint8_t *dataptr; DECLARE_WAITQUEUE(wq, current); int offset, len, i, rc; - struct net *net = server->nfs_client->net; + struct net *net = server->nfs_client->cl_net; struct nfs_net *nn = net_generic(net, nfs_net_id); struct bl_dev_msg *reply = &nn->bl_mount_reply; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index eb95f5091c1..23ff18fe080 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -106,7 +106,7 @@ nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) { int ret; - ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_err; @@ -114,7 +114,7 @@ nfs4_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) dprintk("NFS: Callback listener port = %u (af %u)\n", nfs_callback_tcpport, PF_INET); - ret = svc_create_xprt(serv, "tcp", xprt->xprt_net, PF_INET6, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret > 0) { nfs_callback_tcpport6 = ret; @@ -183,7 +183,7 @@ nfs41_callback_up(struct svc_serv *serv, struct rpc_xprt *xprt) * fore channel connection. * Returns the input port (0) and sets the svc_serv bc_xprt on success */ - ret = svc_create_xprt(serv, "tcp-bc", xprt->xprt_net, PF_INET, 0, + ret = svc_create_xprt(serv, "tcp-bc", &init_net, PF_INET, 0, SVC_SOCK_ANONYMOUS); if (ret < 0) { rqstp = ERR_PTR(ret); @@ -253,6 +253,7 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) char svc_name[12]; int ret = 0; int minorversion_setup; + struct net *net = &init_net; mutex_lock(&nfs_callback_mutex); if (cb_info->users++ || cb_info->task != NULL) { @@ -265,6 +266,12 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto out_err; } + ret = svc_bind(serv, net); + if (ret < 0) { + printk(KERN_WARNING "NFS: bind callback service failed\n"); + goto out_err; + } + minorversion_setup = nfs_minorversion_callback_svc_setup(minorversion, serv, xprt, &rqstp, &callback_svc); if (!minorversion_setup) { @@ -306,6 +313,8 @@ out_err: dprintk("NFS: Couldn't create callback socket or server thread; " "err = %d\n", ret); cb_info->users--; + if (serv) + svc_shutdown_net(serv, net); goto out; } @@ -320,6 +329,7 @@ void nfs_callback_down(int minorversion) cb_info->users--; if (cb_info->users == 0 && cb_info->task != NULL) { kthread_stop(cb_info->task); + svc_shutdown_net(cb_info->serv, &init_net); svc_exit_thread(cb_info->rqst); cb_info->serv = NULL; cb_info->rqst = NULL; @@ -332,7 +342,7 @@ void nfs_callback_down(int minorversion) int check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp) { - char *p = svc_gss_principal(rqstp); + char *p = rqstp->rq_cred.cr_principal; if (rqstp->rq_authop->flavour != RPC_AUTH_GSS) return 1; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 95bfc243992..e64b01d2a33 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -455,9 +455,9 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp, args->csa_nrclists = ntohl(*p++); args->csa_rclists = NULL; if (args->csa_nrclists) { - args->csa_rclists = kmalloc(args->csa_nrclists * - sizeof(*args->csa_rclists), - GFP_KERNEL); + args->csa_rclists = kmalloc_array(args->csa_nrclists, + sizeof(*args->csa_rclists), + GFP_KERNEL); if (unlikely(args->csa_rclists == NULL)) goto out; @@ -696,7 +696,7 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp, const struct cb_sequenceres *res) { __be32 *p; - unsigned status = res->csr_status; + __be32 status = res->csr_status; if (unlikely(status != 0)) goto out; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index da7b5e4ff9e..f005b5bebdc 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -65,7 +65,7 @@ static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq); static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) { int ret = 0; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->rpc_ops->version != 4 || minorversion != 0) return ret; @@ -90,7 +90,9 @@ static bool nfs4_disable_idmapping = true; * RPC cruft for NFS */ static const struct rpc_version *nfs_version[5] = { +#ifdef CONFIG_NFS_V2 [2] = &nfs_version2, +#endif #ifdef CONFIG_NFS_V3 [3] = &nfs_version3, #endif @@ -129,6 +131,7 @@ const struct rpc_program nfsacl_program = { #endif /* CONFIG_NFS_V3_ACL */ struct nfs_client_initdata { + unsigned long init_flags; const char *hostname; const struct sockaddr *addr; size_t addrlen; @@ -172,7 +175,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ clp->cl_rpcclient = ERR_PTR(-EINVAL); clp->cl_proto = cl_init->proto; - clp->net = get_net(cl_init->net); + clp->cl_net = get_net(cl_init->net); #ifdef CONFIG_NFS_V4 err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); @@ -182,7 +185,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ spin_lock_init(&clp->cl_lock); INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); - clp->cl_boot_time = CURRENT_TIME; clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; clp->cl_minorversion = cl_init->minorversion; clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; @@ -205,8 +207,8 @@ error_0: static void nfs4_shutdown_session(struct nfs_client *clp) { if (nfs4_has_session(clp)) { - nfs4_deviceid_purge_client(clp); nfs4_destroy_session(clp->cl_session); + nfs4_destroy_clientid(clp); } } @@ -235,6 +237,9 @@ static void nfs4_shutdown_client(struct nfs_client *clp) nfs_idmap_delete(clp); rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverowner); + kfree(clp->cl_serverscope); + kfree(clp->cl_implid); } /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ @@ -248,7 +253,7 @@ void nfs_cleanup_cb_ident_idr(struct net *net) /* nfs_client_lock held */ static void nfs_cb_idr_remove_locked(struct nfs_client *clp) { - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); if (clp->cl_cb_ident) idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident); @@ -301,10 +306,8 @@ static void nfs_free_client(struct nfs_client *clp) if (clp->cl_machine_cred != NULL) put_rpccred(clp->cl_machine_cred); - put_net(clp->net); + put_net(clp->cl_net); kfree(clp->cl_hostname); - kfree(clp->server_scope); - kfree(clp->impl_id); kfree(clp); dprintk("<-- nfs_free_client()\n"); @@ -321,7 +324,7 @@ void nfs_put_client(struct nfs_client *clp) return; dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count)); - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) { list_del(&clp->cl_share_link); @@ -456,6 +459,8 @@ static bool nfs4_cb_match_client(const struct sockaddr *addr, clp->cl_cons_state == NFS_CS_SESSION_INITING)) return false; + smp_rmb(); + /* Match the version and minorversion */ if (clp->rpc_ops->version != 4 || clp->cl_minorversion != minorversion) @@ -504,6 +509,45 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat return NULL; } +static bool nfs_client_init_is_complete(const struct nfs_client *clp) +{ + return clp->cl_cons_state != NFS_CS_INITING; +} + +int nfs_wait_client_init_complete(const struct nfs_client *clp) +{ + return wait_event_killable(nfs_client_active_wq, + nfs_client_init_is_complete(clp)); +} + +/* + * Found an existing client. Make sure it's ready before returning. + */ +static struct nfs_client * +nfs_found_client(const struct nfs_client_initdata *cl_init, + struct nfs_client *clp) +{ + int error; + + error = nfs_wait_client_init_complete(clp); + if (error < 0) { + nfs_put_client(clp); + return ERR_PTR(-ERESTARTSYS); + } + + if (clp->cl_cons_state < NFS_CS_READY) { + error = clp->cl_cons_state; + nfs_put_client(clp); + return ERR_PTR(error); + } + + smp_rmb(); + + dprintk("<-- %s found nfs_client %p for %s\n", + __func__, clp, cl_init->hostname ?: ""); + return clp; +} + /* * Look up a client by IP address and protocol version * - creates a new record if one doesn't yet exist @@ -512,11 +556,9 @@ static struct nfs_client * nfs_get_client(const struct nfs_client_initdata *cl_init, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) + rpc_authflavor_t authflavour) { struct nfs_client *clp, *new = NULL; - int error; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); dprintk("--> nfs_get_client(%s,v%u)\n", @@ -527,60 +569,29 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, spin_lock(&nn->nfs_client_lock); clp = nfs_match_client(cl_init); - if (clp) - goto found_client; - if (new) - goto install_client; + if (clp) { + spin_unlock(&nn->nfs_client_lock); + if (new) + nfs_free_client(new); + return nfs_found_client(cl_init, clp); + } + if (new) { + list_add(&new->cl_share_link, &nn->nfs_client_list); + spin_unlock(&nn->nfs_client_lock); + new->cl_flags = cl_init->init_flags; + return cl_init->rpc_ops->init_client(new, + timeparms, ip_addr, + authflavour); + } spin_unlock(&nn->nfs_client_lock); new = nfs_alloc_client(cl_init); } while (!IS_ERR(new)); - dprintk("--> nfs_get_client() = %ld [failed]\n", PTR_ERR(new)); + dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n", + cl_init->hostname ?: "", PTR_ERR(new)); return new; - - /* install a new client and return with it unready */ -install_client: - clp = new; - list_add(&clp->cl_share_link, &nn->nfs_client_list); - spin_unlock(&nn->nfs_client_lock); - - error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr, - authflavour, noresvport); - if (error < 0) { - nfs_put_client(clp); - return ERR_PTR(error); - } - dprintk("--> nfs_get_client() = %p [new]\n", clp); - return clp; - - /* found an existing client - * - make sure it's ready before returning - */ -found_client: - spin_unlock(&nn->nfs_client_lock); - - if (new) - nfs_free_client(new); - - error = wait_event_killable(nfs_client_active_wq, - clp->cl_cons_state < NFS_CS_INITING); - if (error < 0) { - nfs_put_client(clp); - return ERR_PTR(-ERESTARTSYS); - } - - if (clp->cl_cons_state < NFS_CS_READY) { - error = clp->cl_cons_state; - nfs_put_client(clp); - return ERR_PTR(error); - } - - BUG_ON(clp->cl_cons_state != NFS_CS_READY); - - dprintk("--> nfs_get_client() = %p [share]\n", clp); - return clp; } /* @@ -588,27 +599,12 @@ found_client: */ void nfs_mark_client_ready(struct nfs_client *clp, int state) { + smp_wmb(); clp->cl_cons_state = state; wake_up_all(&nfs_client_active_wq); } /* - * With sessions, the client is not marked ready until after a - * successful EXCHANGE_ID and CREATE_SESSION. - * - * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate - * other versions of NFS can be tried. - */ -int nfs4_check_client_ready(struct nfs_client *clp) -{ - if (!nfs4_has_session(clp)) - return 0; - if (clp->cl_cons_state < NFS_CS_READY) - return -EPROTONOSUPPORT; - return 0; -} - -/* * Initialise the timeout values for a connection */ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, @@ -654,12 +650,11 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, */ static int nfs_create_rpc_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - rpc_authflavor_t flavor, - int discrtry, int noresvport) + rpc_authflavor_t flavor) { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { - .net = clp->net, + .net = clp->cl_net, .protocol = clp->cl_proto, .address = (struct sockaddr *)&clp->cl_addr, .addrsize = clp->cl_addrlen, @@ -670,9 +665,9 @@ static int nfs_create_rpc_client(struct nfs_client *clp, .authflavor = flavor, }; - if (discrtry) + if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_DISCRTRY; - if (noresvport) + if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags)) args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; if (!IS_ERR(clp->cl_rpcclient)) @@ -713,7 +708,7 @@ static int nfs_start_lockd(struct nfs_server *server) .nfs_version = clp->rpc_ops->version, .noresvport = server->flags & NFS_MOUNT_NORESVPORT ? 1 : 0, - .net = clp->net, + .net = clp->cl_net, }; if (nlm_init.nfs_version > 3) @@ -805,36 +800,43 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, return 0; } -/* - * Initialise an NFS2 or NFS3 client +/** + * nfs_init_client - Initialise an NFS2 or NFS3 client + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: IP presentation address (not used) + * @authflavor: authentication flavor for underlying RPC transport + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport) +struct nfs_client *nfs_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr, rpc_authflavor_t authflavour) { int error; if (clp->cl_cons_state == NFS_CS_READY) { /* the client is already initialised */ dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* * Create a client RPC handle for doing FSSTAT with UNIX auth only * - RFC 2623, sec 2.3.2 */ - error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX, - 0, noresvport); + error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX); if (error < 0) goto error; nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* @@ -847,7 +849,7 @@ static int nfs_init_server(struct nfs_server *server, .hostname = data->nfs_server.hostname, .addr = (const struct sockaddr *)&data->nfs_server.address, .addrlen = data->nfs_server.addrlen, - .rpc_ops = &nfs_v2_clientops, + .rpc_ops = NULL, .proto = data->nfs_server.protocol, .net = data->net, }; @@ -857,17 +859,28 @@ static int nfs_init_server(struct nfs_server *server, dprintk("--> nfs_init_server()\n"); + switch (data->version) { +#ifdef CONFIG_NFS_V2 + case 2: + cl_init.rpc_ops = &nfs_v2_clientops; + break; +#endif #ifdef CONFIG_NFS_V3 - if (data->version == 3) + case 3: cl_init.rpc_ops = &nfs_v3_clientops; + break; #endif + default: + return -EPROTONOSUPPORT; + } nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, data->timeo, data->retrans); + if (data->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX, - data->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX); if (IS_ERR(clp)) { dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp)); return PTR_ERR(clp); @@ -880,7 +893,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); @@ -1048,7 +1061,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve static void nfs_server_insert_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; - struct nfs_net *nn = net_generic(clp->net, nfs_net_id); + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_add_tail_rcu(&server->client_link, &clp->cl_superblocks); @@ -1065,7 +1078,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) if (clp == NULL) return; - nn = net_generic(clp->net, nfs_net_id); + nn = net_generic(clp->cl_net, nfs_net_id); spin_lock(&nn->nfs_client_lock); list_del_rcu(&server->client_link); if (list_empty(&clp->cl_superblocks)) @@ -1333,21 +1346,27 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) * so that the client back channel can find the * nfs_client struct */ - clp->cl_cons_state = NFS_CS_SESSION_INITING; + nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); } #endif /* CONFIG_NFS_V4_1 */ return nfs4_init_callback(clp); } -/* - * Initialise an NFS4 client record +/** + * nfs4_init_client - Initialise an NFS4 client record + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: callback IP address in presentation format + * @authflavor: authentication flavor for underlying RPC transport + * + * Returns pointer to an NFS client, or an ERR_PTR value. */ -int nfs4_init_client(struct nfs_client *clp, - const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport) +struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr, + rpc_authflavor_t authflavour) { char buf[INET6_ADDRSTRLEN + 1]; int error; @@ -1355,14 +1374,14 @@ int nfs4_init_client(struct nfs_client *clp, if (clp->cl_cons_state == NFS_CS_READY) { /* the client is initialised already */ dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); - return 0; + return clp; } /* Check NFS protocol revision and initialize RPC op vector */ clp->rpc_ops = &nfs_v4_clientops; - error = nfs_create_rpc_client(clp, timeparms, authflavour, - 1, noresvport); + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + error = nfs_create_rpc_client(clp, timeparms, authflavour); if (error < 0) goto error; @@ -1395,12 +1414,13 @@ int nfs4_init_client(struct nfs_client *clp, if (!nfs4_has_session(clp)) nfs_mark_client_ready(clp, NFS_CS_READY); - return 0; + return clp; error: nfs_mark_client_ready(clp, error); + nfs_put_client(clp); dprintk("<-- nfs4_init_client() = xerror %d\n", error); - return error; + return ERR_PTR(error); } /* @@ -1429,9 +1449,11 @@ static int nfs4_set_client(struct nfs_server *server, dprintk("--> nfs4_set_client()\n"); + if (server->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour, - server->flags & NFS_MOUNT_NORESVPORT); + clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); if (IS_ERR(clp)) { error = PTR_ERR(clp); goto error; @@ -1465,8 +1487,8 @@ error: * the MDS. */ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, - const struct sockaddr *ds_addr, - int ds_addrlen, int ds_proto) + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) { struct nfs_client_initdata cl_init = { .addr = ds_addr, @@ -1474,14 +1496,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, .rpc_ops = &nfs_v4_clientops, .proto = ds_proto, .minorversion = mds_clp->cl_minorversion, - .net = mds_clp->net, - }; - struct rpc_timeout ds_timeout = { - .to_initval = 15 * HZ, - .to_maxval = 15 * HZ, - .to_retries = 1, - .to_exponential = 1, + .net = mds_clp->cl_net, }; + struct rpc_timeout ds_timeout; struct nfs_client *clp; /* @@ -1489,8 +1506,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS * (section 13.1 RFC 5661). */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, - mds_clp->cl_rpcclient->cl_auth->au_flavor, 0); + mds_clp->cl_rpcclient->cl_auth->au_flavor); dprintk("<-- %s %p\n", __func__, clp); return clp; @@ -1701,7 +1719,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, rpc_protocol(parent_server->client), parent_server->client->cl_timeout, parent_client->cl_mvops->minor_version, - parent_client->net); + parent_client->cl_net); if (error < 0) goto error; @@ -1729,7 +1747,8 @@ error: */ struct nfs_server *nfs_clone_server(struct nfs_server *source, struct nfs_fh *fh, - struct nfs_fattr *fattr) + struct nfs_fattr *fattr, + rpc_authflavor_t flavor) { struct nfs_server *server; struct nfs_fattr *fattr_fsinfo; @@ -1758,7 +1777,7 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, error = nfs_init_server_rpcclient(server, source->client->cl_timeout, - source->client->cl_auth->au_flavor); + flavor); if (error < 0) goto out_free_server; if (!IS_ERR(source->client_acl)) @@ -1804,6 +1823,7 @@ void nfs_clients_init(struct net *net) idr_init(&nn->cb_ident_idr); #endif spin_lock_init(&nn->nfs_client_lock); + nn->boot_time = CURRENT_TIME; } #ifdef CONFIG_PROC_FS diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 89af1d26927..bd3a9601d32 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -316,6 +316,10 @@ out: * nfs_client_return_marked_delegations - return previously marked delegations * @clp: nfs_client to process * + * Note that this function is designed to be called by the state + * manager thread. For this reason, it cannot flush the dirty data, + * since that could deadlock in case of a state recovery error. + * * Returns zero on success, or a negative errno value. */ int nfs_client_return_marked_delegations(struct nfs_client *clp) @@ -340,11 +344,9 @@ restart: server); rcu_read_unlock(); - if (delegation != NULL) { - filemap_flush(inode->i_mapping); + if (delegation != NULL) err = __nfs_inode_return_delegation(inode, delegation, 0); - } iput(inode); if (!err) goto restart; @@ -380,6 +382,10 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode) * nfs_inode_return_delegation - synchronously return a delegation * @inode: inode to process * + * This routine will always flush any dirty data to disk on the + * assumption that if we need to return the delegation, then + * we should stop caching. + * * Returns zero on success, or a negative errno value. */ int nfs_inode_return_delegation(struct inode *inode) @@ -389,10 +395,10 @@ int nfs_inode_return_delegation(struct inode *inode) struct nfs_delegation *delegation; int err = 0; + nfs_wb_all(inode); if (rcu_access_pointer(nfsi->delegation) != NULL) { delegation = nfs_detach_delegation(nfsi, server); if (delegation != NULL) { - nfs_wb_all(inode); err = __nfs_inode_return_delegation(inode, delegation, 1); } } @@ -538,6 +544,8 @@ int nfs_async_inode_return_delegation(struct inode *inode, struct nfs_client *clp = server->nfs_client; struct nfs_delegation *delegation; + filemap_flush(inode->i_mapping); + rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index cd6a7a8dada..72709c4193f 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -66,6 +66,7 @@ static inline int nfs_have_delegation(struct inode *inode, fmode_t flags) static inline int nfs_inode_return_delegation(struct inode *inode) { + nfs_wb_all(inode); return 0; } #endif diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 4aaf0316d76..f430057ff3b 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -475,12 +475,32 @@ different: } static +bool nfs_use_readdirplus(struct inode *dir, struct file *filp) +{ + if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS)) + return false; + if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags)) + return true; + if (filp->f_pos == 0) + return true; + return false; +} + +/* + * This function is called by the lookup code to request the use of + * readdirplus to accelerate any future lookups in the same + * directory. + */ +static +void nfs_advise_use_readdirplus(struct inode *dir) +{ + set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags); +} + +static void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { - struct qstr filename = { - .len = entry->len, - .name = entry->name, - }; + struct qstr filename = QSTR_INIT(entry->name, entry->len); struct dentry *dentry; struct dentry *alias; struct inode *dir = parent->d_inode; @@ -874,7 +894,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) desc->file = filp; desc->dir_cookie = &dir_ctx->dir_cookie; desc->decode = NFS_PROTO(inode)->decode_dirent; - desc->plus = NFS_USE_READDIRPLUS(inode); + desc->plus = nfs_use_readdirplus(inode, filp) ? 1 : 0; nfs_block_sillyrename(dentry); res = nfs_revalidate_mapping(inode, filp->f_mapping); @@ -1114,7 +1134,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (!inode) { if (nfs_neg_need_reval(dir, dentry, nd)) goto out_bad; - goto out_valid; + goto out_valid_noent; } if (is_bad_inode(inode)) { @@ -1143,7 +1163,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) if (fhandle == NULL || fattr == NULL) goto out_error; - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_bad; if (nfs_compare_fh(NFS_FH(inode), fhandle)) @@ -1156,6 +1176,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) out_set_verifier: nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); out_valid: + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + out_valid_noent: dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n", __func__, dentry->d_parent->d_name.name, @@ -1299,7 +1322,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ nfs_block_sillyrename(parent); - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { @@ -1311,6 +1334,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru if (IS_ERR(res)) goto out_unblock_sillyrename; + /* Success: notify readdir to use READDIRPLUS */ + nfs_advise_use_readdirplus(dir); + no_entry: res = d_materialise_unique(dentry, inode); if (res != NULL) { @@ -1328,10 +1354,10 @@ out: } #ifdef CONFIG_NFS_V4 -static int nfs_open_revalidate(struct dentry *, struct nameidata *); +static int nfs4_lookup_revalidate(struct dentry *, struct nameidata *); const struct dentry_operations nfs4_dentry_operations = { - .d_revalidate = nfs_open_revalidate, + .d_revalidate = nfs4_lookup_revalidate, .d_delete = nfs_dentry_delete, .d_iput = nfs_dentry_iput, .d_automount = nfs_d_automount, @@ -1429,7 +1455,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry } open_flags = nd->intent.open.flags; - attr.ia_valid = 0; + attr.ia_valid = ATTR_OPEN; ctx = create_nfs_open_context(dentry, open_flags); res = ERR_CAST(ctx); @@ -1493,13 +1519,11 @@ no_open: return nfs_lookup(dir, dentry, nd); } -static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) +static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) { struct dentry *parent = NULL; struct inode *inode; struct inode *dir; - struct nfs_open_context *ctx; - struct iattr attr; int openflags, ret = 0; if (nd->flags & LOOKUP_RCU) @@ -1528,57 +1552,13 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) /* We cannot do exclusive creation on a positive dentry */ if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL)) goto no_open_dput; - /* We can't create new files here */ - openflags &= ~(O_CREAT|O_EXCL); - ctx = create_nfs_open_context(dentry, openflags); - ret = PTR_ERR(ctx); - if (IS_ERR(ctx)) - goto out; + /* Let f_op->open() actually open (and revalidate) the file */ + ret = 1; - attr.ia_valid = 0; - if (openflags & O_TRUNC) { - attr.ia_valid |= ATTR_SIZE; - attr.ia_size = 0; - nfs_wb_all(inode); - } - - /* - * Note: we're not holding inode->i_mutex and so may be racing with - * operations that change the directory. We therefore save the - * change attribute *before* we do the RPC call. - */ - inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); - if (IS_ERR(inode)) { - ret = PTR_ERR(inode); - switch (ret) { - case -EPERM: - case -EACCES: - case -EDQUOT: - case -ENOSPC: - case -EROFS: - goto out_put_ctx; - default: - goto out_drop; - } - } - iput(inode); - if (inode != dentry->d_inode) - goto out_drop; - - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - ret = nfs_intent_set_file(nd, ctx); - if (ret >= 0) - ret = 1; out: dput(parent); return ret; -out_drop: - d_drop(dentry); - ret = 0; -out_put_ctx: - put_nfs_open_context(ctx); - goto out; no_open_dput: dput(parent); @@ -1646,7 +1626,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, if (dentry->d_inode) goto out; if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 481be7f7bdd..9a4cbfc85d8 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -56,6 +56,7 @@ #include "internal.h" #include "iostat.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -81,16 +82,19 @@ struct nfs_direct_req { struct completion completion; /* wait for i/o completion */ /* commit state */ - struct list_head rewrite_list; /* saved nfs_write_data structs */ - struct nfs_write_data * commit_data; /* special write_data for commits */ + struct nfs_mds_commit_info mds_cinfo; /* Storage for cinfo */ + struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ + struct work_struct work; int flags; #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ struct nfs_writeverf verf; /* unstable write verifier */ }; +static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops; +static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops; static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode); -static const struct rpc_call_ops nfs_write_direct_ops; +static void nfs_direct_write_schedule_work(struct work_struct *work); static inline void get_dreq(struct nfs_direct_req *dreq) { @@ -124,22 +128,6 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_ return -EINVAL; } -static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count) -{ - unsigned int npages; - unsigned int i; - - if (count == 0) - return; - pages += (pgbase >> PAGE_SHIFT); - npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; - for (i = 0; i < npages; i++) { - struct page *page = pages[i]; - if (!PageCompound(page)) - set_page_dirty(page); - } -} - static void nfs_direct_release_pages(struct page **pages, unsigned int npages) { unsigned int i; @@ -147,26 +135,30 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages) page_cache_release(pages[i]); } +void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, + struct nfs_direct_req *dreq) +{ + cinfo->lock = &dreq->lock; + cinfo->mds = &dreq->mds_cinfo; + cinfo->ds = &dreq->ds_cinfo; + cinfo->dreq = dreq; + cinfo->completion_ops = &nfs_direct_commit_completion_ops; +} + static inline struct nfs_direct_req *nfs_direct_req_alloc(void) { struct nfs_direct_req *dreq; - dreq = kmem_cache_alloc(nfs_direct_cachep, GFP_KERNEL); + dreq = kmem_cache_zalloc(nfs_direct_cachep, GFP_KERNEL); if (!dreq) return NULL; kref_init(&dreq->kref); kref_get(&dreq->kref); init_completion(&dreq->completion); - INIT_LIST_HEAD(&dreq->rewrite_list); - dreq->iocb = NULL; - dreq->ctx = NULL; - dreq->l_ctx = NULL; + INIT_LIST_HEAD(&dreq->mds_cinfo.list); + INIT_WORK(&dreq->work, nfs_direct_write_schedule_work); spin_lock_init(&dreq->lock); - atomic_set(&dreq->io_count, 0); - dreq->count = 0; - dreq->error = 0; - dreq->flags = 0; return dreq; } @@ -226,47 +218,80 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) nfs_direct_req_release(dreq); } -/* - * We must hold a reference to all the pages in this direct read request - * until the RPCs complete. This could be long *after* we are woken up in - * nfs_direct_wait (for instance, if someone hits ^C on a slow server). - */ -static void nfs_direct_read_result(struct rpc_task *task, void *calldata) +static void nfs_direct_readpage_release(struct nfs_page *req) { - struct nfs_read_data *data = calldata; - - nfs_readpage_result(task, data); + dprintk("NFS: direct read done (%s/%lld %d@%lld)\n", + req->wb_context->dentry->d_inode->i_sb->s_id, + (long long)NFS_FILEID(req->wb_context->dentry->d_inode), + req->wb_bytes, + (long long)req_offset(req)); + nfs_release_request(req); } -static void nfs_direct_read_release(void *calldata) +static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) { + unsigned long bytes = 0; + struct nfs_direct_req *dreq = hdr->dreq; - struct nfs_read_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; - int status = data->task.tk_status; + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; spin_lock(&dreq->lock); - if (unlikely(status < 0)) { - dreq->error = status; - spin_unlock(&dreq->lock); - } else { - dreq->count += data->res.count; - spin_unlock(&dreq->lock); - nfs_direct_dirty_pages(data->pagevec, - data->args.pgbase, - data->res.count); - } - nfs_direct_release_pages(data->pagevec, data->npages); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0)) + dreq->error = hdr->error; + else + dreq->count += hdr->good_bytes; + spin_unlock(&dreq->lock); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { + if (bytes > hdr->good_bytes) + zero_user(page, 0, PAGE_SIZE); + else if (hdr->good_bytes - bytes < PAGE_SIZE) + zero_user_segment(page, + hdr->good_bytes & ~PAGE_MASK, + PAGE_SIZE); + } + if (!PageCompound(page)) { + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + if (bytes < hdr->good_bytes) + set_page_dirty(page); + } else + set_page_dirty(page); + } + bytes += req->wb_bytes; + nfs_list_remove_request(req); + nfs_direct_readpage_release(req); + } +out_put: if (put_dreq(dreq)) nfs_direct_complete(dreq); - nfs_readdata_free(data); + hdr->release(hdr); +} + +static void nfs_read_sync_pgio_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_release_request(req); + } } -static const struct rpc_call_ops nfs_read_direct_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_direct_read_result, - .rpc_release = nfs_direct_read_release, +static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr) +{ + get_dreq(hdr->dreq); +} + +static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { + .error_cleanup = nfs_read_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_read_completion, }; /* @@ -276,107 +301,82 @@ static const struct rpc_call_ops nfs_read_direct_ops = { * handled automatically by nfs_direct_read_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq, +static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, loff_t pos) { + struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->dentry->d_inode; unsigned long user_addr = (unsigned long)iov->iov_base; size_t count = iov->iov_len; size_t rsize = NFS_SERVER(inode)->rsize; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_cred = ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = NFS_CLIENT(inode), - .rpc_message = &msg, - .callback_ops = &nfs_read_direct_ops, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; unsigned int pgbase; int result; ssize_t started = 0; + struct page **pagevec = NULL; + unsigned int npages; do { - struct nfs_read_data *data; size_t bytes; + int i; pgbase = user_addr & ~PAGE_MASK; - bytes = min(rsize,count); + bytes = min(max_t(size_t, rsize, PAGE_SIZE), count); result = -ENOMEM; - data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + npages = nfs_page_array_len(pgbase, bytes); + if (!pagevec) + pagevec = kmalloc(npages * sizeof(struct page *), + GFP_KERNEL); + if (!pagevec) break; - down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 1, 0, data->pagevec, NULL); + npages, 1, 0, pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (result < 0) { - nfs_readdata_free(data); + if (result < 0) break; - } - if ((unsigned)result < data->npages) { + if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); - nfs_readdata_free(data); + nfs_direct_release_pages(pagevec, result); break; } bytes -= pgbase; - data->npages = result; + npages = result; } - get_dreq(dreq); - - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; - data->args.fh = NFS_FH(inode); - data->args.context = ctx; - data->args.lock_context = dreq->l_ctx; - data->args.offset = pos; - data->args.pgbase = pgbase; - data->args.pages = data->pagevec; - data->args.count = bytes; - data->res.fattr = &data->fattr; - data->res.eof = 0; - data->res.count = bytes; - nfs_fattr_init(&data->fattr); - msg.rpc_argp = &data->args; - msg.rpc_resp = &data->res; - - task_setup_data.task = &data->task; - task_setup_data.callback_data = data; - NFS_PROTO(inode)->read_setup(data, &msg); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - break; - rpc_put_task(task); - - dprintk("NFS: %5u initiated direct read call " - "(req %s/%Ld, %zu bytes @ offset %Lu)\n", - data->task.tk_pid, - inode->i_sb->s_id, - (long long)NFS_FILEID(inode), - bytes, - (unsigned long long)data->args.offset); - - started += bytes; - user_addr += bytes; - pos += bytes; - /* FIXME: Remove this unnecessary math from final patch */ - pgbase += bytes; - pgbase &= ~PAGE_MASK; - BUG_ON(pgbase != (user_addr & ~PAGE_MASK)); - - count -= bytes; - } while (count != 0); + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); + /* XXX do we need to do the eof zeroing found in async_filler? */ + req = nfs_create_request(dreq->ctx, dreq->inode, + pagevec[i], + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(desc, req)) { + result = desc->pg_error; + nfs_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + started += req_len; + user_addr += req_len; + pos += req_len; + count -= req_len; + } + /* The nfs_page now hold references to these pages */ + nfs_direct_release_pages(pagevec, npages); + } while (count != 0 && result >= 0); + + kfree(pagevec); if (started) return started; @@ -388,15 +388,19 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, unsigned long nr_segs, loff_t pos) { + struct nfs_pageio_descriptor desc; ssize_t result = -EINVAL; size_t requested_bytes = 0; unsigned long seg; + nfs_pageio_init_read(&desc, dreq->inode, + &nfs_direct_read_completion_ops); get_dreq(dreq); + desc.pg_dreq = dreq; for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(dreq, vec, pos); + result = nfs_direct_read_schedule_segment(&desc, vec, pos); if (result < 0) break; requested_bytes += result; @@ -405,6 +409,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, pos += vec->iov_len; } + nfs_pageio_complete(&desc); + /* * If no bytes were started, return the error, and let the * generic layer handle the completion. @@ -441,104 +447,71 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos); if (!result) result = nfs_direct_wait(dreq); + NFS_I(inode)->read_io += result; out_release: nfs_direct_req_release(dreq); out: return result; } -static void nfs_direct_free_writedata(struct nfs_direct_req *dreq) +static void nfs_inode_dio_write_done(struct inode *inode) { - while (!list_empty(&dreq->rewrite_list)) { - struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages); - list_del(&data->pages); - nfs_direct_release_pages(data->pagevec, data->npages); - nfs_writedata_free(data); - } + nfs_zap_mapping(inode, inode->i_mapping); + inode_dio_done(inode); } #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { - struct inode *inode = dreq->inode; - struct list_head *p; - struct nfs_write_data *data; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_cred = dreq->ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = NFS_CLIENT(inode), - .rpc_message = &msg, - .callback_ops = &nfs_write_direct_ops, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; + struct nfs_pageio_descriptor desc; + struct nfs_page *req, *tmp; + LIST_HEAD(reqs); + struct nfs_commit_info cinfo; + LIST_HEAD(failed); + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo); + spin_lock(cinfo.lock); + nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0); + spin_unlock(cinfo.lock); dreq->count = 0; get_dreq(dreq); - list_for_each(p, &dreq->rewrite_list) { - data = list_entry(p, struct nfs_write_data, pages); - - get_dreq(dreq); - - /* Use stable writes */ - data->args.stable = NFS_FILE_SYNC; - - /* - * Reset data->res. - */ - nfs_fattr_init(&data->fattr); - data->res.count = data->args.count; - memset(&data->verf, 0, sizeof(data->verf)); - - /* - * Reuse data->task; data->args should not have changed - * since the original request was sent. - */ - task_setup_data.task = &data->task; - task_setup_data.callback_data = data; - msg.rpc_argp = &data->args; - msg.rpc_resp = &data->res; - NFS_PROTO(inode)->write_setup(data, &msg); - - /* - * We're called via an RPC callback, so BKL is already held. - */ - task = rpc_run_task(&task_setup_data); - if (!IS_ERR(task)) - rpc_put_task(task); - - dprintk("NFS: %5u rescheduled direct write call (req %s/%Ld, %u bytes @ offset %Lu)\n", - data->task.tk_pid, - inode->i_sb->s_id, - (long long)NFS_FILEID(inode), - data->args.count, - (unsigned long long)data->args.offset); + nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, + &nfs_direct_write_completion_ops); + desc.pg_dreq = dreq; + + list_for_each_entry_safe(req, tmp, &reqs, wb_list) { + if (!nfs_pageio_add_request(&desc, req)) { + nfs_list_add_request(req, &failed); + spin_lock(cinfo.lock); + dreq->flags = 0; + dreq->error = -EIO; + spin_unlock(cinfo.lock); + } + nfs_release_request(req); } + nfs_pageio_complete(&desc); - if (put_dreq(dreq)) - nfs_direct_write_complete(dreq, inode); -} - -static void nfs_direct_commit_result(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; + while (!list_empty(&failed)) + nfs_unlock_and_release_request(req); - /* Call the NFS version-specific code */ - NFS_PROTO(data->inode)->commit_done(task, data); + if (put_dreq(dreq)) + nfs_direct_write_complete(dreq, dreq->inode); } -static void nfs_direct_commit_release(void *calldata) +static void nfs_direct_commit_complete(struct nfs_commit_data *data) { - struct nfs_write_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; + struct nfs_direct_req *dreq = data->dreq; + struct nfs_commit_info cinfo; + struct nfs_page *req; int status = data->task.tk_status; + nfs_init_cinfo_from_dreq(&cinfo, dreq); if (status < 0) { dprintk("NFS: %5u commit failed with error %d.\n", - data->task.tk_pid, status); + data->task.tk_pid, status); dreq->flags = NFS_ODIRECT_RESCHED_WRITES; } else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) { dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid); @@ -546,62 +519,47 @@ static void nfs_direct_commit_release(void *calldata) } dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status); - nfs_direct_write_complete(dreq, data->inode); - nfs_commit_free(data); + while (!list_empty(&data->pages)) { + req = nfs_list_entry(data->pages.next); + nfs_list_remove_request(req); + if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) { + /* Note the rewrite will go through mds */ + nfs_mark_request_commit(req, NULL, &cinfo); + } else + nfs_release_request(req); + nfs_unlock_and_release_request(req); + } + + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_direct_write_complete(dreq, data->inode); } -static const struct rpc_call_ops nfs_commit_direct_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_direct_commit_result, - .rpc_release = nfs_direct_commit_release, +static void nfs_direct_error_cleanup(struct nfs_inode *nfsi) +{ + /* There is no lock to clear */ +} + +static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = { + .completion = nfs_direct_commit_complete, + .error_cleanup = nfs_direct_error_cleanup, }; static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) { - struct nfs_write_data *data = dreq->commit_data; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_argp = &data->args, - .rpc_resp = &data->res, - .rpc_cred = dreq->ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .task = &data->task, - .rpc_client = NFS_CLIENT(dreq->inode), - .rpc_message = &msg, - .callback_ops = &nfs_commit_direct_ops, - .callback_data = data, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; - - data->inode = dreq->inode; - data->cred = msg.rpc_cred; - - data->args.fh = NFS_FH(data->inode); - data->args.offset = 0; - data->args.count = 0; - data->args.context = dreq->ctx; - data->args.lock_context = dreq->l_ctx; - data->res.count = 0; - data->res.fattr = &data->fattr; - data->res.verf = &data->verf; - nfs_fattr_init(&data->fattr); - - NFS_PROTO(data->inode)->commit_setup(data, &msg); - - /* Note: task.tk_ops->rpc_release will free dreq->commit_data */ - dreq->commit_data = NULL; - - dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid); - - task = rpc_run_task(&task_setup_data); - if (!IS_ERR(task)) - rpc_put_task(task); + int res; + struct nfs_commit_info cinfo; + LIST_HEAD(mds_list); + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_scan_commit(dreq->inode, &mds_list, &cinfo); + res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); + if (res < 0) /* res == -ENOMEM */ + nfs_direct_write_reschedule(dreq); } -static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) +static void nfs_direct_write_schedule_work(struct work_struct *work) { + struct nfs_direct_req *dreq = container_of(work, struct nfs_direct_req, work); int flags = dreq->flags; dreq->flags = 0; @@ -613,89 +571,32 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode nfs_direct_write_reschedule(dreq); break; default: - if (dreq->commit_data != NULL) - nfs_commit_free(dreq->commit_data); - nfs_direct_free_writedata(dreq); - nfs_zap_mapping(inode, inode->i_mapping); + nfs_inode_dio_write_done(dreq->inode); nfs_direct_complete(dreq); } } -static void nfs_alloc_commit_data(struct nfs_direct_req *dreq) +static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) { - dreq->commit_data = nfs_commitdata_alloc(); - if (dreq->commit_data != NULL) - dreq->commit_data->req = (struct nfs_page *) dreq; + schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */ } + #else -static inline void nfs_alloc_commit_data(struct nfs_direct_req *dreq) +static void nfs_direct_write_schedule_work(struct work_struct *work) { - dreq->commit_data = NULL; } static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode) { - nfs_direct_free_writedata(dreq); - nfs_zap_mapping(inode, inode->i_mapping); + nfs_inode_dio_write_done(inode); nfs_direct_complete(dreq); } #endif -static void nfs_direct_write_result(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - - nfs_writeback_done(task, data); -} - /* * NB: Return the value of the first error return code. Subsequent * errors after the first one are ignored. */ -static void nfs_direct_write_release(void *calldata) -{ - struct nfs_write_data *data = calldata; - struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req; - int status = data->task.tk_status; - - spin_lock(&dreq->lock); - - if (unlikely(status < 0)) { - /* An error has occurred, so we should not commit */ - dreq->flags = 0; - dreq->error = status; - } - if (unlikely(dreq->error != 0)) - goto out_unlock; - - dreq->count += data->res.count; - - if (data->res.verf->committed != NFS_FILE_SYNC) { - switch (dreq->flags) { - case 0: - memcpy(&dreq->verf, &data->verf, sizeof(dreq->verf)); - dreq->flags = NFS_ODIRECT_DO_COMMIT; - break; - case NFS_ODIRECT_DO_COMMIT: - if (memcmp(&dreq->verf, &data->verf, sizeof(dreq->verf))) { - dprintk("NFS: %5u write verify failed\n", data->task.tk_pid); - dreq->flags = NFS_ODIRECT_RESCHED_WRITES; - } - } - } -out_unlock: - spin_unlock(&dreq->lock); - - if (put_dreq(dreq)) - nfs_direct_write_complete(dreq, data->inode); -} - -static const struct rpc_call_ops nfs_write_direct_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_direct_write_result, - .rpc_release = nfs_direct_write_release, -}; - /* * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE * operation. If nfs_writedata_alloc() or get_user_pages() fails, @@ -703,132 +604,189 @@ static const struct rpc_call_ops nfs_write_direct_ops = { * handled automatically by nfs_direct_write_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq, +static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, - loff_t pos, int sync) + loff_t pos) { + struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; struct inode *inode = ctx->dentry->d_inode; unsigned long user_addr = (unsigned long)iov->iov_base; size_t count = iov->iov_len; - struct rpc_task *task; - struct rpc_message msg = { - .rpc_cred = ctx->cred, - }; - struct rpc_task_setup task_setup_data = { - .rpc_client = NFS_CLIENT(inode), - .rpc_message = &msg, - .callback_ops = &nfs_write_direct_ops, - .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, - }; size_t wsize = NFS_SERVER(inode)->wsize; unsigned int pgbase; int result; ssize_t started = 0; + struct page **pagevec = NULL; + unsigned int npages; do { - struct nfs_write_data *data; size_t bytes; + int i; pgbase = user_addr & ~PAGE_MASK; - bytes = min(wsize,count); + bytes = min(max_t(size_t, wsize, PAGE_SIZE), count); result = -ENOMEM; - data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes)); - if (unlikely(!data)) + npages = nfs_page_array_len(pgbase, bytes); + if (!pagevec) + pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL); + if (!pagevec) break; down_read(¤t->mm->mmap_sem); result = get_user_pages(current, current->mm, user_addr, - data->npages, 0, 0, data->pagevec, NULL); + npages, 0, 0, pagevec, NULL); up_read(¤t->mm->mmap_sem); - if (result < 0) { - nfs_writedata_free(data); + if (result < 0) break; - } - if ((unsigned)result < data->npages) { + + if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { - nfs_direct_release_pages(data->pagevec, result); - nfs_writedata_free(data); + nfs_direct_release_pages(pagevec, result); break; } bytes -= pgbase; - data->npages = result; + npages = result; } - get_dreq(dreq); - - list_move_tail(&data->pages, &dreq->rewrite_list); - - data->req = (struct nfs_page *) dreq; - data->inode = inode; - data->cred = msg.rpc_cred; - data->args.fh = NFS_FH(inode); - data->args.context = ctx; - data->args.lock_context = dreq->l_ctx; - data->args.offset = pos; - data->args.pgbase = pgbase; - data->args.pages = data->pagevec; - data->args.count = bytes; - data->args.stable = sync; - data->res.fattr = &data->fattr; - data->res.count = bytes; - data->res.verf = &data->verf; - nfs_fattr_init(&data->fattr); - - task_setup_data.task = &data->task; - task_setup_data.callback_data = data; - msg.rpc_argp = &data->args; - msg.rpc_resp = &data->res; - NFS_PROTO(inode)->write_setup(data, &msg); - - task = rpc_run_task(&task_setup_data); - if (IS_ERR(task)) - break; - rpc_put_task(task); + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); - dprintk("NFS: %5u initiated direct write call " - "(req %s/%Ld, %zu bytes @ offset %Lu)\n", - data->task.tk_pid, - inode->i_sb->s_id, - (long long)NFS_FILEID(inode), - bytes, - (unsigned long long)data->args.offset); - - started += bytes; - user_addr += bytes; - pos += bytes; - - /* FIXME: Remove this useless math from the final patch */ - pgbase += bytes; - pgbase &= ~PAGE_MASK; - BUG_ON(pgbase != (user_addr & ~PAGE_MASK)); + req = nfs_create_request(dreq->ctx, dreq->inode, + pagevec[i], + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + nfs_lock_request(req); + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(desc, req)) { + result = desc->pg_error; + nfs_unlock_and_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + started += req_len; + user_addr += req_len; + pos += req_len; + count -= req_len; + } + /* The nfs_page now hold references to these pages */ + nfs_direct_release_pages(pagevec, npages); + } while (count != 0 && result >= 0); - count -= bytes; - } while (count != 0); + kfree(pagevec); if (started) return started; return result < 0 ? (ssize_t) result : -EFAULT; } +static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) +{ + struct nfs_direct_req *dreq = hdr->dreq; + struct nfs_commit_info cinfo; + int bit = -1; + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out_put; + + nfs_init_cinfo_from_dreq(&cinfo, dreq); + + spin_lock(&dreq->lock); + + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + dreq->flags = 0; + dreq->error = hdr->error; + } + if (dreq->error != 0) + bit = NFS_IOHDR_ERROR; + else { + dreq->count += hdr->good_bytes; + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) { + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + bit = NFS_IOHDR_NEED_RESCHED; + } else if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { + if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) + bit = NFS_IOHDR_NEED_RESCHED; + else if (dreq->flags == 0) { + memcpy(&dreq->verf, hdr->verf, + sizeof(dreq->verf)); + bit = NFS_IOHDR_NEED_COMMIT; + dreq->flags = NFS_ODIRECT_DO_COMMIT; + } else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) { + if (memcmp(&dreq->verf, hdr->verf, sizeof(dreq->verf))) { + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + bit = NFS_IOHDR_NEED_RESCHED; + } else + bit = NFS_IOHDR_NEED_COMMIT; + } + } + } + spin_unlock(&dreq->lock); + + while (!list_empty(&hdr->pages)) { + req = nfs_list_entry(hdr->pages.next); + nfs_list_remove_request(req); + switch (bit) { + case NFS_IOHDR_NEED_RESCHED: + case NFS_IOHDR_NEED_COMMIT: + kref_get(&req->wb_kref); + nfs_mark_request_commit(req, hdr->lseg, &cinfo); + } + nfs_unlock_and_release_request(req); + } + +out_put: + if (put_dreq(dreq)) + nfs_direct_write_complete(dreq, hdr->inode); + hdr->release(hdr); +} + +static void nfs_write_sync_pgio_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_unlock_and_release_request(req); + } +} + +static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { + .error_cleanup = nfs_write_sync_pgio_error, + .init_hdr = nfs_direct_pgio_init, + .completion = nfs_direct_write_completion, +}; + static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, const struct iovec *iov, unsigned long nr_segs, - loff_t pos, int sync) + loff_t pos) { + struct nfs_pageio_descriptor desc; + struct inode *inode = dreq->inode; ssize_t result = 0; size_t requested_bytes = 0; unsigned long seg; + nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, + &nfs_direct_write_completion_ops); + desc.pg_dreq = dreq; get_dreq(dreq); + atomic_inc(&inode->i_dio_count); for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_write_schedule_segment(dreq, vec, - pos, sync); + result = nfs_direct_write_schedule_segment(&desc, vec, pos); if (result < 0) break; requested_bytes += result; @@ -836,12 +794,15 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, break; pos += vec->iov_len; } + nfs_pageio_complete(&desc); + NFS_I(dreq->inode)->write_io += desc.pg_bytes_written; /* * If no bytes were started, return the error, and let the * generic layer handle the completion. */ if (requested_bytes == 0) { + inode_dio_done(inode); nfs_direct_req_release(dreq); return result < 0 ? result : -EIO; } @@ -858,16 +819,10 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, ssize_t result = -ENOMEM; struct inode *inode = iocb->ki_filp->f_mapping->host; struct nfs_direct_req *dreq; - size_t wsize = NFS_SERVER(inode)->wsize; - int sync = NFS_UNSTABLE; dreq = nfs_direct_req_alloc(); if (!dreq) goto out; - nfs_alloc_commit_data(dreq); - - if (dreq->commit_data == NULL || count <= wsize) - sync = NFS_FILE_SYNC; dreq->inode = inode; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); @@ -877,7 +832,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync); + result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos); if (!result) result = nfs_direct_wait(dreq); out_release: @@ -997,10 +952,15 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, task_io_account_write(count); retval = nfs_direct_write(iocb, iov, nr_segs, pos, count); + if (retval > 0) { + struct inode *inode = mapping->host; - if (retval > 0) iocb->ki_pos = pos + retval; - + spin_lock(&inode->i_lock); + if (i_size_read(inode) < iocb->ki_pos) + i_size_write(inode, iocb->ki_pos); + spin_unlock(&inode->i_lock); + } out: return retval; } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index aa9b709fd32..a6708e6b438 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -174,6 +174,13 @@ nfs_file_flush(struct file *file, fl_owner_t id) if ((file->f_mode & FMODE_WRITE) == 0) return 0; + /* + * If we're holding a write delegation, then just start the i/o + * but don't wait for completion (or send a commit). + */ + if (nfs_have_delegation(inode, FMODE_WRITE)) + return filemap_fdatawrite(file->f_mapping); + /* Flush writes to the server and return any errors */ return vfs_fsync(file, 0); } @@ -417,6 +424,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping, if (status < 0) return status; + NFS_I(mapping->host)->write_io += copied; return copied; } @@ -871,12 +879,81 @@ const struct file_operations nfs_file_operations = { static int nfs4_file_open(struct inode *inode, struct file *filp) { + struct nfs_open_context *ctx; + struct dentry *dentry = filp->f_path.dentry; + struct dentry *parent = NULL; + struct inode *dir; + unsigned openflags = filp->f_flags; + struct iattr attr; + int err; + + BUG_ON(inode != dentry->d_inode); /* - * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to - * this point, then something is very wrong + * If no cached dentry exists or if it's negative, NFSv4 handled the + * opens in ->lookup() or ->create(). + * + * We only get this far for a cached positive dentry. We skipped + * revalidation, so handle it here by dropping the dentry and returning + * -EOPENSTALE. The VFS will retry the lookup/create/open. */ - dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp); - return -ENOTDIR; + + dprintk("NFS: open file(%s/%s)\n", + dentry->d_parent->d_name.name, + dentry->d_name.name); + + if ((openflags & O_ACCMODE) == 3) + openflags--; + + /* We can't create new files here */ + openflags &= ~(O_CREAT|O_EXCL); + + parent = dget_parent(dentry); + dir = parent->d_inode; + + ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + + attr.ia_valid = ATTR_OPEN; + if (openflags & O_TRUNC) { + attr.ia_valid |= ATTR_SIZE; + attr.ia_size = 0; + nfs_wb_all(inode); + } + + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + switch (err) { + case -EPERM: + case -EACCES: + case -EDQUOT: + case -ENOSPC: + case -EROFS: + goto out_put_ctx; + default: + goto out_drop; + } + } + iput(inode); + if (inode != dentry->d_inode) + goto out_drop; + + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + nfs_file_set_open_context(filp, ctx); + err = 0; + +out_put_ctx: + put_nfs_open_context(ctx); +out: + dput(parent); + return err; + +out_drop: + d_drop(dentry); + err = -EOPENSTALE; + goto out_put_ctx; } const struct file_operations nfs4_file_operations = { diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index ae65c16b367..c817787fbdb 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -64,23 +64,12 @@ void nfs_fscache_release_client_cookie(struct nfs_client *clp) * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent * superblock across an automount point of some nature. */ -void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, - struct nfs_clone_mount *mntdata) +void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) { struct nfs_fscache_key *key, *xkey; struct nfs_server *nfss = NFS_SB(sb); struct rb_node **p, *parent; - int diff, ulen; - - if (uniq) { - ulen = strlen(uniq); - } else if (mntdata) { - struct nfs_server *mnt_s = NFS_SB(mntdata->sb); - if (mnt_s->fscache_key) { - uniq = mnt_s->fscache_key->key.uniquifier; - ulen = mnt_s->fscache_key->key.uniq_len; - } - } + int diff; if (!uniq) { uniq = ""; diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index b9c572d0679..c5b11b53ff3 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -73,9 +73,7 @@ extern void nfs_fscache_unregister(void); extern void nfs_fscache_get_client_cookie(struct nfs_client *); extern void nfs_fscache_release_client_cookie(struct nfs_client *); -extern void nfs_fscache_get_super_cookie(struct super_block *, - const char *, - struct nfs_clone_mount *); +extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); extern void nfs_fscache_release_super_cookie(struct super_block *); extern void nfs_fscache_init_inode_cookie(struct inode *); @@ -172,12 +170,6 @@ static inline void nfs_fscache_unregister(void) {} static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} -static inline void nfs_fscache_get_super_cookie( - struct super_block *sb, - const char *uniq, - struct nfs_clone_mount *mntdata) -{ -} static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {} diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 4ca6f5c8038..8abfb19bd3a 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -150,7 +150,7 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh) goto out; /* Start by getting the root filehandle from the server */ - ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo); + ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo); if (ret < 0) { dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret); goto out; @@ -178,87 +178,4 @@ out: return ret; } -/* - * get an NFS4 root dentry from the root filehandle - */ -struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh, - const char *devname) -{ - struct nfs_server *server = NFS_SB(sb); - struct nfs_fattr *fattr = NULL; - struct dentry *ret; - struct inode *inode; - void *name = kstrdup(devname, GFP_KERNEL); - int error; - - dprintk("--> nfs4_get_root()\n"); - - if (!name) - return ERR_PTR(-ENOMEM); - - /* get the info about the server and filesystem */ - error = nfs4_server_capabilities(server, mntfh); - if (error < 0) { - dprintk("nfs_get_root: getcaps error = %d\n", - -error); - kfree(name); - return ERR_PTR(error); - } - - fattr = nfs_alloc_fattr(); - if (fattr == NULL) { - kfree(name); - return ERR_PTR(-ENOMEM); - } - - /* get the actual root for this mount */ - error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr); - if (error < 0) { - dprintk("nfs_get_root: getattr error = %d\n", -error); - ret = ERR_PTR(error); - goto out; - } - - if (fattr->valid & NFS_ATTR_FATTR_FSID && - !nfs_fsid_equal(&server->fsid, &fattr->fsid)) - memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid)); - - inode = nfs_fhget(sb, mntfh, fattr); - if (IS_ERR(inode)) { - dprintk("nfs_get_root: get root inode failed\n"); - ret = ERR_CAST(inode); - goto out; - } - - error = nfs_superblock_set_dummy_root(sb, inode); - if (error != 0) { - ret = ERR_PTR(error); - goto out; - } - - /* root dentries normally start off anonymous and get spliced in later - * if the dentry tree reaches them; however if the dentry already - * exists, we'll pick it up at this point and use it as the root - */ - ret = d_obtain_alias(inode); - if (IS_ERR(ret)) { - dprintk("nfs_get_root: get root dentry failed\n"); - goto out; - } - - security_d_instantiate(ret, inode); - spin_lock(&ret->d_lock); - if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) { - ret->d_fsdata = name; - name = NULL; - } - spin_unlock(&ret->d_lock); -out: - if (name) - kfree(name); - nfs_free_fattr(fattr); - dprintk("<-- nfs4_get_root()\n"); - return ret; -} - #endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b7f348bb618..864c51e4b40 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -57,6 +57,11 @@ unsigned int nfs_idmap_cache_timeout = 600; static const struct cred *id_resolver_cache; static struct key_type key_type_id_resolver_legacy; +struct idmap { + struct rpc_pipe *idmap_pipe; + struct key_construction *idmap_key_cons; + struct mutex idmap_mutex; +}; /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields @@ -310,9 +315,11 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, name, namelen, type, data, data_size, NULL); if (ret < 0) { + mutex_lock(&idmap->idmap_mutex); ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + mutex_unlock(&idmap->idmap_mutex); } return ret; } @@ -354,11 +361,6 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ /* idmap classic begins here */ module_param(nfs_idmap_cache_timeout, int, 0644); -struct idmap { - struct rpc_pipe *idmap_pipe; - struct key_construction *idmap_key_cons; -}; - enum { Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err }; @@ -415,7 +417,7 @@ static int __nfs_idmap_register(struct dentry *dir, static void nfs_idmap_unregister(struct nfs_client *clp, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; pipefs_sb = rpc_get_sb_net(net); @@ -429,7 +431,7 @@ static int nfs_idmap_register(struct nfs_client *clp, struct idmap *idmap, struct rpc_pipe *pipe) { - struct net *net = clp->net; + struct net *net = clp->cl_net; struct super_block *pipefs_sb; int err = 0; @@ -469,6 +471,7 @@ nfs_idmap_new(struct nfs_client *clp) return error; } idmap->idmap_pipe = pipe; + mutex_init(&idmap->idmap_mutex); clp->cl_idmap = idmap; return 0; @@ -530,9 +533,25 @@ static struct nfs_client *nfs_get_client_for_event(struct net *net, int event) struct nfs_net *nn = net_generic(net, nfs_net_id); struct dentry *cl_dentry; struct nfs_client *clp; + int err; +restart: spin_lock(&nn->nfs_client_lock); list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { + /* Wait for initialisation to finish */ + if (clp->cl_cons_state == NFS_CS_INITING) { + atomic_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + err = nfs_wait_client_init_complete(clp); + nfs_put_client(clp); + if (err) + return NULL; + goto restart; + } + /* Skip nfs_clients that failed to initialise */ + if (clp->cl_cons_state < 0) + continue; + smp_rmb(); if (clp->rpc_ops != &nfs_v4_clientops) continue; cl_dentry = clp->cl_idmap->idmap_pipe->dentry; @@ -554,12 +573,16 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event, struct nfs_client *clp; int error = 0; + if (!try_module_get(THIS_MODULE)) + return 0; + while ((clp = nfs_get_client_for_event(sb->s_fs_info, event))) { error = __rpc_pipefs_event(clp, event, sb); nfs_put_client(clp); if (error) break; } + module_put(THIS_MODULE); return error; } @@ -636,20 +659,16 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; struct key *key = cons->key; - int ret; + int ret = -ENOMEM; /* msg and im are freed in idmap_pipe_destroy_msg */ msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (IS_ERR(msg)) { - ret = PTR_ERR(msg); + if (!msg) goto out0; - } im = kmalloc(sizeof(*im), GFP_KERNEL); - if (IS_ERR(im)) { - ret = PTR_ERR(im); + if (!im) goto out1; - } ret = nfs_idmap_prepare_message(key->description, im, msg); if (ret < 0) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index e8bbfa5b350..f7296983eba 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -121,7 +121,7 @@ static void nfs_clear_inode(struct inode *inode) void nfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); nfs_clear_inode(inode); } @@ -285,9 +285,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_mode = fattr->mode; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && nfs_server_capable(inode, NFS_CAP_MODE)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ @@ -300,8 +298,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; - if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)) - set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { @@ -327,6 +323,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) inode->i_gid = -2; inode->i_blocks = 0; memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + nfsi->write_io = 0; + nfsi->read_io = 0; nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; @@ -337,24 +335,19 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; else if (nfs_server_capable(inode, NFS_CAP_MTIME)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else if (nfs_server_capable(inode, NFS_CAP_CTIME)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA | NFS_INO_REVAL_PAGECACHE; if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); @@ -363,15 +356,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (nfs_server_capable(inode, NFS_CAP_OWNER)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { @@ -429,8 +418,10 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) return 0; /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode)) { + nfs_inode_dio_wait(inode); nfs_wb_all(inode); + } fattr = nfs_alloc_fattr(); if (fattr == NULL) @@ -514,6 +505,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) /* Flush out writes to the server in order to update c/mtime. */ if (S_ISREG(inode->i_mode)) { + nfs_inode_dio_wait(inode); err = filemap_write_and_wait(inode->i_mapping); if (err) goto out; @@ -654,6 +646,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; INIT_LIST_HEAD(&ctx->list); + ctx->mdsthreshold = NULL; return ctx; } @@ -682,6 +675,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) put_rpccred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); + kfree(ctx->mdsthreshold); kfree(ctx); } @@ -870,6 +864,15 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return 0; } +static bool nfs_mapping_need_revalidate_inode(struct inode *inode) +{ + if (nfs_have_delegated_attributes(inode)) + return false; + return (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE) + || nfs_attribute_timeout(inode) + || NFS_STALE(inode); +} + /** * nfs_revalidate_mapping - Revalidate the pagecache * @inode - pointer to host inode @@ -880,9 +883,7 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; - if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) - || nfs_attribute_cache_expired(inode) - || NFS_STALE(inode)) { + if (nfs_mapping_need_revalidate_inode(inode)) { ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) goto out; @@ -948,6 +949,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat unsigned long invalid = 0; + if (nfs_have_delegated_attributes(inode)) + return 0; /* Has the inode gone and changed behind our back? */ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) return -EIO; @@ -960,7 +963,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat /* Verify a few of the more important attributes */ if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime)) - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; + invalid |= NFS_INO_INVALID_ATTR; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); @@ -1279,14 +1282,26 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_display_fhandle_hash(NFS_FH(inode)), atomic_read(&inode->i_count), fattr->valid); - if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) - goto out_fileid; + if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) { + printk(KERN_ERR "NFS: server %s error: fileid changed\n" + "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", + NFS_SERVER(inode)->nfs_client->cl_hostname, + inode->i_sb->s_id, (long long)nfsi->fileid, + (long long)fattr->fileid); + goto out_err; + } /* * Make sure the inode's type hasn't changed. */ - if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) - goto out_changed; + if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) { + /* + * Big trouble! The inode has become a different object. + */ + printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n", + __func__, inode->i_ino, inode->i_mode, fattr->mode); + goto out_err; + } server = NFS_SERVER(inode); /* Update the fsid? */ @@ -1314,7 +1329,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (inode->i_version != fattr->change_attr) { dprintk("NFS: change_attr change on server for file %s/%ld\n", inode->i_sb->s_id, inode->i_ino); - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + invalid |= NFS_INO_INVALID_ATTR + | NFS_INO_INVALID_DATA + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_REVAL_PAGECACHE; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; @@ -1323,38 +1342,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { - /* NFSv2/v3: Check if the mtime agrees */ - if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) { - dprintk("NFS: mtime change on server for file %s/%ld\n", - inode->i_sb->s_id, inode->i_ino); - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; - if (S_ISDIR(inode->i_mode)) - nfs_force_lookup_revalidate(inode); - memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); - } + memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); } else if (server->caps & NFS_CAP_MTIME) invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_DATA - | NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); if (fattr->valid & NFS_ATTR_FATTR_CTIME) { - /* If ctime has changed we should definitely clear access+acl caches */ - if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) { - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; - /* and probably clear data for a directory too as utimes can cause - * havoc with our cache. - */ - if (S_ISDIR(inode->i_mode)) { - invalid |= NFS_INO_INVALID_DATA; - nfs_force_lookup_revalidate(inode); - } - memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); - } + memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime)); } else if (server->caps & NFS_CAP_CTIME) invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR - | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL | NFS_INO_REVAL_FORCED); /* Check if our cached file size is stale */ @@ -1466,12 +1462,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfsi->cache_validity |= invalid; return 0; - out_changed: - /* - * Big trouble! The inode has become a different object. - */ - printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n", - __func__, inode->i_ino, inode->i_mode, fattr->mode); out_err: /* * No need to worry about unhashing the dentry, as the @@ -1480,13 +1470,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) */ nfs_invalidate_inode(inode); return -ESTALE; - - out_fileid: - printk(KERN_ERR "NFS: server %s error: fileid changed\n" - "fsid %s: expected fileid 0x%Lx, got 0x%Lx\n", - NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id, - (long long)nfsi->fileid, (long long)fattr->fileid); - goto out_err; } @@ -1500,7 +1483,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) void nfs4_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); pnfs_return_layout(inode); pnfs_destroy_layout(NFS_I(inode)); /* If we are holding a delegation, return it! */ @@ -1547,7 +1530,6 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); nfsi->layout = NULL; - atomic_set(&nfsi->commits_outstanding, 0); #endif } @@ -1559,9 +1541,10 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); - INIT_LIST_HEAD(&nfsi->commit_list); + INIT_LIST_HEAD(&nfsi->commit_info.list); nfsi->npages = 0; - nfsi->ncommit = 0; + nfsi->commit_info.ncommit = 0; + atomic_set(&nfsi->commit_info.rpcs_out, 0); atomic_set(&nfsi->silly_count, 1); INIT_HLIST_HEAD(&nfsi->silly_list); init_waitqueue_head(&nfsi->waitqueue); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 2476dc69365..18f99ef7134 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -103,6 +103,7 @@ struct nfs_parsed_mount_data { unsigned int version; unsigned int minorversion; char *fscache_uniq; + bool need_mount; struct { struct sockaddr_storage address; @@ -165,12 +166,15 @@ extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *); + struct nfs_fattr *, + rpc_authflavor_t); +extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); -extern int nfs4_check_client_ready(struct nfs_client *clp); extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, const struct sockaddr *ds_addr, - int ds_addrlen, int ds_proto); + int ds_addrlen, int ds_proto, + unsigned int ds_timeo, + unsigned int ds_retrans); #ifdef CONFIG_PROC_FS extern int __init nfs_fs_proc_init(void); extern void nfs_fs_proc_exit(void); @@ -184,21 +188,11 @@ static inline void nfs_fs_proc_exit(void) } #endif -/* nfs4namespace.c */ -#ifdef CONFIG_NFS_V4 -extern struct vfsmount *nfs_do_refmount(struct dentry *dentry); -#else -static inline -struct vfsmount *nfs_do_refmount(struct dentry *dentry) -{ - return ERR_PTR(-ENOENT); -} -#endif - /* callback_xdr.c */ extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; +struct nfs_pageio_descriptor; /* pagelist.c */ extern int __init nfs_init_nfspagecache(void); extern void nfs_destroy_nfspagecache(void); @@ -209,9 +203,13 @@ extern void nfs_destroy_writepagecache(void); extern int __init nfs_init_directcache(void); extern void nfs_destroy_directcache(void); +extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount); +extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)); +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos); /* nfs2xdr.c */ -extern int nfs_stat_to_errno(enum nfs_stat); extern struct rpc_procinfo nfs_procedures[]; extern int nfs2_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); @@ -234,17 +232,15 @@ extern const u32 nfs41_maxwrite_overhead; /* nfs4proc.c */ #ifdef CONFIG_NFS_V4 extern struct rpc_procinfo nfs4_procedures[]; -void nfs_fixup_secinfo_attributes(struct nfs_fattr *, struct nfs_fh *); #endif -extern int nfs4_init_ds_session(struct nfs_client *clp); +extern int nfs4_init_ds_session(struct nfs_client *, unsigned long); /* proc.c */ void nfs_close_context(struct nfs_open_context *ctx, int is_sync); -extern int nfs_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, - const char *ip_addr, rpc_authflavor_t authflavour, - int noresvport); + const char *ip_addr, rpc_authflavor_t authflavour); /* dir.c */ extern int nfs_access_cache_shrinker(struct shrinker *shrink, @@ -280,9 +276,10 @@ extern void nfs_sb_deactive(struct super_block *sb); extern char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen); extern struct vfsmount *nfs_d_automount(struct path *path); -#ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); -#endif +struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); +struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, @@ -294,46 +291,73 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh); #endif -struct nfs_pageio_descriptor; +struct nfs_pgio_completion_ops; /* read.c */ -extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt, - const struct rpc_call_ops *call_ops); +extern struct nfs_read_header *nfs_readhdr_alloc(void); +extern void nfs_readhdr_free(struct nfs_pgio_header *hdr); +extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops); +extern int nfs_initiate_read(struct rpc_clnt *clnt, + struct nfs_read_data *data, + const struct rpc_call_ops *call_ops, int flags); extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, - struct list_head *head); - + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode); + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); /* write.c */ +extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); +extern struct nfs_write_header *nfs_writehdr_alloc(void); +extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, - struct list_head *head); + struct nfs_pgio_header *hdr); extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags); + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_writedata_release(struct nfs_write_data *wdata); -extern void nfs_commit_free(struct nfs_write_data *p); -extern int nfs_initiate_write(struct nfs_write_data *data, - struct rpc_clnt *clnt, +extern void nfs_commit_free(struct nfs_commit_data *p); +extern int nfs_initiate_write(struct rpc_clnt *clnt, + struct nfs_write_data *data, const struct rpc_call_ops *call_ops, - int how); + int how, int flags); extern void nfs_write_prepare(struct rpc_task *task, void *calldata); -extern int nfs_initiate_commit(struct nfs_write_data *data, - struct rpc_clnt *clnt, +extern void nfs_commit_prepare(struct rpc_task *task, void *calldata); +extern int nfs_initiate_commit(struct rpc_clnt *clnt, + struct nfs_commit_data *data, const struct rpc_call_ops *call_ops, - int how); -extern void nfs_init_commit(struct nfs_write_data *data, + int how, int flags); +extern void nfs_init_commit(struct nfs_commit_data *data, struct list_head *head, - struct pnfs_layout_segment *lseg); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); +int nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max); +int nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_mark_request_commit(struct nfs_page *req, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); +int nfs_generic_commit_list(struct inode *inode, struct list_head *head, + int how, struct nfs_commit_info *cinfo); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg); -void nfs_commit_clear_lock(struct nfs_inode *nfsi); -void nfs_commitdata_release(void *data); -void nfs_commit_release_pages(struct nfs_write_data *data); -void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head); -void nfs_request_remove_commit_list(struct nfs_page *req); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); +void nfs_commitdata_release(struct nfs_commit_data *data); +void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo); +void nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo); +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq); #ifdef CONFIG_MIGRATION extern int nfs_migrate_page(struct address_space *, @@ -342,15 +366,20 @@ extern int nfs_migrate_page(struct address_space *, #define nfs_migrate_page NULL #endif +/* direct.c */ +void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo, + struct nfs_direct_req *dreq); +static inline void nfs_inode_dio_wait(struct inode *inode) +{ + inode_dio_wait(inode); +} + /* nfs4proc.c */ extern void __nfs4_read_done_cb(struct nfs_read_data *); -extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data); -extern int nfs4_init_client(struct nfs_client *clp, +extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms, const char *ip_addr, - rpc_authflavor_t authflavour, - int noresvport); -extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data); + rpc_authflavor_t authflavour); extern int _nfs4_call_sync(struct rpc_clnt *clnt, struct nfs_server *server, struct rpc_message *msg, @@ -466,3 +495,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len) PAGE_SIZE - 1) >> PAGE_SHIFT; } +/* + * Convert a struct timespec into a 64-bit change attribute + * + * This does approximately the same thing as timespec_to_ns(), + * but for calculation efficiency, we multiply the seconds by + * 1024*1024*1024. + */ +static inline +u64 nfs_timespec_to_change_attr(const struct timespec *ts) +{ + return ((u64)ts->tv_sec << 30) + ts->tv_nsec; +} diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 1807866bb3a..08b9c93675d 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -26,11 +26,6 @@ static LIST_HEAD(nfs_automount_list); static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts); int nfs_mountpoint_expiry_timeout = 500 * HZ; -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor); - /* * nfs_path - reconstruct the path given an arbitrary dentry * @base - used to return pointer to the end of devname part of path @@ -118,99 +113,6 @@ Elong: return ERR_PTR(-ENAMETOOLONG); } -#ifdef CONFIG_NFS_V4 -rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) -{ - struct gss_api_mech *mech; - struct xdr_netobj oid; - int i; - rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; - - for (i = 0; i < flavors->num_flavors; i++) { - struct nfs4_secinfo_flavor *flavor; - flavor = &flavors->flavors[i]; - - if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { - pseudoflavor = flavor->flavor; - break; - } else if (flavor->flavor == RPC_AUTH_GSS) { - oid.len = flavor->gss.sec_oid4.len; - oid.data = flavor->gss.sec_oid4.data; - mech = gss_mech_get_by_OID(&oid); - if (!mech) - continue; - pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); - gss_mech_put(mech); - break; - } - } - - return pseudoflavor; -} - -static int nfs_negotiate_security(const struct dentry *parent, - const struct dentry *dentry, - rpc_authflavor_t *flavor) -{ - struct page *page; - struct nfs4_secinfo_flavors *flavors; - int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); - int ret = -EPERM; - - secinfo = NFS_PROTO(parent->d_inode)->secinfo; - if (secinfo != NULL) { - page = alloc_page(GFP_KERNEL); - if (!page) { - ret = -ENOMEM; - goto out; - } - flavors = page_address(page); - ret = secinfo(parent->d_inode, &dentry->d_name, flavors); - *flavor = nfs_find_best_sec(flavors); - put_page(page); - } - -out: - return ret; -} - -static int nfs_lookup_with_sec(struct nfs_server *server, struct dentry *parent, - struct dentry *dentry, struct path *path, - struct nfs_fh *fh, struct nfs_fattr *fattr, - rpc_authflavor_t *flavor) -{ - struct rpc_clnt *clone; - struct rpc_auth *auth; - int err; - - err = nfs_negotiate_security(parent, path->dentry, flavor); - if (err < 0) - goto out; - clone = rpc_clone_client(server->client); - auth = rpcauth_create(*flavor, clone); - if (!auth) { - err = -EIO; - goto out_shutdown; - } - err = server->nfs_client->rpc_ops->lookup(clone, parent->d_inode, - &path->dentry->d_name, - fh, fattr); -out_shutdown: - rpc_shutdown_client(clone); -out: - return err; -} -#else /* CONFIG_NFS_V4 */ -static inline int nfs_lookup_with_sec(struct nfs_server *server, - struct dentry *parent, struct dentry *dentry, - struct path *path, struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t *flavor) -{ - return -EPERM; -} -#endif /* CONFIG_NFS_V4 */ - /* * nfs_d_automount - Handle crossing a mountpoint on the server * @path - The mountpoint @@ -227,11 +129,8 @@ struct vfsmount *nfs_d_automount(struct path *path) { struct vfsmount *mnt; struct nfs_server *server = NFS_SERVER(path->dentry->d_inode); - struct dentry *parent; struct nfs_fh *fh = NULL; struct nfs_fattr *fattr = NULL; - int err; - rpc_authflavor_t flavor = RPC_AUTH_UNIX; dprintk("--> nfs_d_automount()\n"); @@ -247,23 +146,7 @@ struct vfsmount *nfs_d_automount(struct path *path) dprintk("%s: enter\n", __func__); - /* Look it up again to get its attributes */ - parent = dget_parent(path->dentry); - err = server->nfs_client->rpc_ops->lookup(server->client, parent->d_inode, - &path->dentry->d_name, - fh, fattr); - if (err == -EPERM && NFS_PROTO(parent->d_inode)->secinfo != NULL) - err = nfs_lookup_with_sec(server, parent, path->dentry, path, fh, fattr, &flavor); - dput(parent); - if (err != 0) { - mnt = ERR_PTR(err); - goto out; - } - - if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) - mnt = nfs_do_refmount(path->dentry); - else - mnt = nfs_do_submount(path->dentry, fh, fattr, flavor); + mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr); if (IS_ERR(mnt)) goto out; @@ -336,10 +219,8 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, * @authflavor - security flavor to use when performing the mount * */ -static struct vfsmount *nfs_do_submount(struct dentry *dentry, - struct nfs_fh *fh, - struct nfs_fattr *fattr, - rpc_authflavor_t authflavor) +struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, + struct nfs_fattr *fattr, rpc_authflavor_t authflavor) { struct nfs_clone_mount mountdata = { .sb = dentry->d_sb, @@ -372,3 +253,18 @@ out: dprintk("<-- nfs_do_submount() = %p\n", mnt); return mnt; } + +struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + int err; + struct dentry *parent = dget_parent(dentry); + + /* Look it up again to get its attributes */ + err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr); + dput(parent); + if (err != 0) + return ERR_PTR(err); + + return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); +} diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index aa14ec303e9..8a6394edb8b 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -1,3 +1,7 @@ +/* + * NFS-private data for each "struct net". Accessed with net_generic(). + */ + #ifndef __NFS_NETNS_H__ #define __NFS_NETNS_H__ @@ -20,6 +24,7 @@ struct nfs_net { struct idr cb_ident_idr; /* Protected by nfs_client_lock */ #endif spinlock_t nfs_client_lock; + struct timespec boot_time; }; extern int nfs_net_id; diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 1f56000fabb..baf759bccd0 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -61,6 +61,7 @@ #define NFS_readdirres_sz (1) #define NFS_statfsres_sz (1+NFS_info_sz) +static int nfs_stat_to_errno(enum nfs_stat); /* * While encoding arguments, set up the reply buffer in advance to @@ -313,6 +314,8 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_time(p, &fattr->atime); p = xdr_decode_time(p, &fattr->mtime); xdr_decode_time(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); + return 0; out_overflow: print_overflow_msg(__func__, xdr); @@ -1109,7 +1112,7 @@ static const struct { * Returns a local errno value, or -EIO if the NFS status code is * not recognized. This function is used jointly by NFSv2 and NFSv3. */ -int nfs_stat_to_errno(enum nfs_stat status) +static int nfs_stat_to_errno(enum nfs_stat status) { int i; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 5242eae6711..2292a0fd2bf 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -142,7 +142,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs3_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs3_diropargs arg = { @@ -398,8 +398,7 @@ nfs3_proc_remove(struct inode *dir, struct qstr *name) { struct nfs_removeargs arg = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, + .name = *name, }; struct nfs_removeres res; struct rpc_message msg = { @@ -811,11 +810,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; - nfs_invalidate_atime(data->inode); - nfs_refresh_inode(data->inode, &data->fattr); + nfs_invalidate_atime(inode); + nfs_refresh_inode(inode, &data->fattr); return 0; } @@ -831,10 +832,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data) { - if (nfs3_async_handle_jukebox(task, data->inode)) + struct inode *inode = data->header->inode; + + if (nfs3_async_handle_jukebox(task, inode)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } @@ -848,7 +851,12 @@ static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_ rpc_call_start(task); } -static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data) +static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ + rpc_call_start(task); +} + +static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data) { if (nfs3_async_handle_jukebox(task, data->inode)) return -EAGAIN; @@ -856,7 +864,7 @@ static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data) return 0; } -static void nfs3_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg) +static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) { msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT]; } @@ -876,6 +884,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .file_inode_ops = &nfs3_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs3_proc_get_root, + .submount = nfs_submount, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, .lookup = nfs3_proc_lookup, @@ -907,6 +916,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .write_rpc_prepare = nfs3_proc_write_rpc_prepare, .write_done = nfs3_write_done, .commit_setup = nfs3_proc_commit_setup, + .commit_rpc_prepare = nfs3_proc_commit_rpc_prepare, .commit_done = nfs3_commit_done, .lock = nfs3_proc_lock, .clear_acl_cache = nfs3_forget_cached_acls, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index a77cc9a3ce5..902de489ec9 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -86,6 +86,8 @@ XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) #define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) +static int nfs3_stat_to_errno(enum nfs_stat); + /* * Map file type to S_IFMT bits */ @@ -675,6 +677,7 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr) p = xdr_decode_nfstime3(p, &fattr->atime); p = xdr_decode_nfstime3(p, &fattr->mtime); xdr_decode_nfstime3(p, &fattr->ctime); + fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime); fattr->valid |= NFS_ATTR_FATTR_V3; return 0; @@ -725,12 +728,14 @@ static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr) goto out_overflow; fattr->valid |= NFS_ATTR_FATTR_PRESIZE + | NFS_ATTR_FATTR_PRECHANGE | NFS_ATTR_FATTR_PREMTIME | NFS_ATTR_FATTR_PRECTIME; p = xdr_decode_size3(p, &fattr->pre_size); p = xdr_decode_nfstime3(p, &fattr->pre_mtime); xdr_decode_nfstime3(p, &fattr->pre_ctime); + fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime); return 0; out_overflow: @@ -1287,7 +1292,7 @@ static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, * }; */ static void encode_commit3args(struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_commitargs *args) { __be32 *p; @@ -1300,7 +1305,7 @@ static void encode_commit3args(struct xdr_stream *xdr, static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req, struct xdr_stream *xdr, - const struct nfs_writeargs *args) + const struct nfs_commitargs *args) { encode_commit3args(xdr, args); } @@ -1385,7 +1390,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req, out: return error; out_default: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1424,7 +1429,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1472,7 +1477,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr); if (unlikely(error)) goto out; - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1513,7 +1518,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req, out: return error; out_default: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1554,7 +1559,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req, out: return error; out_default: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1636,7 +1641,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1706,7 +1711,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1770,7 +1775,7 @@ out_default: error = decode_wcc_data(xdr, result->dir_attr); if (unlikely(error)) goto out; - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1809,7 +1814,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1853,7 +1858,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -1896,7 +1901,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /** @@ -2088,7 +2093,7 @@ out_default: error = decode_post_op_attr(xdr, result->dir_attr); if (unlikely(error)) goto out; - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -2156,7 +2161,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -2232,7 +2237,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -2295,7 +2300,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } /* @@ -2319,7 +2324,7 @@ out_status: */ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_writeres *result) + struct nfs_commitres *result) { enum nfs_stat status; int error; @@ -2336,7 +2341,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, out: return error; out_status: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } #ifdef CONFIG_NFS_V3_ACL @@ -2401,7 +2406,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, @@ -2420,11 +2425,76 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req, out: return error; out_default: - return nfs_stat_to_errno(status); + return nfs3_stat_to_errno(status); } #endif /* CONFIG_NFS_V3_ACL */ + +/* + * We need to translate between nfs status return values and + * the local errno values which may not be the same. + */ +static const struct { + int stat; + int errno; +} nfs_errtbl[] = { + { NFS_OK, 0 }, + { NFSERR_PERM, -EPERM }, + { NFSERR_NOENT, -ENOENT }, + { NFSERR_IO, -errno_NFSERR_IO}, + { NFSERR_NXIO, -ENXIO }, +/* { NFSERR_EAGAIN, -EAGAIN }, */ + { NFSERR_ACCES, -EACCES }, + { NFSERR_EXIST, -EEXIST }, + { NFSERR_XDEV, -EXDEV }, + { NFSERR_NODEV, -ENODEV }, + { NFSERR_NOTDIR, -ENOTDIR }, + { NFSERR_ISDIR, -EISDIR }, + { NFSERR_INVAL, -EINVAL }, + { NFSERR_FBIG, -EFBIG }, + { NFSERR_NOSPC, -ENOSPC }, + { NFSERR_ROFS, -EROFS }, + { NFSERR_MLINK, -EMLINK }, + { NFSERR_NAMETOOLONG, -ENAMETOOLONG }, + { NFSERR_NOTEMPTY, -ENOTEMPTY }, + { NFSERR_DQUOT, -EDQUOT }, + { NFSERR_STALE, -ESTALE }, + { NFSERR_REMOTE, -EREMOTE }, +#ifdef EWFLUSH + { NFSERR_WFLUSH, -EWFLUSH }, +#endif + { NFSERR_BADHANDLE, -EBADHANDLE }, + { NFSERR_NOT_SYNC, -ENOTSYNC }, + { NFSERR_BAD_COOKIE, -EBADCOOKIE }, + { NFSERR_NOTSUPP, -ENOTSUPP }, + { NFSERR_TOOSMALL, -ETOOSMALL }, + { NFSERR_SERVERFAULT, -EREMOTEIO }, + { NFSERR_BADTYPE, -EBADTYPE }, + { NFSERR_JUKEBOX, -EJUKEBOX }, + { -1, -EIO } +}; + +/** + * nfs3_stat_to_errno - convert an NFS status code to a local errno + * @status: NFS status code to convert + * + * Returns a local errno value, or -EIO if the NFS status code is + * not recognized. This function is used jointly by NFSv2 and NFSv3. + */ +static int nfs3_stat_to_errno(enum nfs_stat status) +{ + int i; + + for (i = 0; nfs_errtbl[i].stat != -1; i++) { + if (nfs_errtbl[i].stat == (int)status) + return nfs_errtbl[i].errno; + } + dprintk("NFS: Unrecognized nfs status value: %u\n", status); + return nfs_errtbl[i].errno; +} + + #define PROC(proc, argtype, restype, timer) \ [NFS3PROC_##proc] = { \ .p_proc = NFS3PROC_##proc, \ diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 97ecc863dd7..cc5900ac61b 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -24,6 +24,8 @@ enum nfs4_client_state { NFS4CLNT_RECALL_SLOT, NFS4CLNT_LEASE_CONFIRM, NFS4CLNT_SERVER_SCOPE_MISMATCH, + NFS4CLNT_PURGE_STATE, + NFS4CLNT_BIND_CONN_TO_SESSION, }; enum nfs4_session_state { @@ -52,13 +54,9 @@ struct nfs4_minor_version_ops { const struct nfs4_state_maintenance_ops *state_renewal_ops; }; -struct nfs_unique_id { - struct rb_node rb_node; - __u64 id; -}; - #define NFS_SEQID_CONFIRMED 1 struct nfs_seqid_counter { + ktime_t create_time; int owner_id; int flags; u32 counter; @@ -204,16 +202,28 @@ struct nfs4_state_maintenance_ops { extern const struct dentry_operations nfs4_dentry_operations; extern const struct inode_operations nfs4_dir_inode_operations; +/* nfs4namespace.c */ +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); +struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); +struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, + struct nfs_fh *, struct nfs_fattr *); + /* nfs4proc.c */ extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); +extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); +extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); +extern int nfs4_destroy_clientid(struct nfs_client *clp); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); -extern int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, - struct nfs4_fs_locations *fs_locations, struct page *page); +extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, + struct nfs4_fs_locations *, struct page *); +extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr *, + struct nfs_fh *, struct nfs_fattr *); +extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); extern int nfs4_release_lockowner(struct nfs4_lock_state *); extern const struct xattr_handler *nfs4_xattr_handlers[]; @@ -232,8 +242,8 @@ extern int nfs41_setup_sequence(struct nfs4_session *session, struct rpc_task *task); extern void nfs4_destroy_session(struct nfs4_session *session); extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp); -extern int nfs4_proc_create_session(struct nfs_client *); -extern int nfs4_proc_destroy_session(struct nfs4_session *); +extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *); +extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *); extern int nfs4_init_session(struct nfs_server *server); extern int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo); @@ -285,7 +295,7 @@ is_ds_client(struct nfs_client *clp) extern const struct nfs4_minor_version_ops *nfs_v4_minor_ops[]; -extern const u32 nfs4_fattr_bitmap[2]; +extern const u32 nfs4_fattr_bitmap[3]; extern const u32 nfs4_statfs_bitmap[2]; extern const u32 nfs4_pathconf_bitmap[2]; extern const u32 nfs4_fsinfo_bitmap[3]; @@ -303,9 +313,9 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp); #if defined(CONFIG_NFS_V4_1) struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp); struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp); -extern void nfs4_schedule_session_recovery(struct nfs4_session *); +extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); #else -static inline void nfs4_schedule_session_recovery(struct nfs4_session *session) +static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) { } #endif /* CONFIG_NFS_V4_1 */ @@ -327,7 +337,7 @@ extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags); extern void nfs41_handle_recall_slot(struct nfs_client *clp); extern void nfs41_handle_server_scope(struct nfs_client *, - struct server_scope **); + struct nfs41_server_scope **); extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *, diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index 5acfd9ea8a3..e1340293872 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -82,29 +82,76 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset) BUG(); } +static void filelayout_reset_write(struct nfs_write_data *data) +{ + struct nfs_pgio_header *hdr = data->header; + struct rpc_task *task = &data->task; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%lld, %u bytes @ offset %llu)\n", __func__, + data->task.tk_pid, + hdr->inode->i_sb->s_id, + (long long)NFS_FILEID(hdr->inode), + data->args.count, + (unsigned long long)data->args.offset); + + task->tk_status = pnfs_write_done_resend_to_mds(hdr->inode, + &hdr->pages, + hdr->completion_ops); + } +} + +static void filelayout_reset_read(struct nfs_read_data *data) +{ + struct nfs_pgio_header *hdr = data->header; + struct rpc_task *task = &data->task; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + dprintk("%s Reset task %5u for i/o through MDS " + "(req %s/%lld, %u bytes @ offset %llu)\n", __func__, + data->task.tk_pid, + hdr->inode->i_sb->s_id, + (long long)NFS_FILEID(hdr->inode), + data->args.count, + (unsigned long long)data->args.offset); + + task->tk_status = pnfs_read_done_resend_to_mds(hdr->inode, + &hdr->pages, + hdr->completion_ops); + } +} + static int filelayout_async_handle_error(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, - int *reset) + struct pnfs_layout_segment *lseg) { - struct nfs_server *mds_server = NFS_SERVER(state->inode); + struct inode *inode = lseg->pls_layout->plh_inode; + struct nfs_server *mds_server = NFS_SERVER(inode); + struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); struct nfs_client *mds_client = mds_server->nfs_client; + struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table; if (task->tk_status >= 0) return 0; - *reset = 0; switch (task->tk_status) { /* MDS state errors */ case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: + if (state == NULL) + break; nfs_remove_bad_delegation(state->inode); case -NFS4ERR_OPENMODE: + if (state == NULL) + break; nfs4_schedule_stateid_recovery(mds_server, state); goto wait_on_recovery; case -NFS4ERR_EXPIRED: - nfs4_schedule_stateid_recovery(mds_server, state); + if (state != NULL) + nfs4_schedule_stateid_recovery(mds_server, state); nfs4_schedule_lease_recovery(mds_client); goto wait_on_recovery; /* DS session errors */ @@ -118,7 +165,7 @@ static int filelayout_async_handle_error(struct rpc_task *task, dprintk("%s ERROR %d, Reset session. Exchangeid " "flags 0x%x\n", __func__, task->tk_status, clp->cl_exchange_flags); - nfs4_schedule_session_recovery(clp->cl_session); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); break; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: @@ -127,11 +174,48 @@ static int filelayout_async_handle_error(struct rpc_task *task, break; case -NFS4ERR_RETRY_UNCACHED_REP: break; + /* Invalidate Layout errors */ + case -NFS4ERR_PNFS_NO_LAYOUT: + case -ESTALE: /* mapped NFS4ERR_STALE */ + case -EBADHANDLE: /* mapped NFS4ERR_BADHANDLE */ + case -EISDIR: /* mapped NFS4ERR_ISDIR */ + case -NFS4ERR_FHEXPIRED: + case -NFS4ERR_WRONG_TYPE: + dprintk("%s Invalid layout error %d\n", __func__, + task->tk_status); + /* + * Destroy layout so new i/o will get a new layout. + * Layout will not be destroyed until all current lseg + * references are put. Mark layout as invalid to resend failed + * i/o and all i/o waiting on the slot table to the MDS until + * layout is destroyed and a new valid layout is obtained. + */ + set_bit(NFS_LAYOUT_INVALID, + &NFS_I(inode)->layout->plh_flags); + pnfs_destroy_layout(NFS_I(inode)); + rpc_wake_up(&tbl->slot_tbl_waitq); + goto reset; + /* RPC connection errors */ + case -ECONNREFUSED: + case -EHOSTDOWN: + case -EHOSTUNREACH: + case -ENETUNREACH: + case -EIO: + case -ETIMEDOUT: + case -EPIPE: + dprintk("%s DS connection error %d\n", __func__, + task->tk_status); + if (!filelayout_test_devid_invalid(devid)) + _pnfs_return_layout(inode); + filelayout_mark_devid_invalid(devid); + rpc_wake_up(&tbl->slot_tbl_waitq); + nfs4_ds_disconnect(clp); + /* fall through */ default: - dprintk("%s DS error. Retry through MDS %d\n", __func__, +reset: + dprintk("%s Retry through MDS. Error %d\n", __func__, task->tk_status); - *reset = 1; - break; + return -NFS4ERR_RESET_TO_MDS; } out: task->tk_status = 0; @@ -148,18 +232,17 @@ wait_on_recovery: static int filelayout_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { - int reset = 0; + struct nfs_pgio_header *hdr = data->header; + int err; - dprintk("%s DS read\n", __func__); + err = filelayout_async_handle_error(task, data->args.context->state, + data->ds_clp, hdr->lseg); - if (filelayout_async_handle_error(task, data->args.context->state, - data->ds_clp, &reset) == -EAGAIN) { - dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", - __func__, data->ds_clp, data->ds_clp->cl_session); - if (reset) { - pnfs_set_lo_fail(data->lseg); - nfs4_reset_read(task, data); - } + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + filelayout_reset_read(data); + return task->tk_status; + case -EAGAIN: rpc_restart_call_prepare(task); return -EAGAIN; } @@ -175,13 +258,15 @@ static int filelayout_read_done_cb(struct rpc_task *task, static void filelayout_set_layoutcommit(struct nfs_write_data *wdata) { - if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds || + struct nfs_pgio_header *hdr = wdata->header; + + if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds || wdata->res.verf->committed == NFS_FILE_SYNC) return; pnfs_set_layoutcommit(wdata); - dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino, - (unsigned long) NFS_I(wdata->inode)->layout->plh_lwb); + dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino, + (unsigned long) NFS_I(hdr->inode)->layout->plh_lwb); } /* @@ -191,8 +276,14 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata) */ static void filelayout_read_prepare(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = (struct nfs_read_data *)data; + struct nfs_read_data *rdata = data; + if (filelayout_reset_to_mds(rdata->header->lseg)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + filelayout_reset_read(rdata); + rpc_exit(task, 0); + return; + } rdata->read_done_cb = filelayout_read_done_cb; if (nfs41_setup_sequence(rdata->ds_clp->cl_session, @@ -205,42 +296,47 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data) static void filelayout_read_call_done(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = (struct nfs_read_data *)data; + struct nfs_read_data *rdata = data; dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status); + if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) && + task->tk_status == 0) + return; + /* Note this may cause RPC to be resent */ - rdata->mds_ops->rpc_call_done(task, data); + rdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_read_count_stats(struct rpc_task *task, void *data) { - struct nfs_read_data *rdata = (struct nfs_read_data *)data; + struct nfs_read_data *rdata = data; - rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics); + rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics); } static void filelayout_read_release(void *data) { - struct nfs_read_data *rdata = (struct nfs_read_data *)data; + struct nfs_read_data *rdata = data; - put_lseg(rdata->lseg); - rdata->mds_ops->rpc_release(data); + nfs_put_client(rdata->ds_clp); + rdata->header->mds_ops->rpc_release(data); } static int filelayout_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { - int reset = 0; - - if (filelayout_async_handle_error(task, data->args.context->state, - data->ds_clp, &reset) == -EAGAIN) { - dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", - __func__, data->ds_clp, data->ds_clp->cl_session); - if (reset) { - pnfs_set_lo_fail(data->lseg); - nfs4_reset_write(task, data); - } + struct nfs_pgio_header *hdr = data->header; + int err; + + err = filelayout_async_handle_error(task, data->args.context->state, + data->ds_clp, hdr->lseg); + + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + filelayout_reset_write(data); + return task->tk_status; + case -EAGAIN: rpc_restart_call_prepare(task); return -EAGAIN; } @@ -250,7 +346,7 @@ static int filelayout_write_done_cb(struct rpc_task *task, } /* Fake up some data that will cause nfs_commit_release to retry the writes. */ -static void prepare_to_resend_writes(struct nfs_write_data *data) +static void prepare_to_resend_writes(struct nfs_commit_data *data) { struct nfs_page *first = nfs_list_entry(data->pages.next); @@ -261,19 +357,19 @@ static void prepare_to_resend_writes(struct nfs_write_data *data) } static int filelayout_commit_done_cb(struct rpc_task *task, - struct nfs_write_data *data) + struct nfs_commit_data *data) { - int reset = 0; - - if (filelayout_async_handle_error(task, data->args.context->state, - data->ds_clp, &reset) == -EAGAIN) { - dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n", - __func__, data->ds_clp, data->ds_clp->cl_session); - if (reset) { - prepare_to_resend_writes(data); - pnfs_set_lo_fail(data->lseg); - } else - rpc_restart_call_prepare(task); + int err; + + err = filelayout_async_handle_error(task, NULL, data->ds_clp, + data->lseg); + + switch (err) { + case -NFS4ERR_RESET_TO_MDS: + prepare_to_resend_writes(data); + return -EAGAIN; + case -EAGAIN: + rpc_restart_call_prepare(task); return -EAGAIN; } @@ -282,8 +378,14 @@ static int filelayout_commit_done_cb(struct rpc_task *task, static void filelayout_write_prepare(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = (struct nfs_write_data *)data; + struct nfs_write_data *wdata = data; + if (filelayout_reset_to_mds(wdata->header->lseg)) { + dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid); + filelayout_reset_write(wdata); + rpc_exit(task, 0); + return; + } if (nfs41_setup_sequence(wdata->ds_clp->cl_session, &wdata->args.seq_args, &wdata->res.seq_res, task)) @@ -294,36 +396,66 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data) static void filelayout_write_call_done(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = (struct nfs_write_data *)data; + struct nfs_write_data *wdata = data; + + if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) && + task->tk_status == 0) + return; /* Note this may cause RPC to be resent */ - wdata->mds_ops->rpc_call_done(task, data); + wdata->header->mds_ops->rpc_call_done(task, data); } static void filelayout_write_count_stats(struct rpc_task *task, void *data) { - struct nfs_write_data *wdata = (struct nfs_write_data *)data; + struct nfs_write_data *wdata = data; - rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics); + rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics); } static void filelayout_write_release(void *data) { - struct nfs_write_data *wdata = (struct nfs_write_data *)data; + struct nfs_write_data *wdata = data; + + nfs_put_client(wdata->ds_clp); + wdata->header->mds_ops->rpc_release(data); +} + +static void filelayout_commit_prepare(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; - put_lseg(wdata->lseg); - wdata->mds_ops->rpc_release(data); + if (nfs41_setup_sequence(wdata->ds_clp->cl_session, + &wdata->args.seq_args, &wdata->res.seq_res, + task)) + return; + + rpc_call_start(task); +} + +static void filelayout_write_commit_done(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *wdata = data; + + /* Note this may cause RPC to be resent */ + wdata->mds_ops->rpc_call_done(task, data); +} + +static void filelayout_commit_count_stats(struct rpc_task *task, void *data) +{ + struct nfs_commit_data *cdata = data; + + rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics); } -static void filelayout_commit_release(void *data) +static void filelayout_commit_release(void *calldata) { - struct nfs_write_data *wdata = (struct nfs_write_data *)data; + struct nfs_commit_data *data = calldata; - nfs_commit_release_pages(wdata); - if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding)) - nfs_commit_clear_lock(NFS_I(wdata->inode)); - put_lseg(wdata->lseg); - nfs_commitdata_release(wdata); + data->completion_ops->completion(data); + put_lseg(data->lseg); + nfs_put_client(data->ds_clp); + nfs_commitdata_release(data); } static const struct rpc_call_ops filelayout_read_call_ops = { @@ -341,16 +473,17 @@ static const struct rpc_call_ops filelayout_write_call_ops = { }; static const struct rpc_call_ops filelayout_commit_call_ops = { - .rpc_call_prepare = filelayout_write_prepare, - .rpc_call_done = filelayout_write_call_done, - .rpc_count_stats = filelayout_write_count_stats, + .rpc_call_prepare = filelayout_commit_prepare, + .rpc_call_done = filelayout_write_commit_done, + .rpc_count_stats = filelayout_commit_count_stats, .rpc_release = filelayout_commit_release, }; static enum pnfs_try_status filelayout_read_pagelist(struct nfs_read_data *data) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; @@ -358,25 +491,20 @@ filelayout_read_pagelist(struct nfs_read_data *data) int status; dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n", - __func__, data->inode->i_ino, + __func__, hdr->inode->i_ino, data->args.pgbase, (size_t)data->args.count, offset); - if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags)) - return PNFS_NOT_ATTEMPTED; - /* Retrieve the correct rpc_client for the byte range */ j = nfs4_fl_calc_j_index(lseg, offset); idx = nfs4_fl_calc_ds_index(lseg, j); ds = nfs4_fl_prepare_ds(lseg, idx); - if (!ds) { - /* Either layout fh index faulty, or ds connect failed */ - set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); - set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); + if (!ds) return PNFS_NOT_ATTEMPTED; - } - dprintk("%s USE DS: %s\n", __func__, ds->ds_remotestr); + dprintk("%s USE DS: %s cl_count %d\n", __func__, + ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); /* No multipath support. Use first DS */ + atomic_inc(&ds->ds_clp->cl_count); data->ds_clp = ds->ds_clp; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) @@ -386,8 +514,8 @@ filelayout_read_pagelist(struct nfs_read_data *data) data->mds_offset = offset; /* Perform an asynchronous read to ds */ - status = nfs_initiate_read(data, ds->ds_clp->cl_rpcclient, - &filelayout_read_call_ops); + status = nfs_initiate_read(ds->ds_clp->cl_rpcclient, data, + &filelayout_read_call_ops, RPC_TASK_SOFTCONN); BUG_ON(status != 0); return PNFS_ATTEMPTED; } @@ -396,32 +524,26 @@ filelayout_read_pagelist(struct nfs_read_data *data) static enum pnfs_try_status filelayout_write_pagelist(struct nfs_write_data *data, int sync) { - struct pnfs_layout_segment *lseg = data->lseg; + struct nfs_pgio_header *hdr = data->header; + struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; loff_t offset = data->args.offset; u32 j, idx; struct nfs_fh *fh; int status; - if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags)) - return PNFS_NOT_ATTEMPTED; - /* Retrieve the correct rpc_client for the byte range */ j = nfs4_fl_calc_j_index(lseg, offset); idx = nfs4_fl_calc_ds_index(lseg, j); ds = nfs4_fl_prepare_ds(lseg, idx); - if (!ds) { - printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n", - __func__); - set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); - set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); + if (!ds) return PNFS_NOT_ATTEMPTED; - } - dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__, - data->inode->i_ino, sync, (size_t) data->args.count, offset, - ds->ds_remotestr); + dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n", + __func__, hdr->inode->i_ino, sync, (size_t) data->args.count, + offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count)); data->write_done_cb = filelayout_write_done_cb; + atomic_inc(&ds->ds_clp->cl_count); data->ds_clp = ds->ds_clp; fh = nfs4_fl_select_ds_fh(lseg, j); if (fh) @@ -433,8 +555,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync) data->args.offset = filelayout_get_dserver_offset(lseg, offset); /* Perform an asynchronous write */ - status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient, - &filelayout_write_call_ops, sync); + status = nfs_initiate_write(ds->ds_clp->cl_rpcclient, data, + &filelayout_write_call_ops, sync, + RPC_TASK_SOFTCONN); BUG_ON(status != 0); return PNFS_ATTEMPTED; } @@ -650,10 +773,65 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg) dprintk("--> %s\n", __func__); nfs4_fl_put_deviceid(fl->dsaddr); - kfree(fl->commit_buckets); + /* This assumes a single RW lseg */ + if (lseg->pls_range.iomode == IOMODE_RW) { + struct nfs4_filelayout *flo; + + flo = FILELAYOUT_FROM_HDR(lseg->pls_layout); + flo->commit_info.nbuckets = 0; + kfree(flo->commit_info.buckets); + flo->commit_info.buckets = NULL; + } _filelayout_free_lseg(fl); } +static int +filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo, + gfp_t gfp_flags) +{ + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + struct pnfs_commit_bucket *buckets; + int size; + + if (fl->commit_through_mds) + return 0; + if (cinfo->ds->nbuckets != 0) { + /* This assumes there is only one IOMODE_RW lseg. What + * we really want to do is have a layout_hdr level + * dictionary of <multipath_list4, fh> keys, each + * associated with a struct list_head, populated by calls + * to filelayout_write_pagelist(). + * */ + return 0; + } + + size = (fl->stripe_type == STRIPE_SPARSE) ? + fl->dsaddr->ds_num : fl->dsaddr->stripe_count; + + buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket), + gfp_flags); + if (!buckets) + return -ENOMEM; + else { + int i; + + spin_lock(cinfo->lock); + if (cinfo->ds->nbuckets != 0) + kfree(buckets); + else { + cinfo->ds->buckets = buckets; + cinfo->ds->nbuckets = size; + for (i = 0; i < size; i++) { + INIT_LIST_HEAD(&buckets[i].written); + INIT_LIST_HEAD(&buckets[i].committing); + } + } + spin_unlock(cinfo->lock); + return 0; + } +} + static struct pnfs_layout_segment * filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr, @@ -673,29 +851,6 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, _filelayout_free_lseg(fl); return NULL; } - - /* This assumes there is only one IOMODE_RW lseg. What - * we really want to do is have a layout_hdr level - * dictionary of <multipath_list4, fh> keys, each - * associated with a struct list_head, populated by calls - * to filelayout_write_pagelist(). - * */ - if ((!fl->commit_through_mds) && (lgr->range.iomode == IOMODE_RW)) { - int i; - int size = (fl->stripe_type == STRIPE_SPARSE) ? - fl->dsaddr->ds_num : fl->dsaddr->stripe_count; - - fl->commit_buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), gfp_flags); - if (!fl->commit_buckets) { - filelayout_free_lseg(&fl->generic_hdr); - return NULL; - } - fl->number_of_buckets = size; - for (i = 0; i < size; i++) { - INIT_LIST_HEAD(&fl->commit_buckets[i].written); - INIT_LIST_HEAD(&fl->commit_buckets[i].committing); - } - } return &fl->generic_hdr; } @@ -716,8 +871,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, !nfs_generic_pg_test(pgio, prev, req)) return false; - p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT; - r_stripe = (u64)req->wb_index << PAGE_CACHE_SHIFT; + p_stripe = (u64)req_offset(prev); + r_stripe = (u64)req_offset(req); stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit; do_div(p_stripe, stripe_unit); @@ -732,6 +887,16 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio, { BUG_ON(pgio->pg_lseg != NULL); + if (req->wb_offset != req->wb_pgbase) { + /* + * Handling unaligned pages is difficult, because have to + * somehow split a req in two in certain cases in the + * pg.test code. Avoid this by just not using pnfs + * in this case. + */ + nfs_pageio_reset_read_mds(pgio); + return; + } pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, @@ -747,8 +912,13 @@ static void filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { + struct nfs_commit_info cinfo; + int status; + BUG_ON(pgio->pg_lseg != NULL); + if (req->wb_offset != req->wb_pgbase) + goto out_mds; pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, 0, @@ -757,7 +927,17 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio, GFP_NOFS); /* If no lseg, fall back to write through mds */ if (pgio->pg_lseg == NULL) - nfs_pageio_reset_write_mds(pgio); + goto out_mds; + nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq); + status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS); + if (status < 0) { + put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + goto out_mds; + } + return; +out_mds: + nfs_pageio_reset_write_mds(pgio); } static const struct nfs_pageio_ops filelayout_pg_read_ops = { @@ -784,43 +964,42 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j) * If this will make the bucket empty, it will need to put the lseg reference. */ static void -filelayout_clear_request_commit(struct nfs_page *req) +filelayout_clear_request_commit(struct nfs_page *req, + struct nfs_commit_info *cinfo) { struct pnfs_layout_segment *freeme = NULL; - struct inode *inode = req->wb_context->dentry->d_inode; - spin_lock(&inode->i_lock); + spin_lock(cinfo->lock); if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags)) goto out; + cinfo->ds->nwritten--; if (list_is_singular(&req->wb_list)) { - struct pnfs_layout_segment *lseg; + struct pnfs_commit_bucket *bucket; - /* From here we can find the bucket, but for the moment, - * since there is only one relevant lseg... - */ - list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) { - if (lseg->pls_range.iomode == IOMODE_RW) { - freeme = lseg; - break; - } - } + bucket = list_first_entry(&req->wb_list, + struct pnfs_commit_bucket, + written); + freeme = bucket->wlseg; + bucket->wlseg = NULL; } out: - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_request_remove_commit_list(req, cinfo); + spin_unlock(cinfo->lock); put_lseg(freeme); } static struct list_head * filelayout_choose_commit_list(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); u32 i, j; struct list_head *list; + struct pnfs_commit_bucket *buckets; if (fl->commit_through_mds) - return &NFS_I(req->wb_context->dentry->d_inode)->commit_list; + return &cinfo->mds->list; /* Note that we are calling nfs4_fl_calc_j_index on each page * that ends up being committed to a data server. An attractive @@ -828,31 +1007,33 @@ filelayout_choose_commit_list(struct nfs_page *req, * to store the value calculated in filelayout_write_pagelist * and just use that here. */ - j = nfs4_fl_calc_j_index(lseg, - (loff_t)req->wb_index << PAGE_CACHE_SHIFT); + j = nfs4_fl_calc_j_index(lseg, req_offset(req)); i = select_bucket_index(fl, j); - list = &fl->commit_buckets[i].written; + buckets = cinfo->ds->buckets; + list = &buckets[i].written; if (list_empty(list)) { /* Non-empty buckets hold a reference on the lseg. That ref * is normally transferred to the COMMIT call and released * there. It could also be released if the last req is pulled * off due to a rewrite, in which case it will be done in - * filelayout_remove_commit_req + * filelayout_clear_request_commit */ - get_lseg(lseg); + buckets[i].wlseg = get_lseg(lseg); } set_bit(PG_COMMIT_TO_DS, &req->wb_flags); + cinfo->ds->nwritten++; return list; } static void filelayout_mark_request_commit(struct nfs_page *req, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct list_head *list; - list = filelayout_choose_commit_list(req, lseg); - nfs_request_add_commit_list(req, list); + list = filelayout_choose_commit_list(req, lseg, cinfo); + nfs_request_add_commit_list(req, list, cinfo); } static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i) @@ -880,7 +1061,7 @@ select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i) return flseg->fh_array[i]; } -static int filelayout_initiate_commit(struct nfs_write_data *data, int how) +static int filelayout_initiate_commit(struct nfs_commit_data *data, int how) { struct pnfs_layout_segment *lseg = data->lseg; struct nfs4_pnfs_ds *ds; @@ -890,135 +1071,138 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how) idx = calc_ds_index_from_commit(lseg, data->ds_commit_index); ds = nfs4_fl_prepare_ds(lseg, idx); if (!ds) { - printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n", - __func__); - set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags); - set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags); prepare_to_resend_writes(data); filelayout_commit_release(data); return -EAGAIN; } - dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how); - data->write_done_cb = filelayout_commit_done_cb; + dprintk("%s ino %lu, how %d cl_count %d\n", __func__, + data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count)); + data->commit_done_cb = filelayout_commit_done_cb; + atomic_inc(&ds->ds_clp->cl_count); data->ds_clp = ds->ds_clp; fh = select_ds_fh_from_commit(lseg, data->ds_commit_index); if (fh) data->args.fh = fh; - return nfs_initiate_commit(data, ds->ds_clp->cl_rpcclient, - &filelayout_commit_call_ops, how); -} - -/* - * This is only useful while we are using whole file layouts. - */ -static struct pnfs_layout_segment * -find_only_write_lseg_locked(struct inode *inode) -{ - struct pnfs_layout_segment *lseg; - - list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) - if (lseg->pls_range.iomode == IOMODE_RW) - return lseg; - return NULL; -} - -static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode) -{ - struct pnfs_layout_segment *rv; - - spin_lock(&inode->i_lock); - rv = find_only_write_lseg_locked(inode); - if (rv) - get_lseg(rv); - spin_unlock(&inode->i_lock); - return rv; + return nfs_initiate_commit(ds->ds_clp->cl_rpcclient, data, + &filelayout_commit_call_ops, how, + RPC_TASK_SOFTCONN); } static int -filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max, - spinlock_t *lock) +transfer_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) { - struct list_head *src = &bucket->written; - struct list_head *dst = &bucket->committing; struct nfs_page *req, *tmp; int ret = 0; list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + kref_get(&req->wb_kref); + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); nfs_list_add_request(req, dst); ret++; - if (ret == max) + if ((ret == max) && !cinfo->dreq) break; } return ret; } +static int +filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket, + struct nfs_commit_info *cinfo, + int max) +{ + struct list_head *src = &bucket->written; + struct list_head *dst = &bucket->committing; + int ret; + + ret = transfer_commit_list(src, dst, cinfo, max); + if (ret) { + cinfo->ds->nwritten -= ret; + cinfo->ds->ncommitting += ret; + bucket->clseg = bucket->wlseg; + if (list_empty(src)) + bucket->wlseg = NULL; + else + get_lseg(bucket->clseg); + } + return ret; +} + /* Move reqs from written to committing lists, returning count of number moved. - * Note called with i_lock held. + * Note called with cinfo->lock held. */ -static int filelayout_scan_commit_lists(struct inode *inode, int max, - spinlock_t *lock) +static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo, + int max) { - struct pnfs_layout_segment *lseg; - struct nfs4_filelayout_segment *fl; int i, rv = 0, cnt; - lseg = find_only_write_lseg_locked(inode); - if (!lseg) - goto out_done; - fl = FILELAYOUT_LSEG(lseg); - if (fl->commit_through_mds) - goto out_done; - for (i = 0; i < fl->number_of_buckets && max != 0; i++) { - cnt = filelayout_scan_ds_commit_list(&fl->commit_buckets[i], - max, lock); + for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) { + cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i], + cinfo, max); max -= cnt; rv += cnt; } -out_done: return rv; } +/* Pull everything off the committing lists and dump into @dst */ +static void filelayout_recover_commit_reqs(struct list_head *dst, + struct nfs_commit_info *cinfo) +{ + struct pnfs_commit_bucket *b; + int i; + + /* NOTE cinfo->lock is NOT held, relying on fact that this is + * only called on single thread per dreq. + * Can't take the lock because need to do put_lseg + */ + for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) { + if (transfer_commit_list(&b->written, dst, cinfo, 0)) { + BUG_ON(!list_empty(&b->written)); + put_lseg(b->wlseg); + b->wlseg = NULL; + } + } + cinfo->ds->nwritten = 0; +} + static unsigned int -alloc_ds_commits(struct inode *inode, struct list_head *list) +alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list) { - struct pnfs_layout_segment *lseg; - struct nfs4_filelayout_segment *fl; - struct nfs_write_data *data; + struct pnfs_ds_commit_info *fl_cinfo; + struct pnfs_commit_bucket *bucket; + struct nfs_commit_data *data; int i, j; unsigned int nreq = 0; - /* Won't need this when non-whole file layout segments are supported - * instead we will use a pnfs_layout_hdr structure */ - lseg = find_only_write_lseg(inode); - if (!lseg) - return 0; - fl = FILELAYOUT_LSEG(lseg); - for (i = 0; i < fl->number_of_buckets; i++) { - if (list_empty(&fl->commit_buckets[i].committing)) + fl_cinfo = cinfo->ds; + bucket = fl_cinfo->buckets; + for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) { + if (list_empty(&bucket->committing)) continue; data = nfs_commitdata_alloc(); if (!data) break; data->ds_commit_index = i; - data->lseg = lseg; + data->lseg = bucket->clseg; + bucket->clseg = NULL; list_add(&data->pages, list); nreq++; } /* Clean up on error */ - for (j = i; j < fl->number_of_buckets; j++) { - if (list_empty(&fl->commit_buckets[i].committing)) + for (j = i; j < fl_cinfo->nbuckets; j++, bucket++) { + if (list_empty(&bucket->committing)) continue; - nfs_retry_commit(&fl->commit_buckets[i].committing, lseg); - put_lseg(lseg); /* associated with emptying bucket */ + nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo); + put_lseg(bucket->clseg); + bucket->clseg = NULL; } - put_lseg(lseg); /* Caller will clean up entries put on list */ return nreq; } @@ -1026,9 +1210,9 @@ alloc_ds_commits(struct inode *inode, struct list_head *list) /* This follows nfs_commit_list pretty closely */ static int filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, - int how) + int how, struct nfs_commit_info *cinfo) { - struct nfs_write_data *data, *tmp; + struct nfs_commit_data *data, *tmp; LIST_HEAD(list); unsigned int nreq = 0; @@ -1039,30 +1223,34 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages, list_add(&data->pages, &list); nreq++; } else - nfs_retry_commit(mds_pages, NULL); + nfs_retry_commit(mds_pages, NULL, cinfo); } - nreq += alloc_ds_commits(inode, &list); + nreq += alloc_ds_commits(cinfo, &list); if (nreq == 0) { - nfs_commit_clear_lock(NFS_I(inode)); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); goto out; } - atomic_add(nreq, &NFS_I(inode)->commits_outstanding); + atomic_add(nreq, &cinfo->mds->rpcs_out); list_for_each_entry_safe(data, tmp, &list, pages) { list_del_init(&data->pages); if (!data->lseg) { - nfs_init_commit(data, mds_pages, NULL); - nfs_initiate_commit(data, NFS_CLIENT(inode), - data->mds_ops, how); + nfs_init_commit(data, mds_pages, NULL, cinfo); + nfs_initiate_commit(NFS_CLIENT(inode), data, + data->mds_ops, how, 0); } else { - nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index].committing, data->lseg); + struct pnfs_commit_bucket *buckets; + + buckets = cinfo->ds->buckets; + nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo); filelayout_initiate_commit(data, how); } } out: + cinfo->ds->ncommitting = 0; return PNFS_ATTEMPTED; } @@ -1072,17 +1260,47 @@ filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d) nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node)); } +static struct pnfs_layout_hdr * +filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) +{ + struct nfs4_filelayout *flo; + + flo = kzalloc(sizeof(*flo), gfp_flags); + return &flo->generic_hdr; +} + +static void +filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo) +{ + kfree(FILELAYOUT_FROM_HDR(lo)); +} + +static struct pnfs_ds_commit_info * +filelayout_get_ds_info(struct inode *inode) +{ + struct pnfs_layout_hdr *layout = NFS_I(inode)->layout; + + if (layout == NULL) + return NULL; + else + return &FILELAYOUT_FROM_HDR(layout)->commit_info; +} + static struct pnfs_layoutdriver_type filelayout_type = { .id = LAYOUT_NFSV4_1_FILES, .name = "LAYOUT_NFSV4_1_FILES", .owner = THIS_MODULE, + .alloc_layout_hdr = filelayout_alloc_layout_hdr, + .free_layout_hdr = filelayout_free_layout_hdr, .alloc_lseg = filelayout_alloc_lseg, .free_lseg = filelayout_free_lseg, .pg_read_ops = &filelayout_pg_read_ops, .pg_write_ops = &filelayout_pg_write_ops, + .get_ds_info = &filelayout_get_ds_info, .mark_request_commit = filelayout_mark_request_commit, .clear_request_commit = filelayout_clear_request_commit, .scan_commit_lists = filelayout_scan_commit_lists, + .recover_commit_reqs = filelayout_recover_commit_reqs, .commit_pagelist = filelayout_commit_pagelist, .read_pagelist = filelayout_read_pagelist, .write_pagelist = filelayout_write_pagelist, diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h index 21190bb1f5e..43fe802dd67 100644 --- a/fs/nfs/nfs4filelayout.h +++ b/fs/nfs/nfs4filelayout.h @@ -33,6 +33,13 @@ #include "pnfs.h" /* + * Default data server connection timeout and retrans vaules. + * Set by module paramters dataserver_timeo and dataserver_retrans. + */ +#define NFS4_DEF_DS_TIMEO 60 +#define NFS4_DEF_DS_RETRANS 5 + +/* * Field testing shows we need to support up to 4096 stripe indices. * We store each index as a u8 (u32 on the wire) to keep the memory footprint * reasonable. This in turn means we support a maximum of 256 @@ -41,6 +48,9 @@ #define NFS4_PNFS_MAX_STRIPE_CNT 4096 #define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */ +/* error codes for internal use */ +#define NFS4ERR_RESET_TO_MDS 12001 + enum stripetype4 { STRIPE_SPARSE = 1, STRIPE_DENSE = 2 @@ -62,23 +72,14 @@ struct nfs4_pnfs_ds { atomic_t ds_count; }; -/* nfs4_file_layout_dsaddr flags */ -#define NFS4_DEVICE_ID_NEG_ENTRY 0x00000001 - struct nfs4_file_layout_dsaddr { struct nfs4_deviceid_node id_node; - unsigned long flags; u32 stripe_count; u8 *stripe_indices; u32 ds_num; struct nfs4_pnfs_ds *ds_list[1]; }; -struct nfs4_fl_commit_bucket { - struct list_head written; - struct list_head committing; -}; - struct nfs4_filelayout_segment { struct pnfs_layout_segment generic_hdr; u32 stripe_type; @@ -89,10 +90,19 @@ struct nfs4_filelayout_segment { struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ unsigned int num_fh; struct nfs_fh **fh_array; - struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */ - int number_of_buckets; }; +struct nfs4_filelayout { + struct pnfs_layout_hdr generic_hdr; + struct pnfs_ds_commit_info commit_info; +}; + +static inline struct nfs4_filelayout * +FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo) +{ + return container_of(lo, struct nfs4_filelayout, generic_hdr); +} + static inline struct nfs4_filelayout_segment * FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg) { @@ -107,6 +117,36 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg) return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node; } +static inline void +filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node) +{ + u32 *p = (u32 *)&node->deviceid; + + printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n", + p[0], p[1], p[2], p[3]); + + set_bit(NFS_DEVICEID_INVALID, &node->flags); +} + +static inline bool +filelayout_test_layout_invalid(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_INVALID, &lo->plh_flags); +} + +static inline bool +filelayout_test_devid_invalid(struct nfs4_deviceid_node *node) +{ + return test_bit(NFS_DEVICEID_INVALID, &node->flags); +} + +static inline bool +filelayout_reset_to_mds(struct pnfs_layout_segment *lseg) +{ + return filelayout_test_devid_invalid(FILELAYOUT_DEVID_NODE(lseg)) || + filelayout_test_layout_invalid(lseg->pls_layout); +} + extern struct nfs_fh * nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j); @@ -119,5 +159,6 @@ extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr); extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr); struct nfs4_file_layout_dsaddr * get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags); +void nfs4_ds_disconnect(struct nfs_client *clp); #endif /* FS_NFS_NFS4FILELAYOUT_H */ diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index a866bbd2890..a1fab8da7f0 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -30,12 +30,16 @@ #include <linux/nfs_fs.h> #include <linux/vmalloc.h> +#include <linux/module.h> #include "internal.h" #include "nfs4filelayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD +static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO; +static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS; + /* * Data server cache * @@ -145,6 +149,28 @@ _data_server_lookup_locked(const struct list_head *dsaddrs) } /* + * Lookup DS by nfs_client pointer. Zero data server client pointer + */ +void nfs4_ds_disconnect(struct nfs_client *clp) +{ + struct nfs4_pnfs_ds *ds; + struct nfs_client *found = NULL; + + dprintk("%s clp %p\n", __func__, clp); + spin_lock(&nfs4_ds_cache_lock); + list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) + if (ds->ds_clp && ds->ds_clp == clp) { + found = ds->ds_clp; + ds->ds_clp = NULL; + } + spin_unlock(&nfs4_ds_cache_lock); + if (found) { + set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state); + nfs_put_client(clp); + } +} + +/* * Create an rpc connection to the nfs4_pnfs_ds data server * Currently only supports IPv4 and IPv6 addresses */ @@ -165,8 +191,9 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds) __func__, ds->ds_remotestr, da->da_remotestr); clp = nfs4_set_ds_client(mds_srv->nfs_client, - (struct sockaddr *)&da->da_addr, - da->da_addrlen, IPPROTO_TCP); + (struct sockaddr *)&da->da_addr, + da->da_addrlen, IPPROTO_TCP, + dataserver_timeo, dataserver_retrans); if (!IS_ERR(clp)) break; } @@ -176,28 +203,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds) goto out; } - if ((clp->cl_exchange_flags & EXCHGID4_FLAG_MASK_PNFS) != 0) { - if (!is_ds_client(clp)) { - status = -ENODEV; - goto out_put; - } - ds->ds_clp = clp; - dprintk("%s [existing] server=%s\n", __func__, - ds->ds_remotestr); - goto out; - } - - /* - * Do not set NFS_CS_CHECK_LEASE_TIME instead set the DS lease to - * be equal to the MDS lease. Renewal is scheduled in create_session. - */ - spin_lock(&mds_srv->nfs_client->cl_lock); - clp->cl_lease_time = mds_srv->nfs_client->cl_lease_time; - spin_unlock(&mds_srv->nfs_client->cl_lock); - clp->cl_last_renewal = jiffies; - - /* New nfs_client */ - status = nfs4_init_ds_session(clp); + status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time); if (status) goto out_put; @@ -602,7 +608,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags) mp_count = be32_to_cpup(p); /* multipath count */ for (j = 0; j < mp_count; j++) { - da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net, + da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net, &stream, gfp_flags); if (da) list_add_tail(&da->da_node, &dsaddrs); @@ -699,7 +705,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla * GETDEVICEINFO's maxcount */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); dprintk("%s inode %p max_resp_sz %u max_pages %d\n", __func__, inode, max_resp_sz, max_pages); @@ -791,48 +797,42 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j) return flseg->fh_array[i]; } -static void -filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr, - int err, const char *ds_remotestr) -{ - u32 *p = (u32 *)&dsaddr->id_node.deviceid; - - printk(KERN_ERR "NFS: data server %s connection error %d." - " Deviceid [%x%x%x%x] marked out of use.\n", - ds_remotestr, err, p[0], p[1], p[2], p[3]); - - spin_lock(&nfs4_ds_cache_lock); - dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY; - spin_unlock(&nfs4_ds_cache_lock); -} - struct nfs4_pnfs_ds * nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx) { struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr; struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx]; + struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg); + + if (filelayout_test_devid_invalid(devid)) + return NULL; if (ds == NULL) { printk(KERN_ERR "NFS: %s: No data server for offset index %d\n", __func__, ds_idx); - return NULL; + goto mark_dev_invalid; } if (!ds->ds_clp) { struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode); int err; - if (dsaddr->flags & NFS4_DEVICE_ID_NEG_ENTRY) { - /* Already tried to connect, don't try again */ - dprintk("%s Deviceid marked out of use\n", __func__); - return NULL; - } err = nfs4_ds_connect(s, ds); - if (err) { - filelayout_mark_devid_negative(dsaddr, err, - ds->ds_remotestr); - return NULL; - } + if (err) + goto mark_dev_invalid; } return ds; + +mark_dev_invalid: + filelayout_mark_devid_invalid(devid); + return NULL; } + +module_param(dataserver_retrans, uint, 0644); +MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client " + "retries a request before it attempts further " + " recovery action."); +module_param(dataserver_timeo, uint, 0644); +MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the " + "NFSv4.1 client waits for a response from a " + " data server before it retries an NFS request."); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 9c8eca315f4..017b4b01a69 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -52,6 +52,30 @@ Elong: } /* + * return the path component of "<server>:<path>" + * nfspath - the "<server>:<path>" string + * end - one past the last char that could contain "<server>:" + * returns NULL on failure + */ +static char *nfs_path_component(const char *nfspath, const char *end) +{ + char *p; + + if (*nfspath == '[') { + /* parse [] escaped IPv6 addrs */ + p = strchr(nfspath, ']'); + if (p != NULL && ++p < end && *p == ':') + return p + 1; + } else { + /* otherwise split on first colon */ + p = strchr(nfspath, ':'); + if (p != NULL && p < end) + return p + 1; + } + return NULL; +} + +/* * Determine the mount path as a string */ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) @@ -59,9 +83,9 @@ static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) char *limit; char *path = nfs_path(&limit, dentry, buffer, buflen); if (!IS_ERR(path)) { - char *colon = strchr(path, ':'); - if (colon && colon < limit) - path = colon + 1; + char *path_component = nfs_path_component(path, limit); + if (path_component) + return path_component; } return path; } @@ -108,6 +132,87 @@ static size_t nfs_parse_server_name(char *string, size_t len, return ret; } +rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors) +{ + struct gss_api_mech *mech; + struct xdr_netobj oid; + int i; + rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX; + + for (i = 0; i < flavors->num_flavors; i++) { + struct nfs4_secinfo_flavor *flavor; + flavor = &flavors->flavors[i]; + + if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) { + pseudoflavor = flavor->flavor; + break; + } else if (flavor->flavor == RPC_AUTH_GSS) { + oid.len = flavor->gss.sec_oid4.len; + oid.data = flavor->gss.sec_oid4.data; + mech = gss_mech_get_by_OID(&oid); + if (!mech) + continue; + pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service); + gss_mech_put(mech); + break; + } + } + + return pseudoflavor; +} + +static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) +{ + struct page *page; + struct nfs4_secinfo_flavors *flavors; + rpc_authflavor_t flavor; + int err; + + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + flavors = page_address(page); + + err = nfs4_proc_secinfo(inode, name, flavors); + if (err < 0) { + flavor = err; + goto out; + } + + flavor = nfs_find_best_sec(flavors); + +out: + put_page(page); + return flavor; +} + +/* + * Please call rpc_shutdown_client() when you are done with this client. + */ +struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode, + struct qstr *name) +{ + struct rpc_clnt *clone; + struct rpc_auth *auth; + rpc_authflavor_t flavor; + + flavor = nfs4_negotiate_security(inode, name); + if ((int)flavor < 0) + return ERR_PTR(flavor); + + clone = rpc_clone_client(clnt); + if (IS_ERR(clone)) + return clone; + + auth = rpcauth_create(flavor, clone); + if (!auth) { + rpc_shutdown_client(clone); + clone = ERR_PTR(-EIO); + } + + return clone; +} + static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, char *page, char *page2, const struct nfs4_fs_location *location) @@ -224,7 +329,7 @@ out: * @dentry - dentry of referral * */ -struct vfsmount *nfs_do_refmount(struct dentry *dentry) +static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry) { struct vfsmount *mnt = ERR_PTR(-ENOMEM); struct dentry *parent; @@ -250,7 +355,7 @@ struct vfsmount *nfs_do_refmount(struct dentry *dentry) dprintk("%s: getting locations for %s/%s\n", __func__, parent->d_name.name, dentry->d_name.name); - err = nfs4_proc_fs_locations(parent->d_inode, &dentry->d_name, fs_locations, page); + err = nfs4_proc_fs_locations(client, parent->d_inode, &dentry->d_name, fs_locations, page); dput(parent); if (err != 0 || fs_locations->nlocations <= 0 || @@ -265,3 +370,25 @@ out: dprintk("%s: done\n", __func__); return mnt; } + +struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + struct dentry *parent = dget_parent(dentry); + struct rpc_clnt *client; + struct vfsmount *mnt; + + /* Look it up again to get its attributes and sec flavor */ + client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr); + dput(parent); + if (IS_ERR(client)) + return ERR_CAST(client); + + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + mnt = nfs_do_refmount(client, dentry); + else + mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor); + + rpc_shutdown_client(client); + return mnt; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f82bde005a8..15fc7e4664e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -64,6 +64,7 @@ #include "iostat.h" #include "callback.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_PROC @@ -80,6 +81,7 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); +static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr); static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, @@ -101,6 +103,10 @@ static int nfs4_map_errors(int err) case -NFS4ERR_BADOWNER: case -NFS4ERR_BADNAME: return -EINVAL; + case -NFS4ERR_SHARE_DENIED: + return -EACCES; + case -NFS4ERR_MINOR_VERS_MISMATCH: + return -EPROTONOSUPPORT; default: dprintk("%s could not handle NFSv4 error %d\n", __func__, -err); @@ -112,7 +118,7 @@ static int nfs4_map_errors(int err) /* * This is our standard bitmap for GETATTR requests. */ -const u32 nfs4_fattr_bitmap[2] = { +const u32 nfs4_fattr_bitmap[3] = { FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE @@ -129,6 +135,24 @@ const u32 nfs4_fattr_bitmap[2] = { | FATTR4_WORD1_TIME_MODIFY }; +static const u32 nfs4_pnfs_open_bitmap[3] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY, + FATTR4_WORD2_MDSTHRESHOLD +}; + const u32 nfs4_statfs_bitmap[2] = { FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE @@ -304,7 +328,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc case -NFS4ERR_SEQ_MISORDERED: dprintk("%s ERROR: %d Reset session\n", __func__, errorcode); - nfs4_schedule_session_recovery(clp->cl_session); + nfs4_schedule_session_recovery(clp->cl_session, errorcode); exception->retry = 1; break; #endif /* defined(CONFIG_NFS_V4_1) */ @@ -772,7 +796,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) struct nfs_inode *nfsi = NFS_I(dir); spin_lock(&dir->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; if (!cinfo->atomic || cinfo->before != dir->i_version) nfs_force_lookup_revalidate(dir); dir->i_version = cinfo->after; @@ -788,7 +812,6 @@ struct nfs4_opendata { struct nfs4_string owner_name; struct nfs4_string group_name; struct nfs_fattr f_attr; - struct nfs_fattr dir_attr; struct dentry *dir; struct dentry *dentry; struct nfs4_state_owner *owner; @@ -804,12 +827,10 @@ struct nfs4_opendata { static void nfs4_init_opendata_res(struct nfs4_opendata *p) { p->o_res.f_attr = &p->f_attr; - p->o_res.dir_attr = &p->dir_attr; p->o_res.seqid = p->o_arg.seqid; p->c_res.seqid = p->c_arg.seqid; p->o_res.server = p->o_arg.server; nfs_fattr_init(&p->f_attr); - nfs_fattr_init(&p->dir_attr); nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name); } @@ -838,11 +859,12 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.open_flags = flags; p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE); p->o_arg.clientid = server->nfs_client->cl_clientid; - p->o_arg.id = sp->so_seqid.owner_id; + p->o_arg.id.create_time = ktime_to_ns(sp->so_seqid.create_time); + p->o_arg.id.uniquifier = sp->so_seqid.owner_id; p->o_arg.name = &dentry->d_name; p->o_arg.server = server; p->o_arg.bitmask = server->attr_bitmask; - p->o_arg.dir_bitmask = server->cache_consistency_bitmask; + p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; p->o_arg.claim = NFS4_OPEN_CLAIM_NULL; if (attrs != NULL && attrs->ia_valid != 0) { __be32 verf[2]; @@ -1331,7 +1353,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - nfs4_schedule_session_recovery(server->nfs_client->cl_session); + nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); goto out; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_STALE_STATEID: @@ -1466,8 +1488,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) goto unlock_no_action; rcu_read_unlock(); } - /* Update sequence id. */ - data->o_arg.id = sp->so_seqid.owner_id; + /* Update client id. */ data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid; if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) { task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR]; @@ -1611,8 +1632,6 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr); - nfs_refresh_inode(dir, o_res->dir_attr); - if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { status = _nfs4_proc_open_confirm(data); if (status != 0) @@ -1645,11 +1664,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data) nfs_fattr_map_and_free_names(server, &data->f_attr); - if (o_arg->open_flags & O_CREAT) { + if (o_arg->open_flags & O_CREAT) update_changeattr(dir, &o_res->cinfo); - nfs_post_op_update_inode(dir, o_res->dir_attr); - } else - nfs_refresh_inode(dir, o_res->dir_attr); if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0) server->caps &= ~NFS_CAP_POSIX_LOCK; if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) { @@ -1789,7 +1805,14 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct /* * Returns a referenced nfs4_state */ -static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred, struct nfs4_state **res) +static int _nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_state **res, + struct nfs4_threshold **ctx_th) { struct nfs4_state_owner *sp; struct nfs4_state *state = NULL; @@ -1814,6 +1837,12 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode if (opendata == NULL) goto err_put_state_owner; + if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { + opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); + if (!opendata->f_attr.mdsthreshold) + goto err_opendata_put; + opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; + } if (dentry->d_inode != NULL) opendata->state = nfs4_get_open_state(dentry->d_inode, sp); @@ -1839,11 +1868,19 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode nfs_setattr_update_inode(state->inode, sattr); nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr); } + + if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) + *ctx_th = opendata->f_attr.mdsthreshold; + else + kfree(opendata->f_attr.mdsthreshold); + opendata->f_attr.mdsthreshold = NULL; + nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); *res = state; return 0; err_opendata_put: + kfree(opendata->f_attr.mdsthreshold); nfs4_opendata_put(opendata); err_put_state_owner: nfs4_put_state_owner(sp); @@ -1853,14 +1890,22 @@ out_err: } -static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred) +static struct nfs4_state *nfs4_do_open(struct inode *dir, + struct dentry *dentry, + fmode_t fmode, + int flags, + struct iattr *sattr, + struct rpc_cred *cred, + struct nfs4_threshold **ctx_th) { struct nfs4_exception exception = { }; struct nfs4_state *res; int status; + fmode &= FMODE_READ|FMODE_WRITE; do { - status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, &res); + status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, + &res, ctx_th); if (status == 0) break; /* NOTE: BAD_SEQID means the server and client disagree about the @@ -1954,10 +1999,19 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, }; int err; do { - err = nfs4_handle_exception(server, - _nfs4_do_setattr(inode, cred, fattr, sattr, state), - &exception); + err = _nfs4_do_setattr(inode, cred, fattr, sattr, state); + switch (err) { + case -NFS4ERR_OPENMODE: + if (state && !(state->state & FMODE_WRITE)) { + err = -EBADF; + if (sattr->ia_valid & ATTR_OPEN) + err = -EACCES; + goto out; + } + } + err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); +out: return err; } @@ -2175,7 +2229,8 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags struct nfs4_state *state; /* Protect against concurrent sillydeletes */ - state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, ctx->cred); + state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, + ctx->cred, &ctx->mdsthreshold); if (IS_ERR(state)) return ERR_CAST(state); ctx->state = state; @@ -2345,8 +2400,8 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, /* * get the file handle for the "/" directory on the server */ -static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fsinfo *info) +int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fsinfo *info) { int minor_version = server->nfs_client->cl_minorversion; int status = nfs4_lookup_root(server, fhandle, info); @@ -2363,13 +2418,39 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, return nfs4_map_errors(status); } +static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, + struct nfs_fsinfo *info) +{ + int error; + struct nfs_fattr *fattr = info->fattr; + + error = nfs4_server_capabilities(server, mntfh); + if (error < 0) { + dprintk("nfs4_get_root: getcaps error = %d\n", -error); + return error; + } + + error = nfs4_proc_getattr(server, mntfh, fattr); + if (error < 0) { + dprintk("nfs4_get_root: getattr error = %d\n", -error); + return error; + } + + if (fattr->valid & NFS_ATTR_FATTR_FSID && + !nfs_fsid_equal(&server->fsid, &fattr->fsid)) + memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid)); + + return error; +} + /* * Get locations and (maybe) other attributes of a referral. * Note that we'll actually follow the referral later when * we detect fsid mismatch in inode revalidation */ -static int nfs4_get_referral(struct inode *dir, const struct qstr *name, - struct nfs_fattr *fattr, struct nfs_fh *fhandle) +static int nfs4_get_referral(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, struct nfs_fattr *fattr, + struct nfs_fh *fhandle) { int status = -ENOMEM; struct page *page = NULL; @@ -2382,7 +2463,7 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, if (locations == NULL) goto out; - status = nfs4_proc_fs_locations(dir, name, locations, page); + status = nfs4_proc_fs_locations(client, dir, name, locations, page); if (status != 0) goto out; /* Make sure server returned a different fsid for the referral */ @@ -2468,6 +2549,14 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, nfs_fattr_init(fattr); + /* Deal with open(O_TRUNC) */ + if (sattr->ia_valid & ATTR_OPEN) + sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); + + /* Optimization: if the end result is no change, don't RPC */ + if ((sattr->ia_valid & ~(ATTR_FILE)) == 0) + return 0; + /* Search for an existing open(O_WRITE) file */ if (sattr->ia_valid & ATTR_FILE) { struct nfs_open_context *ctx; @@ -2479,10 +2568,6 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } } - /* Deal with open(O_TRUNC) */ - if (sattr->ia_valid & ATTR_OPEN) - sattr->ia_valid &= ~(ATTR_MTIME|ATTR_CTIME|ATTR_OPEN); - status = nfs4_do_setattr(inode, cred, fattr, sattr, state); if (status == 0) nfs_setattr_update_inode(inode, sattr); @@ -2519,39 +2604,84 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, return status; } -void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr, struct nfs_fh *fh) +static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) { - memset(fh, 0, sizeof(struct nfs_fh)); - fattr->fsid.major = 1; fattr->valid |= NFS_ATTR_FATTR_TYPE | NFS_ATTR_FATTR_MODE | - NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_FSID | NFS_ATTR_FATTR_MOUNTPOINT; + NFS_ATTR_FATTR_NLINK | NFS_ATTR_FATTR_MOUNTPOINT; fattr->mode = S_IFDIR | S_IRUGO | S_IXUGO; fattr->nlink = 2; } -static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, - struct nfs_fh *fhandle, struct nfs_fattr *fattr) +static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, + struct qstr *name, struct nfs_fh *fhandle, + struct nfs_fattr *fattr) { struct nfs4_exception exception = { }; + struct rpc_clnt *client = *clnt; int err; do { - int status; - - status = _nfs4_proc_lookup(clnt, dir, name, fhandle, fattr); - switch (status) { + err = _nfs4_proc_lookup(client, dir, name, fhandle, fattr); + switch (err) { case -NFS4ERR_BADNAME: - return -ENOENT; + err = -ENOENT; + goto out; case -NFS4ERR_MOVED: - return nfs4_get_referral(dir, name, fattr, fhandle); + err = nfs4_get_referral(client, dir, name, fattr, fhandle); + goto out; case -NFS4ERR_WRONGSEC: - nfs_fixup_secinfo_attributes(fattr, fhandle); + err = -EPERM; + if (client != *clnt) + goto out; + + client = nfs4_create_sec_client(client, dir, name); + if (IS_ERR(client)) + return PTR_ERR(client); + + exception.retry = 1; + break; + default: + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); } - err = nfs4_handle_exception(NFS_SERVER(dir), - status, &exception); } while (exception.retry); + +out: + if (err == 0) + *clnt = client; + else if (client != *clnt) + rpc_shutdown_client(client); + return err; } +static int nfs4_proc_lookup(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) +{ + int status; + struct rpc_clnt *client = NFS_CLIENT(dir); + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr); + if (client != NFS_CLIENT(dir)) { + rpc_shutdown_client(client); + nfs_fixup_secinfo_attributes(fattr); + } + return status; +} + +struct rpc_clnt * +nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) +{ + int status; + struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir)); + + status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr); + if (status < 0) { + rpc_shutdown_client(client); + return ERR_PTR(status); + } + return client; +} + static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) { struct nfs_server *server = NFS_SERVER(inode); @@ -2706,7 +2836,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, fmode = ctx->mode; } sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, de, fmode, flags, sattr, cred); + state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); @@ -2727,9 +2857,7 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) struct nfs_server *server = NFS_SERVER(dir); struct nfs_removeargs args = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, - .bitmask = server->attr_bitmask, + .name = *name, }; struct nfs_removeres res = { .server = server, @@ -2739,19 +2867,11 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name) .rpc_argp = &args, .rpc_resp = &res, }; - int status = -ENOMEM; - - res.dir_attr = nfs_alloc_fattr(); - if (res.dir_attr == NULL) - goto out; + int status; status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); - if (status == 0) { + if (status == 0) update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); - } - nfs_free_fattr(res.dir_attr); -out: return status; } @@ -2773,7 +2893,6 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) struct nfs_removeargs *args = msg->rpc_argp; struct nfs_removeres *res = msg->rpc_resp; - args->bitmask = server->cache_consistency_bitmask; res->server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; nfs41_init_sequence(&args->seq_args, &res->seq_res, 1); @@ -2798,7 +2917,6 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) return 0; update_changeattr(dir, &res->cinfo); - nfs_post_op_update_inode(dir, res->dir_attr); return 1; } @@ -2809,7 +2927,6 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) struct nfs_renameres *res = msg->rpc_resp; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; - arg->bitmask = server->attr_bitmask; res->server = server; nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1); } @@ -2835,9 +2952,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, return 0; update_changeattr(old_dir, &res->old_cinfo); - nfs_post_op_update_inode(old_dir, res->old_fattr); update_changeattr(new_dir, &res->new_cinfo); - nfs_post_op_update_inode(new_dir, res->new_fattr); return 1; } @@ -2850,7 +2965,6 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, .new_dir = NFS_FH(new_dir), .old_name = old_name, .new_name = new_name, - .bitmask = server->attr_bitmask, }; struct nfs_renameres res = { .server = server, @@ -2862,21 +2976,11 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, }; int status = -ENOMEM; - res.old_fattr = nfs_alloc_fattr(); - res.new_fattr = nfs_alloc_fattr(); - if (res.old_fattr == NULL || res.new_fattr == NULL) - goto out; - status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(old_dir, &res.old_cinfo); - nfs_post_op_update_inode(old_dir, res.old_fattr); update_changeattr(new_dir, &res.new_cinfo); - nfs_post_op_update_inode(new_dir, res.new_fattr); } -out: - nfs_free_fattr(res.new_fattr); - nfs_free_fattr(res.old_fattr); return status; } @@ -2914,18 +3018,15 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr * int status = -ENOMEM; res.fattr = nfs_alloc_fattr(); - res.dir_attr = nfs_alloc_fattr(); - if (res.fattr == NULL || res.dir_attr == NULL) + if (res.fattr == NULL) goto out; status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { update_changeattr(dir, &res.cinfo); - nfs_post_op_update_inode(dir, res.dir_attr); nfs_post_op_update_inode(inode, res.fattr); } out: - nfs_free_fattr(res.dir_attr); nfs_free_fattr(res.fattr); return status; } @@ -2948,7 +3049,6 @@ struct nfs4_createdata { struct nfs4_create_res res; struct nfs_fh fh; struct nfs_fattr fattr; - struct nfs_fattr dir_fattr; }; static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, @@ -2972,9 +3072,7 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, data->res.server = server; data->res.fh = &data->fh; data->res.fattr = &data->fattr; - data->res.dir_fattr = &data->dir_fattr; nfs_fattr_init(data->res.fattr); - nfs_fattr_init(data->res.dir_fattr); } return data; } @@ -2985,7 +3083,6 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ &data->arg.seq_args, &data->res.seq_res, 1); if (status == 0) { update_changeattr(dir, &data->res.dir_cinfo); - nfs_post_op_update_inode(dir, data->res.dir_fattr); status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); } return status; @@ -3281,12 +3378,12 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, void __nfs4_read_done_cb(struct nfs_read_data *data) { - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(data->header->inode); } static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3321,7 +3418,7 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data) { - if (nfs4_setup_sequence(NFS_SERVER(data->inode), + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), &data->args.seq_args, &data->res.seq_res, task)) @@ -3329,25 +3426,9 @@ static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da rpc_call_start(task); } -/* Reset the the nfs_read_data to send the read to the MDS. */ -void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data) -{ - dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; - /* offsets will differ in the dense stripe case */ - data->args.offset = data->mds_offset; - data->ds_clp = NULL; - data->args.fh = NFS_FH(data->inode); - data->read_done_cb = nfs4_read_done_cb; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); -} -EXPORT_SYMBOL_GPL(nfs4_reset_read); - static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) { rpc_restart_call_prepare(task); @@ -3355,7 +3436,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data } if (task->tk_status >= 0) { renew_lease(NFS_SERVER(inode), data->timestamp); - nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, &data->fattr); } return 0; } @@ -3368,32 +3449,30 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data) nfs4_write_done_cb(task, data); } -/* Reset the the nfs_write_data to send the write to the MDS. */ -void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data) +static +bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data) { - dprintk("%s Reset task for i/o through\n", __func__); - put_lseg(data->lseg); - data->lseg = NULL; - data->ds_clp = NULL; - data->write_done_cb = nfs4_write_done_cb; - data->args.fh = NFS_FH(data->inode); - data->args.bitmask = data->res.server->cache_consistency_bitmask; - data->args.offset = data->mds_offset; - data->res.fattr = &data->fattr; - task->tk_ops = data->mds_ops; - rpc_task_reset_client(task, NFS_CLIENT(data->inode)); + const struct nfs_pgio_header *hdr = data->header; + + /* Don't request attributes for pNFS or O_DIRECT writes */ + if (data->ds_clp != NULL || hdr->dreq != NULL) + return false; + /* Otherwise, request attributes if and only if we don't hold + * a delegation + */ + return nfs_have_delegation(hdr->inode, FMODE_READ) == 0; } -EXPORT_SYMBOL_GPL(nfs4_reset_write); static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) { - struct nfs_server *server = NFS_SERVER(data->inode); + struct nfs_server *server = NFS_SERVER(data->header->inode); - if (data->lseg) { + if (!nfs4_write_need_cache_consistency_data(data)) { data->args.bitmask = NULL; data->res.fattr = NULL; } else data->args.bitmask = server->cache_consistency_bitmask; + if (!data->write_done_cb) data->write_done_cb = nfs4_write_done_cb; data->res.server = server; @@ -3405,6 +3484,16 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data) { + if (nfs4_setup_sequence(NFS_SERVER(data->header->inode), + &data->args.seq_args, + &data->res.seq_res, + task)) + return; + rpc_call_start(task); +} + +static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ if (nfs4_setup_sequence(NFS_SERVER(data->inode), &data->args.seq_args, &data->res.seq_res, @@ -3413,7 +3502,7 @@ static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_ rpc_call_start(task); } -static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *data) { struct inode *inode = data->inode; @@ -3421,28 +3510,22 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *dat rpc_restart_call_prepare(task); return -EAGAIN; } - nfs_refresh_inode(inode, data->res.fattr); return 0; } -static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data) +static int nfs4_commit_done(struct rpc_task *task, struct nfs_commit_data *data) { if (!nfs4_sequence_done(task, &data->res.seq_res)) return -EAGAIN; - return data->write_done_cb(task, data); + return data->commit_done_cb(task, data); } -static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg) +static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) { struct nfs_server *server = NFS_SERVER(data->inode); - if (data->lseg) { - data->args.bitmask = NULL; - data->res.fattr = NULL; - } else - data->args.bitmask = server->cache_consistency_bitmask; - if (!data->write_done_cb) - data->write_done_cb = nfs4_commit_done_cb; + if (data->commit_done_cb == NULL) + data->commit_done_cb = nfs4_commit_done_cb; data->res.server = server; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT]; nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); @@ -3619,16 +3702,16 @@ out: return ret; } -static void nfs4_write_cached_acl(struct inode *inode, const char *buf, size_t acl_len) +static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; - if (buf && acl_len <= PAGE_SIZE) { + if (pages && acl_len <= PAGE_SIZE) { acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; - memcpy(acl->data, buf, acl_len); + _copy_from_pages(acl->data, pages, pgbase, acl_len); } else { acl = kmalloc(sizeof(*acl), GFP_KERNEL); if (acl == NULL) @@ -3661,7 +3744,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu struct nfs_getaclres res = { .acl_len = buflen, }; - void *resp_buf; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETACL], .rpc_argp = &args, @@ -3675,24 +3757,27 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (npages == 0) npages = 1; + /* Add an extra page to handle the bitmap returned */ + npages++; + for (i = 0; i < npages; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) goto out_free; } - if (npages > 1) { - /* for decoding across pages */ - res.acl_scratch = alloc_page(GFP_KERNEL); - if (!res.acl_scratch) - goto out_free; - } + + /* for decoding across pages */ + res.acl_scratch = alloc_page(GFP_KERNEL); + if (!res.acl_scratch) + goto out_free; + args.acl_len = npages * PAGE_SIZE; args.acl_pgbase = 0; + /* Let decode_getfacl know not to fail if the ACL data is larger than * the page we send as a guess */ if (buf == NULL) res.acl_flags |= NFS4_ACL_LEN_REQUEST; - resp_buf = page_address(pages[0]); dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); @@ -3703,9 +3788,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu acl_len = res.acl_len - res.acl_data_offset; if (acl_len > args.acl_len) - nfs4_write_cached_acl(inode, NULL, acl_len); + nfs4_write_cached_acl(inode, NULL, 0, acl_len); else - nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset, + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, acl_len); if (buf) { ret = -ERANGE; @@ -3849,7 +3934,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, case -NFS4ERR_SEQ_MISORDERED: dprintk("%s ERROR %d, Reset session\n", __func__, task->tk_status); - nfs4_schedule_session_recovery(clp->cl_session); + nfs4_schedule_session_recovery(clp->cl_session, task->tk_status); task->tk_status = 0; return -EAGAIN; #endif /* CONFIG_NFS_V4_1 */ @@ -3875,13 +3960,21 @@ wait_on_recovery: return -EAGAIN; } -static void nfs4_construct_boot_verifier(struct nfs_client *clp, - nfs4_verifier *bootverf) +static void nfs4_init_boot_verifier(const struct nfs_client *clp, + nfs4_verifier *bootverf) { __be32 verf[2]; - verf[0] = htonl((u32)clp->cl_boot_time.tv_sec); - verf[1] = htonl((u32)clp->cl_boot_time.tv_nsec); + if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { + /* An impossible timestamp guarantees this value + * will never match a generated boot time. */ + verf[0] = 0; + verf[1] = (__be32)(NSEC_PER_SEC + 1); + } else { + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + verf[0] = (__be32)nn->boot_time.tv_sec; + verf[1] = (__be32)nn->boot_time.tv_nsec; + } memcpy(bootverf->data, verf, sizeof(bootverf->data)); } @@ -3904,7 +3997,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, int loop = 0; int status; - nfs4_construct_boot_verifier(clp, &sc_verifier); + nfs4_init_boot_verifier(clp, &sc_verifier); for(;;) { rcu_read_lock(); @@ -4048,7 +4141,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1); data->args.fhandle = &data->fh; data->args.stateid = &data->stateid; - data->args.bitmask = server->attr_bitmask; + data->args.bitmask = server->cache_consistency_bitmask; nfs_copy_fh(&data->fh, NFS_FH(inode)); nfs4_stateid_copy(&data->stateid, stateid); data->res.fattr = &data->fattr; @@ -4069,9 +4162,10 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co if (status != 0) goto out; status = data->rpc_status; - if (status != 0) - goto out; - nfs_refresh_inode(inode, &data->fattr); + if (status == 0) + nfs_post_op_update_inode_force_wcc(inode, &data->fattr); + else + nfs_refresh_inode(inode, &data->fattr); out: rpc_put_task(task); return status; @@ -4558,7 +4652,9 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request) { struct nfs_server *server = NFS_SERVER(state->inode); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .inode = state->inode, + }; int err; do { @@ -4576,7 +4672,9 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request) { struct nfs_server *server = NFS_SERVER(state->inode); - struct nfs4_exception exception = { }; + struct nfs4_exception exception = { + .inode = state->inode, + }; int err; err = nfs4_set_lock_state(state, request); @@ -4676,6 +4774,7 @@ static int nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock * { struct nfs4_exception exception = { .state = state, + .inode = state->inode, }; int err; @@ -4721,6 +4820,20 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request) if (state == NULL) return -ENOLCK; + /* + * Don't rely on the VFS having checked the file open mode, + * since it won't do this for flock() locks. + */ + switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) { + case F_RDLCK: + if (!(filp->f_mode & FMODE_READ)) + return -EBADF; + break; + case F_WRLCK: + if (!(filp->f_mode & FMODE_WRITE)) + return -EBADF; + } + do { status = nfs4_proc_setlk(state, cmd, request); if ((status != -EAGAIN) || IS_SETLK(cmd)) @@ -4762,7 +4875,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl) case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_DEADSESSION: - nfs4_schedule_session_recovery(server->nfs_client->cl_session); + nfs4_schedule_session_recovery(server->nfs_client->cl_session, err); goto out; case -ERESTARTSYS: /* @@ -4891,8 +5004,10 @@ static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr) fattr->nlink = 2; } -int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, - struct nfs4_fs_locations *fs_locations, struct page *page) +static int _nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) { struct nfs_server *server = NFS_SERVER(dir); u32 bitmask[2] = { @@ -4926,11 +5041,26 @@ int nfs4_proc_fs_locations(struct inode *dir, const struct qstr *name, nfs_fattr_init(&fs_locations->fattr); fs_locations->server = server; fs_locations->nlocations = 0; - status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); + status = nfs4_call_sync(client, server, &msg, &args.seq_args, &res.seq_res, 0); dprintk("%s: returned status = %d\n", __func__, status); return status; } +int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, + const struct qstr *name, + struct nfs4_fs_locations *fs_locations, + struct page *page) +{ + struct nfs4_exception exception = { }; + int err; + do { + err = nfs4_handle_exception(NFS_SERVER(dir), + _nfs4_proc_fs_locations(client, dir, name, fs_locations, page), + &exception); + } while (exception.retry); + return err; +} + static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct nfs4_secinfo_flavors *flavors) { int status; @@ -4953,8 +5083,8 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct return status; } -static int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, - struct nfs4_secinfo_flavors *flavors) +int nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, + struct nfs4_secinfo_flavors *flavors) { struct nfs4_exception exception = { }; int err; @@ -4987,7 +5117,8 @@ out_inval: } static bool -nfs41_same_server_scope(struct server_scope *a, struct server_scope *b) +nfs41_same_server_scope(struct nfs41_server_scope *a, + struct nfs41_server_scope *b) { if (a->server_scope_sz == b->server_scope_sz && memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0) @@ -4997,6 +5128,61 @@ nfs41_same_server_scope(struct server_scope *a, struct server_scope *b) } /* + * nfs4_proc_bind_conn_to_session() + * + * The 4.1 client currently uses the same TCP connection for the + * fore and backchannel. + */ +int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred) +{ + int status; + struct nfs41_bind_conn_to_session_res res; + struct rpc_message msg = { + .rpc_proc = + &nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION], + .rpc_argp = clp, + .rpc_resp = &res, + .rpc_cred = cred, + }; + + dprintk("--> %s\n", __func__); + BUG_ON(clp == NULL); + + res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS); + if (unlikely(res.session == NULL)) { + status = -ENOMEM; + goto out; + } + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status == 0) { + if (memcmp(res.session->sess_id.data, + clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) { + dprintk("NFS: %s: Session ID mismatch\n", __func__); + status = -EIO; + goto out_session; + } + if (res.dir != NFS4_CDFS4_BOTH) { + dprintk("NFS: %s: Unexpected direction from server\n", + __func__); + status = -EIO; + goto out_session; + } + if (res.use_conn_in_rdma_mode) { + dprintk("NFS: %s: Server returned RDMA mode = true\n", + __func__); + status = -EIO; + goto out_session; + } + } +out_session: + kfree(res.session); +out: + dprintk("<-- %s status= %d\n", __func__, status); + return status; +} + +/* * nfs4_proc_exchange_id() * * Since the clientid has expired, all compounds using sessions @@ -5013,7 +5199,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER, }; struct nfs41_exchange_id_res res = { - .client = clp, + 0 }; int status; struct rpc_message msg = { @@ -5026,68 +5212,143 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) dprintk("--> %s\n", __func__); BUG_ON(clp == NULL); - nfs4_construct_boot_verifier(clp, &verifier); + nfs4_init_boot_verifier(clp, &verifier); args.id_len = scnprintf(args.id, sizeof(args.id), - "%s/%s.%s/%u", + "%s/%s/%u", clp->cl_ipaddr, - init_utsname()->nodename, - init_utsname()->domainname, + clp->cl_rpcclient->cl_nodename, clp->cl_rpcclient->cl_auth->au_flavor); - res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL); - if (unlikely(!res.server_scope)) { + res.server_owner = kzalloc(sizeof(struct nfs41_server_owner), + GFP_NOFS); + if (unlikely(res.server_owner == NULL)) { status = -ENOMEM; goto out; } - res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL); - if (unlikely(!res.impl_id)) { + res.server_scope = kzalloc(sizeof(struct nfs41_server_scope), + GFP_NOFS); + if (unlikely(res.server_scope == NULL)) { + status = -ENOMEM; + goto out_server_owner; + } + + res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_NOFS); + if (unlikely(res.impl_id == NULL)) { status = -ENOMEM; goto out_server_scope; } status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); - if (!status) - status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags); + if (status == 0) + status = nfs4_check_cl_exchange_flags(res.flags); + + if (status == 0) { + clp->cl_clientid = res.clientid; + clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R); + if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) + clp->cl_seqid = res.seqid; + + kfree(clp->cl_serverowner); + clp->cl_serverowner = res.server_owner; + res.server_owner = NULL; - if (!status) { /* use the most recent implementation id */ - kfree(clp->impl_id); - clp->impl_id = res.impl_id; - } else - kfree(res.impl_id); + kfree(clp->cl_implid); + clp->cl_implid = res.impl_id; - if (!status) { - if (clp->server_scope && - !nfs41_same_server_scope(clp->server_scope, + if (clp->cl_serverscope != NULL && + !nfs41_same_server_scope(clp->cl_serverscope, res.server_scope)) { dprintk("%s: server_scope mismatch detected\n", __func__); set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state); - kfree(clp->server_scope); - clp->server_scope = NULL; + kfree(clp->cl_serverscope); + clp->cl_serverscope = NULL; } - if (!clp->server_scope) { - clp->server_scope = res.server_scope; + if (clp->cl_serverscope == NULL) { + clp->cl_serverscope = res.server_scope; goto out; } - } + } else + kfree(res.impl_id); +out_server_owner: + kfree(res.server_owner); out_server_scope: kfree(res.server_scope); out: - if (clp->impl_id) + if (clp->cl_implid != NULL) dprintk("%s: Server Implementation ID: " "domain: %s, name: %s, date: %llu,%u\n", - __func__, clp->impl_id->domain, clp->impl_id->name, - clp->impl_id->date.seconds, - clp->impl_id->date.nseconds); + __func__, clp->cl_implid->domain, clp->cl_implid->name, + clp->cl_implid->date.seconds, + clp->cl_implid->date.nseconds); dprintk("<-- %s status= %d\n", __func__, status); return status; } +static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID], + .rpc_argp = clp, + .rpc_cred = cred, + }; + int status; + + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + if (status) + dprintk("NFS: Got error %d from the server %s on " + "DESTROY_CLIENTID.", status, clp->cl_hostname); + return status; +} + +static int nfs4_proc_destroy_clientid(struct nfs_client *clp, + struct rpc_cred *cred) +{ + unsigned int loop; + int ret; + + for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) { + ret = _nfs4_proc_destroy_clientid(clp, cred); + switch (ret) { + case -NFS4ERR_DELAY: + case -NFS4ERR_CLIENTID_BUSY: + ssleep(1); + break; + default: + return ret; + } + } + return 0; +} + +int nfs4_destroy_clientid(struct nfs_client *clp) +{ + struct rpc_cred *cred; + int ret = 0; + + if (clp->cl_mvops->minor_version < 1) + goto out; + if (clp->cl_exchange_flags == 0) + goto out; + cred = nfs4_get_exchange_id_cred(clp); + ret = nfs4_proc_destroy_clientid(clp, cred); + if (cred) + put_rpccred(cred); + switch (ret) { + case 0: + case -NFS4ERR_STALE_CLIENTID: + clp->cl_exchange_flags = 0; + } +out: + return ret; +} + struct nfs4_get_lease_time_data { struct nfs4_get_lease_time_args *args; struct nfs4_get_lease_time_res *res; @@ -5308,8 +5569,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp) void nfs4_destroy_session(struct nfs4_session *session) { struct rpc_xprt *xprt; + struct rpc_cred *cred; - nfs4_proc_destroy_session(session); + cred = nfs4_get_exchange_id_cred(session->clp); + nfs4_proc_destroy_session(session, cred); + if (cred) + put_rpccred(cred); rcu_read_lock(); xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt); @@ -5419,7 +5684,8 @@ static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args, return nfs4_verify_back_channel_attrs(args, session); } -static int _nfs4_proc_create_session(struct nfs_client *clp) +static int _nfs4_proc_create_session(struct nfs_client *clp, + struct rpc_cred *cred) { struct nfs4_session *session = clp->cl_session; struct nfs41_create_session_args args = { @@ -5433,6 +5699,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE_SESSION], .rpc_argp = &args, .rpc_resp = &res, + .rpc_cred = cred, }; int status; @@ -5457,7 +5724,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp) * It is the responsibility of the caller to verify the session is * expired before calling this routine. */ -int nfs4_proc_create_session(struct nfs_client *clp) +int nfs4_proc_create_session(struct nfs_client *clp, struct rpc_cred *cred) { int status; unsigned *ptr; @@ -5465,7 +5732,7 @@ int nfs4_proc_create_session(struct nfs_client *clp) dprintk("--> %s clp=%p session=%p\n", __func__, clp, session); - status = _nfs4_proc_create_session(clp); + status = _nfs4_proc_create_session(clp, cred); if (status) goto out; @@ -5487,10 +5754,15 @@ out: * Issue the over-the-wire RPC DESTROY_SESSION. * The caller must serialize access to this routine. */ -int nfs4_proc_destroy_session(struct nfs4_session *session) +int nfs4_proc_destroy_session(struct nfs4_session *session, + struct rpc_cred *cred) { + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION], + .rpc_argp = session, + .rpc_cred = cred, + }; int status = 0; - struct rpc_message msg; dprintk("--> nfs4_proc_destroy_session\n"); @@ -5498,68 +5770,89 @@ int nfs4_proc_destroy_session(struct nfs4_session *session) if (session->clp->cl_cons_state != NFS_CS_READY) return status; - msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION]; - msg.rpc_argp = session; - msg.rpc_resp = NULL; - msg.rpc_cred = NULL; status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status) - printk(KERN_WARNING - "NFS: Got error %d from the server on DESTROY_SESSION. " + dprintk("NFS: Got error %d from the server on DESTROY_SESSION. " "Session has been destroyed regardless...\n", status); dprintk("<-- nfs4_proc_destroy_session\n"); return status; } +/* + * With sessions, the client is not marked ready until after a + * successful EXCHANGE_ID and CREATE_SESSION. + * + * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate + * other versions of NFS can be tried. + */ +static int nfs41_check_session_ready(struct nfs_client *clp) +{ + int ret; + + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) { + ret = nfs4_client_recover_expired_lease(clp); + if (ret) + return ret; + } + if (clp->cl_cons_state < NFS_CS_READY) + return -EPROTONOSUPPORT; + smp_rmb(); + return 0; +} + int nfs4_init_session(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; struct nfs4_session *session; unsigned int rsize, wsize; - int ret; if (!nfs4_has_session(clp)) return 0; session = clp->cl_session; - if (!test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) - return 0; + spin_lock(&clp->cl_lock); + if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) { - rsize = server->rsize; - if (rsize == 0) - rsize = NFS_MAX_FILE_IO_SIZE; - wsize = server->wsize; - if (wsize == 0) - wsize = NFS_MAX_FILE_IO_SIZE; + rsize = server->rsize; + if (rsize == 0) + rsize = NFS_MAX_FILE_IO_SIZE; + wsize = server->wsize; + if (wsize == 0) + wsize = NFS_MAX_FILE_IO_SIZE; - session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead; - session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead; + session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead; + session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead; + } + spin_unlock(&clp->cl_lock); - ret = nfs4_recover_expired_lease(server); - if (!ret) - ret = nfs4_check_client_ready(clp); - return ret; + return nfs41_check_session_ready(clp); } -int nfs4_init_ds_session(struct nfs_client *clp) +int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time) { struct nfs4_session *session = clp->cl_session; int ret; - if (!test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) - return 0; - - ret = nfs4_client_recover_expired_lease(clp); - if (!ret) - /* Test for the DS role */ - if (!is_ds_client(clp)) - ret = -ENODEV; - if (!ret) - ret = nfs4_check_client_ready(clp); - return ret; + spin_lock(&clp->cl_lock); + if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) { + /* + * Do not set NFS_CS_CHECK_LEASE_TIME instead set the + * DS lease to be equal to the MDS lease. + */ + clp->cl_lease_time = lease_time; + clp->cl_last_renewal = jiffies; + } + spin_unlock(&clp->cl_lock); + ret = nfs41_check_session_ready(clp); + if (ret) + return ret; + /* Test for the DS role */ + if (!is_ds_client(clp)) + return -ENODEV; + return 0; } EXPORT_SYMBOL_GPL(nfs4_init_ds_session); @@ -6466,6 +6759,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .file_inode_ops = &nfs4_file_inode_operations, .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, + .submount = nfs4_submount, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, @@ -6498,13 +6792,13 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .write_rpc_prepare = nfs4_proc_write_rpc_prepare, .write_done = nfs4_write_done, .commit_setup = nfs4_proc_commit_setup, + .commit_rpc_prepare = nfs4_proc_commit_rpc_prepare, .commit_done = nfs4_commit_done, .lock = nfs4_proc_lock, .clear_acl_cache = nfs4_zap_acl_attr, .close_context = nfs4_close_context, .open_context = nfs4_atomic_open, .init_client = nfs4_init_client, - .secinfo = nfs4_proc_secinfo, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index dc484c0eae7..6930bec91bc 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -49,7 +49,7 @@ #include "nfs4_fs.h" #include "delegation.h" -#define NFSDBG_FACILITY NFSDBG_PROC +#define NFSDBG_FACILITY NFSDBG_STATE void nfs4_renew_state(struct work_struct *work) diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 0f43414eb25..f38300e9f17 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -57,6 +57,8 @@ #include "internal.h" #include "pnfs.h" +#define NFSDBG_FACILITY NFSDBG_STATE + #define OPENOWNER_POOL_SIZE 8 const nfs4_stateid zero_stateid; @@ -242,6 +244,16 @@ static int nfs4_begin_drain_session(struct nfs_client *clp) return nfs4_wait_on_slot_tbl(&ses->fc_slot_table); } +static void nfs41_finish_session_reset(struct nfs_client *clp) +{ + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + /* create_session negotiated new slot table */ + clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); + clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + nfs41_setup_state_renewal(clp); +} + int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) { int status; @@ -254,11 +266,10 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) goto out; set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); do_confirm: - status = nfs4_proc_create_session(clp); + status = nfs4_proc_create_session(clp, cred); if (status != 0) goto out; - clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); - nfs41_setup_state_renewal(clp); + nfs41_finish_session_reset(clp); nfs_mark_client_ready(clp, NFS_CS_READY); out: return status; @@ -393,6 +404,7 @@ nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp) static void nfs4_init_seqid_counter(struct nfs_seqid_counter *sc) { + sc->create_time = ktime_get(); sc->flags = 0; sc->counter = 0; spin_lock_init(&sc->lock); @@ -434,13 +446,17 @@ nfs4_alloc_state_owner(struct nfs_server *server, static void nfs4_drop_state_owner(struct nfs4_state_owner *sp) { - if (!RB_EMPTY_NODE(&sp->so_server_node)) { + struct rb_node *rb_node = &sp->so_server_node; + + if (!RB_EMPTY_NODE(rb_node)) { struct nfs_server *server = sp->so_server; struct nfs_client *clp = server->nfs_client; spin_lock(&clp->cl_lock); - rb_erase(&sp->so_server_node, &server->state_owners); - RB_CLEAR_NODE(&sp->so_server_node); + if (!RB_EMPTY_NODE(rb_node)) { + rb_erase(rb_node, &server->state_owners); + RB_CLEAR_NODE(rb_node); + } spin_unlock(&clp->cl_lock); } } @@ -516,6 +532,14 @@ out: /** * nfs4_put_state_owner - Release a nfs4_state_owner * @sp: state owner data to release + * + * Note that we keep released state owners on an LRU + * list. + * This caches valid state owners so that they can be + * reused, to avoid the OPEN_CONFIRM on minor version 0. + * It also pins the uniquifier of dropped state owners for + * a while, to ensure that those state owner names are + * never reused. */ void nfs4_put_state_owner(struct nfs4_state_owner *sp) { @@ -525,15 +549,9 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp) if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock)) return; - if (!RB_EMPTY_NODE(&sp->so_server_node)) { - sp->so_expires = jiffies; - list_add_tail(&sp->so_lru, &server->state_owners_lru); - spin_unlock(&clp->cl_lock); - } else { - nfs4_remove_state_owner_locked(sp); - spin_unlock(&clp->cl_lock); - nfs4_free_state_owner(sp); - } + sp->so_expires = jiffies; + list_add_tail(&sp->so_lru, &server->state_owners_lru); + spin_unlock(&clp->cl_lock); } /** @@ -1099,6 +1117,8 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp) return; if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + dprintk("%s: scheduling lease recovery for server %s\n", __func__, + clp->cl_hostname); nfs4_schedule_state_manager(clp); } EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery); @@ -1115,6 +1135,8 @@ static void nfs40_handle_cb_pathdown(struct nfs_client *clp) { set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); nfs_expire_all_delegations(clp); + dprintk("%s: handling CB_PATHDOWN recovery for server %s\n", __func__, + clp->cl_hostname); } void nfs4_schedule_path_down_recovery(struct nfs_client *clp) @@ -1151,6 +1173,8 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4 struct nfs_client *clp = server->nfs_client; nfs4_state_mark_reclaim_nograce(clp, state); + dprintk("%s: scheduling stateid recovery for server %s\n", __func__, + clp->cl_hostname); nfs4_schedule_state_manager(clp); } EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery); @@ -1484,19 +1508,25 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) case -NFS4ERR_BADSLOT: case -NFS4ERR_BAD_HIGH_SLOT: case -NFS4ERR_DEADSESSION: - case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: case -NFS4ERR_SEQ_FALSE_RETRY: case -NFS4ERR_SEQ_MISORDERED: set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); /* Zero session reset errors */ break; + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + break; case -EKEYEXPIRED: /* Nothing we can do */ nfs4_warn_keyexpired(clp->cl_hostname); break; default: + dprintk("%s: failed to handle error %d for server %s\n", + __func__, error, clp->cl_hostname); return error; } + dprintk("%s: handled error %d for server %s\n", __func__, error, + clp->cl_hostname); return 0; } @@ -1565,34 +1595,82 @@ out: return nfs4_recovery_handle_error(clp, status); } +/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors + * on EXCHANGE_ID for v4.1 + */ +static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) +{ + switch (status) { + case -NFS4ERR_SEQ_MISORDERED: + if (test_and_set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) + return -ESERVERFAULT; + /* Lease confirmation error: retry after purging the lease */ + ssleep(1); + case -NFS4ERR_CLID_INUSE: + case -NFS4ERR_STALE_CLIENTID: + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + break; + case -EACCES: + if (clp->cl_machine_cred == NULL) + return -EACCES; + /* Handle case where the user hasn't set up machine creds */ + nfs4_clear_machine_cred(clp); + case -NFS4ERR_DELAY: + case -ETIMEDOUT: + case -EAGAIN: + ssleep(1); + break; + + case -NFS4ERR_MINOR_VERS_MISMATCH: + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) + nfs_mark_client_ready(clp, -EPROTONOSUPPORT); + dprintk("%s: exit with error %d for server %s\n", + __func__, -EPROTONOSUPPORT, clp->cl_hostname); + return -EPROTONOSUPPORT; + case -EKEYEXPIRED: + nfs4_warn_keyexpired(clp->cl_hostname); + case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery + * in nfs4_exchange_id */ + default: + dprintk("%s: exit with error %d for server %s\n", __func__, + status, clp->cl_hostname); + return status; + } + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + dprintk("%s: handled error %d for server %s\n", __func__, status, + clp->cl_hostname); + return 0; +} + static int nfs4_reclaim_lease(struct nfs_client *clp) { struct rpc_cred *cred; const struct nfs4_state_recovery_ops *ops = clp->cl_mvops->reboot_recovery_ops; - int status = -ENOENT; + int status; cred = ops->get_clid_cred(clp); - if (cred != NULL) { - status = ops->establish_clid(clp, cred); - put_rpccred(cred); - /* Handle case where the user hasn't set up machine creds */ - if (status == -EACCES && cred == clp->cl_machine_cred) { - nfs4_clear_machine_cred(clp); - status = -EAGAIN; - } - if (status == -NFS4ERR_MINOR_VERS_MISMATCH) - status = -EPROTONOSUPPORT; - } - return status; + if (cred == NULL) + return -ENOENT; + status = ops->establish_clid(clp, cred); + put_rpccred(cred); + if (status != 0) + return nfs4_handle_reclaim_lease_error(clp, status); + return 0; } #ifdef CONFIG_NFS_V4_1 -void nfs4_schedule_session_recovery(struct nfs4_session *session) +void nfs4_schedule_session_recovery(struct nfs4_session *session, int err) { struct nfs_client *clp = session->clp; - set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + switch (err) { + default: + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + break; + case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION: + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + } nfs4_schedule_lease_recovery(clp); } EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery); @@ -1600,14 +1678,19 @@ EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery); void nfs41_handle_recall_slot(struct nfs_client *clp) { set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); + dprintk("%s: scheduling slot recall for server %s\n", __func__, + clp->cl_hostname); nfs4_schedule_state_manager(clp); } static void nfs4_reset_all_state(struct nfs_client *clp) { if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { - clp->cl_boot_time = CURRENT_TIME; + set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); nfs4_state_start_reclaim_nograce(clp); + dprintk("%s: scheduling reset of all state for server %s!\n", + __func__, clp->cl_hostname); nfs4_schedule_state_manager(clp); } } @@ -1616,33 +1699,50 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp) { if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) { nfs4_state_start_reclaim_reboot(clp); + dprintk("%s: server %s rebooted!\n", __func__, + clp->cl_hostname); nfs4_schedule_state_manager(clp); } } static void nfs41_handle_state_revoked(struct nfs_client *clp) { - /* Temporary */ nfs4_reset_all_state(clp); + dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); } static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) { /* This will need to handle layouts too */ nfs_expire_all_delegations(clp); + dprintk("%s: Recallable state revoked on server %s!\n", __func__, + clp->cl_hostname); } -static void nfs41_handle_cb_path_down(struct nfs_client *clp) +static void nfs41_handle_backchannel_fault(struct nfs_client *clp) { nfs_expire_all_delegations(clp); if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0) nfs4_schedule_state_manager(clp); + dprintk("%s: server %s declared a backchannel fault\n", __func__, + clp->cl_hostname); +} + +static void nfs41_handle_cb_path_down(struct nfs_client *clp) +{ + if (test_and_set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, + &clp->cl_state) == 0) + nfs4_schedule_state_manager(clp); } void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) { if (!flags) return; + + dprintk("%s: \"%s\" (client ID %llx) flags=0x%08x\n", + __func__, clp->cl_hostname, clp->cl_clientid, flags); + if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) nfs41_handle_server_reboot(clp); if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | @@ -1652,18 +1752,21 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) nfs41_handle_state_revoked(clp); if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) nfs41_handle_recallable_state_revoked(clp); - if (flags & (SEQ4_STATUS_CB_PATH_DOWN | - SEQ4_STATUS_BACKCHANNEL_FAULT | - SEQ4_STATUS_CB_PATH_DOWN_SESSION)) + if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT) + nfs41_handle_backchannel_fault(clp); + else if (flags & (SEQ4_STATUS_CB_PATH_DOWN | + SEQ4_STATUS_CB_PATH_DOWN_SESSION)) nfs41_handle_cb_path_down(clp); } static int nfs4_reset_session(struct nfs_client *clp) { + struct rpc_cred *cred; int status; nfs4_begin_drain_session(clp); - status = nfs4_proc_destroy_session(clp->cl_session); + cred = nfs4_get_exchange_id_cred(clp); + status = nfs4_proc_destroy_session(clp->cl_session, cred); if (status && status != -NFS4ERR_BADSESSION && status != -NFS4ERR_DEADSESSION) { status = nfs4_recovery_handle_error(clp, status); @@ -1671,19 +1774,19 @@ static int nfs4_reset_session(struct nfs_client *clp) } memset(clp->cl_session->sess_id.data, 0, NFS4_MAX_SESSIONID_LEN); - status = nfs4_proc_create_session(clp); + status = nfs4_proc_create_session(clp, cred); if (status) { - status = nfs4_recovery_handle_error(clp, status); + dprintk("%s: session reset failed with status %d for server %s!\n", + __func__, status, clp->cl_hostname); + status = nfs4_handle_reclaim_lease_error(clp, status); goto out; } - clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); - /* create_session negotiated new slot table */ - clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state); - - /* Let the state manager reestablish state */ - if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) - nfs41_setup_state_renewal(clp); + nfs41_finish_session_reset(clp); + dprintk("%s: session reset was successful for server %s!\n", + __func__, clp->cl_hostname); out: + if (cred) + put_rpccred(cred); return status; } @@ -1715,37 +1818,41 @@ static int nfs4_recall_slot(struct nfs_client *clp) return 0; } -#else /* CONFIG_NFS_V4_1 */ -static int nfs4_reset_session(struct nfs_client *clp) { return 0; } -static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; } -static int nfs4_recall_slot(struct nfs_client *clp) { return 0; } -#endif /* CONFIG_NFS_V4_1 */ - -/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors - * on EXCHANGE_ID for v4.1 - */ -static void nfs4_set_lease_expired(struct nfs_client *clp, int status) +static int nfs4_bind_conn_to_session(struct nfs_client *clp) { - switch (status) { - case -NFS4ERR_CLID_INUSE: - case -NFS4ERR_STALE_CLIENTID: - clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + struct rpc_cred *cred; + int ret; + + nfs4_begin_drain_session(clp); + cred = nfs4_get_exchange_id_cred(clp); + ret = nfs4_proc_bind_conn_to_session(clp, cred); + if (cred) + put_rpccred(cred); + clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); + switch (ret) { + case 0: + dprintk("%s: bind_conn_to_session was successful for server %s!\n", + __func__, clp->cl_hostname); break; case -NFS4ERR_DELAY: - case -ETIMEDOUT: - case -EAGAIN: ssleep(1); + set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); break; - - case -EKEYEXPIRED: - nfs4_warn_keyexpired(clp->cl_hostname); - case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery - * in nfs4_exchange_id */ default: - return; + return nfs4_recovery_handle_error(clp, ret); } - set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + return 0; } +#else /* CONFIG_NFS_V4_1 */ +static int nfs4_reset_session(struct nfs_client *clp) { return 0; } +static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; } +static int nfs4_recall_slot(struct nfs_client *clp) { return 0; } + +static int nfs4_bind_conn_to_session(struct nfs_client *clp) +{ + return 0; +} +#endif /* CONFIG_NFS_V4_1 */ static void nfs4_state_manager(struct nfs_client *clp) { @@ -1753,19 +1860,21 @@ static void nfs4_state_manager(struct nfs_client *clp) /* Ensure exclusive access to NFSv4 state */ do { + if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { + status = nfs4_reclaim_lease(clp); + if (status < 0) + goto out_error; + clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + } + if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) { /* We're going to have to re-establish a clientid */ status = nfs4_reclaim_lease(clp); - if (status) { - nfs4_set_lease_expired(clp, status); - if (test_bit(NFS4CLNT_LEASE_EXPIRED, - &clp->cl_state)) - continue; - if (clp->cl_cons_state == - NFS_CS_SESSION_INITING) - nfs_mark_client_ready(clp, status); + if (status < 0) goto out_error; - } + if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) + continue; clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, @@ -1796,6 +1905,15 @@ static void nfs4_state_manager(struct nfs_client *clp) goto out_error; } + /* Send BIND_CONN_TO_SESSION */ + if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, + &clp->cl_state) && nfs4_has_session(clp)) { + status = nfs4_bind_conn_to_session(clp); + if (status < 0) + goto out_error; + continue; + } + /* First recover reboot state... */ if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) { status = nfs4_do_reclaim(clp, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c74fdb114b4..18fae29b030 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -53,9 +53,11 @@ #include <linux/nfs4.h> #include <linux/nfs_fs.h> #include <linux/nfs_idmap.h> + #include "nfs4_fs.h" #include "internal.h" #include "pnfs.h" +#include "netns.h" #define NFSDBG_FACILITY NFSDBG_XDR @@ -74,7 +76,7 @@ static int nfs4_stat_to_errno(int); /* lock,open owner id: * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT >> 2) */ -#define open_owner_id_maxsz (1 + 1 + 4) +#define open_owner_id_maxsz (1 + 2 + 1 + 1 + 2) #define lock_owner_id_maxsz (1 + 1 + 4) #define decode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) #define compound_encode_hdr_maxsz (3 + (NFS4_MAXTAGLEN >> 2)) @@ -99,9 +101,12 @@ static int nfs4_stat_to_errno(int); #define nfs4_path_maxsz (1 + ((3 + NFS4_MAXPATHLEN) >> 2)) #define nfs4_owner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) #define nfs4_group_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) +/* We support only one layout type per file system */ +#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8) /* This is based on getfattr, which uses the most attributes: */ #define nfs4_fattr_value_maxsz (1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \ - 3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz)) + 3 + 3 + 3 + nfs4_owner_maxsz + \ + nfs4_group_maxsz + decode_mdsthreshold_maxsz)) #define nfs4_fattr_maxsz (nfs4_fattr_bitmap_maxsz + \ nfs4_fattr_value_maxsz) #define decode_getattr_maxsz (op_decode_hdr_maxsz + nfs4_fattr_maxsz) @@ -321,8 +326,20 @@ static int nfs4_stat_to_errno(int); 1 /* csr_flags */ + \ decode_channel_attrs_maxsz + \ decode_channel_attrs_maxsz) +#define encode_bind_conn_to_session_maxsz (op_encode_hdr_maxsz + \ + /* bctsa_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsa_dir */ + \ + 1 /* bctsa_use_conn_in_rdma_mode */) +#define decode_bind_conn_to_session_maxsz (op_decode_hdr_maxsz + \ + /* bctsr_sessid */ \ + XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ + 1 /* bctsr_dir */ + \ + 1 /* bctsr_use_conn_in_rdma_mode */) #define encode_destroy_session_maxsz (op_encode_hdr_maxsz + 4) #define decode_destroy_session_maxsz (op_decode_hdr_maxsz) +#define encode_destroy_clientid_maxsz (op_encode_hdr_maxsz + 2) +#define decode_destroy_clientid_maxsz (op_decode_hdr_maxsz) #define encode_sequence_maxsz (op_encode_hdr_maxsz + \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4) #define decode_sequence_maxsz (op_decode_hdr_maxsz + \ @@ -421,30 +438,22 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_commit_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_commit_maxsz + \ - encode_getattr_maxsz) + encode_commit_maxsz) #define NFS4_dec_commit_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_commit_maxsz + \ - decode_getattr_maxsz) + decode_commit_maxsz) #define NFS4_enc_open_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_open_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_open_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_open_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_open_confirm_sz \ (compound_encode_hdr_maxsz + \ @@ -595,47 +604,37 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_remove_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_remove_maxsz + \ - encode_getattr_maxsz) + encode_remove_maxsz) #define NFS4_dec_remove_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_remove_maxsz + \ - decode_getattr_maxsz) + decode_remove_maxsz) #define NFS4_enc_rename_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ - encode_rename_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ - encode_getattr_maxsz) + encode_rename_maxsz) #define NFS4_dec_rename_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_savefh_maxsz + \ decode_putfh_maxsz + \ - decode_rename_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ - decode_getattr_maxsz) + decode_rename_maxsz) #define NFS4_enc_link_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ encode_savefh_maxsz + \ encode_putfh_maxsz + \ encode_link_maxsz + \ - decode_getattr_maxsz + \ encode_restorefh_maxsz + \ - decode_getattr_maxsz) + encode_getattr_maxsz) #define NFS4_dec_link_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ decode_savefh_maxsz + \ decode_putfh_maxsz + \ decode_link_maxsz + \ - decode_getattr_maxsz + \ decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_symlink_sz (compound_encode_hdr_maxsz + \ @@ -653,20 +652,14 @@ static int nfs4_stat_to_errno(int); #define NFS4_enc_create_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ encode_putfh_maxsz + \ - encode_savefh_maxsz + \ encode_create_maxsz + \ encode_getfh_maxsz + \ - encode_getattr_maxsz + \ - encode_restorefh_maxsz + \ encode_getattr_maxsz) #define NFS4_dec_create_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_putfh_maxsz + \ - decode_savefh_maxsz + \ decode_create_maxsz + \ decode_getfh_maxsz + \ - decode_getattr_maxsz + \ - decode_restorefh_maxsz + \ decode_getattr_maxsz) #define NFS4_enc_pathconf_sz (compound_encode_hdr_maxsz + \ encode_sequence_maxsz + \ @@ -738,6 +731,12 @@ static int nfs4_stat_to_errno(int); decode_putfh_maxsz + \ decode_secinfo_maxsz) #if defined(CONFIG_NFS_V4_1) +#define NFS4_enc_bind_conn_to_session_sz \ + (compound_encode_hdr_maxsz + \ + encode_bind_conn_to_session_maxsz) +#define NFS4_dec_bind_conn_to_session_sz \ + (compound_decode_hdr_maxsz + \ + decode_bind_conn_to_session_maxsz) #define NFS4_enc_exchange_id_sz \ (compound_encode_hdr_maxsz + \ encode_exchange_id_maxsz) @@ -754,6 +753,10 @@ static int nfs4_stat_to_errno(int); encode_destroy_session_maxsz) #define NFS4_dec_destroy_session_sz (compound_decode_hdr_maxsz + \ decode_destroy_session_maxsz) +#define NFS4_enc_destroy_clientid_sz (compound_encode_hdr_maxsz + \ + encode_destroy_clientid_maxsz) +#define NFS4_dec_destroy_clientid_sz (compound_decode_hdr_maxsz + \ + decode_destroy_clientid_maxsz) #define NFS4_enc_sequence_sz \ (compound_decode_hdr_maxsz + \ encode_sequence_maxsz) @@ -1103,7 +1106,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg encode_nfs4_stateid(xdr, arg->stateid); } -static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr) +static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr) { __be32 *p; @@ -1194,6 +1197,17 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c bitmask[1] & nfs4_fattr_bitmap[1], hdr); } +static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask, + const u32 *open_bitmap, + struct compound_hdr *hdr) +{ + encode_getattr_three(xdr, + bitmask[0] & open_bitmap[0], + bitmask[1] & open_bitmap[1], + bitmask[2] & open_bitmap[2], + hdr); +} + static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr) { encode_getattr_three(xdr, @@ -1340,12 +1354,13 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena */ encode_nfs4_seqid(xdr, arg->seqid); encode_share_access(xdr, arg->fmode); - p = reserve_space(xdr, 32); + p = reserve_space(xdr, 36); p = xdr_encode_hyper(p, arg->clientid); - *p++ = cpu_to_be32(20); + *p++ = cpu_to_be32(24); p = xdr_encode_opaque_fixed(p, "open id:", 8); *p++ = cpu_to_be32(arg->server->s_dev); - xdr_encode_hyper(p, arg->id); + *p++ = cpu_to_be32(arg->id.uniquifier); + xdr_encode_hyper(p, arg->id.create_time); } static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg) @@ -1677,6 +1692,20 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru #if defined(CONFIG_NFS_V4_1) /* NFSv4.1 operations */ +static void encode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs4_session *session, + struct compound_hdr *hdr) +{ + __be32 *p; + + encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION, + decode_bind_conn_to_session_maxsz, hdr); + encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); + p = xdr_reserve_space(xdr, 8); + *p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH); + *p = 0; /* use_conn_in_rdma_mode = False */ +} + static void encode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_args *args, struct compound_hdr *hdr) @@ -1725,6 +1754,7 @@ static void encode_create_session(struct xdr_stream *xdr, char machine_name[NFS4_MAX_MACHINE_NAME_LEN]; uint32_t len; struct nfs_client *clp = args->client; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); u32 max_resp_sz_cached; /* @@ -1766,7 +1796,7 @@ static void encode_create_session(struct xdr_stream *xdr, *p++ = cpu_to_be32(RPC_AUTH_UNIX); /* auth_sys */ /* authsys_parms rfc1831 */ - *p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec); /* stamp */ + *p++ = (__be32)nn->boot_time.tv_nsec; /* stamp */ p = xdr_encode_opaque(p, machine_name, len); *p++ = cpu_to_be32(0); /* UID */ *p++ = cpu_to_be32(0); /* GID */ @@ -1781,6 +1811,14 @@ static void encode_destroy_session(struct xdr_stream *xdr, encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN); } +static void encode_destroy_clientid(struct xdr_stream *xdr, + uint64_t clientid, + struct compound_hdr *hdr) +{ + encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr); + encode_uint64(xdr, clientid); +} + static void encode_reclaim_complete(struct xdr_stream *xdr, struct nfs41_reclaim_complete_args *args, struct compound_hdr *hdr) @@ -2063,7 +2101,6 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); encode_remove(xdr, &args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2083,9 +2120,6 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->new_dir, &hdr); encode_rename(xdr, args->old_name, args->new_name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2105,7 +2139,6 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr, encode_savefh(xdr, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); encode_link(xdr, args->name, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_restorefh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); @@ -2124,12 +2157,9 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->dir_fh, &hdr); - encode_savefh(xdr, &hdr); encode_create(xdr, args, &hdr); encode_getfh(xdr, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2190,12 +2220,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); - encode_savefh(xdr, &hdr); encode_open(xdr, args, &hdr); encode_getfh(xdr, &hdr); - encode_getfattr(xdr, args->bitmask, &hdr); - encode_restorefh(xdr, &hdr); - encode_getfattr(xdr, args->dir_bitmask, &hdr); + encode_getfattr_open(xdr, args->bitmask, args->open_bitmap, &hdr); encode_nops(&hdr); } @@ -2447,7 +2474,7 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr, * a COMMIT request */ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, - struct nfs_writeargs *args) + struct nfs_commitargs *args) { struct compound_hdr hdr = { .minorversion = nfs4_xdr_minorversion(&args->seq_args), @@ -2457,8 +2484,6 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr, encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fh, &hdr); encode_commit(xdr, args, &hdr); - if (args->bitmask) - encode_getfattr(xdr, args->bitmask, &hdr); encode_nops(&hdr); } @@ -2601,8 +2626,8 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); encode_putfh(xdr, args->fhandle, &hdr); - encode_delegreturn(xdr, args->stateid, &hdr); encode_getfattr(xdr, args->bitmask, &hdr); + encode_delegreturn(xdr, args->stateid, &hdr); encode_nops(&hdr); } @@ -2650,6 +2675,22 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req, #if defined(CONFIG_NFS_V4_1) /* + * BIND_CONN_TO_SESSION request + */ +static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_bind_conn_to_session(xdr, clp->cl_session, &hdr); + encode_nops(&hdr); +} + +/* * EXCHANGE_ID request */ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req, @@ -2698,6 +2739,22 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req, } /* + * a DESTROY_CLIENTID request + */ +static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req, + struct xdr_stream *xdr, + struct nfs_client *clp) +{ + struct compound_hdr hdr = { + .minorversion = clp->cl_mvops->minor_version, + }; + + encode_compound_hdr(xdr, req, &hdr); + encode_destroy_clientid(xdr, clp->cl_clientid, &hdr); + encode_nops(&hdr); +} + +/* * a SEQUENCE request */ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr, @@ -4101,7 +4158,7 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier) return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE); } -static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res) +static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res) { int status; @@ -4219,6 +4276,114 @@ xdr_error: return status; } +static int decode_threshold_hint(struct xdr_stream *xdr, + uint32_t *bitmap, + uint64_t *res, + uint32_t hint_bit) +{ + __be32 *p; + + *res = 0; + if (likely(bitmap[0] & hint_bit)) { + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + xdr_decode_hyper(p, res); + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_first_threshold_item4(struct xdr_stream *xdr, + struct nfs4_threshold *res) +{ + __be32 *p, *savep; + uint32_t bitmap[3] = {0,}, attrlen; + int status; + + /* layout type */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) { + print_overflow_msg(__func__, xdr); + return -EIO; + } + res->l_type = be32_to_cpup(p); + + /* thi_hintset bitmap */ + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + /* thi_hintlist length */ + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + /* thi_hintlist */ + status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz, + THRESHOLD_RD_IO); + if (status < 0) + goto xdr_error; + status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz, + THRESHOLD_WR_IO); + if (status < 0) + goto xdr_error; + + status = verify_attr_len(xdr, savep, attrlen); + res->bm = bitmap[0]; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz, + res->wr_io_sz); +xdr_error: + dprintk("%s ret=%d!\n", __func__, status); + return status; +} + +/* + * Thresholds on pNFS direct I/O vrs MDS I/O + */ +static int decode_attr_mdsthreshold(struct xdr_stream *xdr, + uint32_t *bitmap, + struct nfs4_threshold *res) +{ + __be32 *p; + int status = 0; + uint32_t num; + + if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U))) + return -EIO; + if (bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD) { + /* Did the server return an unrequested attribute? */ + if (unlikely(res == NULL)) + return -EREMOTEIO; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + if (num == 0) + return 0; + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout " + "drivers per filesystem not supported\n", + __func__); + + status = decode_first_threshold_item4(xdr, res); + bitmap[2] &= ~FATTR4_WORD2_MDSTHRESHOLD; + } + return status; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fattr *fattr, struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, @@ -4257,8 +4422,6 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, status = decode_attr_error(xdr, bitmap, &err); if (status < 0) goto xdr_error; - if (err == -NFS4ERR_WRONGSEC) - nfs_fixup_secinfo_attributes(fattr, fh); status = decode_attr_filehandle(xdr, bitmap, fh); if (status < 0) @@ -4327,6 +4490,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, goto xdr_error; fattr->valid |= status; + status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold); + if (status < 0) + goto xdr_error; + xdr_error: dprintk("%s: xdr returned %d\n", __func__, -status); return status; @@ -4901,11 +5068,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, bitmap[3] = {0}; struct kvec *iov = req->rq_rcv_buf.head; int status; + size_t page_len = xdr->buf->page_len; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; + bm_p = xdr->p; + res->acl_data_offset = be32_to_cpup(bm_p) + 2; + res->acl_data_offset <<= 2; + /* Check if the acl data starts beyond the allocated buffer */ + if (res->acl_data_offset > page_len) + return -ERANGE; + if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; if ((status = decode_attr_length(xdr, &attrlen, &savep)) != 0) @@ -4915,28 +5090,24 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACL)) { size_t hdrlen; - u32 recvd; /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ xdr->p = bm_p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base; attrlen += res->acl_data_offset; - recvd = req->rq_rcv_buf.len - hdrlen; - if (attrlen > recvd) { + if (attrlen > page_len) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ res->acl_len = attrlen; goto out; } - dprintk("NFS: acl reply: attrlen %u > recvd %u\n", - attrlen, recvd); + dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", + attrlen, page_len); return -EINVAL; } xdr_read_pages(xdr, attrlen); @@ -5089,16 +5260,13 @@ out_err: return -EINVAL; } -static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) { struct nfs4_secinfo_flavor *sec_flavor; int status; __be32 *p; int i, num_flavors; - status = decode_op_hdr(xdr, OP_SECINFO); - if (status) - goto out; p = xdr_inline_decode(xdr, 4); if (unlikely(!p)) goto out_overflow; @@ -5124,6 +5292,7 @@ static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) res->flavors->num_flavors++; } + status = 0; out: return status; out_overflow: @@ -5131,7 +5300,23 @@ out_overflow: return -EIO; } +static int decode_secinfo(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + #if defined(CONFIG_NFS_V4_1) +static int decode_secinfo_no_name(struct xdr_stream *xdr, struct nfs4_secinfo_res *res) +{ + int status = decode_op_hdr(xdr, OP_SECINFO_NO_NAME); + if (status) + return status; + return decode_secinfo_common(xdr, res); +} + static int decode_exchange_id(struct xdr_stream *xdr, struct nfs41_exchange_id_res *res) { @@ -5139,7 +5324,6 @@ static int decode_exchange_id(struct xdr_stream *xdr, uint32_t dummy; char *dummy_str; int status; - struct nfs_client *clp = res->client; uint32_t impl_id_count; status = decode_op_hdr(xdr, OP_EXCHANGE_ID); @@ -5149,36 +5333,39 @@ static int decode_exchange_id(struct xdr_stream *xdr, p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; - xdr_decode_hyper(p, &clp->cl_clientid); + xdr_decode_hyper(p, &res->clientid); p = xdr_inline_decode(xdr, 12); if (unlikely(!p)) goto out_overflow; - clp->cl_seqid = be32_to_cpup(p++); - clp->cl_exchange_flags = be32_to_cpup(p++); + res->seqid = be32_to_cpup(p++); + res->flags = be32_to_cpup(p++); /* We ask for SP4_NONE */ dummy = be32_to_cpup(p); if (dummy != SP4_NONE) return -EIO; - /* Throw away minor_id */ + /* server_owner4.so_minor_id */ p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; + p = xdr_decode_hyper(p, &res->server_owner->minor_id); - /* Throw away Major id */ + /* server_owner4.so_major_id */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; + if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) + return -EIO; + memcpy(res->server_owner->major_id, dummy_str, dummy); + res->server_owner->major_id_sz = dummy; - /* Save server_scope */ + /* server_scope4 */ status = decode_opaque_inline(xdr, &dummy, &dummy_str); if (unlikely(status)) return status; - if (unlikely(dummy > NFS4_OPAQUE_LIMIT)) return -EIO; - memcpy(res->server_scope->server_scope, dummy_str, dummy); res->server_scope->server_scope_sz = dummy; @@ -5259,6 +5446,37 @@ static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid) return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN); } +static int decode_bind_conn_to_session(struct xdr_stream *xdr, + struct nfs41_bind_conn_to_session_res *res) +{ + __be32 *p; + int status; + + status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION); + if (!status) + status = decode_sessionid(xdr, &res->session->sess_id); + if (unlikely(status)) + return status; + + /* dir flags, rdma mode bool */ + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + + res->dir = be32_to_cpup(p++); + if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH) + return -EIO; + if (be32_to_cpup(p) == 0) + res->use_conn_in_rdma_mode = false; + else + res->use_conn_in_rdma_mode = true; + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_create_session(struct xdr_stream *xdr, struct nfs41_create_session_res *res) { @@ -5295,6 +5513,11 @@ static int decode_destroy_session(struct xdr_stream *xdr, void *dummy) return decode_op_hdr(xdr, OP_DESTROY_SESSION); } +static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy) +{ + return decode_op_hdr(xdr, OP_DESTROY_CLIENTID); +} + static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy) { return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE); @@ -5783,9 +6006,6 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_remove(xdr, &res->cinfo); - if (status) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); out: return status; } @@ -5815,15 +6035,6 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo); - if (status) - goto out; - /* Current FH is target directory */ - if (decode_getfattr(xdr, res->new_fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->old_fattr, res->server); out: return status; } @@ -5859,8 +6070,6 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, * Note order: OP_LINK leaves the directory as the current * filehandle. */ - if (decode_getfattr(xdr, res->dir_attr, res->server)) - goto out; status = decode_restorefh(xdr); if (status) goto out; @@ -5887,21 +6096,13 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_putfh(xdr); if (status) goto out; - status = decode_savefh(xdr); - if (status) - goto out; status = decode_create(xdr, &res->dir_cinfo); if (status) goto out; status = decode_getfh(xdr, res->fh); if (status) goto out; - if (decode_getfattr(xdr, res->fattr, res->server)) - goto out; - status = decode_restorefh(xdr); - if (status) - goto out; - decode_getfattr(xdr, res->dir_fattr, res->server); + decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6058,19 +6259,12 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_putfh(xdr); if (status) goto out; - status = decode_savefh(xdr); - if (status) - goto out; status = decode_open(xdr, res); if (status) goto out; if (decode_getfh(xdr, &res->fh) != 0) goto out; - if (decode_getfattr(xdr, res->f_attr, res->server) != 0) - goto out; - if (decode_restorefh(xdr) != 0) - goto out; - decode_getfattr(xdr, res->dir_attr, res->server); + decode_getfattr(xdr, res->f_attr, res->server); out: return status; } @@ -6336,7 +6530,7 @@ out: * Decode COMMIT response */ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, - struct nfs_writeres *res) + struct nfs_commitres *res) { struct compound_hdr hdr; int status; @@ -6351,10 +6545,6 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr, if (status) goto out; status = decode_commit(xdr, res); - if (status) - goto out; - if (res->fattr) - decode_getfattr(xdr, res->fattr, res->server); out: return status; } @@ -6510,10 +6700,10 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp, status = decode_putfh(xdr); if (status != 0) goto out; - status = decode_delegreturn(xdr); + status = decode_getfattr(xdr, res->fattr, res->server); if (status != 0) goto out; - decode_getfattr(xdr, res->fattr, res->server); + status = decode_delegreturn(xdr); out: return status; } @@ -6574,6 +6764,22 @@ out: #if defined(CONFIG_NFS_V4_1) /* + * Decode BIND_CONN_TO_SESSION response + */ +static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_bind_conn_to_session(xdr, res); + return status; +} + +/* * Decode EXCHANGE_ID response */ static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp, @@ -6622,6 +6828,22 @@ static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp, } /* + * Decode DESTROY_CLIENTID response + */ +static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *res) +{ + struct compound_hdr hdr; + int status; + + status = decode_compound_hdr(xdr, &hdr); + if (!status) + status = decode_destroy_clientid(xdr, res); + return status; +} + +/* * Decode SEQUENCE response */ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp, @@ -6816,7 +7038,7 @@ static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp, status = decode_putrootfh(xdr); if (status) goto out; - status = decode_secinfo(xdr, res); + status = decode_secinfo_no_name(xdr, res); out: return status; } @@ -7068,6 +7290,9 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(TEST_STATEID, enc_test_stateid, dec_test_stateid), PROC(FREE_STATEID, enc_free_stateid, dec_free_stateid), PROC(GETDEVICELIST, enc_getdevicelist, dec_getdevicelist), + PROC(BIND_CONN_TO_SESSION, + enc_bind_conn_to_session, dec_bind_conn_to_session), + PROC(DESTROY_CLIENTID, enc_destroy_clientid, dec_destroy_clientid), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 4bff4a3dab4..b47277baeba 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -211,7 +211,7 @@ static void copy_single_comp(struct ore_components *oc, unsigned c, memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred)); } -int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags, +static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags, struct objio_segment **pseg) { /* This is the in memory structure of the objio_segment @@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private) int objio_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true, - rdata->lseg, rdata->args.pages, rdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true, + hdr->lseg, rdata->args.pages, rdata->args.pgbase, rdata->args.offset, rdata->args.count, rdata, GFP_KERNEL, &objios); if (unlikely(ret)) @@ -483,12 +484,12 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) { struct objio_state *objios = priv; struct nfs_write_data *wdata = objios->oir.rpcdata; + struct address_space *mapping = wdata->header->inode->i_mapping; pgoff_t index = offset / PAGE_SIZE; - struct page *page = find_get_page(wdata->inode->i_mapping, index); + struct page *page = find_get_page(mapping, index); if (!page) { - page = find_or_create_page(wdata->inode->i_mapping, - index, GFP_NOFS); + page = find_or_create_page(mapping, index, GFP_NOFS); if (unlikely(!page)) { dprintk("%s: grab_cache_page Failed index=0x%lx\n", __func__, index); @@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = { int objio_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; struct objio_state *objios; int ret; - ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false, - wdata->lseg, wdata->args.pages, wdata->args.pgbase, + ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false, + hdr->lseg, wdata->args.pages, wdata->args.pgbase, wdata->args.offset, wdata->args.count, wdata, GFP_NOFS, &objios); if (unlikely(ret)) diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c index 8d45f1c318c..87461354530 100644 --- a/fs/nfs/objlayout/objlayout.c +++ b/fs/nfs/objlayout/objlayout.c @@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) if (status >= 0) rdata->res.count = status; else - rdata->pnfs_error = status; + rdata->header->pnfs_error = status; objlayout_iodone(oir); /* must not use oir after this point */ @@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync) enum pnfs_try_status objlayout_read_pagelist(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; loff_t offset = rdata->args.offset; size_t count = rdata->args.count; int err; loff_t eof; - eof = i_size_read(rdata->inode); + eof = i_size_read(inode); if (unlikely(offset + count > eof)) { if (offset >= eof) { err = 0; @@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata) } rdata->res.eof = (offset + count) >= eof; - _fix_verify_io_params(rdata->lseg, &rdata->args.pages, + _fix_verify_io_params(hdr->lseg, &rdata->args.pages, &rdata->args.pgbase, rdata->args.offset, rdata->args.count); dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n", - __func__, rdata->inode->i_ino, offset, count, rdata->res.eof); + __func__, inode->i_ino, offset, count, rdata->res.eof); err = objio_read_pagelist(rdata); out: if (unlikely(err)) { - rdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } @@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync) wdata->res.count = status; wdata->verf.committed = oir->committed; } else { - wdata->pnfs_error = status; + wdata->header->pnfs_error = status; } objlayout_iodone(oir); /* must not use oir after this point */ @@ -363,15 +365,16 @@ enum pnfs_try_status objlayout_write_pagelist(struct nfs_write_data *wdata, int how) { + struct nfs_pgio_header *hdr = wdata->header; int err; - _fix_verify_io_params(wdata->lseg, &wdata->args.pages, + _fix_verify_io_params(hdr->lseg, &wdata->args.pages, &wdata->args.pgbase, wdata->args.offset, wdata->args.count); err = objio_write_pagelist(wdata, how); if (unlikely(err)) { - wdata->pnfs_error = err; + hdr->pnfs_error = err; dprintk("%s: Returned Error %d\n", __func__, err); return PNFS_NOT_ATTEMPTED; } @@ -604,7 +607,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay, { struct objlayout_deviceinfo *odi; struct pnfs_device pd; - struct super_block *sb; struct page *page, **pages; u32 *p; int err; @@ -623,7 +625,6 @@ int objlayout_get_deviceinfo(struct pnfs_layout_hdr *pnfslay, pd.pglen = PAGE_SIZE; pd.mincount = 0; - sb = pnfslay->plh_inode->i_sb; err = nfs4_proc_getdeviceinfo(NFS_SERVER(pnfslay->plh_inode), &pd); dprintk("%s nfs_getdeviceinfo returned %d\n", __func__, err); if (err) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index d21fceaa9f6..aed913c833f 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -26,6 +26,47 @@ static struct kmem_cache *nfs_page_cachep; +bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) +{ + p->npages = pagecount; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; + else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + if (!p->pagevec) + p->npages = 0; + } + return p->pagevec != NULL; +} + +void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr, + void (*release)(struct nfs_pgio_header *hdr)) +{ + hdr->req = nfs_list_entry(desc->pg_list.next); + hdr->inode = desc->pg_inode; + hdr->cred = hdr->req->wb_context->cred; + hdr->io_start = req_offset(hdr->req); + hdr->good_bytes = desc->pg_count; + hdr->dreq = desc->pg_dreq; + hdr->release = release; + hdr->completion_ops = desc->pg_completion_ops; + if (hdr->completion_ops->init_hdr) + hdr->completion_ops->init_hdr(hdr); +} + +void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) +{ + spin_lock(&hdr->lock); + if (pos < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_ERROR, &hdr->flags); + clear_bit(NFS_IOHDR_EOF, &hdr->flags); + hdr->good_bytes = pos - hdr->io_start; + hdr->error = error; + } + spin_unlock(&hdr->lock); +} + static inline struct nfs_page * nfs_page_alloc(void) { @@ -76,12 +117,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ req->wb_page = page; - atomic_set(&req->wb_complete, 0); req->wb_index = page->index; page_cache_get(page); - BUG_ON(PagePrivate(page)); - BUG_ON(!PageLocked(page)); - BUG_ON(page->mapping->host != inode); req->wb_offset = offset; req->wb_pgbase = offset; req->wb_bytes = count; @@ -104,6 +141,15 @@ void nfs_unlock_request(struct nfs_page *req) clear_bit(PG_BUSY, &req->wb_flags); smp_mb__after_clear_bit(); wake_up_bit(&req->wb_flags, PG_BUSY); +} + +/** + * nfs_unlock_and_release_request - Unlock request and release the nfs_page + * @req: + */ +void nfs_unlock_and_release_request(struct nfs_page *req) +{ + nfs_unlock_request(req); nfs_release_request(req); } @@ -203,6 +249,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test); void nfs_pageio_init(struct nfs_pageio_descriptor *desc, struct inode *inode, const struct nfs_pageio_ops *pg_ops, + const struct nfs_pgio_completion_ops *compl_ops, size_t bsize, int io_flags) { @@ -215,9 +262,11 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_recoalesce = 0; desc->pg_inode = inode; desc->pg_ops = pg_ops; + desc->pg_completion_ops = compl_ops; desc->pg_ioflags = io_flags; desc->pg_error = 0; desc->pg_lseg = NULL; + desc->pg_dreq = NULL; } /** @@ -241,12 +290,12 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev, return false; if (req->wb_context->state != prev->wb_context->state) return false; - if (req->wb_index != (prev->wb_index + 1)) - return false; if (req->wb_pgbase != 0) return false; if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE) return false; + if (req_offset(req) != req_offset(prev) + prev->wb_bytes) + return false; return pgio->pg_ops->pg_test(pgio, prev, req); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b5d45158694..bbc49caa7a8 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -70,6 +70,10 @@ find_pnfs_driver(u32 id) spin_lock(&pnfs_spinlock); local = find_pnfs_driver_locked(id); + if (local != NULL && !try_module_get(local->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + local = NULL; + } spin_unlock(&pnfs_spinlock); return local; } @@ -80,6 +84,9 @@ unset_pnfs_layoutdriver(struct nfs_server *nfss) if (nfss->pnfs_curr_ld) { if (nfss->pnfs_curr_ld->clear_layoutdriver) nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + /* Decrement the MDS count. Purge the deviceid cache if zero */ + if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count)) + nfs4_deviceid_purge_client(nfss->nfs_client); module_put(nfss->pnfs_curr_ld->owner); } nfss->pnfs_curr_ld = NULL; @@ -115,10 +122,6 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, goto out_no_driver; } } - if (!try_module_get(ld_type->owner)) { - dprintk("%s: Could not grab reference on module\n", __func__); - goto out_no_driver; - } server->pnfs_curr_ld = ld_type; if (ld_type->set_layoutdriver && ld_type->set_layoutdriver(server, mntfh)) { @@ -127,6 +130,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, module_put(ld_type->owner); goto out_no_driver; } + /* Bump the MDS count */ + atomic_inc(&server->nfs_client->cl_mds_count); dprintk("%s: pNFS module for %u set\n", __func__, id); return; @@ -395,6 +400,9 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo, dprintk("%s:Begin lo %p\n", __func__, lo); if (list_empty(&lo->plh_segs)) { + /* Reset MDS Threshold I/O counters */ + NFS_I(lo->plh_inode)->write_io = 0; + NFS_I(lo->plh_inode)->read_io = 0; if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags)) put_layout_hdr_locked(lo); return 0; @@ -455,6 +463,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) spin_unlock(&nfsi->vfs_inode.i_lock); pnfs_free_lseg_list(&tmp_list); } +EXPORT_SYMBOL_GPL(pnfs_destroy_layout); /* * Called by the state manger to remove all layouts established under an @@ -587,7 +596,7 @@ send_layoutget(struct pnfs_layout_hdr *lo, /* allocate pages for xdr post processing */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = max_resp_sz >> PAGE_SHIFT; + max_pages = nfs_page_array_len(0, max_resp_sz); pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); if (!pages) @@ -692,6 +701,7 @@ out: dprintk("<-- %s status: %d\n", __func__, status); return status; } +EXPORT_SYMBOL_GPL(_pnfs_return_layout); bool pnfs_roc(struct inode *ino) { @@ -931,6 +941,81 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo, } /* + * Use mdsthreshold hints set at each OPEN to determine if I/O should go + * to the MDS or over pNFS + * + * The nfs_inode read_io and write_io fields are cumulative counters reset + * when there are no layout segments. Note that in pnfs_update_layout iomode + * is set to IOMODE_READ for a READ request, and set to IOMODE_RW for a + * WRITE request. + * + * A return of true means use MDS I/O. + * + * From rfc 5661: + * If a file's size is smaller than the file size threshold, data accesses + * SHOULD be sent to the metadata server. If an I/O request has a length that + * is below the I/O size threshold, the I/O SHOULD be sent to the metadata + * server. If both file size and I/O size are provided, the client SHOULD + * reach or exceed both thresholds before sending its read or write + * requests to the data server. + */ +static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, + struct inode *ino, int iomode) +{ + struct nfs4_threshold *t = ctx->mdsthreshold; + struct nfs_inode *nfsi = NFS_I(ino); + loff_t fsize = i_size_read(ino); + bool size = false, size_set = false, io = false, io_set = false, ret = false; + + if (t == NULL) + return ret; + + dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n", + __func__, t->bm, t->rd_sz, t->wr_sz, t->rd_io_sz, t->wr_io_sz); + + switch (iomode) { + case IOMODE_READ: + if (t->bm & THRESHOLD_RD) { + dprintk("%s fsize %llu\n", __func__, fsize); + size_set = true; + if (fsize < t->rd_sz) + size = true; + } + if (t->bm & THRESHOLD_RD_IO) { + dprintk("%s nfsi->read_io %llu\n", __func__, + nfsi->read_io); + io_set = true; + if (nfsi->read_io < t->rd_io_sz) + io = true; + } + break; + case IOMODE_RW: + if (t->bm & THRESHOLD_WR) { + dprintk("%s fsize %llu\n", __func__, fsize); + size_set = true; + if (fsize < t->wr_sz) + size = true; + } + if (t->bm & THRESHOLD_WR_IO) { + dprintk("%s nfsi->write_io %llu\n", __func__, + nfsi->write_io); + io_set = true; + if (nfsi->write_io < t->wr_io_sz) + io = true; + } + break; + } + if (size_set && io_set) { + if (size && io) + ret = true; + } else if (size || io) + ret = true; + + dprintk("<-- %s size %d io %d ret %d\n", __func__, size, io, ret); + return ret; +} + +/* * Layout segment is retreived from the server if not cached. * The appropriate layout segment is referenced and returned to the caller. */ @@ -957,6 +1042,10 @@ pnfs_update_layout(struct inode *ino, if (!pnfs_enabled_sb(NFS_SERVER(ino))) return NULL; + + if (pnfs_within_mdsthreshold(ctx, ino, iomode)) + return NULL; + spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); if (lo == NULL) { @@ -1082,6 +1171,10 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r { BUG_ON(pgio->pg_lseg != NULL); + if (req->wb_offset != req->wb_pgbase) { + nfs_pageio_reset_read_mds(pgio); + return; + } pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, req_offset(req), @@ -1100,6 +1193,10 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page * { BUG_ON(pgio->pg_lseg != NULL); + if (req->wb_offset != req->wb_pgbase) { + nfs_pageio_reset_write_mds(pgio); + return; + } pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, req_offset(req), @@ -1113,26 +1210,31 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page * EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); bool -pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode) +pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_server *server = NFS_SERVER(inode); struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) return false; - nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0); + nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, + server->rsize, 0); return true; } bool -pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags) +pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, + int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_server *server = NFS_SERVER(inode); struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) return false; - nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags); + nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, + server->wsize, ioflags); return true; } @@ -1162,13 +1264,15 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, } EXPORT_SYMBOL_GPL(pnfs_generic_pg_test); -static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head) +int pnfs_write_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE); + nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1188,30 +1292,37 @@ static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head * } return 0; } +EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds); + +static void pnfs_ld_handle_write_error(struct nfs_write_data *data) +{ + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs write error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & + PNFS_LAYOUTRET_ON_ERROR) { + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); + } + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode, + &hdr->pages, + hdr->completion_ops); +} /* * Called by non rpc-based layout drivers */ void pnfs_ld_write_done(struct nfs_write_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (!hdr->pnfs_error) { pnfs_set_layoutcommit(data); - data->mds_ops->rpc_call_done(&data->task, data); - } else { - dprintk("pnfs write error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & - PNFS_LAYOUTRET_ON_ERROR) { - /* Don't lo_commit on error, Server will needs to - * preform a file recovery. - */ - clear_bit(NFS_INO_LAYOUTCOMMIT, - &NFS_I(data->inode)->flags); - pnfs_return_layout(data->inode); - } - data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages); - } - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + hdr->mds_ops->rpc_call_done(&data->task, data); + } else + pnfs_ld_handle_write_error(data); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_write_done); @@ -1219,12 +1330,13 @@ static void pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_write_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); - nfs_pageio_reset_write_mds(desc); - desc->pg_recoalesce = 1; - put_lseg(data->lseg); + struct nfs_pgio_header *hdr = data->header; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_write_mds(desc); + desc->pg_recoalesce = 1; + } nfs_writedata_release(data); } @@ -1234,23 +1346,18 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata, struct pnfs_layout_segment *lseg, int how) { - struct inode *inode = wdata->inode; + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; enum pnfs_try_status trypnfs; struct nfs_server *nfss = NFS_SERVER(inode); - wdata->mds_ops = call_ops; - wdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__, inode->i_ino, wdata->args.count, wdata->args.offset, how); - trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(wdata->lseg); - wdata->lseg = NULL; - } else + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_WRITE); - dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1266,7 +1373,7 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_write_data, list); + data = list_first_entry(head, struct nfs_write_data, list); list_del_init(&data->list); trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how); @@ -1276,43 +1383,82 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he put_lseg(lseg); } +static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_writehdr_free(hdr); +} + int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); - if (ret != 0) { + whdr = nfs_writehdr_alloc(); + if (!whdr) { + desc->pg_completion_ops->error_cleanup(&desc->pg_list); put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; - return ret; + return -ENOMEM; } - pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags); - return 0; + hdr = &whdr->header; + nfs_pgheader_init(desc, hdr, pnfs_writehdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_flush(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + } else + pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags); + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages); -static void pnfs_ld_handle_read_error(struct nfs_read_data *data) +int pnfs_read_done_resend_to_mds(struct inode *inode, + struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops) { struct nfs_pageio_descriptor pgio; + LIST_HEAD(failed); - put_lseg(data->lseg); - data->lseg = NULL; - dprintk("pnfs write error = %d\n", data->pnfs_error); - if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags & - PNFS_LAYOUTRET_ON_ERROR) - pnfs_return_layout(data->inode); - - nfs_pageio_init_read_mds(&pgio, data->inode); - - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); + /* Resend all requests through the MDS */ + nfs_pageio_init_read_mds(&pgio, inode, compl_ops); + while (!list_empty(head)) { + struct nfs_page *req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_pageio_add_request(&pgio, req); + if (!nfs_pageio_add_request(&pgio, req)) + nfs_list_add_request(req, &failed); } nfs_pageio_complete(&pgio); + + if (!list_empty(&failed)) { + list_move(&failed, head); + return -EIO; + } + return 0; +} +EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds); + +static void pnfs_ld_handle_read_error(struct nfs_read_data *data) +{ + struct nfs_pgio_header *hdr = data->header; + + dprintk("pnfs read error = %d\n", hdr->pnfs_error); + if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags & + PNFS_LAYOUTRET_ON_ERROR) { + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags); + pnfs_return_layout(hdr->inode); + } + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) + data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode, + &hdr->pages, + hdr->completion_ops); } /* @@ -1320,13 +1466,14 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data) */ void pnfs_ld_read_done(struct nfs_read_data *data) { - if (likely(!data->pnfs_error)) { + struct nfs_pgio_header *hdr = data->header; + + if (likely(!hdr->pnfs_error)) { __nfs4_read_done_cb(data); - data->mds_ops->rpc_call_done(&data->task, data); + hdr->mds_ops->rpc_call_done(&data->task, data); } else pnfs_ld_handle_read_error(data); - put_lseg(data->lseg); - data->mds_ops->rpc_release(data); + hdr->mds_ops->rpc_release(data); } EXPORT_SYMBOL_GPL(pnfs_ld_read_done); @@ -1334,11 +1481,13 @@ static void pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, struct nfs_read_data *data) { - list_splice_tail_init(&data->pages, &desc->pg_list); - if (data->req && list_empty(&data->req->wb_list)) - nfs_list_add_request(data->req, &desc->pg_list); - nfs_pageio_reset_read_mds(desc); - desc->pg_recoalesce = 1; + struct nfs_pgio_header *hdr = data->header; + + if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) { + list_splice_tail_init(&hdr->pages, &desc->pg_list); + nfs_pageio_reset_read_mds(desc); + desc->pg_recoalesce = 1; + } nfs_readdata_release(data); } @@ -1350,23 +1499,19 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata, const struct rpc_call_ops *call_ops, struct pnfs_layout_segment *lseg) { - struct inode *inode = rdata->inode; + struct nfs_pgio_header *hdr = rdata->header; + struct inode *inode = hdr->inode; struct nfs_server *nfss = NFS_SERVER(inode); enum pnfs_try_status trypnfs; - rdata->mds_ops = call_ops; - rdata->lseg = get_lseg(lseg); + hdr->mds_ops = call_ops; dprintk("%s: Reading ino:%lu %u@%llu\n", __func__, inode->i_ino, rdata->args.count, rdata->args.offset); trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata); - if (trypnfs == PNFS_NOT_ATTEMPTED) { - put_lseg(rdata->lseg); - rdata->lseg = NULL; - } else { + if (trypnfs != PNFS_NOT_ATTEMPTED) nfs_inc_stats(inode, NFSIOS_PNFS_READ); - } dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs); return trypnfs; } @@ -1382,7 +1527,7 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea while (!list_empty(head)) { enum pnfs_try_status trypnfs; - data = list_entry(head->next, struct nfs_read_data, list); + data = list_first_entry(head, struct nfs_read_data, list); list_del_init(&data->list); trypnfs = pnfs_try_to_read_data(data, call_ops, lseg); @@ -1392,20 +1537,40 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea put_lseg(lseg); } +static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) +{ + put_lseg(hdr->lseg); + nfs_readhdr_free(hdr); +} + int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); - if (ret != 0) { + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + desc->pg_completion_ops->error_cleanup(&desc->pg_list); + ret = -ENOMEM; put_lseg(desc->pg_lseg); desc->pg_lseg = NULL; return ret; } - pnfs_do_multiple_reads(desc, &head); - return 0; + hdr = &rhdr->header; + nfs_pgheader_init(desc, hdr, pnfs_readhdr_free); + hdr->lseg = get_lseg(desc->pg_lseg); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pagein(desc, hdr); + if (ret != 0) { + put_lseg(desc->pg_lseg); + desc->pg_lseg = NULL; + } else + pnfs_do_multiple_reads(desc, &hdr->rpc_list); + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); + return ret; } EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages); @@ -1438,30 +1603,32 @@ EXPORT_SYMBOL_GPL(pnfs_set_lo_fail); void pnfs_set_layoutcommit(struct nfs_write_data *wdata) { - struct nfs_inode *nfsi = NFS_I(wdata->inode); + struct nfs_pgio_header *hdr = wdata->header; + struct inode *inode = hdr->inode; + struct nfs_inode *nfsi = NFS_I(inode); loff_t end_pos = wdata->mds_offset + wdata->res.count; bool mark_as_dirty = false; - spin_lock(&nfsi->vfs_inode.i_lock); + spin_lock(&inode->i_lock); if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) { mark_as_dirty = true; dprintk("%s: Set layoutcommit for inode %lu ", - __func__, wdata->inode->i_ino); + __func__, inode->i_ino); } - if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) { + if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) { /* references matched in nfs4_layoutcommit_release */ - get_lseg(wdata->lseg); + get_lseg(hdr->lseg); } if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; - spin_unlock(&nfsi->vfs_inode.i_lock); + spin_unlock(&inode->i_lock); dprintk("%s: lseg %p end_pos %llu\n", - __func__, wdata->lseg, nfsi->layout->plh_lwb); + __func__, hdr->lseg, nfsi->layout->plh_lwb); /* if pnfs_layoutcommit_inode() runs between inode locks, the next one * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */ if (mark_as_dirty) - mark_inode_dirty_sync(wdata->inode); + mark_inode_dirty_sync(inode); } EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit); @@ -1550,3 +1717,15 @@ out_free: kfree(data); goto out; } + +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + struct nfs4_threshold *thp; + + thp = kzalloc(sizeof(*thp), GFP_NOFS); + if (!thp) { + dprintk("%s mdsthreshold allocation failed\n", __func__); + return NULL; + } + return thp; +} diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 442ebf68eee..64f90d845f6 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -63,6 +63,7 @@ enum { NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ NFS_LAYOUT_ROC, /* some lseg had roc bit set */ NFS_LAYOUT_DESTROYED, /* no new use of layout allowed */ + NFS_LAYOUT_INVALID, /* layout is being destroyed */ }; enum layoutdriver_policy_flags { @@ -94,11 +95,20 @@ struct pnfs_layoutdriver_type { const struct nfs_pageio_ops *pg_read_ops; const struct nfs_pageio_ops *pg_write_ops; + struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode); void (*mark_request_commit) (struct nfs_page *req, - struct pnfs_layout_segment *lseg); - void (*clear_request_commit) (struct nfs_page *req); - int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock); - int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how); + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo); + void (*clear_request_commit) (struct nfs_page *req, + struct nfs_commit_info *cinfo); + int (*scan_commit_lists) (struct nfs_commit_info *cinfo, + int max); + void (*recover_commit_reqs) (struct list_head *list, + struct nfs_commit_info *cinfo); + int (*commit_pagelist)(struct inode *inode, + struct list_head *mds_pages, + int how, + struct nfs_commit_info *cinfo); /* * Return PNFS_ATTEMPTED to indicate the layout code has attempted @@ -168,8 +178,10 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); void get_layout_hdr(struct pnfs_layout_hdr *lo); void put_lseg(struct pnfs_layout_segment *lseg); -bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *); -bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int); +bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, + const struct nfs_pgio_completion_ops *); +bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, + int, const struct nfs_pgio_completion_ops *); void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); void unset_pnfs_layoutdriver(struct nfs_server *); @@ -211,6 +223,11 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino, gfp_t gfp_flags); void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp); +int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops); +int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head, + const struct nfs_pgio_completion_ops *compl_ops); +struct nfs4_threshold *pnfs_mdsthreshold_alloc(void); /* nfs4_deviceid_flags */ enum { @@ -261,49 +278,66 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss) } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { - if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags)) + if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0) return PNFS_NOT_ATTEMPTED; - return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how); + return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo); +} + +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; + + if (ld == NULL || ld->get_ds_info == NULL) + return NULL; + return ld->get_ds_info(inode); } static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (lseg == NULL || ld->mark_request_commit == NULL) return false; - ld->mark_request_commit(req, lseg); + ld->mark_request_commit(req, lseg, cinfo); return true; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { struct inode *inode = req->wb_context->dentry->d_inode; struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; if (ld == NULL || ld->clear_request_commit == NULL) return false; - ld->clear_request_commit(req); + ld->clear_request_commit(req, cinfo); return true; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { - struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld; - int ret; - - if (ld == NULL || ld->scan_commit_lists == NULL) + if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) return 0; - ret = ld->scan_commit_lists(inode, max, lock); - if (ret != 0) - set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags); - return ret; + else + return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max); +} + +static inline void +pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list, + struct nfs_commit_info *cinfo) +{ + if (cinfo->ds == NULL || cinfo->ds->nwritten == 0) + return; + NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo); } /* Should the pNFS client commit and return the layout upon a setattr */ @@ -327,6 +361,14 @@ static inline int pnfs_return_layout(struct inode *ino) return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return (dst && src && src->bm != 0 && nfss->pnfs_curr_ld && + nfss->pnfs_curr_ld->id == src->l_type); +} + #ifdef NFS_DEBUG void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id); #else @@ -396,45 +438,74 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s) { } -static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode) +static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { return false; } -static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags) +static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { return false; } static inline int -pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how) +pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how, + struct nfs_commit_info *cinfo) { return PNFS_NOT_ATTEMPTED; } +static inline struct pnfs_ds_commit_info * +pnfs_get_ds_info(struct inode *inode) +{ + return NULL; +} + static inline bool -pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { return false; } static inline bool -pnfs_clear_request_commit(struct nfs_page *req) +pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo) { return false; } static inline int -pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock) +pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo, + int max) { return 0; } +static inline void +pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list, + struct nfs_commit_info *cinfo) +{ +} + static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync) { return 0; } +static inline bool +pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src, + struct nfs_server *nfss) +{ + return false; +} + +static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void) +{ + return NULL; +} + #endif /* CONFIG_NFS_V4_1 */ #endif /* FS_NFS_PNFS_H */ diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index b63b6f4d14f..617c7419a08 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -178,7 +178,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name, +nfs_proc_lookup(struct inode *dir, struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { @@ -335,8 +335,7 @@ nfs_proc_remove(struct inode *dir, struct qstr *name) { struct nfs_removeargs arg = { .fh = NFS_FH(dir), - .name.len = name->len, - .name.name = name->name, + .name = *name, }; struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_REMOVE], @@ -641,16 +640,18 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; - nfs_invalidate_atime(data->inode); + nfs_invalidate_atime(inode); if (task->tk_status >= 0) { - nfs_refresh_inode(data->inode, data->res.fattr); + nfs_refresh_inode(inode, data->res.fattr); /* Emulate the eof flag, which isn't normally needed in NFSv2 * as it is guaranteed to always return the file attributes */ - if (data->args.offset + data->args.count >= data->res.fattr->size) + if (data->args.offset + data->res.count >= data->res.fattr->size) data->res.eof = 1; } return 0; @@ -668,11 +669,13 @@ static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data) { + struct inode *inode = data->header->inode; + if (nfs_async_handle_expired_key(task)) return -EAGAIN; if (task->tk_status >= 0) - nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr); + nfs_post_op_update_inode_force_wcc(inode, data->res.fattr); return 0; } @@ -688,8 +691,13 @@ static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_d rpc_call_start(task); } +static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data) +{ + BUG(); +} + static void -nfs_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg) +nfs_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg) { BUG(); } @@ -733,6 +741,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .file_inode_ops = &nfs_file_inode_operations, .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, + .submount = nfs_submount, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, .lookup = nfs_proc_lookup, @@ -764,6 +773,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .write_rpc_prepare = nfs_proc_write_rpc_prepare, .write_done = nfs_write_done, .commit_setup = nfs_proc_commit_setup, + .commit_rpc_prepare = nfs_proc_commit_rpc_prepare, .lock = nfs_proc_lock, .lock_check_bounds = nfs_lock_check_bounds, .close_context = nfs_close_context, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 9a0e8ef4a40..86ced783621 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -30,43 +30,73 @@ #define NFSDBG_FACILITY NFSDBG_PAGECACHE static const struct nfs_pageio_ops nfs_pageio_read_ops; -static const struct rpc_call_ops nfs_read_partial_ops; -static const struct rpc_call_ops nfs_read_full_ops; +static const struct rpc_call_ops nfs_read_common_ops; +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops; static struct kmem_cache *nfs_rdata_cachep; -struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) +struct nfs_read_header *nfs_readhdr_alloc(void) { - struct nfs_read_data *p; - - p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); - if (p) { - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; - else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); - if (!p->pagevec) { - kmem_cache_free(nfs_rdata_cachep, p); - p = NULL; - } - } + struct nfs_read_header *rhdr; + + rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL); + if (rhdr) { + struct nfs_pgio_header *hdr = &rhdr->header; + + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); + } + return rhdr; +} + +static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + struct nfs_read_data *data, *prealloc; + + prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data; + if (prealloc->header == NULL) + data = prealloc; + else + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + if (nfs_pgarray_set(&data->pages, pagecount)) { + data->header = hdr; + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; } - return p; +out: + return data; } -void nfs_readdata_free(struct nfs_read_data *p) +void nfs_readhdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - kmem_cache_free(nfs_rdata_cachep, p); + struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header); + + kmem_cache_free(nfs_rdata_cachep, rhdr); } void nfs_readdata_release(struct nfs_read_data *rdata) { + struct nfs_pgio_header *hdr = rdata->header; + struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header); + put_nfs_open_context(rdata->args.context); - nfs_readdata_free(rdata); + if (rdata->pages.pagevec != rdata->pages.page_array) + kfree(rdata->pages.pagevec); + if (rdata != &read_header->rpc_data) + kfree(rdata); + else + rdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); } static @@ -78,39 +108,11 @@ int nfs_return_empty_page(struct page *page) return 0; } -static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) -{ - unsigned int remainder = data->args.count - data->res.count; - unsigned int base = data->args.pgbase + data->res.count; - unsigned int pglen; - struct page **pages; - - if (data->res.eof == 0 || remainder == 0) - return; - /* - * Note: "remainder" can never be negative, since we check for - * this in the XDR code. - */ - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - pglen = PAGE_CACHE_SIZE - base; - for (;;) { - if (remainder <= pglen) { - zero_user(*pages, base, remainder); - break; - } - zero_user(*pages, base, pglen); - pages++; - remainder -= pglen; - pglen = PAGE_CACHE_SIZE; - base = 0; - } -} - void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode) + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops, NFS_SERVER(inode)->rsize, 0); } @@ -121,11 +123,12 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); -static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode) +void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, + struct inode *inode, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_read(pgio, inode)) - nfs_pageio_init_read_mds(pgio, inode); + if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) + nfs_pageio_init_read_mds(pgio, inode, compl_ops); } int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, @@ -146,9 +149,10 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); - nfs_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; return 0; } @@ -169,16 +173,49 @@ static void nfs_readpage_release(struct nfs_page *req) nfs_release_request(req); } -int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt, - const struct rpc_call_ops *call_ops) +/* Note io was page aligned */ +static void nfs_read_completion(struct nfs_pgio_header *hdr) { - struct inode *inode = data->inode; + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + struct page *page = req->wb_page; + + if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) { + if (bytes > hdr->good_bytes) + zero_user(page, 0, PAGE_SIZE); + else if (hdr->good_bytes - bytes < PAGE_SIZE) + zero_user_segment(page, + hdr->good_bytes & ~PAGE_MASK, + PAGE_SIZE); + } + bytes += req->wb_bytes; + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) { + if (bytes <= hdr->good_bytes) + SetPageUptodate(page); + } else + SetPageUptodate(page); + nfs_list_remove_request(req); + nfs_readpage_release(req); + } +out: + hdr->release(hdr); +} + +int nfs_initiate_read(struct rpc_clnt *clnt, + struct nfs_read_data *data, + const struct rpc_call_ops *call_ops, int flags) +{ + struct inode *inode = data->header->inode; int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0; struct rpc_task *task; struct rpc_message msg = { .rpc_argp = &data->args, .rpc_resp = &data->res, - .rpc_cred = data->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .task = &data->task, @@ -187,7 +224,7 @@ int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt, .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC | swap_flags, + .flags = RPC_TASK_ASYNC | swap_flags | flags, }; /* Set up the initial task struct. */ @@ -212,19 +249,15 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read); /* * Set up the NFS read request struct */ -static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, +static void nfs_read_rpcsetup(struct nfs_read_data *data, unsigned int count, unsigned int offset) { - struct inode *inode = req->wb_context->dentry->d_inode; - - data->req = req; - data->inode = inode; - data->cred = req->wb_context->cred; + struct nfs_page *req = data->header->req; - data->args.fh = NFS_FH(inode); + data->args.fh = NFS_FH(data->header->inode); data->args.offset = req_offset(req) + offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + data->args.pages = data->pages.pagevec; data->args.count = count; data->args.context = get_nfs_open_context(req->wb_context); data->args.lock_context = req->wb_lock_context; @@ -238,9 +271,9 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data, static int nfs_do_read(struct nfs_read_data *data, const struct rpc_call_ops *call_ops) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; - return nfs_initiate_read(data, NFS_CLIENT(inode), call_ops); + return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0); } static int @@ -253,7 +286,7 @@ nfs_do_multiple_reads(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_read_data, list); + data = list_first_entry(head, struct nfs_read_data, list); list_del_init(&data->list); ret2 = nfs_do_read(data, call_ops); @@ -275,6 +308,24 @@ nfs_async_read_error(struct list_head *head) } } +static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = { + .error_cleanup = nfs_async_read_error, + .completion = nfs_read_completion, +}; + +static void nfs_pagein_error(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + set_bit(NFS_IOHDR_REDO, &hdr->flags); + while (!list_empty(&hdr->rpc_list)) { + struct nfs_read_data *data = list_first_entry(&hdr->rpc_list, + struct nfs_read_data, list); + list_del(&data->list); + nfs_readdata_release(data); + } + desc->pg_completion_ops->error_cleanup(&desc->pg_list); +} + /* * Generate multiple requests to fill a single page. * @@ -288,93 +339,95 @@ nfs_async_read_error(struct list_head *head) * won't see the new data until our attribute cache is updated. This is more * or less conventional NFS client behavior. */ -static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; struct nfs_read_data *data; size_t rsize = desc->pg_bsize, nbytes; unsigned int offset; - int requests = 0; - int ret = 0; - - nfs_list_remove_request(req); offset = 0; nbytes = desc->pg_count; do { size_t len = min(nbytes,rsize); - data = nfs_readdata_alloc(1); - if (!data) - goto out_bad; - data->pagevec[0] = page; - nfs_read_rpcsetup(req, data, len, offset); - list_add(&data->list, res); - requests++; + data = nfs_readdata_alloc(hdr, 1); + if (!data) { + nfs_pagein_error(desc, hdr); + return -ENOMEM; + } + data->pages.pagevec[0] = page; + nfs_read_rpcsetup(data, len, offset); + list_add(&data->list, &hdr->rpc_list); nbytes -= len; offset += len; - } while(nbytes != 0); - atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_read_partial_ops; - return ret; -out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_read_data, list); - list_del(&data->list); - nfs_readdata_free(data); - } - nfs_readpage_release(req); - return -ENOMEM; + } while (nbytes != 0); + + nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); + desc->pg_rpc_callops = &nfs_read_common_ops; + return 0; } -static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { struct nfs_page *req; struct page **pages; - struct nfs_read_data *data; + struct nfs_read_data *data; struct list_head *head = &desc->pg_list; - int ret = 0; - data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); + data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); if (!data) { - nfs_async_read_error(head); - ret = -ENOMEM; - goto out; + nfs_pagein_error(desc, hdr); + return -ENOMEM; } - pages = data->pagevec; + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); - nfs_read_rpcsetup(req, data, desc->pg_count, 0); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_read_full_ops; -out: - return ret; + nfs_read_rpcsetup(data, desc->pg_count, 0); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_read_common_ops; + return 0; } -int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head) +int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_pagein_multi(desc, head); - return nfs_pagein_one(desc, head); + return nfs_pagein_multi(desc, hdr); + return nfs_pagein_one(desc, hdr); } static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_read_header *rhdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_pagein(desc, &head); + rhdr = nfs_readhdr_alloc(); + if (!rhdr) { + desc->pg_completion_ops->error_cleanup(&desc->pg_list); + return -ENOMEM; + } + hdr = &rhdr->header; + nfs_pgheader_init(desc, hdr, nfs_readhdr_free); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_pagein(desc, hdr); if (ret == 0) - ret = nfs_do_multiple_reads(&head, desc->pg_rpc_callops); + ret = nfs_do_multiple_reads(&hdr->rpc_list, + desc->pg_rpc_callops); + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); return ret; } @@ -389,20 +442,21 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops = { */ int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data) { + struct inode *inode = data->header->inode; int status; dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid, task->tk_status); - status = NFS_PROTO(data->inode)->read_done(task, data); + status = NFS_PROTO(inode)->read_done(task, data); if (status != 0) return status; - nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count); + nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count); if (task->tk_status == -ESTALE) { - set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags); - nfs_mark_for_revalidate(data->inode); + set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); + nfs_mark_for_revalidate(inode); } return 0; } @@ -412,15 +466,13 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data struct nfs_readargs *argp = &data->args; struct nfs_readres *resp = &data->res; - if (resp->eof || resp->count == argp->count) - return; - /* This is a short read! */ - nfs_inc_stats(data->inode, NFSIOS_SHORTREAD); + nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD); /* Has the server at least made some progress? */ - if (resp->count == 0) + if (resp->count == 0) { + nfs_set_pgio_error(data->header, -EIO, argp->offset); return; - + } /* Yes, so retry the read at the end of the data */ data->mds_offset += resp->count; argp->offset += resp->count; @@ -429,114 +481,46 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data rpc_restart_call_prepare(task); } -/* - * Handle a read reply that fills part of a page. - */ -static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) +static void nfs_readpage_result_common(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - + struct nfs_pgio_header *hdr = data->header; + + /* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */ if (nfs_readpage_result(task, data) != 0) return; if (task->tk_status < 0) - return; - - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_retry(task, data); + nfs_set_pgio_error(hdr, task->tk_status, data->args.offset); + else if (data->res.eof) { + loff_t bound; + + bound = data->args.offset + data->res.count; + spin_lock(&hdr->lock); + if (bound < hdr->io_start + hdr->good_bytes) { + set_bit(NFS_IOHDR_EOF, &hdr->flags); + clear_bit(NFS_IOHDR_ERROR, &hdr->flags); + hdr->good_bytes = bound - hdr->io_start; + } + spin_unlock(&hdr->lock); + } else if (data->res.count != data->args.count) + nfs_readpage_retry(task, data); } -static void nfs_readpage_release_partial(void *calldata) +static void nfs_readpage_release_common(void *calldata) { - struct nfs_read_data *data = calldata; - struct nfs_page *req = data->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) - set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags); - - if (atomic_dec_and_test(&req->wb_complete)) { - if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags)) - SetPageUptodate(page); - nfs_readpage_release(req); - } nfs_readdata_release(calldata); } void nfs_read_prepare(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - NFS_PROTO(data->inode)->read_rpc_prepare(task, data); -} - -static const struct rpc_call_ops nfs_read_partial_ops = { - .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_partial, - .rpc_release = nfs_readpage_release_partial, -}; - -static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) -{ - unsigned int count = data->res.count; - unsigned int base = data->args.pgbase; - struct page **pages; - - if (data->res.eof) - count = data->args.count; - if (unlikely(count == 0)) - return; - pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; - base &= ~PAGE_CACHE_MASK; - count += base; - for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) - SetPageUptodate(*pages); - if (count == 0) - return; - /* Was this a short read? */ - if (data->res.eof || data->res.count == data->args.count) - SetPageUptodate(*pages); -} - -/* - * This is the callback from RPC telling us whether a reply was - * received or some error occurred (timeout or socket shutdown). - */ -static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) -{ - struct nfs_read_data *data = calldata; - - if (nfs_readpage_result(task, data) != 0) - return; - if (task->tk_status < 0) - return; - /* - * Note: nfs_readpage_retry may change the values of - * data->args. In the multi-page case, we therefore need - * to ensure that we call nfs_readpage_set_pages_uptodate() - * first. - */ - nfs_readpage_truncate_uninitialised_page(data); - nfs_readpage_set_pages_uptodate(data); - nfs_readpage_retry(task, data); -} - -static void nfs_readpage_release_full(void *calldata) -{ - struct nfs_read_data *data = calldata; - - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); - - nfs_list_remove_request(req); - nfs_readpage_release(req); - } - nfs_readdata_release(calldata); + NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_read_full_ops = { +static const struct rpc_call_ops nfs_read_common_ops = { .rpc_call_prepare = nfs_read_prepare, - .rpc_call_done = nfs_readpage_result_full, - .rpc_release = nfs_readpage_release_full, + .rpc_call_done = nfs_readpage_result_common, + .rpc_release = nfs_readpage_release_common, }; /* @@ -668,11 +652,12 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&pgio, inode); + nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); nfs_pageio_complete(&pgio); + NFS_I(inode)->read_io += pgio.pg_bytes_written; npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; nfs_add_stats(inode, NFSIOS_READPAGES, npages); read_complete: @@ -684,7 +669,7 @@ out: int __init nfs_init_readpagecache(void) { nfs_rdata_cachep = kmem_cache_create("nfs_read_data", - sizeof(struct nfs_read_data), + sizeof(struct nfs_read_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_rdata_cachep == NULL) diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 37412f706b3..906f09c7d84 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -66,6 +66,7 @@ #include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_VFS +#define NFS_TEXT_DATA 1 #ifdef CONFIG_NFS_V3 #define NFS_DEFAULT_VERSION 3 @@ -277,12 +278,22 @@ static match_table_t nfs_vers_tokens = { { Opt_vers_err, NULL } }; +struct nfs_mount_info { + void (*fill_super)(struct super_block *, struct nfs_mount_info *); + int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); + struct nfs_parsed_mount_data *parsed; + struct nfs_clone_mount *cloned; + struct nfs_fh *mntfh; +}; + static void nfs_umount_begin(struct super_block *); static int nfs_statfs(struct dentry *, struct kstatfs *); static int nfs_show_options(struct seq_file *, struct dentry *); static int nfs_show_devname(struct seq_file *, struct dentry *); static int nfs_show_path(struct seq_file *, struct dentry *); static int nfs_show_stats(struct seq_file *, struct dentry *); +static struct dentry *nfs_fs_mount_common(struct file_system_type *, + struct nfs_server *, int, const char *, struct nfs_mount_info *); static struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *); static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type, @@ -323,12 +334,11 @@ static const struct super_operations nfs_sops = { }; #ifdef CONFIG_NFS_V4 -static int nfs4_validate_text_mount_data(void *options, +static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); +static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); static struct dentry *nfs4_try_mount(int flags, const char *dev_name, - struct nfs_parsed_mount_data *data); -static struct dentry *nfs4_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); + struct nfs_mount_info *mount_info); static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data); static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type, @@ -342,7 +352,7 @@ static void nfs4_kill_super(struct super_block *sb); static struct file_system_type nfs4_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .mount = nfs4_mount, + .mount = nfs_fs_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -786,8 +796,8 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server) static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) { - if (nfss->nfs_client && nfss->nfs_client->impl_id) { - struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id; + if (nfss->nfs_client && nfss->nfs_client->cl_implid) { + struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid; seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s'," "date='%llu,%u'", impl_id->name, impl_id->domain, @@ -938,7 +948,7 @@ static void nfs_umount_begin(struct super_block *sb) rpc_killall_tasks(rpc); } -static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int version) +static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) { struct nfs_parsed_mount_data *data; @@ -953,8 +963,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve data->nfs_server.protocol = XPRT_TRANSPORT_TCP; data->auth_flavors[0] = RPC_AUTH_UNIX; data->auth_flavor_len = 1; - data->version = version; data->minorversion = 0; + data->need_mount = true; data->net = current->nsproxy->net_ns; security_init_mnt_opts(&data->lsm_opts); } @@ -1674,8 +1684,8 @@ static int nfs_walk_authlist(struct nfs_parsed_mount_data *args, * Use the remote server's MOUNT service to request the NFS file handle * corresponding to the provided path. */ -static int nfs_try_mount(struct nfs_parsed_mount_data *args, - struct nfs_fh *root_fh) +static int nfs_request_mount(struct nfs_parsed_mount_data *args, + struct nfs_fh *root_fh) { rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS]; unsigned int server_authlist_len = ARRAY_SIZE(server_authlist); @@ -1738,6 +1748,26 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args, return nfs_walk_authlist(args, &request); } +static struct dentry *nfs_try_mount(int flags, const char *dev_name, + struct nfs_mount_info *mount_info) +{ + int status; + struct nfs_server *server; + + if (mount_info->parsed->need_mount) { + status = nfs_request_mount(mount_info->parsed, mount_info->mntfh); + if (status) + return ERR_PTR(status); + } + + /* Get a volume representation */ + server = nfs_create_server(mount_info->parsed, mount_info->mntfh); + if (IS_ERR(server)) + return ERR_CAST(server); + + return nfs_fs_mount_common(&nfs_fs_type, server, flags, dev_name, mount_info); +} + /* * Split "dev_name" into "hostname:export_path". * @@ -1826,10 +1856,10 @@ out_path: * + breaking back: trying proto=udp after proto=tcp, v2 after v3, * mountproto=tcp after mountproto=udp, and so on */ -static int nfs_validate_mount_data(void *options, - struct nfs_parsed_mount_data *args, - struct nfs_fh *mntfh, - const char *dev_name) +static int nfs23_validate_mount_data(void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) { struct nfs_mount_data *data = (struct nfs_mount_data *)options; struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; @@ -1837,6 +1867,7 @@ static int nfs_validate_mount_data(void *options, if (data == NULL) goto out_no_data; + args->version = NFS_DEFAULT_VERSION; switch (data->version) { case 1: data->namlen = 0; @@ -1883,6 +1914,7 @@ static int nfs_validate_mount_data(void *options, args->acregmax = data->acregmax; args->acdirmin = data->acdirmin; args->acdirmax = data->acdirmax; + args->need_mount = false; memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); @@ -1934,43 +1966,8 @@ static int nfs_validate_mount_data(void *options, } break; - default: { - int status; - - if (nfs_parse_mount_options((char *)options, args) == 0) - return -EINVAL; - - if (!nfs_verify_server_address(sap)) - goto out_no_address; - - if (args->version == 4) -#ifdef CONFIG_NFS_V4 - return nfs4_validate_text_mount_data(options, - args, dev_name); -#else - goto out_v4_not_compiled; -#endif - - nfs_set_port(sap, &args->nfs_server.port, 0); - - nfs_set_mount_transport_protocol(args); - - status = nfs_parse_devname(dev_name, - &args->nfs_server.hostname, - PAGE_SIZE, - &args->nfs_server.export_path, - NFS_MAXPATHLEN); - if (!status) - status = nfs_try_mount(args, mntfh); - - kfree(args->nfs_server.export_path); - args->nfs_server.export_path = NULL; - - if (status) - return status; - - break; - } + default: + return NFS_TEXT_DATA; } #ifndef CONFIG_NFS_V3 @@ -1999,12 +1996,6 @@ out_v3_not_compiled: return -EPROTONOSUPPORT; #endif /* !CONFIG_NFS_V3 */ -#ifndef CONFIG_NFS_V4 -out_v4_not_compiled: - dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); - return -EPROTONOSUPPORT; -#endif /* !CONFIG_NFS_V4 */ - out_nomem: dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n"); return -ENOMEM; @@ -2018,6 +2009,82 @@ out_invalid_fh: return -EINVAL; } +#ifdef CONFIG_NFS_V4 +static int nfs_validate_mount_data(struct file_system_type *fs_type, + void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) +{ + if (fs_type == &nfs_fs_type) + return nfs23_validate_mount_data(options, args, mntfh, dev_name); + return nfs4_validate_mount_data(options, args, dev_name); +} +#else +static int nfs_validate_mount_data(struct file_system_type *fs_type, + void *options, + struct nfs_parsed_mount_data *args, + struct nfs_fh *mntfh, + const char *dev_name) +{ + return nfs23_validate_mount_data(options, args, mntfh, dev_name); +} +#endif + +static int nfs_validate_text_mount_data(void *options, + struct nfs_parsed_mount_data *args, + const char *dev_name) +{ + int port = 0; + int max_namelen = PAGE_SIZE; + int max_pathlen = NFS_MAXPATHLEN; + struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; + + if (nfs_parse_mount_options((char *)options, args) == 0) + return -EINVAL; + + if (!nfs_verify_server_address(sap)) + goto out_no_address; + + if (args->version == 4) { +#ifdef CONFIG_NFS_V4 + port = NFS_PORT; + max_namelen = NFS4_MAXNAMLEN; + max_pathlen = NFS4_MAXPATHLEN; + nfs_validate_transport_protocol(args); + nfs4_validate_mount_flags(args); +#else + goto out_v4_not_compiled; +#endif /* CONFIG_NFS_V4 */ + } else + nfs_set_mount_transport_protocol(args); + + nfs_set_port(sap, &args->nfs_server.port, port); + + if (args->auth_flavor_len > 1) + goto out_bad_auth; + + return nfs_parse_devname(dev_name, + &args->nfs_server.hostname, + max_namelen, + &args->nfs_server.export_path, + max_pathlen); + +#ifndef CONFIG_NFS_V4 +out_v4_not_compiled: + dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); + return -EPROTONOSUPPORT; +#endif /* !CONFIG_NFS_V4 */ + +out_no_address: + dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n"); + return -EINVAL; + +out_bad_auth: + dfprintk(MOUNT, "NFS: Too many RPC auth flavours specified\n"); + return -EINVAL; +} + static int nfs_compare_remount_data(struct nfs_server *nfss, struct nfs_parsed_mount_data *data) @@ -2129,8 +2196,9 @@ static inline void nfs_initialise_sb(struct super_block *sb) * Finish setting up an NFS2/3 superblock */ static void nfs_fill_super(struct super_block *sb, - struct nfs_parsed_mount_data *data) + struct nfs_mount_info *mount_info) { + struct nfs_parsed_mount_data *data = mount_info->parsed; struct nfs_server *server = NFS_SB(sb); sb->s_blocksize_bits = 0; @@ -2154,8 +2222,9 @@ static void nfs_fill_super(struct super_block *sb, * Finish setting up a cloned NFS2/3 superblock */ static void nfs_clone_super(struct super_block *sb, - const struct super_block *old_sb) + struct nfs_mount_info *mount_info) { + const struct super_block *old_sb = mount_info->cloned->sb; struct nfs_server *server = NFS_SB(sb); sb->s_blocksize_bits = old_sb->s_blocksize_bits; @@ -2278,52 +2347,70 @@ static int nfs_compare_super(struct super_block *sb, void *data) return nfs_compare_mount_options(sb, server, mntflags); } +#ifdef CONFIG_NFS_FSCACHE +static void nfs_get_cache_cookie(struct super_block *sb, + struct nfs_parsed_mount_data *parsed, + struct nfs_clone_mount *cloned) +{ + char *uniq = NULL; + int ulen = 0; + + if (parsed && parsed->fscache_uniq) { + uniq = parsed->fscache_uniq; + ulen = strlen(parsed->fscache_uniq); + } else if (cloned) { + struct nfs_server *mnt_s = NFS_SB(cloned->sb); + if (mnt_s->fscache_key) { + uniq = mnt_s->fscache_key->key.uniquifier; + ulen = mnt_s->fscache_key->key.uniq_len; + }; + } + + nfs_fscache_get_super_cookie(sb, uniq, ulen); +} +#else +static void nfs_get_cache_cookie(struct super_block *sb, + struct nfs_parsed_mount_data *parsed, + struct nfs_clone_mount *cloned) +{ +} +#endif + static int nfs_bdi_register(struct nfs_server *server) { return bdi_register_dev(&server->backing_dev_info, server->s_dev); } -static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) +static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) +{ + return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts); +} + +static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) +{ + /* clone any lsm security options from the parent to the new sb */ + security_sb_clone_mnt_opts(mount_info->cloned->sb, s); + if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) + return -ESTALE; + return 0; +} + +static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type, + struct nfs_server *server, + int flags, const char *dev_name, + struct nfs_mount_info *mount_info) { - struct nfs_server *server = NULL; struct super_block *s; - struct nfs_parsed_mount_data *data; - struct nfs_fh *mntfh; struct dentry *mntroot = ERR_PTR(-ENOMEM); int (*compare_super)(struct super_block *, void *) = nfs_compare_super; struct nfs_sb_mountdata sb_mntdata = { .mntflags = flags, + .server = server, }; int error; - data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION); - mntfh = nfs_alloc_fhandle(); - if (data == NULL || mntfh == NULL) - goto out; - - /* Validate the mount data */ - error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name); - if (error < 0) { - mntroot = ERR_PTR(error); - goto out; - } - -#ifdef CONFIG_NFS_V4 - if (data->version == 4) { - mntroot = nfs4_try_mount(flags, dev_name, data); - goto out; - } -#endif /* CONFIG_NFS_V4 */ - - /* Get a volume representation */ - server = nfs_create_server(data, mntfh); - if (IS_ERR(server)) { - mntroot = ERR_CAST(server); - goto out; - } - sb_mntdata.server = server; - if (server->flags & NFS_MOUNT_UNSHARED) compare_super = NULL; @@ -2351,23 +2438,21 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, if (!s->s_root) { /* initial superblock/root creation */ - nfs_fill_super(s, data); - nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL); + mount_info->fill_super(s, mount_info); + nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned); } - mntroot = nfs_get_root(s, mntfh, dev_name); + mntroot = nfs_get_root(s, mount_info->mntfh, dev_name); if (IS_ERR(mntroot)) goto error_splat_super; - error = security_sb_set_mnt_opts(s, &data->lsm_opts); + error = mount_info->set_security(s, mntroot, mount_info); if (error) goto error_splat_root; s->s_flags |= MS_ACTIVE; out: - nfs_free_parsed_mount_data(data); - nfs_free_fhandle(mntfh); return mntroot; out_err_nosb: @@ -2385,6 +2470,43 @@ error_splat_bdi: goto out; } +static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_mount_info mount_info = { + .fill_super = nfs_fill_super, + .set_security = nfs_set_sb_security, + }; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + int error; + + mount_info.parsed = nfs_alloc_parsed_mount_data(); + mount_info.mntfh = nfs_alloc_fhandle(); + if (mount_info.parsed == NULL || mount_info.mntfh == NULL) + goto out; + + /* Validate the mount data */ + error = nfs_validate_mount_data(fs_type, raw_data, mount_info.parsed, mount_info.mntfh, dev_name); + if (error == NFS_TEXT_DATA) + error = nfs_validate_text_mount_data(raw_data, mount_info.parsed, dev_name); + if (error < 0) { + mntroot = ERR_PTR(error); + goto out; + } + +#ifdef CONFIG_NFS_V4 + if (mount_info.parsed->version == 4) + mntroot = nfs4_try_mount(flags, dev_name, &mount_info); + else +#endif /* CONFIG_NFS_V4 */ + mntroot = nfs_try_mount(flags, dev_name, &mount_info); + +out: + nfs_free_parsed_mount_data(mount_info.parsed); + nfs_free_fhandle(mount_info.mntfh); + return mntroot; +} + /* * Ensure that we unregister the bdi before kill_anon_super * releases the device name @@ -2409,93 +2531,51 @@ static void nfs_kill_super(struct super_block *s) } /* - * Clone an NFS2/3 server record on xdev traversal (FSID-change) + * Clone an NFS2/3/4 server record on xdev traversal (FSID-change) */ static struct dentry * -nfs_xdev_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) +nfs_xdev_mount_common(struct file_system_type *fs_type, int flags, + const char *dev_name, struct nfs_mount_info *mount_info) { - struct nfs_clone_mount *data = raw_data; - struct super_block *s; + struct nfs_clone_mount *data = mount_info->cloned; struct nfs_server *server; - struct dentry *mntroot; - int (*compare_super)(struct super_block *, void *) = nfs_compare_super; - struct nfs_sb_mountdata sb_mntdata = { - .mntflags = flags, - }; + struct dentry *mntroot = ERR_PTR(-ENOMEM); int error; - dprintk("--> nfs_xdev_mount()\n"); + dprintk("--> nfs_xdev_mount_common()\n"); + + mount_info->mntfh = data->fh; /* create a new volume representation */ - server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); + server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); if (IS_ERR(server)) { error = PTR_ERR(server); - goto out_err_noserver; - } - sb_mntdata.server = server; - - if (server->flags & NFS_MOUNT_UNSHARED) - compare_super = NULL; - - /* -o noac implies -o sync */ - if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; - - /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata); - if (IS_ERR(s)) { - error = PTR_ERR(s); - goto out_err_nosb; - } - - if (s->s_fs_info != server) { - nfs_free_server(server); - server = NULL; - } else { - error = nfs_bdi_register(server); - if (error) - goto error_splat_bdi; - } - - if (!s->s_root) { - /* initial superblock/root creation */ - nfs_clone_super(s, data->sb); - nfs_fscache_get_super_cookie(s, NULL, data); - } - - mntroot = nfs_get_root(s, data->fh, dev_name); - if (IS_ERR(mntroot)) { - error = PTR_ERR(mntroot); - goto error_splat_super; - } - if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { - dput(mntroot); - error = -ESTALE; - goto error_splat_super; + goto out_err; } - s->s_flags |= MS_ACTIVE; - - /* clone any lsm security options from the parent to the new sb */ - security_sb_clone_mnt_opts(data->sb, s); - - dprintk("<-- nfs_xdev_mount() = 0\n"); + mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info); + dprintk("<-- nfs_xdev_mount_common() = 0\n"); +out: return mntroot; -out_err_nosb: - nfs_free_server(server); -out_err_noserver: - dprintk("<-- nfs_xdev_mount() = %d [error]\n", error); - return ERR_PTR(error); +out_err: + dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error); + goto out; +} -error_splat_super: - if (server && !s->s_root) - bdi_unregister(&server->backing_dev_info); -error_splat_bdi: - deactivate_locked_super(s); - dprintk("<-- nfs_xdev_mount() = %d [splat]\n", error); - return ERR_PTR(error); +/* + * Clone an NFS2/3 server record on xdev traversal (FSID-change) + */ +static struct dentry * +nfs_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + struct nfs_mount_info mount_info = { + .fill_super = nfs_clone_super, + .set_security = nfs_clone_sb_security, + .cloned = raw_data, + }; + return nfs_xdev_mount_common(&nfs_fs_type, flags, dev_name, &mount_info); } #ifdef CONFIG_NFS_V4 @@ -2504,8 +2584,9 @@ error_splat_bdi: * Finish setting up a cloned NFS4 superblock */ static void nfs4_clone_super(struct super_block *sb, - const struct super_block *old_sb) + struct nfs_mount_info *mount_info) { + const struct super_block *old_sb = mount_info->cloned->sb; sb->s_blocksize_bits = old_sb->s_blocksize_bits; sb->s_blocksize = old_sb->s_blocksize; sb->s_maxbytes = old_sb->s_maxbytes; @@ -2523,7 +2604,8 @@ static void nfs4_clone_super(struct super_block *sb, /* * Set up an NFS4 superblock */ -static void nfs4_fill_super(struct super_block *sb) +static void nfs4_fill_super(struct super_block *sb, + struct nfs_mount_info *mount_info) { sb->s_time_gran = 1; sb->s_op = &nfs4_sops; @@ -2542,37 +2624,6 @@ static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL); } -static int nfs4_validate_text_mount_data(void *options, - struct nfs_parsed_mount_data *args, - const char *dev_name) -{ - struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address; - - nfs_set_port(sap, &args->nfs_server.port, NFS_PORT); - - nfs_validate_transport_protocol(args); - - nfs4_validate_mount_flags(args); - - if (args->version != 4) { - dfprintk(MOUNT, - "NFS4: Illegal mount version\n"); - return -EINVAL; - } - - if (args->auth_flavor_len > 1) { - dfprintk(MOUNT, - "NFS4: Too many RPC auth flavours specified\n"); - return -EINVAL; - } - - return nfs_parse_devname(dev_name, - &args->nfs_server.hostname, - NFS4_MAXNAMLEN, - &args->nfs_server.export_path, - NFS4_MAXPATHLEN); -} - /* * Validate NFSv4 mount options */ @@ -2587,6 +2638,8 @@ static int nfs4_validate_mount_data(void *options, if (data == NULL) goto out_no_data; + args->version = 4; + switch (data->version) { case 1: if (data->host_addrlen > sizeof(args->nfs_server.address)) @@ -2643,13 +2696,7 @@ static int nfs4_validate_mount_data(void *options, break; default: - if (nfs_parse_mount_options((char *)options, args) == 0) - return -EINVAL; - - if (!nfs_verify_server_address(sap)) - return -EINVAL; - - return nfs4_validate_text_mount_data(options, args, dev_name); + return NFS_TEXT_DATA; } return 0; @@ -2673,91 +2720,26 @@ out_no_address: */ static struct dentry * nfs4_remote_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) + const char *dev_name, void *info) { - struct nfs_parsed_mount_data *data = raw_data; - struct super_block *s; + struct nfs_mount_info *mount_info = info; struct nfs_server *server; - struct nfs_fh *mntfh; - struct dentry *mntroot; - int (*compare_super)(struct super_block *, void *) = nfs_compare_super; - struct nfs_sb_mountdata sb_mntdata = { - .mntflags = flags, - }; - int error = -ENOMEM; + struct dentry *mntroot = ERR_PTR(-ENOMEM); - mntfh = nfs_alloc_fhandle(); - if (data == NULL || mntfh == NULL) - goto out; + mount_info->fill_super = nfs4_fill_super; + mount_info->set_security = nfs_set_sb_security; /* Get a volume representation */ - server = nfs4_create_server(data, mntfh); + server = nfs4_create_server(mount_info->parsed, mount_info->mntfh); if (IS_ERR(server)) { - error = PTR_ERR(server); + mntroot = ERR_CAST(server); goto out; } - sb_mntdata.server = server; - - if (server->flags & NFS4_MOUNT_UNSHARED) - compare_super = NULL; - - /* -o noac implies -o sync */ - if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; - - /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); - if (IS_ERR(s)) { - error = PTR_ERR(s); - goto out_free; - } - - if (s->s_fs_info != server) { - nfs_free_server(server); - server = NULL; - } else { - error = nfs_bdi_register(server); - if (error) - goto error_splat_bdi; - } - - if (!s->s_root) { - /* initial superblock/root creation */ - nfs4_fill_super(s); - nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL); - } - mntroot = nfs4_get_root(s, mntfh, dev_name); - if (IS_ERR(mntroot)) { - error = PTR_ERR(mntroot); - goto error_splat_super; - } - - error = security_sb_set_mnt_opts(s, &data->lsm_opts); - if (error) - goto error_splat_root; - - s->s_flags |= MS_ACTIVE; - - nfs_free_fhandle(mntfh); - return mntroot; + mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info); out: - nfs_free_fhandle(mntfh); - return ERR_PTR(error); - -out_free: - nfs_free_server(server); - goto out; - -error_splat_root: - dput(mntroot); -error_splat_super: - if (server && !s->s_root) - bdi_unregister(&server->backing_dev_info); -error_splat_bdi: - deactivate_locked_super(s); - goto out; + return mntroot; } static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, @@ -2767,11 +2749,15 @@ static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, char *root_devname; size_t len; - len = strlen(hostname) + 3; + len = strlen(hostname) + 5; root_devname = kmalloc(len, GFP_KERNEL); if (root_devname == NULL) return ERR_PTR(-ENOMEM); - snprintf(root_devname, len, "%s:/", hostname); + /* Does hostname needs to be enclosed in brackets? */ + if (strchr(hostname, ':')) + snprintf(root_devname, len, "[%s]:/", hostname); + else + snprintf(root_devname, len, "%s:/", hostname); root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); kfree(root_devname); return root_mnt; @@ -2865,17 +2851,18 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, } static struct dentry *nfs4_try_mount(int flags, const char *dev_name, - struct nfs_parsed_mount_data *data) + struct nfs_mount_info *mount_info) { char *export_path; struct vfsmount *root_mnt; struct dentry *res; + struct nfs_parsed_mount_data *data = mount_info->parsed; dfprintk(MOUNT, "--> nfs4_try_mount()\n"); export_path = data->nfs_server.export_path; data->nfs_server.export_path = "/"; - root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data, + root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, data->nfs_server.hostname); data->nfs_server.export_path = export_path; @@ -2887,38 +2874,6 @@ static struct dentry *nfs4_try_mount(int flags, const char *dev_name, return res; } -/* - * Get the superblock for an NFS4 mountpoint - */ -static struct dentry *nfs4_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) -{ - struct nfs_parsed_mount_data *data; - int error = -ENOMEM; - struct dentry *res = ERR_PTR(-ENOMEM); - - data = nfs_alloc_parsed_mount_data(4); - if (data == NULL) - goto out; - - /* Validate the mount data */ - error = nfs4_validate_mount_data(raw_data, data, dev_name); - if (error < 0) { - res = ERR_PTR(error); - goto out; - } - - res = nfs4_try_mount(flags, dev_name, data); - if (IS_ERR(res)) - error = PTR_ERR(res); - -out: - nfs_free_parsed_mount_data(data); - dprintk("<-- nfs4_mount() = %d%s\n", error, - error != 0 ? " [error]" : ""); - return res; -} - static void nfs4_kill_super(struct super_block *sb) { struct nfs_server *server = NFS_SB(sb); @@ -2938,181 +2893,43 @@ static struct dentry * nfs4_xdev_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data) { - struct nfs_clone_mount *data = raw_data; - struct super_block *s; - struct nfs_server *server; - struct dentry *mntroot; - int (*compare_super)(struct super_block *, void *) = nfs_compare_super; - struct nfs_sb_mountdata sb_mntdata = { - .mntflags = flags, + struct nfs_mount_info mount_info = { + .fill_super = nfs4_clone_super, + .set_security = nfs_clone_sb_security, + .cloned = raw_data, }; - int error; - - dprintk("--> nfs4_xdev_mount()\n"); - - /* create a new volume representation */ - server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); - if (IS_ERR(server)) { - error = PTR_ERR(server); - goto out_err_noserver; - } - sb_mntdata.server = server; - - if (server->flags & NFS4_MOUNT_UNSHARED) - compare_super = NULL; - - /* -o noac implies -o sync */ - if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; - - /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); - if (IS_ERR(s)) { - error = PTR_ERR(s); - goto out_err_nosb; - } - - if (s->s_fs_info != server) { - nfs_free_server(server); - server = NULL; - } else { - error = nfs_bdi_register(server); - if (error) - goto error_splat_bdi; - } - - if (!s->s_root) { - /* initial superblock/root creation */ - nfs4_clone_super(s, data->sb); - nfs_fscache_get_super_cookie(s, NULL, data); - } - - mntroot = nfs4_get_root(s, data->fh, dev_name); - if (IS_ERR(mntroot)) { - error = PTR_ERR(mntroot); - goto error_splat_super; - } - if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { - dput(mntroot); - error = -ESTALE; - goto error_splat_super; - } - - s->s_flags |= MS_ACTIVE; - - security_sb_clone_mnt_opts(data->sb, s); - - dprintk("<-- nfs4_xdev_mount() = 0\n"); - return mntroot; - -out_err_nosb: - nfs_free_server(server); -out_err_noserver: - dprintk("<-- nfs4_xdev_mount() = %d [error]\n", error); - return ERR_PTR(error); - -error_splat_super: - if (server && !s->s_root) - bdi_unregister(&server->backing_dev_info); -error_splat_bdi: - deactivate_locked_super(s); - dprintk("<-- nfs4_xdev_mount() = %d [splat]\n", error); - return ERR_PTR(error); + return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info); } static struct dentry * nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data) { - struct nfs_clone_mount *data = raw_data; - struct super_block *s; - struct nfs_server *server; - struct dentry *mntroot; - struct nfs_fh *mntfh; - int (*compare_super)(struct super_block *, void *) = nfs_compare_super; - struct nfs_sb_mountdata sb_mntdata = { - .mntflags = flags, + struct nfs_mount_info mount_info = { + .fill_super = nfs4_fill_super, + .set_security = nfs_clone_sb_security, + .cloned = raw_data, }; - int error = -ENOMEM; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); dprintk("--> nfs4_referral_get_sb()\n"); - mntfh = nfs_alloc_fhandle(); - if (mntfh == NULL) - goto out_err_nofh; + mount_info.mntfh = nfs_alloc_fhandle(); + if (mount_info.cloned == NULL || mount_info.mntfh == NULL) + goto out; /* create a new volume representation */ - server = nfs4_create_referral_server(data, mntfh); + server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh); if (IS_ERR(server)) { - error = PTR_ERR(server); - goto out_err_noserver; - } - sb_mntdata.server = server; - - if (server->flags & NFS4_MOUNT_UNSHARED) - compare_super = NULL; - - /* -o noac implies -o sync */ - if (server->flags & NFS_MOUNT_NOAC) - sb_mntdata.mntflags |= MS_SYNCHRONOUS; - - /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata); - if (IS_ERR(s)) { - error = PTR_ERR(s); - goto out_err_nosb; - } - - if (s->s_fs_info != server) { - nfs_free_server(server); - server = NULL; - } else { - error = nfs_bdi_register(server); - if (error) - goto error_splat_bdi; - } - - if (!s->s_root) { - /* initial superblock/root creation */ - nfs4_fill_super(s); - nfs_fscache_get_super_cookie(s, NULL, data); - } - - mntroot = nfs4_get_root(s, mntfh, dev_name); - if (IS_ERR(mntroot)) { - error = PTR_ERR(mntroot); - goto error_splat_super; - } - if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) { - dput(mntroot); - error = -ESTALE; - goto error_splat_super; + mntroot = ERR_CAST(server); + goto out; } - s->s_flags |= MS_ACTIVE; - - security_sb_clone_mnt_opts(data->sb, s); - - nfs_free_fhandle(mntfh); - dprintk("<-- nfs4_referral_get_sb() = 0\n"); + mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info); +out: + nfs_free_fhandle(mount_info.mntfh); return mntroot; - -out_err_nosb: - nfs_free_server(server); -out_err_noserver: - nfs_free_fhandle(mntfh); -out_err_nofh: - dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error); - return ERR_PTR(error); - -error_splat_super: - if (server && !s->s_root) - bdi_unregister(&server->backing_dev_info); -error_splat_bdi: - deactivate_locked_super(s); - nfs_free_fhandle(mntfh); - dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); - return ERR_PTR(error); } /* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2c68818f68a..4d6861c0dc1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -39,20 +39,20 @@ /* * Local function declarations */ -static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc, - struct inode *inode, int ioflags); static void nfs_redirty_request(struct nfs_page *req); -static const struct rpc_call_ops nfs_write_partial_ops; -static const struct rpc_call_ops nfs_write_full_ops; +static const struct rpc_call_ops nfs_write_common_ops; static const struct rpc_call_ops nfs_commit_ops; +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; +static struct kmem_cache *nfs_cdata_cachep; static mempool_t *nfs_commit_mempool; -struct nfs_write_data *nfs_commitdata_alloc(void) +struct nfs_commit_data *nfs_commitdata_alloc(void) { - struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS); + struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS); if (p) { memset(p, 0, sizeof(*p)); @@ -62,46 +62,74 @@ struct nfs_write_data *nfs_commitdata_alloc(void) } EXPORT_SYMBOL_GPL(nfs_commitdata_alloc); -void nfs_commit_free(struct nfs_write_data *p) +void nfs_commit_free(struct nfs_commit_data *p) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); mempool_free(p, nfs_commit_mempool); } EXPORT_SYMBOL_GPL(nfs_commit_free); -struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) +struct nfs_write_header *nfs_writehdr_alloc(void) { - struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); + struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); if (p) { + struct nfs_pgio_header *hdr = &p->header; + memset(p, 0, sizeof(*p)); - INIT_LIST_HEAD(&p->pages); - p->npages = pagecount; - if (pagecount <= ARRAY_SIZE(p->page_array)) - p->pagevec = p->page_array; - else { - p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); - if (!p->pagevec) { - mempool_free(p, nfs_wdata_mempool); - p = NULL; - } - } + INIT_LIST_HEAD(&hdr->pages); + INIT_LIST_HEAD(&hdr->rpc_list); + spin_lock_init(&hdr->lock); + atomic_set(&hdr->refcnt, 0); + hdr->verf = &p->verf; } return p; } -void nfs_writedata_free(struct nfs_write_data *p) +static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, + unsigned int pagecount) +{ + struct nfs_write_data *data, *prealloc; + + prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data; + if (prealloc->header == NULL) + data = prealloc; + else + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + goto out; + + if (nfs_pgarray_set(&data->pages, pagecount)) { + data->header = hdr; + atomic_inc(&hdr->refcnt); + } else { + if (data != prealloc) + kfree(data); + data = NULL; + } +out: + return data; +} + +void nfs_writehdr_free(struct nfs_pgio_header *hdr) { - if (p && (p->pagevec != &p->page_array[0])) - kfree(p->pagevec); - mempool_free(p, nfs_wdata_mempool); + struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); + mempool_free(whdr, nfs_wdata_mempool); } void nfs_writedata_release(struct nfs_write_data *wdata) { + struct nfs_pgio_header *hdr = wdata->header; + struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header); + put_nfs_open_context(wdata->args.context); - nfs_writedata_free(wdata); + if (wdata->pages.pagevec != wdata->pages.page_array) + kfree(wdata->pages.pagevec); + if (wdata != &write_header->rpc_data) + kfree(wdata); + else + wdata->header = NULL; + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); } static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) @@ -203,7 +231,6 @@ static int nfs_set_page_writeback(struct page *page) struct inode *inode = page->mapping->host; struct nfs_server *nfss = NFS_SERVER(inode); - page_cache_get(page); if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH) { set_bdi_congested(&nfss->backing_dev_info, @@ -219,7 +246,6 @@ static void nfs_end_page_writeback(struct page *page) struct nfs_server *nfss = NFS_SERVER(inode); end_page_writeback(page); - page_cache_release(page); if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } @@ -235,10 +261,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo req = nfs_page_find_request_locked(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* Note: If we hold the page lock, as is the case in nfs_writepage, - * then the call to nfs_lock_request_dontget() will always + * then the call to nfs_lock_request() will always * succeed provided that someone hasn't already marked the * request as dirty (in which case we don't care). */ @@ -310,7 +336,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc struct nfs_pageio_descriptor pgio; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), + &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); if (err < 0) @@ -353,7 +380,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc)); + nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), + &nfs_async_write_completion_ops); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); @@ -379,7 +407,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) struct nfs_inode *nfsi = NFS_I(inode); /* Lock the request! */ - nfs_lock_request_dontget(req); + nfs_lock_request(req); spin_lock(&inode->i_lock); if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE)) @@ -421,65 +449,88 @@ nfs_mark_request_dirty(struct nfs_page *req) /** * nfs_request_add_commit_list - add request to a commit list * @req: pointer to a struct nfs_page - * @head: commit list head + * @dst: commit list head + * @cinfo: holds list lock and accounting info * - * This sets the PG_CLEAN bit, updates the inode global count of + * This sets the PG_CLEAN bit, updates the cinfo count of * number of outstanding requests requiring a commit as well as * the MM page stats. * - * The caller must _not_ hold the inode->i_lock, but must be + * The caller must _not_ hold the cinfo->lock, but must be * holding the nfs_page lock. */ void -nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head) +nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - set_bit(PG_CLEAN, &(req)->wb_flags); - spin_lock(&inode->i_lock); - nfs_list_add_request(req, head); - NFS_I(inode)->ncommit++; - spin_unlock(&inode->i_lock); - inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE); - __mark_inode_dirty(inode, I_DIRTY_DATASYNC); + spin_lock(cinfo->lock); + nfs_list_add_request(req, dst); + cinfo->mds->ncommit++; + spin_unlock(cinfo->lock); + if (!cinfo->dreq) { + inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); + inc_bdi_stat(req->wb_page->mapping->backing_dev_info, + BDI_RECLAIMABLE); + __mark_inode_dirty(req->wb_context->dentry->d_inode, + I_DIRTY_DATASYNC); + } } EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); /** * nfs_request_remove_commit_list - Remove request from a commit list * @req: pointer to a nfs_page + * @cinfo: holds list lock and accounting info * - * This clears the PG_CLEAN bit, and updates the inode global count of + * This clears the PG_CLEAN bit, and updates the cinfo's count of * number of outstanding requests requiring a commit * It does not update the MM page stats. * - * The caller _must_ hold the inode->i_lock and the nfs_page lock. + * The caller _must_ hold the cinfo->lock and the nfs_page lock. */ void -nfs_request_remove_commit_list(struct nfs_page *req) +nfs_request_remove_commit_list(struct nfs_page *req, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) return; nfs_list_remove_request(req); - NFS_I(inode)->ncommit--; + cinfo->mds->ncommit--; } EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode) +{ + cinfo->lock = &inode->i_lock; + cinfo->mds = &NFS_I(inode)->commit_info; + cinfo->ds = pnfs_get_ds_info(inode); + cinfo->dreq = NULL; + cinfo->completion_ops = &nfs_commit_completion_ops; +} + +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq) +{ + if (dreq) + nfs_init_cinfo_from_dreq(cinfo, dreq); + else + nfs_init_cinfo_from_inode(cinfo, inode); +} +EXPORT_SYMBOL_GPL(nfs_init_cinfo); /* * Add a request to the inode's commit list. */ -static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) +void +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; - - if (pnfs_mark_request_commit(req, lseg)) + if (pnfs_mark_request_commit(req, lseg, cinfo)) return; - nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list); + nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo); } static void @@ -494,11 +545,13 @@ nfs_clear_request_commit(struct nfs_page *req) { if (test_bit(PG_CLEAN, &req->wb_flags)) { struct inode *inode = req->wb_context->dentry->d_inode; + struct nfs_commit_info cinfo; - if (!pnfs_clear_request_commit(req)) { - spin_lock(&inode->i_lock); - nfs_request_remove_commit_list(req); - spin_unlock(&inode->i_lock); + nfs_init_cinfo_from_inode(&cinfo, inode); + if (!pnfs_clear_request_commit(req, &cinfo)) { + spin_lock(cinfo.lock); + nfs_request_remove_commit_list(req, &cinfo); + spin_unlock(cinfo.lock); } nfs_clear_page_commit(req->wb_page); } @@ -508,28 +561,25 @@ static inline int nfs_write_need_commit(struct nfs_write_data *data) { if (data->verf.committed == NFS_DATA_SYNC) - return data->lseg == NULL; - else - return data->verf.committed != NFS_FILE_SYNC; + return data->header->lseg == NULL; + return data->verf.committed != NFS_FILE_SYNC; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) +#else +static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, + struct inode *inode) { - if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) { - nfs_mark_request_commit(req, data->lseg); - return 1; - } - if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) { - nfs_mark_request_dirty(req); - return 1; - } - return 0; } -#else -static void -nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg) + +void nfs_init_cinfo(struct nfs_commit_info *cinfo, + struct inode *inode, + struct nfs_direct_req *dreq) +{ +} + +void +nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { } @@ -544,25 +594,58 @@ int nfs_write_need_commit(struct nfs_write_data *data) return 0; } -static inline -int nfs_reschedule_unstable_write(struct nfs_page *req, - struct nfs_write_data *data) +#endif + +static void nfs_write_completion(struct nfs_pgio_header *hdr) { - return 0; + struct nfs_commit_info cinfo; + unsigned long bytes = 0; + + if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) + goto out; + nfs_init_cinfo_from_inode(&cinfo, hdr->inode); + while (!list_empty(&hdr->pages)) { + struct nfs_page *req = nfs_list_entry(hdr->pages.next); + + bytes += req->wb_bytes; + nfs_list_remove_request(req); + if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && + (hdr->good_bytes < bytes)) { + nfs_set_pageerror(req->wb_page); + nfs_context_set_write_error(req->wb_context, hdr->error); + goto remove_req; + } + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) { + nfs_mark_request_dirty(req); + goto next; + } + if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { + memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf)); + nfs_mark_request_commit(req, hdr->lseg, &cinfo); + goto next; + } +remove_req: + nfs_inode_remove_request(req); +next: + nfs_unlock_request(req); + nfs_end_page_writeback(req->wb_page); + nfs_release_request(req); + } +out: + hdr->release(hdr); } -#endif #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) -static int -nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long +nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { - return nfsi->ncommit > 0; + return cinfo->mds->ncommit; } -/* i_lock held by caller */ -static int -nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, - spinlock_t *lock) +/* cinfo->lock held by caller */ +int +nfs_scan_commit_list(struct list_head *src, struct list_head *dst, + struct nfs_commit_info *cinfo, int max) { struct nfs_page *req, *tmp; int ret = 0; @@ -570,12 +653,13 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, list_for_each_entry_safe(req, tmp, src, wb_list) { if (!nfs_lock_request(req)) continue; - if (cond_resched_lock(lock)) + kref_get(&req->wb_kref); + if (cond_resched_lock(cinfo->lock)) list_safe_reset_next(req, tmp, wb_list); - nfs_request_remove_commit_list(req); + nfs_request_remove_commit_list(req, cinfo); nfs_list_add_request(req, dst); ret++; - if (ret == max) + if ((ret == max) && !cinfo->dreq) break; } return ret; @@ -584,37 +668,38 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max, /* * nfs_scan_commit - Scan an inode for commit requests * @inode: NFS inode to scan - * @dst: destination list + * @dst: mds destination list + * @cinfo: mds and ds lists of reqs ready to commit * * Moves requests from the inode's 'commit' request list. * The requests are *not* checked to ensure that they form a contiguous set. */ -static int -nfs_scan_commit(struct inode *inode, struct list_head *dst) +int +nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { - struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; - spin_lock(&inode->i_lock); - if (nfsi->ncommit > 0) { + spin_lock(cinfo->lock); + if (cinfo->mds->ncommit > 0) { const int max = INT_MAX; - ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max, - &inode->i_lock); - ret += pnfs_scan_commit_lists(inode, max - ret, - &inode->i_lock); + ret = nfs_scan_commit_list(&cinfo->mds->list, dst, + cinfo, max); + ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); } - spin_unlock(&inode->i_lock); + spin_unlock(cinfo->lock); return ret; } #else -static inline int nfs_need_commit(struct nfs_inode *nfsi) +static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { return 0; } -static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst) +int nfs_scan_commit(struct inode *inode, struct list_head *dst, + struct nfs_commit_info *cinfo) { return 0; } @@ -659,7 +744,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, || end < req->wb_offset) goto out_flushme; - if (nfs_lock_request_dontget(req)) + if (nfs_lock_request(req)) break; /* The request is locked, so wait and then retry */ @@ -682,7 +767,8 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, req->wb_bytes = rqend - req->wb_offset; out_unlock: spin_unlock(&inode->i_lock); - nfs_clear_request_commit(req); + if (req) + nfs_clear_request_commit(req); return req; out_flushme: spin_unlock(&inode->i_lock); @@ -728,7 +814,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page, nfs_grow_file(page, offset, count); nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes); nfs_mark_request_dirty(req); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); return 0; } @@ -765,10 +851,14 @@ int nfs_flush_incompatible(struct file *file, struct page *page) * the PageUptodate() flag. In this case, we will need to turn off * write optimisations that depend on the page contents being correct. */ -static int nfs_write_pageuptodate(struct page *page, struct inode *inode) +static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) { - return PageUptodate(page) && - !(NFS_I(inode)->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA)); + if (nfs_have_delegated_attributes(inode)) + goto out; + if (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE) + return false; +out: + return PageUptodate(page) != 0; } /* @@ -814,17 +904,6 @@ int nfs_updatepage(struct file *file, struct page *page, return status; } -static void nfs_writepage_release(struct nfs_page *req, - struct nfs_write_data *data) -{ - struct page *page = req->wb_page; - - if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data)) - nfs_inode_remove_request(req); - nfs_unlock_request(req); - nfs_end_page_writeback(page); -} - static int flush_task_priority(int how) { switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) { @@ -836,18 +915,18 @@ static int flush_task_priority(int how) return RPC_PRIORITY_NORMAL; } -int nfs_initiate_write(struct nfs_write_data *data, - struct rpc_clnt *clnt, +int nfs_initiate_write(struct rpc_clnt *clnt, + struct nfs_write_data *data, const struct rpc_call_ops *call_ops, - int how) + int how, int flags) { - struct inode *inode = data->inode; + struct inode *inode = data->header->inode; int priority = flush_task_priority(how); struct rpc_task *task; struct rpc_message msg = { .rpc_argp = &data->args, .rpc_resp = &data->res, - .rpc_cred = data->cred, + .rpc_cred = data->header->cred, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, @@ -856,7 +935,7 @@ int nfs_initiate_write(struct nfs_write_data *data, .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | flags, .priority = priority, }; int ret = 0; @@ -891,26 +970,21 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write); /* * Set up the argument/result storage required for the RPC call. */ -static void nfs_write_rpcsetup(struct nfs_page *req, - struct nfs_write_data *data, +static void nfs_write_rpcsetup(struct nfs_write_data *data, unsigned int count, unsigned int offset, - int how) + int how, struct nfs_commit_info *cinfo) { - struct inode *inode = req->wb_context->dentry->d_inode; + struct nfs_page *req = data->header->req; /* Set up the RPC argument and reply structs * NB: take care not to mess about with data->commit et al. */ - data->req = req; - data->inode = inode = req->wb_context->dentry->d_inode; - data->cred = req->wb_context->cred; - - data->args.fh = NFS_FH(inode); + data->args.fh = NFS_FH(data->header->inode); data->args.offset = req_offset(req) + offset; /* pnfs_set_layoutcommit needs this */ data->mds_offset = data->args.offset; data->args.pgbase = req->wb_pgbase + offset; - data->args.pages = data->pagevec; + data->args.pages = data->pages.pagevec; data->args.count = count; data->args.context = get_nfs_open_context(req->wb_context); data->args.lock_context = req->wb_lock_context; @@ -919,7 +993,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req, case 0: break; case FLUSH_COND_STABLE: - if (nfs_need_commit(NFS_I(inode))) + if (nfs_reqs_to_commit(cinfo)) break; default: data->args.stable = NFS_FILE_SYNC; @@ -935,9 +1009,9 @@ static int nfs_do_write(struct nfs_write_data *data, const struct rpc_call_ops *call_ops, int how) { - struct inode *inode = data->args.context->dentry->d_inode; + struct inode *inode = data->header->inode; - return nfs_initiate_write(data, NFS_CLIENT(inode), call_ops, how); + return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how, 0); } static int nfs_do_multiple_writes(struct list_head *head, @@ -950,7 +1024,7 @@ static int nfs_do_multiple_writes(struct list_head *head, while (!list_empty(head)) { int ret2; - data = list_entry(head->next, struct nfs_write_data, list); + data = list_first_entry(head, struct nfs_write_data, list); list_del_init(&data->list); ret2 = nfs_do_write(data, call_ops, how); @@ -966,31 +1040,60 @@ static int nfs_do_multiple_writes(struct list_head *head, */ static void nfs_redirty_request(struct nfs_page *req) { - struct page *page = req->wb_page; - nfs_mark_request_dirty(req); nfs_unlock_request(req); - nfs_end_page_writeback(page); + nfs_end_page_writeback(req->wb_page); + nfs_release_request(req); +} + +static void nfs_async_write_error(struct list_head *head) +{ + struct nfs_page *req; + + while (!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_redirty_request(req); + } +} + +static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { + .error_cleanup = nfs_async_write_error, + .completion = nfs_write_completion, +}; + +static void nfs_flush_error(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) +{ + set_bit(NFS_IOHDR_REDO, &hdr->flags); + while (!list_empty(&hdr->rpc_list)) { + struct nfs_write_data *data = list_first_entry(&hdr->rpc_list, + struct nfs_write_data, list); + list_del(&data->list); + nfs_writedata_release(data); + } + desc->pg_completion_ops->error_cleanup(&desc->pg_list); } /* * Generate multiple small requests to write out a single * contiguous dirty area on one page. */ -static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { - struct nfs_page *req = nfs_list_entry(desc->pg_list.next); + struct nfs_page *req = hdr->req; struct page *page = req->wb_page; struct nfs_write_data *data; size_t wsize = desc->pg_bsize, nbytes; unsigned int offset; int requests = 0; - int ret = 0; + struct nfs_commit_info cinfo; - nfs_list_remove_request(req); + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit || + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) || desc->pg_count > wsize)) desc->pg_ioflags &= ~FLUSH_COND_STABLE; @@ -1000,28 +1103,22 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head do { size_t len = min(nbytes, wsize); - data = nfs_writedata_alloc(1); - if (!data) - goto out_bad; - data->pagevec[0] = page; - nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags); - list_add(&data->list, res); + data = nfs_writedata_alloc(hdr, 1); + if (!data) { + nfs_flush_error(desc, hdr); + return -ENOMEM; + } + data->pages.pagevec[0] = page; + nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo); + list_add(&data->list, &hdr->rpc_list); requests++; nbytes -= len; offset += len; } while (nbytes != 0); - atomic_set(&req->wb_complete, requests); - desc->pg_rpc_callops = &nfs_write_partial_ops; - return ret; - -out_bad: - while (!list_empty(res)) { - data = list_entry(res->next, struct nfs_write_data, list); - list_del(&data->list); - nfs_writedata_free(data); - } - nfs_redirty_request(req); - return -ENOMEM; + nfs_list_remove_request(req); + nfs_list_add_request(req, &hdr->pages); + desc->pg_rpc_callops = &nfs_write_common_ops; + return 0; } /* @@ -1032,62 +1129,71 @@ out_bad: * This is the case if nfs_updatepage detects a conflicting request * that has been written but not committed. */ -static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *res) +static int nfs_flush_one(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { struct nfs_page *req; struct page **pages; struct nfs_write_data *data; struct list_head *head = &desc->pg_list; - int ret = 0; + struct nfs_commit_info cinfo; - data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base, - desc->pg_count)); + data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base, + desc->pg_count)); if (!data) { - while (!list_empty(head)) { - req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_redirty_request(req); - } - ret = -ENOMEM; - goto out; + nfs_flush_error(desc, hdr); + return -ENOMEM; } - pages = data->pagevec; + + nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq); + pages = data->pages.pagevec; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); - nfs_list_add_request(req, &data->pages); + nfs_list_add_request(req, &hdr->pages); *pages++ = req->wb_page; } - req = nfs_list_entry(data->pages.next); if ((desc->pg_ioflags & FLUSH_COND_STABLE) && - (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit)) + (desc->pg_moreio || nfs_reqs_to_commit(&cinfo))) desc->pg_ioflags &= ~FLUSH_COND_STABLE; /* Set up the argument struct */ - nfs_write_rpcsetup(req, data, desc->pg_count, 0, desc->pg_ioflags); - list_add(&data->list, res); - desc->pg_rpc_callops = &nfs_write_full_ops; -out: - return ret; + nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo); + list_add(&data->list, &hdr->rpc_list); + desc->pg_rpc_callops = &nfs_write_common_ops; + return 0; } -int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head) +int nfs_generic_flush(struct nfs_pageio_descriptor *desc, + struct nfs_pgio_header *hdr) { if (desc->pg_bsize < PAGE_CACHE_SIZE) - return nfs_flush_multi(desc, head); - return nfs_flush_one(desc, head); + return nfs_flush_multi(desc, hdr); + return nfs_flush_one(desc, hdr); } static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { - LIST_HEAD(head); + struct nfs_write_header *whdr; + struct nfs_pgio_header *hdr; int ret; - ret = nfs_generic_flush(desc, &head); + whdr = nfs_writehdr_alloc(); + if (!whdr) { + desc->pg_completion_ops->error_cleanup(&desc->pg_list); + return -ENOMEM; + } + hdr = &whdr->header; + nfs_pgheader_init(desc, hdr, nfs_writehdr_free); + atomic_inc(&hdr->refcnt); + ret = nfs_generic_flush(desc, hdr); if (ret == 0) - ret = nfs_do_multiple_writes(&head, desc->pg_rpc_callops, - desc->pg_ioflags); + ret = nfs_do_multiple_writes(&hdr->rpc_list, + desc->pg_rpc_callops, + desc->pg_ioflags); + if (atomic_dec_and_test(&hdr->refcnt)) + hdr->completion_ops->completion(hdr); return ret; } @@ -1097,9 +1203,10 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = { }; void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, + nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops, NFS_SERVER(inode)->wsize, ioflags); } @@ -1110,80 +1217,27 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); -static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags) +void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, + struct inode *inode, int ioflags, + const struct nfs_pgio_completion_ops *compl_ops) { - if (!pnfs_pageio_init_write(pgio, inode, ioflags)) - nfs_pageio_init_write_mds(pgio, inode, ioflags); + if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops)) + nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops); } -/* - * Handle a write reply that flushed part of a page. - */ -static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata) +void nfs_write_prepare(struct rpc_task *task, void *calldata) { - struct nfs_write_data *data = calldata; - - dprintk("NFS: %5u write(%s/%lld %d@%lld)", - task->tk_pid, - data->req->wb_context->dentry->d_inode->i_sb->s_id, - (long long) - NFS_FILEID(data->req->wb_context->dentry->d_inode), - data->req->wb_bytes, (long long)req_offset(data->req)); - - nfs_writeback_done(task, data); + struct nfs_write_data *data = calldata; + NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data); } -static void nfs_writeback_release_partial(void *calldata) +void nfs_commit_prepare(struct rpc_task *task, void *calldata) { - struct nfs_write_data *data = calldata; - struct nfs_page *req = data->req; - struct page *page = req->wb_page; - int status = data->task.tk_status; - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto out; - } - - if (nfs_write_need_commit(data)) { - struct inode *inode = page->mapping->host; - - spin_lock(&inode->i_lock); - if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) { - /* Do nothing we need to resend the writes */ - } else if (!test_and_set_bit(PG_NEED_COMMIT, &req->wb_flags)) { - memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - dprintk(" defer commit\n"); - } else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) { - set_bit(PG_NEED_RESCHED, &req->wb_flags); - clear_bit(PG_NEED_COMMIT, &req->wb_flags); - dprintk(" server reboot detected\n"); - } - spin_unlock(&inode->i_lock); - } else - dprintk(" OK\n"); - -out: - if (atomic_dec_and_test(&req->wb_complete)) - nfs_writepage_release(req, data); - nfs_writedata_release(calldata); -} + struct nfs_commit_data *data = calldata; -void nfs_write_prepare(struct rpc_task *task, void *calldata) -{ - struct nfs_write_data *data = calldata; - NFS_PROTO(data->inode)->write_rpc_prepare(task, data); + NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); } -static const struct rpc_call_ops nfs_write_partial_ops = { - .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_partial, - .rpc_release = nfs_writeback_release_partial, -}; - /* * Handle a write reply that flushes a whole page. * @@ -1191,59 +1245,36 @@ static const struct rpc_call_ops nfs_write_partial_ops = { * writebacks since the page->count is kept > 1 for as long * as the page has a write request pending. */ -static void nfs_writeback_done_full(struct rpc_task *task, void *calldata) +static void nfs_writeback_done_common(struct rpc_task *task, void *calldata) { struct nfs_write_data *data = calldata; nfs_writeback_done(task, data); } -static void nfs_writeback_release_full(void *calldata) +static void nfs_writeback_release_common(void *calldata) { struct nfs_write_data *data = calldata; + struct nfs_pgio_header *hdr = data->header; int status = data->task.tk_status; - /* Update attributes as result of writeback. */ - while (!list_empty(&data->pages)) { - struct nfs_page *req = nfs_list_entry(data->pages.next); - struct page *page = req->wb_page; - - nfs_list_remove_request(req); - - dprintk("NFS: %5u write (%s/%lld %d@%lld)", - data->task.tk_pid, - req->wb_context->dentry->d_inode->i_sb->s_id, - (long long)NFS_FILEID(req->wb_context->dentry->d_inode), - req->wb_bytes, - (long long)req_offset(req)); - - if (status < 0) { - nfs_set_pageerror(page); - nfs_context_set_write_error(req->wb_context, status); - dprintk(", error = %d\n", status); - goto remove_request; - } - - if (nfs_write_need_commit(data)) { - memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf)); - nfs_mark_request_commit(req, data->lseg); - dprintk(" marked for commit\n"); - goto next; - } - dprintk(" OK\n"); -remove_request: - nfs_inode_remove_request(req); - next: - nfs_unlock_request(req); - nfs_end_page_writeback(page); + if ((status >= 0) && nfs_write_need_commit(data)) { + spin_lock(&hdr->lock); + if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) + ; /* Do nothing */ + else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) + memcpy(hdr->verf, &data->verf, sizeof(*hdr->verf)); + else if (memcmp(hdr->verf, &data->verf, sizeof(*hdr->verf))) + set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags); + spin_unlock(&hdr->lock); } - nfs_writedata_release(calldata); + nfs_writedata_release(data); } -static const struct rpc_call_ops nfs_write_full_ops = { +static const struct rpc_call_ops nfs_write_common_ops = { .rpc_call_prepare = nfs_write_prepare, - .rpc_call_done = nfs_writeback_done_full, - .rpc_release = nfs_writeback_release_full, + .rpc_call_done = nfs_writeback_done_common, + .rpc_release = nfs_writeback_release_common, }; @@ -1254,6 +1285,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) { struct nfs_writeargs *argp = &data->args; struct nfs_writeres *resp = &data->res; + struct inode *inode = data->header->inode; int status; dprintk("NFS: %5u nfs_writeback_done (status %d)\n", @@ -1266,10 +1298,10 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) * another writer had changed the file, but some applications * depend on tighter cache coherency when writing. */ - status = NFS_PROTO(data->inode)->write_done(task, data); + status = NFS_PROTO(inode)->write_done(task, data); if (status != 0) return; - nfs_add_stats(data->inode, NFSIOS_SERVERWRITTENBYTES, resp->count); + nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count); #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) if (resp->verf->committed < argp->stable && task->tk_status >= 0) { @@ -1287,46 +1319,47 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) if (time_before(complain, jiffies)) { dprintk("NFS: faulty NFS server %s:" " (committed = %d) != (stable = %d)\n", - NFS_SERVER(data->inode)->nfs_client->cl_hostname, + NFS_SERVER(inode)->nfs_client->cl_hostname, resp->verf->committed, argp->stable); complain = jiffies + 300 * HZ; } } #endif - /* Is this a short write? */ - if (task->tk_status >= 0 && resp->count < argp->count) { + if (task->tk_status < 0) + nfs_set_pgio_error(data->header, task->tk_status, argp->offset); + else if (resp->count < argp->count) { static unsigned long complain; - nfs_inc_stats(data->inode, NFSIOS_SHORTWRITE); + /* This a short write! */ + nfs_inc_stats(inode, NFSIOS_SHORTWRITE); /* Has the server at least made some progress? */ - if (resp->count != 0) { - /* Was this an NFSv2 write or an NFSv3 stable write? */ - if (resp->verf->committed != NFS_UNSTABLE) { - /* Resend from where the server left off */ - data->mds_offset += resp->count; - argp->offset += resp->count; - argp->pgbase += resp->count; - argp->count -= resp->count; - } else { - /* Resend as a stable write in order to avoid - * headaches in the case of a server crash. - */ - argp->stable = NFS_FILE_SYNC; + if (resp->count == 0) { + if (time_before(complain, jiffies)) { + printk(KERN_WARNING + "NFS: Server wrote zero bytes, expected %u.\n", + argp->count); + complain = jiffies + 300 * HZ; } - rpc_restart_call_prepare(task); + nfs_set_pgio_error(data->header, -EIO, argp->offset); + task->tk_status = -EIO; return; } - if (time_before(complain, jiffies)) { - printk(KERN_WARNING - "NFS: Server wrote zero bytes, expected %u.\n", - argp->count); - complain = jiffies + 300 * HZ; + /* Was this an NFSv2 write or an NFSv3 stable write? */ + if (resp->verf->committed != NFS_UNSTABLE) { + /* Resend from where the server left off */ + data->mds_offset += resp->count; + argp->offset += resp->count; + argp->pgbase += resp->count; + argp->count -= resp->count; + } else { + /* Resend as a stable write in order to avoid + * headaches in the case of a server crash. + */ + argp->stable = NFS_FILE_SYNC; } - /* Can't do anything about it except throw an error. */ - task->tk_status = -EIO; + rpc_restart_call_prepare(task); } - return; } @@ -1346,26 +1379,23 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) return (ret < 0) ? ret : 1; } -void nfs_commit_clear_lock(struct nfs_inode *nfsi) +static void nfs_commit_clear_lock(struct nfs_inode *nfsi) { clear_bit(NFS_INO_COMMIT, &nfsi->flags); smp_mb__after_clear_bit(); wake_up_bit(&nfsi->flags, NFS_INO_COMMIT); } -EXPORT_SYMBOL_GPL(nfs_commit_clear_lock); -void nfs_commitdata_release(void *data) +void nfs_commitdata_release(struct nfs_commit_data *data) { - struct nfs_write_data *wdata = data; - - put_nfs_open_context(wdata->args.context); - nfs_commit_free(wdata); + put_nfs_open_context(data->context); + nfs_commit_free(data); } EXPORT_SYMBOL_GPL(nfs_commitdata_release); -int nfs_initiate_commit(struct nfs_write_data *data, struct rpc_clnt *clnt, +int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, const struct rpc_call_ops *call_ops, - int how) + int how, int flags) { struct rpc_task *task; int priority = flush_task_priority(how); @@ -1381,7 +1411,7 @@ int nfs_initiate_commit(struct nfs_write_data *data, struct rpc_clnt *clnt, .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC, + .flags = RPC_TASK_ASYNC | flags, .priority = priority, }; /* Set up the initial task struct. */ @@ -1402,9 +1432,10 @@ EXPORT_SYMBOL_GPL(nfs_initiate_commit); /* * Set up the argument/result storage required for the RPC call. */ -void nfs_init_commit(struct nfs_write_data *data, - struct list_head *head, - struct pnfs_layout_segment *lseg) +void nfs_init_commit(struct nfs_commit_data *data, + struct list_head *head, + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *first = nfs_list_entry(head->next); struct inode *inode = first->wb_context->dentry->d_inode; @@ -1418,13 +1449,14 @@ void nfs_init_commit(struct nfs_write_data *data, data->cred = first->wb_context->cred; data->lseg = lseg; /* reference transferred */ data->mds_ops = &nfs_commit_ops; + data->completion_ops = cinfo->completion_ops; + data->dreq = cinfo->dreq; data->args.fh = NFS_FH(data->inode); /* Note: we always request a commit of the entire inode */ data->args.offset = 0; data->args.count = 0; - data->args.context = get_nfs_open_context(first->wb_context); - data->res.count = 0; + data->context = get_nfs_open_context(first->wb_context); data->res.fattr = &data->fattr; data->res.verf = &data->verf; nfs_fattr_init(&data->fattr); @@ -1432,18 +1464,21 @@ void nfs_init_commit(struct nfs_write_data *data, EXPORT_SYMBOL_GPL(nfs_init_commit); void nfs_retry_commit(struct list_head *page_list, - struct pnfs_layout_segment *lseg) + struct pnfs_layout_segment *lseg, + struct nfs_commit_info *cinfo) { struct nfs_page *req; while (!list_empty(page_list)) { req = nfs_list_entry(page_list->next); nfs_list_remove_request(req); - nfs_mark_request_commit(req, lseg); - dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - dec_bdi_stat(req->wb_page->mapping->backing_dev_info, - BDI_RECLAIMABLE); - nfs_unlock_request(req); + nfs_mark_request_commit(req, lseg, cinfo); + if (!cinfo->dreq) { + dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); + dec_bdi_stat(req->wb_page->mapping->backing_dev_info, + BDI_RECLAIMABLE); + } + nfs_unlock_and_release_request(req); } } EXPORT_SYMBOL_GPL(nfs_retry_commit); @@ -1452,9 +1487,10 @@ EXPORT_SYMBOL_GPL(nfs_retry_commit); * Commit dirty pages */ static int -nfs_commit_list(struct inode *inode, struct list_head *head, int how) +nfs_commit_list(struct inode *inode, struct list_head *head, int how, + struct nfs_commit_info *cinfo) { - struct nfs_write_data *data; + struct nfs_commit_data *data; data = nfs_commitdata_alloc(); @@ -1462,11 +1498,13 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how) goto out_bad; /* Set up the argument struct */ - nfs_init_commit(data, head, NULL); - return nfs_initiate_commit(data, NFS_CLIENT(inode), data->mds_ops, how); + nfs_init_commit(data, head, NULL, cinfo); + atomic_inc(&cinfo->mds->rpcs_out); + return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops, + how, 0); out_bad: - nfs_retry_commit(head, NULL); - nfs_commit_clear_lock(NFS_I(inode)); + nfs_retry_commit(head, NULL, cinfo); + cinfo->completion_ops->error_cleanup(NFS_I(inode)); return -ENOMEM; } @@ -1475,7 +1513,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how) */ static void nfs_commit_done(struct rpc_task *task, void *calldata) { - struct nfs_write_data *data = calldata; + struct nfs_commit_data *data = calldata; dprintk("NFS: %5u nfs_commit_done (status %d)\n", task->tk_pid, task->tk_status); @@ -1484,10 +1522,11 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata) NFS_PROTO(data->inode)->commit_done(task, data); } -void nfs_commit_release_pages(struct nfs_write_data *data) +static void nfs_commit_release_pages(struct nfs_commit_data *data) { struct nfs_page *req; int status = data->task.tk_status; + struct nfs_commit_info cinfo; while (!list_empty(&data->pages)) { req = nfs_list_entry(data->pages.next); @@ -1518,42 +1557,59 @@ void nfs_commit_release_pages(struct nfs_write_data *data) dprintk(" mismatch\n"); nfs_mark_request_dirty(req); next: - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); } + nfs_init_cinfo(&cinfo, data->inode, data->dreq); + if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + nfs_commit_clear_lock(NFS_I(data->inode)); } -EXPORT_SYMBOL_GPL(nfs_commit_release_pages); static void nfs_commit_release(void *calldata) { - struct nfs_write_data *data = calldata; + struct nfs_commit_data *data = calldata; - nfs_commit_release_pages(data); - nfs_commit_clear_lock(NFS_I(data->inode)); + data->completion_ops->completion(data); nfs_commitdata_release(calldata); } static const struct rpc_call_ops nfs_commit_ops = { - .rpc_call_prepare = nfs_write_prepare, + .rpc_call_prepare = nfs_commit_prepare, .rpc_call_done = nfs_commit_done, .rpc_release = nfs_commit_release, }; +static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { + .completion = nfs_commit_release_pages, + .error_cleanup = nfs_commit_clear_lock, +}; + +int nfs_generic_commit_list(struct inode *inode, struct list_head *head, + int how, struct nfs_commit_info *cinfo) +{ + int status; + + status = pnfs_commit_list(inode, head, how, cinfo); + if (status == PNFS_NOT_ATTEMPTED) + status = nfs_commit_list(inode, head, how, cinfo); + return status; +} + int nfs_commit_inode(struct inode *inode, int how) { LIST_HEAD(head); + struct nfs_commit_info cinfo; int may_wait = how & FLUSH_SYNC; int res; res = nfs_commit_set_lock(NFS_I(inode), may_wait); if (res <= 0) goto out_mark_dirty; - res = nfs_scan_commit(inode, &head); + nfs_init_cinfo_from_inode(&cinfo, inode); + res = nfs_scan_commit(inode, &head, &cinfo); if (res) { int error; - error = pnfs_commit_list(inode, &head, how); - if (error == PNFS_NOT_ATTEMPTED) - error = nfs_commit_list(inode, &head, how); + error = nfs_generic_commit_list(inode, &head, how, &cinfo); if (error < 0) return error; if (!may_wait) @@ -1584,14 +1640,14 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int ret = 0; /* no commits means nothing needs to be done */ - if (!nfsi->ncommit) + if (!nfsi->commit_info.ncommit) return ret; if (wbc->sync_mode == WB_SYNC_NONE) { /* Don't commit yet if this is a non-blocking flush and there * are a lot of outstanding writes for this mapping. */ - if (nfsi->ncommit <= (nfsi->npages >> 1)) + if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1)) goto out_mark_dirty; /* don't wait for the COMMIT response */ @@ -1664,7 +1720,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) req = nfs_page_find_request(page); if (req == NULL) break; - if (nfs_lock_request_dontget(req)) { + if (nfs_lock_request(req)) { nfs_clear_request_commit(req); nfs_inode_remove_request(req); /* @@ -1672,7 +1728,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) * page as being dirty */ cancel_dirty_page(page, PAGE_CACHE_SIZE); - nfs_unlock_request(req); + nfs_unlock_and_release_request(req); break; } ret = nfs_wait_on_request(req); @@ -1741,7 +1797,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", - sizeof(struct nfs_write_data), + sizeof(struct nfs_write_header), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_wdata_cachep == NULL) @@ -1752,6 +1808,13 @@ int __init nfs_init_writepagecache(void) if (nfs_wdata_mempool == NULL) return -ENOMEM; + nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", + sizeof(struct nfs_commit_data), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (nfs_cdata_cachep == NULL) + return -ENOMEM; + nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, nfs_wdata_cachep); if (nfs_commit_mempool == NULL) diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 79717a40dab..34a10d78b83 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -1,6 +1,7 @@ /* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */ #include <linux/sched.h> +#include <linux/user_namespace.h> #include "nfsd.h" #include "auth.h" @@ -10,7 +11,7 @@ int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors; for (f = exp->ex_flavors; f < end; f++) { - if (f->pseudoflavor == rqstp->rq_flavor) + if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) return f->flags; } return exp->ex_flags; @@ -56,8 +57,8 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) goto oom; for (i = 0; i < rqgi->ngroups; i++) { - if (!GROUP_AT(rqgi, i)) - GROUP_AT(gi, i) = exp->ex_anon_gid; + if (gid_eq(GLOBAL_ROOT_GID, GROUP_AT(rqgi, i))) + GROUP_AT(gi, i) = make_kgid(&init_user_ns, exp->ex_anon_gid); else GROUP_AT(gi, i) = GROUP_AT(rqgi, i); } diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 8e9689abbc0..ba233499b9a 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -15,11 +15,13 @@ #include <linux/namei.h> #include <linux/module.h> #include <linux/exportfs.h> +#include <linux/sunrpc/svc_xprt.h> #include <net/ipv6.h> #include "nfsd.h" #include "nfsfh.h" +#include "netns.h" #define NFSDDBG_FACILITY NFSDDBG_EXPORT @@ -38,7 +40,6 @@ typedef struct svc_export svc_export; #define EXPKEY_HASHBITS 8 #define EXPKEY_HASHMAX (1 << EXPKEY_HASHBITS) #define EXPKEY_HASHMASK (EXPKEY_HASHMAX -1) -static struct cache_head *expkey_table[EXPKEY_HASHMAX]; static void expkey_put(struct kref *ref) { @@ -71,9 +72,9 @@ static int expkey_upcall(struct cache_detail *cd, struct cache_head *h) return sunrpc_cache_pipe_upcall(cd, h, expkey_request); } -static struct svc_expkey *svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old); -static struct svc_expkey *svc_expkey_lookup(struct svc_expkey *); -static struct cache_detail svc_expkey_cache; +static struct svc_expkey *svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, + struct svc_expkey *old); +static struct svc_expkey *svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *); static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) { @@ -131,7 +132,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) key.ek_fsidtype = fsidtype; memcpy(key.ek_fsid, buf, len); - ek = svc_expkey_lookup(&key); + ek = svc_expkey_lookup(cd, &key); err = -ENOMEM; if (!ek) goto out; @@ -145,7 +146,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) err = 0; if (len == 0) { set_bit(CACHE_NEGATIVE, &key.h.flags); - ek = svc_expkey_update(&key, ek); + ek = svc_expkey_update(cd, &key, ek); if (!ek) err = -ENOMEM; } else { @@ -155,7 +156,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) dprintk("Found the path %s\n", buf); - ek = svc_expkey_update(&key, ek); + ek = svc_expkey_update(cd, &key, ek); if (!ek) err = -ENOMEM; path_put(&key.ek_path); @@ -163,7 +164,7 @@ static int expkey_parse(struct cache_detail *cd, char *mesg, int mlen) cache_flush(); out: if (ek) - cache_put(&ek->h, &svc_expkey_cache); + cache_put(&ek->h, cd); if (dom) auth_domain_put(dom); kfree(buf); @@ -239,10 +240,9 @@ static struct cache_head *expkey_alloc(void) return NULL; } -static struct cache_detail svc_expkey_cache = { +static struct cache_detail svc_expkey_cache_template = { .owner = THIS_MODULE, .hash_size = EXPKEY_HASHMAX, - .hash_table = expkey_table, .name = "nfsd.fh", .cache_put = expkey_put, .cache_upcall = expkey_upcall, @@ -268,13 +268,12 @@ svc_expkey_hash(struct svc_expkey *item) } static struct svc_expkey * -svc_expkey_lookup(struct svc_expkey *item) +svc_expkey_lookup(struct cache_detail *cd, struct svc_expkey *item) { struct cache_head *ch; int hash = svc_expkey_hash(item); - ch = sunrpc_cache_lookup(&svc_expkey_cache, &item->h, - hash); + ch = sunrpc_cache_lookup(cd, &item->h, hash); if (ch) return container_of(ch, struct svc_expkey, h); else @@ -282,13 +281,13 @@ svc_expkey_lookup(struct svc_expkey *item) } static struct svc_expkey * -svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old) +svc_expkey_update(struct cache_detail *cd, struct svc_expkey *new, + struct svc_expkey *old) { struct cache_head *ch; int hash = svc_expkey_hash(new); - ch = sunrpc_cache_update(&svc_expkey_cache, &new->h, - &old->h, hash); + ch = sunrpc_cache_update(cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct svc_expkey, h); else @@ -299,8 +298,6 @@ svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old) #define EXPORT_HASHBITS 8 #define EXPORT_HASHMAX (1<< EXPORT_HASHBITS) -static struct cache_head *export_table[EXPORT_HASHMAX]; - static void nfsd4_fslocs_free(struct nfsd4_fs_locations *fsloc) { int i; @@ -525,6 +522,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen) goto out1; exp.ex_client = dom; + exp.cd = cd; /* expiry */ err = -EINVAL; @@ -672,6 +670,7 @@ static void svc_export_init(struct cache_head *cnew, struct cache_head *citem) new->ex_fslocs.locations = NULL; new->ex_fslocs.locations_count = 0; new->ex_fslocs.migrated = 0; + new->cd = item->cd; } static void export_update(struct cache_head *cnew, struct cache_head *citem) @@ -707,10 +706,9 @@ static struct cache_head *svc_export_alloc(void) return NULL; } -struct cache_detail svc_export_cache = { +static struct cache_detail svc_export_cache_template = { .owner = THIS_MODULE, .hash_size = EXPORT_HASHMAX, - .hash_table = export_table, .name = "nfsd.export", .cache_put = svc_export_put, .cache_upcall = svc_export_upcall, @@ -739,8 +737,7 @@ svc_export_lookup(struct svc_export *exp) struct cache_head *ch; int hash = svc_export_hash(exp); - ch = sunrpc_cache_lookup(&svc_export_cache, &exp->h, - hash); + ch = sunrpc_cache_lookup(exp->cd, &exp->h, hash); if (ch) return container_of(ch, struct svc_export, h); else @@ -753,9 +750,7 @@ svc_export_update(struct svc_export *new, struct svc_export *old) struct cache_head *ch; int hash = svc_export_hash(old); - ch = sunrpc_cache_update(&svc_export_cache, &new->h, - &old->h, - hash); + ch = sunrpc_cache_update(old->cd, &new->h, &old->h, hash); if (ch) return container_of(ch, struct svc_export, h); else @@ -764,7 +759,8 @@ svc_export_update(struct svc_export *new, struct svc_export *old) static struct svc_expkey * -exp_find_key(svc_client *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) +exp_find_key(struct cache_detail *cd, svc_client *clp, int fsid_type, + u32 *fsidv, struct cache_req *reqp) { struct svc_expkey key, *ek; int err; @@ -776,18 +772,18 @@ exp_find_key(svc_client *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) key.ek_fsidtype = fsid_type; memcpy(key.ek_fsid, fsidv, key_len(fsid_type)); - ek = svc_expkey_lookup(&key); + ek = svc_expkey_lookup(cd, &key); if (ek == NULL) return ERR_PTR(-ENOMEM); - err = cache_check(&svc_expkey_cache, &ek->h, reqp); + err = cache_check(cd, &ek->h, reqp); if (err) return ERR_PTR(err); return ek; } -static svc_export *exp_get_by_name(svc_client *clp, const struct path *path, - struct cache_req *reqp) +static svc_export *exp_get_by_name(struct cache_detail *cd, svc_client *clp, + const struct path *path, struct cache_req *reqp) { struct svc_export *exp, key; int err; @@ -797,11 +793,12 @@ static svc_export *exp_get_by_name(svc_client *clp, const struct path *path, key.ex_client = clp; key.ex_path = *path; + key.cd = cd; exp = svc_export_lookup(&key); if (exp == NULL) return ERR_PTR(-ENOMEM); - err = cache_check(&svc_export_cache, &exp->h, reqp); + err = cache_check(cd, &exp->h, reqp); if (err) return ERR_PTR(err); return exp; @@ -810,16 +807,17 @@ static svc_export *exp_get_by_name(svc_client *clp, const struct path *path, /* * Find the export entry for a given dentry. */ -static struct svc_export *exp_parent(svc_client *clp, struct path *path) +static struct svc_export *exp_parent(struct cache_detail *cd, svc_client *clp, + struct path *path) { struct dentry *saved = dget(path->dentry); - svc_export *exp = exp_get_by_name(clp, path, NULL); + svc_export *exp = exp_get_by_name(cd, clp, path, NULL); while (PTR_ERR(exp) == -ENOENT && !IS_ROOT(path->dentry)) { struct dentry *parent = dget_parent(path->dentry); dput(path->dentry); path->dentry = parent; - exp = exp_get_by_name(clp, path, NULL); + exp = exp_get_by_name(cd, clp, path, NULL); } dput(path->dentry); path->dentry = saved; @@ -834,13 +832,16 @@ static struct svc_export *exp_parent(svc_client *clp, struct path *path) * since its harder to fool a kernel module than a user space program. */ int -exp_rootfh(svc_client *clp, char *name, struct knfsd_fh *f, int maxsize) +exp_rootfh(struct net *net, svc_client *clp, char *name, + struct knfsd_fh *f, int maxsize) { struct svc_export *exp; struct path path; struct inode *inode; struct svc_fh fh; int err; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct cache_detail *cd = nn->svc_export_cache; err = -EPERM; /* NB: we probably ought to check that it's NUL-terminated */ @@ -853,7 +854,7 @@ exp_rootfh(svc_client *clp, char *name, struct knfsd_fh *f, int maxsize) dprintk("nfsd: exp_rootfh(%s [%p] %s:%s/%ld)\n", name, path.dentry, clp->name, inode->i_sb->s_id, inode->i_ino); - exp = exp_parent(clp, &path); + exp = exp_parent(cd, clp, &path); if (IS_ERR(exp)) { err = PTR_ERR(exp); goto out; @@ -875,16 +876,18 @@ out: return err; } -static struct svc_export *exp_find(struct auth_domain *clp, int fsid_type, +static struct svc_export *exp_find(struct cache_detail *cd, + struct auth_domain *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp) { struct svc_export *exp; - struct svc_expkey *ek = exp_find_key(clp, fsid_type, fsidv, reqp); + struct nfsd_net *nn = net_generic(cd->net, nfsd_net_id); + struct svc_expkey *ek = exp_find_key(nn->svc_expkey_cache, clp, fsid_type, fsidv, reqp); if (IS_ERR(ek)) return ERR_CAST(ek); - exp = exp_get_by_name(clp, &ek->ek_path, reqp); - cache_put(&ek->h, &svc_expkey_cache); + exp = exp_get_by_name(cd, clp, &ek->ek_path, reqp); + cache_put(&ek->h, nn->svc_expkey_cache); if (IS_ERR(exp)) return ERR_CAST(exp); @@ -901,13 +904,13 @@ __be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp) return 0; /* ip-address based client; check sec= export option: */ for (f = exp->ex_flavors; f < end; f++) { - if (f->pseudoflavor == rqstp->rq_flavor) + if (f->pseudoflavor == rqstp->rq_cred.cr_flavor) return 0; } /* defaults in absence of sec= options: */ if (exp->ex_nflavors == 0) { - if (rqstp->rq_flavor == RPC_AUTH_NULL || - rqstp->rq_flavor == RPC_AUTH_UNIX) + if (rqstp->rq_cred.cr_flavor == RPC_AUTH_NULL || + rqstp->rq_cred.cr_flavor == RPC_AUTH_UNIX) return 0; } return nfserr_wrongsec; @@ -926,12 +929,14 @@ struct svc_export * rqst_exp_get_by_name(struct svc_rqst *rqstp, struct path *path) { struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); + struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id); + struct cache_detail *cd = nn->svc_export_cache; if (rqstp->rq_client == NULL) goto gss; /* First try the auth_unix client: */ - exp = exp_get_by_name(rqstp->rq_client, path, &rqstp->rq_chandle); + exp = exp_get_by_name(cd, rqstp->rq_client, path, &rqstp->rq_chandle); if (PTR_ERR(exp) == -ENOENT) goto gss; if (IS_ERR(exp)) @@ -943,7 +948,7 @@ gss: /* Otherwise, try falling back on gss client */ if (rqstp->rq_gssclient == NULL) return exp; - gssexp = exp_get_by_name(rqstp->rq_gssclient, path, &rqstp->rq_chandle); + gssexp = exp_get_by_name(cd, rqstp->rq_gssclient, path, &rqstp->rq_chandle); if (PTR_ERR(gssexp) == -ENOENT) return exp; if (!IS_ERR(exp)) @@ -955,12 +960,15 @@ struct svc_export * rqst_exp_find(struct svc_rqst *rqstp, int fsid_type, u32 *fsidv) { struct svc_export *gssexp, *exp = ERR_PTR(-ENOENT); + struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id); + struct cache_detail *cd = nn->svc_export_cache; if (rqstp->rq_client == NULL) goto gss; /* First try the auth_unix client: */ - exp = exp_find(rqstp->rq_client, fsid_type, fsidv, &rqstp->rq_chandle); + exp = exp_find(cd, rqstp->rq_client, fsid_type, + fsidv, &rqstp->rq_chandle); if (PTR_ERR(exp) == -ENOENT) goto gss; if (IS_ERR(exp)) @@ -972,7 +980,7 @@ gss: /* Otherwise, try falling back on gss client */ if (rqstp->rq_gssclient == NULL) return exp; - gssexp = exp_find(rqstp->rq_gssclient, fsid_type, fsidv, + gssexp = exp_find(cd, rqstp->rq_gssclient, fsid_type, fsidv, &rqstp->rq_chandle); if (PTR_ERR(gssexp) == -ENOENT) return exp; @@ -1029,13 +1037,15 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp) /* Iterator */ static void *e_start(struct seq_file *m, loff_t *pos) - __acquires(svc_export_cache.hash_lock) + __acquires(((struct cache_detail *)m->private)->hash_lock) { loff_t n = *pos; unsigned hash, export; struct cache_head *ch; - - read_lock(&svc_export_cache.hash_lock); + struct cache_detail *cd = m->private; + struct cache_head **export_table = cd->hash_table; + + read_lock(&cd->hash_lock); if (!n--) return SEQ_START_TOKEN; hash = n >> 32; @@ -1060,6 +1070,8 @@ static void *e_next(struct seq_file *m, void *p, loff_t *pos) { struct cache_head *ch = p; int hash = (*pos >> 32); + struct cache_detail *cd = m->private; + struct cache_head **export_table = cd->hash_table; if (p == SEQ_START_TOKEN) hash = 0; @@ -1082,9 +1094,11 @@ static void *e_next(struct seq_file *m, void *p, loff_t *pos) } static void e_stop(struct seq_file *m, void *p) - __releases(svc_export_cache.hash_lock) + __releases(((struct cache_detail *)m->private)->hash_lock) { - read_unlock(&svc_export_cache.hash_lock); + struct cache_detail *cd = m->private; + + read_unlock(&cd->hash_lock); } static struct flags { @@ -1195,6 +1209,7 @@ static int e_show(struct seq_file *m, void *p) { struct cache_head *cp = p; struct svc_export *exp = container_of(cp, struct svc_export, h); + struct cache_detail *cd = m->private; if (p == SEQ_START_TOKEN) { seq_puts(m, "# Version 1.1\n"); @@ -1203,10 +1218,10 @@ static int e_show(struct seq_file *m, void *p) } cache_get(&exp->h); - if (cache_check(&svc_export_cache, &exp->h, NULL)) + if (cache_check(cd, &exp->h, NULL)) return 0; - cache_put(&exp->h, &svc_export_cache); - return svc_export_show(m, &svc_export_cache, cp); + exp_put(exp); + return svc_export_show(m, cd, cp); } const struct seq_operations nfs_exports_op = { @@ -1216,48 +1231,70 @@ const struct seq_operations nfs_exports_op = { .show = e_show, }; - /* * Initialize the exports module. */ int -nfsd_export_init(void) +nfsd_export_init(struct net *net) { int rv; - dprintk("nfsd: initializing export module.\n"); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + dprintk("nfsd: initializing export module (net: %p).\n", net); - rv = cache_register_net(&svc_export_cache, &init_net); + nn->svc_export_cache = cache_create_net(&svc_export_cache_template, net); + if (IS_ERR(nn->svc_export_cache)) + return PTR_ERR(nn->svc_export_cache); + rv = cache_register_net(nn->svc_export_cache, net); if (rv) - return rv; - rv = cache_register_net(&svc_expkey_cache, &init_net); + goto destroy_export_cache; + + nn->svc_expkey_cache = cache_create_net(&svc_expkey_cache_template, net); + if (IS_ERR(nn->svc_expkey_cache)) { + rv = PTR_ERR(nn->svc_expkey_cache); + goto unregister_export_cache; + } + rv = cache_register_net(nn->svc_expkey_cache, net); if (rv) - cache_unregister_net(&svc_export_cache, &init_net); - return rv; + goto destroy_expkey_cache; + return 0; +destroy_expkey_cache: + cache_destroy_net(nn->svc_expkey_cache, net); +unregister_export_cache: + cache_unregister_net(nn->svc_export_cache, net); +destroy_export_cache: + cache_destroy_net(nn->svc_export_cache, net); + return rv; } /* * Flush exports table - called when last nfsd thread is killed */ void -nfsd_export_flush(void) +nfsd_export_flush(struct net *net) { - cache_purge(&svc_expkey_cache); - cache_purge(&svc_export_cache); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + cache_purge(nn->svc_expkey_cache); + cache_purge(nn->svc_export_cache); } /* * Shutdown the exports module. */ void -nfsd_export_shutdown(void) +nfsd_export_shutdown(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - dprintk("nfsd: shutting down export module.\n"); + dprintk("nfsd: shutting down export module (net: %p).\n", net); - cache_unregister_net(&svc_expkey_cache, &init_net); - cache_unregister_net(&svc_export_cache, &init_net); - svcauth_unix_purge(); + cache_unregister_net(nn->svc_expkey_cache, net); + cache_unregister_net(nn->svc_export_cache, net); + cache_destroy_net(nn->svc_expkey_cache, net); + cache_destroy_net(nn->svc_export_cache, net); + svcauth_unix_purge(net); - dprintk("nfsd: export shutdown complete.\n"); + dprintk("nfsd: export shutdown complete (net: %p).\n", net); } diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c index 9559ce46873..e6c38159622 100644 --- a/fs/nfsd/fault_inject.c +++ b/fs/nfsd/fault_inject.c @@ -58,6 +58,7 @@ static int nfsd_inject_set(void *op_ptr, u64 val) static int nfsd_inject_get(void *data, u64 *val) { + *val = 0; return 0; } diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h index 2f3be132153..9d513efc01b 100644 --- a/fs/nfsd/idmap.h +++ b/fs/nfsd/idmap.h @@ -42,14 +42,14 @@ #define IDMAP_NAMESZ 128 #ifdef CONFIG_NFSD_V4 -int nfsd_idmap_init(void); -void nfsd_idmap_shutdown(void); +int nfsd_idmap_init(struct net *); +void nfsd_idmap_shutdown(struct net *); #else -static inline int nfsd_idmap_init(void) +static inline int nfsd_idmap_init(struct net *net) { return 0; } -static inline void nfsd_idmap_shutdown(void) +static inline void nfsd_idmap_shutdown(struct net *net) { } #endif diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 12e0cff435b..39365636b24 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -28,6 +28,12 @@ struct cld_net; struct nfsd_net { struct cld_net *cld_net; + + struct cache_detail *svc_expkey_cache; + struct cache_detail *svc_export_cache; + + struct cache_detail *idtoname_cache; + struct cache_detail *nametoid_cache; }; extern int nfsd_net_id; diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index c8e9f637153..a5fd6b982f2 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -650,9 +650,10 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c struct rpc_clnt *client; if (clp->cl_minorversion == 0) { - if (!clp->cl_principal && (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) + if (!clp->cl_cred.cr_principal && + (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) return -EINVAL; - args.client_name = clp->cl_principal; + args.client_name = clp->cl_cred.cr_principal; args.prognumber = conn->cb_prog, args.protocol = XPRT_TRANSPORT_TCP; args.authflavor = clp->cl_flavor; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index 322d11ce06a..dae36f1dee9 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -36,9 +36,11 @@ #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/sunrpc/svc_xprt.h> #include <net/net_namespace.h> #include "idmap.h" #include "nfsd.h" +#include "netns.h" /* * Turn off idmapping when using AUTH_SYS. @@ -107,8 +109,6 @@ ent_alloc(void) * ID -> Name cache */ -static struct cache_head *idtoname_table[ENT_HASHMAX]; - static uint32_t idtoname_hash(struct ent *ent) { @@ -183,13 +183,13 @@ warn_no_idmapd(struct cache_detail *detail, int has_died) static int idtoname_parse(struct cache_detail *, char *, int); -static struct ent *idtoname_lookup(struct ent *); -static struct ent *idtoname_update(struct ent *, struct ent *); +static struct ent *idtoname_lookup(struct cache_detail *, struct ent *); +static struct ent *idtoname_update(struct cache_detail *, struct ent *, + struct ent *); -static struct cache_detail idtoname_cache = { +static struct cache_detail idtoname_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, - .hash_table = idtoname_table, .name = "nfs4.idtoname", .cache_put = ent_put, .cache_upcall = idtoname_upcall, @@ -244,7 +244,7 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) goto out; error = -ENOMEM; - res = idtoname_lookup(&ent); + res = idtoname_lookup(cd, &ent); if (!res) goto out; @@ -260,11 +260,11 @@ idtoname_parse(struct cache_detail *cd, char *buf, int buflen) else memcpy(ent.name, buf1, sizeof(ent.name)); error = -ENOMEM; - res = idtoname_update(&ent, res); + res = idtoname_update(cd, &ent, res); if (res == NULL) goto out; - cache_put(&res->h, &idtoname_cache); + cache_put(&res->h, cd); error = 0; out: @@ -275,10 +275,9 @@ out: static struct ent * -idtoname_lookup(struct ent *item) +idtoname_lookup(struct cache_detail *cd, struct ent *item) { - struct cache_head *ch = sunrpc_cache_lookup(&idtoname_cache, - &item->h, + struct cache_head *ch = sunrpc_cache_lookup(cd, &item->h, idtoname_hash(item)); if (ch) return container_of(ch, struct ent, h); @@ -287,10 +286,9 @@ idtoname_lookup(struct ent *item) } static struct ent * -idtoname_update(struct ent *new, struct ent *old) +idtoname_update(struct cache_detail *cd, struct ent *new, struct ent *old) { - struct cache_head *ch = sunrpc_cache_update(&idtoname_cache, - &new->h, &old->h, + struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h, idtoname_hash(new)); if (ch) return container_of(ch, struct ent, h); @@ -303,8 +301,6 @@ idtoname_update(struct ent *new, struct ent *old) * Name -> ID cache */ -static struct cache_head *nametoid_table[ENT_HASHMAX]; - static inline int nametoid_hash(struct ent *ent) { @@ -359,14 +355,14 @@ nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) return 0; } -static struct ent *nametoid_lookup(struct ent *); -static struct ent *nametoid_update(struct ent *, struct ent *); +static struct ent *nametoid_lookup(struct cache_detail *, struct ent *); +static struct ent *nametoid_update(struct cache_detail *, struct ent *, + struct ent *); static int nametoid_parse(struct cache_detail *, char *, int); -static struct cache_detail nametoid_cache = { +static struct cache_detail nametoid_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, - .hash_table = nametoid_table, .name = "nfs4.nametoid", .cache_put = ent_put, .cache_upcall = nametoid_upcall, @@ -426,14 +422,14 @@ nametoid_parse(struct cache_detail *cd, char *buf, int buflen) set_bit(CACHE_NEGATIVE, &ent.h.flags); error = -ENOMEM; - res = nametoid_lookup(&ent); + res = nametoid_lookup(cd, &ent); if (res == NULL) goto out; - res = nametoid_update(&ent, res); + res = nametoid_update(cd, &ent, res); if (res == NULL) goto out; - cache_put(&res->h, &nametoid_cache); + cache_put(&res->h, cd); error = 0; out: kfree(buf1); @@ -443,10 +439,9 @@ out: static struct ent * -nametoid_lookup(struct ent *item) +nametoid_lookup(struct cache_detail *cd, struct ent *item) { - struct cache_head *ch = sunrpc_cache_lookup(&nametoid_cache, - &item->h, + struct cache_head *ch = sunrpc_cache_lookup(cd, &item->h, nametoid_hash(item)); if (ch) return container_of(ch, struct ent, h); @@ -455,10 +450,9 @@ nametoid_lookup(struct ent *item) } static struct ent * -nametoid_update(struct ent *new, struct ent *old) +nametoid_update(struct cache_detail *cd, struct ent *new, struct ent *old) { - struct cache_head *ch = sunrpc_cache_update(&nametoid_cache, - &new->h, &old->h, + struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h, nametoid_hash(new)); if (ch) return container_of(ch, struct ent, h); @@ -471,34 +465,55 @@ nametoid_update(struct ent *new, struct ent *old) */ int -nfsd_idmap_init(void) +nfsd_idmap_init(struct net *net) { int rv; + struct nfsd_net *nn = net_generic(net, nfsd_net_id); - rv = cache_register_net(&idtoname_cache, &init_net); + nn->idtoname_cache = cache_create_net(&idtoname_cache_template, net); + if (IS_ERR(nn->idtoname_cache)) + return PTR_ERR(nn->idtoname_cache); + rv = cache_register_net(nn->idtoname_cache, net); if (rv) - return rv; - rv = cache_register_net(&nametoid_cache, &init_net); + goto destroy_idtoname_cache; + nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net); + if (IS_ERR(nn->nametoid_cache)) { + rv = PTR_ERR(nn->idtoname_cache); + goto unregister_idtoname_cache; + } + rv = cache_register_net(nn->nametoid_cache, net); if (rv) - cache_unregister_net(&idtoname_cache, &init_net); + goto destroy_nametoid_cache; + return 0; + +destroy_nametoid_cache: + cache_destroy_net(nn->nametoid_cache, net); +unregister_idtoname_cache: + cache_unregister_net(nn->idtoname_cache, net); +destroy_idtoname_cache: + cache_destroy_net(nn->idtoname_cache, net); return rv; } void -nfsd_idmap_shutdown(void) +nfsd_idmap_shutdown(struct net *net) { - cache_unregister_net(&idtoname_cache, &init_net); - cache_unregister_net(&nametoid_cache, &init_net); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + + cache_unregister_net(nn->idtoname_cache, net); + cache_unregister_net(nn->nametoid_cache, net); + cache_destroy_net(nn->idtoname_cache, net); + cache_destroy_net(nn->nametoid_cache, net); } static int idmap_lookup(struct svc_rqst *rqstp, - struct ent *(*lookup_fn)(struct ent *), struct ent *key, - struct cache_detail *detail, struct ent **item) + struct ent *(*lookup_fn)(struct cache_detail *, struct ent *), + struct ent *key, struct cache_detail *detail, struct ent **item) { int ret; - *item = lookup_fn(key); + *item = lookup_fn(detail, key); if (!*item) return -ENOMEM; retry: @@ -506,7 +521,7 @@ idmap_lookup(struct svc_rqst *rqstp, if (ret == -ETIMEDOUT) { struct ent *prev_item = *item; - *item = lookup_fn(key); + *item = lookup_fn(detail, key); if (*item != prev_item) goto retry; cache_put(&(*item)->h, detail); @@ -531,19 +546,20 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen .type = type, }; int ret; + struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id); if (namelen + 1 > sizeof(key.name)) return nfserr_badowner; memcpy(key.name, name, namelen); key.name[namelen] = '\0'; strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); - ret = idmap_lookup(rqstp, nametoid_lookup, &key, &nametoid_cache, &item); + ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item); if (ret == -ENOENT) return nfserr_badowner; if (ret) return nfserrno(ret); *id = item->id; - cache_put(&item->h, &nametoid_cache); + cache_put(&item->h, nn->nametoid_cache); return 0; } @@ -555,9 +571,10 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name) .type = type, }; int ret; + struct nfsd_net *nn = net_generic(rqstp->rq_xprt->xpt_net, nfsd_net_id); strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); - ret = idmap_lookup(rqstp, idtoname_lookup, &key, &idtoname_cache, &item); + ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item); if (ret == -ENOENT) return sprintf(name, "%u", id); if (ret) @@ -565,7 +582,7 @@ idmap_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name) ret = strlen(item->name); BUG_ON(ret > IDMAP_NAMESZ); memcpy(name, item->name, ret); - cache_put(&item->h, &idtoname_cache); + cache_put(&item->h, nn->idtoname_cache); return ret; } @@ -588,7 +605,7 @@ numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namel static __be32 do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, uid_t *id) { - if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS) + if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) if (numeric_name_to_id(rqstp, type, name, namelen, id)) return 0; /* @@ -601,7 +618,7 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u static int do_id_to_name(struct svc_rqst *rqstp, int type, uid_t id, char *name) { - if (nfs4_disable_idmapping && rqstp->rq_flavor < RPC_AUTH_GSS) + if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) return sprintf(name, "%u", id); return idmap_id_to_name(rqstp, type, id, name); } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 4767429264a..5ff0b7b9fc0 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -570,14 +570,14 @@ static ssize_t cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct cld_upcall *tmp, *cup; - struct cld_msg *cmsg = (struct cld_msg *)src; + struct cld_msg __user *cmsg = (struct cld_msg __user *)src; uint32_t xid; struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info, nfsd_net_id); struct cld_net *cn = nn->cld_net; if (mlen != sizeof(*cmsg)) { - dprintk("%s: got %lu bytes, expected %lu\n", __func__, mlen, + dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen, sizeof(*cmsg)); return -EINVAL; } @@ -1029,7 +1029,7 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr) return ret; } -struct notifier_block nfsd4_cld_block = { +static struct notifier_block nfsd4_cld_block = { .notifier_call = rpc_pipefs_event, }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 7f71c69cdcd..94effd5bc4a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -42,6 +42,7 @@ #include <linux/sunrpc/clnt.h> #include "xdr4.h" #include "vfs.h" +#include "current_stateid.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -447,37 +448,69 @@ static struct list_head close_lru; * * which we should reject. */ -static void -set_access(unsigned int *access, unsigned long bmap) { +static unsigned int +bmap_to_share_mode(unsigned long bmap) { int i; + unsigned int access = 0; - *access = 0; for (i = 1; i < 4; i++) { if (test_bit(i, &bmap)) - *access |= i; - } -} - -static void -set_deny(unsigned int *deny, unsigned long bmap) { - int i; - - *deny = 0; - for (i = 0; i < 4; i++) { - if (test_bit(i, &bmap)) - *deny |= i ; + access |= i; } + return access; } -static int +static bool test_share(struct nfs4_ol_stateid *stp, struct nfsd4_open *open) { unsigned int access, deny; - set_access(&access, stp->st_access_bmap); - set_deny(&deny, stp->st_deny_bmap); + access = bmap_to_share_mode(stp->st_access_bmap); + deny = bmap_to_share_mode(stp->st_deny_bmap); if ((access & open->op_share_deny) || (deny & open->op_share_access)) - return 0; - return 1; + return false; + return true; +} + +/* set share access for a given stateid */ +static inline void +set_access(u32 access, struct nfs4_ol_stateid *stp) +{ + __set_bit(access, &stp->st_access_bmap); +} + +/* clear share access for a given stateid */ +static inline void +clear_access(u32 access, struct nfs4_ol_stateid *stp) +{ + __clear_bit(access, &stp->st_access_bmap); +} + +/* test whether a given stateid has access */ +static inline bool +test_access(u32 access, struct nfs4_ol_stateid *stp) +{ + return test_bit(access, &stp->st_access_bmap); +} + +/* set share deny for a given stateid */ +static inline void +set_deny(u32 access, struct nfs4_ol_stateid *stp) +{ + __set_bit(access, &stp->st_deny_bmap); +} + +/* clear share deny for a given stateid */ +static inline void +clear_deny(u32 access, struct nfs4_ol_stateid *stp) +{ + __clear_bit(access, &stp->st_deny_bmap); +} + +/* test whether a given stateid is denying specific access */ +static inline bool +test_deny(u32 access, struct nfs4_ol_stateid *stp) +{ + return test_bit(access, &stp->st_deny_bmap); } static int nfs4_access_to_omode(u32 access) @@ -493,6 +526,20 @@ static int nfs4_access_to_omode(u32 access) BUG(); } +/* release all access and file references for a given stateid */ +static void +release_all_access(struct nfs4_ol_stateid *stp) +{ + int i; + + for (i = 1; i < 4; i++) { + if (test_access(i, stp)) + nfs4_file_put_access(stp->st_file, + nfs4_access_to_omode(i)); + clear_access(i, stp); + } +} + static void unhash_generic_stateid(struct nfs4_ol_stateid *stp) { list_del(&stp->st_perfile); @@ -501,16 +548,7 @@ static void unhash_generic_stateid(struct nfs4_ol_stateid *stp) static void close_generic_stateid(struct nfs4_ol_stateid *stp) { - int i; - - if (stp->st_access_bmap) { - for (i = 1; i < 4; i++) { - if (test_bit(i, &stp->st_access_bmap)) - nfs4_file_put_access(stp->st_file, - nfs4_access_to_omode(i)); - __clear_bit(i, &stp->st_access_bmap); - } - } + release_all_access(stp); put_nfs4_file(stp->st_file); stp->st_file = NULL; } @@ -862,7 +900,7 @@ static void free_session(struct kref *kref) struct nfsd4_session *ses; int mem; - BUG_ON(!spin_is_locked(&client_lock)); + lockdep_assert_held(&client_lock); ses = container_of(kref, struct nfsd4_session, se_ref); nfsd4_del_conns(ses); spin_lock(&nfsd_drc_lock); @@ -885,7 +923,7 @@ static struct nfsd4_session *alloc_init_session(struct svc_rqst *rqstp, struct n struct nfsd4_session *new; struct nfsd4_channel_attrs *fchan = &cses->fore_channel; int numslots, slotsize; - int status; + __be32 status; int idx; /* @@ -984,7 +1022,8 @@ static inline void renew_client_locked(struct nfs4_client *clp) { if (is_client_expired(clp)) { - dprintk("%s: client (clientid %08x/%08x) already expired\n", + WARN_ON(1); + printk("%s: client (clientid %08x/%08x) already expired\n", __func__, clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); @@ -1041,7 +1080,7 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) static inline void free_client(struct nfs4_client *clp) { - BUG_ON(!spin_is_locked(&client_lock)); + lockdep_assert_held(&client_lock); while (!list_empty(&clp->cl_sessions)) { struct nfsd4_session *ses; ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, @@ -1049,9 +1088,7 @@ free_client(struct nfs4_client *clp) list_del(&ses->se_perclnt); nfsd4_put_session_locked(ses); } - if (clp->cl_cred.cr_group_info) - put_group_info(clp->cl_cred.cr_group_info); - kfree(clp->cl_principal); + free_svc_cred(&clp->cl_cred); kfree(clp->cl_name.data); kfree(clp); } @@ -1132,12 +1169,21 @@ static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) target->cl_clientid.cl_id = source->cl_clientid.cl_id; } -static void copy_cred(struct svc_cred *target, struct svc_cred *source) +static int copy_cred(struct svc_cred *target, struct svc_cred *source) { + if (source->cr_principal) { + target->cr_principal = + kstrdup(source->cr_principal, GFP_KERNEL); + if (target->cr_principal == NULL) + return -ENOMEM; + } else + target->cr_principal = NULL; + target->cr_flavor = source->cr_flavor; target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); + return 0; } static int same_name(const char *n1, const char *n2) @@ -1157,11 +1203,31 @@ same_clid(clientid_t *cl1, clientid_t *cl2) return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id); } -/* XXX what about NGROUP */ +static bool groups_equal(struct group_info *g1, struct group_info *g2) +{ + int i; + + if (g1->ngroups != g2->ngroups) + return false; + for (i=0; i<g1->ngroups; i++) + if (GROUP_AT(g1, i) != GROUP_AT(g2, i)) + return false; + return true; +} + static int same_creds(struct svc_cred *cr1, struct svc_cred *cr2) { - return cr1->cr_uid == cr2->cr_uid; + if ((cr1->cr_flavor != cr2->cr_flavor) + || (cr1->cr_uid != cr2->cr_uid) + || (cr1->cr_gid != cr2->cr_gid) + || !groups_equal(cr1->cr_group_info, cr2->cr_group_info)) + return false; + if (cr1->cr_principal == cr2->cr_principal) + return true; + if (!cr1->cr_principal || !cr2->cr_principal) + return false; + return 0 == strcmp(cr1->cr_principal, cr1->cr_principal); } static void gen_clid(struct nfs4_client *clp) @@ -1204,25 +1270,20 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, { struct nfs4_client *clp; struct sockaddr *sa = svc_addr(rqstp); - char *princ; + int ret; clp = alloc_client(name); if (clp == NULL) return NULL; INIT_LIST_HEAD(&clp->cl_sessions); - - princ = svc_gss_principal(rqstp); - if (princ) { - clp->cl_principal = kstrdup(princ, GFP_KERNEL); - if (clp->cl_principal == NULL) { - spin_lock(&client_lock); - free_client(clp); - spin_unlock(&client_lock); - return NULL; - } + ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); + if (ret) { + spin_lock(&client_lock); + free_client(clp); + spin_unlock(&client_lock); + return NULL; } - idr_init(&clp->cl_stateids); memcpy(clp->cl_recdir, recdir, HEXDIR_LEN); atomic_set(&clp->cl_refcount, 0); @@ -1240,8 +1301,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir, rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); copy_verf(clp, verf); rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); - clp->cl_flavor = rqstp->rq_flavor; - copy_cred(&clp->cl_cred, &rqstp->rq_cred); gen_confirm(clp); clp->cl_cb_session = NULL; return clp; @@ -1470,18 +1529,32 @@ nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) clid->flags = new->cl_exchange_flags; } +static bool client_has_state(struct nfs4_client *clp) +{ + /* + * Note clp->cl_openowners check isn't quite right: there's no + * need to count owners without stateid's. + * + * Also note we should probably be using this in 4.0 case too. + */ + return !list_empty(&clp->cl_openowners) + || !list_empty(&clp->cl_delegations) + || !list_empty(&clp->cl_sessions); +} + __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_exchange_id *exid) { struct nfs4_client *unconf, *conf, *new; - int status; + __be32 status; unsigned int strhashval; char dname[HEXDIR_LEN]; char addr_str[INET6_ADDRSTRLEN]; nfs4_verifier verf = exid->verifier; struct sockaddr *sa = svc_addr(rqstp); + bool update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A; rpc_ntop(sa, addr_str, sizeof(addr_str)); dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " @@ -1507,71 +1580,63 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, status = nfs4_make_rec_clidname(dname, &exid->clname); if (status) - goto error; + return status; strhashval = clientstr_hashval(dname); + /* Cases below refer to rfc 5661 section 18.35.4: */ nfs4_lock_state(); - status = nfs_ok; - conf = find_confirmed_client_by_str(dname, strhashval); if (conf) { - if (!clp_used_exchangeid(conf)) { - status = nfserr_clid_inuse; /* XXX: ? */ - goto out; - } - if (!same_verf(&verf, &conf->cl_verifier)) { - /* 18.35.4 case 8 */ - if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred); + bool verfs_match = same_verf(&verf, &conf->cl_verifier); + + if (update) { + if (!clp_used_exchangeid(conf)) { /* buggy client */ + status = nfserr_inval; + goto out; + } + if (!creds_match) { /* case 9 */ + status = nfserr_perm; + goto out; + } + if (!verfs_match) { /* case 8 */ status = nfserr_not_same; goto out; } - /* Client reboot: destroy old state */ - expire_client(conf); - goto out_new; + /* case 6 */ + exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; + new = conf; + goto out_copy; } - if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { - /* 18.35.4 case 9 */ - if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { - status = nfserr_perm; + if (!creds_match) { /* case 3 */ + if (client_has_state(conf)) { + status = nfserr_clid_inuse; goto out; } expire_client(conf); goto out_new; } - /* - * Set bit when the owner id and verifier map to an already - * confirmed client id (18.35.3). - */ - exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; - - /* - * Falling into 18.35.4 case 2, possible router replay. - * Leave confirmed record intact and return same result. - */ - copy_verf(conf, &verf); - new = conf; - goto out_copy; + if (verfs_match) { /* case 2 */ + conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R; + new = conf; + goto out_copy; + } + /* case 5, client reboot */ + goto out_new; } - /* 18.35.4 case 7 */ - if (exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A) { + if (update) { /* case 7 */ status = nfserr_noent; goto out; } unconf = find_unconfirmed_client_by_str(dname, strhashval); - if (unconf) { - /* - * Possible retry or client restart. Per 18.35.4 case 4, - * a new unconfirmed record should be generated regardless - * of whether any properties have changed. - */ + if (unconf) /* case 4, possible retry or client restart */ expire_client(unconf); - } + /* case 1 (normal case) */ out_new: - /* Normal case */ new = create_client(exid->clname, dname, rqstp, &verf); if (new == NULL) { status = nfserr_jukebox; @@ -1584,7 +1649,7 @@ out_copy: exid->clientid.cl_boot = new->cl_clientid.cl_boot; exid->clientid.cl_id = new->cl_clientid.cl_id; - exid->seqid = 1; + exid->seqid = new->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(new, exid); dprintk("nfsd4_exchange_id seqid %d flags %x\n", @@ -1593,12 +1658,10 @@ out_copy: out: nfs4_unlock_state(); -error: - dprintk("nfsd4_exchange_id returns %d\n", ntohl(status)); return status; } -static int +static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) { dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid, @@ -1626,7 +1689,7 @@ check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) */ static void nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses, - struct nfsd4_clid_slot *slot, int nfserr) + struct nfsd4_clid_slot *slot, __be32 nfserr) { slot->sl_status = nfserr; memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses)); @@ -1657,7 +1720,7 @@ nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses, /* seqid, slotID, slotID, slotID, status */ \ 5 ) * sizeof(__be32)) -static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs fchannel) +static bool check_forechannel_attrs(struct nfsd4_channel_attrs fchannel) { return fchannel.maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ || fchannel.maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ; @@ -1673,7 +1736,7 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_session *new; struct nfsd4_clid_slot *cs_slot = NULL; bool confirm_me = false; - int status = 0; + __be32 status = 0; if (cr_ses->flags & ~SESSION4_FLAG_MASK_A) return nfserr_inval; @@ -1686,16 +1749,10 @@ nfsd4_create_session(struct svc_rqst *rqstp, cs_slot = &conf->cl_cs_slot; status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); if (status == nfserr_replay_cache) { - dprintk("Got a create_session replay! seqid= %d\n", - cs_slot->sl_seqid); - /* Return the cached reply status */ status = nfsd4_replay_create_session(cr_ses, cs_slot); goto out; } else if (cr_ses->seqid != cs_slot->sl_seqid + 1) { status = nfserr_seq_misordered; - dprintk("Sequence misordered!\n"); - dprintk("Expected seqid= %d but got seqid= %d\n", - cs_slot->sl_seqid, cr_ses->seqid); goto out; } } else if (unconf) { @@ -1704,7 +1761,6 @@ nfsd4_create_session(struct svc_rqst *rqstp, status = nfserr_clid_inuse; goto out; } - cs_slot = &unconf->cl_cs_slot; status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); if (status) { @@ -1712,7 +1768,6 @@ nfsd4_create_session(struct svc_rqst *rqstp, status = nfserr_seq_misordered; goto out; } - confirm_me = true; conf = unconf; } else { @@ -1749,8 +1804,14 @@ nfsd4_create_session(struct svc_rqst *rqstp, /* cache solo and embedded create sessions under the state lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); - if (confirm_me) + if (confirm_me) { + unsigned int hash = clientstr_hashval(unconf->cl_recdir); + struct nfs4_client *old = + find_confirmed_client_by_str(conf->cl_recdir, hash); + if (old) + expire_client(old); move_to_confirmed(conf); + } out: nfs4_unlock_state(); dprintk("%s returns %d\n", __func__, ntohl(status)); @@ -1818,7 +1879,7 @@ nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_destroy_session *sessionid) { struct nfsd4_session *ses; - u32 status = nfserr_badsession; + __be32 status = nfserr_badsession; /* Notes: * - The confirmed nfs4_client->cl_sessionid holds destroyed sessinid @@ -1914,7 +1975,7 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_session *session; struct nfsd4_slot *slot; struct nfsd4_conn *conn; - int status; + __be32 status; if (resp->opcnt != 1) return nfserr_sequence_pos; @@ -2008,18 +2069,11 @@ out: return status; } -static inline bool has_resources(struct nfs4_client *clp) -{ - return !list_empty(&clp->cl_openowners) - || !list_empty(&clp->cl_delegations) - || !list_empty(&clp->cl_sessions); -} - __be32 nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc) { struct nfs4_client *conf, *unconf, *clp; - int status = 0; + __be32 status = 0; nfs4_lock_state(); unconf = find_unconfirmed_client(&dc->clientid); @@ -2028,7 +2082,7 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta if (conf) { clp = conf; - if (!is_client_expired(conf) && has_resources(conf)) { + if (!is_client_expired(conf) && client_has_state(conf)) { status = nfserr_clientid_busy; goto out; } @@ -2055,7 +2109,7 @@ out: __be32 nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc) { - int status = 0; + __be32 status = 0; if (rc->rca_one_fs) { if (!cstate->current_fh.fh_dentry) @@ -2106,17 +2160,13 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) return status; - /* - * XXX The Duplicate Request Cache (DRC) has been checked (??) - * We get here on a DRC miss. - */ - strhashval = clientstr_hashval(dname); + /* Cases below refer to rfc 3530 section 14.2.33: */ nfs4_lock_state(); conf = find_confirmed_client_by_str(dname, strhashval); if (conf) { - /* RFC 3530 14.2.33 CASE 0: */ + /* case 0: */ status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) goto out; @@ -2129,63 +2179,18 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } } - /* - * section 14.2.33 of RFC 3530 (under the heading "IMPLEMENTATION") - * has a description of SETCLIENTID request processing consisting - * of 5 bullet points, labeled as CASE0 - CASE4 below. - */ unconf = find_unconfirmed_client_by_str(dname, strhashval); + if (unconf) + expire_client(unconf); status = nfserr_jukebox; - if (!conf) { - /* - * RFC 3530 14.2.33 CASE 4: - * placed first, because it is the normal case - */ - if (unconf) - expire_client(unconf); - new = create_client(clname, dname, rqstp, &clverifier); - if (new == NULL) - goto out; - gen_clid(new); - } else if (same_verf(&conf->cl_verifier, &clverifier)) { - /* - * RFC 3530 14.2.33 CASE 1: - * probable callback update - */ - if (unconf) { - /* Note this is removing unconfirmed {*x***}, - * which is stronger than RFC recommended {vxc**}. - * This has the advantage that there is at most - * one {*x***} in either list at any time. - */ - expire_client(unconf); - } - new = create_client(clname, dname, rqstp, &clverifier); - if (new == NULL) - goto out; + new = create_client(clname, dname, rqstp, &clverifier); + if (new == NULL) + goto out; + if (conf && same_verf(&conf->cl_verifier, &clverifier)) + /* case 1: probable callback update */ copy_clid(new, conf); - } else if (!unconf) { - /* - * RFC 3530 14.2.33 CASE 2: - * probable client reboot; state will be removed if - * confirmed. - */ - new = create_client(clname, dname, rqstp, &clverifier); - if (new == NULL) - goto out; - gen_clid(new); - } else { - /* - * RFC 3530 14.2.33 CASE 3: - * probable client reboot; state will be removed if - * confirmed. - */ - expire_client(unconf); - new = create_client(clname, dname, rqstp, &clverifier); - if (new == NULL) - goto out; + else /* case 4 (new client) or cases 2, 3 (client reboot): */ gen_clid(new); - } /* * XXX: we should probably set this at creation time, and check * for consistent minorversion use throughout: @@ -2203,17 +2208,11 @@ out: } -/* - * Section 14.2.34 of RFC 3530 (under the heading "IMPLEMENTATION") has - * a description of SETCLIENTID_CONFIRM request processing consisting of 4 - * bullets, labeled as CASE1 - CASE4 below. - */ __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_setclientid_confirm *setclientid_confirm) { - struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; nfs4_verifier confirm = setclientid_confirm->sc_confirm; clientid_t * clid = &setclientid_confirm->sc_clientid; @@ -2221,84 +2220,44 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, if (STALE_CLIENTID(clid)) return nfserr_stale_clientid; - /* - * XXX The Duplicate Request Cache (DRC) has been checked (??) - * We get here on a DRC miss. - */ - nfs4_lock_state(); conf = find_confirmed_client(clid); unconf = find_unconfirmed_client(clid); - - status = nfserr_clid_inuse; - if (conf && !rpc_cmp_addr((struct sockaddr *) &conf->cl_addr, sa)) - goto out; - if (unconf && !rpc_cmp_addr((struct sockaddr *) &unconf->cl_addr, sa)) - goto out; - /* - * section 14.2.34 of RFC 3530 has a description of - * SETCLIENTID_CONFIRM request processing consisting - * of 4 bullet points, labeled as CASE1 - CASE4 below. + * We try hard to give out unique clientid's, so if we get an + * attempt to confirm the same clientid with a different cred, + * there's a bug somewhere. Let's charitably assume it's our + * bug. */ - if (conf && unconf && same_verf(&confirm, &unconf->cl_confirm)) { - /* - * RFC 3530 14.2.34 CASE 1: - * callback update - */ - if (!same_creds(&conf->cl_cred, &unconf->cl_cred)) - status = nfserr_clid_inuse; - else { - nfsd4_change_callback(conf, &unconf->cl_cb_conn); - nfsd4_probe_callback(conf); - expire_client(unconf); + status = nfserr_serverfault; + if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) + goto out; + if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) + goto out; + /* cases below refer to rfc 3530 section 14.2.34: */ + if (!unconf || !same_verf(&confirm, &unconf->cl_confirm)) { + if (conf && !unconf) /* case 2: probable retransmit */ status = nfs_ok; + else /* case 4: client hasn't noticed we rebooted yet? */ + status = nfserr_stale_clientid; + goto out; + } + status = nfs_ok; + if (conf) { /* case 1: callback update */ + nfsd4_change_callback(conf, &unconf->cl_cb_conn); + nfsd4_probe_callback(conf); + expire_client(unconf); + } else { /* case 3: normal case; new or rebooted client */ + unsigned int hash = clientstr_hashval(unconf->cl_recdir); + conf = find_confirmed_client_by_str(unconf->cl_recdir, hash); + if (conf) { + nfsd4_client_record_remove(conf); + expire_client(conf); } - } else if (conf && !unconf) { - /* - * RFC 3530 14.2.34 CASE 2: - * probable retransmitted request; play it safe and - * do nothing. - */ - if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) - status = nfserr_clid_inuse; - else - status = nfs_ok; - } else if (!conf && unconf - && same_verf(&unconf->cl_confirm, &confirm)) { - /* - * RFC 3530 14.2.34 CASE 3: - * Normal case; new or rebooted client: - */ - if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { - status = nfserr_clid_inuse; - } else { - unsigned int hash = - clientstr_hashval(unconf->cl_recdir); - conf = find_confirmed_client_by_str(unconf->cl_recdir, - hash); - if (conf) { - nfsd4_client_record_remove(conf); - expire_client(conf); - } - move_to_confirmed(unconf); - conf = unconf; - nfsd4_probe_callback(conf); - status = nfs_ok; - } - } else if ((!conf || (conf && !same_verf(&conf->cl_confirm, &confirm))) - && (!unconf || (unconf && !same_verf(&unconf->cl_confirm, - &confirm)))) { - /* - * RFC 3530 14.2.34 CASE 4: - * Client probably hasn't noticed that we rebooted yet. - */ - status = nfserr_stale_clientid; - } else { - /* check that we have hit one of the cases...*/ - status = nfserr_clid_inuse; + move_to_confirmed(unconf); + nfsd4_probe_callback(unconf); } out: nfs4_unlock_state(); @@ -2454,8 +2413,8 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, stp->st_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = 0; - __set_bit(open->op_share_access, &stp->st_access_bmap); - __set_bit(open->op_share_deny, &stp->st_deny_bmap); + set_access(open->op_share_access, stp); + set_deny(open->op_share_deny, stp); stp->st_openstp = NULL; } @@ -2534,8 +2493,8 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) ret = nfserr_locked; /* Search for conflicting share reservations */ list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { - if (test_bit(deny_type, &stp->st_deny_bmap) || - test_bit(NFS4_SHARE_DENY_BOTH, &stp->st_deny_bmap)) + if (test_deny(deny_type, stp) || + test_deny(NFS4_SHARE_DENY_BOTH, stp)) goto out; } ret = nfs_ok; @@ -2791,7 +2750,7 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c bool new_access; __be32 status; - new_access = !test_bit(op_share_access, &stp->st_access_bmap); + new_access = !test_access(op_share_access, stp); if (new_access) { status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open); if (status) @@ -2806,8 +2765,8 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *c return status; } /* remember the open */ - __set_bit(op_share_access, &stp->st_access_bmap); - __set_bit(open->op_share_deny, &stp->st_deny_bmap); + set_access(op_share_access, stp); + set_deny(open->op_share_deny, stp); return nfs_ok; } @@ -3155,10 +3114,17 @@ out: static struct lock_manager nfsd4_manager = { }; +static bool grace_ended; + static void nfsd4_end_grace(void) { + /* do nothing if grace period already ended */ + if (grace_ended) + return; + dprintk("NFSD: end of grace period\n"); + grace_ended = true; nfsd4_record_grace_done(&init_net, boot_time); locks_end_grace(&nfsd4_manager); /* @@ -3183,8 +3149,7 @@ nfs4_laundromat(void) nfs4_lock_state(); dprintk("NFSD: laundromat service - starting\n"); - if (locks_in_grace()) - nfsd4_end_grace(); + nfsd4_end_grace(); INIT_LIST_HEAD(&reaplist); spin_lock(&client_lock); list_for_each_safe(pos, next, &client_lru) { @@ -3276,18 +3241,18 @@ STALE_STATEID(stateid_t *stateid) } static inline int -access_permit_read(unsigned long access_bmap) +access_permit_read(struct nfs4_ol_stateid *stp) { - return test_bit(NFS4_SHARE_ACCESS_READ, &access_bmap) || - test_bit(NFS4_SHARE_ACCESS_BOTH, &access_bmap) || - test_bit(NFS4_SHARE_ACCESS_WRITE, &access_bmap); + return test_access(NFS4_SHARE_ACCESS_READ, stp) || + test_access(NFS4_SHARE_ACCESS_BOTH, stp) || + test_access(NFS4_SHARE_ACCESS_WRITE, stp); } static inline int -access_permit_write(unsigned long access_bmap) +access_permit_write(struct nfs4_ol_stateid *stp) { - return test_bit(NFS4_SHARE_ACCESS_WRITE, &access_bmap) || - test_bit(NFS4_SHARE_ACCESS_BOTH, &access_bmap); + return test_access(NFS4_SHARE_ACCESS_WRITE, stp) || + test_access(NFS4_SHARE_ACCESS_BOTH, stp); } static @@ -3298,9 +3263,9 @@ __be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags) /* For lock stateid's, we test the parent open, not the lock: */ if (stp->st_openstp) stp = stp->st_openstp; - if ((flags & WR_STATE) && (!access_permit_write(stp->st_access_bmap))) + if ((flags & WR_STATE) && !access_permit_write(stp)) goto out; - if ((flags & RD_STATE) && (!access_permit_read(stp->st_access_bmap))) + if ((flags & RD_STATE) && !access_permit_read(stp)) goto out; status = nfs_ok; out: @@ -3340,7 +3305,7 @@ static bool stateid_generation_after(stateid_t *a, stateid_t *b) return (s32)a->si_generation - (s32)b->si_generation > 0; } -static int check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) +static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) { /* * When sessions are used the stateid generation number is ignored @@ -3649,10 +3614,10 @@ out: static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 access) { - if (!test_bit(access, &stp->st_access_bmap)) + if (!test_access(access, stp)) return; nfs4_file_put_access(stp->st_file, nfs4_access_to_omode(access)); - __clear_bit(access, &stp->st_access_bmap); + clear_access(access, stp); } static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_access) @@ -3674,12 +3639,12 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac } static void -reset_union_bmap_deny(unsigned long deny, unsigned long *bmap) +reset_union_bmap_deny(unsigned long deny, struct nfs4_ol_stateid *stp) { int i; for (i = 0; i < 4; i++) { if ((i & deny) != i) - __clear_bit(i, bmap); + clear_deny(i, stp); } } @@ -3706,19 +3671,19 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp, if (status) goto out; status = nfserr_inval; - if (!test_bit(od->od_share_access, &stp->st_access_bmap)) { - dprintk("NFSD:access not a subset current bitmap: 0x%lx, input access=%08x\n", + if (!test_access(od->od_share_access, stp)) { + dprintk("NFSD: access not a subset current bitmap: 0x%lx, input access=%08x\n", stp->st_access_bmap, od->od_share_access); goto out; } - if (!test_bit(od->od_share_deny, &stp->st_deny_bmap)) { + if (!test_deny(od->od_share_deny, stp)) { dprintk("NFSD:deny not a subset current bitmap: 0x%lx, input deny=%08x\n", stp->st_deny_bmap, od->od_share_deny); goto out; } nfs4_stateid_downgrade(stp, od->od_share_access); - reset_union_bmap_deny(od->od_share_deny, &stp->st_deny_bmap); + reset_union_bmap_deny(od->od_share_deny, stp); update_stateid(&stp->st_stid.sc_stateid); memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t)); @@ -4008,13 +3973,13 @@ static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access) struct nfs4_file *fp = lock_stp->st_file; int oflag = nfs4_access_to_omode(access); - if (test_bit(access, &lock_stp->st_access_bmap)) + if (test_access(access, lock_stp)) return; nfs4_file_get_access(fp, oflag); - __set_bit(access, &lock_stp->st_access_bmap); + set_access(access, lock_stp); } -__be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **lst, bool *new) +static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **lst, bool *new) { struct nfs4_file *fi = ost->st_file; struct nfs4_openowner *oo = openowner(ost->st_stateowner); @@ -4055,7 +4020,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp; - struct nfs4_file *fp; struct file *filp = NULL; struct file_lock file_lock; struct file_lock conflock; @@ -4123,7 +4087,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } lock_sop = lockowner(lock_stp->st_stateowner); - fp = lock_stp->st_file; lkflg = setlkflg(lock->lk_type); status = nfs4_check_openmode(lock_stp, lkflg); @@ -4715,6 +4678,7 @@ nfs4_state_start(void) nfsd4_client_tracking_init(&init_net); boot_time = get_seconds(); locks_start_grace(&nfsd4_manager); + grace_ended = false; printk(KERN_INFO "NFSD: starting %ld-second grace period\n", nfsd4_grace); ret = set_callback_cred(); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 74c00bc92b9..4949667c84e 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1674,12 +1674,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) static void write32(__be32 **p, u32 n) { - *(*p)++ = n; + *(*p)++ = htonl(n); } static void write64(__be32 **p, u64 n) { - write32(p, (u32)(n >> 32)); + write32(p, (n >> 32)); write32(p, (u32)n); } @@ -1744,15 +1744,16 @@ static void encode_seqid_op_tail(struct nfsd4_compoundres *resp, __be32 *save, _ } /* Encode as an array of strings the string given with components - * separated @sep. + * separated @sep, escaped with esc_enter and esc_exit. */ -static __be32 nfsd4_encode_components(char sep, char *components, - __be32 **pp, int *buflen) +static __be32 nfsd4_encode_components_esc(char sep, char *components, + __be32 **pp, int *buflen, + char esc_enter, char esc_exit) { __be32 *p = *pp; __be32 *countp = p; int strlen, count=0; - char *str, *end; + char *str, *end, *next; dprintk("nfsd4_encode_components(%s)\n", components); if ((*buflen -= 4) < 0) @@ -1760,8 +1761,23 @@ static __be32 nfsd4_encode_components(char sep, char *components, WRITE32(0); /* We will fill this in with @count later */ end = str = components; while (*end) { - for (; *end && (*end != sep); end++) - ; /* Point to end of component */ + bool found_esc = false; + + /* try to parse as esc_start, ..., esc_end, sep */ + if (*str == esc_enter) { + for (; *end && (*end != esc_exit); end++) + /* find esc_exit or end of string */; + next = end + 1; + if (*end && (!*next || *next == sep)) { + str++; + found_esc = true; + } + } + + if (!found_esc) + for (; *end && (*end != sep); end++) + /* find sep or end of string */; + strlen = end - str; if (strlen) { if ((*buflen -= ((XDR_QUADLEN(strlen) << 2) + 4)) < 0) @@ -1780,6 +1796,15 @@ static __be32 nfsd4_encode_components(char sep, char *components, return 0; } +/* Encode as an array of strings the string given with components + * separated @sep. + */ +static __be32 nfsd4_encode_components(char sep, char *components, + __be32 **pp, int *buflen) +{ + return nfsd4_encode_components_esc(sep, components, pp, buflen, 0, 0); +} + /* * encode a location element of a fs_locations structure */ @@ -1789,7 +1814,8 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location, __be32 status; __be32 *p = *pp; - status = nfsd4_encode_components(':', location->hosts, &p, buflen); + status = nfsd4_encode_components_esc(':', location->hosts, &p, buflen, + '[', ']'); if (status) return status; status = nfsd4_encode_components('/', location->path, &p, buflen); @@ -3251,7 +3277,7 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w } static __be32 -nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr, +nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_exchange_id *exid) { __be32 *p; @@ -3306,7 +3332,7 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, int nfserr, } static __be32 -nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr, +nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create_session *sess) { __be32 *p; @@ -3355,14 +3381,14 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, int nfserr, } static __be32 -nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, int nfserr, +nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_destroy_session *destroy_session) { return nfserr; } static __be32 -nfsd4_encode_free_stateid(struct nfsd4_compoundres *resp, int nfserr, +nfsd4_encode_free_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_free_stateid *free_stateid) { __be32 *p; @@ -3371,13 +3397,13 @@ nfsd4_encode_free_stateid(struct nfsd4_compoundres *resp, int nfserr, return nfserr; RESERVE_SPACE(4); - WRITE32(nfserr); + *p++ = nfserr; ADJUST_ARGS(); return nfserr; } static __be32 -nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr, +nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_sequence *seq) { __be32 *p; @@ -3399,8 +3425,8 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, int nfserr, return 0; } -__be32 -nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, int nfserr, +static __be32 +nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_test_stateid *test_stateid) { struct nfsd4_test_stateid_id *stateid, *next; @@ -3503,7 +3529,7 @@ static nfsd4_enc nfsd4_enc_ops[] = { * Our se_fmaxresp_cached will always be a multiple of PAGE_SIZE, and so * will be at least a page and will therefore hold the xdr_buf head. */ -int nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad) +__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *resp, u32 pad) { struct xdr_buf *xb = &resp->rqstp->rq_res; struct nfsd4_session *session = NULL; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 2c53be6d357..c55298ed577 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -127,7 +127,17 @@ static const struct file_operations transaction_ops = { static int exports_open(struct inode *inode, struct file *file) { - return seq_open(file, &nfs_exports_op); + int err; + struct seq_file *seq; + struct nfsd_net *nn = net_generic(&init_net, nfsd_net_id); + + err = seq_open(file, &nfs_exports_op); + if (err) + return err; + + seq = file->private_data; + seq->private = nn->svc_export_cache; + return 0; } static const struct file_operations exports_operations = { @@ -345,7 +355,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) if (!dom) return -ENOMEM; - len = exp_rootfh(dom, path, &fh, maxsize); + len = exp_rootfh(&init_net, dom, path, &fh, maxsize); auth_domain_put(dom); if (len) return len; @@ -651,6 +661,7 @@ static ssize_t __write_ports_addfd(char *buf) { char *mesg = buf; int fd, err; + struct net *net = &init_net; err = get_int(&mesg, &fd); if (err != 0 || fd < 0) @@ -662,6 +673,8 @@ static ssize_t __write_ports_addfd(char *buf) err = svc_addsock(nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT); if (err < 0) { + if (nfsd_serv->sv_nrthreads == 1) + svc_shutdown_net(nfsd_serv, net); svc_destroy(nfsd_serv); return err; } @@ -699,6 +712,7 @@ static ssize_t __write_ports_addxprt(char *buf) char transport[16]; struct svc_xprt *xprt; int port, err; + struct net *net = &init_net; if (sscanf(buf, "%15s %4u", transport, &port) != 2) return -EINVAL; @@ -710,12 +724,12 @@ static ssize_t __write_ports_addxprt(char *buf) if (err != 0) return err; - err = svc_create_xprt(nfsd_serv, transport, &init_net, + err = svc_create_xprt(nfsd_serv, transport, net, PF_INET, port, SVC_SOCK_ANONYMOUS); if (err < 0) goto out_err; - err = svc_create_xprt(nfsd_serv, transport, &init_net, + err = svc_create_xprt(nfsd_serv, transport, net, PF_INET6, port, SVC_SOCK_ANONYMOUS); if (err < 0 && err != -EAFNOSUPPORT) goto out_close; @@ -724,12 +738,14 @@ static ssize_t __write_ports_addxprt(char *buf) nfsd_serv->sv_nrthreads--; return 0; out_close: - xprt = svc_find_xprt(nfsd_serv, transport, &init_net, PF_INET, port); + xprt = svc_find_xprt(nfsd_serv, transport, net, PF_INET, port); if (xprt != NULL) { svc_close_xprt(xprt); svc_xprt_put(xprt); } out_err: + if (nfsd_serv->sv_nrthreads == 1) + svc_shutdown_net(nfsd_serv, net); svc_destroy(nfsd_serv); return err; } @@ -1127,7 +1143,34 @@ static int create_proc_exports_entry(void) #endif int nfsd_net_id; + +static __net_init int nfsd_init_net(struct net *net) +{ + int retval; + + retval = nfsd_export_init(net); + if (retval) + goto out_export_error; + retval = nfsd_idmap_init(net); + if (retval) + goto out_idmap_error; + return 0; + +out_idmap_error: + nfsd_export_shutdown(net); +out_export_error: + return retval; +} + +static __net_exit void nfsd_exit_net(struct net *net) +{ + nfsd_idmap_shutdown(net); + nfsd_export_shutdown(net); +} + static struct pernet_operations nfsd_net_ops = { + .init = nfsd_init_net, + .exit = nfsd_exit_net, .id = &nfsd_net_id, .size = sizeof(struct nfsd_net), }; @@ -1154,16 +1197,10 @@ static int __init init_nfsd(void) retval = nfsd_reply_cache_init(); if (retval) goto out_free_stat; - retval = nfsd_export_init(); - if (retval) - goto out_free_cache; nfsd_lockd_init(); /* lockd->nfsd callbacks */ - retval = nfsd_idmap_init(); - if (retval) - goto out_free_lockd; retval = create_proc_exports_entry(); if (retval) - goto out_free_idmap; + goto out_free_lockd; retval = register_filesystem(&nfsd_fs_type); if (retval) goto out_free_all; @@ -1171,12 +1208,8 @@ static int __init init_nfsd(void) out_free_all: remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); -out_free_idmap: - nfsd_idmap_shutdown(); out_free_lockd: nfsd_lockd_shutdown(); - nfsd_export_shutdown(); -out_free_cache: nfsd_reply_cache_shutdown(); out_free_stat: nfsd_stat_shutdown(); @@ -1192,13 +1225,11 @@ out_unregister_notifier: static void __exit exit_nfsd(void) { - nfsd_export_shutdown(); nfsd_reply_cache_shutdown(); remove_proc_entry("fs/nfs/exports", NULL); remove_proc_entry("fs/nfs", NULL); nfsd_stat_shutdown(); nfsd_lockd_shutdown(); - nfsd_idmap_shutdown(); nfsd4_free_slabs(); nfsd_fault_inject_cleanup(); unregister_filesystem(&nfsd_fs_type); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 68454e75fce..cc793005a87 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -636,7 +636,7 @@ fh_put(struct svc_fh *fhp) #endif } if (exp) { - cache_put(&exp->h, &svc_export_cache); + exp_put(exp); fhp->fh_export = NULL; } return; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 28dfad39f0c..ee709fc8f58 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/fs_struct.h> #include <linux/swap.h> +#include <linux/nsproxy.h> #include <linux/sunrpc/stats.h> #include <linux/sunrpc/svcsock.h> @@ -220,7 +221,7 @@ static int nfsd_startup(unsigned short port, int nrservs) ret = nfsd_init_socks(port); if (ret) goto out_racache; - ret = lockd_up(); + ret = lockd_up(&init_net); if (ret) goto out_racache; ret = nfs4_state_start(); @@ -229,7 +230,7 @@ static int nfsd_startup(unsigned short port, int nrservs) nfsd_up = true; return 0; out_lockd: - lockd_down(); + lockd_down(&init_net); out_racache: nfsd_racache_shutdown(); return ret; @@ -246,7 +247,7 @@ static void nfsd_shutdown(void) if (!nfsd_up) return; nfs4_state_shutdown(); - lockd_down(); + lockd_down(&init_net); nfsd_racache_shutdown(); nfsd_up = false; } @@ -261,7 +262,7 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net) printk(KERN_WARNING "nfsd: last server has exited, flushing export " "cache\n"); - nfsd_export_flush(); + nfsd_export_flush(net); } void nfsd_reset_versions(void) @@ -330,6 +331,8 @@ static int nfsd_get_default_max_blksize(void) int nfsd_create_serv(void) { + int error; + WARN_ON(!mutex_is_locked(&nfsd_mutex)); if (nfsd_serv) { svc_get(nfsd_serv); @@ -343,6 +346,12 @@ int nfsd_create_serv(void) if (nfsd_serv == NULL) return -ENOMEM; + error = svc_bind(nfsd_serv, current->nsproxy->net_ns); + if (error < 0) { + svc_destroy(nfsd_serv); + return error; + } + set_max_drc(); do_gettimeofday(&nfssvc_boot); /* record boot time */ return 0; @@ -373,6 +382,7 @@ int nfsd_set_nrthreads(int n, int *nthreads) int i = 0; int tot = 0; int err = 0; + struct net *net = &init_net; WARN_ON(!mutex_is_locked(&nfsd_mutex)); @@ -417,6 +427,9 @@ int nfsd_set_nrthreads(int n, int *nthreads) if (err) break; } + + if (nfsd_serv->sv_nrthreads == 1) + svc_shutdown_net(nfsd_serv, net); svc_destroy(nfsd_serv); return err; @@ -432,6 +445,7 @@ nfsd_svc(unsigned short port, int nrservs) { int error; bool nfsd_up_before; + struct net *net = &init_net; mutex_lock(&nfsd_mutex); dprintk("nfsd: creating service\n"); @@ -464,6 +478,8 @@ out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown(); out_destroy: + if (nfsd_serv->sv_nrthreads == 1) + svc_shutdown_net(nfsd_serv, net); svc_destroy(nfsd_serv); /* Release server */ out: mutex_unlock(&nfsd_mutex); @@ -547,6 +563,9 @@ nfsd(void *vrqstp) nfsdstats.th_cnt --; out: + if (rqstp->rq_server->sv_nrthreads == 1) + svc_shutdown_net(rqstp->rq_server, &init_net); + /* Release the thread */ svc_exit_thread(rqstp); @@ -659,8 +678,12 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) int nfsd_pool_stats_release(struct inode *inode, struct file *file) { int ret = seq_release(inode, file); + struct net *net = &init_net; + mutex_lock(&nfsd_mutex); /* this function really, really should have been called svc_put() */ + if (nfsd_serv->sv_nrthreads == 1) + svc_shutdown_net(nfsd_serv, net); svc_destroy(nfsd_serv); mutex_unlock(&nfsd_mutex); return ret; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 89ab137d379..849091e16ea 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -232,7 +232,6 @@ struct nfs4_client { time_t cl_time; /* time of last lease renewal */ struct sockaddr_storage cl_addr; /* client ipaddress */ u32 cl_flavor; /* setclientid pseudoflavor */ - char *cl_principal; /* setclientid principal name */ struct svc_cred cl_cred; /* setclientid principal */ clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 568666156ea..c8bd9c3be7f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -2039,7 +2039,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, if (err) goto out; - offset = vfs_llseek(file, offset, 0); + offset = vfs_llseek(file, offset, SEEK_SET); if (offset < 0) { err = nfserrno((int)offset); goto out_close; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 1b3501598ab..acd127d4ee8 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -60,7 +60,7 @@ struct nfsd4_compound_state { __be32 *datap; size_t iovlen; u32 minorversion; - u32 status; + __be32 status; stateid_t current_stateid; stateid_t save_stateid; /* to indicate current and saved state id presents */ @@ -364,7 +364,7 @@ struct nfsd4_test_stateid_id { }; struct nfsd4_test_stateid { - __be32 ts_num_ids; + u32 ts_num_ids; struct list_head ts_stateid_list; }; @@ -549,7 +549,7 @@ int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *, struct nfsd4_compoundargs *); int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *, struct nfsd4_compoundres *); -int nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); +__be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op); __be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 26601529dc1..62cebc8e1a1 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -37,6 +37,7 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) * This function should be implemented when the writeback function * will be implemented. */ + struct the_nilfs *nilfs; struct inode *inode = file->f_mapping->host; int err; @@ -45,18 +46,21 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) return err; mutex_lock(&inode->i_mutex); - if (!nilfs_inode_dirty(inode)) { - mutex_unlock(&inode->i_mutex); - return 0; + if (nilfs_inode_dirty(inode)) { + if (datasync) + err = nilfs_construct_dsync_segment(inode->i_sb, inode, + 0, LLONG_MAX); + else + err = nilfs_construct_segment(inode->i_sb); } - - if (datasync) - err = nilfs_construct_dsync_segment(inode->i_sb, inode, 0, - LLONG_MAX); - else - err = nilfs_construct_segment(inode->i_sb); - mutex_unlock(&inode->i_mutex); + + nilfs = inode->i_sb->s_fs_info; + if (!err && nilfs_test_opt(nilfs, BARRIER)) { + err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (err != -EIO) + err = 0; + } return err; } diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 08a07a218d2..57ceaf33d17 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -191,6 +191,8 @@ void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs) while (!list_empty(head)) { ii = list_first_entry(head, struct nilfs_inode_info, i_dirty); list_del_init(&ii->i_dirty); + truncate_inode_pages(&ii->vfs_inode.i_data, 0); + nilfs_btnode_cache_clear(&ii->i_btnode_cache); iput(&ii->vfs_inode); } } diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 8f7b95ac1f7..7cc64465ec2 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -734,7 +734,7 @@ void nilfs_evict_inode(struct inode *inode) if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) { if (inode->i_data.nrpages) truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); nilfs_clear_inode(inode); return; } @@ -746,7 +746,7 @@ void nilfs_evict_inode(struct inode *inode) /* TODO: some of the following operations may fail. */ nilfs_truncate_bmap(ii, 0); nilfs_mark_inode_dirty(inode); - end_writeback(inode); + clear_inode(inode); ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino); if (!ret) diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 2a70fce70c6..06658caa18b 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -692,8 +692,14 @@ static int nilfs_ioctl_sync(struct inode *inode, struct file *filp, if (ret < 0) return ret; + nilfs = inode->i_sb->s_fs_info; + if (nilfs_test_opt(nilfs, BARRIER)) { + ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (ret == -EIO) + return ret; + } + if (argp != NULL) { - nilfs = inode->i_sb->s_fs_info; down_read(&nilfs->ns_segctor_sem); cno = nilfs->ns_cno - 1; up_read(&nilfs->ns_segctor_sem); diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index fce2bbee66d..b72847988b7 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -441,7 +441,7 @@ static struct dentry *nilfs_get_parent(struct dentry *child) { unsigned long ino; struct inode *inode; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct nilfs_root *root; ino = nilfs_inode_by_name(child->d_inode, &dotdot); @@ -508,31 +508,29 @@ static struct dentry *nilfs_fh_to_parent(struct super_block *sb, struct fid *fh, return nilfs_get_dentry(sb, fid->cno, fid->parent_ino, fid->parent_gen); } -static int nilfs_encode_fh(struct dentry *dentry, __u32 *fh, int *lenp, - int connectable) +static int nilfs_encode_fh(struct inode *inode, __u32 *fh, int *lenp, + struct inode *parent) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; - struct inode *inode = dentry->d_inode; struct nilfs_root *root = NILFS_I(inode)->i_root; int type; - if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE || - (connectable && *lenp < NILFS_FID_SIZE_CONNECTABLE)) + if (parent && *lenp < NILFS_FID_SIZE_CONNECTABLE) { + *lenp = NILFS_FID_SIZE_CONNECTABLE; + return 255; + } + if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE) { + *lenp = NILFS_FID_SIZE_NON_CONNECTABLE; return 255; + } fid->cno = root->cno; fid->ino = inode->i_ino; fid->gen = inode->i_generation; - if (connectable && !S_ISDIR(inode->i_mode)) { - struct inode *parent; - - spin_lock(&dentry->d_lock); - parent = dentry->d_parent->d_inode; + if (parent) { fid->parent_ino = parent->i_ino; fid->parent_gen = parent->i_generation; - spin_unlock(&dentry->d_lock); - type = FILEID_NILFS_WITH_PARENT; *lenp = NILFS_FID_SIZE_CONNECTABLE; } else { diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0e72ad6f22a..88e11fb346b 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2309,6 +2309,8 @@ nilfs_remove_written_gcinodes(struct the_nilfs *nilfs, struct list_head *head) if (!test_bit(NILFS_I_UPDATED, &ii->i_state)) continue; list_del_init(&ii->i_dirty); + truncate_inode_pages(&ii->vfs_inode.i_data, 0); + nilfs_btnode_cache_clear(&ii->i_btnode_cache); iput(&ii->vfs_inode); } } diff --git a/fs/nls/Kconfig b/fs/nls/Kconfig index a39edc41bec..e2ce79ef48c 100644 --- a/fs/nls/Kconfig +++ b/fs/nls/Kconfig @@ -30,7 +30,7 @@ config NLS_DEFAULT cp949, cp950, cp1251, cp1255, euc-jp, euc-kr, gb2312, iso8859-1, iso8859-2, iso8859-3, iso8859-4, iso8859-5, iso8859-6, iso8859-7, iso8859-8, iso8859-9, iso8859-13, iso8859-14, iso8859-15, - koi8-r, koi8-ru, koi8-u, sjis, tis-620, utf8. + koi8-r, koi8-ru, koi8-u, sjis, tis-620, macroman, utf8. If you specify a wrong value, it will use the built-in NLS; compatible with iso8859-1. @@ -452,6 +452,161 @@ config NLS_KOI8_U input/output character sets. Say Y here for the preferred Ukrainian (koi8-u) and Belarusian (koi8-ru) character sets. +config NLS_MAC_ROMAN + tristate "Codepage macroman" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + much of Europe -- United Kingdom, Germany, Spain, Italy, and [add + more countries here]. + + If unsure, say Y. + +config NLS_MAC_CELTIC + tristate "Codepage macceltic" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Celtic. + + If unsure, say Y. + +config NLS_MAC_CENTEURO + tristate "Codepage maccenteuro" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Central Europe. + + If unsure, say Y. + +config NLS_MAC_CROATIAN + tristate "Codepage maccroatian" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Croatian. + + If unsure, say Y. + +config NLS_MAC_CYRILLIC + tristate "Codepage maccyrillic" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Cyrillic. + + If unsure, say Y. + +config NLS_MAC_GAELIC + tristate "Codepage macgaelic" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Gaelic. + + If unsure, say Y. + +config NLS_MAC_GREEK + tristate "Codepage macgreek" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Greek. + + If unsure, say Y. + +config NLS_MAC_ICELAND + tristate "Codepage maciceland" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Iceland. + + If unsure, say Y. + +config NLS_MAC_INUIT + tristate "Codepage macinuit" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Inuit. + + If unsure, say Y. + +config NLS_MAC_ROMANIAN + tristate "Codepage macromanian" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Romanian. + + If unsure, say Y. + +config NLS_MAC_TURKISH + tristate "Codepage macturkish" + ---help--- + The Apple HFS file system family can deal with filenames in + native language character sets. These character sets are stored in + so-called MAC codepages. You need to include the appropriate + codepage if you want to be able to read/write these filenames on + Mac partitions correctly. This does apply to the filenames + only, not to the file contents. You can include several codepages; + say Y here if you want to include the Mac codepage that is used for + Turkish. + + If unsure, say Y. + config NLS_UTF8 tristate "NLS UTF-8" help diff --git a/fs/nls/Makefile b/fs/nls/Makefile index f499dd7c390..8ae37c1b524 100644 --- a/fs/nls/Makefile +++ b/fs/nls/Makefile @@ -42,3 +42,14 @@ obj-$(CONFIG_NLS_ISO8859_15) += nls_iso8859-15.o obj-$(CONFIG_NLS_KOI8_R) += nls_koi8-r.o obj-$(CONFIG_NLS_KOI8_U) += nls_koi8-u.o nls_koi8-ru.o obj-$(CONFIG_NLS_UTF8) += nls_utf8.o +obj-$(CONFIG_NLS_MAC_CELTIC) += mac-celtic.o +obj-$(CONFIG_NLS_MAC_CENTEURO) += mac-centeuro.o +obj-$(CONFIG_NLS_MAC_CROATIAN) += mac-croatian.o +obj-$(CONFIG_NLS_MAC_CYRILLIC) += mac-cyrillic.o +obj-$(CONFIG_NLS_MAC_GAELIC) += mac-gaelic.o +obj-$(CONFIG_NLS_MAC_GREEK) += mac-greek.o +obj-$(CONFIG_NLS_MAC_ICELAND) += mac-iceland.o +obj-$(CONFIG_NLS_MAC_INUIT) += mac-inuit.o +obj-$(CONFIG_NLS_MAC_ROMANIAN) += mac-romanian.o +obj-$(CONFIG_NLS_MAC_ROMAN) += mac-roman.o +obj-$(CONFIG_NLS_MAC_TURKISH) += mac-turkish.o diff --git a/fs/nls/mac-celtic.c b/fs/nls/mac-celtic.c new file mode 100644 index 00000000000..634a8b717b0 --- /dev/null +++ b/fs/nls/mac-celtic.c @@ -0,0 +1,602 @@ +/* + * linux/fs/nls/mac-celtic.c + * + * Charset macceltic translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x00c6, 0x00d8, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x03c0, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x00e6, 0x00f8, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x00ff, 0x0178, 0x2044, 0x20ac, + 0x2039, 0x203a, 0x0176, 0x0177, + /* 0xe0 */ + 0x2021, 0x00b7, 0x1ef2, 0x1ef3, + 0x2030, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0x2663, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x00dd, 0x00fd, + 0x0174, 0x0175, 0x1e84, 0x1e85, + 0x1e80, 0x1e81, 0x1e82, 0x1e83, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0x00, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xf6, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xf7, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0xf8, 0xf9, 0xde, 0xdf, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page1e[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0xfc, 0xfd, 0xfe, 0xff, 0xfa, 0xfb, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0xe2, 0xe3, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ + 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page26[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, NULL, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, page1e, NULL, + page20, page21, page22, NULL, NULL, page25, page26, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x00-0x07 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x08-0x0f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x10-0x17 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x18-0x1f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x20-0x27 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x28-0x2f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x30-0x37 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x38-0x3f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x40-0x47 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x48-0x4f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x50-0x57 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x58-0x5f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x60-0x67 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x68-0x6f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x70-0x77 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x78-0x7f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x80-0x87 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x88-0x8f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x90-0x97 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x98-0x9f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa0-0xa7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa8-0xaf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb0-0xb7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb8-0xbf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc0-0xc7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc8-0xcf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd0-0xd7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd8-0xdf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe0-0xe7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe8-0xef */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf0-0xf7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macceltic", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macceltic(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macceltic(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macceltic) +module_exit(exit_nls_macceltic) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-centeuro.c b/fs/nls/mac-centeuro.c new file mode 100644 index 00000000000..979e6265ac5 --- /dev/null +++ b/fs/nls/mac-centeuro.c @@ -0,0 +1,532 @@ +/* + * linux/fs/nls/mac-centeuro.c + * + * Charset maccenteuro translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x0100, 0x0101, 0x00c9, + 0x0104, 0x00d6, 0x00dc, 0x00e1, + 0x0105, 0x010c, 0x00e4, 0x010d, + 0x0106, 0x0107, 0x00e9, 0x0179, + /* 0x90 */ + 0x017a, 0x010e, 0x00ed, 0x010f, + 0x0112, 0x0113, 0x0116, 0x00f3, + 0x0117, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x011a, 0x011b, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x0118, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x0119, + 0x00a8, 0x2260, 0x0123, 0x012e, + /* 0xb0 */ + 0x012f, 0x012a, 0x2264, 0x2265, + 0x012b, 0x0136, 0x2202, 0x2211, + 0x0142, 0x013b, 0x013c, 0x013d, + 0x013e, 0x0139, 0x013a, 0x0145, + /* 0xc0 */ + 0x0146, 0x0143, 0x00ac, 0x221a, + 0x0144, 0x0147, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x0148, + 0x0150, 0x00d5, 0x0151, 0x014c, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x014d, 0x0154, 0x0155, 0x0158, + 0x2039, 0x203a, 0x0159, 0x0156, + /* 0xe0 */ + 0x0157, 0x0160, 0x201a, 0x201e, + 0x0161, 0x015a, 0x015b, 0x00c1, + 0x0164, 0x0165, 0x00cd, 0x017d, + 0x017e, 0x016a, 0x00d3, 0x00d4, + /* 0xf0 */ + 0x016b, 0x016e, 0x00da, 0x016f, + 0x0170, 0x0171, 0x0172, 0x0173, + 0x00dd, 0x00fd, 0x0137, 0x017b, + 0x0141, 0x017c, 0x0122, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0x00, 0x00, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0x00, 0xc7, 0xc2, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xa1, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa6, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0xc8, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0xe7, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x83, 0x00, 0x00, 0x00, 0xea, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0xf2, 0x00, 0x86, 0xf8, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x00, 0x87, 0x00, 0x00, 0x8a, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x8e, 0x00, 0x00, 0x00, 0x92, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x9c, 0x00, 0x9f, 0xf9, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x81, 0x82, 0x00, 0x00, 0x84, 0x88, 0x8c, 0x8d, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x89, 0x8b, 0x91, 0x93, /* 0x08-0x0f */ + 0x00, 0x00, 0x94, 0x95, 0x00, 0x00, 0x96, 0x98, /* 0x10-0x17 */ + 0xa2, 0xab, 0x9d, 0x9e, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xfe, 0xae, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0xb1, 0xb4, 0x00, 0x00, 0xaf, 0xb0, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb5, 0xfa, /* 0x30-0x37 */ + 0x00, 0xbd, 0xbe, 0xb9, 0xba, 0xbb, 0xbc, 0x00, /* 0x38-0x3f */ + 0x00, 0xfc, 0xb8, 0xc1, 0xc4, 0xbf, 0xc0, 0xc5, /* 0x40-0x47 */ + 0xcb, 0x00, 0x00, 0x00, 0xcf, 0xd8, 0x00, 0x00, /* 0x48-0x4f */ + 0xcc, 0xce, 0x00, 0x00, 0xd9, 0xda, 0xdf, 0xe0, /* 0x50-0x57 */ + 0xdb, 0xde, 0xe5, 0xe6, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xe1, 0xe4, 0x00, 0x00, 0xe8, 0xe9, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0xed, 0xf0, 0x00, 0x00, 0xf1, 0xf3, /* 0x68-0x6f */ + 0xf4, 0xf5, 0xf6, 0xf7, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x8f, 0x90, 0xfb, 0xfd, 0xeb, 0xec, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "maccenteuro", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_maccenteuro(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_maccenteuro(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_maccenteuro) +module_exit(exit_nls_maccenteuro) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-croatian.c b/fs/nls/mac-croatian.c new file mode 100644 index 00000000000..dd3f675911e --- /dev/null +++ b/fs/nls/mac-croatian.c @@ -0,0 +1,602 @@ +/* + * linux/fs/nls/mac-croatian.c + * + * Charset maccroatian translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x0160, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x017d, 0x00d8, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x2206, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x0161, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x017e, 0x00f8, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x0106, 0x00ab, + 0x010c, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x0110, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0xf8ff, 0x00a9, 0x2044, 0x20ac, + 0x2039, 0x203a, 0x00c6, 0x00bb, + /* 0xe0 */ + 0x2013, 0x00b7, 0x201a, 0x201e, + 0x2030, 0x00c2, 0x0107, 0x00c1, + 0x010d, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0x0111, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x02c6, 0x02dc, + 0x00af, 0x03c0, 0x00cb, 0x02da, + 0x00b8, 0x00ca, 0x00e6, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xd9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0xfc, 0x00, 0xbc, 0xdf, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xde, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xfd, 0xfa, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xfe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0xe6, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0xc8, 0xe8, 0x00, 0x00, /* 0x08-0x0f */ + 0xd0, 0xf0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xa9, 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0xae, 0xbe, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0xfb, 0x00, 0xf7, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xf9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xe0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xb4, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char pagef8[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + pagef8, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "maccroatian", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_maccroatian(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_maccroatian(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_maccroatian) +module_exit(exit_nls_maccroatian) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-cyrillic.c b/fs/nls/mac-cyrillic.c new file mode 100644 index 00000000000..1112c84dd8b --- /dev/null +++ b/fs/nls/mac-cyrillic.c @@ -0,0 +1,497 @@ +/* + * linux/fs/nls/mac-cyrillic.c + * + * Charset maccyrillic translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x0410, 0x0411, 0x0412, 0x0413, + 0x0414, 0x0415, 0x0416, 0x0417, + 0x0418, 0x0419, 0x041a, 0x041b, + 0x041c, 0x041d, 0x041e, 0x041f, + /* 0x90 */ + 0x0420, 0x0421, 0x0422, 0x0423, + 0x0424, 0x0425, 0x0426, 0x0427, + 0x0428, 0x0429, 0x042a, 0x042b, + 0x042c, 0x042d, 0x042e, 0x042f, + /* 0xa0 */ + 0x2020, 0x00b0, 0x0490, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x0406, + 0x00ae, 0x00a9, 0x2122, 0x0402, + 0x0452, 0x2260, 0x0403, 0x0453, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x0456, 0x00b5, 0x0491, 0x0408, + 0x0404, 0x0454, 0x0407, 0x0457, + 0x0409, 0x0459, 0x040a, 0x045a, + /* 0xc0 */ + 0x0458, 0x0405, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x040b, + 0x045b, 0x040c, 0x045c, 0x0455, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x201e, + 0x040e, 0x045e, 0x040f, 0x045f, + 0x2116, 0x0401, 0x0451, 0x044f, + /* 0xe0 */ + 0x0430, 0x0431, 0x0432, 0x0433, + 0x0434, 0x0435, 0x0436, 0x0437, + 0x0438, 0x0439, 0x043a, 0x043b, + 0x043c, 0x043d, 0x043e, 0x043f, + /* 0xf0 */ + 0x0440, 0x0441, 0x0442, 0x0443, + 0x0444, 0x0445, 0x0446, 0x0447, + 0x0448, 0x0449, 0x044a, 0x044b, + 0x044c, 0x044d, 0x044e, 0x20ac, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0x00, 0x00, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0x00, 0xa9, 0x00, 0xc7, 0xc2, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0x00, 0xb5, 0xa6, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0xc8, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xd6, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page04[256] = { + 0x00, 0xdd, 0xab, 0xae, 0xb8, 0xc1, 0xa7, 0xba, /* 0x00-0x07 */ + 0xb7, 0xbc, 0xbe, 0xcb, 0xcd, 0x00, 0xd8, 0xda, /* 0x08-0x0f */ + 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x10-0x17 */ + 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x18-0x1f */ + 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x20-0x27 */ + 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x28-0x2f */ + 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x30-0x37 */ + 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x38-0x3f */ + 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, /* 0x40-0x47 */ + 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf, /* 0x48-0x4f */ + 0x00, 0xde, 0xac, 0xaf, 0xb9, 0xcf, 0xb4, 0xbb, /* 0x50-0x57 */ + 0xc0, 0xbd, 0xbf, 0xcc, 0xce, 0x00, 0xd9, 0xdb, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0xa2, 0xb6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0xd7, 0x00, /* 0x18-0x1f */ + 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xff, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xdc, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, NULL, NULL, page04, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "maccyrillic", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_maccyrillic(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_maccyrillic(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_maccyrillic) +module_exit(exit_nls_maccyrillic) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-gaelic.c b/fs/nls/mac-gaelic.c new file mode 100644 index 00000000000..2de9158409c --- /dev/null +++ b/fs/nls/mac-gaelic.c @@ -0,0 +1,567 @@ +/* + * linux/fs/nls/mac-gaelic.c + * + * Charset macgaelic translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x00c6, 0x00d8, + /* 0xb0 */ + 0x1e02, 0x00b1, 0x2264, 0x2265, + 0x1e03, 0x010a, 0x010b, 0x1e0a, + 0x1e0b, 0x1e1e, 0x1e1f, 0x0120, + 0x0121, 0x1e40, 0x00e6, 0x00f8, + /* 0xc0 */ + 0x1e41, 0x1e56, 0x1e57, 0x027c, + 0x0192, 0x017f, 0x1e60, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x1e61, 0x1e9b, + 0x00ff, 0x0178, 0x1e6a, 0x20ac, + 0x2039, 0x203a, 0x0176, 0x0177, + /* 0xe0 */ + 0x1e6b, 0x00b7, 0x1ef2, 0x1ef3, + 0x204a, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0x2663, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x00dd, 0x00fd, + 0x0174, 0x0175, 0x1e84, 0x1e85, + 0x1e80, 0x1e81, 0x1e82, 0x1e83, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0x00, 0xa2, 0xa3, 0x00, 0x00, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0x00, 0xc7, 0x00, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0x00, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0xc8, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xf6, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0x00, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xf7, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0xb5, 0xb6, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0xbb, 0xbc, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0xf8, 0xf9, 0xde, 0xdf, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc5, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page1e[256] = { + 0x00, 0x00, 0xb0, 0xb4, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0xb7, 0xb8, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb9, 0xba, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0xbd, 0xc0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc1, 0xc2, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xc6, 0xd6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0xda, 0xe0, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0xfc, 0xfd, 0xfe, 0xff, 0xfa, 0xfb, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0xe2, 0xe3, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ + 0xa0, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page26[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0xf0, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, page1e, NULL, + page20, page21, page22, NULL, NULL, NULL, page26, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x00-0x07 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x08-0x0f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x10-0x17 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x18-0x1f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x20-0x27 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x28-0x2f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x30-0x37 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x38-0x3f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x40-0x47 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x48-0x4f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x50-0x57 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x58-0x5f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x60-0x67 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x68-0x6f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x70-0x77 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x78-0x7f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x80-0x87 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x88-0x8f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x90-0x97 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x98-0x9f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa0-0xa7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa8-0xaf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb0-0xb7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb8-0xbf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc0-0xc7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc8-0xcf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd0-0xd7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd8-0xdf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe0-0xe7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe8-0xef */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf0-0xf7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macgaelic", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macgaelic(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macgaelic(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macgaelic) +module_exit(exit_nls_macgaelic) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-greek.c b/fs/nls/mac-greek.c new file mode 100644 index 00000000000..a8631008280 --- /dev/null +++ b/fs/nls/mac-greek.c @@ -0,0 +1,497 @@ +/* + * linux/fs/nls/mac-greek.c + * + * Charset macgreek translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00b9, 0x00b2, 0x00c9, + 0x00b3, 0x00d6, 0x00dc, 0x0385, + 0x00e0, 0x00e2, 0x00e4, 0x0384, + 0x00a8, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00a3, 0x2122, + 0x00ee, 0x00ef, 0x2022, 0x00bd, + 0x2030, 0x00f4, 0x00f6, 0x00a6, + 0x20ac, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x0393, 0x0394, 0x0398, + 0x039b, 0x039e, 0x03a0, 0x00df, + 0x00ae, 0x00a9, 0x03a3, 0x03aa, + 0x00a7, 0x2260, 0x00b0, 0x00b7, + /* 0xb0 */ + 0x0391, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x0392, 0x0395, 0x0396, + 0x0397, 0x0399, 0x039a, 0x039c, + 0x03a6, 0x03ab, 0x03a8, 0x03a9, + /* 0xc0 */ + 0x03ac, 0x039d, 0x00ac, 0x039f, + 0x03a1, 0x2248, 0x03a4, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x03a5, + 0x03a7, 0x0386, 0x0388, 0x0153, + /* 0xd0 */ + 0x2013, 0x2015, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x0389, + 0x038a, 0x038c, 0x038e, 0x03ad, + 0x03ae, 0x03af, 0x03cc, 0x038f, + /* 0xe0 */ + 0x03cd, 0x03b1, 0x03b2, 0x03c8, + 0x03b4, 0x03b5, 0x03c6, 0x03b3, + 0x03b7, 0x03b9, 0x03be, 0x03ba, + 0x03bb, 0x03bc, 0x03bd, 0x03bf, + /* 0xf0 */ + 0x03c0, 0x03ce, 0x03c1, 0x03c3, + 0x03c4, 0x03b8, 0x03c9, 0x03c2, + 0x03c7, 0x03c5, 0x03b6, 0x03ca, + 0x03cb, 0x0390, 0x03b0, 0x00ad, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0x00, 0x00, 0x92, 0x00, 0xb4, 0x9b, 0xac, /* 0xa0-0xa7 */ + 0x8c, 0xa9, 0x00, 0xc7, 0xc2, 0xff, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xae, 0xb1, 0x82, 0x84, 0x00, 0x00, 0x00, 0xaf, /* 0xb0-0xb7 */ + 0x00, 0x81, 0x00, 0xc8, 0x00, 0x97, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x80, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x83, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x85, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x00, 0x89, 0x00, 0x8a, 0x00, 0x00, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x00, 0x00, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x99, 0x00, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0x00, 0x9d, 0x00, 0x9e, 0x9f, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x8b, 0x87, 0xcd, 0x00, /* 0x80-0x87 */ + 0xce, 0xd7, 0xd8, 0x00, 0xd9, 0x00, 0xda, 0xdf, /* 0x88-0x8f */ + 0xfd, 0xb0, 0xb5, 0xa1, 0xa2, 0xb6, 0xb7, 0xb8, /* 0x90-0x97 */ + 0xa3, 0xb9, 0xba, 0xa4, 0xbb, 0xc1, 0xa5, 0xc3, /* 0x98-0x9f */ + 0xa6, 0xc4, 0x00, 0xaa, 0xc6, 0xcb, 0xbc, 0xcc, /* 0xa0-0xa7 */ + 0xbe, 0xbf, 0xab, 0xbd, 0xc0, 0xdb, 0xdc, 0xdd, /* 0xa8-0xaf */ + 0xfe, 0xe1, 0xe2, 0xe7, 0xe4, 0xe5, 0xfa, 0xe8, /* 0xb0-0xb7 */ + 0xf5, 0xe9, 0xeb, 0xec, 0xed, 0xee, 0xea, 0xef, /* 0xb8-0xbf */ + 0xf0, 0xf2, 0xf7, 0xf3, 0xf4, 0xf9, 0xe6, 0xf8, /* 0xc0-0xc7 */ + 0xe3, 0xf6, 0xfb, 0xfc, 0xde, 0xe0, 0xf1, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0x00, 0xd1, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ + 0xa0, 0x00, 0x96, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x98, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x9c, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x93, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, NULL, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macgreek", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macgreek(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macgreek(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macgreek) +module_exit(exit_nls_macgreek) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-iceland.c b/fs/nls/mac-iceland.c new file mode 100644 index 00000000000..babe2998d5c --- /dev/null +++ b/fs/nls/mac-iceland.c @@ -0,0 +1,602 @@ +/* + * linux/fs/nls/mac-iceland.c + * + * Charset maciceland translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x00dd, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x00c6, 0x00d8, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x03c0, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x00e6, 0x00f8, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x00ff, 0x0178, 0x2044, 0x20ac, + 0x00d0, 0x00f0, 0x00de, 0x00fe, + /* 0xe0 */ + 0x00fd, 0x00b7, 0x201a, 0x201e, + 0x2030, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0xf8ff, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x02c6, 0x02dc, + 0x00af, 0x02d8, 0x02d9, 0x02da, + 0x00b8, 0x02dd, 0x02db, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0xfc, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0xdc, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0xa0, 0xde, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0xdd, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0xe0, 0xdf, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0xf9, 0xfa, 0xfb, 0xfe, 0xf7, 0xfd, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char pagef8[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + pagef8, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "maciceland", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_maciceland(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_maciceland(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_maciceland) +module_exit(exit_nls_maciceland) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-inuit.c b/fs/nls/mac-inuit.c new file mode 100644 index 00000000000..312364f010d --- /dev/null +++ b/fs/nls/mac-inuit.c @@ -0,0 +1,532 @@ +/* + * linux/fs/nls/mac-inuit.c + * + * Charset macinuit translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x1403, 0x1404, 0x1405, 0x1406, + 0x140a, 0x140b, 0x1431, 0x1432, + 0x1433, 0x1434, 0x1438, 0x1439, + 0x1449, 0x144e, 0x144f, 0x1450, + /* 0x90 */ + 0x1451, 0x1455, 0x1456, 0x1466, + 0x146d, 0x146e, 0x146f, 0x1470, + 0x1472, 0x1473, 0x1483, 0x148b, + 0x148c, 0x148d, 0x148e, 0x1490, + /* 0xa0 */ + 0x1491, 0x00b0, 0x14a1, 0x14a5, + 0x14a6, 0x2022, 0x00b6, 0x14a7, + 0x00ae, 0x00a9, 0x2122, 0x14a8, + 0x14aa, 0x14ab, 0x14bb, 0x14c2, + /* 0xb0 */ + 0x14c3, 0x14c4, 0x14c5, 0x14c7, + 0x14c8, 0x14d0, 0x14ef, 0x14f0, + 0x14f1, 0x14f2, 0x14f4, 0x14f5, + 0x1505, 0x14d5, 0x14d6, 0x14d7, + /* 0xc0 */ + 0x14d8, 0x14da, 0x14db, 0x14ea, + 0x1528, 0x1529, 0x152a, 0x152b, + 0x152d, 0x2026, 0x00a0, 0x152e, + 0x153e, 0x1555, 0x1556, 0x1557, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x1558, 0x1559, + 0x155a, 0x155d, 0x1546, 0x1547, + 0x1548, 0x1549, 0x154b, 0x154c, + /* 0xe0 */ + 0x1550, 0x157f, 0x1580, 0x1581, + 0x1582, 0x1583, 0x1584, 0x1585, + 0x158f, 0x1590, 0x1591, 0x1592, + 0x1593, 0x1594, 0x1595, 0x1671, + /* 0xf0 */ + 0x1672, 0x1673, 0x1674, 0x1675, + 0x1676, 0x1596, 0x15a0, 0x15a1, + 0x15a2, 0x15a3, 0x15a4, 0x15a5, + 0x15a6, 0x157c, 0x0141, 0x0142, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xa9, 0x00, 0x00, 0x00, 0x00, 0xa8, 0x00, /* 0xa8-0xaf */ + 0xa1, 0x00, 0x00, 0x00, 0x00, 0x00, 0xa6, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0xfe, 0xff, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page14[256] = { + 0x00, 0x00, 0x00, 0x80, 0x81, 0x82, 0x83, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x84, 0x85, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x86, 0x87, 0x88, 0x89, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x8a, 0x8b, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x8c, 0x00, 0x00, 0x00, 0x00, 0x8d, 0x8e, /* 0x48-0x4f */ + 0x8f, 0x90, 0x00, 0x00, 0x00, 0x91, 0x92, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x93, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x94, 0x95, 0x96, /* 0x68-0x6f */ + 0x97, 0x00, 0x98, 0x99, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x9a, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x9b, 0x9c, 0x9d, 0x9e, 0x00, /* 0x88-0x8f */ + 0x9f, 0xa0, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0xa2, 0x00, 0x00, 0x00, 0xa3, 0xa4, 0xa7, /* 0xa0-0xa7 */ + 0xab, 0x00, 0xac, 0xad, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0xae, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0xaf, 0xb0, 0xb1, 0xb2, 0x00, 0xb3, /* 0xc0-0xc7 */ + 0xb4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0xb5, 0x00, 0x00, 0x00, 0x00, 0xbd, 0xbe, 0xbf, /* 0xd0-0xd7 */ + 0xc0, 0x00, 0xc1, 0xc2, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0x00, 0xb6, /* 0xe8-0xef */ + 0xb7, 0xb8, 0xb9, 0x00, 0xba, 0xbb, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page15[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0xbc, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0xc4, 0xc5, 0xc6, 0xc7, 0x00, 0xc8, 0xcb, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xcc, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xda, 0xdb, /* 0x40-0x47 */ + 0xdc, 0xdd, 0x00, 0xde, 0xdf, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0xe0, 0x00, 0x00, 0x00, 0x00, 0xcd, 0xce, 0xcf, /* 0x50-0x57 */ + 0xd6, 0xd7, 0xd8, 0x00, 0x00, 0xd9, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0xfd, 0x00, 0x00, 0xe1, /* 0x78-0x7f */ + 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xe8, /* 0x88-0x8f */ + 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xf5, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page16[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0x00, 0x00, 0xd2, 0xd3, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, page14, page15, page16, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x00-0x07 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x08-0x0f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x10-0x17 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x18-0x1f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x20-0x27 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x28-0x2f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x30-0x37 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x38-0x3f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x40-0x47 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x48-0x4f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x50-0x57 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x58-0x5f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x60-0x67 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x68-0x6f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x70-0x77 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x78-0x7f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x80-0x87 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x88-0x8f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x90-0x97 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0x98-0x9f */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa0-0xa7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xa8-0xaf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb0-0xb7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xb8-0xbf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc0-0xc7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xc8-0xcf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd0-0xd7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xd8-0xdf */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe0-0xe7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xe8-0xef */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf0-0xf7 */ + 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macinuit", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macinuit(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macinuit(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macinuit) +module_exit(exit_nls_macinuit) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-roman.c b/fs/nls/mac-roman.c new file mode 100644 index 00000000000..53ce0809cbd --- /dev/null +++ b/fs/nls/mac-roman.c @@ -0,0 +1,637 @@ +/* + * linux/fs/nls/mac-roman.c + * + * Charset macroman translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x00c6, 0x00d8, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x03c0, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x00e6, 0x00f8, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x00ff, 0x0178, 0x2044, 0x20ac, + 0x2039, 0x203a, 0xfb01, 0xfb02, + /* 0xe0 */ + 0x2021, 0x00b7, 0x201a, 0x201e, + 0x2030, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0xf8ff, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x02c6, 0x02dc, + 0x00af, 0x02d8, 0x02d9, 0x02da, + 0x00b8, 0x02dd, 0x02db, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0xfc, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0x00, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0xf9, 0xfa, 0xfb, 0xfe, 0xf7, 0xfd, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char pagef8[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, /* 0xf8-0xff */ +}; + +static const unsigned char pagefb[256] = { + 0x00, 0xde, 0xdf, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + pagef8, NULL, NULL, pagefb, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macroman", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macroman(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macroman(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macroman) +module_exit(exit_nls_macroman) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-romanian.c b/fs/nls/mac-romanian.c new file mode 100644 index 00000000000..add6f7a0c66 --- /dev/null +++ b/fs/nls/mac-romanian.c @@ -0,0 +1,602 @@ +/* + * linux/fs/nls/mac-romanian.c + * + * Charset macromanian translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x0102, 0x0218, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x03c0, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x0103, 0x0219, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x00ff, 0x0178, 0x2044, 0x20ac, + 0x2039, 0x203a, 0x021a, 0x021b, + /* 0xe0 */ + 0x2021, 0x00b7, 0x201a, 0x201e, + 0x2030, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0xf8ff, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0x0131, 0x02c6, 0x02dc, + 0x00af, 0x02d8, 0x02d9, 0x02da, + 0x00b8, 0x02dd, 0x02db, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0xfc, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0x00, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0x00, 0xf4, 0xf2, 0xf3, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0x00, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0x00, 0x9d, 0x9c, 0x9e, 0x9f, 0x00, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0xae, 0xbe, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xaf, 0xbf, 0xde, 0xdf, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0xf9, 0xfa, 0xfb, 0xfe, 0xf7, 0xfd, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0xda, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0xdb, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char pagef8[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + pagef8, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macromanian", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macromanian(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macromanian(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macromanian) +module_exit(exit_nls_macromanian) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/nls/mac-turkish.c b/fs/nls/mac-turkish.c new file mode 100644 index 00000000000..dffa96d5de0 --- /dev/null +++ b/fs/nls/mac-turkish.c @@ -0,0 +1,602 @@ +/* + * linux/fs/nls/mac-turkish.c + * + * Charset macturkish translation tables. + * Generated automatically from the Unicode and charset + * tables from the Unicode Organization (www.unicode.org). + * The Unicode to charset table has only exact mappings. + */ + +/* + * COPYRIGHT AND PERMISSION NOTICE + * + * Copyright 1991-2012 Unicode, Inc. All rights reserved. Distributed under + * the Terms of Use in http://www.unicode.org/copyright.html. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of the Unicode data files and any associated documentation (the "Data + * Files") or Unicode software and any associated documentation (the + * "Software") to deal in the Data Files or Software without restriction, + * including without limitation the rights to use, copy, modify, merge, + * publish, distribute, and/or sell copies of the Data Files or Software, and + * to permit persons to whom the Data Files or Software are furnished to do + * so, provided that (a) the above copyright notice(s) and this permission + * notice appear with all copies of the Data Files or Software, (b) both the + * above copyright notice(s) and this permission notice appear in associated + * documentation, and (c) there is clear notice in each modified Data File or + * in the Software as well as in the documentation associated with the Data + * File(s) or Software that the data or software has been modified. + * + * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY + * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF + * THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS + * INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT + * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF + * USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR + * OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR + * PERFORMANCE OF THE DATA FILES OR SOFTWARE. + * + * Except as contained in this notice, the name of a copyright holder shall + * not be used in advertising or otherwise to promote the sale, use or other + * dealings in these Data Files or Software without prior written + * authorization of the copyright holder. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/errno.h> + +static const wchar_t charset2uni[256] = { + /* 0x00 */ + 0x0000, 0x0001, 0x0002, 0x0003, + 0x0004, 0x0005, 0x0006, 0x0007, + 0x0008, 0x0009, 0x000a, 0x000b, + 0x000c, 0x000d, 0x000e, 0x000f, + /* 0x10 */ + 0x0010, 0x0011, 0x0012, 0x0013, + 0x0014, 0x0015, 0x0016, 0x0017, + 0x0018, 0x0019, 0x001a, 0x001b, + 0x001c, 0x001d, 0x001e, 0x001f, + /* 0x20 */ + 0x0020, 0x0021, 0x0022, 0x0023, + 0x0024, 0x0025, 0x0026, 0x0027, + 0x0028, 0x0029, 0x002a, 0x002b, + 0x002c, 0x002d, 0x002e, 0x002f, + /* 0x30 */ + 0x0030, 0x0031, 0x0032, 0x0033, + 0x0034, 0x0035, 0x0036, 0x0037, + 0x0038, 0x0039, 0x003a, 0x003b, + 0x003c, 0x003d, 0x003e, 0x003f, + /* 0x40 */ + 0x0040, 0x0041, 0x0042, 0x0043, + 0x0044, 0x0045, 0x0046, 0x0047, + 0x0048, 0x0049, 0x004a, 0x004b, + 0x004c, 0x004d, 0x004e, 0x004f, + /* 0x50 */ + 0x0050, 0x0051, 0x0052, 0x0053, + 0x0054, 0x0055, 0x0056, 0x0057, + 0x0058, 0x0059, 0x005a, 0x005b, + 0x005c, 0x005d, 0x005e, 0x005f, + /* 0x60 */ + 0x0060, 0x0061, 0x0062, 0x0063, + 0x0064, 0x0065, 0x0066, 0x0067, + 0x0068, 0x0069, 0x006a, 0x006b, + 0x006c, 0x006d, 0x006e, 0x006f, + /* 0x70 */ + 0x0070, 0x0071, 0x0072, 0x0073, + 0x0074, 0x0075, 0x0076, 0x0077, + 0x0078, 0x0079, 0x007a, 0x007b, + 0x007c, 0x007d, 0x007e, 0x007f, + /* 0x80 */ + 0x00c4, 0x00c5, 0x00c7, 0x00c9, + 0x00d1, 0x00d6, 0x00dc, 0x00e1, + 0x00e0, 0x00e2, 0x00e4, 0x00e3, + 0x00e5, 0x00e7, 0x00e9, 0x00e8, + /* 0x90 */ + 0x00ea, 0x00eb, 0x00ed, 0x00ec, + 0x00ee, 0x00ef, 0x00f1, 0x00f3, + 0x00f2, 0x00f4, 0x00f6, 0x00f5, + 0x00fa, 0x00f9, 0x00fb, 0x00fc, + /* 0xa0 */ + 0x2020, 0x00b0, 0x00a2, 0x00a3, + 0x00a7, 0x2022, 0x00b6, 0x00df, + 0x00ae, 0x00a9, 0x2122, 0x00b4, + 0x00a8, 0x2260, 0x00c6, 0x00d8, + /* 0xb0 */ + 0x221e, 0x00b1, 0x2264, 0x2265, + 0x00a5, 0x00b5, 0x2202, 0x2211, + 0x220f, 0x03c0, 0x222b, 0x00aa, + 0x00ba, 0x03a9, 0x00e6, 0x00f8, + /* 0xc0 */ + 0x00bf, 0x00a1, 0x00ac, 0x221a, + 0x0192, 0x2248, 0x2206, 0x00ab, + 0x00bb, 0x2026, 0x00a0, 0x00c0, + 0x00c3, 0x00d5, 0x0152, 0x0153, + /* 0xd0 */ + 0x2013, 0x2014, 0x201c, 0x201d, + 0x2018, 0x2019, 0x00f7, 0x25ca, + 0x00ff, 0x0178, 0x011e, 0x011f, + 0x0130, 0x0131, 0x015e, 0x015f, + /* 0xe0 */ + 0x2021, 0x00b7, 0x201a, 0x201e, + 0x2030, 0x00c2, 0x00ca, 0x00c1, + 0x00cb, 0x00c8, 0x00cd, 0x00ce, + 0x00cf, 0x00cc, 0x00d3, 0x00d4, + /* 0xf0 */ + 0xf8ff, 0x00d2, 0x00da, 0x00db, + 0x00d9, 0xf8a0, 0x02c6, 0x02dc, + 0x00af, 0x02d8, 0x02d9, 0x02da, + 0x00b8, 0x02dd, 0x02db, 0x02c7, +}; + +static const unsigned char page00[256] = { + 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ + 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ + 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ + 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ + 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ + 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ + 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ + 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ + 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ + 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ + 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ + 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ + 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ + 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ + 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ + 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xca, 0xc1, 0xa2, 0xa3, 0x00, 0xb4, 0x00, 0xa4, /* 0xa0-0xa7 */ + 0xac, 0xa9, 0xbb, 0xc7, 0xc2, 0x00, 0xa8, 0xf8, /* 0xa8-0xaf */ + 0xa1, 0xb1, 0x00, 0x00, 0xab, 0xb5, 0xa6, 0xe1, /* 0xb0-0xb7 */ + 0xfc, 0x00, 0xbc, 0xc8, 0x00, 0x00, 0x00, 0xc0, /* 0xb8-0xbf */ + 0xcb, 0xe7, 0xe5, 0xcc, 0x80, 0x81, 0xae, 0x82, /* 0xc0-0xc7 */ + 0xe9, 0x83, 0xe6, 0xe8, 0xed, 0xea, 0xeb, 0xec, /* 0xc8-0xcf */ + 0x00, 0x84, 0xf1, 0xee, 0xef, 0xcd, 0x85, 0x00, /* 0xd0-0xd7 */ + 0xaf, 0xf4, 0xf2, 0xf3, 0x86, 0x00, 0x00, 0xa7, /* 0xd8-0xdf */ + 0x88, 0x87, 0x89, 0x8b, 0x8a, 0x8c, 0xbe, 0x8d, /* 0xe0-0xe7 */ + 0x8f, 0x8e, 0x90, 0x91, 0x93, 0x92, 0x94, 0x95, /* 0xe8-0xef */ + 0x00, 0x96, 0x98, 0x97, 0x99, 0x9b, 0x9a, 0xd6, /* 0xf0-0xf7 */ + 0xbf, 0x9d, 0x9c, 0x9e, 0x9f, 0x00, 0x00, 0xd8, /* 0xf8-0xff */ +}; + +static const unsigned char page01[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xda, 0xdb, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xdc, 0xdd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0xce, 0xcf, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xde, 0xdf, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0xd9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0xc4, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page02[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf6, 0xff, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0xf9, 0xfa, 0xfb, 0xfe, 0xf7, 0xfd, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page03[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0xbd, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0xb9, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page20[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0xd0, 0xd1, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0xd4, 0xd5, 0xe2, 0x00, 0xd2, 0xd3, 0xe3, 0x00, /* 0x18-0x1f */ + 0xa0, 0xe0, 0xa5, 0x00, 0x00, 0x00, 0xc9, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0xe4, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page21[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0xaa, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page22[256] = { + 0x00, 0x00, 0xb6, 0x00, 0x00, 0x00, 0xc6, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xb8, /* 0x08-0x0f */ + 0x00, 0xb7, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0xc3, 0x00, 0x00, 0x00, 0xb0, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0xba, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0xc5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0xad, 0x00, 0x00, 0x00, 0xb2, 0xb3, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char page25[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0xd7, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ +}; + +static const unsigned char pagef8[256] = { + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x08-0x0f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x18-0x1f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x20-0x27 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x28-0x2f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x40-0x47 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x48-0x4f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x60-0x67 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x70-0x77 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x78-0x7f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x80-0x87 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x88-0x8f */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x90-0x97 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x98-0x9f */ + 0xf5, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xa8-0xaf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb8-0xbf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc0-0xc7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xc8-0xcf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd0-0xd7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe0-0xe7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xe8-0xef */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xf0, /* 0xf8-0xff */ +}; + +static const unsigned char *const page_uni2charset[256] = { + page00, page01, page02, page03, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + page20, page21, page22, NULL, NULL, page25, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + pagef8, NULL, NULL, NULL, NULL, NULL, NULL, NULL, +}; + +static const unsigned char charset2lower[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static const unsigned char charset2upper[256] = { + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x00-0x07 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x08-0x0f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x10-0x17 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x18-0x1f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x20-0x27 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x28-0x2f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x30-0x37 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x38-0x3f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x40-0x47 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x48-0x4f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x50-0x57 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x58-0x5f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x60-0x67 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x68-0x6f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x70-0x77 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x78-0x7f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x80-0x87 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x88-0x8f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x90-0x97 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0x98-0x9f */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa0-0xa7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xa8-0xaf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb0-0xb7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xb8-0xbf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc0-0xc7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xc8-0xcf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd0-0xd7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xd8-0xdf */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe0-0xe7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xe8-0xef */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf0-0xf7 */ + 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, /* 0xf8-0xff */ +}; + +static int uni2char(wchar_t uni, unsigned char *out, int boundlen) +{ + const unsigned char *uni2charset; + unsigned char cl = uni & 0x00ff; + unsigned char ch = (uni & 0xff00) >> 8; + + if (boundlen <= 0) + return -ENAMETOOLONG; + + uni2charset = page_uni2charset[ch]; + if (uni2charset && uni2charset[cl]) + out[0] = uni2charset[cl]; + else + return -EINVAL; + return 1; +} + +static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) +{ + *uni = charset2uni[*rawstring]; + if (*uni == 0x0000) + return -EINVAL; + return 1; +} + +static struct nls_table table = { + .charset = "macturkish", + .uni2char = uni2char, + .char2uni = char2uni, + .charset2lower = charset2lower, + .charset2upper = charset2upper, + .owner = THIS_MODULE, +}; + +static int __init init_nls_macturkish(void) +{ + return register_nls(&table); +} + +static void __exit exit_nls_macturkish(void) +{ + unregister_nls(&table); +} + +module_init(init_nls_macturkish) +module_exit(exit_nls_macturkish) + +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index ccb14d3fc0d..b39c5c161ad 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -123,7 +123,7 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) } EXPORT_SYMBOL_GPL(__fsnotify_parent); -static int send_to_group(struct inode *to_tell, struct vfsmount *mnt, +static int send_to_group(struct inode *to_tell, struct fsnotify_mark *inode_mark, struct fsnotify_mark *vfsmount_mark, __u32 mask, void *data, @@ -168,10 +168,10 @@ static int send_to_group(struct inode *to_tell, struct vfsmount *mnt, vfsmount_test_mask &= ~inode_mark->ignored_mask; } - pr_debug("%s: group=%p to_tell=%p mnt=%p mask=%x inode_mark=%p" + pr_debug("%s: group=%p to_tell=%p mask=%x inode_mark=%p" " inode_test_mask=%x vfsmount_mark=%p vfsmount_test_mask=%x" " data=%p data_is=%d cookie=%d event=%p\n", - __func__, group, to_tell, mnt, mask, inode_mark, + __func__, group, to_tell, mask, inode_mark, inode_test_mask, vfsmount_mark, vfsmount_test_mask, data, data_is, cookie, *event); @@ -258,16 +258,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, if (inode_group > vfsmount_group) { /* handle inode */ - ret = send_to_group(to_tell, NULL, inode_mark, NULL, mask, data, + ret = send_to_group(to_tell, inode_mark, NULL, mask, data, data_is, cookie, file_name, &event); /* we didn't use the vfsmount_mark */ vfsmount_group = NULL; } else if (vfsmount_group > inode_group) { - ret = send_to_group(to_tell, &mnt->mnt, NULL, vfsmount_mark, mask, data, + ret = send_to_group(to_tell, NULL, vfsmount_mark, mask, data, data_is, cookie, file_name, &event); inode_group = NULL; } else { - ret = send_to_group(to_tell, &mnt->mnt, inode_mark, vfsmount_mark, + ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask, data, data_is, cookie, file_name, &event); } diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 8639169221c..7389d2d5e51 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2096,7 +2096,9 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, err = file_remove_suid(file); if (err) goto out; - file_update_time(file); + err = file_update_time(file); + if (err) + goto out; written = ntfs_file_buffered_write(iocb, iov, nr_segs, pos, ppos, count); out: diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 2eaa6665294..c6dbd3db6ca 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2258,7 +2258,7 @@ void ntfs_evict_big_inode(struct inode *vi) ntfs_inode *ni = NTFS_I(vi); truncate_inode_pages(&vi->i_data, 0); - end_writeback(vi); + clear_inode(vi); #ifdef NTFS_RW if (NInoDirty(ni)) { diff --git a/fs/ocfs2/blockcheck.c b/fs/ocfs2/blockcheck.c index c7ee03c2222..0725e605465 100644 --- a/fs/ocfs2/blockcheck.c +++ b/fs/ocfs2/blockcheck.c @@ -422,45 +422,46 @@ int ocfs2_block_check_validate(void *data, size_t blocksize, struct ocfs2_blockcheck_stats *stats) { int rc = 0; - struct ocfs2_block_check check; + u32 bc_crc32e; + u16 bc_ecc; u32 crc, ecc; ocfs2_blockcheck_inc_check(stats); - check.bc_crc32e = le32_to_cpu(bc->bc_crc32e); - check.bc_ecc = le16_to_cpu(bc->bc_ecc); + bc_crc32e = le32_to_cpu(bc->bc_crc32e); + bc_ecc = le16_to_cpu(bc->bc_ecc); memset(bc, 0, sizeof(struct ocfs2_block_check)); /* Fast path - if the crc32 validates, we're good to go */ crc = crc32_le(~0, data, blocksize); - if (crc == check.bc_crc32e) + if (crc == bc_crc32e) goto out; ocfs2_blockcheck_inc_failure(stats); mlog(ML_ERROR, "CRC32 failed: stored: 0x%x, computed 0x%x. Applying ECC.\n", - (unsigned int)check.bc_crc32e, (unsigned int)crc); + (unsigned int)bc_crc32e, (unsigned int)crc); /* Ok, try ECC fixups */ ecc = ocfs2_hamming_encode_block(data, blocksize); - ocfs2_hamming_fix_block(data, blocksize, ecc ^ check.bc_ecc); + ocfs2_hamming_fix_block(data, blocksize, ecc ^ bc_ecc); /* And check the crc32 again */ crc = crc32_le(~0, data, blocksize); - if (crc == check.bc_crc32e) { + if (crc == bc_crc32e) { ocfs2_blockcheck_inc_recover(stats); goto out; } mlog(ML_ERROR, "Fixed CRC32 failed: stored: 0x%x, computed 0x%x\n", - (unsigned int)check.bc_crc32e, (unsigned int)crc); + (unsigned int)bc_crc32e, (unsigned int)crc); rc = -EIO; out: - bc->bc_crc32e = cpu_to_le32(check.bc_crc32e); - bc->bc_ecc = cpu_to_le16(check.bc_ecc); + bc->bc_crc32e = cpu_to_le32(bc_crc32e); + bc->bc_ecc = cpu_to_le16(bc_ecc); return rc; } @@ -528,7 +529,8 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, struct ocfs2_blockcheck_stats *stats) { int i, rc = 0; - struct ocfs2_block_check check; + u32 bc_crc32e; + u16 bc_ecc; u32 crc, ecc, fix; BUG_ON(nr < 0); @@ -538,21 +540,21 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, ocfs2_blockcheck_inc_check(stats); - check.bc_crc32e = le32_to_cpu(bc->bc_crc32e); - check.bc_ecc = le16_to_cpu(bc->bc_ecc); + bc_crc32e = le32_to_cpu(bc->bc_crc32e); + bc_ecc = le16_to_cpu(bc->bc_ecc); memset(bc, 0, sizeof(struct ocfs2_block_check)); /* Fast path - if the crc32 validates, we're good to go */ for (i = 0, crc = ~0; i < nr; i++) crc = crc32_le(crc, bhs[i]->b_data, bhs[i]->b_size); - if (crc == check.bc_crc32e) + if (crc == bc_crc32e) goto out; ocfs2_blockcheck_inc_failure(stats); mlog(ML_ERROR, "CRC32 failed: stored: %u, computed %u. Applying ECC.\n", - (unsigned int)check.bc_crc32e, (unsigned int)crc); + (unsigned int)bc_crc32e, (unsigned int)crc); /* Ok, try ECC fixups */ for (i = 0, ecc = 0; i < nr; i++) { @@ -565,7 +567,7 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, bhs[i]->b_size * 8, bhs[i]->b_size * 8 * i); } - fix = ecc ^ check.bc_ecc; + fix = ecc ^ bc_ecc; for (i = 0; i < nr; i++) { /* * Try the fix against each buffer. It will only affect @@ -578,19 +580,19 @@ int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr, /* And check the crc32 again */ for (i = 0, crc = ~0; i < nr; i++) crc = crc32_le(crc, bhs[i]->b_data, bhs[i]->b_size); - if (crc == check.bc_crc32e) { + if (crc == bc_crc32e) { ocfs2_blockcheck_inc_recover(stats); goto out; } mlog(ML_ERROR, "Fixed CRC32 failed: stored: %u, computed %u\n", - (unsigned int)check.bc_crc32e, (unsigned int)crc); + (unsigned int)bc_crc32e, (unsigned int)crc); rc = -EIO; out: - bc->bc_crc32e = cpu_to_le32(check.bc_crc32e); - bc->bc_ecc = cpu_to_le16(check.bc_ecc); + bc->bc_crc32e = cpu_to_le32(bc_crc32e); + bc->bc_ecc = cpu_to_le16(bc_ecc); return rc; } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 044e7b58d31..1bfe8802cc1 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -2005,7 +2005,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port) o2net_listen_sock = sock; INIT_WORK(&o2net_listen_work, o2net_accept_many); - sock->sk->sk_reuse = 1; + sock->sk->sk_reuse = SK_CAN_REUSE; ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin)); if (ret < 0) { printk(KERN_ERR "o2net: Error %d while binding socket at " diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c index 3a3ed4bb794..fbec0be6232 100644 --- a/fs/ocfs2/dlm/dlmast.c +++ b/fs/ocfs2/dlm/dlmast.c @@ -293,7 +293,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data, struct dlm_proxy_ast *past = (struct dlm_proxy_ast *) msg->buf; char *name; struct list_head *iter, *head=NULL; - u64 cookie; + __be64 cookie; u32 flags; u8 node; diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index a5952ceecba..de854cca12a 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -679,7 +679,7 @@ struct dlm_query_join_packet { }; union dlm_query_join_response { - u32 intval; + __be32 intval; struct dlm_query_join_packet packet; }; @@ -755,8 +755,8 @@ struct dlm_query_region { struct dlm_node_info { u8 ni_nodenum; u8 pad1; - u16 ni_ipv4_port; - u32 ni_ipv4_address; + __be16 ni_ipv4_port; + __be32 ni_ipv4_address; }; struct dlm_query_nodeinfo { diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 92f2ead0fab..9e89d70df33 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -818,7 +818,7 @@ static void dlm_query_join_packet_to_wire(struct dlm_query_join_packet *packet, union dlm_query_join_response response; response.packet = *packet; - *wire = cpu_to_be32(response.intval); + *wire = be32_to_cpu(response.intval); } static void dlm_query_join_wire_to_packet(u32 wire, diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c index 3b5825ef319..e31d6ae013a 100644 --- a/fs/ocfs2/dlmfs/dlmfs.c +++ b/fs/ocfs2/dlmfs/dlmfs.c @@ -367,7 +367,7 @@ static void dlmfs_evict_inode(struct inode *inode) int status; struct dlmfs_inode_private *ip; - end_writeback(inode); + clear_inode(inode); mlog(0, "inode %lu\n", inode->i_ino); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 81a4cd22f80..4f7795fb5fc 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -456,7 +456,7 @@ static void ocfs2_update_lock_stats(struct ocfs2_lock_res *res, int level, stats->ls_gets++; stats->ls_total += ktime_to_ns(kt); /* overflow */ - if (unlikely(stats->ls_gets) == 0) { + if (unlikely(stats->ls_gets == 0)) { stats->ls_gets++; stats->ls_total = ktime_to_ns(kt); } @@ -3932,6 +3932,8 @@ unqueue: static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, struct ocfs2_lock_res *lockres) { + unsigned long flags; + assert_spin_locked(&lockres->l_lock); if (lockres->l_flags & OCFS2_LOCK_FREEING) { @@ -3945,21 +3947,22 @@ static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb, lockres_or_flags(lockres, OCFS2_LOCK_QUEUED); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&lockres->l_blocked_list)) { list_add_tail(&lockres->l_blocked_list, &osb->blocked_lock_list); osb->blocked_lock_count++; } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) { unsigned long processed; + unsigned long flags; struct ocfs2_lock_res *lockres; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); /* grab this early so we know to try again if a state change and * wake happens part-way through our work */ osb->dc_work_sequence = osb->dc_wake_sequence; @@ -3972,38 +3975,40 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); osb->blocked_lock_count--; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); BUG_ON(!processed); processed--; ocfs2_process_blocked_lock(osb, lockres); - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); } - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); } static int ocfs2_downconvert_thread_lists_empty(struct ocfs2_super *osb) { int empty = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (list_empty(&osb->blocked_lock_list)) empty = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return empty; } static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb) { int should_wake = 0; + unsigned long flags; - spin_lock(&osb->dc_task_lock); + spin_lock_irqsave(&osb->dc_task_lock, flags); if (osb->dc_work_sequence != osb->dc_wake_sequence) should_wake = 1; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); return should_wake; } @@ -4033,10 +4038,12 @@ static int ocfs2_downconvert_thread(void *arg) void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb) { - spin_lock(&osb->dc_task_lock); + unsigned long flags; + + spin_lock_irqsave(&osb->dc_task_lock, flags); /* make sure the voting thread gets a swipe at whatever changes * the caller may have made to the voting state */ osb->dc_wake_sequence++; - spin_unlock(&osb->dc_task_lock); + spin_unlock_irqrestore(&osb->dc_task_lock, flags); wake_up(&osb->dc_event); } diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 745db42528d..322216a5f0d 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -177,21 +177,23 @@ bail: return parent; } -static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len, - int connectable) +static int ocfs2_encode_fh(struct inode *inode, u32 *fh_in, int *max_len, + struct inode *parent) { - struct inode *inode = dentry->d_inode; int len = *max_len; int type = 1; u64 blkno; u32 generation; __le32 *fh = (__force __le32 *) fh_in; +#ifdef TRACE_HOOKS_ARE_NOT_BRAINDEAD_IN_YOUR_OPINION +#error "You go ahead and fix that mess, then. Somehow" trace_ocfs2_encode_fh_begin(dentry, dentry->d_name.len, dentry->d_name.name, fh, len, connectable); +#endif - if (connectable && (len < 6)) { + if (parent && (len < 6)) { *max_len = 6; type = 255; goto bail; @@ -211,12 +213,7 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len, fh[1] = cpu_to_le32((u32)(blkno & 0xffffffff)); fh[2] = cpu_to_le32(generation); - if (connectable && !S_ISDIR(inode->i_mode)) { - struct inode *parent; - - spin_lock(&dentry->d_lock); - - parent = dentry->d_parent->d_inode; + if (parent) { blkno = OCFS2_I(parent)->ip_blkno; generation = parent->i_generation; @@ -224,8 +221,6 @@ static int ocfs2_encode_fh(struct dentry *dentry, u32 *fh_in, int *max_len, fh[4] = cpu_to_le32((u32)(blkno & 0xffffffff)); fh[5] = cpu_to_le32(generation); - spin_unlock(&dentry->d_lock); - len = 6; type = 2; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index 2f5b92ef0e5..70b5863a2d6 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -923,8 +923,6 @@ out_unlock: ocfs2_inode_unlock(inode, 0); out: - if (ret && ret != -ENXIO) - ret = -ENXIO; return ret; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 061591a3ab0..7602783d7f4 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1950,7 +1950,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, if (ret < 0) mlog_errno(ret); - if (file->f_flags & O_SYNC) + if (file && (file->f_flags & O_SYNC)) handle->h_sync = 1; ocfs2_commit_trans(osb, handle); @@ -2422,8 +2422,10 @@ out_dio: unaligned_dio = 0; } - if (unaligned_dio) + if (unaligned_dio) { + ocfs2_iocb_clear_unaligned_aio(iocb); atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio); + } out: if (rw_level != -1) diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c index 17454a904d7..d89e08a81ed 100644 --- a/fs/ocfs2/inode.c +++ b/fs/ocfs2/inode.c @@ -273,11 +273,13 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, inode->i_gid = le32_to_cpu(fe->i_gid); /* Fast symlinks will have i_size but no allocated clusters. */ - if (S_ISLNK(inode->i_mode) && !fe->i_clusters) + if (S_ISLNK(inode->i_mode) && !fe->i_clusters) { inode->i_blocks = 0; - else + inode->i_mapping->a_ops = &ocfs2_fast_symlink_aops; + } else { inode->i_blocks = ocfs2_inode_sector_count(inode); - inode->i_mapping->a_ops = &ocfs2_aops; + inode->i_mapping->a_ops = &ocfs2_aops; + } inode->i_atime.tv_sec = le64_to_cpu(fe->i_atime); inode->i_atime.tv_nsec = le32_to_cpu(fe->i_atime_nsec); inode->i_mtime.tv_sec = le64_to_cpu(fe->i_mtime); @@ -331,10 +333,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe, OCFS2_I(inode)->ip_dir_lock_gen = 1; break; case S_IFLNK: - if (ocfs2_inode_is_fast_symlink(inode)) - inode->i_op = &ocfs2_fast_symlink_inode_operations; - else - inode->i_op = &ocfs2_symlink_inode_operations; + inode->i_op = &ocfs2_symlink_inode_operations; i_size_write(inode, le64_to_cpu(fe->i_size)); break; default: @@ -1069,7 +1068,7 @@ static void ocfs2_clear_inode(struct inode *inode) int status; struct ocfs2_inode_info *oi = OCFS2_I(inode); - end_writeback(inode); + clear_inode(inode); trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno, inode->i_nlink); diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index a1a1bfd652c..d96f7f81d8d 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -864,7 +864,7 @@ int ocfs2_info_handle(struct inode *inode, struct ocfs2_info *info, if (status) break; - reqp = (struct ocfs2_info_request *)(unsigned long)req_addr; + reqp = (struct ocfs2_info_request __user *)(unsigned long)req_addr; if (!reqp) { status = -EINVAL; goto bail; @@ -888,9 +888,11 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) struct ocfs2_space_resv sr; struct ocfs2_new_group_input input; struct reflink_arguments args; - const char *old_path, *new_path; + const char __user *old_path; + const char __user *new_path; bool preserve; struct ocfs2_info info; + void __user *argp = (void __user *)arg; switch (cmd) { case OCFS2_IOC_GETFLAGS: @@ -937,17 +939,15 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return ocfs2_group_add(inode, &input); case OCFS2_IOC_REFLINK: - if (copy_from_user(&args, (struct reflink_arguments *)arg, - sizeof(args))) + if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; - old_path = (const char *)(unsigned long)args.old_path; - new_path = (const char *)(unsigned long)args.new_path; + old_path = (const char __user *)(unsigned long)args.old_path; + new_path = (const char __user *)(unsigned long)args.new_path; preserve = (args.preserve != 0); return ocfs2_reflink_ioctl(inode, old_path, new_path, preserve); case OCFS2_IOC_INFO: - if (copy_from_user(&info, (struct ocfs2_info __user *)arg, - sizeof(struct ocfs2_info))) + if (copy_from_user(&info, argp, sizeof(struct ocfs2_info))) return -EFAULT; return ocfs2_info_handle(inode, &info, 0); @@ -960,22 +960,20 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (copy_from_user(&range, (struct fstrim_range *)arg, - sizeof(range))) + if (copy_from_user(&range, argp, sizeof(range))) return -EFAULT; ret = ocfs2_trim_fs(sb, &range); if (ret < 0) return ret; - if (copy_to_user((struct fstrim_range *)arg, &range, - sizeof(range))) + if (copy_to_user(argp, &range, sizeof(range))) return -EFAULT; return 0; } case OCFS2_IOC_MOVE_EXT: - return ocfs2_ioctl_move_extents(filp, (void __user *)arg); + return ocfs2_ioctl_move_extents(filp, argp); default: return -ENOTTY; } @@ -988,6 +986,7 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct reflink_arguments args; struct inode *inode = file->f_path.dentry->d_inode; struct ocfs2_info info; + void __user *argp = (void __user *)arg; switch (cmd) { case OCFS2_IOC32_GETFLAGS: @@ -1006,16 +1005,14 @@ long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg) case FITRIM: break; case OCFS2_IOC_REFLINK: - if (copy_from_user(&args, (struct reflink_arguments *)arg, - sizeof(args))) + if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; preserve = (args.preserve != 0); return ocfs2_reflink_ioctl(inode, compat_ptr(args.old_path), compat_ptr(args.new_path), preserve); case OCFS2_IOC_INFO: - if (copy_from_user(&info, (struct ocfs2_info __user *)arg, - sizeof(struct ocfs2_info))) + if (copy_from_user(&info, argp, sizeof(struct ocfs2_info))) return -EFAULT; return ocfs2_info_handle(inode, &info, 1); diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index b1e3fce72ea..6083432f667 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -1082,8 +1082,7 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->file = filp; if (argp) { - if (copy_from_user(&range, (struct ocfs2_move_extents *)argp, - sizeof(range))) { + if (copy_from_user(&range, argp, sizeof(range))) { status = -EFAULT; goto out; } @@ -1138,8 +1137,7 @@ out: * length and new_offset even if failure happens somewhere. */ if (argp) { - if (copy_to_user((struct ocfs2_move_extents *)argp, &range, - sizeof(range))) + if (copy_to_user(argp, &range, sizeof(range))) status = -EFAULT; } diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index a9856e3eaaf..9f39c640cdd 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1724,15 +1724,16 @@ static int ocfs2_symlink(struct inode *dir, fe = (struct ocfs2_dinode *) new_fe_bh->b_data; inode->i_rdev = 0; newsize = l - 1; + inode->i_op = &ocfs2_symlink_inode_operations; if (l > ocfs2_fast_symlink_chars(sb)) { u32 offset = 0; - inode->i_op = &ocfs2_symlink_inode_operations; status = dquot_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb, 1)); if (status) goto bail; did_quota = 1; + inode->i_mapping->a_ops = &ocfs2_aops; status = ocfs2_add_inode_data(osb, inode, &offset, 1, 0, new_fe_bh, handle, data_ac, NULL, @@ -1750,7 +1751,7 @@ static int ocfs2_symlink(struct inode *dir, i_size_write(inode, newsize); inode->i_blocks = ocfs2_inode_sector_count(inode); } else { - inode->i_op = &ocfs2_fast_symlink_inode_operations; + inode->i_mapping->a_ops = &ocfs2_fast_symlink_aops; memcpy((char *) fe->id2.i_symlink, symname, l); i_size_write(inode, newsize); inode->i_blocks = 0; diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c index 92fcd575775..0a86e302655 100644 --- a/fs/ocfs2/quota_global.c +++ b/fs/ocfs2/quota_global.c @@ -399,8 +399,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type) msecs_to_jiffies(oinfo->dqi_syncms)); out_err: - if (status) - mlog_errno(status); return status; out_unlock: ocfs2_unlock_global_qf(oinfo, 0); diff --git a/fs/ocfs2/symlink.c b/fs/ocfs2/symlink.c index 5d22872e2bb..f1fbb4b552a 100644 --- a/fs/ocfs2/symlink.c +++ b/fs/ocfs2/symlink.c @@ -54,101 +54,40 @@ #include "buffer_head_io.h" -static char *ocfs2_fast_symlink_getlink(struct inode *inode, - struct buffer_head **bh) +static int ocfs2_fast_symlink_readpage(struct file *unused, struct page *page) { - int status; - char *link = NULL; + struct inode *inode = page->mapping->host; + struct buffer_head *bh; + int status = ocfs2_read_inode_block(inode, &bh); struct ocfs2_dinode *fe; + const char *link; + void *kaddr; + size_t len; - status = ocfs2_read_inode_block(inode, bh); if (status < 0) { mlog_errno(status); - link = ERR_PTR(status); - goto bail; + return status; } - fe = (struct ocfs2_dinode *) (*bh)->b_data; + fe = (struct ocfs2_dinode *) bh->b_data; link = (char *) fe->id2.i_symlink; -bail: - - return link; -} - -static int ocfs2_readlink(struct dentry *dentry, - char __user *buffer, - int buflen) -{ - int ret; - char *link; - struct buffer_head *bh = NULL; - struct inode *inode = dentry->d_inode; - - link = ocfs2_fast_symlink_getlink(inode, &bh); - if (IS_ERR(link)) { - ret = PTR_ERR(link); - goto out; - } - - /* - * Without vfsmount we can't update atime now, - * but we will update atime here ultimately. - */ - ret = vfs_readlink(dentry, buffer, buflen, link); - + /* will be less than a page size */ + len = strnlen(link, ocfs2_fast_symlink_chars(inode->i_sb)); + kaddr = kmap_atomic(page); + memcpy(kaddr, link, len + 1); + kunmap_atomic(kaddr); + SetPageUptodate(page); + unlock_page(page); brelse(bh); -out: - if (ret < 0) - mlog_errno(ret); - return ret; + return 0; } -static void *ocfs2_fast_follow_link(struct dentry *dentry, - struct nameidata *nd) -{ - int status = 0; - int len; - char *target, *link = ERR_PTR(-ENOMEM); - struct inode *inode = dentry->d_inode; - struct buffer_head *bh = NULL; - - BUG_ON(!ocfs2_inode_is_fast_symlink(inode)); - target = ocfs2_fast_symlink_getlink(inode, &bh); - if (IS_ERR(target)) { - status = PTR_ERR(target); - mlog_errno(status); - goto bail; - } - - /* Fast symlinks can't be large */ - len = strnlen(target, ocfs2_fast_symlink_chars(inode->i_sb)); - link = kzalloc(len + 1, GFP_NOFS); - if (!link) { - status = -ENOMEM; - mlog_errno(status); - goto bail; - } - - memcpy(link, target, len); - -bail: - nd_set_link(nd, status ? ERR_PTR(status) : link); - brelse(bh); - - if (status) - mlog_errno(status); - return NULL; -} - -static void ocfs2_fast_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) -{ - char *link = nd_get_link(nd); - if (!IS_ERR(link)) - kfree(link); -} +const struct address_space_operations ocfs2_fast_symlink_aops = { + .readpage = ocfs2_fast_symlink_readpage, +}; const struct inode_operations ocfs2_symlink_inode_operations = { - .readlink = page_readlink, + .readlink = generic_readlink, .follow_link = page_follow_link_light, .put_link = page_put_link, .getattr = ocfs2_getattr, @@ -159,15 +98,3 @@ const struct inode_operations ocfs2_symlink_inode_operations = { .removexattr = generic_removexattr, .fiemap = ocfs2_fiemap, }; -const struct inode_operations ocfs2_fast_symlink_inode_operations = { - .readlink = ocfs2_readlink, - .follow_link = ocfs2_fast_follow_link, - .put_link = ocfs2_fast_put_link, - .getattr = ocfs2_getattr, - .setattr = ocfs2_setattr, - .setxattr = generic_setxattr, - .getxattr = generic_getxattr, - .listxattr = ocfs2_listxattr, - .removexattr = generic_removexattr, - .fiemap = ocfs2_fiemap, -}; diff --git a/fs/ocfs2/symlink.h b/fs/ocfs2/symlink.h index 65a6c9c6ad5..71ee4245e91 100644 --- a/fs/ocfs2/symlink.h +++ b/fs/ocfs2/symlink.h @@ -27,7 +27,7 @@ #define OCFS2_SYMLINK_H extern const struct inode_operations ocfs2_symlink_inode_operations; -extern const struct inode_operations ocfs2_fast_symlink_inode_operations; +extern const struct address_space_operations ocfs2_fast_symlink_aops; /* * Test whether an inode is a fast symlink. diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index dbc84222258..e6213b3725d 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -184,7 +184,7 @@ int omfs_sync_inode(struct inode *inode) static void omfs_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); if (inode->i_nlink) return; diff --git a/fs/open.c b/fs/open.c index 5720854156d..1540632d838 100644 --- a/fs/open.c +++ b/fs/open.c @@ -316,7 +316,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode) if (!issecure(SECURE_NO_SETUID_FIXUP)) { /* Clear the capabilities if we switch to a non-root user */ - if (override_cred->uid) + kuid_t root_uid = make_kuid(override_cred->user_ns, 0); + if (!uid_eq(override_cred->uid, root_uid)) cap_clear(override_cred->cap_effective); else override_cred->cap_effective = @@ -396,10 +397,10 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) { struct file *file; struct inode *inode; - int error; + int error, fput_needed; error = -EBADF; - file = fget(fd); + file = fget_raw_light(fd, &fput_needed); if (!file) goto out; @@ -413,7 +414,7 @@ SYSCALL_DEFINE1(fchdir, unsigned int, fd) if (!error) set_fs_pwd(current->fs, &file->f_path); out_putf: - fput(file); + fput_light(file, fput_needed); out: return error; } @@ -505,15 +506,24 @@ static int chown_common(struct path *path, uid_t user, gid_t group) struct inode *inode = path->dentry->d_inode; int error; struct iattr newattrs; + kuid_t uid; + kgid_t gid; + + uid = make_kuid(current_user_ns(), user); + gid = make_kgid(current_user_ns(), group); newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { + if (!uid_valid(uid)) + return -EINVAL; newattrs.ia_valid |= ATTR_UID; - newattrs.ia_uid = user; + newattrs.ia_uid = uid; } if (group != (gid_t) -1) { + if (!gid_valid(gid)) + return -EINVAL; newattrs.ia_valid |= ATTR_GID; - newattrs.ia_gid = group; + newattrs.ia_gid = gid; } if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= @@ -644,10 +654,23 @@ static inline int __get_file_write_access(struct inode *inode, return error; } -static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, - struct file *f, - int (*open)(struct inode *, struct file *), - const struct cred *cred) +int open_check_o_direct(struct file *f) +{ + /* NB: we're sure to have correct a_ops only after f_op->open */ + if (f->f_flags & O_DIRECT) { + if (!f->f_mapping->a_ops || + ((!f->f_mapping->a_ops->direct_IO) && + (!f->f_mapping->a_ops->get_xip_mem))) { + return -EINVAL; + } + } + return 0; +} + +static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt, + struct file *f, + int (*open)(struct inode *, struct file *), + const struct cred *cred) { static const struct file_operations empty_fops = {}; struct inode *inode; @@ -681,7 +704,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_op = fops_get(inode->i_fop); - error = security_dentry_open(f, cred); + error = security_file_open(f, cred); if (error) goto cleanup_all; @@ -703,16 +726,6 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping); - /* NB: we're sure to have correct a_ops only after f_op->open */ - if (f->f_flags & O_DIRECT) { - if (!f->f_mapping->a_ops || - ((!f->f_mapping->a_ops->direct_IO) && - (!f->f_mapping->a_ops->get_xip_mem))) { - fput(f); - f = ERR_PTR(-EINVAL); - } - } - return f; cleanup_all: @@ -734,12 +747,29 @@ cleanup_all: f->f_path.dentry = NULL; f->f_path.mnt = NULL; cleanup_file: - put_filp(f); dput(dentry); mntput(mnt); return ERR_PTR(error); } +static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, + struct file *f, + int (*open)(struct inode *, struct file *), + const struct cred *cred) +{ + struct file *res = do_dentry_open(dentry, mnt, f, open, cred); + if (!IS_ERR(res)) { + int error = open_check_o_direct(f); + if (error) { + fput(res); + res = ERR_PTR(error); + } + } else { + put_filp(f); + } + return res; +} + /** * lookup_instantiate_filp - instantiates the open intent filp * @nd: pointer to nameidata @@ -794,13 +824,31 @@ struct file *nameidata_to_filp(struct nameidata *nd) /* Pick up the filp from the open intent */ filp = nd->intent.open.file; - nd->intent.open.file = NULL; /* Has the filesystem initialised the file for us? */ - if (filp->f_path.dentry == NULL) { + if (filp->f_path.dentry != NULL) { + nd->intent.open.file = NULL; + } else { + struct file *res; + path_get(&nd->path); - filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp, - NULL, cred); + res = do_dentry_open(nd->path.dentry, nd->path.mnt, + filp, NULL, cred); + if (!IS_ERR(res)) { + int error; + + nd->intent.open.file = NULL; + BUG_ON(res != filp); + + error = open_check_o_direct(filp); + if (error) { + fput(filp); + filp = ERR_PTR(error); + } + } else { + /* Allow nd->intent.open.file to be recycled */ + filp = res; + } } return filp; } diff --git a/fs/pipe.c b/fs/pipe.c index 25feaa3faac..49c1065256f 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -346,6 +346,16 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +static const struct pipe_buf_operations packet_pipe_buf_ops = { + .can_merge = 0, + .map = generic_pipe_buf_map, + .unmap = generic_pipe_buf_unmap, + .confirm = generic_pipe_buf_confirm, + .release = anon_pipe_buf_release, + .steal = generic_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + static ssize_t pipe_read(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t pos) @@ -407,6 +417,13 @@ redo: ret += chars; buf->offset += chars; buf->len -= chars; + + /* Was it a packet buffer? Clean up and exit */ + if (buf->flags & PIPE_BUF_FLAG_PACKET) { + total_len = chars; + buf->len = 0; + } + if (!buf->len) { buf->ops = NULL; ops->release(pipe, buf); @@ -459,6 +476,11 @@ redo: return ret; } +static inline int is_packetized(struct file *file) +{ + return (file->f_flags & O_DIRECT) != 0; +} + static ssize_t pipe_write(struct kiocb *iocb, const struct iovec *_iov, unsigned long nr_segs, loff_t ppos) @@ -593,6 +615,11 @@ redo2: buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = chars; + buf->flags = 0; + if (is_packetized(filp)) { + buf->ops = &packet_pipe_buf_ops; + buf->flags = PIPE_BUF_FLAG_PACKET; + } pipe->nrbufs = ++bufs; pipe->tmp_page = NULL; @@ -627,8 +654,11 @@ out: wake_up_interruptible_sync_poll(&pipe->wait, POLLIN | POLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } - if (ret > 0) - file_update_time(filp); + if (ret > 0) { + int err = file_update_time(filp); + if (err) + ret = err; + } return ret; } @@ -666,7 +696,7 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return put_user(count, (int __user *)arg); default: - return -EINVAL; + return -ENOIOCTLCMD; } } @@ -1013,7 +1043,7 @@ struct file *create_write_pipe(int flags) goto err_dentry; f->f_mapping = inode->i_mapping; - f->f_flags = O_WRONLY | (flags & O_NONBLOCK); + f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)); f->f_version = 0; return f; @@ -1057,7 +1087,7 @@ int do_pipe_flags(int *fd, int flags) int error; int fdw, fdr; - if (flags & ~(O_CLOEXEC | O_NONBLOCK)) + if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) return -EINVAL; fw = create_write_pipe(flags); diff --git a/fs/pnode.c b/fs/pnode.c index ab5fa9e1a79..bed378db075 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -257,12 +257,12 @@ int propagate_mnt(struct mount *dest_mnt, struct dentry *dest_dentry, prev_src_mnt = child; } out: - br_write_lock(vfsmount_lock); + br_write_lock(&vfsmount_lock); while (!list_empty(&tmp_list)) { child = list_first_entry(&tmp_list, struct mount, mnt_hash); umount_tree(child, 0, &umount_list); } - br_write_unlock(vfsmount_lock); + br_write_unlock(&vfsmount_lock); release_mounts(&umount_list); return ret; } diff --git a/fs/proc/array.c b/fs/proc/array.c index f9bd395b347..c1c207c36ca 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -81,6 +81,7 @@ #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/tracehook.h> +#include <linux/user_namespace.h> #include <asm/pgtable.h> #include <asm/processor.h> @@ -161,6 +162,7 @@ static inline const char *get_task_state(struct task_struct *tsk) static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *p) { + struct user_namespace *user_ns = current_user_ns(); struct group_info *group_info; int g; struct fdtable *fdt = NULL; @@ -189,8 +191,14 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_tgid_nr_ns(p, ns), pid_nr_ns(pid, ns), ppid, tpid, - cred->uid, cred->euid, cred->suid, cred->fsuid, - cred->gid, cred->egid, cred->sgid, cred->fsgid); + from_kuid_munged(user_ns, cred->uid), + from_kuid_munged(user_ns, cred->euid), + from_kuid_munged(user_ns, cred->suid), + from_kuid_munged(user_ns, cred->fsuid), + from_kgid_munged(user_ns, cred->gid), + from_kgid_munged(user_ns, cred->egid), + from_kgid_munged(user_ns, cred->sgid), + from_kgid_munged(user_ns, cred->fsgid)); task_lock(p); if (p->files) @@ -205,7 +213,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_unlock(p); for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++) - seq_printf(m, "%d ", GROUP_AT(group_info, g)); + seq_printf(m, "%d ", + from_kgid_munged(user_ns, GROUP_AT(group_info, g))); put_cred(cred); seq_putc(m, '\n'); @@ -361,7 +370,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task, int whole) { unsigned long vsize, eip, esp, wchan = ~0UL; - long priority, nice; + int priority, nice; int tty_pgrp = -1, tty_nr = 0; sigset_t sigign, sigcatch; char state; @@ -483,7 +492,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, ' ', 0); seq_put_decimal_ull(m, ' ', start_time); seq_put_decimal_ull(m, ' ', vsize); - seq_put_decimal_ll(m, ' ', mm ? get_mm_rss(mm) : 0); + seq_put_decimal_ull(m, ' ', mm ? get_mm_rss(mm) : 0); seq_put_decimal_ull(m, ' ', rsslim); seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->start_code : 1) : 0); seq_put_decimal_ull(m, ' ', mm ? (permitted ? mm->end_code : 1) : 0); @@ -508,9 +517,23 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, seq_put_decimal_ull(m, ' ', delayacct_blkio_ticks(task)); seq_put_decimal_ull(m, ' ', cputime_to_clock_t(gtime)); seq_put_decimal_ll(m, ' ', cputime_to_clock_t(cgtime)); - seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_data : 0); - seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->end_data : 0); - seq_put_decimal_ull(m, ' ', (mm && permitted) ? mm->start_brk : 0); + + if (mm && permitted) { + seq_put_decimal_ull(m, ' ', mm->start_data); + seq_put_decimal_ull(m, ' ', mm->end_data); + seq_put_decimal_ull(m, ' ', mm->start_brk); + seq_put_decimal_ull(m, ' ', mm->arg_start); + seq_put_decimal_ull(m, ' ', mm->arg_end); + seq_put_decimal_ull(m, ' ', mm->env_start); + seq_put_decimal_ull(m, ' ', mm->env_end); + } else + seq_printf(m, " 0 0 0 0 0 0 0"); + + if (permitted) + seq_put_decimal_ll(m, ' ', task->exit_code); + else + seq_put_decimal_ll(m, ' ', 0); + seq_putc(m, '\n'); if (mm) mmput(mm); @@ -556,3 +579,126 @@ int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, return 0; } + +#ifdef CONFIG_CHECKPOINT_RESTORE +static struct pid * +get_children_pid(struct inode *inode, struct pid *pid_prev, loff_t pos) +{ + struct task_struct *start, *task; + struct pid *pid = NULL; + + read_lock(&tasklist_lock); + + start = pid_task(proc_pid(inode), PIDTYPE_PID); + if (!start) + goto out; + + /* + * Lets try to continue searching first, this gives + * us significant speedup on children-rich processes. + */ + if (pid_prev) { + task = pid_task(pid_prev, PIDTYPE_PID); + if (task && task->real_parent == start && + !(list_empty(&task->sibling))) { + if (list_is_last(&task->sibling, &start->children)) + goto out; + task = list_first_entry(&task->sibling, + struct task_struct, sibling); + pid = get_pid(task_pid(task)); + goto out; + } + } + + /* + * Slow search case. + * + * We might miss some children here if children + * are exited while we were not holding the lock, + * but it was never promised to be accurate that + * much. + * + * "Just suppose that the parent sleeps, but N children + * exit after we printed their tids. Now the slow paths + * skips N extra children, we miss N tasks." (c) + * + * So one need to stop or freeze the leader and all + * its children to get a precise result. + */ + list_for_each_entry(task, &start->children, sibling) { + if (pos-- == 0) { + pid = get_pid(task_pid(task)); + break; + } + } + +out: + read_unlock(&tasklist_lock); + return pid; +} + +static int children_seq_show(struct seq_file *seq, void *v) +{ + struct inode *inode = seq->private; + pid_t pid; + + pid = pid_nr_ns(v, inode->i_sb->s_fs_info); + return seq_printf(seq, "%d ", pid); +} + +static void *children_seq_start(struct seq_file *seq, loff_t *pos) +{ + return get_children_pid(seq->private, NULL, *pos); +} + +static void *children_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct pid *pid; + + pid = get_children_pid(seq->private, v, *pos + 1); + put_pid(v); + + ++*pos; + return pid; +} + +static void children_seq_stop(struct seq_file *seq, void *v) +{ + put_pid(v); +} + +static const struct seq_operations children_seq_ops = { + .start = children_seq_start, + .next = children_seq_next, + .stop = children_seq_stop, + .show = children_seq_show, +}; + +static int children_seq_open(struct inode *inode, struct file *file) +{ + struct seq_file *m; + int ret; + + ret = seq_open(file, &children_seq_ops); + if (ret) + return ret; + + m = file->private_data; + m->private = inode; + + return ret; +} + +int children_seq_release(struct inode *inode, struct file *file) +{ + seq_release(inode, file); + return 0; +} + +const struct file_operations proc_tid_children_operations = { + .open = children_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = children_seq_release, +}; +#endif /* CONFIG_CHECKPOINT_RESTORE */ diff --git a/fs/proc/base.c b/fs/proc/base.c index 1c8b280146d..437195f204e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -81,6 +81,7 @@ #include <linux/oom.h> #include <linux/elf.h> #include <linux/pid_namespace.h> +#include <linux/user_namespace.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/flex_array.h> @@ -198,11 +199,6 @@ static int proc_root_link(struct dentry *dentry, struct path *path) return result; } -struct mm_struct *mm_for_maps(struct task_struct *task) -{ - return mm_access(task, PTRACE_MODE_READ); -} - static int proc_pid_cmdline(struct task_struct *task, char * buffer) { int res = 0; @@ -242,7 +238,7 @@ out: static int proc_pid_auxv(struct task_struct *task, char *buffer) { - struct mm_struct *mm = mm_for_maps(task); + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); int res = PTR_ERR(mm); if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; @@ -410,12 +406,13 @@ static const struct file_operations proc_lstats_operations = { static int proc_oom_score(struct task_struct *task, char *buffer) { + unsigned long totalpages = totalram_pages + total_swap_pages; unsigned long points = 0; read_lock(&tasklist_lock); if (pid_alive(task)) - points = oom_badness(task, NULL, NULL, - totalram_pages + total_swap_pages); + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } @@ -677,7 +674,7 @@ static const struct file_operations proc_single_file_operations = { .release = single_release, }; -static int mem_open(struct inode* inode, struct file* file) +static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) { struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); struct mm_struct *mm; @@ -685,7 +682,7 @@ static int mem_open(struct inode* inode, struct file* file) if (!task) return -ESRCH; - mm = mm_access(task, PTRACE_MODE_ATTACH); + mm = mm_access(task, mode); put_task_struct(task); if (IS_ERR(mm)) @@ -705,6 +702,11 @@ static int mem_open(struct inode* inode, struct file* file) return 0; } +static int mem_open(struct inode *inode, struct file *file) +{ + return __mem_open(inode, file, PTRACE_MODE_ATTACH); +} + static ssize_t mem_rw(struct file *file, char __user *buf, size_t count, loff_t *ppos, int write) { @@ -801,30 +803,29 @@ static const struct file_operations proc_mem_operations = { .release = mem_release, }; +static int environ_open(struct inode *inode, struct file *file) +{ + return __mem_open(inode, file, PTRACE_MODE_READ); +} + static ssize_t environ_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct task_struct *task = get_proc_task(file->f_dentry->d_inode); char *page; unsigned long src = *ppos; - int ret = -ESRCH; - struct mm_struct *mm; + int ret = 0; + struct mm_struct *mm = file->private_data; - if (!task) - goto out_no_task; + if (!mm) + return 0; - ret = -ENOMEM; page = (char *)__get_free_page(GFP_TEMPORARY); if (!page) - goto out; - - - mm = mm_for_maps(task); - ret = PTR_ERR(mm); - if (!mm || IS_ERR(mm)) - goto out_free; + return -ENOMEM; ret = 0; + if (!atomic_inc_not_zero(&mm->mm_users)) + goto free; while (count > 0) { int this_len, retval, max_len; @@ -836,7 +837,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; this_len = (this_len > max_len) ? max_len : this_len; - retval = access_process_vm(task, (mm->env_start + src), + retval = access_remote_vm(mm, (mm->env_start + src), page, this_len, 0); if (retval <= 0) { @@ -855,19 +856,18 @@ static ssize_t environ_read(struct file *file, char __user *buf, count -= retval; } *ppos = src; - mmput(mm); -out_free: + +free: free_page((unsigned long) page); -out: - put_task_struct(task); -out_no_task: return ret; } static const struct file_operations proc_environ_operations = { + .open = environ_open, .read = environ_read, .llseek = generic_file_llseek, + .release = mem_release, }; static ssize_t oom_adjust_read(struct file *file, char __user *buf, @@ -1561,8 +1561,8 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) generic_fillattr(inode, stat); rcu_read_lock(); - stat->uid = 0; - stat->gid = 0; + stat->uid = GLOBAL_ROOT_UID; + stat->gid = GLOBAL_ROOT_GID; task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) { if (!has_pid_permissions(pid, task, 2)) { @@ -1622,8 +1622,8 @@ int pid_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } inode->i_mode &= ~(S_ISUID | S_ISGID); security_task_to_inode(task, inode); @@ -1799,10 +1799,15 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) if (task) { files = get_files_struct(task); if (files) { + struct file *file; rcu_read_lock(); - if (fcheck_files(files, fd)) { + file = fcheck_files(files, fd); + if (file) { + unsigned f_mode = file->f_mode; + rcu_read_unlock(); put_files_struct(files); + if (task_dumpable(task)) { rcu_read_lock(); cred = __task_cred(task); @@ -1810,10 +1815,19 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } + + if (S_ISLNK(inode->i_mode)) { + unsigned i_mode = S_IFLNK; + if (f_mode & FMODE_READ) + i_mode |= S_IRUSR | S_IXUSR; + if (f_mode & FMODE_WRITE) + i_mode |= S_IWUSR | S_IXUSR; + inode->i_mode = i_mode; } - inode->i_mode &= ~(S_ISUID | S_ISGID); + security_task_to_inode(task, inode); put_task_struct(task); return 1; @@ -1836,9 +1850,7 @@ static const struct dentry_operations tid_fd_dentry_operations = static struct dentry *proc_fd_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { - unsigned fd = *(const unsigned *)ptr; - struct file *file; - struct files_struct *files; + unsigned fd = (unsigned long)ptr; struct inode *inode; struct proc_inode *ei; struct dentry *error = ERR_PTR(-ENOENT); @@ -1848,26 +1860,8 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, goto out; ei = PROC_I(inode); ei->fd = fd; - files = get_files_struct(task); - if (!files) - goto out_iput; - inode->i_mode = S_IFLNK; - - /* - * We are not taking a ref to the file structure, so we must - * hold ->file_lock. - */ - spin_lock(&files->file_lock); - file = fcheck_files(files, fd); - if (!file) - goto out_unlock; - if (file->f_mode & FMODE_READ) - inode->i_mode |= S_IRUSR | S_IXUSR; - if (file->f_mode & FMODE_WRITE) - inode->i_mode |= S_IWUSR | S_IXUSR; - spin_unlock(&files->file_lock); - put_files_struct(files); + inode->i_mode = S_IFLNK; inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; ei->op.proc_get_link = proc_fd_link; @@ -1879,12 +1873,6 @@ static struct dentry *proc_fd_instantiate(struct inode *dir, out: return error; -out_unlock: - spin_unlock(&files->file_lock); - put_files_struct(files); -out_iput: - iput(inode); - goto out; } static struct dentry *proc_lookupfd_common(struct inode *dir, @@ -1900,7 +1888,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir, if (fd == ~0U) goto out; - result = instantiate(dir, dentry, task, &fd); + result = instantiate(dir, dentry, task, (void *)(unsigned long)fd); out: put_task_struct(task); out_no_task: @@ -1943,21 +1931,22 @@ static int proc_readfd_common(struct file * filp, void * dirent, fd++, filp->f_pos++) { char name[PROC_NUMBUF]; int len; + int rv; if (!fcheck_files(files, fd)) continue; rcu_read_unlock(); len = snprintf(name, sizeof(name), "%d", fd); - if (proc_fill_cache(filp, dirent, filldir, - name, len, instantiate, - p, &fd) < 0) { - rcu_read_lock(); - break; - } + rv = proc_fill_cache(filp, dirent, filldir, + name, len, instantiate, p, + (void *)(unsigned long)fd); + if (rv < 0) + goto out_fd_loop; rcu_read_lock(); } rcu_read_unlock(); +out_fd_loop: put_files_struct(files); } out: @@ -2037,11 +2026,8 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) if (!task) goto out_notask; - if (!ptrace_may_access(task, PTRACE_MODE_READ)) - goto out; - - mm = get_task_mm(task); - if (!mm) + mm = mm_access(task, PTRACE_MODE_READ); + if (IS_ERR_OR_NULL(mm)) goto out; if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { @@ -2060,8 +2046,8 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd) inode->i_gid = cred->egid; rcu_read_unlock(); } else { - inode->i_uid = 0; - inode->i_gid = 0; + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } security_task_to_inode(task, inode); status = 1; @@ -2177,16 +2163,16 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, goto out; result = ERR_PTR(-EACCES); - if (lock_trace(task)) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; result = ERR_PTR(-ENOENT); if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) - goto out_unlock; + goto out_put_task; mm = get_task_mm(task); if (!mm) - goto out_unlock; + goto out_put_task; down_read(&mm->mmap_sem); vma = find_exact_vma(mm, vm_start, vm_end); @@ -2198,8 +2184,6 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, out_no_vma: up_read(&mm->mmap_sem); mmput(mm); -out_unlock: - unlock_trace(task); out_put_task: put_task_struct(task); out: @@ -2233,7 +2217,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) goto out; ret = -EACCES; - if (lock_trace(task)) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) goto out_put_task; ret = 0; @@ -2241,12 +2225,12 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) case 0: ino = inode->i_ino; if (filldir(dirent, ".", 1, 0, ino, DT_DIR) < 0) - goto out_unlock; + goto out_put_task; filp->f_pos++; case 1: ino = parent_ino(dentry); if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) - goto out_unlock; + goto out_put_task; filp->f_pos++; default: { @@ -2257,7 +2241,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) mm = get_task_mm(task); if (!mm) - goto out_unlock; + goto out_put_task; down_read(&mm->mmap_sem); nr_files = 0; @@ -2287,7 +2271,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) flex_array_free(fa); up_read(&mm->mmap_sem); mmput(mm); - goto out_unlock; + goto out_put_task; } for (i = 0, vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { @@ -2332,8 +2316,6 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir) } } -out_unlock: - unlock_trace(task); out_put_task: put_task_struct(task); out: @@ -2374,7 +2356,7 @@ static const struct inode_operations proc_fd_inode_operations = { static struct dentry *proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry, struct task_struct *task, const void *ptr) { - unsigned fd = *(unsigned *)ptr; + unsigned fd = (unsigned long)ptr; struct inode *inode; struct proc_inode *ei; struct dentry *error = ERR_PTR(-ENOENT); @@ -2943,6 +2925,74 @@ static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) } #endif /* CONFIG_TASK_IO_ACCOUNTING */ +#ifdef CONFIG_USER_NS +static int proc_id_map_open(struct inode *inode, struct file *file, + struct seq_operations *seq_ops) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + struct seq_file *seq; + int ret = -EINVAL; + + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + ret = seq_open(file, seq_ops); + if (ret) + goto err_put_ns; + + seq = file->private_data; + seq->private = ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_id_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + put_user_ns(ns); + return seq_release(inode, file); +} + +static int proc_uid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_uid_seq_operations); +} + +static int proc_gid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_gid_seq_operations); +} + +static const struct file_operations proc_uid_map_operations = { + .open = proc_uid_map_open, + .write = proc_uid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; + +static const struct file_operations proc_gid_map_operations = { + .open = proc_gid_map_open, + .write = proc_gid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; +#endif /* CONFIG_USER_NS */ + static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { @@ -3045,6 +3095,10 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), #endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), +#endif }; static int proc_tgid_base_readdir(struct file * filp, @@ -3349,6 +3403,9 @@ static const struct pid_entry tid_base_stuff[] = { ONE("stat", S_IRUGO, proc_tid_stat), ONE("statm", S_IRUGO, proc_pid_statm), REG("maps", S_IRUGO, proc_tid_maps_operations), +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("children", S_IRUGO, proc_tid_children_operations), +#endif #ifdef CONFIG_NUMA REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations), #endif @@ -3400,6 +3457,10 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_HARDWALL INF("hardwall", S_IRUGO, proc_pid_hardwall), #endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), +#endif }; static int proc_tid_base_readdir(struct file * filp, diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 205c9228083..7ac817b64a7 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -33,7 +33,7 @@ static void proc_evict_inode(struct inode *inode) const struct proc_ns_operations *ns_ops; truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); /* Stop tracking associated processes */ put_pid(PROC_I(inode)->pid); @@ -108,8 +108,8 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root) struct super_block *sb = root->d_sb; struct pid_namespace *pid = sb->s_fs_info; - if (pid->pid_gid) - seq_printf(seq, ",gid=%lu", (unsigned long)pid->pid_gid); + if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID)) + seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid)); if (pid->hide_pid != 0) seq_printf(seq, ",hidepid=%u", pid->hide_pid); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5f79bb8b4c6..eca4aca5b6e 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -31,8 +31,6 @@ struct vmalloc_info { unsigned long largest_chunk; }; -extern struct mm_struct *mm_for_maps(struct task_struct *); - #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) extern void get_vmalloc_info(struct vmalloc_info *vmi); @@ -56,6 +54,7 @@ extern int proc_pid_statm(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); extern loff_t mem_lseek(struct file *file, loff_t offset, int orig); +extern const struct file_operations proc_tid_children_operations; extern const struct file_operations proc_pid_maps_operations; extern const struct file_operations proc_tid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 21d836f4029..3476bca8f7a 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -371,9 +371,9 @@ void register_sysctl_root(struct ctl_table_root *root) static int test_perm(int mode, int op) { - if (!current_euid()) + if (uid_eq(current_euid(), GLOBAL_ROOT_UID)) mode >>= 6; - else if (in_egroup_p(0)) + else if (in_egroup_p(GLOBAL_ROOT_GID)) mode >>= 3; if ((op & ~mode & (MAY_READ|MAY_WRITE|MAY_EXEC)) == 0) return 0; diff --git a/fs/proc/root.c b/fs/proc/root.c index eed44bfc85d..7c30fce037c 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -67,7 +67,7 @@ static int proc_parse_options(char *options, struct pid_namespace *pid) case Opt_gid: if (match_int(&args[0], &option)) return 0; - pid->pid_gid = option; + pid->pid_gid = make_kgid(current_user_ns(), option); break; case Opt_hidepid: if (match_int(&args[0], &option)) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 2b9a7607cbd..4540b8f76f1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -125,7 +125,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_for_maps(priv->task); + mm = mm_access(priv->task, PTRACE_MODE_READ); if (!mm || IS_ERR(mm)) return mm; down_read(&mm->mmap_sem); @@ -393,6 +393,7 @@ struct mem_size_stats { unsigned long anonymous; unsigned long anonymous_thp; unsigned long swap; + unsigned long nonlinear; u64 pss; }; @@ -402,24 +403,33 @@ static void smaps_pte_entry(pte_t ptent, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = mss->vma; - struct page *page; + pgoff_t pgoff = linear_page_index(vma, addr); + struct page *page = NULL; int mapcount; - if (is_swap_pte(ptent)) { - mss->swap += ptent_size; - return; + if (pte_present(ptent)) { + page = vm_normal_page(vma, addr, ptent); + } else if (is_swap_pte(ptent)) { + swp_entry_t swpent = pte_to_swp_entry(ptent); + + if (!non_swap_entry(swpent)) + mss->swap += ptent_size; + else if (is_migration_entry(swpent)) + page = migration_entry_to_page(swpent); + } else if (pte_file(ptent)) { + if (pte_to_pgoff(ptent) != pgoff) + mss->nonlinear += ptent_size; } - if (!pte_present(ptent)) - return; - - page = vm_normal_page(vma, addr, ptent); if (!page) return; if (PageAnon(page)) mss->anonymous += ptent_size; + if (page->index != pgoff) + mss->nonlinear += ptent_size; + mss->resident += ptent_size; /* Accumulate the size in pages that have been accessed. */ if (pte_young(ptent) || PageReferenced(page)) @@ -521,6 +531,10 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) (vma->vm_flags & VM_LOCKED) ? (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0); + if (vma->vm_flags & VM_NONLINEAR) + seq_printf(m, "Nonlinear: %8lu kB\n", + mss.nonlinear >> 10); + if (m->count < m->size) /* vma is copied successfully */ m->version = (vma != get_gate_vma(task->mm)) ? vma->vm_start : 0; @@ -597,9 +611,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, if (!page) continue; - if (PageReserved(page)) - continue; - /* Clear accessed and referenced bits. */ ptep_test_and_clear_young(vma, addr, pte); ClearPageReferenced(page); @@ -703,6 +714,7 @@ struct pagemapread { #define PM_PRESENT PM_STATUS(4LL) #define PM_SWAP PM_STATUS(2LL) +#define PM_FILE PM_STATUS(1LL) #define PM_NOT_PRESENT PM_PSHIFT(PAGE_SHIFT) #define PM_END_OF_BUFFER 1 @@ -736,20 +748,33 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end, return err; } -static u64 swap_pte_to_pagemap_entry(pte_t pte) +static void pte_to_pagemap_entry(pagemap_entry_t *pme, + struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - swp_entry_t e = pte_to_swp_entry(pte); - return swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT); -} + u64 frame, flags; + struct page *page = NULL; + + if (pte_present(pte)) { + frame = pte_pfn(pte); + flags = PM_PRESENT; + page = vm_normal_page(vma, addr, pte); + } else if (is_swap_pte(pte)) { + swp_entry_t entry = pte_to_swp_entry(pte); + + frame = swp_type(entry) | + (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + flags = PM_SWAP; + if (is_migration_entry(entry)) + page = migration_entry_to_page(entry); + } else { + *pme = make_pme(PM_NOT_PRESENT); + return; + } -static void pte_to_pagemap_entry(pagemap_entry_t *pme, pte_t pte) -{ - if (is_swap_pte(pte)) - *pme = make_pme(PM_PFRAME(swap_pte_to_pagemap_entry(pte)) - | PM_PSHIFT(PAGE_SHIFT) | PM_SWAP); - else if (pte_present(pte)) - *pme = make_pme(PM_PFRAME(pte_pfn(pte)) - | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + if (page && !PageAnon(page)) + flags |= PM_FILE; + + *pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -764,6 +789,8 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, if (pmd_present(pmd)) *pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset) | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT); } #else static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, @@ -783,7 +810,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, /* find the first VMA at or above 'addr' */ vma = find_vma(walk->mm, addr); - if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (vma && pmd_trans_huge_lock(pmd, vma) == 1) { for (; addr != end; addr += PAGE_SIZE) { unsigned long offset; @@ -804,15 +831,17 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, /* check to see if we've left 'vma' behind * and need a new, higher one */ - if (vma && (addr >= vma->vm_end)) + if (vma && (addr >= vma->vm_end)) { vma = find_vma(walk->mm, addr); + pme = make_pme(PM_NOT_PRESENT); + } /* check that 'vma' actually covers this address, * and that it isn't a huge page vma */ if (vma && (vma->vm_start <= addr) && !is_vm_hugetlb_page(vma)) { pte = pte_offset_map(pmd, addr); - pte_to_pagemap_entry(&pme, *pte); + pte_to_pagemap_entry(&pme, vma, addr, *pte); /* unmap before userspace copy */ pte_unmap(pte); } @@ -833,6 +862,8 @@ static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, if (pte_present(pte)) *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) | PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT); + else + *pme = make_pme(PM_NOT_PRESENT); } /* This function walks within one hugetlb entry in the single call */ @@ -842,7 +873,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, { struct pagemapread *pm = walk->private; int err = 0; - pagemap_entry_t pme = make_pme(PM_NOT_PRESENT); + pagemap_entry_t pme; for (; addr != end; addr += PAGE_SIZE) { int offset = (addr & ~hmask) >> PAGE_SHIFT; @@ -864,11 +895,11 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, * For each page in the address space, this file contains one 64-bit entry * consisting of the following: * - * Bits 0-55 page frame number (PFN) if present + * Bits 0-54 page frame number (PFN) if present * Bits 0-4 swap type if swapped - * Bits 5-55 swap offset if swapped + * Bits 5-54 swap offset if swapped * Bits 55-60 page shift (page size = 1<<page shift) - * Bit 61 reserved for future use + * Bit 61 page is file-page or shared-anon * Bit 62 page swapped * Bit 63 page present * @@ -914,7 +945,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!pm.buffer) goto out_task; - mm = mm_for_maps(task); + mm = mm_access(task, PTRACE_MODE_READ); ret = PTR_ERR(mm); if (!mm || IS_ERR(mm)) goto out_free; diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index 74fe164d1b2..1ccfa537f5f 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -223,7 +223,7 @@ static void *m_start(struct seq_file *m, loff_t *pos) if (!priv->task) return ERR_PTR(-ESRCH); - mm = mm_for_maps(priv->task); + mm = mm_access(priv->task, PTRACE_MODE_READ); if (!mm || IS_ERR(mm)) { put_task_struct(priv->task); priv->task = NULL; diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 12412852d88..5e289a7cbad 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -23,12 +23,12 @@ static unsigned mounts_poll(struct file *file, poll_table *wait) poll_wait(file, &p->ns->poll, wait); - br_read_lock(vfsmount_lock); + br_read_lock(&vfsmount_lock); if (p->m.poll_event != ns->event) { p->m.poll_event = ns->event; res |= POLLERR | POLLPRI; } - br_read_unlock(vfsmount_lock); + br_read_unlock(&vfsmount_lock); return res; } diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 8007ae7c0d8..23ade2680a4 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -11,3 +11,20 @@ config PSTORE (e.g. ACPI_APEI on X86) which will select this for you. If you don't have a platform persistent store driver, say N. + +config PSTORE_RAM + tristate "Log panic/oops to a RAM buffer" + depends on PSTORE + depends on HAS_IOMEM + depends on HAVE_MEMBLOCK + select REED_SOLOMON + select REED_SOLOMON_ENC8 + select REED_SOLOMON_DEC8 + help + This enables panic and oops messages to be logged to a circular + buffer in RAM where it can be read back at some later point. + + Note that for historical reasons, the module will be named + "ramoops.ko". + + For more information, see Documentation/ramoops.txt. diff --git a/fs/pstore/Makefile b/fs/pstore/Makefile index 760f4bce7d1..278a44e0d4e 100644 --- a/fs/pstore/Makefile +++ b/fs/pstore/Makefile @@ -5,3 +5,6 @@ obj-y += pstore.o pstore-objs += inode.o platform.o + +ramoops-objs += ram.o ram_core.o +obj-$(CONFIG_PSTORE_RAM) += ramoops.o diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 19507889bb7..11a2aa2a56c 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -85,7 +85,7 @@ static void pstore_evict_inode(struct inode *inode) struct pstore_private *p = inode->i_private; unsigned long flags; - end_writeback(inode); + clear_inode(inode); if (p) { spin_lock_irqsave(&allpstore_lock, flags); list_del(&p->list); @@ -258,7 +258,7 @@ fail: return rc; } -int pstore_fill_super(struct super_block *sb, void *data, int silent) +static int pstore_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 82c585f715e..03ce7a9b81c 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -94,20 +94,15 @@ static const char *get_reason_str(enum kmsg_dump_reason reason) * as we can from the end of the buffer. */ static void pstore_dump(struct kmsg_dumper *dumper, - enum kmsg_dump_reason reason, - const char *s1, unsigned long l1, - const char *s2, unsigned long l2) + enum kmsg_dump_reason reason) { - unsigned long s1_start, s2_start; - unsigned long l1_cpy, l2_cpy; - unsigned long size, total = 0; - char *dst; + unsigned long total = 0; const char *why; u64 id; - int hsize, ret; unsigned int part = 1; unsigned long flags = 0; int is_locked = 0; + int ret; why = get_reason_str(reason); @@ -119,30 +114,25 @@ static void pstore_dump(struct kmsg_dumper *dumper, spin_lock_irqsave(&psinfo->buf_lock, flags); oopscount++; while (total < kmsg_bytes) { + char *dst; + unsigned long size; + int hsize; + size_t len; + dst = psinfo->buf; hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part); size = psinfo->bufsize - hsize; dst += hsize; - l2_cpy = min(l2, size); - l1_cpy = min(l1, size - l2_cpy); - - if (l1_cpy + l2_cpy == 0) + if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len)) break; - s2_start = l2 - l2_cpy; - s1_start = l1 - l1_cpy; - - memcpy(dst, s1 + s1_start, l1_cpy); - memcpy(dst + l1_cpy, s2 + s2_start, l2_cpy); - ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part, - hsize + l1_cpy + l2_cpy, psinfo); + hsize + len, psinfo); if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted()) pstore_new_entry = 1; - l1 -= l1_cpy; - l2 -= l2_cpy; - total += l1_cpy + l2_cpy; + + total += hsize + len; part++; } if (in_nmi()) { diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c new file mode 100644 index 00000000000..453030f9c5b --- /dev/null +++ b/fs/pstore/ram.c @@ -0,0 +1,386 @@ +/* + * RAM Oops/Panic logger + * + * Copyright (C) 2010 Marco Stornelli <marco.stornelli@gmail.com> + * Copyright (C) 2011 Kees Cook <keescook@chromium.org> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA + * 02110-1301 USA + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/err.h> +#include <linux/module.h> +#include <linux/pstore.h> +#include <linux/time.h> +#include <linux/io.h> +#include <linux/ioport.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/pstore_ram.h> + +#define RAMOOPS_KERNMSG_HDR "====" +#define MIN_MEM_SIZE 4096UL + +static ulong record_size = MIN_MEM_SIZE; +module_param(record_size, ulong, 0400); +MODULE_PARM_DESC(record_size, + "size of each dump done on oops/panic"); + +static ulong mem_address; +module_param(mem_address, ulong, 0400); +MODULE_PARM_DESC(mem_address, + "start of reserved RAM used to store oops/panic logs"); + +static ulong mem_size; +module_param(mem_size, ulong, 0400); +MODULE_PARM_DESC(mem_size, + "size of reserved RAM used to store oops/panic logs"); + +static int dump_oops = 1; +module_param(dump_oops, int, 0600); +MODULE_PARM_DESC(dump_oops, + "set to 1 to dump oopses, 0 to only dump panics (default 1)"); + +static int ramoops_ecc; +module_param_named(ecc, ramoops_ecc, int, 0600); +MODULE_PARM_DESC(ramoops_ecc, + "set to 1 to enable ECC support"); + +struct ramoops_context { + struct persistent_ram_zone **przs; + phys_addr_t phys_addr; + unsigned long size; + size_t record_size; + int dump_oops; + bool ecc; + unsigned int count; + unsigned int max_count; + unsigned int read_count; + struct pstore_info pstore; +}; + +static struct platform_device *dummy; +static struct ramoops_platform_data *dummy_data; + +static int ramoops_pstore_open(struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + + cxt->read_count = 0; + return 0; +} + +static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type, + struct timespec *time, + char **buf, + struct pstore_info *psi) +{ + ssize_t size; + struct ramoops_context *cxt = psi->data; + struct persistent_ram_zone *prz; + + if (cxt->read_count >= cxt->max_count) + return -EINVAL; + + *id = cxt->read_count++; + prz = cxt->przs[*id]; + + /* Only supports dmesg output so far. */ + *type = PSTORE_TYPE_DMESG; + /* TODO(kees): Bogus time for the moment. */ + time->tv_sec = 0; + time->tv_nsec = 0; + + /* Update old/shadowed buffer. */ + persistent_ram_save_old(prz); + size = persistent_ram_old_size(prz); + *buf = kmalloc(size, GFP_KERNEL); + if (*buf == NULL) + return -ENOMEM; + memcpy(*buf, persistent_ram_old(prz), size); + + return size; +} + +static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) +{ + char *hdr; + struct timeval timestamp; + size_t len; + + do_gettimeofday(×tamp); + hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n", + (long)timestamp.tv_sec, (long)timestamp.tv_usec); + WARN_ON_ONCE(!hdr); + len = hdr ? strlen(hdr) : 0; + persistent_ram_write(prz, hdr, len); + kfree(hdr); + + return len; +} + +static int ramoops_pstore_write(enum pstore_type_id type, + enum kmsg_dump_reason reason, + u64 *id, + unsigned int part, + size_t size, struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + struct persistent_ram_zone *prz = cxt->przs[cxt->count]; + size_t hlen; + + /* Currently ramoops is designed to only store dmesg dumps. */ + if (type != PSTORE_TYPE_DMESG) + return -EINVAL; + + /* Out of the various dmesg dump types, ramoops is currently designed + * to only store crash logs, rather than storing general kernel logs. + */ + if (reason != KMSG_DUMP_OOPS && + reason != KMSG_DUMP_PANIC) + return -EINVAL; + + /* Skip Oopes when configured to do so. */ + if (reason == KMSG_DUMP_OOPS && !cxt->dump_oops) + return -EINVAL; + + /* Explicitly only take the first part of any new crash. + * If our buffer is larger than kmsg_bytes, this can never happen, + * and if our buffer is smaller than kmsg_bytes, we don't want the + * report split across multiple records. + */ + if (part != 1) + return -ENOSPC; + + hlen = ramoops_write_kmsg_hdr(prz); + if (size + hlen > prz->buffer_size) + size = prz->buffer_size - hlen; + persistent_ram_write(prz, cxt->pstore.buf, size); + + cxt->count = (cxt->count + 1) % cxt->max_count; + + return 0; +} + +static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, + struct pstore_info *psi) +{ + struct ramoops_context *cxt = psi->data; + + if (id >= cxt->max_count) + return -EINVAL; + + persistent_ram_free_old(cxt->przs[id]); + persistent_ram_zap(cxt->przs[id]); + + return 0; +} + +static struct ramoops_context oops_cxt = { + .pstore = { + .owner = THIS_MODULE, + .name = "ramoops", + .open = ramoops_pstore_open, + .read = ramoops_pstore_read, + .write = ramoops_pstore_write, + .erase = ramoops_pstore_erase, + }, +}; + +static int __init ramoops_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct ramoops_platform_data *pdata = pdev->dev.platform_data; + struct ramoops_context *cxt = &oops_cxt; + int err = -EINVAL; + int i; + + /* Only a single ramoops area allowed at a time, so fail extra + * probes. + */ + if (cxt->max_count) + goto fail_out; + + if (!pdata->mem_size || !pdata->record_size) { + pr_err("The memory size and the record size must be " + "non-zero\n"); + goto fail_out; + } + + pdata->mem_size = rounddown_pow_of_two(pdata->mem_size); + pdata->record_size = rounddown_pow_of_two(pdata->record_size); + + /* Check for the minimum memory size */ + if (pdata->mem_size < MIN_MEM_SIZE && + pdata->record_size < MIN_MEM_SIZE) { + pr_err("memory size too small, minimum is %lu\n", + MIN_MEM_SIZE); + goto fail_out; + } + + if (pdata->mem_size < pdata->record_size) { + pr_err("The memory size must be larger than the " + "records size\n"); + goto fail_out; + } + + cxt->max_count = pdata->mem_size / pdata->record_size; + cxt->count = 0; + cxt->size = pdata->mem_size; + cxt->phys_addr = pdata->mem_address; + cxt->record_size = pdata->record_size; + cxt->dump_oops = pdata->dump_oops; + cxt->ecc = pdata->ecc; + + cxt->przs = kzalloc(sizeof(*cxt->przs) * cxt->max_count, GFP_KERNEL); + if (!cxt->przs) { + err = -ENOMEM; + dev_err(dev, "failed to initialize a prz array\n"); + goto fail_out; + } + + for (i = 0; i < cxt->max_count; i++) { + size_t sz = cxt->record_size; + phys_addr_t start = cxt->phys_addr + sz * i; + + cxt->przs[i] = persistent_ram_new(start, sz, cxt->ecc); + if (IS_ERR(cxt->przs[i])) { + err = PTR_ERR(cxt->przs[i]); + dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", + sz, (unsigned long long)start, err); + goto fail_przs; + } + } + + cxt->pstore.data = cxt; + cxt->pstore.bufsize = cxt->przs[0]->buffer_size; + cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + spin_lock_init(&cxt->pstore.buf_lock); + if (!cxt->pstore.buf) { + pr_err("cannot allocate pstore buffer\n"); + goto fail_clear; + } + + err = pstore_register(&cxt->pstore); + if (err) { + pr_err("registering with pstore failed\n"); + goto fail_buf; + } + + /* + * Update the module parameter variables as well so they are visible + * through /sys/module/ramoops/parameters/ + */ + mem_size = pdata->mem_size; + mem_address = pdata->mem_address; + record_size = pdata->record_size; + dump_oops = pdata->dump_oops; + + pr_info("attached 0x%lx@0x%llx (%ux0x%zx), ecc: %s\n", + cxt->size, (unsigned long long)cxt->phys_addr, + cxt->max_count, cxt->record_size, + ramoops_ecc ? "on" : "off"); + + return 0; + +fail_buf: + kfree(cxt->pstore.buf); +fail_clear: + cxt->pstore.bufsize = 0; + cxt->max_count = 0; +fail_przs: + for (i = 0; cxt->przs[i]; i++) + persistent_ram_free(cxt->przs[i]); + kfree(cxt->przs); +fail_out: + return err; +} + +static int __exit ramoops_remove(struct platform_device *pdev) +{ +#if 0 + /* TODO(kees): We cannot unload ramoops since pstore doesn't support + * unregistering yet. + */ + struct ramoops_context *cxt = &oops_cxt; + + iounmap(cxt->virt_addr); + release_mem_region(cxt->phys_addr, cxt->size); + cxt->max_count = 0; + + /* TODO(kees): When pstore supports unregistering, call it here. */ + kfree(cxt->pstore.buf); + cxt->pstore.bufsize = 0; + + return 0; +#endif + return -EBUSY; +} + +static struct platform_driver ramoops_driver = { + .remove = __exit_p(ramoops_remove), + .driver = { + .name = "ramoops", + .owner = THIS_MODULE, + }, +}; + +static int __init ramoops_init(void) +{ + int ret; + ret = platform_driver_probe(&ramoops_driver, ramoops_probe); + if (ret == -ENODEV) { + /* + * If we didn't find a platform device, we use module parameters + * building platform data on the fly. + */ + pr_info("platform device not found, using module parameters\n"); + dummy_data = kzalloc(sizeof(struct ramoops_platform_data), + GFP_KERNEL); + if (!dummy_data) + return -ENOMEM; + dummy_data->mem_size = mem_size; + dummy_data->mem_address = mem_address; + dummy_data->record_size = record_size; + dummy_data->dump_oops = dump_oops; + dummy_data->ecc = ramoops_ecc; + dummy = platform_create_bundle(&ramoops_driver, ramoops_probe, + NULL, 0, dummy_data, + sizeof(struct ramoops_platform_data)); + + if (IS_ERR(dummy)) + ret = PTR_ERR(dummy); + else + ret = 0; + } + + return ret; +} + +static void __exit ramoops_exit(void) +{ + platform_driver_unregister(&ramoops_driver); + kfree(dummy_data); +} + +module_init(ramoops_init); +module_exit(ramoops_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Marco Stornelli <marco.stornelli@gmail.com>"); +MODULE_DESCRIPTION("RAM Oops/Panic logger/driver"); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c new file mode 100644 index 00000000000..c5fbdbbf81a --- /dev/null +++ b/fs/pstore/ram_core.c @@ -0,0 +1,539 @@ +/* + * Copyright (C) 2012 Google, Inc. + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/rslib.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/pstore_ram.h> +#include <asm/page.h> + +struct persistent_ram_buffer { + uint32_t sig; + atomic_t start; + atomic_t size; + uint8_t data[0]; +}; + +#define PERSISTENT_RAM_SIG (0x43474244) /* DBGC */ + +static __initdata LIST_HEAD(persistent_ram_list); + +static inline size_t buffer_size(struct persistent_ram_zone *prz) +{ + return atomic_read(&prz->buffer->size); +} + +static inline size_t buffer_start(struct persistent_ram_zone *prz) +{ + return atomic_read(&prz->buffer->start); +} + +/* increase and wrap the start pointer, returning the old value */ +static inline size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) +{ + int old; + int new; + + do { + old = atomic_read(&prz->buffer->start); + new = old + a; + while (unlikely(new > prz->buffer_size)) + new -= prz->buffer_size; + } while (atomic_cmpxchg(&prz->buffer->start, old, new) != old); + + return old; +} + +/* increase the size counter until it hits the max size */ +static inline void buffer_size_add(struct persistent_ram_zone *prz, size_t a) +{ + size_t old; + size_t new; + + if (atomic_read(&prz->buffer->size) == prz->buffer_size) + return; + + do { + old = atomic_read(&prz->buffer->size); + new = old + a; + if (new > prz->buffer_size) + new = prz->buffer_size; + } while (atomic_cmpxchg(&prz->buffer->size, old, new) != old); +} + +static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz, + uint8_t *data, size_t len, uint8_t *ecc) +{ + int i; + uint16_t par[prz->ecc_size]; + + /* Initialize the parity buffer */ + memset(par, 0, sizeof(par)); + encode_rs8(prz->rs_decoder, data, len, par, 0); + for (i = 0; i < prz->ecc_size; i++) + ecc[i] = par[i]; +} + +static int persistent_ram_decode_rs8(struct persistent_ram_zone *prz, + void *data, size_t len, uint8_t *ecc) +{ + int i; + uint16_t par[prz->ecc_size]; + + for (i = 0; i < prz->ecc_size; i++) + par[i] = ecc[i]; + return decode_rs8(prz->rs_decoder, data, par, len, + NULL, 0, NULL, 0, NULL); +} + +static void notrace persistent_ram_update_ecc(struct persistent_ram_zone *prz, + unsigned int start, unsigned int count) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + uint8_t *buffer_end = buffer->data + prz->buffer_size; + uint8_t *block; + uint8_t *par; + int ecc_block_size = prz->ecc_block_size; + int ecc_size = prz->ecc_size; + int size = prz->ecc_block_size; + + if (!prz->ecc) + return; + + block = buffer->data + (start & ~(ecc_block_size - 1)); + par = prz->par_buffer + (start / ecc_block_size) * prz->ecc_size; + + do { + if (block + ecc_block_size > buffer_end) + size = buffer_end - block; + persistent_ram_encode_rs8(prz, block, size, par); + block += ecc_block_size; + par += ecc_size; + } while (block < buffer->data + start + count); +} + +static void persistent_ram_update_header_ecc(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + + if (!prz->ecc) + return; + + persistent_ram_encode_rs8(prz, (uint8_t *)buffer, sizeof(*buffer), + prz->par_header); +} + +static void persistent_ram_ecc_old(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + uint8_t *block; + uint8_t *par; + + if (!prz->ecc) + return; + + block = buffer->data; + par = prz->par_buffer; + while (block < buffer->data + buffer_size(prz)) { + int numerr; + int size = prz->ecc_block_size; + if (block + size > buffer->data + prz->buffer_size) + size = buffer->data + prz->buffer_size - block; + numerr = persistent_ram_decode_rs8(prz, block, size, par); + if (numerr > 0) { + pr_devel("persistent_ram: error in block %p, %d\n", + block, numerr); + prz->corrected_bytes += numerr; + } else if (numerr < 0) { + pr_devel("persistent_ram: uncorrectable error in block %p\n", + block); + prz->bad_blocks++; + } + block += prz->ecc_block_size; + par += prz->ecc_size; + } +} + +static int persistent_ram_init_ecc(struct persistent_ram_zone *prz, + size_t buffer_size) +{ + int numerr; + struct persistent_ram_buffer *buffer = prz->buffer; + int ecc_blocks; + + if (!prz->ecc) + return 0; + + prz->ecc_block_size = 128; + prz->ecc_size = 16; + prz->ecc_symsize = 8; + prz->ecc_poly = 0x11d; + + ecc_blocks = DIV_ROUND_UP(prz->buffer_size, prz->ecc_block_size); + prz->buffer_size -= (ecc_blocks + 1) * prz->ecc_size; + + if (prz->buffer_size > buffer_size) { + pr_err("persistent_ram: invalid size %zu, non-ecc datasize %zu\n", + buffer_size, prz->buffer_size); + return -EINVAL; + } + + prz->par_buffer = buffer->data + prz->buffer_size; + prz->par_header = prz->par_buffer + ecc_blocks * prz->ecc_size; + + /* + * first consecutive root is 0 + * primitive element to generate roots = 1 + */ + prz->rs_decoder = init_rs(prz->ecc_symsize, prz->ecc_poly, 0, 1, + prz->ecc_size); + if (prz->rs_decoder == NULL) { + pr_info("persistent_ram: init_rs failed\n"); + return -EINVAL; + } + + prz->corrected_bytes = 0; + prz->bad_blocks = 0; + + numerr = persistent_ram_decode_rs8(prz, buffer, sizeof(*buffer), + prz->par_header); + if (numerr > 0) { + pr_info("persistent_ram: error in header, %d\n", numerr); + prz->corrected_bytes += numerr; + } else if (numerr < 0) { + pr_info("persistent_ram: uncorrectable error in header\n"); + prz->bad_blocks++; + } + + return 0; +} + +ssize_t persistent_ram_ecc_string(struct persistent_ram_zone *prz, + char *str, size_t len) +{ + ssize_t ret; + + if (prz->corrected_bytes || prz->bad_blocks) + ret = snprintf(str, len, "" + "\n%d Corrected bytes, %d unrecoverable blocks\n", + prz->corrected_bytes, prz->bad_blocks); + else + ret = snprintf(str, len, "\nNo errors detected\n"); + + return ret; +} + +static void notrace persistent_ram_update(struct persistent_ram_zone *prz, + const void *s, unsigned int start, unsigned int count) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + memcpy(buffer->data + start, s, count); + persistent_ram_update_ecc(prz, start, count); +} + +void persistent_ram_save_old(struct persistent_ram_zone *prz) +{ + struct persistent_ram_buffer *buffer = prz->buffer; + size_t size = buffer_size(prz); + size_t start = buffer_start(prz); + + if (!size) + return; + + if (!prz->old_log) { + persistent_ram_ecc_old(prz); + prz->old_log = kmalloc(size, GFP_KERNEL); + } + if (!prz->old_log) { + pr_err("persistent_ram: failed to allocate buffer\n"); + return; + } + + prz->old_log_size = size; + memcpy(prz->old_log, &buffer->data[start], size - start); + memcpy(prz->old_log + size - start, &buffer->data[0], start); +} + +int notrace persistent_ram_write(struct persistent_ram_zone *prz, + const void *s, unsigned int count) +{ + int rem; + int c = count; + size_t start; + + if (unlikely(c > prz->buffer_size)) { + s += c - prz->buffer_size; + c = prz->buffer_size; + } + + buffer_size_add(prz, c); + + start = buffer_start_add(prz, c); + + rem = prz->buffer_size - start; + if (unlikely(rem < c)) { + persistent_ram_update(prz, s, start, rem); + s += rem; + c -= rem; + start = 0; + } + persistent_ram_update(prz, s, start, c); + + persistent_ram_update_header_ecc(prz); + + return count; +} + +size_t persistent_ram_old_size(struct persistent_ram_zone *prz) +{ + return prz->old_log_size; +} + +void *persistent_ram_old(struct persistent_ram_zone *prz) +{ + return prz->old_log; +} + +void persistent_ram_free_old(struct persistent_ram_zone *prz) +{ + kfree(prz->old_log); + prz->old_log = NULL; + prz->old_log_size = 0; +} + +void persistent_ram_zap(struct persistent_ram_zone *prz) +{ + atomic_set(&prz->buffer->start, 0); + atomic_set(&prz->buffer->size, 0); + persistent_ram_update_header_ecc(prz); +} + +static void *persistent_ram_vmap(phys_addr_t start, size_t size) +{ + struct page **pages; + phys_addr_t page_start; + unsigned int page_count; + pgprot_t prot; + unsigned int i; + void *vaddr; + + page_start = start - offset_in_page(start); + page_count = DIV_ROUND_UP(size + offset_in_page(start), PAGE_SIZE); + + prot = pgprot_noncached(PAGE_KERNEL); + + pages = kmalloc(sizeof(struct page *) * page_count, GFP_KERNEL); + if (!pages) { + pr_err("%s: Failed to allocate array for %u pages\n", __func__, + page_count); + return NULL; + } + + for (i = 0; i < page_count; i++) { + phys_addr_t addr = page_start + i * PAGE_SIZE; + pages[i] = pfn_to_page(addr >> PAGE_SHIFT); + } + vaddr = vmap(pages, page_count, VM_MAP, prot); + kfree(pages); + + return vaddr; +} + +static void *persistent_ram_iomap(phys_addr_t start, size_t size) +{ + if (!request_mem_region(start, size, "persistent_ram")) { + pr_err("request mem region (0x%llx@0x%llx) failed\n", + (unsigned long long)size, (unsigned long long)start); + return NULL; + } + + return ioremap(start, size); +} + +static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, + struct persistent_ram_zone *prz) +{ + prz->paddr = start; + prz->size = size; + + if (pfn_valid(start >> PAGE_SHIFT)) + prz->vaddr = persistent_ram_vmap(start, size); + else + prz->vaddr = persistent_ram_iomap(start, size); + + if (!prz->vaddr) { + pr_err("%s: Failed to map 0x%llx pages at 0x%llx\n", __func__, + (unsigned long long)size, (unsigned long long)start); + return -ENOMEM; + } + + prz->buffer = prz->vaddr + offset_in_page(start); + prz->buffer_size = size - sizeof(struct persistent_ram_buffer); + + return 0; +} + +static int __init persistent_ram_post_init(struct persistent_ram_zone *prz, bool ecc) +{ + int ret; + + prz->ecc = ecc; + + ret = persistent_ram_init_ecc(prz, prz->buffer_size); + if (ret) + return ret; + + if (prz->buffer->sig == PERSISTENT_RAM_SIG) { + if (buffer_size(prz) > prz->buffer_size || + buffer_start(prz) > buffer_size(prz)) + pr_info("persistent_ram: found existing invalid buffer," + " size %zu, start %zu\n", + buffer_size(prz), buffer_start(prz)); + else { + pr_info("persistent_ram: found existing buffer," + " size %zu, start %zu\n", + buffer_size(prz), buffer_start(prz)); + persistent_ram_save_old(prz); + return 0; + } + } else { + pr_info("persistent_ram: no valid data in buffer" + " (sig = 0x%08x)\n", prz->buffer->sig); + } + + prz->buffer->sig = PERSISTENT_RAM_SIG; + persistent_ram_zap(prz); + + return 0; +} + +void persistent_ram_free(struct persistent_ram_zone *prz) +{ + if (pfn_valid(prz->paddr >> PAGE_SHIFT)) { + vunmap(prz->vaddr); + } else { + iounmap(prz->vaddr); + release_mem_region(prz->paddr, prz->size); + } + persistent_ram_free_old(prz); + kfree(prz); +} + +struct persistent_ram_zone * __init persistent_ram_new(phys_addr_t start, + size_t size, + bool ecc) +{ + struct persistent_ram_zone *prz; + int ret = -ENOMEM; + + prz = kzalloc(sizeof(struct persistent_ram_zone), GFP_KERNEL); + if (!prz) { + pr_err("persistent_ram: failed to allocate persistent ram zone\n"); + goto err; + } + + ret = persistent_ram_buffer_map(start, size, prz); + if (ret) + goto err; + + persistent_ram_post_init(prz, ecc); + + return prz; +err: + kfree(prz); + return ERR_PTR(ret); +} + +#ifndef MODULE +static int __init persistent_ram_buffer_init(const char *name, + struct persistent_ram_zone *prz) +{ + int i; + struct persistent_ram *ram; + struct persistent_ram_descriptor *desc; + phys_addr_t start; + + list_for_each_entry(ram, &persistent_ram_list, node) { + start = ram->start; + for (i = 0; i < ram->num_descs; i++) { + desc = &ram->descs[i]; + if (!strcmp(desc->name, name)) + return persistent_ram_buffer_map(start, + desc->size, prz); + start += desc->size; + } + } + + return -EINVAL; +} + +static __init +struct persistent_ram_zone *__persistent_ram_init(struct device *dev, bool ecc) +{ + struct persistent_ram_zone *prz; + int ret = -ENOMEM; + + prz = kzalloc(sizeof(struct persistent_ram_zone), GFP_KERNEL); + if (!prz) { + pr_err("persistent_ram: failed to allocate persistent ram zone\n"); + goto err; + } + + ret = persistent_ram_buffer_init(dev_name(dev), prz); + if (ret) { + pr_err("persistent_ram: failed to initialize buffer\n"); + goto err; + } + + persistent_ram_post_init(prz, ecc); + + return prz; +err: + kfree(prz); + return ERR_PTR(ret); +} + +struct persistent_ram_zone * __init +persistent_ram_init_ringbuffer(struct device *dev, bool ecc) +{ + return __persistent_ram_init(dev, ecc); +} + +int __init persistent_ram_early_init(struct persistent_ram *ram) +{ + int ret; + + ret = memblock_reserve(ram->start, ram->size); + if (ret) { + pr_err("Failed to reserve persistent memory from %08lx-%08lx\n", + (long)ram->start, (long)(ram->start + ram->size - 1)); + return ret; + } + + list_add_tail(&ram->node, &persistent_ram_list); + + pr_info("Initialized persistent memory from %08lx-%08lx\n", + (long)ram->start, (long)(ram->start + ram->size - 1)); + + return 0; +} +#endif diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index d69a1d1d7e1..10cbe841cb7 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -116,15 +116,15 @@ * spinlock to internal buffers before writing. * * Lock ordering (including related VFS locks) is the following: - * i_mutex > dqonoff_sem > journal_lock > dqptr_sem > dquot->dq_lock > + * dqonoff_mutex > i_mutex > journal_lock > dqptr_sem > dquot->dq_lock > * dqio_mutex + * dqonoff_mutex > i_mutex comes from dquot_quota_sync, dquot_enable, etc. * The lock ordering of dqptr_sem imposed by quota code is only dqonoff_sem > * dqptr_sem. But filesystem has to count with the fact that functions such as * dquot_alloc_space() acquire dqptr_sem and they usually have to be called * from inside a transaction to keep filesystem consistency after a crash. Also * filesystems usually want to do some IO on dquot from ->mark_dirty which is * called with dqptr_sem held. - * i_mutex on quota files is special (it's below dqio_mutex) */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(dq_list_lock); @@ -638,7 +638,7 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) dqstats_inc(DQST_SYNCS); mutex_unlock(&dqopt->dqonoff_mutex); - if (!wait || (sb_dqopt(sb)->flags & DQUOT_QUOTA_SYS_FILE)) + if (!wait || (dqopt->flags & DQUOT_QUOTA_SYS_FILE)) return 0; /* This is not very clever (and fast) but currently I don't know about @@ -652,18 +652,17 @@ int dquot_quota_sync(struct super_block *sb, int type, int wait) * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ - mutex_lock(&sb_dqopt(sb)->dqonoff_mutex); + mutex_lock(&dqopt->dqonoff_mutex); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; - mutex_lock_nested(&sb_dqopt(sb)->files[cnt]->i_mutex, - I_MUTEX_QUOTA); - truncate_inode_pages(&sb_dqopt(sb)->files[cnt]->i_data, 0); - mutex_unlock(&sb_dqopt(sb)->files[cnt]->i_mutex); + mutex_lock(&dqopt->files[cnt]->i_mutex); + truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); + mutex_unlock(&dqopt->files[cnt]->i_mutex); } - mutex_unlock(&sb_dqopt(sb)->dqonoff_mutex); + mutex_unlock(&dqopt->dqonoff_mutex); return 0; } @@ -907,14 +906,14 @@ static void add_dquot_ref(struct super_block *sb, int type) spin_unlock(&inode->i_lock); continue; } -#ifdef CONFIG_QUOTA_DEBUG - if (unlikely(inode_get_rsv_space(inode) > 0)) - reserved = 1; -#endif __iget(inode); spin_unlock(&inode->i_lock); spin_unlock(&inode_sb_list_lock); +#ifdef CONFIG_QUOTA_DEBUG + if (unlikely(inode_get_rsv_space(inode) > 0)) + reserved = 1; +#endif iput(old_inode); __dquot_initialize(inode, type); @@ -2037,8 +2036,7 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags) /* If quota was reenabled in the meantime, we have * nothing to do */ if (!sb_has_quota_loaded(sb, cnt)) { - mutex_lock_nested(&toputinode[cnt]->i_mutex, - I_MUTEX_QUOTA); + mutex_lock(&toputinode[cnt]->i_mutex); toputinode[cnt]->i_flags &= ~(S_IMMUTABLE | S_NOATIME | S_NOQUOTA); truncate_inode_pages(&toputinode[cnt]->i_data, @@ -2133,7 +2131,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id, /* We don't want quota and atime on quota files (deadlocks * possible) Also nobody should write to the file - we use * special IO operations which ignore the immutable bit. */ - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); + mutex_lock(&inode->i_mutex); oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE | S_NOQUOTA); inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE; @@ -2180,7 +2178,7 @@ out_file_init: iput(inode); out_lock: if (oldflags != -1) { - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); + mutex_lock(&inode->i_mutex); /* Set the flags back (in the case of accidental quotaon() * on a wrong file we don't want to mess up the flags) */ inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE); diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index fbb0b478a34..d5378d02858 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -110,6 +110,7 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize) /* prevent the page from being discarded on memory pressure */ SetPageDirty(page); + SetPageUptodate(page); unlock_page(page); put_page(page); diff --git a/fs/read_write.c b/fs/read_write.c index ffc99d22e0a..c20614f86c0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -633,8 +633,7 @@ ssize_t do_loop_readv_writev(struct file *filp, struct iovec *iov, ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, - struct iovec **ret_pointer, - int check_access) + struct iovec **ret_pointer) { unsigned long seg; ssize_t ret; @@ -690,7 +689,7 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, ret = -EINVAL; goto out; } - if (check_access + if (type >= 0 && unlikely(!access_ok(vrfy_dir(type), buf, len))) { ret = -EFAULT; goto out; @@ -723,7 +722,7 @@ static ssize_t do_readv_writev(int type, struct file *file, } ret = rw_copy_check_uvector(type, uvector, nr_segs, - ARRAY_SIZE(iovstack), iovstack, &iov, 1); + ARRAY_SIZE(iovstack), iovstack, &iov); if (ret <= 0) goto out; diff --git a/fs/readdir.c b/fs/readdir.c index cc0a8227cdd..39e3370d79c 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -108,11 +108,11 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, int error; struct file * file; struct readdir_callback buf; + int fput_needed; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.result = 0; buf.dirent = dirent; @@ -121,8 +121,7 @@ SYSCALL_DEFINE3(old_readdir, unsigned int, fd, if (buf.result) error = buf.result; - fput(file); -out: + fput_light(file, fput_needed); return error; } @@ -195,16 +194,15 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct file * file; struct linux_dirent __user * lastdirent; struct getdents_callback buf; + int fput_needed; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; + return -EFAULT; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.current_dir = dirent; buf.previous = NULL; @@ -221,8 +219,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, else error = count - buf.count; } - fput(file); -out: + fput_light(file, fput_needed); return error; } @@ -278,16 +275,15 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, struct file * file; struct linux_dirent64 __user * lastdirent; struct getdents_callback64 buf; + int fput_needed; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; + return -EFAULT; - error = -EBADF; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) - goto out; + return -EBADF; buf.current_dir = dirent; buf.previous = NULL; @@ -305,7 +301,6 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd, else error = count - buf.count; } - fput(file); -out: + fput_light(file, fput_needed); return error; } diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index 494c315c741..a6d4268fb6c 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -76,14 +76,14 @@ void reiserfs_evict_inode(struct inode *inode) ; } out: - end_writeback(inode); /* note this must go after the journal_end to prevent deadlock */ + clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */ dquot_drop(inode); inode->i_blocks = 0; reiserfs_write_unlock_once(inode->i_sb, depth); return; no_delete: - end_writeback(inode); + clear_inode(inode); dquot_drop(inode); } @@ -1592,13 +1592,12 @@ struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid, (fh_type == 6) ? fid->raw[5] : 0); } -int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, - int need_parent) +int reiserfs_encode_fh(struct inode *inode, __u32 * data, int *lenp, + struct inode *parent) { - struct inode *inode = dentry->d_inode; int maxlen = *lenp; - if (need_parent && (maxlen < 5)) { + if (parent && (maxlen < 5)) { *lenp = 5; return 255; } else if (maxlen < 3) { @@ -1610,20 +1609,15 @@ int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, data[1] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id); data[2] = inode->i_generation; *lenp = 3; - /* no room for directory info? return what we've stored so far */ - if (maxlen < 5 || !need_parent) - return 3; - - spin_lock(&dentry->d_lock); - inode = dentry->d_parent->d_inode; - data[3] = inode->i_ino; - data[4] = le32_to_cpu(INODE_PKEY(inode)->k_dir_id); - *lenp = 5; - if (maxlen >= 6) { - data[5] = inode->i_generation; - *lenp = 6; - } - spin_unlock(&dentry->d_lock); + if (parent) { + data[3] = parent->i_ino; + data[4] = le32_to_cpu(INODE_PKEY(parent)->k_dir_id); + *lenp = 5; + if (maxlen >= 6) { + data[5] = parent->i_generation; + *lenp = 6; + } + } return *lenp; } diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index b1a08573fe1..afcadcc03e8 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1923,6 +1923,8 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, * the workqueue job (flush_async_commit) needs this lock */ reiserfs_write_unlock(sb); + + cancel_delayed_work_sync(&REISERFS_SB(sb)->old_work); flush_workqueue(commit_wq); if (!reiserfs_mounted_fs_count) { @@ -3231,8 +3233,6 @@ int journal_mark_dirty(struct reiserfs_transaction_handle *th, th->t_trans_id, journal->j_trans_id); } - sb->s_dirt = 1; - prepared = test_clear_buffer_journal_prepared(bh); clear_buffer_journal_restore_dirty(bh); /* already in this transaction, we are done */ @@ -3316,6 +3316,7 @@ int journal_mark_dirty(struct reiserfs_transaction_handle *th, journal->j_first = cn; journal->j_last = cn; } + reiserfs_schedule_old_flush(sb); return 0; } @@ -3492,7 +3493,7 @@ static void flush_async_commits(struct work_struct *work) ** flushes any old transactions to disk ** ends the current transaction if it is too old */ -int reiserfs_flush_old_commits(struct super_block *sb) +void reiserfs_flush_old_commits(struct super_block *sb) { time_t now; struct reiserfs_transaction_handle th; @@ -3502,9 +3503,8 @@ int reiserfs_flush_old_commits(struct super_block *sb) /* safety check so we don't flush while we are replaying the log during * mount */ - if (list_empty(&journal->j_journal_list)) { - return 0; - } + if (list_empty(&journal->j_journal_list)) + return; /* check the current transaction. If there are no writers, and it is * too old, finish it, and force the commit blocks to disk @@ -3526,7 +3526,6 @@ int reiserfs_flush_old_commits(struct super_block *sb) do_journal_end(&th, sb, 1, COMMIT_NOW | WAIT); } } - return sb->s_dirt; } /* @@ -3955,7 +3954,7 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, ** it tells us if we should continue with the journal_end, or just return */ if (!check_journal_end(th, sb, nblocks, flags)) { - sb->s_dirt = 1; + reiserfs_schedule_old_flush(sb); wake_queued_writers(sb); reiserfs_async_progress_wait(sb); goto out; diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index a59d2712633..33215f57ea0 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -480,6 +480,11 @@ struct reiserfs_sb_info { struct dentry *priv_root; /* root of /.reiserfs_priv */ struct dentry *xattr_root; /* root of /.reiserfs_priv/xattrs */ int j_errno; + + int work_queued; /* non-zero delayed work is queued */ + struct delayed_work old_work; /* old transactions flush delayed work */ + spinlock_t old_work_lock; /* protects old_work and work_queued */ + #ifdef CONFIG_QUOTA char *s_qf_names[MAXQUOTAS]; int s_jquota_fmt; @@ -2452,7 +2457,7 @@ struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *); int reiserfs_commit_page(struct inode *inode, struct page *page, unsigned from, unsigned to); -int reiserfs_flush_old_commits(struct super_block *); +void reiserfs_flush_old_commits(struct super_block *); int reiserfs_commit_for_inode(struct inode *); int reiserfs_inode_needs_commit(struct inode *); void reiserfs_update_inode_transaction(struct inode *); @@ -2487,6 +2492,7 @@ void reiserfs_abort(struct super_block *sb, int errno, const char *fmt, ...); int reiserfs_allocate_list_bitmaps(struct super_block *s, struct reiserfs_list_bitmap *, unsigned int); +void reiserfs_schedule_old_flush(struct super_block *s); void add_save_link(struct reiserfs_transaction_handle *th, struct inode *inode, int truncate); int remove_save_link(struct inode *inode, int truncate); @@ -2611,8 +2617,8 @@ struct dentry *reiserfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); struct dentry *reiserfs_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type); -int reiserfs_encode_fh(struct dentry *dentry, __u32 * data, int *lenp, - int connectable); +int reiserfs_encode_fh(struct inode *inode, __u32 * data, int *lenp, + struct inode *parent); int reiserfs_truncate_file(struct inode *, int update_timestamps); void make_cpu_key(struct cpu_key *cpu_key, struct inode *inode, loff_t offset, diff --git a/fs/reiserfs/resize.c b/fs/reiserfs/resize.c index 9a17f63c3fd..3ce02cff5e9 100644 --- a/fs/reiserfs/resize.c +++ b/fs/reiserfs/resize.c @@ -200,7 +200,6 @@ int reiserfs_resize(struct super_block *s, unsigned long block_count_new) (bmap_nr_new - bmap_nr))); PUT_SB_BLOCK_COUNT(s, block_count_new); PUT_SB_BMAP_NR(s, bmap_would_wrap(bmap_nr_new) ? : bmap_nr_new); - s->s_dirt = 1; journal_mark_dirty(&th, s, SB_BUFFER_WITH_SB(s)); diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 8b7616ef06d..651ce767b55 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -72,20 +72,58 @@ static int reiserfs_sync_fs(struct super_block *s, int wait) if (!journal_begin(&th, s, 1)) if (!journal_end_sync(&th, s, 1)) reiserfs_flush_old_commits(s); - s->s_dirt = 0; /* Even if it's not true. - * We'll loop forever in sync_supers otherwise */ reiserfs_write_unlock(s); return 0; } -static void reiserfs_write_super(struct super_block *s) +static void flush_old_commits(struct work_struct *work) { + struct reiserfs_sb_info *sbi; + struct super_block *s; + + sbi = container_of(work, struct reiserfs_sb_info, old_work.work); + s = sbi->s_journal->j_work_sb; + + spin_lock(&sbi->old_work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->old_work_lock); + reiserfs_sync_fs(s, 1); } +void reiserfs_schedule_old_flush(struct super_block *s) +{ + struct reiserfs_sb_info *sbi = REISERFS_SB(s); + unsigned long delay; + + if (s->s_flags & MS_RDONLY) + return; + + spin_lock(&sbi->old_work_lock); + if (!sbi->work_queued) { + delay = msecs_to_jiffies(dirty_writeback_interval * 10); + queue_delayed_work(system_long_wq, &sbi->old_work, delay); + sbi->work_queued = 1; + } + spin_unlock(&sbi->old_work_lock); +} + +static void cancel_old_flush(struct super_block *s) +{ + struct reiserfs_sb_info *sbi = REISERFS_SB(s); + + cancel_delayed_work_sync(&REISERFS_SB(s)->old_work); + spin_lock(&sbi->old_work_lock); + sbi->work_queued = 0; + spin_unlock(&sbi->old_work_lock); +} + static int reiserfs_freeze(struct super_block *s) { struct reiserfs_transaction_handle th; + + cancel_old_flush(s); + reiserfs_write_lock(s); if (!(s->s_flags & MS_RDONLY)) { int err = journal_begin(&th, s, 1); @@ -99,7 +137,6 @@ static int reiserfs_freeze(struct super_block *s) journal_end_sync(&th, s, 1); } } - s->s_dirt = 0; reiserfs_write_unlock(s); return 0; } @@ -483,9 +520,6 @@ static void reiserfs_put_super(struct super_block *s) reiserfs_write_lock(s); - if (s->s_dirt) - reiserfs_write_super(s); - /* change file system state to current state if it was mounted with read-write permissions */ if (!(s->s_flags & MS_RDONLY)) { if (!journal_begin(&th, s, 10)) { @@ -692,7 +726,6 @@ static const struct super_operations reiserfs_sops = { .dirty_inode = reiserfs_dirty_inode, .evict_inode = reiserfs_evict_inode, .put_super = reiserfs_put_super, - .write_super = reiserfs_write_super, .sync_fs = reiserfs_sync_fs, .freeze_fs = reiserfs_freeze, .unfreeze_fs = reiserfs_unfreeze, @@ -1400,7 +1433,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) err = journal_end(&th, s, 10); if (err) goto out_err; - s->s_dirt = 0; if (!(*mount_flags & MS_RDONLY)) { dquot_resume(s, -1); @@ -1730,19 +1762,21 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) return -ENOMEM; s->s_fs_info = sbi; /* Set default values for options: non-aggressive tails, RO on errors */ - REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_SMALLTAIL); - REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_ERROR_RO); - REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_BARRIER_FLUSH); + sbi->s_mount_opt |= (1 << REISERFS_SMALLTAIL); + sbi->s_mount_opt |= (1 << REISERFS_ERROR_RO); + sbi->s_mount_opt |= (1 << REISERFS_BARRIER_FLUSH); /* no preallocation minimum, be smart in reiserfs_file_write instead */ - REISERFS_SB(s)->s_alloc_options.preallocmin = 0; + sbi->s_alloc_options.preallocmin = 0; /* Preallocate by 16 blocks (17-1) at once */ - REISERFS_SB(s)->s_alloc_options.preallocsize = 17; + sbi->s_alloc_options.preallocsize = 17; /* setup default block allocator options */ reiserfs_init_alloc_options(s); - mutex_init(&REISERFS_SB(s)->lock); - REISERFS_SB(s)->lock_depth = -1; + spin_lock_init(&sbi->old_work_lock); + INIT_DELAYED_WORK(&sbi->old_work, flush_old_commits); + mutex_init(&sbi->lock); + sbi->lock_depth = -1; jdev_name = NULL; if (reiserfs_parse_options @@ -1751,8 +1785,8 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) goto error_unlocked; } if (jdev_name && jdev_name[0]) { - REISERFS_SB(s)->s_jdev = kstrdup(jdev_name, GFP_KERNEL); - if (!REISERFS_SB(s)->s_jdev) { + sbi->s_jdev = kstrdup(jdev_name, GFP_KERNEL); + if (!sbi->s_jdev) { SWARN(silent, s, "", "Cannot allocate memory for " "journal device name"); goto error; @@ -1810,7 +1844,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) /* make data=ordered the default */ if (!reiserfs_data_log(s) && !reiserfs_data_ordered(s) && !reiserfs_data_writeback(s)) { - REISERFS_SB(s)->s_mount_opt |= (1 << REISERFS_DATA_ORDERED); + sbi->s_mount_opt |= (1 << REISERFS_DATA_ORDERED); } if (reiserfs_data_log(s)) { @@ -2003,6 +2037,8 @@ error_unlocked: reiserfs_write_unlock(s); } + cancel_delayed_work_sync(&REISERFS_SB(s)->old_work); + reiserfs_free_bitmap_cache(s); if (SB_BUFFER_WITH_SB(s)) brelse(SB_BUFFER_WITH_SB(s)); @@ -2270,7 +2306,6 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, (unsigned long long)off, (unsigned long long)len); return -EIO; } - mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA); while (towrite > 0) { tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; @@ -2302,16 +2337,13 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, blk++; } out: - if (len == towrite) { - mutex_unlock(&inode->i_mutex); + if (len == towrite) return err; - } if (inode->i_size < off + len - towrite) i_size_write(inode, off + len - towrite); inode->i_version++; inode->i_mtime = inode->i_ctime = CURRENT_TIME; mark_inode_dirty(inode); - mutex_unlock(&inode->i_mutex); return len - towrite; } diff --git a/fs/select.c b/fs/select.c index 17d33d09fc1..bae321569df 100644 --- a/fs/select.c +++ b/fs/select.c @@ -614,7 +614,6 @@ SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp, return ret; } -#ifdef HAVE_SET_RESTORE_SIGMASK static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize) @@ -686,7 +685,6 @@ SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp, return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize); } -#endif /* HAVE_SET_RESTORE_SIGMASK */ #ifdef __ARCH_WANT_SYS_OLD_SELECT struct sel_arg_struct { @@ -941,7 +939,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, return ret; } -#ifdef HAVE_SET_RESTORE_SIGMASK SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, struct timespec __user *, tsp, const sigset_t __user *, sigmask, size_t, sigsetsize) @@ -992,4 +989,3 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, return ret; } -#endif /* HAVE_SET_RESTORE_SIGMASK */ diff --git a/fs/signalfd.c b/fs/signalfd.c index 7ae2a574cb2..9f35a37173d 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -269,12 +269,13 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, if (ufd < 0) kfree(ctx); } else { - struct file *file = fget(ufd); + int fput_needed; + struct file *file = fget_light(ufd, &fput_needed); if (!file) return -EBADF; ctx = file->private_data; if (file->f_op != &signalfd_fops) { - fput(file); + fput_light(file, fput_needed); return -EINVAL; } spin_lock_irq(¤t->sighand->siglock); @@ -282,7 +283,7 @@ SYSCALL_DEFINE4(signalfd4, int, ufd, sigset_t __user *, user_mask, spin_unlock_irq(¤t->sighand->siglock); wake_up(¤t->sighand->signalfd_wqh); - fput(file); + fput_light(file, fput_needed); } return ufd; diff --git a/fs/splice.c b/fs/splice.c index f8476841eb0..7bf08fa22ec 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) * Check if we need to grow the arrays holding pages and partial page * descriptions. */ -int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) +int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + unsigned int buffers = ACCESS_ONCE(pipe->buffers); + + spd->nr_pages_max = buffers; + if (buffers <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL); + spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; @@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) return -ENOMEM; } -void splice_shrink_spd(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +void splice_shrink_spd(struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); @@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); /* * Lookup the (hopefully) full range of pages we need. @@ -497,7 +500,7 @@ fill_it: if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return error; } @@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &default_pipe_buf_ops, .spd_release = spd_release_page, @@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, res = -ENOMEM; vec = __vec; - if (pipe->buffers > PIPE_DEF_BUFFERS) { - vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL); + if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { + vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); if (!vec) goto shrink_ret; } @@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, offset = *ppos & ~PAGE_CACHE_MASK; nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) { + for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; page = alloc_page(GFP_USER); @@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return res; err: @@ -1003,8 +1007,10 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); ret = file_remove_suid(out); if (!ret) { - file_update_time(out); - ret = splice_from_pipe_feed(pipe, &sd, pipe_to_file); + ret = file_update_time(out); + if (!ret) + ret = splice_from_pipe_feed(pipe, &sd, + pipe_to_file); } mutex_unlock(&inode->i_mutex); } while (ret > 0); @@ -1388,7 +1394,7 @@ static long do_splice(struct file *in, loff_t __user *off_in, */ static int get_iovec_page_array(const struct iovec __user *iov, unsigned int nr_vecs, struct page **pages, - struct partial_page *partial, int aligned, + struct partial_page *partial, bool aligned, unsigned int pipe_buffers) { int buffers = 0, error = 0; @@ -1612,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &user_page_pipe_buf_ops, .spd_release = spd_release_page, @@ -1626,14 +1633,14 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, return -ENOMEM; spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages, - spd.partial, flags & SPLICE_F_GIFT, - pipe->buffers); + spd.partial, false, + spd.nr_pages_max); if (spd.nr_pages <= 0) ret = spd.nr_pages; else ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; } diff --git a/fs/stat.c b/fs/stat.c index c733dc5753a..b6ff11825fc 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -57,12 +57,13 @@ EXPORT_SYMBOL(vfs_getattr); int vfs_fstat(unsigned int fd, struct kstat *stat) { - struct file *f = fget(fd); + int fput_needed; + struct file *f = fget_light(fd, &fput_needed); int error = -EBADF; if (f) { error = vfs_getattr(f->f_path.mnt, f->f_path.dentry, stat); - fput(f); + fput_light(f, fput_needed); } return error; } @@ -137,8 +138,8 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); tmp.st_rdev = old_encode_dev(stat->rdev); #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -190,24 +191,32 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat #endif /* __ARCH_WANT_OLD_STAT */ +#if BITS_PER_LONG == 32 +# define choose_32_64(a,b) a +#else +# define choose_32_64(a,b) b +#endif + +#define valid_dev(x) choose_32_64(old_valid_dev,new_valid_dev)(x) +#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) + +#ifndef INIT_STRUCT_STAT_PADDING +# define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) +#endif + static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; -#if BITS_PER_LONG == 32 - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) return -EOVERFLOW; -#else - if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) +#if BITS_PER_LONG == 32 + if (stat->size > MAX_NON_LFS) return -EOVERFLOW; #endif - memset(&tmp, 0, sizeof(tmp)); -#if BITS_PER_LONG == 32 - tmp.st_dev = old_encode_dev(stat->dev); -#else - tmp.st_dev = new_encode_dev(stat->dev); -#endif + INIT_STRUCT_STAT_PADDING(tmp); + tmp.st_dev = encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -215,17 +224,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) tmp.st_nlink = stat->nlink; if (tmp.st_nlink != stat->nlink) return -EOVERFLOW; - SET_UID(tmp.st_uid, stat->uid); - SET_GID(tmp.st_gid, stat->gid); -#if BITS_PER_LONG == 32 - tmp.st_rdev = old_encode_dev(stat->rdev); -#else - tmp.st_rdev = new_encode_dev(stat->rdev); -#endif -#if BITS_PER_LONG == 32 - if (stat->size > MAX_NON_LFS) - return -EOVERFLOW; -#endif + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); + tmp.st_rdev = encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -327,11 +328,15 @@ SYSCALL_DEFINE3(readlink, const char __user *, path, char __user *, buf, /* ---------- LFS-64 ----------- */ #ifdef __ARCH_WANT_STAT64 +#ifndef INIT_STRUCT_STAT64_PADDING +# define INIT_STRUCT_STAT64_PADDING(st) memset(&st, 0, sizeof(st)) +#endif + static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) { struct stat64 tmp; - memset(&tmp, 0, sizeof(struct stat64)); + INIT_STRUCT_STAT64_PADDING(tmp); #ifdef CONFIG_MIPS /* mips has weird padding, so we don't get 64 bits there */ if (!new_valid_dev(stat->dev) || !new_valid_dev(stat->rdev)) @@ -350,8 +355,8 @@ static long cp_new_stat64(struct kstat *stat, struct stat64 __user *statbuf) #endif tmp.st_mode = stat->mode; tmp.st_nlink = stat->nlink; - tmp.st_uid = stat->uid; - tmp.st_gid = stat->gid; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); tmp.st_atime = stat->atime.tv_sec; tmp.st_atime_nsec = stat->atime.tv_nsec; tmp.st_mtime = stat->mtime.tv_sec; diff --git a/fs/statfs.c b/fs/statfs.c index 43e6b6fe4e8..95ad5c0e586 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -87,11 +87,12 @@ int user_statfs(const char __user *pathname, struct kstatfs *st) int fd_statfs(int fd, struct kstatfs *st) { - struct file *file = fget(fd); + int fput_needed; + struct file *file = fget_light(fd, &fput_needed); int error = -EBADF; if (file) { error = vfs_statfs(&file->f_path, st); - fput(file); + fput_light(file, fput_needed); } return error; } diff --git a/fs/sync.c b/fs/sync.c index 0e8db939d96..11e3d1c4490 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -188,11 +188,12 @@ static int do_fsync(unsigned int fd, int datasync) { struct file *file; int ret = -EBADF; + int fput_needed; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (file) { ret = vfs_fsync(file, datasync); - fput(file); + fput_light(file, fput_needed); } return ret; } diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 35a36d39fa2..e6bb9b2a4cb 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -132,6 +132,24 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd) rb_erase(&sd->s_rb, &sd->s_parent->s_dir.children); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC + +/* Test for attributes that want to ignore lockdep for read-locking */ +static bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return sysfs_type(sd) == SYSFS_KOBJ_ATTR && + sd->s_attr.attr->ignore_lockdep; +} + +#else + +static inline bool ignore_lockdep(struct sysfs_dirent *sd) +{ + return true; +} + +#endif + /** * sysfs_get_active - get an active reference to sysfs_dirent * @sd: sysfs_dirent to get an active reference to @@ -155,15 +173,17 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd) return NULL; t = atomic_cmpxchg(&sd->s_active, v, v + 1); - if (likely(t == v)) { - rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); - return sd; - } + if (likely(t == v)) + break; if (t < 0) return NULL; cpu_relax(); } + + if (likely(!ignore_lockdep(sd))) + rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_); + return sd; } /** @@ -180,7 +200,8 @@ void sysfs_put_active(struct sysfs_dirent *sd) if (unlikely(!sd)) return; - rwsem_release(&sd->dep_map, 1, _RET_IP_); + if (likely(!ignore_lockdep(sd))) + rwsem_release(&sd->dep_map, 1, _RET_IP_); v = atomic_dec_return(&sd->s_active); if (likely(v != SD_DEACTIVATED_BIAS)) return; @@ -858,7 +879,6 @@ int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, const void *new_ns, const char *new_name) { - const char *dup_name = NULL; int error; mutex_lock(&sysfs_mutex); @@ -875,11 +895,11 @@ int sysfs_rename(struct sysfs_dirent *sd, /* rename sysfs_dirent */ if (strcmp(sd->s_name, new_name) != 0) { error = -ENOMEM; - new_name = dup_name = kstrdup(new_name, GFP_KERNEL); + new_name = kstrdup(new_name, GFP_KERNEL); if (!new_name) goto out; - dup_name = sd->s_name; + kfree(sd->s_name); sd->s_name = new_name; } @@ -895,7 +915,6 @@ int sysfs_rename(struct sysfs_dirent *sd, error = 0; out: mutex_unlock(&sysfs_mutex); - kfree(dup_name); return error; } diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index feb2d69396c..0ce3ccf7f40 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -62,8 +62,8 @@ static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd) /* assign default attributes */ iattrs->ia_mode = sd->s_mode; - iattrs->ia_uid = 0; - iattrs->ia_gid = 0; + iattrs->ia_uid = GLOBAL_ROOT_UID; + iattrs->ia_gid = GLOBAL_ROOT_GID; iattrs->ia_atime = iattrs->ia_mtime = iattrs->ia_ctime = CURRENT_TIME; return attrs; @@ -310,7 +310,7 @@ void sysfs_evict_inode(struct inode *inode) struct sysfs_dirent *sd = inode->i_private; truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); sysfs_put(sd); } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 3da5ce25faf..08d0b2568cd 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -316,7 +316,7 @@ static void sysv_evict_inode(struct inode *inode) sysv_truncate(inode); } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); if (!inode->i_nlink) sysv_free_inode(inode); } diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index f8b0160da2d..ba66d508006 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -11,12 +11,6 @@ config UBIFS_FS help UBIFS is a file system for flash devices which works on top of UBI. -config UBIFS_FS_XATTR - bool "Extended attributes support" - depends on UBIFS_FS - help - This option enables support of extended attributes. - config UBIFS_FS_ADVANCED_COMPR bool "Advanced compression options" depends on UBIFS_FS @@ -41,20 +35,3 @@ config UBIFS_FS_ZLIB default y help Zlib compresses better than LZO but it is slower. Say 'Y' if unsure. - -# Debugging-related stuff -config UBIFS_FS_DEBUG - bool "Enable debugging support" - depends on UBIFS_FS - select DEBUG_FS - select KALLSYMS - help - This option enables UBIFS debugging support. It makes sure various - assertions, self-checks, debugging messages and test modes are compiled - in (this all is compiled out otherwise). Assertions are light-weight - and this option also enables them. Self-checks, debugging messages and - test modes are switched off by default. Thus, it is safe and actually - recommended to have debugging support enabled, and it should not slow - down UBIFS. You can then further enable / disable individual debugging - features using UBIFS module parameters and the corresponding sysfs - interfaces. diff --git a/fs/ubifs/Makefile b/fs/ubifs/Makefile index 80e93c35e49..2c6f0cb816b 100644 --- a/fs/ubifs/Makefile +++ b/fs/ubifs/Makefile @@ -3,7 +3,4 @@ obj-$(CONFIG_UBIFS_FS) += ubifs.o ubifs-y += shrinker.o journal.o file.o dir.o super.o sb.o io.o ubifs-y += tnc.o master.o scan.o replay.o log.o commit.o gc.o orphan.o ubifs-y += budget.o find.o tnc_commit.o compress.o lpt.o lprops.o -ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o - -ubifs-$(CONFIG_UBIFS_FS_DEBUG) += debug.o -ubifs-$(CONFIG_UBIFS_FS_XATTR) += xattr.o +ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o xattr.o debug.o diff --git a/fs/ubifs/commit.c b/fs/ubifs/commit.c index fb3b5c813a3..8eda717cb99 100644 --- a/fs/ubifs/commit.c +++ b/fs/ubifs/commit.c @@ -496,7 +496,9 @@ int ubifs_gc_should_commit(struct ubifs_info *c) return ret; } -#ifdef CONFIG_UBIFS_FS_DEBUG +/* + * Everything below is related to debugging. + */ /** * struct idx_node - hold index nodes during index tree traversal. @@ -714,14 +716,14 @@ out: return 0; out_dump: - dbg_err("dumping index node (iip=%d)", i->iip); - dbg_dump_node(c, idx); + ubifs_err("dumping index node (iip=%d)", i->iip); + ubifs_dump_node(c, idx); list_del(&i->list); kfree(i); if (!list_empty(&list)) { i = list_entry(list.prev, struct idx_node, list); - dbg_err("dumping parent index node"); - dbg_dump_node(c, &i->idx); + ubifs_err("dumping parent index node"); + ubifs_dump_node(c, &i->idx); } out_free: while (!list_empty(&list)) { @@ -734,5 +736,3 @@ out_free: err = -EINVAL; return err; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 1934084e208..92df3b08153 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -34,8 +34,6 @@ #include <linux/random.h> #include "ubifs.h" -#ifdef CONFIG_UBIFS_FS_DEBUG - static DEFINE_SPINLOCK(dbg_lock); static const char *get_key_fmt(int fmt) @@ -232,7 +230,7 @@ static void dump_ch(const struct ubifs_ch *ch) printk(KERN_ERR "\tlen %u\n", le32_to_cpu(ch->len)); } -void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode) +void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode) { const struct ubifs_inode *ui = ubifs_inode(inode); struct qstr nm = { .name = NULL }; @@ -300,7 +298,7 @@ void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode) kfree(pdent); } -void dbg_dump_node(const struct ubifs_info *c, const void *node) +void ubifs_dump_node(const struct ubifs_info *c, const void *node) { int i, n; union ubifs_key key; @@ -603,7 +601,7 @@ void dbg_dump_node(const struct ubifs_info *c, const void *node) spin_unlock(&dbg_lock); } -void dbg_dump_budget_req(const struct ubifs_budget_req *req) +void ubifs_dump_budget_req(const struct ubifs_budget_req *req) { spin_lock(&dbg_lock); printk(KERN_ERR "Budgeting request: new_ino %d, dirtied_ino %d\n", @@ -620,7 +618,7 @@ void dbg_dump_budget_req(const struct ubifs_budget_req *req) spin_unlock(&dbg_lock); } -void dbg_dump_lstats(const struct ubifs_lp_stats *lst) +void ubifs_dump_lstats(const struct ubifs_lp_stats *lst) { spin_lock(&dbg_lock); printk(KERN_ERR "(pid %d) Lprops statistics: empty_lebs %d, " @@ -634,7 +632,7 @@ void dbg_dump_lstats(const struct ubifs_lp_stats *lst) spin_unlock(&dbg_lock); } -void dbg_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi) +void ubifs_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi) { int i; struct rb_node *rb; @@ -707,7 +705,7 @@ out_unlock: spin_unlock(&c->space_lock); } -void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp) +void ubifs_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp) { int i, spc, dark = 0, dead = 0; struct rb_node *rb; @@ -801,7 +799,7 @@ void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp) printk(KERN_CONT ")\n"); } -void dbg_dump_lprops(struct ubifs_info *c) +void ubifs_dump_lprops(struct ubifs_info *c) { int lnum, err; struct ubifs_lprops lp; @@ -810,20 +808,20 @@ void dbg_dump_lprops(struct ubifs_info *c) printk(KERN_ERR "(pid %d) start dumping LEB properties\n", current->pid); ubifs_get_lp_stats(c, &lst); - dbg_dump_lstats(&lst); + ubifs_dump_lstats(&lst); for (lnum = c->main_first; lnum < c->leb_cnt; lnum++) { err = ubifs_read_one_lp(c, lnum, &lp); if (err) ubifs_err("cannot read lprops for LEB %d", lnum); - dbg_dump_lprop(c, &lp); + ubifs_dump_lprop(c, &lp); } printk(KERN_ERR "(pid %d) finish dumping LEB properties\n", current->pid); } -void dbg_dump_lpt_info(struct ubifs_info *c) +void ubifs_dump_lpt_info(struct ubifs_info *c) { int i; @@ -862,8 +860,8 @@ void dbg_dump_lpt_info(struct ubifs_info *c) spin_unlock(&dbg_lock); } -void dbg_dump_sleb(const struct ubifs_info *c, - const struct ubifs_scan_leb *sleb, int offs) +void ubifs_dump_sleb(const struct ubifs_info *c, + const struct ubifs_scan_leb *sleb, int offs) { struct ubifs_scan_node *snod; @@ -874,11 +872,11 @@ void dbg_dump_sleb(const struct ubifs_info *c, cond_resched(); printk(KERN_ERR "Dumping node at LEB %d:%d len %d\n", sleb->lnum, snod->offs, snod->len); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); } } -void dbg_dump_leb(const struct ubifs_info *c, int lnum) +void ubifs_dump_leb(const struct ubifs_info *c, int lnum) { struct ubifs_scan_leb *sleb; struct ubifs_scan_node *snod; @@ -909,7 +907,7 @@ void dbg_dump_leb(const struct ubifs_info *c, int lnum) cond_resched(); printk(KERN_ERR "Dumping node at LEB %d:%d len %d\n", lnum, snod->offs, snod->len); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); } printk(KERN_ERR "(pid %d) finish dumping LEB %d\n", @@ -921,8 +919,8 @@ out: return; } -void dbg_dump_znode(const struct ubifs_info *c, - const struct ubifs_znode *znode) +void ubifs_dump_znode(const struct ubifs_info *c, + const struct ubifs_znode *znode) { int n; const struct ubifs_zbranch *zbr; @@ -965,7 +963,7 @@ void dbg_dump_znode(const struct ubifs_info *c, spin_unlock(&dbg_lock); } -void dbg_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat) +void ubifs_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat) { int i; @@ -981,8 +979,8 @@ void dbg_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat) printk(KERN_ERR "(pid %d) finish dumping heap\n", current->pid); } -void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, - struct ubifs_nnode *parent, int iip) +void ubifs_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, + struct ubifs_nnode *parent, int iip) { int i; @@ -999,7 +997,7 @@ void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, } } -void dbg_dump_tnc(struct ubifs_info *c) +void ubifs_dump_tnc(struct ubifs_info *c) { struct ubifs_znode *znode; int level; @@ -1014,7 +1012,7 @@ void dbg_dump_tnc(struct ubifs_info *c) level = znode->level; printk(KERN_ERR "== Level %d ==\n", level); } - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); znode = ubifs_tnc_levelorder_next(c->zroot.znode, znode); } printk(KERN_ERR "(pid %d) finish dumping TNC tree\n", current->pid); @@ -1023,18 +1021,18 @@ void dbg_dump_tnc(struct ubifs_info *c) static int dump_znode(struct ubifs_info *c, struct ubifs_znode *znode, void *priv) { - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); return 0; } /** - * dbg_dump_index - dump the on-flash index. + * ubifs_dump_index - dump the on-flash index. * @c: UBIFS file-system description object * - * This function dumps whole UBIFS indexing B-tree, unlike 'dbg_dump_tnc()' + * This function dumps whole UBIFS indexing B-tree, unlike 'ubifs_dump_tnc()' * which dumps only in-memory znodes and does not read znodes which from flash. */ -void dbg_dump_index(struct ubifs_info *c) +void ubifs_dump_index(struct ubifs_info *c) { dbg_walk_index(c, NULL, dump_znode, NULL); } @@ -1120,15 +1118,15 @@ int dbg_check_space_info(struct ubifs_info *c) out: ubifs_msg("saved lprops statistics dump"); - dbg_dump_lstats(&d->saved_lst); + ubifs_dump_lstats(&d->saved_lst); ubifs_msg("saved budgeting info dump"); - dbg_dump_budg(c, &d->saved_bi); + ubifs_dump_budg(c, &d->saved_bi); ubifs_msg("saved idx_gc_cnt %d", d->saved_idx_gc_cnt); ubifs_msg("current lprops statistics dump"); ubifs_get_lp_stats(c, &lst); - dbg_dump_lstats(&lst); + ubifs_dump_lstats(&lst); ubifs_msg("current budgeting info dump"); - dbg_dump_budg(c, &c->bi); + ubifs_dump_budg(c, &c->bi); dump_stack(); return -EINVAL; } @@ -1160,7 +1158,7 @@ int dbg_check_synced_i_size(const struct ubifs_info *c, struct inode *inode) "is clean", ui->ui_size, ui->synced_i_size); ubifs_err("i_ino %lu, i_mode %#x, i_size %lld", inode->i_ino, inode->i_mode, i_size_read(inode)); - dbg_dump_stack(); + dump_stack(); err = -EINVAL; } spin_unlock(&ui->ui_lock); @@ -1223,14 +1221,14 @@ int dbg_check_dir(struct ubifs_info *c, const struct inode *dir) "but calculated size is %llu", dir->i_ino, (unsigned long long)i_size_read(dir), (unsigned long long)size); - dbg_dump_inode(c, dir); + ubifs_dump_inode(c, dir); dump_stack(); return -EINVAL; } if (dir->i_nlink != nlink) { ubifs_err("directory inode %lu has nlink %u, but calculated " "nlink is %u", dir->i_ino, dir->i_nlink, nlink); - dbg_dump_inode(c, dir); + ubifs_dump_inode(c, dir); dump_stack(); return -EINVAL; } @@ -1287,25 +1285,25 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1, err = 1; key_read(c, &dent1->key, &key); if (keys_cmp(c, &zbr1->key, &key)) { - dbg_err("1st entry at %d:%d has key %s", zbr1->lnum, - zbr1->offs, dbg_snprintf_key(c, &key, key_buf, - DBG_KEY_BUF_LEN)); - dbg_err("but it should have key %s according to tnc", - dbg_snprintf_key(c, &zbr1->key, key_buf, - DBG_KEY_BUF_LEN)); - dbg_dump_node(c, dent1); + ubifs_err("1st entry at %d:%d has key %s", zbr1->lnum, + zbr1->offs, dbg_snprintf_key(c, &key, key_buf, + DBG_KEY_BUF_LEN)); + ubifs_err("but it should have key %s according to tnc", + dbg_snprintf_key(c, &zbr1->key, key_buf, + DBG_KEY_BUF_LEN)); + ubifs_dump_node(c, dent1); goto out_free; } key_read(c, &dent2->key, &key); if (keys_cmp(c, &zbr2->key, &key)) { - dbg_err("2nd entry at %d:%d has key %s", zbr1->lnum, - zbr1->offs, dbg_snprintf_key(c, &key, key_buf, - DBG_KEY_BUF_LEN)); - dbg_err("but it should have key %s according to tnc", - dbg_snprintf_key(c, &zbr2->key, key_buf, - DBG_KEY_BUF_LEN)); - dbg_dump_node(c, dent2); + ubifs_err("2nd entry at %d:%d has key %s", zbr1->lnum, + zbr1->offs, dbg_snprintf_key(c, &key, key_buf, + DBG_KEY_BUF_LEN)); + ubifs_err("but it should have key %s according to tnc", + dbg_snprintf_key(c, &zbr2->key, key_buf, + DBG_KEY_BUF_LEN)); + ubifs_dump_node(c, dent2); goto out_free; } @@ -1318,15 +1316,15 @@ static int dbg_check_key_order(struct ubifs_info *c, struct ubifs_zbranch *zbr1, goto out_free; } if (cmp == 0 && nlen1 == nlen2) - dbg_err("2 xent/dent nodes with the same name"); + ubifs_err("2 xent/dent nodes with the same name"); else - dbg_err("bad order of colliding key %s", - dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN)); + ubifs_err("bad order of colliding key %s", + dbg_snprintf_key(c, &key, key_buf, DBG_KEY_BUF_LEN)); ubifs_msg("first node at %d:%d\n", zbr1->lnum, zbr1->offs); - dbg_dump_node(c, dent1); + ubifs_dump_node(c, dent1); ubifs_msg("second node at %d:%d\n", zbr2->lnum, zbr2->offs); - dbg_dump_node(c, dent2); + ubifs_dump_node(c, dent2); out_free: kfree(dent2); @@ -1529,10 +1527,10 @@ static int dbg_check_znode(struct ubifs_info *c, struct ubifs_zbranch *zbr) out: ubifs_err("failed, error %d", err); ubifs_msg("dump of the znode"); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); if (zp) { ubifs_msg("dump of the parent znode"); - dbg_dump_znode(c, zp); + ubifs_dump_znode(c, zp); } dump_stack(); return -EINVAL; @@ -1599,9 +1597,9 @@ int dbg_check_tnc(struct ubifs_info *c, int extra) return err; if (err) { ubifs_msg("first znode"); - dbg_dump_znode(c, prev); + ubifs_dump_znode(c, prev); ubifs_msg("second znode"); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); return -EINVAL; } } @@ -1690,7 +1688,7 @@ int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, if (err) { ubifs_err("znode checking function returned " "error %d", err); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); goto out_dump; } } @@ -1758,7 +1756,7 @@ out_dump: else zbr = &c->zroot; ubifs_msg("dump of znode at LEB %d:%d", zbr->lnum, zbr->offs); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); out_unlock: mutex_unlock(&c->tnc_mutex); return err; @@ -2194,7 +2192,7 @@ out: out_dump: ubifs_msg("dump of node at LEB %d:%d", zbr->lnum, zbr->offs); - dbg_dump_node(c, node); + ubifs_dump_node(c, node); out_free: kfree(node); return err; @@ -2352,7 +2350,7 @@ out_dump: ubifs_msg("dump of the inode %lu sitting in LEB %d:%d", (unsigned long)fscki->inum, zbr->lnum, zbr->offs); - dbg_dump_node(c, ino); + ubifs_dump_node(c, ino); kfree(ino); return -EINVAL; } @@ -2423,12 +2421,12 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) if (sa->type != UBIFS_DATA_NODE) { ubifs_err("bad node type %d", sa->type); - dbg_dump_node(c, sa->node); + ubifs_dump_node(c, sa->node); return -EINVAL; } if (sb->type != UBIFS_DATA_NODE) { ubifs_err("bad node type %d", sb->type); - dbg_dump_node(c, sb->node); + ubifs_dump_node(c, sb->node); return -EINVAL; } @@ -2459,8 +2457,8 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head) return 0; error_dump: - dbg_dump_node(c, sa->node); - dbg_dump_node(c, sb->node); + ubifs_dump_node(c, sa->node); + ubifs_dump_node(c, sb->node); return -EINVAL; } @@ -2491,13 +2489,13 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && sa->type != UBIFS_XENT_NODE) { ubifs_err("bad node type %d", sa->type); - dbg_dump_node(c, sa->node); + ubifs_dump_node(c, sa->node); return -EINVAL; } if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE && sa->type != UBIFS_XENT_NODE) { ubifs_err("bad node type %d", sb->type); - dbg_dump_node(c, sb->node); + ubifs_dump_node(c, sb->node); return -EINVAL; } @@ -2547,9 +2545,9 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head) error_dump: ubifs_msg("dumping first node"); - dbg_dump_node(c, sa->node); + ubifs_dump_node(c, sa->node); ubifs_msg("dumping second node"); - dbg_dump_node(c, sb->node); + ubifs_dump_node(c, sb->node); return -EINVAL; return 0; } @@ -2678,7 +2676,7 @@ static void cut_data(const void *buf, unsigned int len) } int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, - int offs, int len, int dtype) + int offs, int len) { int err, failing; @@ -2688,7 +2686,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, failing = power_cut_emulated(c, lnum, 1); if (failing) cut_data(buf, len); - err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); + err = ubi_leb_write(c->ubi, lnum, buf, offs, len); if (err) return err; if (failing) @@ -2697,7 +2695,7 @@ int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, } int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, - int len, int dtype) + int len) { int err; @@ -2705,7 +2703,7 @@ int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, return -EROFS; if (power_cut_emulated(c, lnum, 1)) return -EROFS; - err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); + err = ubi_leb_change(c->ubi, lnum, buf, len); if (err) return err; if (power_cut_emulated(c, lnum, 1)) @@ -2729,7 +2727,7 @@ int dbg_leb_unmap(struct ubifs_info *c, int lnum) return 0; } -int dbg_leb_map(struct ubifs_info *c, int lnum, int dtype) +int dbg_leb_map(struct ubifs_info *c, int lnum) { int err; @@ -2737,7 +2735,7 @@ int dbg_leb_map(struct ubifs_info *c, int lnum, int dtype) return -EROFS; if (power_cut_emulated(c, lnum, 0)) return -EROFS; - err = ubi_leb_map(c->ubi, lnum, dtype); + err = ubi_leb_map(c->ubi, lnum); if (err) return err; if (power_cut_emulated(c, lnum, 0)) @@ -2857,16 +2855,16 @@ static ssize_t dfs_file_write(struct file *file, const char __user *u, * 'ubifs-debug' file-system instead. */ if (file->f_path.dentry == d->dfs_dump_lprops) { - dbg_dump_lprops(c); + ubifs_dump_lprops(c); return count; } if (file->f_path.dentry == d->dfs_dump_budg) { - dbg_dump_budg(c, &c->bi); + ubifs_dump_budg(c, &c->bi); return count; } if (file->f_path.dentry == d->dfs_dump_tnc) { mutex_lock(&c->tnc_mutex); - dbg_dump_tnc(c); + ubifs_dump_tnc(c); mutex_unlock(&c->tnc_mutex); return count; } @@ -2920,6 +2918,9 @@ int dbg_debugfs_init_fs(struct ubifs_info *c) struct dentry *dent; struct ubifs_debug_info *d = c->dbg; + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME, c->vi.ubi_num, c->vi.vol_id); if (n == UBIFS_DFS_DIR_LEN) { @@ -3012,7 +3013,8 @@ out: */ void dbg_debugfs_exit_fs(struct ubifs_info *c) { - debugfs_remove_recursive(c->dbg->dfs_dir); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + debugfs_remove_recursive(c->dbg->dfs_dir); } struct ubifs_global_debug_info ubifs_dbg; @@ -3097,6 +3099,9 @@ int dbg_debugfs_init(void) const char *fname; struct dentry *dent; + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + fname = "ubifs"; dent = debugfs_create_dir(fname, NULL); if (IS_ERR_OR_NULL(dent)) @@ -3161,7 +3166,8 @@ out: */ void dbg_debugfs_exit(void) { - debugfs_remove_recursive(dfs_rootdir); + if (IS_ENABLED(CONFIG_DEBUG_FS)) + debugfs_remove_recursive(dfs_rootdir); } /** @@ -3189,5 +3195,3 @@ void ubifs_debugging_exit(struct ubifs_info *c) { kfree(c->dbg); } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 9f717655df1..486a8e024fb 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -29,8 +29,6 @@ typedef int (*dbg_leaf_callback)(struct ubifs_info *c, typedef int (*dbg_znode_callback)(struct ubifs_info *c, struct ubifs_znode *znode, void *priv); -#ifdef CONFIG_UBIFS_FS_DEBUG - /* * The UBIFS debugfs directory name pattern and maximum name length (3 for "ubi" * + 1 for "_" and plus 2x2 for 2 UBI numbers and 1 for the trailing zero byte. @@ -149,7 +147,7 @@ struct ubifs_global_debug_info { if (unlikely(!(expr))) { \ printk(KERN_CRIT "UBIFS assert failed in %s at %u (pid %d)\n", \ __func__, __LINE__, current->pid); \ - dbg_dump_stack(); \ + dump_stack(); \ } \ } while (0) @@ -161,12 +159,6 @@ struct ubifs_global_debug_info { } \ } while (0) -#define dbg_dump_stack() dump_stack() - -#define dbg_err(fmt, ...) do { \ - ubifs_err(fmt, ##__VA_ARGS__); \ -} while (0) - #define ubifs_dbg_msg(type, fmt, ...) \ pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__) @@ -257,27 +249,27 @@ const char *dbg_get_key_dump(const struct ubifs_info *c, const union ubifs_key *key); const char *dbg_snprintf_key(const struct ubifs_info *c, const union ubifs_key *key, char *buffer, int len); -void dbg_dump_inode(struct ubifs_info *c, const struct inode *inode); -void dbg_dump_node(const struct ubifs_info *c, const void *node); -void dbg_dump_lpt_node(const struct ubifs_info *c, void *node, int lnum, - int offs); -void dbg_dump_budget_req(const struct ubifs_budget_req *req); -void dbg_dump_lstats(const struct ubifs_lp_stats *lst); -void dbg_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi); -void dbg_dump_lprop(const struct ubifs_info *c, const struct ubifs_lprops *lp); -void dbg_dump_lprops(struct ubifs_info *c); -void dbg_dump_lpt_info(struct ubifs_info *c); -void dbg_dump_leb(const struct ubifs_info *c, int lnum); -void dbg_dump_sleb(const struct ubifs_info *c, - const struct ubifs_scan_leb *sleb, int offs); -void dbg_dump_znode(const struct ubifs_info *c, - const struct ubifs_znode *znode); -void dbg_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat); -void dbg_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, - struct ubifs_nnode *parent, int iip); -void dbg_dump_tnc(struct ubifs_info *c); -void dbg_dump_index(struct ubifs_info *c); -void dbg_dump_lpt_lebs(const struct ubifs_info *c); +void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode); +void ubifs_dump_node(const struct ubifs_info *c, const void *node); +void ubifs_dump_budget_req(const struct ubifs_budget_req *req); +void ubifs_dump_lstats(const struct ubifs_lp_stats *lst); +void ubifs_dump_budg(struct ubifs_info *c, const struct ubifs_budg_info *bi); +void ubifs_dump_lprop(const struct ubifs_info *c, + const struct ubifs_lprops *lp); +void ubifs_dump_lprops(struct ubifs_info *c); +void ubifs_dump_lpt_info(struct ubifs_info *c); +void ubifs_dump_leb(const struct ubifs_info *c, int lnum); +void ubifs_dump_sleb(const struct ubifs_info *c, + const struct ubifs_scan_leb *sleb, int offs); +void ubifs_dump_znode(const struct ubifs_info *c, + const struct ubifs_znode *znode); +void ubifs_dump_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, + int cat); +void ubifs_dump_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, + struct ubifs_nnode *parent, int iip); +void ubifs_dump_tnc(struct ubifs_info *c); +void ubifs_dump_index(struct ubifs_info *c); +void ubifs_dump_lpt_lebs(const struct ubifs_info *c); int dbg_walk_index(struct ubifs_info *c, dbg_leaf_callback leaf_cb, dbg_znode_callback znode_cb, void *priv); @@ -307,11 +299,10 @@ int dbg_check_data_nodes_order(struct ubifs_info *c, struct list_head *head); int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head); int dbg_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, - int len, int dtype); -int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, - int dtype); + int len); +int dbg_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len); int dbg_leb_unmap(struct ubifs_info *c, int lnum); -int dbg_leb_map(struct ubifs_info *c, int lnum, int dtype); +int dbg_leb_map(struct ubifs_info *c, int lnum); /* Debugfs-related stuff */ int dbg_debugfs_init(void); @@ -319,162 +310,4 @@ void dbg_debugfs_exit(void); int dbg_debugfs_init_fs(struct ubifs_info *c); void dbg_debugfs_exit_fs(struct ubifs_info *c); -#else /* !CONFIG_UBIFS_FS_DEBUG */ - -/* Use "if (0)" to make compiler check arguments even if debugging is off */ -#define ubifs_assert(expr) do { \ - if (0) \ - printk(KERN_CRIT "UBIFS assert failed in %s at %u (pid %d)\n", \ - __func__, __LINE__, current->pid); \ -} while (0) - -#define dbg_err(fmt, ...) do { \ - if (0) \ - ubifs_err(fmt, ##__VA_ARGS__); \ -} while (0) - -#define DBGKEY(key) ((char *)(key)) -#define DBGKEY1(key) ((char *)(key)) - -#define ubifs_dbg_msg(fmt, ...) do { \ - if (0) \ - printk(KERN_DEBUG fmt "\n", ##__VA_ARGS__); \ -} while (0) - -#define dbg_dump_stack() -#define ubifs_assert_cmt_locked(c) - -#define dbg_msg(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_gen(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_jnl(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_jnlk(key, fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_tnc(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_tnck(key, fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_lp(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_find(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_mnt(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_mntk(key, fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_io(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_cmt(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_budg(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_log(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_gc(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_scan(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) -#define dbg_rcvry(fmt, ...) ubifs_dbg_msg(fmt, ##__VA_ARGS__) - -static inline int ubifs_debugging_init(struct ubifs_info *c) { return 0; } -static inline void ubifs_debugging_exit(struct ubifs_info *c) { return; } -static inline const char *dbg_ntype(int type) { return ""; } -static inline const char *dbg_cstate(int cmt_state) { return ""; } -static inline const char *dbg_jhead(int jhead) { return ""; } -static inline const char * -dbg_get_key_dump(const struct ubifs_info *c, - const union ubifs_key *key) { return ""; } -static inline const char * -dbg_snprintf_key(const struct ubifs_info *c, - const union ubifs_key *key, char *buffer, - int len) { return ""; } -static inline void dbg_dump_inode(struct ubifs_info *c, - const struct inode *inode) { return; } -static inline void dbg_dump_node(const struct ubifs_info *c, - const void *node) { return; } -static inline void dbg_dump_lpt_node(const struct ubifs_info *c, - void *node, int lnum, - int offs) { return; } -static inline void -dbg_dump_budget_req(const struct ubifs_budget_req *req) { return; } -static inline void -dbg_dump_lstats(const struct ubifs_lp_stats *lst) { return; } -static inline void -dbg_dump_budg(struct ubifs_info *c, - const struct ubifs_budg_info *bi) { return; } -static inline void dbg_dump_lprop(const struct ubifs_info *c, - const struct ubifs_lprops *lp) { return; } -static inline void dbg_dump_lprops(struct ubifs_info *c) { return; } -static inline void dbg_dump_lpt_info(struct ubifs_info *c) { return; } -static inline void dbg_dump_leb(const struct ubifs_info *c, - int lnum) { return; } -static inline void -dbg_dump_sleb(const struct ubifs_info *c, - const struct ubifs_scan_leb *sleb, int offs) { return; } -static inline void -dbg_dump_znode(const struct ubifs_info *c, - const struct ubifs_znode *znode) { return; } -static inline void dbg_dump_heap(struct ubifs_info *c, - struct ubifs_lpt_heap *heap, - int cat) { return; } -static inline void dbg_dump_pnode(struct ubifs_info *c, - struct ubifs_pnode *pnode, - struct ubifs_nnode *parent, - int iip) { return; } -static inline void dbg_dump_tnc(struct ubifs_info *c) { return; } -static inline void dbg_dump_index(struct ubifs_info *c) { return; } -static inline void dbg_dump_lpt_lebs(const struct ubifs_info *c) { return; } - -static inline int dbg_walk_index(struct ubifs_info *c, - dbg_leaf_callback leaf_cb, - dbg_znode_callback znode_cb, - void *priv) { return 0; } -static inline void dbg_save_space_info(struct ubifs_info *c) { return; } -static inline int dbg_check_space_info(struct ubifs_info *c) { return 0; } -static inline int dbg_check_lprops(struct ubifs_info *c) { return 0; } -static inline int -dbg_old_index_check_init(struct ubifs_info *c, - struct ubifs_zbranch *zroot) { return 0; } -static inline int -dbg_check_old_index(struct ubifs_info *c, - struct ubifs_zbranch *zroot) { return 0; } -static inline int dbg_check_cats(struct ubifs_info *c) { return 0; } -static inline int dbg_check_ltab(struct ubifs_info *c) { return 0; } -static inline int dbg_chk_lpt_free_spc(struct ubifs_info *c) { return 0; } -static inline int dbg_chk_lpt_sz(struct ubifs_info *c, - int action, int len) { return 0; } -static inline int -dbg_check_synced_i_size(const struct ubifs_info *c, - struct inode *inode) { return 0; } -static inline int dbg_check_dir(struct ubifs_info *c, - const struct inode *dir) { return 0; } -static inline int dbg_check_tnc(struct ubifs_info *c, int extra) { return 0; } -static inline int dbg_check_idx_size(struct ubifs_info *c, - long long idx_size) { return 0; } -static inline int dbg_check_filesystem(struct ubifs_info *c) { return 0; } -static inline void dbg_check_heap(struct ubifs_info *c, - struct ubifs_lpt_heap *heap, - int cat, int add_pos) { return; } -static inline int dbg_check_lpt_nodes(struct ubifs_info *c, - struct ubifs_cnode *cnode, int row, int col) { return 0; } -static inline int dbg_check_inode_size(struct ubifs_info *c, - const struct inode *inode, - loff_t size) { return 0; } -static inline int -dbg_check_data_nodes_order(struct ubifs_info *c, - struct list_head *head) { return 0; } -static inline int -dbg_check_nondata_nodes_order(struct ubifs_info *c, - struct list_head *head) { return 0; } - -static inline int dbg_leb_write(struct ubifs_info *c, int lnum, - const void *buf, int offset, - int len, int dtype) { return 0; } -static inline int dbg_leb_change(struct ubifs_info *c, int lnum, - const void *buf, int len, - int dtype) { return 0; } -static inline int dbg_leb_unmap(struct ubifs_info *c, int lnum) { return 0; } -static inline int dbg_leb_map(struct ubifs_info *c, int lnum, - int dtype) { return 0; } - -static inline int dbg_is_chk_gen(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_chk_index(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_chk_orph(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_chk_lprops(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_chk_fs(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_tst_rcvry(const struct ubifs_info *c) { return 0; } -static inline int dbg_is_power_cut(const struct ubifs_info *c) { return 0; } - -static inline int dbg_debugfs_init(void) { return 0; } -static inline void dbg_debugfs_exit(void) { return; } -static inline int dbg_debugfs_init_fs(struct ubifs_info *c) { return 0; } -static inline int dbg_debugfs_exit_fs(struct ubifs_info *c) { return 0; } - -#endif /* !CONFIG_UBIFS_FS_DEBUG */ #endif /* !__UBIFS_DEBUG_H__ */ diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index ec9f1870ab7..a6d42efc76d 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -170,8 +170,6 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, return inode; } -#ifdef CONFIG_UBIFS_FS_DEBUG - static int dbg_check_name(const struct ubifs_info *c, const struct ubifs_dent_node *dent, const struct qstr *nm) @@ -185,12 +183,6 @@ static int dbg_check_name(const struct ubifs_info *c, return 0; } -#else - -#define dbg_check_name(c, dent, nm) 0 - -#endif - static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { @@ -1135,16 +1127,7 @@ int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct ubifs_inode *ui = ubifs_inode(inode); mutex_lock(&ui->ui_mutex); - stat->dev = inode->i_sb->s_dev; - stat->ino = inode->i_ino; - stat->mode = inode->i_mode; - stat->nlink = inode->i_nlink; - stat->uid = inode->i_uid; - stat->gid = inode->i_gid; - stat->rdev = inode->i_rdev; - stat->atime = inode->i_atime; - stat->mtime = inode->i_mtime; - stat->ctime = inode->i_ctime; + generic_fillattr(inode, stat); stat->blksize = UBIFS_BLOCK_SIZE; stat->size = ui->ui_size; @@ -1187,12 +1170,10 @@ const struct inode_operations ubifs_dir_inode_operations = { .rename = ubifs_rename, .setattr = ubifs_setattr, .getattr = ubifs_getattr, -#ifdef CONFIG_UBIFS_FS_XATTR .setxattr = ubifs_setxattr, .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, -#endif }; const struct file_operations ubifs_dir_operations = { diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5c8f6dc1d28..35389ca2d26 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -97,7 +97,7 @@ static int read_block(struct inode *inode, void *addr, unsigned int block, dump: ubifs_err("bad data node (block %u, inode %lu)", block, inode->i_ino); - dbg_dump_node(c, dn); + ubifs_dump_node(c, dn); return -EINVAL; } @@ -1562,12 +1562,10 @@ const struct address_space_operations ubifs_file_address_operations = { const struct inode_operations ubifs_file_inode_operations = { .setattr = ubifs_setattr, .getattr = ubifs_getattr, -#ifdef CONFIG_UBIFS_FS_XATTR .setxattr = ubifs_setxattr, .getxattr = ubifs_getxattr, .listxattr = ubifs_listxattr, .removexattr = ubifs_removexattr, -#endif }; const struct inode_operations ubifs_symlink_inode_operations = { diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 2559d174e00..28ec13af28d 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -939,8 +939,8 @@ static int find_dirtiest_idx_leb(struct ubifs_info *c) } dbg_find("LEB %d, dirty %d and free %d flags %#x", lp->lnum, lp->dirty, lp->free, lp->flags); - ubifs_assert(lp->flags | LPROPS_TAKEN); - ubifs_assert(lp->flags | LPROPS_INDEX); + ubifs_assert(lp->flags & LPROPS_TAKEN); + ubifs_assert(lp->flags & LPROPS_INDEX); return lnum; } diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index ded29f6224c..04dd6f47635 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -109,7 +109,7 @@ static int switch_gc_head(struct ubifs_info *c) return err; c->gc_lnum = -1; - err = ubifs_wbuf_seek_nolock(wbuf, gc_lnum, 0, UBI_LONGTERM); + err = ubifs_wbuf_seek_nolock(wbuf, gc_lnum, 0); return err; } diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 9228950a658..e18b9889a51 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -109,13 +109,13 @@ int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, if (err && (err != -EBADMSG || even_ebadmsg)) { ubifs_err("reading %d bytes from LEB %d:%d failed, error %d", len, lnum, offs, err); - dbg_dump_stack(); + dump_stack(); } return err; } int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, - int len, int dtype) + int len) { int err; @@ -123,20 +123,19 @@ int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, if (c->ro_error) return -EROFS; if (!dbg_is_tst_rcvry(c)) - err = ubi_leb_write(c->ubi, lnum, buf, offs, len, dtype); + err = ubi_leb_write(c->ubi, lnum, buf, offs, len); else - err = dbg_leb_write(c, lnum, buf, offs, len, dtype); + err = dbg_leb_write(c, lnum, buf, offs, len); if (err) { ubifs_err("writing %d bytes to LEB %d:%d failed, error %d", len, lnum, offs, err); ubifs_ro_mode(c, err); - dbg_dump_stack(); + dump_stack(); } return err; } -int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, - int dtype) +int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len) { int err; @@ -144,14 +143,14 @@ int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, if (c->ro_error) return -EROFS; if (!dbg_is_tst_rcvry(c)) - err = ubi_leb_change(c->ubi, lnum, buf, len, dtype); + err = ubi_leb_change(c->ubi, lnum, buf, len); else - err = dbg_leb_change(c, lnum, buf, len, dtype); + err = dbg_leb_change(c, lnum, buf, len); if (err) { ubifs_err("changing %d bytes in LEB %d failed, error %d", len, lnum, err); ubifs_ro_mode(c, err); - dbg_dump_stack(); + dump_stack(); } return err; } @@ -170,12 +169,12 @@ int ubifs_leb_unmap(struct ubifs_info *c, int lnum) if (err) { ubifs_err("unmap LEB %d failed, error %d", lnum, err); ubifs_ro_mode(c, err); - dbg_dump_stack(); + dump_stack(); } return err; } -int ubifs_leb_map(struct ubifs_info *c, int lnum, int dtype) +int ubifs_leb_map(struct ubifs_info *c, int lnum) { int err; @@ -183,13 +182,13 @@ int ubifs_leb_map(struct ubifs_info *c, int lnum, int dtype) if (c->ro_error) return -EROFS; if (!dbg_is_tst_rcvry(c)) - err = ubi_leb_map(c->ubi, lnum, dtype); + err = ubi_leb_map(c->ubi, lnum); else - err = dbg_leb_map(c, lnum, dtype); + err = dbg_leb_map(c, lnum); if (err) { ubifs_err("mapping LEB %d failed, error %d", lnum, err); ubifs_ro_mode(c, err); - dbg_dump_stack(); + dump_stack(); } return err; } @@ -202,7 +201,7 @@ int ubifs_is_mapped(const struct ubifs_info *c, int lnum) if (err < 0) { ubifs_err("ubi_is_mapped failed for LEB %d, error %d", lnum, err); - dbg_dump_stack(); + dump_stack(); } return err; } @@ -294,8 +293,8 @@ out_len: out: if (!quiet) { ubifs_err("bad node at LEB %d:%d", lnum, offs); - dbg_dump_node(c, buf); - dbg_dump_stack(); + ubifs_dump_node(c, buf); + dump_stack(); } return err; } @@ -523,8 +522,7 @@ int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf) dirt = sync_len - wbuf->used; if (dirt) ubifs_pad(c, wbuf->buf + wbuf->used, dirt); - err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, sync_len, - wbuf->dtype); + err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, sync_len); if (err) return err; @@ -562,14 +560,12 @@ int ubifs_wbuf_sync_nolock(struct ubifs_wbuf *wbuf) * @wbuf: write-buffer * @lnum: logical eraseblock number to seek to * @offs: logical eraseblock offset to seek to - * @dtype: data type * * This function targets the write-buffer to logical eraseblock @lnum:@offs. * The write-buffer has to be empty. Returns zero in case of success and a * negative error code in case of failure. */ -int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs, - int dtype) +int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs) { const struct ubifs_info *c = wbuf->c; @@ -592,7 +588,6 @@ int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs, wbuf->avail = wbuf->size; wbuf->used = 0; spin_unlock(&wbuf->lock); - wbuf->dtype = dtype; return 0; } @@ -719,8 +714,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) dbg_io("flush jhead %s wbuf to LEB %d:%d", dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs); err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, - wbuf->offs, wbuf->size, - wbuf->dtype); + wbuf->offs, wbuf->size); if (err) goto out; @@ -756,7 +750,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) dbg_jhead(wbuf->jhead), wbuf->lnum, wbuf->offs); memcpy(wbuf->buf + wbuf->used, buf, wbuf->avail); err = ubifs_leb_write(c, wbuf->lnum, wbuf->buf, wbuf->offs, - wbuf->size, wbuf->dtype); + wbuf->size); if (err) goto out; @@ -775,7 +769,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) dbg_io("write %d bytes to LEB %d:%d", wbuf->size, wbuf->lnum, wbuf->offs); err = ubifs_leb_write(c, wbuf->lnum, buf, wbuf->offs, - wbuf->size, wbuf->dtype); + wbuf->size); if (err) goto out; @@ -797,7 +791,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len) dbg_io("write %d bytes to LEB %d:%d", n, wbuf->lnum, wbuf->offs); err = ubifs_leb_write(c, wbuf->lnum, buf + written, - wbuf->offs, n, wbuf->dtype); + wbuf->offs, n); if (err) goto out; wbuf->offs += n; @@ -841,9 +835,9 @@ exit: out: ubifs_err("cannot write %d bytes to LEB %d:%d, error %d", len, wbuf->lnum, wbuf->offs, err); - dbg_dump_node(c, buf); - dbg_dump_stack(); - dbg_dump_leb(c, wbuf->lnum); + ubifs_dump_node(c, buf); + dump_stack(); + ubifs_dump_leb(c, wbuf->lnum); return err; } @@ -854,7 +848,6 @@ out: * @len: node length * @lnum: logical eraseblock number * @offs: offset within the logical eraseblock - * @dtype: node life-time hint (%UBI_LONGTERM, %UBI_SHORTTERM, %UBI_UNKNOWN) * * This function automatically fills node magic number, assigns sequence * number, and calculates node CRC checksum. The length of the @buf buffer has @@ -863,7 +856,7 @@ out: * success and a negative error code in case of failure. */ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, - int offs, int dtype) + int offs) { int err, buf_len = ALIGN(len, c->min_io_size); @@ -879,9 +872,9 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, return -EROFS; ubifs_prepare_node(c, buf, len, 1); - err = ubifs_leb_write(c, lnum, buf, offs, buf_len, dtype); + err = ubifs_leb_write(c, lnum, buf, offs, buf_len); if (err) - dbg_dump_node(c, buf); + ubifs_dump_node(c, buf); return err; } @@ -960,8 +953,8 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, out: ubifs_err("bad node at LEB %d:%d", lnum, offs); - dbg_dump_node(c, buf); - dbg_dump_stack(); + ubifs_dump_node(c, buf); + dump_stack(); return -EINVAL; } @@ -1017,8 +1010,8 @@ int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len, out: ubifs_err("bad node at LEB %d:%d, LEB mapping status %d", lnum, offs, ubi_is_mapped(c->ubi, lnum)); - dbg_dump_node(c, buf); - dbg_dump_stack(); + ubifs_dump_node(c, buf); + dump_stack(); return -EINVAL; } @@ -1056,7 +1049,6 @@ int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf) */ size = c->max_write_size - (c->leb_start % c->max_write_size); wbuf->avail = wbuf->size = size; - wbuf->dtype = UBI_UNKNOWN; wbuf->sync_callback = NULL; mutex_init(&wbuf->io_mutex); spin_lock_init(&wbuf->lock); diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 2f438ab2e7a..12c0f154ca8 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -214,7 +214,7 @@ out: err = ubifs_add_bud_to_log(c, jhead, lnum, offs); if (err) goto out_return; - err = ubifs_wbuf_seek_nolock(wbuf, lnum, offs, wbuf->dtype); + err = ubifs_wbuf_seek_nolock(wbuf, lnum, offs); if (err) goto out_unlock; @@ -385,9 +385,9 @@ out: if (err == -ENOSPC) { /* This are some budgeting problems, print useful information */ down_write(&c->commit_sem); - dbg_dump_stack(); - dbg_dump_budg(c, &c->bi); - dbg_dump_lprops(c); + dump_stack(); + ubifs_dump_budg(c, &c->bi); + ubifs_dump_lprops(c); cmt_retries = dbg_check_lprops(c); up_write(&c->commit_sem); } @@ -1267,7 +1267,6 @@ out_free: return err; } -#ifdef CONFIG_UBIFS_FS_XATTR /** * ubifs_jnl_delete_xattr - delete an extended attribute. @@ -1462,4 +1461,3 @@ out_free: return err; } -#endif /* CONFIG_UBIFS_FS_XATTR */ diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index f9fd068d1ae..c80b15d6c8d 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -29,11 +29,7 @@ #include "ubifs.h" -#ifdef CONFIG_UBIFS_FS_DEBUG static int dbg_check_bud_bytes(struct ubifs_info *c); -#else -#define dbg_check_bud_bytes(c) 0 -#endif /** * ubifs_search_bud - search bud LEB. @@ -262,7 +258,7 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) * an unclean reboot, because the target LEB might have been * unmapped, but not yet physically erased. */ - err = ubifs_leb_map(c, bud->lnum, UBI_SHORTTERM); + err = ubifs_leb_map(c, bud->lnum); if (err) goto out_unlock; } @@ -270,7 +266,7 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) dbg_log("write ref LEB %d:%d", c->lhead_lnum, c->lhead_offs); err = ubifs_write_node(c, ref, UBIFS_REF_NODE_SZ, c->lhead_lnum, - c->lhead_offs, UBI_SHORTTERM); + c->lhead_offs); if (err) goto out_unlock; @@ -422,7 +418,7 @@ int ubifs_log_start_commit(struct ubifs_info *c, int *ltail_lnum) len = ALIGN(len, c->min_io_size); dbg_log("writing commit start at LEB %d:0, len %d", c->lhead_lnum, len); - err = ubifs_leb_write(c, c->lhead_lnum, cs, 0, len, UBI_SHORTTERM); + err = ubifs_leb_write(c, c->lhead_lnum, cs, 0, len); if (err) goto out; @@ -623,7 +619,7 @@ static int add_node(struct ubifs_info *c, void *buf, int *lnum, int *offs, int sz = ALIGN(*offs, c->min_io_size), err; ubifs_pad(c, buf + *offs, sz - *offs); - err = ubifs_leb_change(c, *lnum, buf, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, *lnum, buf, sz); if (err) return err; *lnum = ubifs_next_log_lnum(c, *lnum); @@ -702,7 +698,7 @@ int ubifs_consolidate_log(struct ubifs_info *c) int sz = ALIGN(offs, c->min_io_size); ubifs_pad(c, buf + offs, sz - offs); - err = ubifs_leb_change(c, write_lnum, buf, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, write_lnum, buf, sz); if (err) goto out_free; offs = ALIGN(offs, c->min_io_size); @@ -734,8 +730,6 @@ out_free: return err; } -#ifdef CONFIG_UBIFS_FS_DEBUG - /** * dbg_check_bud_bytes - make sure bud bytes calculation are all right. * @c: UBIFS file-system description object @@ -767,5 +761,3 @@ static int dbg_check_bud_bytes(struct ubifs_info *c) return err; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index f8a181e647c..86eb8e53324 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -447,7 +447,7 @@ static void change_category(struct ubifs_info *c, struct ubifs_lprops *lprops) int new_cat = ubifs_categorize_lprops(c, lprops); if (old_cat == new_cat) { - struct ubifs_lpt_heap *heap = &c->lpt_heap[new_cat - 1]; + struct ubifs_lpt_heap *heap; /* lprops on a heap now must be moved up or down */ if (new_cat < 1 || new_cat > LPROPS_HEAP_CNT) @@ -846,7 +846,9 @@ const struct ubifs_lprops *ubifs_fast_find_frdi_idx(struct ubifs_info *c) return lprops; } -#ifdef CONFIG_UBIFS_FS_DEBUG +/* + * Everything below is related to debugging. + */ /** * dbg_check_cats - check category heaps and lists. @@ -1001,8 +1003,8 @@ void dbg_check_heap(struct ubifs_info *c, struct ubifs_lpt_heap *heap, int cat, out: if (err) { dbg_msg("failed cat %d hpos %d err %d", cat, i, err); - dbg_dump_stack(); - dbg_dump_heap(c, heap, cat); + dump_stack(); + ubifs_dump_heap(c, heap, cat); } } @@ -1109,8 +1111,8 @@ static int scan_check_cb(struct ubifs_info *c, if (IS_ERR(sleb)) { ret = PTR_ERR(sleb); if (ret == -EUCLEAN) { - dbg_dump_lprops(c); - dbg_dump_budg(c, &c->bi); + ubifs_dump_lprops(c); + ubifs_dump_budg(c, &c->bi); } goto out; } @@ -1237,7 +1239,7 @@ out_print: ubifs_err("bad accounting of LEB %d: free %d, dirty %d flags %#x, " "should be free %d, dirty %d", lnum, lp->free, lp->dirty, lp->flags, free, dirty); - dbg_dump_leb(c, lnum); + ubifs_dump_leb(c, lnum); out_destroy: ubifs_scan_destroy(sleb); ret = -EINVAL; @@ -1315,5 +1317,3 @@ int dbg_check_lprops(struct ubifs_info *c) out: return err; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 66d59d0a140..ce33b2beb15 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -701,8 +701,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubifs_leb_change(c, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen); if (err) goto out; p = buf; @@ -732,8 +731,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubifs_leb_change(c, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen); if (err) goto out; p = buf; @@ -780,8 +778,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubifs_leb_change(c, lnum++, buf, alen, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen); if (err) goto out; p = buf; @@ -806,7 +803,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, alen = ALIGN(len, c->min_io_size); set_ltab(c, lnum, c->leb_size - alen, alen - len); memset(p, 0xff, alen - len); - err = ubifs_leb_change(c, lnum++, buf, alen, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum++, buf, alen); if (err) goto out; p = buf; @@ -826,7 +823,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, /* Write remaining buffer */ memset(p, 0xff, alen - len); - err = ubifs_leb_change(c, lnum, buf, alen, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum, buf, alen); if (err) goto out; @@ -926,7 +923,7 @@ static int check_lpt_crc(void *buf, int len) if (crc != calc_crc) { ubifs_err("invalid crc in LPT node: crc %hx calc %hx", crc, calc_crc); - dbg_dump_stack(); + dump_stack(); return -EINVAL; } return 0; @@ -949,7 +946,7 @@ static int check_lpt_type(uint8_t **addr, int *pos, int type) if (node_type != type) { ubifs_err("invalid type (%d) in LPT node type %d", node_type, type); - dbg_dump_stack(); + dump_stack(); return -EINVAL; } return 0; @@ -1247,7 +1244,7 @@ int ubifs_read_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) out: ubifs_err("error %d reading nnode at %d:%d", err, lnum, offs); - dbg_dump_stack(); + dump_stack(); kfree(nnode); return err; } @@ -1312,8 +1309,8 @@ static int read_pnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip) out: ubifs_err("error %d reading pnode at %d:%d", err, lnum, offs); - dbg_dump_pnode(c, pnode, parent, iip); - dbg_dump_stack(); + ubifs_dump_pnode(c, pnode, parent, iip); + dump_stack(); dbg_msg("calc num: %d", calc_pnode_num_from_parent(c, parent, iip)); kfree(pnode); return err; @@ -1740,16 +1737,20 @@ int ubifs_lpt_init(struct ubifs_info *c, int rd, int wr) if (rd) { err = lpt_init_rd(c); if (err) - return err; + goto out_err; } if (wr) { err = lpt_init_wr(c); if (err) - return err; + goto out_err; } return 0; + +out_err: + ubifs_lpt_free(c, 0); + return err; } /** @@ -2080,8 +2081,6 @@ out: return err; } -#ifdef CONFIG_UBIFS_FS_DEBUG - /** * dbg_chk_pnode - check a pnode. * @c: the UBIFS file-system description object @@ -2096,8 +2095,8 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, int i; if (pnode->num != col) { - dbg_err("pnode num %d expected %d parent num %d iip %d", - pnode->num, col, pnode->parent->num, pnode->iip); + ubifs_err("pnode num %d expected %d parent num %d iip %d", + pnode->num, col, pnode->parent->num, pnode->iip); return -EINVAL; } for (i = 0; i < UBIFS_LPT_FANOUT; i++) { @@ -2111,14 +2110,14 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, if (lnum >= c->leb_cnt) continue; if (lprops->lnum != lnum) { - dbg_err("bad LEB number %d expected %d", - lprops->lnum, lnum); + ubifs_err("bad LEB number %d expected %d", + lprops->lnum, lnum); return -EINVAL; } if (lprops->flags & LPROPS_TAKEN) { if (cat != LPROPS_UNCAT) { - dbg_err("LEB %d taken but not uncat %d", - lprops->lnum, cat); + ubifs_err("LEB %d taken but not uncat %d", + lprops->lnum, cat); return -EINVAL; } continue; @@ -2130,8 +2129,8 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, case LPROPS_FRDI_IDX: break; default: - dbg_err("LEB %d index but cat %d", - lprops->lnum, cat); + ubifs_err("LEB %d index but cat %d", + lprops->lnum, cat); return -EINVAL; } } else { @@ -2143,8 +2142,8 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, case LPROPS_FREEABLE: break; default: - dbg_err("LEB %d not index but cat %d", - lprops->lnum, cat); + ubifs_err("LEB %d not index but cat %d", + lprops->lnum, cat); return -EINVAL; } } @@ -2184,24 +2183,24 @@ static int dbg_chk_pnode(struct ubifs_info *c, struct ubifs_pnode *pnode, break; } if (!found) { - dbg_err("LEB %d cat %d not found in cat heap/list", - lprops->lnum, cat); + ubifs_err("LEB %d cat %d not found in cat heap/list", + lprops->lnum, cat); return -EINVAL; } switch (cat) { case LPROPS_EMPTY: if (lprops->free != c->leb_size) { - dbg_err("LEB %d cat %d free %d dirty %d", - lprops->lnum, cat, lprops->free, - lprops->dirty); + ubifs_err("LEB %d cat %d free %d dirty %d", + lprops->lnum, cat, lprops->free, + lprops->dirty); return -EINVAL; } case LPROPS_FREEABLE: case LPROPS_FRDI_IDX: if (lprops->free + lprops->dirty != c->leb_size) { - dbg_err("LEB %d cat %d free %d dirty %d", - lprops->lnum, cat, lprops->free, - lprops->dirty); + ubifs_err("LEB %d cat %d free %d dirty %d", + lprops->lnum, cat, lprops->free, + lprops->dirty); return -EINVAL; } } @@ -2235,9 +2234,10 @@ int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, /* cnode is a nnode */ num = calc_nnode_num(row, col); if (cnode->num != num) { - dbg_err("nnode num %d expected %d " - "parent num %d iip %d", cnode->num, num, - (nnode ? nnode->num : 0), cnode->iip); + ubifs_err("nnode num %d expected %d " + "parent num %d iip %d", + cnode->num, num, + (nnode ? nnode->num : 0), cnode->iip); return -EINVAL; } nn = (struct ubifs_nnode *)cnode; @@ -2274,5 +2274,3 @@ int dbg_check_lpt_nodes(struct ubifs_info *c, struct ubifs_cnode *cnode, } return 0; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index cddd6bd214f..4fa70734e6e 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -30,11 +30,7 @@ #include <linux/random.h> #include "ubifs.h" -#ifdef CONFIG_UBIFS_FS_DEBUG static int dbg_populate_lsave(struct ubifs_info *c); -#else -#define dbg_populate_lsave(c) 0 -#endif /** * first_dirty_cnode - find first dirty cnode. @@ -324,11 +320,10 @@ static int layout_cnodes(struct ubifs_info *c) return 0; no_space: - ubifs_err("LPT out of space"); - dbg_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, " - "done_lsave %d", lnum, offs, len, done_ltab, done_lsave); - dbg_dump_lpt_info(c); - dbg_dump_lpt_lebs(c); + ubifs_err("LPT out of space at LEB %d:%d needing %d, done_ltab %d, " + "done_lsave %d", lnum, offs, len, done_ltab, done_lsave); + ubifs_dump_lpt_info(c); + ubifs_dump_lpt_lebs(c); dump_stack(); return err; } @@ -421,7 +416,7 @@ static int write_cnodes(struct ubifs_info *c) alen = ALIGN(wlen, c->min_io_size); memset(buf + offs, 0xff, alen - wlen); err = ubifs_leb_write(c, lnum, buf + from, from, - alen, UBI_SHORTTERM); + alen); if (err) return err; } @@ -479,8 +474,7 @@ static int write_cnodes(struct ubifs_info *c) wlen = offs - from; alen = ALIGN(wlen, c->min_io_size); memset(buf + offs, 0xff, alen - wlen); - err = ubifs_leb_write(c, lnum, buf + from, from, alen, - UBI_SHORTTERM); + err = ubifs_leb_write(c, lnum, buf + from, from, alen); if (err) return err; dbg_chk_lpt_sz(c, 2, c->leb_size - offs); @@ -506,8 +500,7 @@ static int write_cnodes(struct ubifs_info *c) wlen = offs - from; alen = ALIGN(wlen, c->min_io_size); memset(buf + offs, 0xff, alen - wlen); - err = ubifs_leb_write(c, lnum, buf + from, from, alen, - UBI_SHORTTERM); + err = ubifs_leb_write(c, lnum, buf + from, from, alen); if (err) return err; dbg_chk_lpt_sz(c, 2, c->leb_size - offs); @@ -531,7 +524,7 @@ static int write_cnodes(struct ubifs_info *c) wlen = offs - from; alen = ALIGN(wlen, c->min_io_size); memset(buf + offs, 0xff, alen - wlen); - err = ubifs_leb_write(c, lnum, buf + from, from, alen, UBI_SHORTTERM); + err = ubifs_leb_write(c, lnum, buf + from, from, alen); if (err) return err; @@ -552,11 +545,10 @@ static int write_cnodes(struct ubifs_info *c) return 0; no_space: - ubifs_err("LPT out of space mismatch"); - dbg_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab " - "%d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave); - dbg_dump_lpt_info(c); - dbg_dump_lpt_lebs(c); + ubifs_err("LPT out of space mismatch at LEB %d:%d needing %d, done_ltab " + "%d, done_lsave %d", lnum, offs, len, done_ltab, done_lsave); + ubifs_dump_lpt_info(c); + ubifs_dump_lpt_lebs(c); dump_stack(); return err; } @@ -1497,7 +1489,9 @@ void ubifs_lpt_free(struct ubifs_info *c, int wr_only) kfree(c->lpt_nod_buf); } -#ifdef CONFIG_UBIFS_FS_DEBUG +/* + * Everything below is related to debugging. + */ /** * dbg_is_all_ff - determine if a buffer contains only 0xFF bytes. @@ -1735,7 +1729,7 @@ int dbg_check_ltab(struct ubifs_info *c) for (lnum = c->lpt_first; lnum <= c->lpt_last; lnum++) { err = dbg_check_ltab_lnum(c, lnum); if (err) { - dbg_err("failed at LEB %d", lnum); + ubifs_err("failed at LEB %d", lnum); return err; } } @@ -1767,10 +1761,10 @@ int dbg_chk_lpt_free_spc(struct ubifs_info *c) free += c->leb_size; } if (free < c->lpt_sz) { - dbg_err("LPT space error: free %lld lpt_sz %lld", - free, c->lpt_sz); - dbg_dump_lpt_info(c); - dbg_dump_lpt_lebs(c); + ubifs_err("LPT space error: free %lld lpt_sz %lld", + free, c->lpt_sz); + ubifs_dump_lpt_info(c); + ubifs_dump_lpt_lebs(c); dump_stack(); return -EINVAL; } @@ -1807,13 +1801,13 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) d->chk_lpt_lebs = 0; d->chk_lpt_wastage = 0; if (c->dirty_pn_cnt > c->pnode_cnt) { - dbg_err("dirty pnodes %d exceed max %d", - c->dirty_pn_cnt, c->pnode_cnt); + ubifs_err("dirty pnodes %d exceed max %d", + c->dirty_pn_cnt, c->pnode_cnt); err = -EINVAL; } if (c->dirty_nn_cnt > c->nnode_cnt) { - dbg_err("dirty nnodes %d exceed max %d", - c->dirty_nn_cnt, c->nnode_cnt); + ubifs_err("dirty nnodes %d exceed max %d", + c->dirty_nn_cnt, c->nnode_cnt); err = -EINVAL; } return err; @@ -1830,23 +1824,23 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) chk_lpt_sz *= d->chk_lpt_lebs; chk_lpt_sz += len - c->nhead_offs; if (d->chk_lpt_sz != chk_lpt_sz) { - dbg_err("LPT wrote %lld but space used was %lld", - d->chk_lpt_sz, chk_lpt_sz); + ubifs_err("LPT wrote %lld but space used was %lld", + d->chk_lpt_sz, chk_lpt_sz); err = -EINVAL; } if (d->chk_lpt_sz > c->lpt_sz) { - dbg_err("LPT wrote %lld but lpt_sz is %lld", - d->chk_lpt_sz, c->lpt_sz); + ubifs_err("LPT wrote %lld but lpt_sz is %lld", + d->chk_lpt_sz, c->lpt_sz); err = -EINVAL; } if (d->chk_lpt_sz2 && d->chk_lpt_sz != d->chk_lpt_sz2) { - dbg_err("LPT layout size %lld but wrote %lld", - d->chk_lpt_sz, d->chk_lpt_sz2); + ubifs_err("LPT layout size %lld but wrote %lld", + d->chk_lpt_sz, d->chk_lpt_sz2); err = -EINVAL; } if (d->chk_lpt_sz2 && d->new_nhead_offs != len) { - dbg_err("LPT new nhead offs: expected %d was %d", - d->new_nhead_offs, len); + ubifs_err("LPT new nhead offs: expected %d was %d", + d->new_nhead_offs, len); err = -EINVAL; } lpt_sz = (long long)c->pnode_cnt * c->pnode_sz; @@ -1855,13 +1849,13 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) if (c->big_lpt) lpt_sz += c->lsave_sz; if (d->chk_lpt_sz - d->chk_lpt_wastage > lpt_sz) { - dbg_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld", - d->chk_lpt_sz, d->chk_lpt_wastage, lpt_sz); + ubifs_err("LPT chk_lpt_sz %lld + waste %lld exceeds %lld", + d->chk_lpt_sz, d->chk_lpt_wastage, lpt_sz); err = -EINVAL; } if (err) { - dbg_dump_lpt_info(c); - dbg_dump_lpt_lebs(c); + ubifs_dump_lpt_info(c); + ubifs_dump_lpt_lebs(c); dump_stack(); } d->chk_lpt_sz2 = d->chk_lpt_sz; @@ -1880,7 +1874,7 @@ int dbg_chk_lpt_sz(struct ubifs_info *c, int action, int len) } /** - * dbg_dump_lpt_leb - dump an LPT LEB. + * ubifs_dump_lpt_leb - dump an LPT LEB. * @c: UBIFS file-system description object * @lnum: LEB number to dump * @@ -1986,13 +1980,13 @@ out: } /** - * dbg_dump_lpt_lebs - dump LPT lebs. + * ubifs_dump_lpt_lebs - dump LPT lebs. * @c: UBIFS file-system description object * * This function dumps all LPT LEBs. The caller has to make sure the LPT is * locked. */ -void dbg_dump_lpt_lebs(const struct ubifs_info *c) +void ubifs_dump_lpt_lebs(const struct ubifs_info *c) { int i; @@ -2046,5 +2040,3 @@ static int dbg_populate_lsave(struct ubifs_info *c) return 1; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index 278c2382e8c..ab83ace9910 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -241,7 +241,7 @@ static int validate_master(const struct ubifs_info *c) out: ubifs_err("bad master node at offset %d error %d", c->mst_offs, err); - dbg_dump_node(c, c->mst_node); + ubifs_dump_node(c, c->mst_node); return -EINVAL; } @@ -317,7 +317,7 @@ int ubifs_read_master(struct ubifs_info *c) if (c->leb_cnt < old_leb_cnt || c->leb_cnt < UBIFS_MIN_LEB_CNT) { ubifs_err("bad leb_cnt on master node"); - dbg_dump_node(c, c->mst_node); + ubifs_dump_node(c, c->mst_node); return -EINVAL; } @@ -379,7 +379,7 @@ int ubifs_write_master(struct ubifs_info *c) c->mst_offs = offs; c->mst_node->highest_inum = cpu_to_le64(c->highest_inum); - err = ubifs_write_node(c, c->mst_node, len, lnum, offs, UBI_SHORTTERM); + err = ubifs_write_node(c, c->mst_node, len, lnum, offs); if (err) return err; @@ -390,7 +390,7 @@ int ubifs_write_master(struct ubifs_info *c) if (err) return err; } - err = ubifs_write_node(c, c->mst_node, len, lnum, offs, UBI_SHORTTERM); + err = ubifs_write_node(c, c->mst_node, len, lnum, offs); return err; } diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index c542c73cfa3..b02734db187 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -52,11 +52,7 @@ * than the maximum number of orphans allowed. */ -#ifdef CONFIG_UBIFS_FS_DEBUG static int dbg_check_orphans(struct ubifs_info *c); -#else -#define dbg_check_orphans(c) 0 -#endif /** * ubifs_add_orphan - add an orphan. @@ -92,7 +88,7 @@ int ubifs_add_orphan(struct ubifs_info *c, ino_t inum) else if (inum > o->inum) p = &(*p)->rb_right; else { - dbg_err("orphaned twice"); + ubifs_err("orphaned twice"); spin_unlock(&c->orphan_lock); kfree(orphan); return 0; @@ -158,8 +154,8 @@ void ubifs_delete_orphan(struct ubifs_info *c, ino_t inum) } } spin_unlock(&c->orphan_lock); - dbg_err("missing orphan ino %lu", (unsigned long)inum); - dbg_dump_stack(); + ubifs_err("missing orphan ino %lu", (unsigned long)inum); + dump_stack(); } /** @@ -248,8 +244,7 @@ static int do_write_orph_node(struct ubifs_info *c, int len, int atomic) ubifs_assert(c->ohead_offs == 0); ubifs_prepare_node(c, c->orph_buf, len, 1); len = ALIGN(len, c->min_io_size); - err = ubifs_leb_change(c, c->ohead_lnum, c->orph_buf, len, - UBI_SHORTTERM); + err = ubifs_leb_change(c, c->ohead_lnum, c->orph_buf, len); } else { if (c->ohead_offs == 0) { /* Ensure LEB has been unmapped */ @@ -258,7 +253,7 @@ static int do_write_orph_node(struct ubifs_info *c, int len, int atomic) return err; } err = ubifs_write_node(c, c->orph_buf, len, c->ohead_lnum, - c->ohead_offs, UBI_SHORTTERM); + c->ohead_offs); } return err; } @@ -569,7 +564,7 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, if (snod->type != UBIFS_ORPH_NODE) { ubifs_err("invalid node type %d in orphan area at " "%d:%d", snod->type, sleb->lnum, snod->offs); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); return -EINVAL; } @@ -597,7 +592,7 @@ static int do_kill_orphans(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ubifs_err("out of order commit number %llu in " "orphan node at %d:%d", cmt_no, sleb->lnum, snod->offs); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); return -EINVAL; } dbg_rcvry("out of date LEB %d", sleb->lnum); @@ -725,7 +720,9 @@ int ubifs_mount_orphans(struct ubifs_info *c, int unclean, int read_only) return err; } -#ifdef CONFIG_UBIFS_FS_DEBUG +/* + * Everything below is related to debugging. + */ struct check_orphan { struct rb_node rb; @@ -968,5 +965,3 @@ out: kfree(ci.node); return err; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 2a935b31723..c30d976b4be 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -213,10 +213,10 @@ static int write_rcvrd_mst_node(struct ubifs_info *c, mst->flags |= cpu_to_le32(UBIFS_MST_RCVRY); ubifs_prepare_node(c, mst, UBIFS_MST_NODE_SZ, 1); - err = ubifs_leb_change(c, lnum, mst, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum, mst, sz); if (err) goto out; - err = ubifs_leb_change(c, lnum + 1, mst, sz, UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum + 1, mst, sz); if (err) goto out; out: @@ -362,12 +362,12 @@ out_err: out_free: ubifs_err("failed to recover master node"); if (mst1) { - dbg_err("dumping first master node"); - dbg_dump_node(c, mst1); + ubifs_err("dumping first master node"); + ubifs_dump_node(c, mst1); } if (mst2) { - dbg_err("dumping second master node"); - dbg_dump_node(c, mst2); + ubifs_err("dumping second master node"); + ubifs_dump_node(c, mst2); } vfree(buf2); vfree(buf1); @@ -555,8 +555,7 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb, ubifs_pad(c, buf, pad_len); } } - err = ubifs_leb_change(c, lnum, sleb->buf, len, - UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, sleb->buf, len); if (err) return err; } @@ -683,7 +682,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, ret, lnum, offs); break; } else { - dbg_err("unexpected return value %d", ret); + ubifs_err("unexpected return value %d", ret); err = -EINVAL; goto error; } @@ -789,7 +788,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ - dbg_err("corruptio %d", ret); + ubifs_err("corruptio %d", ret); ubifs_scan_a_node(c, buf, len, lnum, offs, 1); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); @@ -827,17 +826,17 @@ static int get_cs_sqnum(struct ubifs_info *c, int lnum, int offs, goto out_free; ret = ubifs_scan_a_node(c, cs_node, UBIFS_CS_NODE_SZ, lnum, offs, 0); if (ret != SCANNED_A_NODE) { - dbg_err("Not a valid node"); + ubifs_err("Not a valid node"); goto out_err; } if (cs_node->ch.node_type != UBIFS_CS_NODE) { - dbg_err("Node a CS node, type is %d", cs_node->ch.node_type); + ubifs_err("Node a CS node, type is %d", cs_node->ch.node_type); goto out_err; } if (le64_to_cpu(cs_node->cmt_no) != c->cmt_no) { - dbg_err("CS node cmt_no %llu != current cmt_no %llu", - (unsigned long long)le64_to_cpu(cs_node->cmt_no), - c->cmt_no); + ubifs_err("CS node cmt_no %llu != current cmt_no %llu", + (unsigned long long)le64_to_cpu(cs_node->cmt_no), + c->cmt_no); goto out_err; } *cs_sqnum = le64_to_cpu(cs_node->ch.sqnum); @@ -941,7 +940,7 @@ static int recover_head(struct ubifs_info *c, int lnum, int offs, void *sbuf) err = ubifs_leb_read(c, lnum, sbuf, 0, offs, 1); if (err) return err; - return ubifs_leb_change(c, lnum, sbuf, offs, UBI_UNKNOWN); + return ubifs_leb_change(c, lnum, sbuf, offs); } return 0; @@ -1071,7 +1070,7 @@ static int clean_an_unclean_leb(struct ubifs_info *c, } /* Write back the LEB atomically */ - err = ubifs_leb_change(c, lnum, sbuf, len, UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, sbuf, len); if (err) return err; @@ -1138,9 +1137,9 @@ static int grab_empty_leb(struct ubifs_info *c) */ lnum = ubifs_find_free_leb_for_idx(c); if (lnum < 0) { - dbg_err("could not find an empty LEB"); - dbg_dump_lprops(c); - dbg_dump_budg(c, &c->bi); + ubifs_err("could not find an empty LEB"); + ubifs_dump_lprops(c); + ubifs_dump_budg(c, &c->bi); return lnum; } @@ -1218,7 +1217,7 @@ int ubifs_rcvry_gc_commit(struct ubifs_info *c) } mutex_unlock(&wbuf->io_mutex); if (err < 0) { - dbg_err("GC failed, error %d", err); + ubifs_err("GC failed, error %d", err); if (err == -EAGAIN) err = -EINVAL; return err; @@ -1472,7 +1471,7 @@ static int fix_size_in_place(struct ubifs_info *c, struct size_entry *e) len -= 1; len = ALIGN(len + 1, c->min_io_size); /* Atomically write the fixed LEB back again */ - err = ubifs_leb_change(c, lnum, c->sbuf, len, UBI_UNKNOWN); + err = ubifs_leb_change(c, lnum, c->sbuf, len); if (err) goto out; dbg_rcvry("inode %lu at %d:%d size %lld -> %lld", diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index b007637f040..3a2da7e476e 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -154,8 +154,7 @@ static int set_bud_lprops(struct ubifs_info *c, struct bud_entry *b) /* Make sure the journal head points to the latest bud */ err = ubifs_wbuf_seek_nolock(&c->jheads[b->bud->jhead].wbuf, - b->bud->lnum, c->leb_size - b->free, - UBI_SHORTTERM); + b->bud->lnum, c->leb_size - b->free); out: ubifs_release_lprops(c); @@ -686,7 +685,7 @@ out: out_dump: ubifs_err("bad node is at LEB %d:%d", lnum, snod->offs); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); ubifs_scan_destroy(sleb); return -EINVAL; } @@ -861,16 +860,16 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) * numbers. */ if (snod->type != UBIFS_CS_NODE) { - dbg_err("first log node at LEB %d:%d is not CS node", - lnum, offs); + ubifs_err("first log node at LEB %d:%d is not CS node", + lnum, offs); goto out_dump; } if (le64_to_cpu(node->cmt_no) != c->cmt_no) { - dbg_err("first CS node at LEB %d:%d has wrong " - "commit number %llu expected %llu", - lnum, offs, - (unsigned long long)le64_to_cpu(node->cmt_no), - c->cmt_no); + ubifs_err("first CS node at LEB %d:%d has wrong " + "commit number %llu expected %llu", + lnum, offs, + (unsigned long long)le64_to_cpu(node->cmt_no), + c->cmt_no); goto out_dump; } @@ -892,7 +891,7 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) /* Make sure the first node sits at offset zero of the LEB */ if (snod->offs != 0) { - dbg_err("first node is not at zero offset"); + ubifs_err("first node is not at zero offset"); goto out_dump; } @@ -905,8 +904,8 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) } if (snod->sqnum < c->cs_sqnum) { - dbg_err("bad sqnum %llu, commit sqnum %llu", - snod->sqnum, c->cs_sqnum); + ubifs_err("bad sqnum %llu, commit sqnum %llu", + snod->sqnum, c->cs_sqnum); goto out_dump; } @@ -958,7 +957,7 @@ out: out_dump: ubifs_err("log error detected while replaying the log at LEB %d:%d", lnum, offs + snod->offs); - dbg_dump_node(c, snod->node); + ubifs_dump_node(c, snod->node); ubifs_scan_destroy(sleb); return -EINVAL; } diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index 771f7fb6ce9..ef3d1ba6d99 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -130,7 +130,6 @@ static int create_default_filesystem(struct ubifs_info *c) * orphan node. */ orph_lebs = UBIFS_MIN_ORPH_LEBS; -#ifdef CONFIG_UBIFS_FS_DEBUG if (c->leb_cnt - min_leb_cnt > 1) /* * For debugging purposes it is better to have at least 2 @@ -138,7 +137,6 @@ static int create_default_filesystem(struct ubifs_info *c) * consolidations and would be stressed more. */ orph_lebs += 1; -#endif main_lebs = c->leb_cnt - UBIFS_SB_LEBS - UBIFS_MST_LEBS - log_lebs; main_lebs -= orph_lebs; @@ -196,7 +194,7 @@ static int create_default_filesystem(struct ubifs_info *c) sup->rp_size = cpu_to_le64(tmp64); sup->ro_compat_version = cpu_to_le32(UBIFS_RO_COMPAT_VERSION); - err = ubifs_write_node(c, sup, UBIFS_SB_NODE_SZ, 0, 0, UBI_LONGTERM); + err = ubifs_write_node(c, sup, UBIFS_SB_NODE_SZ, 0, 0); kfree(sup); if (err) return err; @@ -252,14 +250,13 @@ static int create_default_filesystem(struct ubifs_info *c) mst->total_used = cpu_to_le64(UBIFS_INO_NODE_SZ); - err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM, 0, - UBI_UNKNOWN); + err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM, 0); if (err) { kfree(mst); return err; } - err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM + 1, 0, - UBI_UNKNOWN); + err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM + 1, + 0); kfree(mst); if (err) return err; @@ -282,8 +279,7 @@ static int create_default_filesystem(struct ubifs_info *c) key_write_idx(c, &key, &br->key); br->lnum = cpu_to_le32(main_first + DEFAULT_DATA_LEB); br->len = cpu_to_le32(UBIFS_INO_NODE_SZ); - err = ubifs_write_node(c, idx, tmp, main_first + DEFAULT_IDX_LEB, 0, - UBI_UNKNOWN); + err = ubifs_write_node(c, idx, tmp, main_first + DEFAULT_IDX_LEB, 0); kfree(idx); if (err) return err; @@ -315,8 +311,7 @@ static int create_default_filesystem(struct ubifs_info *c) ino->flags = cpu_to_le32(UBIFS_COMPR_FL); err = ubifs_write_node(c, ino, UBIFS_INO_NODE_SZ, - main_first + DEFAULT_DATA_LEB, 0, - UBI_UNKNOWN); + main_first + DEFAULT_DATA_LEB, 0); kfree(ino); if (err) return err; @@ -335,8 +330,7 @@ static int create_default_filesystem(struct ubifs_info *c) return -ENOMEM; cs->ch.node_type = UBIFS_CS_NODE; - err = ubifs_write_node(c, cs, UBIFS_CS_NODE_SZ, UBIFS_LOG_LNUM, - 0, UBI_UNKNOWN); + err = ubifs_write_node(c, cs, UBIFS_CS_NODE_SZ, UBIFS_LOG_LNUM, 0); kfree(cs); ubifs_msg("default file-system created"); @@ -475,7 +469,7 @@ static int validate_sb(struct ubifs_info *c, struct ubifs_sb_node *sup) failed: ubifs_err("bad superblock, error %d", err); - dbg_dump_node(c, sup); + ubifs_dump_node(c, sup); return -EINVAL; } @@ -518,7 +512,7 @@ int ubifs_write_sb_node(struct ubifs_info *c, struct ubifs_sb_node *sup) int len = ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size); ubifs_prepare_node(c, sup, UBIFS_SB_NODE_SZ, 1); - return ubifs_leb_change(c, UBIFS_SB_LNUM, sup, len, UBI_LONGTERM); + return ubifs_leb_change(c, UBIFS_SB_LNUM, sup, len); } /** @@ -691,7 +685,7 @@ static int fixup_leb(struct ubifs_info *c, int lnum, int len) if (err) return err; - return ubifs_leb_change(c, lnum, c->sbuf, len, UBI_UNKNOWN); + return ubifs_leb_change(c, lnum, c->sbuf, len); } /** diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index 37383e8011b..7c40e6025fd 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -101,7 +101,7 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum, if (!quiet) { ubifs_err("bad pad node at LEB %d:%d", lnum, offs); - dbg_dump_node(c, pad); + ubifs_dump_node(c, pad); } return SCANNED_A_BAD_PAD_NODE; } @@ -109,8 +109,8 @@ int ubifs_scan_a_node(const struct ubifs_info *c, void *buf, int len, int lnum, /* Make the node pads to 8-byte boundary */ if ((node_len + pad_len) & 7) { if (!quiet) - dbg_err("bad padding length %d - %d", - offs, offs + node_len + pad_len); + ubifs_err("bad padding length %d - %d", + offs, offs + node_len + pad_len); return SCANNED_A_BAD_PAD_NODE; } @@ -245,7 +245,7 @@ void ubifs_scanned_corruption(const struct ubifs_info *c, int lnum, int offs, len = c->leb_size - offs; if (len > 8192) len = 8192; - dbg_err("first %d bytes from LEB %d:%d", len, lnum, offs); + ubifs_err("first %d bytes from LEB %d:%d", len, lnum, offs); print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 32, 4, buf, len, 1); } @@ -300,16 +300,16 @@ struct ubifs_scan_leb *ubifs_scan(const struct ubifs_info *c, int lnum, switch (ret) { case SCANNED_GARBAGE: - dbg_err("garbage"); + ubifs_err("garbage"); goto corrupted; case SCANNED_A_NODE: break; case SCANNED_A_CORRUPT_NODE: case SCANNED_A_BAD_PAD_NODE: - dbg_err("bad node"); + ubifs_err("bad node"); goto corrupted; default: - dbg_err("unknown"); + ubifs_err("unknown"); err = -EINVAL; goto error; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 76e4e0566ad..5862dd9d278 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -246,8 +246,8 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum) out_invalid: ubifs_err("inode %lu validation failed, error %d", inode->i_ino, err); - dbg_dump_node(c, ino); - dbg_dump_inode(c, inode); + ubifs_dump_node(c, ino); + ubifs_dump_inode(c, inode); err = -EINVAL; out_ino: kfree(ino); @@ -378,7 +378,7 @@ out: smp_wmb(); } done: - end_writeback(inode); + clear_inode(inode); } static void ubifs_dirty_inode(struct inode *inode, int flags) @@ -668,8 +668,8 @@ static int init_constants_sb(struct ubifs_info *c) tmp = UBIFS_CS_NODE_SZ + UBIFS_REF_NODE_SZ * c->jhead_cnt; tmp = ALIGN(tmp, c->min_io_size); if (tmp > c->leb_size) { - dbg_err("too small LEB size %d, at least %d needed", - c->leb_size, tmp); + ubifs_err("too small LEB size %d, at least %d needed", + c->leb_size, tmp); return -EINVAL; } @@ -683,8 +683,8 @@ static int init_constants_sb(struct ubifs_info *c) tmp /= c->leb_size; tmp += 1; if (c->log_lebs < tmp) { - dbg_err("too small log %d LEBs, required min. %d LEBs", - c->log_lebs, tmp); + ubifs_err("too small log %d LEBs, required min. %d LEBs", + c->log_lebs, tmp); return -EINVAL; } @@ -813,13 +813,10 @@ static int alloc_wbufs(struct ubifs_info *c) c->jheads[i].grouped = 1; } - c->jheads[BASEHD].wbuf.dtype = UBI_SHORTTERM; /* - * Garbage Collector head likely contains long-term data and - * does not need to be synchronized by timer. Also GC head nodes are - * not grouped. + * Garbage Collector head does not need to be synchronized by timer. + * Also GC head nodes are not grouped. */ - c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM; c->jheads[GCHD].wbuf.no_timer = 1; c->jheads[GCHD].grouped = 0; @@ -863,7 +860,7 @@ static void free_orphans(struct ubifs_info *c) orph = list_entry(c->orph_list.next, struct ubifs_orphan, list); list_del(&orph->list); kfree(orph); - dbg_err("orphan list not empty at unmount"); + ubifs_err("orphan list not empty at unmount"); } vfree(c->orph_buf); @@ -1147,8 +1144,8 @@ static int check_free_space(struct ubifs_info *c) ubifs_assert(c->dark_wm > 0); if (c->lst.total_free + c->lst.total_dirty < c->dark_wm) { ubifs_err("insufficient free space to mount in R/W mode"); - dbg_dump_budg(c, &c->bi); - dbg_dump_lprops(c); + ubifs_dump_budg(c, &c->bi); + ubifs_dump_lprops(c); return -ENOSPC; } return 0; @@ -1301,7 +1298,7 @@ static int mount_ubifs(struct ubifs_info *c) if (!c->ro_mount && c->space_fixup) { err = ubifs_fixup_free_space(c); if (err) - goto out_master; + goto out_lpt; } if (!c->ro_mount) { @@ -2126,8 +2123,8 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags, */ ubi = open_ubi(name, UBI_READONLY); if (IS_ERR(ubi)) { - dbg_err("cannot open \"%s\", error %d", - name, (int)PTR_ERR(ubi)); + ubifs_err("cannot open \"%s\", error %d", + name, (int)PTR_ERR(ubi)); return ERR_CAST(ubi); } diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index 16ad84d8402..349f31a30f4 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -339,8 +339,8 @@ static int lnc_add(struct ubifs_info *c, struct ubifs_zbranch *zbr, err = ubifs_validate_entry(c, dent); if (err) { - dbg_dump_stack(); - dbg_dump_node(c, dent); + dump_stack(); + ubifs_dump_node(c, dent); return err; } @@ -372,8 +372,8 @@ static int lnc_add_directly(struct ubifs_info *c, struct ubifs_zbranch *zbr, err = ubifs_validate_entry(c, node); if (err) { - dbg_dump_stack(); - dbg_dump_node(c, node); + dump_stack(); + ubifs_dump_node(c, node); return err; } @@ -1733,8 +1733,8 @@ out_err: err = -EINVAL; out: ubifs_err("bad node at LEB %d:%d", zbr->lnum, zbr->offs); - dbg_dump_node(c, buf); - dbg_dump_stack(); + ubifs_dump_node(c, buf); + dump_stack(); return err; } @@ -1775,7 +1775,7 @@ int ubifs_tnc_bulk_read(struct ubifs_info *c, struct bu_info *bu) if (err && err != -EBADMSG) { ubifs_err("failed to read from LEB %d:%d, error %d", lnum, offs, err); - dbg_dump_stack(); + dump_stack(); dbg_tnck(&bu->key, "key "); return err; } @@ -2361,7 +2361,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, * by passing 'ubifs_tnc_remove_nm()' the same key but * an unmatchable name. */ - struct qstr noname = { .len = 0, .name = "" }; + struct qstr noname = { .name = "" }; err = dbg_check_tnc(c, 0); mutex_unlock(&c->tnc_mutex); @@ -2403,7 +2403,7 @@ static int tnc_delete(struct ubifs_info *c, struct ubifs_znode *znode, int n) err = ubifs_add_dirt(c, zbr->lnum, zbr->len); if (err) { - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); return err; } @@ -2649,7 +2649,7 @@ int ubifs_tnc_remove_range(struct ubifs_info *c, union ubifs_key *from_key, err = ubifs_add_dirt(c, znode->zbranch[i].lnum, znode->zbranch[i].len); if (err) { - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); goto out_unlock; } dbg_tnck(key, "removing key "); @@ -3275,8 +3275,6 @@ out_unlock: return err; } -#ifdef CONFIG_UBIFS_FS_DEBUG - /** * dbg_check_inode_size - check if inode size is correct. * @c: UBIFS file-system description object @@ -3335,13 +3333,11 @@ out_dump: (unsigned long)inode->i_ino, size, ((loff_t)block) << UBIFS_BLOCK_SHIFT); mutex_unlock(&c->tnc_mutex); - dbg_dump_inode(c, inode); - dbg_dump_stack(); + ubifs_dump_inode(c, inode); + dump_stack(); return -EINVAL; out_unlock: mutex_unlock(&c->tnc_mutex); return err; } - -#endif /* CONFIG_UBIFS_FS_DEBUG */ diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index 4c15f07a8bb..523bbad69c0 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -54,18 +54,16 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, br->len = cpu_to_le32(zbr->len); if (!zbr->lnum || !zbr->len) { ubifs_err("bad ref in znode"); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); if (zbr->znode) - dbg_dump_znode(c, zbr->znode); + ubifs_dump_znode(c, zbr->znode); } } ubifs_prepare_node(c, idx, len, 0); -#ifdef CONFIG_UBIFS_FS_DEBUG znode->lnum = lnum; znode->offs = offs; znode->len = len; -#endif err = insert_old_idx_znode(c, znode); @@ -322,8 +320,7 @@ static int layout_leb_in_gaps(struct ubifs_info *c, int *p) 0, 0, 0); if (err) return err; - err = ubifs_leb_change(c, lnum, c->ileb_buf, c->ileb_len, - UBI_SHORTTERM); + err = ubifs_leb_change(c, lnum, c->ileb_buf, c->ileb_len); if (err) return err; dbg_gc("LEB %d wrote %d index nodes", lnum, tot_written); @@ -388,8 +385,8 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) * option which forces in-the-gaps is enabled. */ ubifs_warn("out of space"); - dbg_dump_budg(c, &c->bi); - dbg_dump_lprops(c); + ubifs_dump_budg(c, &c->bi); + ubifs_dump_lprops(c); } /* Try to commit anyway */ err = 0; @@ -456,11 +453,9 @@ static int layout_in_empty_space(struct ubifs_info *c) offs = buf_offs + used; -#ifdef CONFIG_UBIFS_FS_DEBUG znode->lnum = lnum; znode->offs = offs; znode->len = len; -#endif /* Update the parent */ zp = znode->parent; @@ -536,10 +531,8 @@ static int layout_in_empty_space(struct ubifs_info *c) break; } -#ifdef CONFIG_UBIFS_FS_DEBUG c->dbg->new_ihead_lnum = lnum; c->dbg->new_ihead_offs = buf_offs; -#endif return 0; } @@ -864,9 +857,9 @@ static int write_index(struct ubifs_info *c) br->len = cpu_to_le32(zbr->len); if (!zbr->lnum || !zbr->len) { ubifs_err("bad ref in znode"); - dbg_dump_znode(c, znode); + ubifs_dump_znode(c, znode); if (zbr->znode) - dbg_dump_znode(c, zbr->znode); + ubifs_dump_znode(c, zbr->znode); } } len = ubifs_idx_node_sz(c, znode->child_cnt); @@ -881,13 +874,11 @@ static int write_index(struct ubifs_info *c) } offs = buf_offs + used; -#ifdef CONFIG_UBIFS_FS_DEBUG if (lnum != znode->lnum || offs != znode->offs || len != znode->len) { ubifs_err("inconsistent znode posn"); return -EINVAL; } -#endif /* Grab some stuff from znode while we still can */ cnext = znode->cnext; @@ -959,8 +950,7 @@ static int write_index(struct ubifs_info *c) } /* The buffer is full or there are no more znodes to do */ - err = ubifs_leb_write(c, lnum, c->cbuf, buf_offs, blen, - UBI_SHORTTERM); + err = ubifs_leb_write(c, lnum, c->cbuf, buf_offs, blen); if (err) return err; buf_offs += blen; @@ -982,13 +972,11 @@ static int write_index(struct ubifs_info *c) break; } -#ifdef CONFIG_UBIFS_FS_DEBUG if (lnum != c->dbg->new_ihead_lnum || buf_offs != c->dbg->new_ihead_offs) { ubifs_err("inconsistent ihead"); return -EINVAL; } -#endif c->ihead_lnum = lnum; c->ihead_offs = buf_offs; diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index dc28fe6ec07..d38ac7f9654 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -293,10 +293,10 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, lnum, offs, znode->level, znode->child_cnt); if (znode->child_cnt > c->fanout || znode->level > UBIFS_MAX_LEVELS) { - dbg_err("current fanout %d, branch count %d", - c->fanout, znode->child_cnt); - dbg_err("max levels %d, znode level %d", - UBIFS_MAX_LEVELS, znode->level); + ubifs_err("current fanout %d, branch count %d", + c->fanout, znode->child_cnt); + ubifs_err("max levels %d, znode level %d", + UBIFS_MAX_LEVELS, znode->level); err = 1; goto out_dump; } @@ -316,7 +316,7 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, if (zbr->lnum < c->main_first || zbr->lnum >= c->leb_cnt || zbr->offs < 0 || zbr->offs + zbr->len > c->leb_size || zbr->offs & 7) { - dbg_err("bad branch %d", i); + ubifs_err("bad branch %d", i); err = 2; goto out_dump; } @@ -340,19 +340,19 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, type = key_type(c, &zbr->key); if (c->ranges[type].max_len == 0) { if (zbr->len != c->ranges[type].len) { - dbg_err("bad target node (type %d) length (%d)", - type, zbr->len); - dbg_err("have to be %d", c->ranges[type].len); + ubifs_err("bad target node (type %d) length (%d)", + type, zbr->len); + ubifs_err("have to be %d", c->ranges[type].len); err = 4; goto out_dump; } } else if (zbr->len < c->ranges[type].min_len || zbr->len > c->ranges[type].max_len) { - dbg_err("bad target node (type %d) length (%d)", - type, zbr->len); - dbg_err("have to be in range of %d-%d", - c->ranges[type].min_len, - c->ranges[type].max_len); + ubifs_err("bad target node (type %d) length (%d)", + type, zbr->len); + ubifs_err("have to be in range of %d-%d", + c->ranges[type].min_len, + c->ranges[type].max_len); err = 5; goto out_dump; } @@ -370,13 +370,13 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, cmp = keys_cmp(c, key1, key2); if (cmp > 0) { - dbg_err("bad key order (keys %d and %d)", i, i + 1); + ubifs_err("bad key order (keys %d and %d)", i, i + 1); err = 6; goto out_dump; } else if (cmp == 0 && !is_hash_key(c, key1)) { /* These can only be keys with colliding hash */ - dbg_err("keys %d and %d are not hashed but equivalent", - i, i + 1); + ubifs_err("keys %d and %d are not hashed but equivalent", + i, i + 1); err = 7; goto out_dump; } @@ -387,7 +387,7 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, out_dump: ubifs_err("bad indexing node at LEB %d:%d, error %d", lnum, offs, err); - dbg_dump_node(c, idx); + ubifs_dump_node(c, idx); kfree(idx); return -EINVAL; } @@ -486,7 +486,7 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, zbr->lnum, zbr->offs); dbg_tnck(key, "looked for key "); dbg_tnck(&key1, "but found node's key "); - dbg_dump_node(c, node); + ubifs_dump_node(c, node); return -EINVAL; } diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 93d59aceaae..1e5a08623d1 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -650,8 +650,6 @@ typedef int (*ubifs_lpt_scan_callback)(struct ubifs_info *c, * @avail: number of bytes available in the write-buffer * @used: number of used bytes in the write-buffer * @size: write-buffer size (in [@c->min_io_size, @c->max_write_size] range) - * @dtype: type of data stored in this LEB (%UBI_LONGTERM, %UBI_SHORTTERM, - * %UBI_UNKNOWN) * @jhead: journal head the mutex belongs to (note, needed only to shut lockdep * up by 'mutex_lock_nested()). * @sync_callback: write-buffer synchronization callback @@ -685,7 +683,6 @@ struct ubifs_wbuf { int avail; int used; int size; - int dtype; int jhead; int (*sync_callback)(struct ubifs_info *c, int lnum, int free, int pad); struct mutex io_mutex; @@ -762,6 +759,9 @@ struct ubifs_zbranch { * @offs: offset of the corresponding indexing node * @len: length of the corresponding indexing node * @zbranch: array of znode branches (@c->fanout elements) + * + * Note! The @lnum, @offs, and @len fields are not really needed - we have them + * only for internal consistency check. They could be removed to save some RAM. */ struct ubifs_znode { struct ubifs_znode *parent; @@ -772,9 +772,9 @@ struct ubifs_znode { int child_cnt; int iip; int alt; -#ifdef CONFIG_UBIFS_FS_DEBUG - int lnum, offs, len; -#endif + int lnum; + int offs; + int len; struct ubifs_zbranch zbranch[]; }; @@ -1444,9 +1444,7 @@ struct ubifs_info { struct rb_root size_tree; struct ubifs_mount_opts mount_opts; -#ifdef CONFIG_UBIFS_FS_DEBUG struct ubifs_debug_info *dbg; -#endif }; extern struct list_head ubifs_infos; @@ -1468,22 +1466,20 @@ void ubifs_ro_mode(struct ubifs_info *c, int err); int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, int len, int even_ebadmsg); int ubifs_leb_write(struct ubifs_info *c, int lnum, const void *buf, int offs, - int len, int dtype); -int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len, - int dtype); + int len); +int ubifs_leb_change(struct ubifs_info *c, int lnum, const void *buf, int len); int ubifs_leb_unmap(struct ubifs_info *c, int lnum); -int ubifs_leb_map(struct ubifs_info *c, int lnum, int dtype); +int ubifs_leb_map(struct ubifs_info *c, int lnum); int ubifs_is_mapped(const struct ubifs_info *c, int lnum); int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len); -int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs, - int dtype); +int ubifs_wbuf_seek_nolock(struct ubifs_wbuf *wbuf, int lnum, int offs); int ubifs_wbuf_init(struct ubifs_info *c, struct ubifs_wbuf *wbuf); int ubifs_read_node(const struct ubifs_info *c, void *buf, int type, int len, int lnum, int offs); int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, int lnum, int offs); int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum, - int offs, int dtype); + int offs); int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, int offs, int quiet, int must_chk_crc); void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad); diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 85b27226875..0f7139bdb2c 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -298,7 +298,7 @@ int ubifs_setxattr(struct dentry *dentry, const char *name, { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; int err, type; @@ -361,7 +361,7 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_inode *ui; struct ubifs_dent_node *xent; union ubifs_key key; @@ -399,8 +399,8 @@ ssize_t ubifs_getxattr(struct dentry *dentry, const char *name, void *buf, if (buf) { /* If @buf is %NULL we are supposed to return the length */ if (ui->data_len > size) { - dbg_err("buffer size %zd, xattr len %d", - size, ui->data_len); + ubifs_err("buffer size %zd, xattr len %d", + size, ui->data_len); err = -ERANGE; goto out_iput; } @@ -524,7 +524,7 @@ int ubifs_removexattr(struct dentry *dentry, const char *name) { struct inode *inode, *host = dentry->d_inode; struct ubifs_info *c = host->i_sb->s_fs_info; - struct qstr nm = { .name = name, .len = strlen(name) }; + struct qstr nm = QSTR_INIT(name, strlen(name)); struct ubifs_dent_node *xent; union ubifs_key key; int err; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7d752800835..873e1bab9c4 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -80,7 +80,7 @@ void udf_evict_inode(struct inode *inode) } else truncate_inode_pages(&inode->i_data, 0); invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && inode->i_size != iinfo->i_lenExtents) { udf_warn(inode->i_sb, "Inode %lu (mode %o) has inode size %llu different from extent length %llu. Filesystem need not be standards compliant.\n", diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 38de8f234b9..18024178ac4 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -1193,7 +1193,7 @@ static struct dentry *udf_get_parent(struct dentry *child) { struct kernel_lb_addr tloc; struct inode *inode = NULL; - struct qstr dotdot = {.name = "..", .len = 2}; + struct qstr dotdot = QSTR_INIT("..", 2); struct fileIdentDesc cfi; struct udf_fileident_bh fibh; @@ -1260,16 +1260,15 @@ static struct dentry *udf_fh_to_parent(struct super_block *sb, fid->udf.parent_partref, fid->udf.parent_generation); } -static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp, - int connectable) +static int udf_encode_fh(struct inode *inode, __u32 *fh, int *lenp, + struct inode *parent) { int len = *lenp; - struct inode *inode = de->d_inode; struct kernel_lb_addr location = UDF_I(inode)->i_location; struct fid *fid = (struct fid *)fh; int type = FILEID_UDF_WITHOUT_PARENT; - if (connectable && (len < 5)) { + if (parent && (len < 5)) { *lenp = 5; return 255; } else if (len < 3) { @@ -1282,14 +1281,11 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp, fid->udf.partref = location.partitionReferenceNum; fid->udf.generation = inode->i_generation; - if (connectable && !S_ISDIR(inode->i_mode)) { - spin_lock(&de->d_lock); - inode = de->d_parent->d_inode; - location = UDF_I(inode)->i_location; + if (parent) { + location = UDF_I(parent)->i_location; fid->udf.parent_block = location.logicalBlockNum; fid->udf.parent_partref = location.partitionReferenceNum; fid->udf.parent_generation = inode->i_generation; - spin_unlock(&de->d_lock); *lenp = 5; type = FILEID_UDF_WITH_PARENT; } diff --git a/fs/udf/super.c b/fs/udf/super.c index ac8a348dcb6..8d86a8706c0 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -56,6 +56,7 @@ #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/crc-itu-t.h> +#include <linux/log2.h> #include <asm/byteorder.h> #include "udf_sb.h" @@ -1215,16 +1216,65 @@ out_bh: return ret; } +static int udf_load_sparable_map(struct super_block *sb, + struct udf_part_map *map, + struct sparablePartitionMap *spm) +{ + uint32_t loc; + uint16_t ident; + struct sparingTable *st; + struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing; + int i; + struct buffer_head *bh; + + map->s_partition_type = UDF_SPARABLE_MAP15; + sdata->s_packet_len = le16_to_cpu(spm->packetLength); + if (!is_power_of_2(sdata->s_packet_len)) { + udf_err(sb, "error loading logical volume descriptor: " + "Invalid packet length %u\n", + (unsigned)sdata->s_packet_len); + return -EIO; + } + if (spm->numSparingTables > 4) { + udf_err(sb, "error loading logical volume descriptor: " + "Too many sparing tables (%d)\n", + (int)spm->numSparingTables); + return -EIO; + } + + for (i = 0; i < spm->numSparingTables; i++) { + loc = le32_to_cpu(spm->locSparingTable[i]); + bh = udf_read_tagged(sb, loc, loc, &ident); + if (!bh) + continue; + + st = (struct sparingTable *)bh->b_data; + if (ident != 0 || + strncmp(st->sparingIdent.ident, UDF_ID_SPARING, + strlen(UDF_ID_SPARING)) || + sizeof(*st) + le16_to_cpu(st->reallocationTableLen) > + sb->s_blocksize) { + brelse(bh); + continue; + } + + sdata->s_spar_map[i] = bh; + } + map->s_partition_func = udf_get_pblock_spar15; + return 0; +} + static int udf_load_logicalvol(struct super_block *sb, sector_t block, struct kernel_lb_addr *fileset) { struct logicalVolDesc *lvd; - int i, j, offset; + int i, offset; uint8_t type; struct udf_sb_info *sbi = UDF_SB(sb); struct genericPartitionMap *gpm; uint16_t ident; struct buffer_head *bh; + unsigned int table_len; int ret = 0; bh = udf_read_tagged(sb, block, block, &ident); @@ -1232,15 +1282,20 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, return 1; BUG_ON(ident != TAG_IDENT_LVD); lvd = (struct logicalVolDesc *)bh->b_data; - - i = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); - if (i != 0) { - ret = i; + table_len = le32_to_cpu(lvd->mapTableLength); + if (sizeof(*lvd) + table_len > sb->s_blocksize) { + udf_err(sb, "error loading logical volume descriptor: " + "Partition table too long (%u > %lu)\n", table_len, + sb->s_blocksize - sizeof(*lvd)); goto out_bh; } + ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps)); + if (ret) + goto out_bh; + for (i = 0, offset = 0; - i < sbi->s_partitions && offset < le32_to_cpu(lvd->mapTableLength); + i < sbi->s_partitions && offset < table_len; i++, offset += gpm->partitionMapLength) { struct udf_part_map *map = &sbi->s_partmaps[i]; gpm = (struct genericPartitionMap *) @@ -1275,38 +1330,9 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, } else if (!strncmp(upm2->partIdent.ident, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { - uint32_t loc; - struct sparingTable *st; - struct sparablePartitionMap *spm = - (struct sparablePartitionMap *)gpm; - - map->s_partition_type = UDF_SPARABLE_MAP15; - map->s_type_specific.s_sparing.s_packet_len = - le16_to_cpu(spm->packetLength); - for (j = 0; j < spm->numSparingTables; j++) { - struct buffer_head *bh2; - - loc = le32_to_cpu( - spm->locSparingTable[j]); - bh2 = udf_read_tagged(sb, loc, loc, - &ident); - map->s_type_specific.s_sparing. - s_spar_map[j] = bh2; - - if (bh2 == NULL) - continue; - - st = (struct sparingTable *)bh2->b_data; - if (ident != 0 || strncmp( - st->sparingIdent.ident, - UDF_ID_SPARING, - strlen(UDF_ID_SPARING))) { - brelse(bh2); - map->s_type_specific.s_sparing. - s_spar_map[j] = NULL; - } - } - map->s_partition_func = udf_get_pblock_spar15; + if (udf_load_sparable_map(sb, map, + (struct sparablePartitionMap *)gpm) < 0) + goto out_bh; } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 7cdd3953d67..dd7c89d8a1c 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -895,7 +895,7 @@ void ufs_evict_inode(struct inode * inode) } invalidate_inode_buffers(inode); - end_writeback(inode); + clear_inode(inode); if (want_delete) { lock_ufs(inode->i_sb); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index ac8e279eccc..302f340d007 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -146,10 +146,7 @@ static struct dentry *ufs_fh_to_parent(struct super_block *sb, struct fid *fid, static struct dentry *ufs_get_parent(struct dentry *child) { - struct qstr dot_dot = { - .name = "..", - .len = 2, - }; + struct qstr dot_dot = QSTR_INIT("..", 2); ino_t ino; ino = ufs_inode_by_name(child->d_inode, &dot_dot); diff --git a/fs/utimes.c b/fs/utimes.c index ba653f3dc1b..fa4dbe451e2 100644 --- a/fs/utimes.c +++ b/fs/utimes.c @@ -140,18 +140,19 @@ long do_utimes(int dfd, const char __user *filename, struct timespec *times, goto out; if (filename == NULL && dfd != AT_FDCWD) { + int fput_needed; struct file *file; if (flags & AT_SYMLINK_NOFOLLOW) goto out; - file = fget(dfd); + file = fget_light(dfd, &fput_needed); error = -EBADF; if (!file) goto out; error = utimes_common(&file->f_path, times); - fput(file); + fput_light(file, fput_needed); } else { struct path path; int lookup_flags = 0; diff --git a/fs/xattr.c b/fs/xattr.c index 3c8c1cc333c..1d7ac379045 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -399,11 +399,12 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname, SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, const void __user *,value, size_t, size, int, flags) { + int fput_needed; struct file *f; struct dentry *dentry; int error = -EBADF; - f = fget(fd); + f = fget_light(fd, &fput_needed); if (!f) return error; dentry = f->f_path.dentry; @@ -413,7 +414,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, error = setxattr(dentry, name, value, size, flags); mnt_drop_write_file(f); } - fput(f); + fput_light(f, fput_needed); return error; } @@ -486,15 +487,16 @@ SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname, SYSCALL_DEFINE4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size) { + int fput_needed; struct file *f; ssize_t error = -EBADF; - f = fget(fd); + f = fget_light(fd, &fput_needed); if (!f) return error; audit_inode(NULL, f->f_path.dentry); error = getxattr(f->f_path.dentry, name, value, size); - fput(f); + fput_light(f, fput_needed); return error; } @@ -566,15 +568,16 @@ SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list, SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size) { + int fput_needed; struct file *f; ssize_t error = -EBADF; - f = fget(fd); + f = fget_light(fd, &fput_needed); if (!f) return error; audit_inode(NULL, f->f_path.dentry); error = listxattr(f->f_path.dentry, list, size); - fput(f); + fput_light(f, fput_needed); return error; } @@ -634,11 +637,12 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname, SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) { + int fput_needed; struct file *f; struct dentry *dentry; int error = -EBADF; - f = fget(fd); + f = fget_light(fd, &fput_needed); if (!f) return error; dentry = f->f_path.dentry; @@ -648,7 +652,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) error = removexattr(dentry, name); mnt_drop_write_file(f); } - fput(f); + fput_light(f, fput_needed); return error; } diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile index 0a9977983f9..d2bf974b1a2 100644 --- a/fs/xfs/Makefile +++ b/fs/xfs/Makefile @@ -33,6 +33,7 @@ xfs-y += xfs_aops.o \ xfs_discard.o \ xfs_error.o \ xfs_export.o \ + xfs_extent_busy.o \ xfs_file.o \ xfs_filestream.o \ xfs_fsops.o \ @@ -49,7 +50,6 @@ xfs-y += xfs_aops.o \ xfs_sync.o \ xfs_xattr.o \ xfs_rename.o \ - xfs_rw.o \ xfs_utils.o \ xfs_vnodeops.o \ kmem.o \ diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index a907de565db..4a7286c1dc8 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -46,7 +46,7 @@ kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize) } void * -kmem_alloc(size_t size, unsigned int __nocast flags) +kmem_alloc(size_t size, xfs_km_flags_t flags) { int retries = 0; gfp_t lflags = kmem_flags_convert(flags); @@ -65,7 +65,7 @@ kmem_alloc(size_t size, unsigned int __nocast flags) } void * -kmem_zalloc(size_t size, unsigned int __nocast flags) +kmem_zalloc(size_t size, xfs_km_flags_t flags) { void *ptr; @@ -87,7 +87,7 @@ kmem_free(const void *ptr) void * kmem_realloc(const void *ptr, size_t newsize, size_t oldsize, - unsigned int __nocast flags) + xfs_km_flags_t flags) { void *new; @@ -102,7 +102,7 @@ kmem_realloc(const void *ptr, size_t newsize, size_t oldsize, } void * -kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags) +kmem_zone_alloc(kmem_zone_t *zone, xfs_km_flags_t flags) { int retries = 0; gfp_t lflags = kmem_flags_convert(flags); @@ -121,7 +121,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsigned int __nocast flags) } void * -kmem_zone_zalloc(kmem_zone_t *zone, unsigned int __nocast flags) +kmem_zone_zalloc(kmem_zone_t *zone, xfs_km_flags_t flags) { void *ptr; diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index ab7c53fe346..b2f2620f9a8 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -27,10 +27,11 @@ * General memory allocation interfaces */ -#define KM_SLEEP 0x0001u -#define KM_NOSLEEP 0x0002u -#define KM_NOFS 0x0004u -#define KM_MAYFAIL 0x0008u +typedef unsigned __bitwise xfs_km_flags_t; +#define KM_SLEEP ((__force xfs_km_flags_t)0x0001u) +#define KM_NOSLEEP ((__force xfs_km_flags_t)0x0002u) +#define KM_NOFS ((__force xfs_km_flags_t)0x0004u) +#define KM_MAYFAIL ((__force xfs_km_flags_t)0x0008u) /* * We use a special process flag to avoid recursive callbacks into @@ -38,7 +39,7 @@ * warnings, so we explicitly skip any generic ones (silly of us). */ static inline gfp_t -kmem_flags_convert(unsigned int __nocast flags) +kmem_flags_convert(xfs_km_flags_t flags) { gfp_t lflags; @@ -54,9 +55,9 @@ kmem_flags_convert(unsigned int __nocast flags) return lflags; } -extern void *kmem_alloc(size_t, unsigned int __nocast); -extern void *kmem_zalloc(size_t, unsigned int __nocast); -extern void *kmem_realloc(const void *, size_t, size_t, unsigned int __nocast); +extern void *kmem_alloc(size_t, xfs_km_flags_t); +extern void *kmem_zalloc(size_t, xfs_km_flags_t); +extern void *kmem_realloc(const void *, size_t, size_t, xfs_km_flags_t); extern void kmem_free(const void *); static inline void *kmem_zalloc_large(size_t size) @@ -107,7 +108,7 @@ kmem_zone_destroy(kmem_zone_t *zone) kmem_cache_destroy(zone); } -extern void *kmem_zone_alloc(kmem_zone_t *, unsigned int __nocast); -extern void *kmem_zone_zalloc(kmem_zone_t *, unsigned int __nocast); +extern void *kmem_zone_alloc(kmem_zone_t *, xfs_km_flags_t); +extern void *kmem_zone_zalloc(kmem_zone_t *, xfs_km_flags_t); #endif /* __XFS_SUPPORT_KMEM_H__ */ diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h index 4805f009f92..44d65c1533c 100644 --- a/fs/xfs/xfs_ag.h +++ b/fs/xfs/xfs_ag.h @@ -175,24 +175,6 @@ typedef struct xfs_agfl { } xfs_agfl_t; /* - * Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that - * have been freed but whose transactions aren't committed to disk yet. - * - * Note that we use the transaction ID to record the transaction, not the - * transaction structure itself. See xfs_alloc_busy_insert() for details. - */ -struct xfs_busy_extent { - struct rb_node rb_node; /* ag by-bno indexed search tree */ - struct list_head list; /* transaction busy extent list */ - xfs_agnumber_t agno; - xfs_agblock_t bno; - xfs_extlen_t length; - unsigned int flags; -#define XFS_ALLOC_BUSY_DISCARDED 0x01 /* undergoing a discard op. */ -#define XFS_ALLOC_BUSY_SKIP_DISCARD 0x02 /* do not discard */ -}; - -/* * Per-ag incore structure, copies of information in agf and agi, * to improve the performance of allocation group selection. */ diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 0f0df2759b0..9d1aeb7e273 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -32,6 +31,7 @@ #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_alloc.h" +#include "xfs_extent_busy.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -47,8 +47,6 @@ STATIC int xfs_alloc_ag_vextent_near(xfs_alloc_arg_t *); STATIC int xfs_alloc_ag_vextent_size(xfs_alloc_arg_t *); STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *, xfs_btree_cur_t *, xfs_agblock_t *, xfs_extlen_t *, int *); -STATIC void xfs_alloc_busy_trim(struct xfs_alloc_arg *, - xfs_agblock_t, xfs_extlen_t, xfs_agblock_t *, xfs_extlen_t *); /* * Lookup the record equal to [bno, len] in the btree given by cur. @@ -152,7 +150,7 @@ xfs_alloc_compute_aligned( xfs_extlen_t len; /* Trim busy sections out of found extent */ - xfs_alloc_busy_trim(args, foundbno, foundlen, &bno, &len); + xfs_extent_busy_trim(args, foundbno, foundlen, &bno, &len); if (args->alignment > 1 && len >= args->minlen) { xfs_agblock_t aligned_bno = roundup(bno, args->alignment); @@ -536,7 +534,7 @@ xfs_alloc_ag_vextent( if (error) return error; - ASSERT(!xfs_alloc_busy_search(args->mp, args->agno, + ASSERT(!xfs_extent_busy_search(args->mp, args->agno, args->agbno, args->len)); } @@ -603,7 +601,7 @@ xfs_alloc_ag_vextent_exact( /* * Check for overlapping busy extents. */ - xfs_alloc_busy_trim(args, fbno, flen, &tbno, &tlen); + xfs_extent_busy_trim(args, fbno, flen, &tbno, &tlen); /* * Give up if the start of the extent is busy, or the freespace isn't @@ -1082,6 +1080,7 @@ restart: goto restart; } + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); trace_xfs_alloc_size_neither(args); args->agbno = NULLAGBLOCK; return 0; @@ -1391,7 +1390,7 @@ xfs_alloc_ag_vextent_small( if (error) goto error0; if (fbno != NULLAGBLOCK) { - xfs_alloc_busy_reuse(args->mp, args->agno, fbno, 1, + xfs_extent_busy_reuse(args->mp, args->agno, fbno, 1, args->userdata); if (args->userdata) { @@ -2443,7 +2442,7 @@ xfs_alloc_vextent( DECLARE_COMPLETION_ONSTACK(done); args->done = &done; - INIT_WORK(&args->work, xfs_alloc_vextent_worker); + INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); queue_work(xfs_alloc_wq, &args->work); wait_for_completion(&done); return args->result; @@ -2496,579 +2495,8 @@ xfs_free_extent( error = xfs_free_ag_extent(tp, args.agbp, args.agno, args.agbno, len, 0); if (!error) - xfs_alloc_busy_insert(tp, args.agno, args.agbno, len, 0); + xfs_extent_busy_insert(tp, args.agno, args.agbno, len, 0); error0: xfs_perag_put(args.pag); return error; } - -void -xfs_alloc_busy_insert( - struct xfs_trans *tp, - xfs_agnumber_t agno, - xfs_agblock_t bno, - xfs_extlen_t len, - unsigned int flags) -{ - struct xfs_busy_extent *new; - struct xfs_busy_extent *busyp; - struct xfs_perag *pag; - struct rb_node **rbp; - struct rb_node *parent = NULL; - - new = kmem_zalloc(sizeof(struct xfs_busy_extent), KM_MAYFAIL); - if (!new) { - /* - * No Memory! Since it is now not possible to track the free - * block, make this a synchronous transaction to insure that - * the block is not reused before this transaction commits. - */ - trace_xfs_alloc_busy_enomem(tp->t_mountp, agno, bno, len); - xfs_trans_set_sync(tp); - return; - } - - new->agno = agno; - new->bno = bno; - new->length = len; - INIT_LIST_HEAD(&new->list); - new->flags = flags; - - /* trace before insert to be able to see failed inserts */ - trace_xfs_alloc_busy(tp->t_mountp, agno, bno, len); - - pag = xfs_perag_get(tp->t_mountp, new->agno); - spin_lock(&pag->pagb_lock); - rbp = &pag->pagb_tree.rb_node; - while (*rbp) { - parent = *rbp; - busyp = rb_entry(parent, struct xfs_busy_extent, rb_node); - - if (new->bno < busyp->bno) { - rbp = &(*rbp)->rb_left; - ASSERT(new->bno + new->length <= busyp->bno); - } else if (new->bno > busyp->bno) { - rbp = &(*rbp)->rb_right; - ASSERT(bno >= busyp->bno + busyp->length); - } else { - ASSERT(0); - } - } - - rb_link_node(&new->rb_node, parent, rbp); - rb_insert_color(&new->rb_node, &pag->pagb_tree); - - list_add(&new->list, &tp->t_busy); - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); -} - -/* - * Search for a busy extent within the range of the extent we are about to - * allocate. You need to be holding the busy extent tree lock when calling - * xfs_alloc_busy_search(). This function returns 0 for no overlapping busy - * extent, -1 for an overlapping but not exact busy extent, and 1 for an exact - * match. This is done so that a non-zero return indicates an overlap that - * will require a synchronous transaction, but it can still be - * used to distinguish between a partial or exact match. - */ -int -xfs_alloc_busy_search( - struct xfs_mount *mp, - xfs_agnumber_t agno, - xfs_agblock_t bno, - xfs_extlen_t len) -{ - struct xfs_perag *pag; - struct rb_node *rbp; - struct xfs_busy_extent *busyp; - int match = 0; - - pag = xfs_perag_get(mp, agno); - spin_lock(&pag->pagb_lock); - - rbp = pag->pagb_tree.rb_node; - - /* find closest start bno overlap */ - while (rbp) { - busyp = rb_entry(rbp, struct xfs_busy_extent, rb_node); - if (bno < busyp->bno) { - /* may overlap, but exact start block is lower */ - if (bno + len > busyp->bno) - match = -1; - rbp = rbp->rb_left; - } else if (bno > busyp->bno) { - /* may overlap, but exact start block is higher */ - if (bno < busyp->bno + busyp->length) - match = -1; - rbp = rbp->rb_right; - } else { - /* bno matches busyp, length determines exact match */ - match = (busyp->length == len) ? 1 : -1; - break; - } - } - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); - return match; -} - -/* - * The found free extent [fbno, fend] overlaps part or all of the given busy - * extent. If the overlap covers the beginning, the end, or all of the busy - * extent, the overlapping portion can be made unbusy and used for the - * allocation. We can't split a busy extent because we can't modify a - * transaction/CIL context busy list, but we can update an entries block - * number or length. - * - * Returns true if the extent can safely be reused, or false if the search - * needs to be restarted. - */ -STATIC bool -xfs_alloc_busy_update_extent( - struct xfs_mount *mp, - struct xfs_perag *pag, - struct xfs_busy_extent *busyp, - xfs_agblock_t fbno, - xfs_extlen_t flen, - bool userdata) -{ - xfs_agblock_t fend = fbno + flen; - xfs_agblock_t bbno = busyp->bno; - xfs_agblock_t bend = bbno + busyp->length; - - /* - * This extent is currently being discarded. Give the thread - * performing the discard a chance to mark the extent unbusy - * and retry. - */ - if (busyp->flags & XFS_ALLOC_BUSY_DISCARDED) { - spin_unlock(&pag->pagb_lock); - delay(1); - spin_lock(&pag->pagb_lock); - return false; - } - - /* - * If there is a busy extent overlapping a user allocation, we have - * no choice but to force the log and retry the search. - * - * Fortunately this does not happen during normal operation, but - * only if the filesystem is very low on space and has to dip into - * the AGFL for normal allocations. - */ - if (userdata) - goto out_force_log; - - if (bbno < fbno && bend > fend) { - /* - * Case 1: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +---------+ - * fbno fend - */ - - /* - * We would have to split the busy extent to be able to track - * it correct, which we cannot do because we would have to - * modify the list of busy extents attached to the transaction - * or CIL context, which is immutable. - * - * Force out the log to clear the busy extent and retry the - * search. - */ - goto out_force_log; - } else if (bbno >= fbno && bend <= fend) { - /* - * Case 2: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-----------------+ - * fbno fend - * - * Case 3: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +--------------------------+ - * fbno fend - * - * Case 4: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +--------------------------+ - * fbno fend - * - * Case 5: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-----------------------------------+ - * fbno fend - * - */ - - /* - * The busy extent is fully covered by the extent we are - * allocating, and can simply be removed from the rbtree. - * However we cannot remove it from the immutable list - * tracking busy extents in the transaction or CIL context, - * so set the length to zero to mark it invalid. - * - * We also need to restart the busy extent search from the - * tree root, because erasing the node can rearrange the - * tree topology. - */ - rb_erase(&busyp->rb_node, &pag->pagb_tree); - busyp->length = 0; - return false; - } else if (fend < bend) { - /* - * Case 6: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +---------+ - * fbno fend - * - * Case 7: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +------------------+ - * fbno fend - * - */ - busyp->bno = fend; - } else if (bbno < fbno) { - /* - * Case 8: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-------------+ - * fbno fend - * - * Case 9: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +----------------------+ - * fbno fend - */ - busyp->length = fbno - busyp->bno; - } else { - ASSERT(0); - } - - trace_xfs_alloc_busy_reuse(mp, pag->pag_agno, fbno, flen); - return true; - -out_force_log: - spin_unlock(&pag->pagb_lock); - xfs_log_force(mp, XFS_LOG_SYNC); - trace_xfs_alloc_busy_force(mp, pag->pag_agno, fbno, flen); - spin_lock(&pag->pagb_lock); - return false; -} - - -/* - * For a given extent [fbno, flen], make sure we can reuse it safely. - */ -void -xfs_alloc_busy_reuse( - struct xfs_mount *mp, - xfs_agnumber_t agno, - xfs_agblock_t fbno, - xfs_extlen_t flen, - bool userdata) -{ - struct xfs_perag *pag; - struct rb_node *rbp; - - ASSERT(flen > 0); - - pag = xfs_perag_get(mp, agno); - spin_lock(&pag->pagb_lock); -restart: - rbp = pag->pagb_tree.rb_node; - while (rbp) { - struct xfs_busy_extent *busyp = - rb_entry(rbp, struct xfs_busy_extent, rb_node); - xfs_agblock_t bbno = busyp->bno; - xfs_agblock_t bend = bbno + busyp->length; - - if (fbno + flen <= bbno) { - rbp = rbp->rb_left; - continue; - } else if (fbno >= bend) { - rbp = rbp->rb_right; - continue; - } - - if (!xfs_alloc_busy_update_extent(mp, pag, busyp, fbno, flen, - userdata)) - goto restart; - } - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); -} - -/* - * For a given extent [fbno, flen], search the busy extent list to find a - * subset of the extent that is not busy. If *rlen is smaller than - * args->minlen no suitable extent could be found, and the higher level - * code needs to force out the log and retry the allocation. - */ -STATIC void -xfs_alloc_busy_trim( - struct xfs_alloc_arg *args, - xfs_agblock_t bno, - xfs_extlen_t len, - xfs_agblock_t *rbno, - xfs_extlen_t *rlen) -{ - xfs_agblock_t fbno; - xfs_extlen_t flen; - struct rb_node *rbp; - - ASSERT(len > 0); - - spin_lock(&args->pag->pagb_lock); -restart: - fbno = bno; - flen = len; - rbp = args->pag->pagb_tree.rb_node; - while (rbp && flen >= args->minlen) { - struct xfs_busy_extent *busyp = - rb_entry(rbp, struct xfs_busy_extent, rb_node); - xfs_agblock_t fend = fbno + flen; - xfs_agblock_t bbno = busyp->bno; - xfs_agblock_t bend = bbno + busyp->length; - - if (fend <= bbno) { - rbp = rbp->rb_left; - continue; - } else if (fbno >= bend) { - rbp = rbp->rb_right; - continue; - } - - /* - * If this is a metadata allocation, try to reuse the busy - * extent instead of trimming the allocation. - */ - if (!args->userdata && - !(busyp->flags & XFS_ALLOC_BUSY_DISCARDED)) { - if (!xfs_alloc_busy_update_extent(args->mp, args->pag, - busyp, fbno, flen, - false)) - goto restart; - continue; - } - - if (bbno <= fbno) { - /* start overlap */ - - /* - * Case 1: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +---------+ - * fbno fend - * - * Case 2: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-------------+ - * fbno fend - * - * Case 3: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-------------+ - * fbno fend - * - * Case 4: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-----------------+ - * fbno fend - * - * No unbusy region in extent, return failure. - */ - if (fend <= bend) - goto fail; - - /* - * Case 5: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +----------------------+ - * fbno fend - * - * Case 6: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +--------------------------+ - * fbno fend - * - * Needs to be trimmed to: - * +-------+ - * fbno fend - */ - fbno = bend; - } else if (bend >= fend) { - /* end overlap */ - - /* - * Case 7: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +------------------+ - * fbno fend - * - * Case 8: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +--------------------------+ - * fbno fend - * - * Needs to be trimmed to: - * +-------+ - * fbno fend - */ - fend = bbno; - } else { - /* middle overlap */ - - /* - * Case 9: - * bbno bend - * +BBBBBBBBBBBBBBBBB+ - * +-----------------------------------+ - * fbno fend - * - * Can be trimmed to: - * +-------+ OR +-------+ - * fbno fend fbno fend - * - * Backward allocation leads to significant - * fragmentation of directories, which degrades - * directory performance, therefore we always want to - * choose the option that produces forward allocation - * patterns. - * Preferring the lower bno extent will make the next - * request use "fend" as the start of the next - * allocation; if the segment is no longer busy at - * that point, we'll get a contiguous allocation, but - * even if it is still busy, we will get a forward - * allocation. - * We try to avoid choosing the segment at "bend", - * because that can lead to the next allocation - * taking the segment at "fbno", which would be a - * backward allocation. We only use the segment at - * "fbno" if it is much larger than the current - * requested size, because in that case there's a - * good chance subsequent allocations will be - * contiguous. - */ - if (bbno - fbno >= args->maxlen) { - /* left candidate fits perfect */ - fend = bbno; - } else if (fend - bend >= args->maxlen * 4) { - /* right candidate has enough free space */ - fbno = bend; - } else if (bbno - fbno >= args->minlen) { - /* left candidate fits minimum requirement */ - fend = bbno; - } else { - goto fail; - } - } - - flen = fend - fbno; - } - spin_unlock(&args->pag->pagb_lock); - - if (fbno != bno || flen != len) { - trace_xfs_alloc_busy_trim(args->mp, args->agno, bno, len, - fbno, flen); - } - *rbno = fbno; - *rlen = flen; - return; -fail: - /* - * Return a zero extent length as failure indications. All callers - * re-check if the trimmed extent satisfies the minlen requirement. - */ - spin_unlock(&args->pag->pagb_lock); - trace_xfs_alloc_busy_trim(args->mp, args->agno, bno, len, fbno, 0); - *rbno = fbno; - *rlen = 0; -} - -static void -xfs_alloc_busy_clear_one( - struct xfs_mount *mp, - struct xfs_perag *pag, - struct xfs_busy_extent *busyp) -{ - if (busyp->length) { - trace_xfs_alloc_busy_clear(mp, busyp->agno, busyp->bno, - busyp->length); - rb_erase(&busyp->rb_node, &pag->pagb_tree); - } - - list_del_init(&busyp->list); - kmem_free(busyp); -} - -/* - * Remove all extents on the passed in list from the busy extents tree. - * If do_discard is set skip extents that need to be discarded, and mark - * these as undergoing a discard operation instead. - */ -void -xfs_alloc_busy_clear( - struct xfs_mount *mp, - struct list_head *list, - bool do_discard) -{ - struct xfs_busy_extent *busyp, *n; - struct xfs_perag *pag = NULL; - xfs_agnumber_t agno = NULLAGNUMBER; - - list_for_each_entry_safe(busyp, n, list, list) { - if (busyp->agno != agno) { - if (pag) { - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); - } - pag = xfs_perag_get(mp, busyp->agno); - spin_lock(&pag->pagb_lock); - agno = busyp->agno; - } - - if (do_discard && busyp->length && - !(busyp->flags & XFS_ALLOC_BUSY_SKIP_DISCARD)) - busyp->flags = XFS_ALLOC_BUSY_DISCARDED; - else - xfs_alloc_busy_clear_one(mp, pag, busyp); - } - - if (pag) { - spin_unlock(&pag->pagb_lock); - xfs_perag_put(pag); - } -} - -/* - * Callback for list_sort to sort busy extents by the AG they reside in. - */ -int -xfs_busy_extent_ag_cmp( - void *priv, - struct list_head *a, - struct list_head *b) -{ - return container_of(a, struct xfs_busy_extent, list)->agno - - container_of(b, struct xfs_busy_extent, list)->agno; -} diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h index 3a7e7d8f8de..93be4a667ca 100644 --- a/fs/xfs/xfs_alloc.h +++ b/fs/xfs/xfs_alloc.h @@ -23,7 +23,6 @@ struct xfs_btree_cur; struct xfs_mount; struct xfs_perag; struct xfs_trans; -struct xfs_busy_extent; extern struct workqueue_struct *xfs_alloc_wq; @@ -139,33 +138,6 @@ xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_mount *mp, struct xfs_perag *pag); -#ifdef __KERNEL__ -void -xfs_alloc_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags); - -void -xfs_alloc_busy_clear(struct xfs_mount *mp, struct list_head *list, - bool do_discard); - -int -xfs_alloc_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agblock_t bno, xfs_extlen_t len); - -void -xfs_alloc_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno, - xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata); - -int -xfs_busy_extent_ag_cmp(void *priv, struct list_head *a, struct list_head *b); - -static inline void xfs_alloc_busy_sort(struct list_head *list) -{ - list_sort(NULL, list, xfs_busy_extent_ag_cmp); -} - -#endif /* __KERNEL__ */ - /* * Compute and fill in value of m_ag_maxlevels. */ diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index ffb3386e45c..f1647caace8 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -32,6 +30,7 @@ #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_alloc.h" +#include "xfs_extent_busy.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -94,7 +93,7 @@ xfs_allocbt_alloc_block( return 0; } - xfs_alloc_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false); + xfs_extent_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false); xfs_trans_agbtree_delta(cur->bc_tp, 1); new->s = cpu_to_be32(bno); @@ -119,8 +118,8 @@ xfs_allocbt_free_block( if (error) return error; - xfs_alloc_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, - XFS_ALLOC_BUSY_SKIP_DISCARD); + xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, + XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 0dbb9e70fe2..8dad722c004 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -16,9 +16,7 @@ * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include "xfs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_trans.h" @@ -29,7 +27,6 @@ #include "xfs_inode_item.h" #include "xfs_alloc.h" #include "xfs_error.h" -#include "xfs_rw.h" #include "xfs_iomap.h" #include "xfs_vnodeops.h" #include "xfs_trace.h" @@ -623,7 +620,7 @@ xfs_map_at_offset( * or delayed allocate extent. */ STATIC int -xfs_is_delayed_page( +xfs_check_page_type( struct page *page, unsigned int type) { @@ -637,11 +634,11 @@ xfs_is_delayed_page( bh = head = page_buffers(page); do { if (buffer_unwritten(bh)) - acceptable = (type == IO_UNWRITTEN); + acceptable += (type == IO_UNWRITTEN); else if (buffer_delay(bh)) - acceptable = (type == IO_DELALLOC); + acceptable += (type == IO_DELALLOC); else if (buffer_dirty(bh) && buffer_mapped(bh)) - acceptable = (type == IO_OVERWRITE); + acceptable += (type == IO_OVERWRITE); else break; } while ((bh = bh->b_this_page) != head); @@ -684,7 +681,7 @@ xfs_convert_page( goto fail_unlock_page; if (page->mapping != inode->i_mapping) goto fail_unlock_page; - if (!xfs_is_delayed_page(page, (*ioendp)->io_type)) + if (!xfs_check_page_type(page, (*ioendp)->io_type)) goto fail_unlock_page; /* @@ -834,7 +831,7 @@ xfs_aops_discard_page( struct buffer_head *bh, *head; loff_t offset = page_offset(page); - if (!xfs_is_delayed_page(page, IO_DELALLOC)) + if (!xfs_check_page_type(page, IO_DELALLOC)) goto out_invalidate; if (XFS_FORCED_SHUTDOWN(ip->i_mount)) @@ -984,10 +981,15 @@ xfs_vm_writepage( imap_valid = 0; } } else { - if (PageUptodate(page)) { + if (PageUptodate(page)) ASSERT(buffer_mapped(bh)); - imap_valid = 0; - } + /* + * This buffer is not uptodate and will not be + * written to disk. Ensure that we will put any + * subsequent writeable buffers into a new + * ioend. + */ + imap_valid = 0; continue; } @@ -1146,7 +1148,14 @@ __xfs_get_blocks( if (!create && direct && offset >= i_size_read(inode)) return 0; - if (create) { + /* + * Direct I/O is usually done on preallocated files, so try getting + * a block mapping without an exclusive lock first. For buffered + * writes we already have the exclusive iolock anyway, so avoiding + * a lock roundtrip here by taking the ilock exclusive from the + * beginning is a useful micro optimization. + */ + if (create && !direct) { lockmode = XFS_ILOCK_EXCL; xfs_ilock(ip, lockmode); } else { @@ -1168,23 +1177,45 @@ __xfs_get_blocks( (!nimaps || (imap.br_startblock == HOLESTARTBLOCK || imap.br_startblock == DELAYSTARTBLOCK))) { - if (direct) { + if (direct || xfs_get_extsz_hint(ip)) { + /* + * Drop the ilock in preparation for starting the block + * allocation transaction. It will be retaken + * exclusively inside xfs_iomap_write_direct for the + * actual allocation. + */ + xfs_iunlock(ip, lockmode); error = xfs_iomap_write_direct(ip, offset, size, &imap, nimaps); + if (error) + return -error; + new = 1; } else { + /* + * Delalloc reservations do not require a transaction, + * we can go on without dropping the lock here. If we + * are allocating a new delalloc block, make sure that + * we set the new flag so that we mark the buffer new so + * that we know that it is newly allocated if the write + * fails. + */ + if (nimaps && imap.br_startblock == HOLESTARTBLOCK) + new = 1; error = xfs_iomap_write_delay(ip, offset, size, &imap); + if (error) + goto out_unlock; + + xfs_iunlock(ip, lockmode); } - if (error) - goto out_unlock; trace_xfs_get_blocks_alloc(ip, offset, size, 0, &imap); } else if (nimaps) { trace_xfs_get_blocks_found(ip, offset, size, 0, &imap); + xfs_iunlock(ip, lockmode); } else { trace_xfs_get_blocks_notfound(ip, offset, size); goto out_unlock; } - xfs_iunlock(ip, lockmode); if (imap.br_startblock != HOLESTARTBLOCK && imap.br_startblock != DELAYSTARTBLOCK) { @@ -1386,52 +1417,91 @@ out_destroy_ioend: return ret; } +/* + * Punch out the delalloc blocks we have already allocated. + * + * Don't bother with xfs_setattr given that nothing can have made it to disk yet + * as the page is still locked at this point. + */ +STATIC void +xfs_vm_kill_delalloc_range( + struct inode *inode, + loff_t start, + loff_t end) +{ + struct xfs_inode *ip = XFS_I(inode); + xfs_fileoff_t start_fsb; + xfs_fileoff_t end_fsb; + int error; + + start_fsb = XFS_B_TO_FSB(ip->i_mount, start); + end_fsb = XFS_B_TO_FSB(ip->i_mount, end); + if (end_fsb <= start_fsb) + return; + + xfs_ilock(ip, XFS_ILOCK_EXCL); + error = xfs_bmap_punch_delalloc_range(ip, start_fsb, + end_fsb - start_fsb); + if (error) { + /* something screwed, just bail */ + if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { + xfs_alert(ip->i_mount, + "xfs_vm_write_failed: unable to clean up ino %lld", + ip->i_ino); + } + } + xfs_iunlock(ip, XFS_ILOCK_EXCL); +} + STATIC void xfs_vm_write_failed( - struct address_space *mapping, - loff_t to) + struct inode *inode, + struct page *page, + loff_t pos, + unsigned len) { - struct inode *inode = mapping->host; + loff_t block_offset = pos & PAGE_MASK; + loff_t block_start; + loff_t block_end; + loff_t from = pos & (PAGE_CACHE_SIZE - 1); + loff_t to = from + len; + struct buffer_head *bh, *head; - if (to > inode->i_size) { - /* - * Punch out the delalloc blocks we have already allocated. - * - * Don't bother with xfs_setattr given that nothing can have - * made it to disk yet as the page is still locked at this - * point. - */ - struct xfs_inode *ip = XFS_I(inode); - xfs_fileoff_t start_fsb; - xfs_fileoff_t end_fsb; - int error; + ASSERT(block_offset + from == pos); - truncate_pagecache(inode, to, inode->i_size); + head = page_buffers(page); + block_start = 0; + for (bh = head; bh != head || !block_start; + bh = bh->b_this_page, block_start = block_end, + block_offset += bh->b_size) { + block_end = block_start + bh->b_size; - /* - * Check if there are any blocks that are outside of i_size - * that need to be trimmed back. - */ - start_fsb = XFS_B_TO_FSB(ip->i_mount, inode->i_size) + 1; - end_fsb = XFS_B_TO_FSB(ip->i_mount, to); - if (end_fsb <= start_fsb) - return; - - xfs_ilock(ip, XFS_ILOCK_EXCL); - error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - end_fsb - start_fsb); - if (error) { - /* something screwed, just bail */ - if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - xfs_alert(ip->i_mount, - "xfs_vm_write_failed: unable to clean up ino %lld", - ip->i_ino); - } - } - xfs_iunlock(ip, XFS_ILOCK_EXCL); + /* skip buffers before the write */ + if (block_end <= from) + continue; + + /* if the buffer is after the write, we're done */ + if (block_start >= to) + break; + + if (!buffer_delay(bh)) + continue; + + if (!buffer_new(bh) && block_offset < i_size_read(inode)) + continue; + + xfs_vm_kill_delalloc_range(inode, block_offset, + block_offset + bh->b_size); } + } +/* + * This used to call block_write_begin(), but it unlocks and releases the page + * on error, and we need that page to be able to punch stale delalloc blocks out + * on failure. hence we copy-n-waste it here and call xfs_vm_write_failed() at + * the appropriate point. + */ STATIC int xfs_vm_write_begin( struct file *file, @@ -1442,15 +1512,40 @@ xfs_vm_write_begin( struct page **pagep, void **fsdata) { - int ret; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + struct page *page; + int status; - ret = block_write_begin(mapping, pos, len, flags | AOP_FLAG_NOFS, - pagep, xfs_get_blocks); - if (unlikely(ret)) - xfs_vm_write_failed(mapping, pos + len); - return ret; + ASSERT(len <= PAGE_CACHE_SIZE); + + page = grab_cache_page_write_begin(mapping, index, + flags | AOP_FLAG_NOFS); + if (!page) + return -ENOMEM; + + status = __block_write_begin(page, pos, len, xfs_get_blocks); + if (unlikely(status)) { + struct inode *inode = mapping->host; + + xfs_vm_write_failed(inode, page, pos, len); + unlock_page(page); + + if (pos + len > i_size_read(inode)) + truncate_pagecache(inode, pos + len, i_size_read(inode)); + + page_cache_release(page); + page = NULL; + } + + *pagep = page; + return status; } +/* + * On failure, we only need to kill delalloc blocks beyond EOF because they + * will never be written. For blocks within EOF, generic_write_end() zeros them + * so they are safe to leave alone and be written with all the other valid data. + */ STATIC int xfs_vm_write_end( struct file *file, @@ -1463,9 +1558,19 @@ xfs_vm_write_end( { int ret; + ASSERT(len <= PAGE_CACHE_SIZE); + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); - if (unlikely(ret < len)) - xfs_vm_write_failed(mapping, pos + len); + if (unlikely(ret < len)) { + struct inode *inode = mapping->host; + size_t isize = i_size_read(inode); + loff_t to = pos + len; + + if (to > isize) { + truncate_pagecache(inode, to, isize); + xfs_vm_kill_delalloc_range(inode, isize, to); + } + } return ret; } diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c index 65d61b948ea..a17ff01b5ad 100644 --- a/fs/xfs/xfs_attr.c +++ b/fs/xfs/xfs_attr.c @@ -21,7 +21,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -39,7 +38,6 @@ #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_trans_space.h" -#include "xfs_rw.h" #include "xfs_vnodeops.h" #include "xfs_trace.h" @@ -1987,14 +1985,12 @@ xfs_attr_rmtval_get(xfs_da_args_t *args) (map[i].br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); - error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno, - blkcnt, XBF_LOCK | XBF_DONT_BLOCK, - &bp); + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, + dblkno, blkcnt, 0, &bp); if (error) return(error); - tmp = (valuelen < XFS_BUF_SIZE(bp)) - ? valuelen : XFS_BUF_SIZE(bp); + tmp = min_t(int, valuelen, BBTOB(bp->b_length)); xfs_buf_iomove(bp, 0, tmp, dst, XBRW_READ); xfs_buf_relse(bp); dst += tmp; @@ -2097,6 +2093,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) lblkno = args->rmtblkno; valuelen = args->valuelen; while (valuelen > 0) { + int buflen; + /* * Try to remember where we decided to put the value. */ @@ -2114,15 +2112,16 @@ xfs_attr_rmtval_set(xfs_da_args_t *args) dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock), blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount); - bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt, - XBF_LOCK | XBF_DONT_BLOCK); + bp = xfs_buf_get(mp->m_ddev_targp, dblkno, blkcnt, 0); if (!bp) return ENOMEM; - tmp = (valuelen < XFS_BUF_SIZE(bp)) ? valuelen : - XFS_BUF_SIZE(bp); + + buflen = BBTOB(bp->b_length); + tmp = min_t(int, valuelen, buflen); xfs_buf_iomove(bp, 0, tmp, src, XBRW_WRITE); - if (tmp < XFS_BUF_SIZE(bp)) - xfs_buf_zero(bp, tmp, XFS_BUF_SIZE(bp) - tmp); + if (tmp < buflen) + xfs_buf_zero(bp, tmp, buflen - tmp); + error = xfs_bwrite(bp); /* GROT: NOTE: synchronous write */ xfs_buf_relse(bp); if (error) diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index 76d93dc953e..7d89d800f51 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -2983,7 +2982,7 @@ xfs_attr_leaf_freextent(xfs_trans_t **trans, xfs_inode_t *dp, map.br_blockcount); bp = xfs_trans_get_buf(*trans, dp->i_mount->m_ddev_targp, - dblkno, dblkcnt, XBF_LOCK); + dblkno, dblkcnt, 0); if (!bp) return ENOMEM; xfs_trans_binval(*trans, bp); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 85e7e327bcd..58b815ec8c9 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -41,7 +41,6 @@ #include "xfs_rtalloc.h" #include "xfs_error.h" #include "xfs_attr_leaf.h" -#include "xfs_rw.h" #include "xfs_quota.h" #include "xfs_trans_space.h" #include "xfs_buf_item.h" @@ -4527,7 +4526,7 @@ out_unreserve_blocks: xfs_icsb_modify_counters(mp, XFS_SBS_FDBLOCKS, alen, 0); out_unreserve_quota: if (XFS_IS_QUOTA_ON(mp)) - xfs_trans_unreserve_quota_nblks(NULL, ip, alen, 0, rt ? + xfs_trans_unreserve_quota_nblks(NULL, ip, (long)alen, 0, rt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); return error; } @@ -5621,8 +5620,20 @@ xfs_getbmap( XFS_FSB_TO_BB(mp, map[i].br_blockcount); out[cur_ext].bmv_unused1 = 0; out[cur_ext].bmv_unused2 = 0; - ASSERT(((iflags & BMV_IF_DELALLOC) != 0) || - (map[i].br_startblock != DELAYSTARTBLOCK)); + + /* + * delayed allocation extents that start beyond EOF can + * occur due to speculative EOF allocation when the + * delalloc extent is larger than the largest freespace + * extent at conversion time. These extents cannot be + * converted by data writeback, so can exist here even + * if we are not supposed to be finding delalloc + * extents. + */ + if (map[i].br_startblock == DELAYSTARTBLOCK && + map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) + ASSERT((iflags & BMV_IF_DELALLOC) != 0); + if (map[i].br_startblock == HOLESTARTBLOCK && whichfork == XFS_ATTR_FORK) { /* came to the end of attribute fork */ @@ -6157,3 +6168,16 @@ next_block: return error; } + +/* + * Convert the given file system block to a disk block. We have to treat it + * differently based on whether the file is a real time file or not, because the + * bmap code does. + */ +xfs_daddr_t +xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) +{ + return (XFS_IS_REALTIME_INODE(ip) ? \ + (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \ + XFS_FSB_TO_DADDR((ip)->i_mount, (fsb))); +} diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 89ee672d378..803b56d7ce1 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -211,6 +211,9 @@ int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, int *count); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, xfs_fileoff_t start_fsb, xfs_fileoff_t length); + +xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb); + #endif /* __KERNEL__ */ #endif /* __XFS_BMAP_H__ */ diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c index e2f5d59cbea..862084a47a7 100644 --- a/fs/xfs/xfs_bmap_btree.c +++ b/fs/xfs/xfs_bmap_btree.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index 1f19f03af9d..e53e317b158 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 6819b5163e3..a4beb421018 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -35,14 +35,12 @@ #include <linux/freezer.h> #include "xfs_sb.h" -#include "xfs_inum.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_mount.h" #include "xfs_trace.h" static kmem_zone_t *xfs_buf_zone; -STATIC int xfsbufd(void *); static struct workqueue_struct *xfslogd_workqueue; @@ -57,11 +55,7 @@ static struct workqueue_struct *xfslogd_workqueue; #endif #define xb_to_gfp(flags) \ - ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : \ - ((flags) & XBF_DONT_BLOCK) ? GFP_NOFS : GFP_KERNEL) | __GFP_NOWARN) - -#define xb_to_km(flags) \ - (((flags) & XBF_DONT_BLOCK) ? KM_NOFS : KM_SLEEP) + ((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN) static inline int @@ -71,11 +65,11 @@ xfs_buf_is_vmapped( /* * Return true if the buffer is vmapped. * - * The XBF_MAPPED flag is set if the buffer should be mapped, but the - * code is clever enough to know it doesn't have to map a single page, - * so the check has to be both for XBF_MAPPED and bp->b_page_count > 1. + * b_addr is null if the buffer is not mapped, but the code is clever + * enough to know it doesn't have to map a single page, so the check has + * to be both for b_addr and bp->b_page_count > 1. */ - return (bp->b_flags & XBF_MAPPED) && bp->b_page_count > 1; + return bp->b_addr && bp->b_page_count > 1; } static inline int @@ -144,8 +138,17 @@ void xfs_buf_stale( struct xfs_buf *bp) { + ASSERT(xfs_buf_islocked(bp)); + bp->b_flags |= XBF_STALE; - xfs_buf_delwri_dequeue(bp); + + /* + * Clear the delwri status so that a delwri queue walker will not + * flush this buffer to disk now that it is stale. The delwri queue has + * a reference to the buffer, so this is safe to do. + */ + bp->b_flags &= ~_XBF_DELWRI_Q; + atomic_set(&(bp)->b_lru_ref, 0); if (!list_empty(&bp->b_lru)) { struct xfs_buftarg *btp = bp->b_target; @@ -164,22 +167,22 @@ xfs_buf_stale( struct xfs_buf * xfs_buf_alloc( struct xfs_buftarg *target, - xfs_off_t range_base, - size_t range_length, + xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags) { struct xfs_buf *bp; - bp = kmem_zone_alloc(xfs_buf_zone, xb_to_km(flags)); + bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS); if (unlikely(!bp)) return NULL; /* - * We don't want certain flags to appear in b_flags. + * We don't want certain flags to appear in b_flags unless they are + * specifically set by later operations on the buffer. */ - flags &= ~(XBF_LOCK|XBF_MAPPED|XBF_DONT_BLOCK|XBF_READ_AHEAD); + flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - memset(bp, 0, sizeof(xfs_buf_t)); atomic_set(&bp->b_hold, 1); atomic_set(&bp->b_lru_ref, 1); init_completion(&bp->b_iowait); @@ -189,15 +192,16 @@ xfs_buf_alloc( sema_init(&bp->b_sema, 0); /* held, no waiters */ XB_SET_OWNER(bp); bp->b_target = target; - bp->b_file_offset = range_base; + /* - * Set buffer_length and count_desired to the same value initially. - * I/O routines should use count_desired, which will be the same in + * Set length and io_length to the same value initially. + * I/O routines should use io_length, which will be the same in * most cases but may be reset (e.g. XFS recovery). */ - bp->b_buffer_length = bp->b_count_desired = range_length; + bp->b_length = numblks; + bp->b_io_length = numblks; bp->b_flags = flags; - bp->b_bn = XFS_BUF_DADDR_NULL; + bp->b_bn = blkno; atomic_set(&bp->b_pin_count, 0); init_waitqueue_head(&bp->b_waiters); @@ -219,13 +223,12 @@ _xfs_buf_get_pages( { /* Make sure that we have a page list */ if (bp->b_pages == NULL) { - bp->b_offset = xfs_buf_poff(bp->b_file_offset); bp->b_page_count = page_count; if (page_count <= XB_PAGES) { bp->b_pages = bp->b_page_array; } else { bp->b_pages = kmem_alloc(sizeof(struct page *) * - page_count, xb_to_km(flags)); + page_count, KM_NOFS); if (bp->b_pages == NULL) return -ENOMEM; } @@ -288,11 +291,11 @@ xfs_buf_allocate_memory( xfs_buf_t *bp, uint flags) { - size_t size = bp->b_count_desired; + size_t size; size_t nbytes, offset; gfp_t gfp_mask = xb_to_gfp(flags); unsigned short page_count, i; - xfs_off_t end; + xfs_off_t start, end; int error; /* @@ -300,15 +303,15 @@ xfs_buf_allocate_memory( * the memory from the heap - there's no need for the complexity of * page arrays to keep allocation down to order 0. */ - if (bp->b_buffer_length < PAGE_SIZE) { - bp->b_addr = kmem_alloc(bp->b_buffer_length, xb_to_km(flags)); + size = BBTOB(bp->b_length); + if (size < PAGE_SIZE) { + bp->b_addr = kmem_alloc(size, KM_NOFS); if (!bp->b_addr) { /* low memory - use alloc_page loop instead */ goto use_alloc_page; } - if (((unsigned long)(bp->b_addr + bp->b_buffer_length - 1) & - PAGE_MASK) != + if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) != ((unsigned long)bp->b_addr & PAGE_MASK)) { /* b_addr spans two pages - use alloc_page instead */ kmem_free(bp->b_addr); @@ -319,13 +322,14 @@ xfs_buf_allocate_memory( bp->b_pages = bp->b_page_array; bp->b_pages[0] = virt_to_page(bp->b_addr); bp->b_page_count = 1; - bp->b_flags |= XBF_MAPPED | _XBF_KMEM; + bp->b_flags |= _XBF_KMEM; return 0; } use_alloc_page: - end = bp->b_file_offset + bp->b_buffer_length; - page_count = xfs_buf_btoc(end) - xfs_buf_btoct(bp->b_file_offset); + start = BBTOB(bp->b_bn) >> PAGE_SHIFT; + end = (BBTOB(bp->b_bn + bp->b_length) + PAGE_SIZE - 1) >> PAGE_SHIFT; + page_count = end - start; error = _xfs_buf_get_pages(bp, page_count, flags); if (unlikely(error)) return error; @@ -388,8 +392,9 @@ _xfs_buf_map_pages( if (bp->b_page_count == 1) { /* A single page buffer is always mappable */ bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset; - bp->b_flags |= XBF_MAPPED; - } else if (flags & XBF_MAPPED) { + } else if (flags & XBF_UNMAPPED) { + bp->b_addr = NULL; + } else { int retried = 0; do { @@ -403,7 +408,6 @@ _xfs_buf_map_pages( if (!bp->b_addr) return -ENOMEM; bp->b_addr += bp->b_offset; - bp->b_flags |= XBF_MAPPED; } return 0; @@ -420,29 +424,27 @@ _xfs_buf_map_pages( */ xfs_buf_t * _xfs_buf_find( - xfs_buftarg_t *btp, /* block device target */ - xfs_off_t ioff, /* starting offset of range */ - size_t isize, /* length of range */ + struct xfs_buftarg *btp, + xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags, xfs_buf_t *new_bp) { - xfs_off_t range_base; - size_t range_length; + size_t numbytes; struct xfs_perag *pag; struct rb_node **rbp; struct rb_node *parent; xfs_buf_t *bp; - range_base = (ioff << BBSHIFT); - range_length = (isize << BBSHIFT); + numbytes = BBTOB(numblks); /* Check for IOs smaller than the sector size / not sector aligned */ - ASSERT(!(range_length < (1 << btp->bt_sshift))); - ASSERT(!(range_base & (xfs_off_t)btp->bt_smask)); + ASSERT(!(numbytes < (1 << btp->bt_sshift))); + ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_smask)); /* get tree root */ pag = xfs_perag_get(btp->bt_mount, - xfs_daddr_to_agno(btp->bt_mount, ioff)); + xfs_daddr_to_agno(btp->bt_mount, blkno)); /* walk tree */ spin_lock(&pag->pag_buf_lock); @@ -453,20 +455,20 @@ _xfs_buf_find( parent = *rbp; bp = rb_entry(parent, struct xfs_buf, b_rbnode); - if (range_base < bp->b_file_offset) + if (blkno < bp->b_bn) rbp = &(*rbp)->rb_left; - else if (range_base > bp->b_file_offset) + else if (blkno > bp->b_bn) rbp = &(*rbp)->rb_right; else { /* - * found a block offset match. If the range doesn't + * found a block number match. If the range doesn't * match, the only way this is allowed is if the buffer * in the cache is stale and the transaction that made * it stale has not yet committed. i.e. we are * reallocating a busy extent. Skip this buffer and * continue searching to the right for an exact match. */ - if (bp->b_buffer_length != range_length) { + if (bp->b_length != numblks) { ASSERT(bp->b_flags & XBF_STALE); rbp = &(*rbp)->rb_right; continue; @@ -511,7 +513,7 @@ found: */ if (bp->b_flags & XBF_STALE) { ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0); - bp->b_flags &= XBF_MAPPED | _XBF_KMEM | _XBF_PAGES; + bp->b_flags &= _XBF_KMEM | _XBF_PAGES; } trace_xfs_buf_find(bp, flags, _RET_IP_); @@ -526,63 +528,54 @@ found: */ struct xfs_buf * xfs_buf_get( - xfs_buftarg_t *target,/* target for buffer */ - xfs_off_t ioff, /* starting offset of range */ - size_t isize, /* length of range */ + xfs_buftarg_t *target, + xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags) { struct xfs_buf *bp; struct xfs_buf *new_bp; int error = 0; - bp = _xfs_buf_find(target, ioff, isize, flags, NULL); + bp = _xfs_buf_find(target, blkno, numblks, flags, NULL); if (likely(bp)) goto found; - new_bp = xfs_buf_alloc(target, ioff << BBSHIFT, isize << BBSHIFT, - flags); + new_bp = xfs_buf_alloc(target, blkno, numblks, flags); if (unlikely(!new_bp)) return NULL; - bp = _xfs_buf_find(target, ioff, isize, flags, new_bp); - if (!bp) { + error = xfs_buf_allocate_memory(new_bp, flags); + if (error) { kmem_zone_free(xfs_buf_zone, new_bp); return NULL; } - if (bp == new_bp) { - error = xfs_buf_allocate_memory(bp, flags); - if (error) - goto no_buffer; - } else - kmem_zone_free(xfs_buf_zone, new_bp); + bp = _xfs_buf_find(target, blkno, numblks, flags, new_bp); + if (!bp) { + xfs_buf_free(new_bp); + return NULL; + } - /* - * Now we have a workable buffer, fill in the block number so - * that we can do IO on it. - */ - bp->b_bn = ioff; - bp->b_count_desired = bp->b_buffer_length; + if (bp != new_bp) + xfs_buf_free(new_bp); + + bp->b_io_length = bp->b_length; found: - if (!(bp->b_flags & XBF_MAPPED)) { + if (!bp->b_addr) { error = _xfs_buf_map_pages(bp, flags); if (unlikely(error)) { xfs_warn(target->bt_mount, "%s: failed to map pages\n", __func__); - goto no_buffer; + xfs_buf_relse(bp); + return NULL; } } XFS_STATS_INC(xb_get); trace_xfs_buf_get(bp, flags, _RET_IP_); return bp; - -no_buffer: - if (flags & (XBF_LOCK | XBF_TRYLOCK)) - xfs_buf_unlock(bp); - xfs_buf_rele(bp); - return NULL; } STATIC int @@ -590,32 +583,30 @@ _xfs_buf_read( xfs_buf_t *bp, xfs_buf_flags_t flags) { - int status; - - ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE))); + ASSERT(!(flags & XBF_WRITE)); ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL); - bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD); + bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD); bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD); - status = xfs_buf_iorequest(bp); - if (status || bp->b_error || (flags & XBF_ASYNC)) - return status; + xfs_buf_iorequest(bp); + if (flags & XBF_ASYNC) + return 0; return xfs_buf_iowait(bp); } xfs_buf_t * xfs_buf_read( xfs_buftarg_t *target, - xfs_off_t ioff, - size_t isize, + xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags) { xfs_buf_t *bp; flags |= XBF_READ; - bp = xfs_buf_get(target, ioff, isize, flags); + bp = xfs_buf_get(target, blkno, numblks, flags); if (bp) { trace_xfs_buf_read(bp, flags, _RET_IP_); @@ -627,7 +618,8 @@ xfs_buf_read( * Read ahead call which is already satisfied, * drop the buffer */ - goto no_buffer; + xfs_buf_relse(bp); + return NULL; } else { /* We do not want read in the flags */ bp->b_flags &= ~XBF_READ; @@ -635,12 +627,6 @@ xfs_buf_read( } return bp; - - no_buffer: - if (flags & (XBF_LOCK | XBF_TRYLOCK)) - xfs_buf_unlock(bp); - xfs_buf_rele(bp); - return NULL; } /* @@ -650,14 +636,14 @@ xfs_buf_read( void xfs_buf_readahead( xfs_buftarg_t *target, - xfs_off_t ioff, - size_t isize) + xfs_daddr_t blkno, + size_t numblks) { if (bdi_read_congested(target->bt_bdi)) return; - xfs_buf_read(target, ioff, isize, - XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD|XBF_DONT_BLOCK); + xfs_buf_read(target, blkno, numblks, + XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD); } /* @@ -666,16 +652,15 @@ xfs_buf_readahead( */ struct xfs_buf * xfs_buf_read_uncached( - struct xfs_mount *mp, struct xfs_buftarg *target, xfs_daddr_t daddr, - size_t length, + size_t numblks, int flags) { xfs_buf_t *bp; int error; - bp = xfs_buf_get_uncached(target, length, flags); + bp = xfs_buf_get_uncached(target, numblks, flags); if (!bp) return NULL; @@ -683,9 +668,9 @@ xfs_buf_read_uncached( XFS_BUF_SET_ADDR(bp, daddr); XFS_BUF_READ(bp); - xfsbdstrat(mp, bp); + xfsbdstrat(target->bt_mount, bp); error = xfs_buf_iowait(bp); - if (error || bp->b_error) { + if (error) { xfs_buf_relse(bp); return NULL; } @@ -699,7 +684,7 @@ xfs_buf_read_uncached( void xfs_buf_set_empty( struct xfs_buf *bp, - size_t len) + size_t numblks) { if (bp->b_pages) _xfs_buf_free_pages(bp); @@ -707,10 +692,9 @@ xfs_buf_set_empty( bp->b_pages = NULL; bp->b_page_count = 0; bp->b_addr = NULL; - bp->b_file_offset = 0; - bp->b_buffer_length = bp->b_count_desired = len; + bp->b_length = numblks; + bp->b_io_length = numblks; bp->b_bn = XFS_BUF_DADDR_NULL; - bp->b_flags &= ~XBF_MAPPED; } static inline struct page * @@ -749,7 +733,7 @@ xfs_buf_associate_memory( bp->b_pages = NULL; bp->b_addr = mem; - rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK); + rval = _xfs_buf_get_pages(bp, page_count, 0); if (rval) return rval; @@ -760,9 +744,8 @@ xfs_buf_associate_memory( pageaddr += PAGE_SIZE; } - bp->b_count_desired = len; - bp->b_buffer_length = buflen; - bp->b_flags |= XBF_MAPPED; + bp->b_io_length = BTOBB(len); + bp->b_length = BTOBB(buflen); return 0; } @@ -770,17 +753,18 @@ xfs_buf_associate_memory( xfs_buf_t * xfs_buf_get_uncached( struct xfs_buftarg *target, - size_t len, + size_t numblks, int flags) { - unsigned long page_count = PAGE_ALIGN(len) >> PAGE_SHIFT; + unsigned long page_count; int error, i; xfs_buf_t *bp; - bp = xfs_buf_alloc(target, 0, len, 0); + bp = xfs_buf_alloc(target, XFS_BUF_DADDR_NULL, numblks, 0); if (unlikely(bp == NULL)) goto fail; + page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT; error = _xfs_buf_get_pages(bp, page_count, 0); if (error) goto fail_free_buf; @@ -792,7 +776,7 @@ xfs_buf_get_uncached( } bp->b_flags |= _XBF_PAGES; - error = _xfs_buf_map_pages(bp, XBF_MAPPED); + error = _xfs_buf_map_pages(bp, 0); if (unlikely(error)) { xfs_warn(target->bt_mount, "%s: failed to map pages\n", __func__); @@ -855,7 +839,7 @@ xfs_buf_rele( spin_unlock(&pag->pag_buf_lock); } else { xfs_buf_lru_del(bp); - ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q))); + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rb_erase(&bp->b_rbnode, &pag->pag_buf_tree); spin_unlock(&pag->pag_buf_lock); xfs_perag_put(pag); @@ -915,13 +899,6 @@ xfs_buf_lock( trace_xfs_buf_lock_done(bp, _RET_IP_); } -/* - * Releases the lock on the buffer object. - * If the buffer is marked delwri but is not queued, do so before we - * unlock the buffer as we need to set flags correctly. We also need to - * take a reference for the delwri queue because the unlocker is going to - * drop their's and they don't know we just queued it. - */ void xfs_buf_unlock( struct xfs_buf *bp) @@ -1008,9 +985,8 @@ xfs_buf_ioerror_alert( const char *func) { xfs_alert(bp->b_target->bt_mount, -"metadata I/O error: block 0x%llx (\"%s\") error %d buf count %zd", - (__uint64_t)XFS_BUF_ADDR(bp), func, - bp->b_error, XFS_BUF_COUNT(bp)); +"metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d", + (__uint64_t)XFS_BUF_ADDR(bp), func, bp->b_error, bp->b_length); } int @@ -1019,10 +995,11 @@ xfs_bwrite( { int error; + ASSERT(xfs_buf_islocked(bp)); + bp->b_flags |= XBF_WRITE; - bp->b_flags &= ~(XBF_ASYNC | XBF_READ); + bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q); - xfs_buf_delwri_dequeue(bp); xfs_bdstrat_cb(bp); error = xfs_buf_iowait(bp); @@ -1181,7 +1158,7 @@ _xfs_buf_ioapply( int rw, map_i, total_nr_pages, nr_pages; struct bio *bio; int offset = bp->b_offset; - int size = bp->b_count_desired; + int size = BBTOB(bp->b_io_length); sector_t sector = bp->b_bn; total_nr_pages = bp->b_page_count; @@ -1229,7 +1206,7 @@ next_chunk: break; offset = 0; - sector += nbytes >> BBSHIFT; + sector += BTOBB(nbytes); size -= nbytes; total_nr_pages--; } @@ -1248,13 +1225,13 @@ next_chunk: } } -int +void xfs_buf_iorequest( xfs_buf_t *bp) { trace_xfs_buf_iorequest(bp, _RET_IP_); - ASSERT(!(bp->b_flags & XBF_DELWRI)); + ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); if (bp->b_flags & XBF_WRITE) xfs_buf_wait_unpin(bp); @@ -1269,13 +1246,12 @@ xfs_buf_iorequest( _xfs_buf_ioend(bp, 0); xfs_buf_rele(bp); - return 0; } /* - * Waits for I/O to complete on the buffer supplied. - * It returns immediately if no I/O is pending. - * It returns the I/O error code, if any, or 0 if there was no error. + * Waits for I/O to complete on the buffer supplied. It returns immediately if + * no I/O is pending or there is already a pending error on the buffer. It + * returns the I/O error code, if any, or 0 if there was no error. */ int xfs_buf_iowait( @@ -1283,7 +1259,8 @@ xfs_buf_iowait( { trace_xfs_buf_iowait(bp, _RET_IP_); - wait_for_completion(&bp->b_iowait); + if (!bp->b_error) + wait_for_completion(&bp->b_iowait); trace_xfs_buf_iowait_done(bp, _RET_IP_); return bp->b_error; @@ -1296,7 +1273,7 @@ xfs_buf_offset( { struct page *page; - if (bp->b_flags & XBF_MAPPED) + if (bp->b_addr) return bp->b_addr + offset; offset += bp->b_offset; @@ -1315,27 +1292,30 @@ xfs_buf_iomove( void *data, /* data address */ xfs_buf_rw_t mode) /* read/write/zero flag */ { - size_t bend, cpoff, csize; - struct page *page; + size_t bend; bend = boff + bsize; while (boff < bend) { - page = bp->b_pages[xfs_buf_btoct(boff + bp->b_offset)]; - cpoff = xfs_buf_poff(boff + bp->b_offset); - csize = min_t(size_t, - PAGE_SIZE-cpoff, bp->b_count_desired-boff); + struct page *page; + int page_index, page_offset, csize; + + page_index = (boff + bp->b_offset) >> PAGE_SHIFT; + page_offset = (boff + bp->b_offset) & ~PAGE_MASK; + page = bp->b_pages[page_index]; + csize = min_t(size_t, PAGE_SIZE - page_offset, + BBTOB(bp->b_io_length) - boff); - ASSERT(((csize + cpoff) <= PAGE_SIZE)); + ASSERT((csize + page_offset) <= PAGE_SIZE); switch (mode) { case XBRW_ZERO: - memset(page_address(page) + cpoff, 0, csize); + memset(page_address(page) + page_offset, 0, csize); break; case XBRW_READ: - memcpy(data, page_address(page) + cpoff, csize); + memcpy(data, page_address(page) + page_offset, csize); break; case XBRW_WRITE: - memcpy(page_address(page) + cpoff, data, csize); + memcpy(page_address(page) + page_offset, data, csize); } boff += csize; @@ -1435,11 +1415,9 @@ xfs_free_buftarg( { unregister_shrinker(&btp->bt_shrinker); - xfs_flush_buftarg(btp, 1); if (mp->m_flags & XFS_MOUNT_BARRIER) xfs_blkdev_issue_flush(btp); - kthread_stop(btp->bt_task); kmem_free(btp); } @@ -1491,20 +1469,6 @@ xfs_setsize_buftarg( return xfs_setsize_buftarg_flags(btp, blocksize, sectorsize, 1); } -STATIC int -xfs_alloc_delwri_queue( - xfs_buftarg_t *btp, - const char *fsname) -{ - INIT_LIST_HEAD(&btp->bt_delwri_queue); - spin_lock_init(&btp->bt_delwri_lock); - btp->bt_flags = 0; - btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd/%s", fsname); - if (IS_ERR(btp->bt_task)) - return PTR_ERR(btp->bt_task); - return 0; -} - xfs_buftarg_t * xfs_alloc_buftarg( struct xfs_mount *mp, @@ -1527,8 +1491,6 @@ xfs_alloc_buftarg( spin_lock_init(&btp->bt_lru_lock); if (xfs_setsize_buftarg_early(btp, bdev)) goto error; - if (xfs_alloc_delwri_queue(btp, fsname)) - goto error; btp->bt_shrinker.shrink = xfs_buftarg_shrink; btp->bt_shrinker.seeks = DEFAULT_SEEKS; register_shrinker(&btp->bt_shrinker); @@ -1539,125 +1501,52 @@ error: return NULL; } - /* - * Delayed write buffer handling + * Add a buffer to the delayed write list. + * + * This queues a buffer for writeout if it hasn't already been. Note that + * neither this routine nor the buffer list submission functions perform + * any internal synchronization. It is expected that the lists are thread-local + * to the callers. + * + * Returns true if we queued up the buffer, or false if it already had + * been on the buffer list. */ -void +bool xfs_buf_delwri_queue( - xfs_buf_t *bp) + struct xfs_buf *bp, + struct list_head *list) { - struct xfs_buftarg *btp = bp->b_target; - - trace_xfs_buf_delwri_queue(bp, _RET_IP_); - + ASSERT(xfs_buf_islocked(bp)); ASSERT(!(bp->b_flags & XBF_READ)); - spin_lock(&btp->bt_delwri_lock); - if (!list_empty(&bp->b_list)) { - /* if already in the queue, move it to the tail */ - ASSERT(bp->b_flags & _XBF_DELWRI_Q); - list_move_tail(&bp->b_list, &btp->bt_delwri_queue); - } else { - /* start xfsbufd as it is about to have something to do */ - if (list_empty(&btp->bt_delwri_queue)) - wake_up_process(bp->b_target->bt_task); - - atomic_inc(&bp->b_hold); - bp->b_flags |= XBF_DELWRI | _XBF_DELWRI_Q | XBF_ASYNC; - list_add_tail(&bp->b_list, &btp->bt_delwri_queue); - } - bp->b_queuetime = jiffies; - spin_unlock(&btp->bt_delwri_lock); -} - -void -xfs_buf_delwri_dequeue( - xfs_buf_t *bp) -{ - int dequeued = 0; - - spin_lock(&bp->b_target->bt_delwri_lock); - if ((bp->b_flags & XBF_DELWRI) && !list_empty(&bp->b_list)) { - ASSERT(bp->b_flags & _XBF_DELWRI_Q); - list_del_init(&bp->b_list); - dequeued = 1; + /* + * If the buffer is already marked delwri it already is queued up + * by someone else for imediate writeout. Just ignore it in that + * case. + */ + if (bp->b_flags & _XBF_DELWRI_Q) { + trace_xfs_buf_delwri_queued(bp, _RET_IP_); + return false; } - bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q); - spin_unlock(&bp->b_target->bt_delwri_lock); - - if (dequeued) - xfs_buf_rele(bp); - - trace_xfs_buf_delwri_dequeue(bp, _RET_IP_); -} - -/* - * If a delwri buffer needs to be pushed before it has aged out, then promote - * it to the head of the delwri queue so that it will be flushed on the next - * xfsbufd run. We do this by resetting the queuetime of the buffer to be older - * than the age currently needed to flush the buffer. Hence the next time the - * xfsbufd sees it is guaranteed to be considered old enough to flush. - */ -void -xfs_buf_delwri_promote( - struct xfs_buf *bp) -{ - struct xfs_buftarg *btp = bp->b_target; - long age = xfs_buf_age_centisecs * msecs_to_jiffies(10) + 1; - ASSERT(bp->b_flags & XBF_DELWRI); - ASSERT(bp->b_flags & _XBF_DELWRI_Q); + trace_xfs_buf_delwri_queue(bp, _RET_IP_); /* - * Check the buffer age before locking the delayed write queue as we - * don't need to promote buffers that are already past the flush age. + * If a buffer gets written out synchronously or marked stale while it + * is on a delwri list we lazily remove it. To do this, the other party + * clears the _XBF_DELWRI_Q flag but otherwise leaves the buffer alone. + * It remains referenced and on the list. In a rare corner case it + * might get readded to a delwri list after the synchronous writeout, in + * which case we need just need to re-add the flag here. */ - if (bp->b_queuetime < jiffies - age) - return; - bp->b_queuetime = jiffies - age; - spin_lock(&btp->bt_delwri_lock); - list_move(&bp->b_list, &btp->bt_delwri_queue); - spin_unlock(&btp->bt_delwri_lock); -} - -/* - * Move as many buffers as specified to the supplied list - * idicating if we skipped any buffers to prevent deadlocks. - */ -STATIC int -xfs_buf_delwri_split( - xfs_buftarg_t *target, - struct list_head *list, - unsigned long age) -{ - xfs_buf_t *bp, *n; - int skipped = 0; - int force; - - force = test_and_clear_bit(XBT_FORCE_FLUSH, &target->bt_flags); - INIT_LIST_HEAD(list); - spin_lock(&target->bt_delwri_lock); - list_for_each_entry_safe(bp, n, &target->bt_delwri_queue, b_list) { - ASSERT(bp->b_flags & XBF_DELWRI); - - if (!xfs_buf_ispinned(bp) && xfs_buf_trylock(bp)) { - if (!force && - time_before(jiffies, bp->b_queuetime + age)) { - xfs_buf_unlock(bp); - break; - } - - bp->b_flags &= ~(XBF_DELWRI | _XBF_DELWRI_Q); - bp->b_flags |= XBF_WRITE; - list_move_tail(&bp->b_list, list); - trace_xfs_buf_delwri_split(bp, _RET_IP_); - } else - skipped++; + bp->b_flags |= _XBF_DELWRI_Q; + if (list_empty(&bp->b_list)) { + atomic_inc(&bp->b_hold); + list_add_tail(&bp->b_list, list); } - spin_unlock(&target->bt_delwri_lock); - return skipped; + return true; } /* @@ -1683,99 +1572,109 @@ xfs_buf_cmp( return 0; } -STATIC int -xfsbufd( - void *data) +static int +__xfs_buf_delwri_submit( + struct list_head *buffer_list, + struct list_head *io_list, + bool wait) { - xfs_buftarg_t *target = (xfs_buftarg_t *)data; - - current->flags |= PF_MEMALLOC; - - set_freezable(); + struct blk_plug plug; + struct xfs_buf *bp, *n; + int pinned = 0; + + list_for_each_entry_safe(bp, n, buffer_list, b_list) { + if (!wait) { + if (xfs_buf_ispinned(bp)) { + pinned++; + continue; + } + if (!xfs_buf_trylock(bp)) + continue; + } else { + xfs_buf_lock(bp); + } - do { - long age = xfs_buf_age_centisecs * msecs_to_jiffies(10); - long tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10); - struct list_head tmp; - struct blk_plug plug; + /* + * Someone else might have written the buffer synchronously or + * marked it stale in the meantime. In that case only the + * _XBF_DELWRI_Q flag got cleared, and we have to drop the + * reference and remove it from the list here. + */ + if (!(bp->b_flags & _XBF_DELWRI_Q)) { + list_del_init(&bp->b_list); + xfs_buf_relse(bp); + continue; + } - if (unlikely(freezing(current))) - try_to_freeze(); + list_move_tail(&bp->b_list, io_list); + trace_xfs_buf_delwri_split(bp, _RET_IP_); + } - /* sleep for a long time if there is nothing to do. */ - if (list_empty(&target->bt_delwri_queue)) - tout = MAX_SCHEDULE_TIMEOUT; - schedule_timeout_interruptible(tout); + list_sort(NULL, io_list, xfs_buf_cmp); - xfs_buf_delwri_split(target, &tmp, age); - list_sort(NULL, &tmp, xfs_buf_cmp); + blk_start_plug(&plug); + list_for_each_entry_safe(bp, n, io_list, b_list) { + bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC); + bp->b_flags |= XBF_WRITE; - blk_start_plug(&plug); - while (!list_empty(&tmp)) { - struct xfs_buf *bp; - bp = list_first_entry(&tmp, struct xfs_buf, b_list); + if (!wait) { + bp->b_flags |= XBF_ASYNC; list_del_init(&bp->b_list); - xfs_bdstrat_cb(bp); } - blk_finish_plug(&plug); - } while (!kthread_should_stop()); + xfs_bdstrat_cb(bp); + } + blk_finish_plug(&plug); - return 0; + return pinned; } /* - * Go through all incore buffers, and release buffers if they belong to - * the given device. This is used in filesystem error handling to - * preserve the consistency of its metadata. + * Write out a buffer list asynchronously. + * + * This will take the @buffer_list, write all non-locked and non-pinned buffers + * out and not wait for I/O completion on any of the buffers. This interface + * is only safely useable for callers that can track I/O completion by higher + * level means, e.g. AIL pushing as the @buffer_list is consumed in this + * function. */ int -xfs_flush_buftarg( - xfs_buftarg_t *target, - int wait) +xfs_buf_delwri_submit_nowait( + struct list_head *buffer_list) { - xfs_buf_t *bp; - int pincount = 0; - LIST_HEAD(tmp_list); - LIST_HEAD(wait_list); - struct blk_plug plug; + LIST_HEAD (io_list); + return __xfs_buf_delwri_submit(buffer_list, &io_list, false); +} - flush_workqueue(xfslogd_workqueue); +/* + * Write out a buffer list synchronously. + * + * This will take the @buffer_list, write all buffers out and wait for I/O + * completion on all of the buffers. @buffer_list is consumed by the function, + * so callers must have some other way of tracking buffers if they require such + * functionality. + */ +int +xfs_buf_delwri_submit( + struct list_head *buffer_list) +{ + LIST_HEAD (io_list); + int error = 0, error2; + struct xfs_buf *bp; - set_bit(XBT_FORCE_FLUSH, &target->bt_flags); - pincount = xfs_buf_delwri_split(target, &tmp_list, 0); + __xfs_buf_delwri_submit(buffer_list, &io_list, true); - /* - * Dropped the delayed write list lock, now walk the temporary list. - * All I/O is issued async and then if we need to wait for completion - * we do that after issuing all the IO. - */ - list_sort(NULL, &tmp_list, xfs_buf_cmp); + /* Wait for IO to complete. */ + while (!list_empty(&io_list)) { + bp = list_first_entry(&io_list, struct xfs_buf, b_list); - blk_start_plug(&plug); - while (!list_empty(&tmp_list)) { - bp = list_first_entry(&tmp_list, struct xfs_buf, b_list); - ASSERT(target == bp->b_target); list_del_init(&bp->b_list); - if (wait) { - bp->b_flags &= ~XBF_ASYNC; - list_add(&bp->b_list, &wait_list); - } - xfs_bdstrat_cb(bp); - } - blk_finish_plug(&plug); - - if (wait) { - /* Wait for IO to complete. */ - while (!list_empty(&wait_list)) { - bp = list_first_entry(&wait_list, struct xfs_buf, b_list); - - list_del_init(&bp->b_list); - xfs_buf_iowait(bp); - xfs_buf_relse(bp); - } + error2 = xfs_buf_iowait(bp); + xfs_buf_relse(bp); + if (!error) + error = error2; } - return pincount; + return error; } int __init diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 5bf3be45f54..7f1d1392ce3 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -32,11 +32,6 @@ #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) -#define xfs_buf_ctob(pp) ((pp) * PAGE_CACHE_SIZE) -#define xfs_buf_btoc(dd) (((dd) + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) -#define xfs_buf_btoct(dd) ((dd) >> PAGE_CACHE_SHIFT) -#define xfs_buf_poff(aa) ((aa) & ~PAGE_CACHE_MASK) - typedef enum { XBRW_READ = 1, /* transfer into target memory */ XBRW_WRITE = 2, /* transfer from target memory */ @@ -46,11 +41,9 @@ typedef enum { #define XBF_READ (1 << 0) /* buffer intended for reading from device */ #define XBF_WRITE (1 << 1) /* buffer intended for writing to device */ #define XBF_READ_AHEAD (1 << 2) /* asynchronous read-ahead */ -#define XBF_MAPPED (1 << 3) /* buffer mapped (b_addr valid) */ #define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */ #define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */ -#define XBF_DELWRI (1 << 6) /* buffer has dirty pages */ -#define XBF_STALE (1 << 7) /* buffer has been staled, do not find it */ +#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */ /* I/O hints for the BIO layer */ #define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */ @@ -58,14 +51,13 @@ typedef enum { #define XBF_FLUSH (1 << 12)/* flush the disk cache before a write */ /* flags used only as arguments to access routines */ -#define XBF_LOCK (1 << 15)/* lock requested */ #define XBF_TRYLOCK (1 << 16)/* lock requested, but do not wait */ -#define XBF_DONT_BLOCK (1 << 17)/* do not block in current thread */ +#define XBF_UNMAPPED (1 << 17)/* do not map the buffer */ /* flags used only internally */ #define _XBF_PAGES (1 << 20)/* backed by refcounted pages */ #define _XBF_KMEM (1 << 21)/* backed by heap memory */ -#define _XBF_DELWRI_Q (1 << 22)/* buffer on delwri queue */ +#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ typedef unsigned int xfs_buf_flags_t; @@ -73,25 +65,18 @@ typedef unsigned int xfs_buf_flags_t; { XBF_READ, "READ" }, \ { XBF_WRITE, "WRITE" }, \ { XBF_READ_AHEAD, "READ_AHEAD" }, \ - { XBF_MAPPED, "MAPPED" }, \ { XBF_ASYNC, "ASYNC" }, \ { XBF_DONE, "DONE" }, \ - { XBF_DELWRI, "DELWRI" }, \ { XBF_STALE, "STALE" }, \ { XBF_SYNCIO, "SYNCIO" }, \ { XBF_FUA, "FUA" }, \ { XBF_FLUSH, "FLUSH" }, \ - { XBF_LOCK, "LOCK" }, /* should never be set */\ - { XBF_TRYLOCK, "TRYLOCK" }, /* ditto */\ - { XBF_DONT_BLOCK, "DONT_BLOCK" }, /* ditto */\ + { XBF_TRYLOCK, "TRYLOCK" }, /* should never be set */\ + { XBF_UNMAPPED, "UNMAPPED" }, /* ditto */\ { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" } -typedef enum { - XBT_FORCE_FLUSH = 0, -} xfs_buftarg_flags_t; - typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; @@ -101,12 +86,6 @@ typedef struct xfs_buftarg { unsigned int bt_sshift; size_t bt_smask; - /* per device delwri queue */ - struct task_struct *bt_task; - struct list_head bt_delwri_queue; - spinlock_t bt_delwri_lock; - unsigned long bt_flags; - /* LRU control structures */ struct shrinker bt_shrinker; struct list_head bt_lru; @@ -128,8 +107,8 @@ typedef struct xfs_buf { * fast-path on locking. */ struct rb_node b_rbnode; /* rbtree node */ - xfs_off_t b_file_offset; /* offset in file */ - size_t b_buffer_length;/* size of buffer in bytes */ + xfs_daddr_t b_bn; /* block number for I/O */ + int b_length; /* size of buffer in BBs */ atomic_t b_hold; /* reference count */ atomic_t b_lru_ref; /* lru reclaim ref count */ xfs_buf_flags_t b_flags; /* status flags */ @@ -140,8 +119,6 @@ typedef struct xfs_buf { struct list_head b_list; struct xfs_perag *b_pag; /* contains rbtree root */ xfs_buftarg_t *b_target; /* buffer target (device) */ - xfs_daddr_t b_bn; /* block number for I/O */ - size_t b_count_desired;/* desired transfer size */ void *b_addr; /* virtual address of buffer */ struct work_struct b_iodone_work; xfs_buf_iodone_t b_iodone; /* I/O completion function */ @@ -150,7 +127,7 @@ typedef struct xfs_buf { struct xfs_trans *b_transp; struct page **b_pages; /* array of page pointers */ struct page *b_page_array[XB_PAGES]; /* inline pages */ - unsigned long b_queuetime; /* time buffer was queued */ + int b_io_length; /* IO size in BBs */ atomic_t b_pin_count; /* pin count */ atomic_t b_io_remaining; /* #outstanding I/O requests */ unsigned int b_page_count; /* size of page array */ @@ -163,26 +140,30 @@ typedef struct xfs_buf { /* Finding and Reading Buffers */ -extern xfs_buf_t *_xfs_buf_find(xfs_buftarg_t *, xfs_off_t, size_t, - xfs_buf_flags_t, xfs_buf_t *); +struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target, xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags, + struct xfs_buf *new_bp); #define xfs_incore(buftarg,blkno,len,lockit) \ _xfs_buf_find(buftarg, blkno ,len, lockit, NULL) -extern xfs_buf_t *xfs_buf_get(xfs_buftarg_t *, xfs_off_t, size_t, - xfs_buf_flags_t); -extern xfs_buf_t *xfs_buf_read(xfs_buftarg_t *, xfs_off_t, size_t, - xfs_buf_flags_t); - -struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *, xfs_off_t, size_t, - xfs_buf_flags_t); -extern void xfs_buf_set_empty(struct xfs_buf *bp, size_t len); -extern xfs_buf_t *xfs_buf_get_uncached(struct xfs_buftarg *, size_t, int); -extern int xfs_buf_associate_memory(xfs_buf_t *, void *, size_t); -extern void xfs_buf_hold(xfs_buf_t *); -extern void xfs_buf_readahead(xfs_buftarg_t *, xfs_off_t, size_t); -struct xfs_buf *xfs_buf_read_uncached(struct xfs_mount *mp, - struct xfs_buftarg *target, - xfs_daddr_t daddr, size_t length, int flags); +struct xfs_buf *xfs_buf_get(struct xfs_buftarg *target, xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags); +struct xfs_buf *xfs_buf_read(struct xfs_buftarg *target, xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags); +void xfs_buf_readahead(struct xfs_buftarg *target, xfs_daddr_t blkno, + size_t numblks); + +struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks); +struct xfs_buf *xfs_buf_alloc(struct xfs_buftarg *target, xfs_daddr_t blkno, + size_t numblks, xfs_buf_flags_t flags); +void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks); +int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length); + +struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks, + int flags); +struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target, + xfs_daddr_t daddr, size_t numblks, int flags); +void xfs_buf_hold(struct xfs_buf *bp); /* Releasing Buffers */ extern void xfs_buf_free(xfs_buf_t *); @@ -204,7 +185,7 @@ extern int xfs_bdstrat_cb(struct xfs_buf *); extern void xfs_buf_ioend(xfs_buf_t *, int); extern void xfs_buf_ioerror(xfs_buf_t *, int); extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func); -extern int xfs_buf_iorequest(xfs_buf_t *); +extern void xfs_buf_iorequest(xfs_buf_t *); extern int xfs_buf_iowait(xfs_buf_t *); extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *, xfs_buf_rw_t); @@ -220,24 +201,22 @@ static inline int xfs_buf_geterror(xfs_buf_t *bp) extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t); /* Delayed Write Buffer Routines */ -extern void xfs_buf_delwri_queue(struct xfs_buf *); -extern void xfs_buf_delwri_dequeue(struct xfs_buf *); -extern void xfs_buf_delwri_promote(struct xfs_buf *); +extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); +extern int xfs_buf_delwri_submit(struct list_head *); +extern int xfs_buf_delwri_submit_nowait(struct list_head *); /* Buffer Daemon Setup Routines */ extern int xfs_buf_init(void); extern void xfs_buf_terminate(void); #define XFS_BUF_ZEROFLAGS(bp) \ - ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \ + ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \ XBF_SYNCIO|XBF_FUA|XBF_FLUSH)) void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE) #define XFS_BUF_ISSTALE(bp) ((bp)->b_flags & XBF_STALE) -#define XFS_BUF_ISDELAYWRITE(bp) ((bp)->b_flags & XBF_DELWRI) - #define XFS_BUF_DONE(bp) ((bp)->b_flags |= XBF_DONE) #define XFS_BUF_UNDONE(bp) ((bp)->b_flags &= ~XBF_DONE) #define XFS_BUF_ISDONE(bp) ((bp)->b_flags & XBF_DONE) @@ -256,12 +235,6 @@ void xfs_buf_stale(struct xfs_buf *bp); #define XFS_BUF_ADDR(bp) ((bp)->b_bn) #define XFS_BUF_SET_ADDR(bp, bno) ((bp)->b_bn = (xfs_daddr_t)(bno)) -#define XFS_BUF_OFFSET(bp) ((bp)->b_file_offset) -#define XFS_BUF_SET_OFFSET(bp, off) ((bp)->b_file_offset = (off)) -#define XFS_BUF_COUNT(bp) ((bp)->b_count_desired) -#define XFS_BUF_SET_COUNT(bp, cnt) ((bp)->b_count_desired = (cnt)) -#define XFS_BUF_SIZE(bp) ((bp)->b_buffer_length) -#define XFS_BUF_SET_SIZE(bp, cnt) ((bp)->b_buffer_length = (cnt)) static inline void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref) { @@ -287,7 +260,6 @@ extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *, extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *); extern void xfs_wait_buftarg(xfs_buftarg_t *); extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int); -extern int xfs_flush_buftarg(xfs_buftarg_t *, int); #define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index eac97ef81e2..45df2b857d4 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -123,11 +122,11 @@ xfs_buf_item_log_check( ASSERT(bip->bli_logged != NULL); bp = bip->bli_buf; - ASSERT(XFS_BUF_COUNT(bp) > 0); + ASSERT(bp->b_length > 0); ASSERT(bp->b_addr != NULL); orig = bip->bli_orig; buffer = bp->b_addr; - for (x = 0; x < XFS_BUF_COUNT(bp); x++) { + for (x = 0; x < BBTOB(bp->b_length); x++) { if (orig[x] != buffer[x] && !btst(bip->bli_logged, x)) { xfs_emerg(bp->b_mount, "%s: bip %x buffer %x orig %x index %d", @@ -418,7 +417,6 @@ xfs_buf_item_unpin( if (freed && stale) { ASSERT(bip->bli_flags & XFS_BLI_STALE); ASSERT(xfs_buf_islocked(bp)); - ASSERT(!(XFS_BUF_ISDELAYWRITE(bp))); ASSERT(XFS_BUF_ISSTALE(bp)); ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL); @@ -455,42 +453,42 @@ xfs_buf_item_unpin( bp->b_iodone = NULL; } else { spin_lock(&ailp->xa_lock); - xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip); + xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR); xfs_buf_item_relse(bp); ASSERT(bp->b_fspriv == NULL); } xfs_buf_relse(bp); + } else if (freed && remove) { + xfs_buf_lock(bp); + xfs_buf_ioerror(bp, EIO); + XFS_BUF_UNDONE(bp); + xfs_buf_stale(bp); + xfs_buf_ioend(bp, 0); } } -/* - * This is called to attempt to lock the buffer associated with this - * buf log item. Don't sleep on the buffer lock. If we can't get - * the lock right away, return 0. If we can get the lock, take a - * reference to the buffer. If this is a delayed write buffer that - * needs AIL help to be written back, invoke the pushbuf routine - * rather than the normal success path. - */ STATIC uint -xfs_buf_item_trylock( - struct xfs_log_item *lip) +xfs_buf_item_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; + uint rval = XFS_ITEM_SUCCESS; if (xfs_buf_ispinned(bp)) return XFS_ITEM_PINNED; if (!xfs_buf_trylock(bp)) return XFS_ITEM_LOCKED; - /* take a reference to the buffer. */ - xfs_buf_hold(bp); - ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); - trace_xfs_buf_item_trylock(bip); - if (XFS_BUF_ISDELAYWRITE(bp)) - return XFS_ITEM_PUSHBUF; - return XFS_ITEM_SUCCESS; + + trace_xfs_buf_item_push(bip); + + if (!xfs_buf_delwri_queue(bp, buffer_list)) + rval = XFS_ITEM_FLUSHING; + xfs_buf_unlock(bp); + return rval; } /* @@ -603,49 +601,6 @@ xfs_buf_item_committed( return lsn; } -/* - * The buffer is locked, but is not a delayed write buffer. This happens - * if we race with IO completion and hence we don't want to try to write it - * again. Just release the buffer. - */ -STATIC void -xfs_buf_item_push( - struct xfs_log_item *lip) -{ - struct xfs_buf_log_item *bip = BUF_ITEM(lip); - struct xfs_buf *bp = bip->bli_buf; - - ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); - ASSERT(!XFS_BUF_ISDELAYWRITE(bp)); - - trace_xfs_buf_item_push(bip); - - xfs_buf_relse(bp); -} - -/* - * The buffer is locked and is a delayed write buffer. Promote the buffer - * in the delayed write queue as the caller knows that they must invoke - * the xfsbufd to get this buffer written. We have to unlock the buffer - * to allow the xfsbufd to write it, too. - */ -STATIC bool -xfs_buf_item_pushbuf( - struct xfs_log_item *lip) -{ - struct xfs_buf_log_item *bip = BUF_ITEM(lip); - struct xfs_buf *bp = bip->bli_buf; - - ASSERT(!(bip->bli_flags & XFS_BLI_STALE)); - ASSERT(XFS_BUF_ISDELAYWRITE(bp)); - - trace_xfs_buf_item_pushbuf(bip); - - xfs_buf_delwri_promote(bp); - xfs_buf_relse(bp); - return true; -} - STATIC void xfs_buf_item_committing( struct xfs_log_item *lip, @@ -661,11 +616,9 @@ static const struct xfs_item_ops xfs_buf_item_ops = { .iop_format = xfs_buf_item_format, .iop_pin = xfs_buf_item_pin, .iop_unpin = xfs_buf_item_unpin, - .iop_trylock = xfs_buf_item_trylock, .iop_unlock = xfs_buf_item_unlock, .iop_committed = xfs_buf_item_committed, .iop_push = xfs_buf_item_push, - .iop_pushbuf = xfs_buf_item_pushbuf, .iop_committing = xfs_buf_item_committing }; @@ -703,7 +656,8 @@ xfs_buf_item_init( * truncate any pieces. map_size is the size of the * bitmap needed to describe the chunks of the buffer. */ - chunks = (int)((XFS_BUF_COUNT(bp) + (XFS_BLF_CHUNK - 1)) >> XFS_BLF_SHIFT); + chunks = (int)((BBTOB(bp->b_length) + (XFS_BLF_CHUNK - 1)) >> + XFS_BLF_SHIFT); map_size = (int)((chunks + NBWORD) >> BIT_TO_WORD_SHIFT); bip = (xfs_buf_log_item_t*)kmem_zone_zalloc(xfs_buf_item_zone, @@ -713,7 +667,7 @@ xfs_buf_item_init( xfs_buf_hold(bp); bip->bli_format.blf_type = XFS_LI_BUF; bip->bli_format.blf_blkno = (__int64_t)XFS_BUF_ADDR(bp); - bip->bli_format.blf_len = (ushort)BTOBB(XFS_BUF_COUNT(bp)); + bip->bli_format.blf_len = (ushort)bp->b_length; bip->bli_format.blf_map_size = map_size; #ifdef XFS_TRANS_DEBUG @@ -725,9 +679,9 @@ xfs_buf_item_init( * the buffer to indicate which bytes the callers have asked * to have logged. */ - bip->bli_orig = (char *)kmem_alloc(XFS_BUF_COUNT(bp), KM_SLEEP); - memcpy(bip->bli_orig, bp->b_addr, XFS_BUF_COUNT(bp)); - bip->bli_logged = (char *)kmem_zalloc(XFS_BUF_COUNT(bp) / NBBY, KM_SLEEP); + bip->bli_orig = kmem_alloc(BBTOB(bp->b_length), KM_SLEEP); + memcpy(bip->bli_orig, bp->b_addr, BBTOB(bp->b_length)); + bip->bli_logged = kmem_zalloc(BBTOB(bp->b_length) / NBBY, KM_SLEEP); #endif /* @@ -984,20 +938,27 @@ xfs_buf_iodone_callbacks( * If the write was asynchronous then no one will be looking for the * error. Clear the error state and write the buffer out again. * - * During sync or umount we'll write all pending buffers again - * synchronous, which will catch these errors if they keep hanging - * around. + * XXX: This helps against transient write errors, but we need to find + * a way to shut the filesystem down if the writes keep failing. + * + * In practice we'll shut the filesystem down soon as non-transient + * erorrs tend to affect the whole device and a failing log write + * will make us give up. But we really ought to do better here. */ if (XFS_BUF_ISASYNC(bp)) { + ASSERT(bp->b_iodone != NULL); + + trace_xfs_buf_item_iodone_async(bp, _RET_IP_); + xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */ if (!XFS_BUF_ISSTALE(bp)) { - xfs_buf_delwri_queue(bp); - XFS_BUF_DONE(bp); + bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE; + xfs_bdstrat_cb(bp); + } else { + xfs_buf_relse(bp); } - ASSERT(bp->b_iodone != NULL); - trace_xfs_buf_item_iodone_async(bp, _RET_IP_); - xfs_buf_relse(bp); + return; } @@ -1045,6 +1006,6 @@ xfs_buf_iodone( * Either way, AIL is useless if we're forcing a shutdown. */ spin_lock(&ailp->xa_lock); - xfs_trans_ail_delete(ailp, lip); + xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); xfs_buf_item_free(BUF_ITEM(lip)); } diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c index 7f1a6f5b05a..015b946c580 100644 --- a/fs/xfs/xfs_da_btree.c +++ b/fs/xfs/xfs_da_btree.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -2277,20 +2276,20 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps) if (nbuf == 1) { dabuf->nbuf = 1; bp = bps[0]; - dabuf->bbcount = (short)BTOBB(XFS_BUF_COUNT(bp)); + dabuf->bbcount = bp->b_length; dabuf->data = bp->b_addr; dabuf->bps[0] = bp; } else { dabuf->nbuf = nbuf; for (i = 0, dabuf->bbcount = 0; i < nbuf; i++) { dabuf->bps[i] = bp = bps[i]; - dabuf->bbcount += BTOBB(XFS_BUF_COUNT(bp)); + dabuf->bbcount += bp->b_length; } dabuf->data = kmem_alloc(BBTOB(dabuf->bbcount), KM_SLEEP); - for (i = off = 0; i < nbuf; i++, off += XFS_BUF_COUNT(bp)) { + for (i = off = 0; i < nbuf; i++, off += BBTOB(bp->b_length)) { bp = bps[i]; memcpy((char *)dabuf->data + off, bp->b_addr, - XFS_BUF_COUNT(bp)); + BBTOB(bp->b_length)); } } return dabuf; @@ -2310,10 +2309,10 @@ xfs_da_buf_clean(xfs_dabuf_t *dabuf) ASSERT(dabuf->nbuf > 1); dabuf->dirty = 0; for (i = off = 0; i < dabuf->nbuf; - i++, off += XFS_BUF_COUNT(bp)) { + i++, off += BBTOB(bp->b_length)) { bp = dabuf->bps[i]; memcpy(bp->b_addr, dabuf->data + off, - XFS_BUF_COUNT(bp)); + BBTOB(bp->b_length)); } } } @@ -2356,10 +2355,10 @@ xfs_da_log_buf(xfs_trans_t *tp, xfs_dabuf_t *dabuf, uint first, uint last) } dabuf->dirty = 1; ASSERT(first <= last); - for (i = off = 0; i < dabuf->nbuf; i++, off += XFS_BUF_COUNT(bp)) { + for (i = off = 0; i < dabuf->nbuf; i++, off += BBTOB(bp->b_length)) { bp = dabuf->bps[i]; f = off; - l = f + XFS_BUF_COUNT(bp) - 1; + l = f + BBTOB(bp->b_length) - 1; if (f < first) f = first; if (l > last) diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c index 1137bbc5ecc..e00de08dc8a 100644 --- a/fs/xfs/xfs_dfrag.c +++ b/fs/xfs/xfs_dfrag.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c index a2e27010c7f..67a250c36d4 100644 --- a/fs/xfs/xfs_dir2.c +++ b/fs/xfs/xfs_dir2.c @@ -18,7 +18,6 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c index d3b63aefd01..586732f2d80 100644 --- a/fs/xfs/xfs_dir2_block.c +++ b/fs/xfs/xfs_dir2_block.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_dir2_data.c b/fs/xfs/xfs_dir2_data.c index 5bbe2a8a023..2046988e9eb 100644 --- a/fs/xfs/xfs_dir2_data.c +++ b/fs/xfs/xfs_dir2_data.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c index 66e108f561a..397ffbcbab1 100644 --- a/fs/xfs/xfs_dir2_leaf.c +++ b/fs/xfs/xfs_dir2_leaf.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c index 0179a41d9e5..b0f26780449 100644 --- a/fs/xfs/xfs_dir2_node.c +++ b/fs/xfs/xfs_dir2_node.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c index 79d05e84e29..19bf0c5e38f 100644 --- a/fs/xfs/xfs_dir2_sf.c +++ b/fs/xfs/xfs_dir2_sf.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 1ad3a4b8ca4..f9c3fe304a1 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -17,7 +17,6 @@ */ #include "xfs.h" #include "xfs_sb.h" -#include "xfs_inum.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_mount.h" @@ -30,6 +29,7 @@ #include "xfs_inode.h" #include "xfs_alloc.h" #include "xfs_error.h" +#include "xfs_extent_busy.h" #include "xfs_discard.h" #include "xfs_trace.h" @@ -118,7 +118,7 @@ xfs_trim_extents( * If any blocks in the range are still busy, skip the * discard and try again the next time. */ - if (xfs_alloc_busy_search(mp, agno, fbno, flen)) { + if (xfs_extent_busy_search(mp, agno, fbno, flen)) { trace_xfs_discard_busy(mp, agno, fbno, flen); goto next_extent; } @@ -212,7 +212,7 @@ xfs_discard_extents( struct xfs_mount *mp, struct list_head *list) { - struct xfs_busy_extent *busyp; + struct xfs_extent_busy *busyp; int error = 0; list_for_each_entry(busyp, list, list) { diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index 1155208fa83..bf27fcca484 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -857,7 +856,7 @@ xfs_qm_dqflush_done( /* xfs_trans_ail_delete() drops the AIL lock. */ spin_lock(&ailp->xa_lock); if (lip->li_lsn == qip->qli_flush_lsn) - xfs_trans_ail_delete(ailp, lip); + xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); else spin_unlock(&ailp->xa_lock); } @@ -878,8 +877,8 @@ xfs_qm_dqflush_done( */ int xfs_qm_dqflush( - xfs_dquot_t *dqp, - uint flags) + struct xfs_dquot *dqp, + struct xfs_buf **bpp) { struct xfs_mount *mp = dqp->q_mount; struct xfs_buf *bp; @@ -891,25 +890,30 @@ xfs_qm_dqflush( trace_xfs_dqflush(dqp); - /* - * If not dirty, or it's pinned and we are not supposed to block, nada. - */ - if (!XFS_DQ_IS_DIRTY(dqp) || - ((flags & SYNC_TRYLOCK) && atomic_read(&dqp->q_pincount) > 0)) { - xfs_dqfunlock(dqp); - return 0; - } + *bpp = NULL; + xfs_qm_dqunpin_wait(dqp); /* * This may have been unpinned because the filesystem is shutting * down forcibly. If that's the case we must not write this dquot - * to disk, because the log record didn't make it to disk! + * to disk, because the log record didn't make it to disk. + * + * We also have to remove the log item from the AIL in this case, + * as we wait for an emptry AIL as part of the unmount process. */ if (XFS_FORCED_SHUTDOWN(mp)) { + struct xfs_log_item *lip = &dqp->q_logitem.qli_item; dqp->dq_flags &= ~XFS_DQ_DIRTY; - xfs_dqfunlock(dqp); - return XFS_ERROR(EIO); + + spin_lock(&mp->m_ail->xa_lock); + if (lip->li_flags & XFS_LI_IN_AIL) + xfs_trans_ail_delete(mp->m_ail, lip, + SHUTDOWN_CORRUPT_INCORE); + else + spin_unlock(&mp->m_ail->xa_lock); + error = XFS_ERROR(EIO); + goto out_unlock; } /* @@ -917,11 +921,8 @@ xfs_qm_dqflush( */ error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, mp->m_quotainfo->qi_dqchunklen, 0, &bp); - if (error) { - ASSERT(error != ENOENT); - xfs_dqfunlock(dqp); - return error; - } + if (error) + goto out_unlock; /* * Calculate the location of the dquot inside the buffer. @@ -967,20 +968,13 @@ xfs_qm_dqflush( xfs_log_force(mp, 0); } - if (flags & SYNC_WAIT) - error = xfs_bwrite(bp); - else - xfs_buf_delwri_queue(bp); - - xfs_buf_relse(bp); - trace_xfs_dqflush_done(dqp); + *bpp = bp; + return 0; - /* - * dqp is still locked, but caller is free to unlock it now. - */ - return error; - +out_unlock: + xfs_dqfunlock(dqp); + return XFS_ERROR(EIO); } /* @@ -1011,39 +1005,6 @@ xfs_dqlock2( } } -/* - * Give the buffer a little push if it is incore and - * wait on the flush lock. - */ -void -xfs_dqflock_pushbuf_wait( - xfs_dquot_t *dqp) -{ - xfs_mount_t *mp = dqp->q_mount; - xfs_buf_t *bp; - - /* - * Check to see if the dquot has been flushed delayed - * write. If so, grab its buffer and send it - * out immediately. We'll be able to acquire - * the flush lock when the I/O completes. - */ - bp = xfs_incore(mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK); - if (!bp) - goto out_lock; - - if (XFS_BUF_ISDELAYWRITE(bp)) { - if (xfs_buf_ispinned(bp)) - xfs_log_force(mp, 0); - xfs_buf_delwri_promote(bp); - wake_up_process(bp->b_target->bt_task); - } - xfs_buf_relse(bp); -out_lock: - xfs_dqflock(dqp); -} - int __init xfs_qm_init(void) { diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index ef9190bd8b3..7d20af27346 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -141,7 +141,7 @@ static inline xfs_dquot_t *xfs_inode_dquot(struct xfs_inode *ip, int type) extern int xfs_qm_dqread(struct xfs_mount *, xfs_dqid_t, uint, uint, struct xfs_dquot **); extern void xfs_qm_dqdestroy(xfs_dquot_t *); -extern int xfs_qm_dqflush(xfs_dquot_t *, uint); +extern int xfs_qm_dqflush(struct xfs_dquot *, struct xfs_buf **); extern void xfs_qm_dqunpin_wait(xfs_dquot_t *); extern void xfs_qm_adjust_dqtimers(xfs_mount_t *, xfs_disk_dquot_t *); @@ -152,7 +152,6 @@ extern int xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *, extern void xfs_qm_dqput(xfs_dquot_t *); extern void xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *); -extern void xfs_dqflock_pushbuf_wait(struct xfs_dquot *dqp); static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp) { diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 34baeae4526..57aa4b03720 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -108,38 +106,6 @@ xfs_qm_dquot_logitem_unpin( wake_up(&dqp->q_pinwait); } -/* - * Given the logitem, this writes the corresponding dquot entry to disk - * asynchronously. This is called with the dquot entry securely locked; - * we simply get xfs_qm_dqflush() to do the work, and unlock the dquot - * at the end. - */ -STATIC void -xfs_qm_dquot_logitem_push( - struct xfs_log_item *lip) -{ - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; - int error; - - ASSERT(XFS_DQ_IS_LOCKED(dqp)); - ASSERT(!completion_done(&dqp->q_flush)); - - /* - * Since we were able to lock the dquot's flush lock and - * we found it on the AIL, the dquot must be dirty. This - * is because the dquot is removed from the AIL while still - * holding the flush lock in xfs_dqflush_done(). Thus, if - * we found it in the AIL and were able to obtain the flush - * lock without sleeping, then there must not have been - * anyone in the process of flushing the dquot. - */ - error = xfs_qm_dqflush(dqp, SYNC_TRYLOCK); - if (error) - xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p", - __func__, error, dqp); - xfs_dqunlock(dqp); -} - STATIC xfs_lsn_t xfs_qm_dquot_logitem_committed( struct xfs_log_item *lip, @@ -171,67 +137,15 @@ xfs_qm_dqunpin_wait( wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0)); } -/* - * This is called when IOP_TRYLOCK returns XFS_ITEM_PUSHBUF to indicate that - * the dquot is locked by us, but the flush lock isn't. So, here we are - * going to see if the relevant dquot buffer is incore, waiting on DELWRI. - * If so, we want to push it out to help us take this item off the AIL as soon - * as possible. - * - * We must not be holding the AIL lock at this point. Calling incore() to - * search the buffer cache can be a time consuming thing, and AIL lock is a - * spinlock. - */ -STATIC bool -xfs_qm_dquot_logitem_pushbuf( - struct xfs_log_item *lip) -{ - struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); - struct xfs_dquot *dqp = qlip->qli_dquot; - struct xfs_buf *bp; - bool ret = true; - - ASSERT(XFS_DQ_IS_LOCKED(dqp)); - - /* - * If flushlock isn't locked anymore, chances are that the - * inode flush completed and the inode was taken off the AIL. - * So, just get out. - */ - if (completion_done(&dqp->q_flush) || - !(lip->li_flags & XFS_LI_IN_AIL)) { - xfs_dqunlock(dqp); - return true; - } - - bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno, - dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK); - xfs_dqunlock(dqp); - if (!bp) - return true; - if (XFS_BUF_ISDELAYWRITE(bp)) - xfs_buf_delwri_promote(bp); - if (xfs_buf_ispinned(bp)) - ret = false; - xfs_buf_relse(bp); - return ret; -} - -/* - * This is called to attempt to lock the dquot associated with this - * dquot log item. Don't sleep on the dquot lock or the flush lock. - * If the flush lock is already held, indicating that the dquot has - * been or is in the process of being flushed, then see if we can - * find the dquot's buffer in the buffer cache without sleeping. If - * we can and it is marked delayed write, then we want to send it out. - * We delay doing so until the push routine, though, to avoid sleeping - * in any device strategy routines. - */ STATIC uint -xfs_qm_dquot_logitem_trylock( - struct xfs_log_item *lip) +xfs_qm_dquot_logitem_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; + struct xfs_buf *bp = NULL; + uint rval = XFS_ITEM_SUCCESS; + int error; if (atomic_read(&dqp->q_pincount) > 0) return XFS_ITEM_PINNED; @@ -239,16 +153,41 @@ xfs_qm_dquot_logitem_trylock( if (!xfs_dqlock_nowait(dqp)) return XFS_ITEM_LOCKED; + /* + * Re-check the pincount now that we stabilized the value by + * taking the quota lock. + */ + if (atomic_read(&dqp->q_pincount) > 0) { + rval = XFS_ITEM_PINNED; + goto out_unlock; + } + + /* + * Someone else is already flushing the dquot. Nothing we can do + * here but wait for the flush to finish and remove the item from + * the AIL. + */ if (!xfs_dqflock_nowait(dqp)) { - /* - * dquot has already been flushed to the backing buffer, - * leave it locked, pushbuf routine will unlock it. - */ - return XFS_ITEM_PUSHBUF; + rval = XFS_ITEM_FLUSHING; + goto out_unlock; } - ASSERT(lip->li_flags & XFS_LI_IN_AIL); - return XFS_ITEM_SUCCESS; + spin_unlock(&lip->li_ailp->xa_lock); + + error = xfs_qm_dqflush(dqp, &bp); + if (error) { + xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p", + __func__, error, dqp); + } else { + if (!xfs_buf_delwri_queue(bp, buffer_list)) + rval = XFS_ITEM_FLUSHING; + xfs_buf_relse(bp); + } + + spin_lock(&lip->li_ailp->xa_lock); +out_unlock: + xfs_dqunlock(dqp); + return rval; } /* @@ -299,11 +238,9 @@ static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_format = xfs_qm_dquot_logitem_format, .iop_pin = xfs_qm_dquot_logitem_pin, .iop_unpin = xfs_qm_dquot_logitem_unpin, - .iop_trylock = xfs_qm_dquot_logitem_trylock, .iop_unlock = xfs_qm_dquot_logitem_unlock, .iop_committed = xfs_qm_dquot_logitem_committed, .iop_push = xfs_qm_dquot_logitem_push, - .iop_pushbuf = xfs_qm_dquot_logitem_pushbuf, .iop_committing = xfs_qm_dquot_logitem_committing }; @@ -398,11 +335,13 @@ xfs_qm_qoff_logitem_unpin( } /* - * Quotaoff items have no locking, so just return success. + * There isn't much you can do to push a quotaoff item. It is simply + * stuck waiting for the log to be flushed to disk. */ STATIC uint -xfs_qm_qoff_logitem_trylock( - struct xfs_log_item *lip) +xfs_qm_qoff_logitem_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { return XFS_ITEM_LOCKED; } @@ -429,17 +368,6 @@ xfs_qm_qoff_logitem_committed( return lsn; } -/* - * There isn't much you can do to push on an quotaoff item. It is simply - * stuck waiting for the log to be flushed to disk. - */ -STATIC void -xfs_qm_qoff_logitem_push( - struct xfs_log_item *lip) -{ -} - - STATIC xfs_lsn_t xfs_qm_qoffend_logitem_committed( struct xfs_log_item *lip, @@ -454,7 +382,7 @@ xfs_qm_qoffend_logitem_committed( * xfs_trans_ail_delete() drops the AIL lock. */ spin_lock(&ailp->xa_lock); - xfs_trans_ail_delete(ailp, (xfs_log_item_t *)qfs); + xfs_trans_ail_delete(ailp, &qfs->qql_item, SHUTDOWN_LOG_IO_ERROR); kmem_free(qfs); kmem_free(qfe); @@ -487,7 +415,6 @@ static const struct xfs_item_ops xfs_qm_qoffend_logitem_ops = { .iop_format = xfs_qm_qoff_logitem_format, .iop_pin = xfs_qm_qoff_logitem_pin, .iop_unpin = xfs_qm_qoff_logitem_unpin, - .iop_trylock = xfs_qm_qoff_logitem_trylock, .iop_unlock = xfs_qm_qoff_logitem_unlock, .iop_committed = xfs_qm_qoffend_logitem_committed, .iop_push = xfs_qm_qoff_logitem_push, @@ -502,7 +429,6 @@ static const struct xfs_item_ops xfs_qm_qoff_logitem_ops = { .iop_format = xfs_qm_qoff_logitem_format, .iop_pin = xfs_qm_qoff_logitem_pin, .iop_unpin = xfs_qm_qoff_logitem_unpin, - .iop_trylock = xfs_qm_qoff_logitem_trylock, .iop_unlock = xfs_qm_qoff_logitem_unlock, .iop_committed = xfs_qm_qoff_logitem_committed, .iop_push = xfs_qm_qoff_logitem_push, diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 39f06336b99..610456054dc 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c index 558910f5e3c..42679223a0f 100644 --- a/fs/xfs/xfs_export.c +++ b/fs/xfs/xfs_export.c @@ -17,7 +17,6 @@ */ #include "xfs.h" #include "xfs_types.h" -#include "xfs_inum.h" #include "xfs_log.h" #include "xfs_trans.h" #include "xfs_sb.h" @@ -53,19 +52,18 @@ static int xfs_fileid_length(int fileid_type) STATIC int xfs_fs_encode_fh( - struct dentry *dentry, - __u32 *fh, - int *max_len, - int connectable) + struct inode *inode, + __u32 *fh, + int *max_len, + struct inode *parent) { struct fid *fid = (struct fid *)fh; struct xfs_fid64 *fid64 = (struct xfs_fid64 *)fh; - struct inode *inode = dentry->d_inode; int fileid_type; int len; /* Directories don't need their parent encoded, they have ".." */ - if (S_ISDIR(inode->i_mode) || !connectable) + if (!parent) fileid_type = FILEID_INO32_GEN; else fileid_type = FILEID_INO32_GEN_PARENT; @@ -97,20 +95,16 @@ xfs_fs_encode_fh( switch (fileid_type) { case FILEID_INO32_GEN_PARENT: - spin_lock(&dentry->d_lock); - fid->i32.parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino; - fid->i32.parent_gen = dentry->d_parent->d_inode->i_generation; - spin_unlock(&dentry->d_lock); + fid->i32.parent_ino = XFS_I(parent)->i_ino; + fid->i32.parent_gen = parent->i_generation; /*FALLTHRU*/ case FILEID_INO32_GEN: fid->i32.ino = XFS_I(inode)->i_ino; fid->i32.gen = inode->i_generation; break; case FILEID_INO32_GEN_PARENT | XFS_FILEID_TYPE_64FLAG: - spin_lock(&dentry->d_lock); - fid64->parent_ino = XFS_I(dentry->d_parent->d_inode)->i_ino; - fid64->parent_gen = dentry->d_parent->d_inode->i_generation; - spin_unlock(&dentry->d_lock); + fid64->parent_ino = XFS_I(parent)->i_ino; + fid64->parent_gen = parent->i_generation; /*FALLTHRU*/ case FILEID_INO32_GEN | XFS_FILEID_TYPE_64FLAG: fid64->ino = XFS_I(inode)->i_ino; diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c new file mode 100644 index 00000000000..85e9f87a1a7 --- /dev/null +++ b/fs/xfs/xfs_extent_busy.c @@ -0,0 +1,603 @@ +/* + * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. + * Copyright (c) 2010 David Chinner. + * Copyright (c) 2011 Christoph Hellwig. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#include "xfs.h" +#include "xfs_fs.h" +#include "xfs_types.h" +#include "xfs_log.h" +#include "xfs_trans.h" +#include "xfs_sb.h" +#include "xfs_ag.h" +#include "xfs_mount.h" +#include "xfs_bmap_btree.h" +#include "xfs_alloc.h" +#include "xfs_inode.h" +#include "xfs_extent_busy.h" +#include "xfs_trace.h" + +void +xfs_extent_busy_insert( + struct xfs_trans *tp, + xfs_agnumber_t agno, + xfs_agblock_t bno, + xfs_extlen_t len, + unsigned int flags) +{ + struct xfs_extent_busy *new; + struct xfs_extent_busy *busyp; + struct xfs_perag *pag; + struct rb_node **rbp; + struct rb_node *parent = NULL; + + new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_MAYFAIL); + if (!new) { + /* + * No Memory! Since it is now not possible to track the free + * block, make this a synchronous transaction to insure that + * the block is not reused before this transaction commits. + */ + trace_xfs_extent_busy_enomem(tp->t_mountp, agno, bno, len); + xfs_trans_set_sync(tp); + return; + } + + new->agno = agno; + new->bno = bno; + new->length = len; + INIT_LIST_HEAD(&new->list); + new->flags = flags; + + /* trace before insert to be able to see failed inserts */ + trace_xfs_extent_busy(tp->t_mountp, agno, bno, len); + + pag = xfs_perag_get(tp->t_mountp, new->agno); + spin_lock(&pag->pagb_lock); + rbp = &pag->pagb_tree.rb_node; + while (*rbp) { + parent = *rbp; + busyp = rb_entry(parent, struct xfs_extent_busy, rb_node); + + if (new->bno < busyp->bno) { + rbp = &(*rbp)->rb_left; + ASSERT(new->bno + new->length <= busyp->bno); + } else if (new->bno > busyp->bno) { + rbp = &(*rbp)->rb_right; + ASSERT(bno >= busyp->bno + busyp->length); + } else { + ASSERT(0); + } + } + + rb_link_node(&new->rb_node, parent, rbp); + rb_insert_color(&new->rb_node, &pag->pagb_tree); + + list_add(&new->list, &tp->t_busy); + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); +} + +/* + * Search for a busy extent within the range of the extent we are about to + * allocate. You need to be holding the busy extent tree lock when calling + * xfs_extent_busy_search(). This function returns 0 for no overlapping busy + * extent, -1 for an overlapping but not exact busy extent, and 1 for an exact + * match. This is done so that a non-zero return indicates an overlap that + * will require a synchronous transaction, but it can still be + * used to distinguish between a partial or exact match. + */ +int +xfs_extent_busy_search( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_agblock_t bno, + xfs_extlen_t len) +{ + struct xfs_perag *pag; + struct rb_node *rbp; + struct xfs_extent_busy *busyp; + int match = 0; + + pag = xfs_perag_get(mp, agno); + spin_lock(&pag->pagb_lock); + + rbp = pag->pagb_tree.rb_node; + + /* find closest start bno overlap */ + while (rbp) { + busyp = rb_entry(rbp, struct xfs_extent_busy, rb_node); + if (bno < busyp->bno) { + /* may overlap, but exact start block is lower */ + if (bno + len > busyp->bno) + match = -1; + rbp = rbp->rb_left; + } else if (bno > busyp->bno) { + /* may overlap, but exact start block is higher */ + if (bno < busyp->bno + busyp->length) + match = -1; + rbp = rbp->rb_right; + } else { + /* bno matches busyp, length determines exact match */ + match = (busyp->length == len) ? 1 : -1; + break; + } + } + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); + return match; +} + +/* + * The found free extent [fbno, fend] overlaps part or all of the given busy + * extent. If the overlap covers the beginning, the end, or all of the busy + * extent, the overlapping portion can be made unbusy and used for the + * allocation. We can't split a busy extent because we can't modify a + * transaction/CIL context busy list, but we can update an entries block + * number or length. + * + * Returns true if the extent can safely be reused, or false if the search + * needs to be restarted. + */ +STATIC bool +xfs_extent_busy_update_extent( + struct xfs_mount *mp, + struct xfs_perag *pag, + struct xfs_extent_busy *busyp, + xfs_agblock_t fbno, + xfs_extlen_t flen, + bool userdata) +{ + xfs_agblock_t fend = fbno + flen; + xfs_agblock_t bbno = busyp->bno; + xfs_agblock_t bend = bbno + busyp->length; + + /* + * This extent is currently being discarded. Give the thread + * performing the discard a chance to mark the extent unbusy + * and retry. + */ + if (busyp->flags & XFS_EXTENT_BUSY_DISCARDED) { + spin_unlock(&pag->pagb_lock); + delay(1); + spin_lock(&pag->pagb_lock); + return false; + } + + /* + * If there is a busy extent overlapping a user allocation, we have + * no choice but to force the log and retry the search. + * + * Fortunately this does not happen during normal operation, but + * only if the filesystem is very low on space and has to dip into + * the AGFL for normal allocations. + */ + if (userdata) + goto out_force_log; + + if (bbno < fbno && bend > fend) { + /* + * Case 1: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +---------+ + * fbno fend + */ + + /* + * We would have to split the busy extent to be able to track + * it correct, which we cannot do because we would have to + * modify the list of busy extents attached to the transaction + * or CIL context, which is immutable. + * + * Force out the log to clear the busy extent and retry the + * search. + */ + goto out_force_log; + } else if (bbno >= fbno && bend <= fend) { + /* + * Case 2: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-----------------+ + * fbno fend + * + * Case 3: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +--------------------------+ + * fbno fend + * + * Case 4: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +--------------------------+ + * fbno fend + * + * Case 5: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-----------------------------------+ + * fbno fend + * + */ + + /* + * The busy extent is fully covered by the extent we are + * allocating, and can simply be removed from the rbtree. + * However we cannot remove it from the immutable list + * tracking busy extents in the transaction or CIL context, + * so set the length to zero to mark it invalid. + * + * We also need to restart the busy extent search from the + * tree root, because erasing the node can rearrange the + * tree topology. + */ + rb_erase(&busyp->rb_node, &pag->pagb_tree); + busyp->length = 0; + return false; + } else if (fend < bend) { + /* + * Case 6: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +---------+ + * fbno fend + * + * Case 7: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +------------------+ + * fbno fend + * + */ + busyp->bno = fend; + } else if (bbno < fbno) { + /* + * Case 8: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-------------+ + * fbno fend + * + * Case 9: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +----------------------+ + * fbno fend + */ + busyp->length = fbno - busyp->bno; + } else { + ASSERT(0); + } + + trace_xfs_extent_busy_reuse(mp, pag->pag_agno, fbno, flen); + return true; + +out_force_log: + spin_unlock(&pag->pagb_lock); + xfs_log_force(mp, XFS_LOG_SYNC); + trace_xfs_extent_busy_force(mp, pag->pag_agno, fbno, flen); + spin_lock(&pag->pagb_lock); + return false; +} + + +/* + * For a given extent [fbno, flen], make sure we can reuse it safely. + */ +void +xfs_extent_busy_reuse( + struct xfs_mount *mp, + xfs_agnumber_t agno, + xfs_agblock_t fbno, + xfs_extlen_t flen, + bool userdata) +{ + struct xfs_perag *pag; + struct rb_node *rbp; + + ASSERT(flen > 0); + + pag = xfs_perag_get(mp, agno); + spin_lock(&pag->pagb_lock); +restart: + rbp = pag->pagb_tree.rb_node; + while (rbp) { + struct xfs_extent_busy *busyp = + rb_entry(rbp, struct xfs_extent_busy, rb_node); + xfs_agblock_t bbno = busyp->bno; + xfs_agblock_t bend = bbno + busyp->length; + + if (fbno + flen <= bbno) { + rbp = rbp->rb_left; + continue; + } else if (fbno >= bend) { + rbp = rbp->rb_right; + continue; + } + + if (!xfs_extent_busy_update_extent(mp, pag, busyp, fbno, flen, + userdata)) + goto restart; + } + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); +} + +/* + * For a given extent [fbno, flen], search the busy extent list to find a + * subset of the extent that is not busy. If *rlen is smaller than + * args->minlen no suitable extent could be found, and the higher level + * code needs to force out the log and retry the allocation. + */ +void +xfs_extent_busy_trim( + struct xfs_alloc_arg *args, + xfs_agblock_t bno, + xfs_extlen_t len, + xfs_agblock_t *rbno, + xfs_extlen_t *rlen) +{ + xfs_agblock_t fbno; + xfs_extlen_t flen; + struct rb_node *rbp; + + ASSERT(len > 0); + + spin_lock(&args->pag->pagb_lock); +restart: + fbno = bno; + flen = len; + rbp = args->pag->pagb_tree.rb_node; + while (rbp && flen >= args->minlen) { + struct xfs_extent_busy *busyp = + rb_entry(rbp, struct xfs_extent_busy, rb_node); + xfs_agblock_t fend = fbno + flen; + xfs_agblock_t bbno = busyp->bno; + xfs_agblock_t bend = bbno + busyp->length; + + if (fend <= bbno) { + rbp = rbp->rb_left; + continue; + } else if (fbno >= bend) { + rbp = rbp->rb_right; + continue; + } + + /* + * If this is a metadata allocation, try to reuse the busy + * extent instead of trimming the allocation. + */ + if (!args->userdata && + !(busyp->flags & XFS_EXTENT_BUSY_DISCARDED)) { + if (!xfs_extent_busy_update_extent(args->mp, args->pag, + busyp, fbno, flen, + false)) + goto restart; + continue; + } + + if (bbno <= fbno) { + /* start overlap */ + + /* + * Case 1: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +---------+ + * fbno fend + * + * Case 2: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-------------+ + * fbno fend + * + * Case 3: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-------------+ + * fbno fend + * + * Case 4: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-----------------+ + * fbno fend + * + * No unbusy region in extent, return failure. + */ + if (fend <= bend) + goto fail; + + /* + * Case 5: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +----------------------+ + * fbno fend + * + * Case 6: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +--------------------------+ + * fbno fend + * + * Needs to be trimmed to: + * +-------+ + * fbno fend + */ + fbno = bend; + } else if (bend >= fend) { + /* end overlap */ + + /* + * Case 7: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +------------------+ + * fbno fend + * + * Case 8: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +--------------------------+ + * fbno fend + * + * Needs to be trimmed to: + * +-------+ + * fbno fend + */ + fend = bbno; + } else { + /* middle overlap */ + + /* + * Case 9: + * bbno bend + * +BBBBBBBBBBBBBBBBB+ + * +-----------------------------------+ + * fbno fend + * + * Can be trimmed to: + * +-------+ OR +-------+ + * fbno fend fbno fend + * + * Backward allocation leads to significant + * fragmentation of directories, which degrades + * directory performance, therefore we always want to + * choose the option that produces forward allocation + * patterns. + * Preferring the lower bno extent will make the next + * request use "fend" as the start of the next + * allocation; if the segment is no longer busy at + * that point, we'll get a contiguous allocation, but + * even if it is still busy, we will get a forward + * allocation. + * We try to avoid choosing the segment at "bend", + * because that can lead to the next allocation + * taking the segment at "fbno", which would be a + * backward allocation. We only use the segment at + * "fbno" if it is much larger than the current + * requested size, because in that case there's a + * good chance subsequent allocations will be + * contiguous. + */ + if (bbno - fbno >= args->maxlen) { + /* left candidate fits perfect */ + fend = bbno; + } else if (fend - bend >= args->maxlen * 4) { + /* right candidate has enough free space */ + fbno = bend; + } else if (bbno - fbno >= args->minlen) { + /* left candidate fits minimum requirement */ + fend = bbno; + } else { + goto fail; + } + } + + flen = fend - fbno; + } + spin_unlock(&args->pag->pagb_lock); + + if (fbno != bno || flen != len) { + trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, + fbno, flen); + } + *rbno = fbno; + *rlen = flen; + return; +fail: + /* + * Return a zero extent length as failure indications. All callers + * re-check if the trimmed extent satisfies the minlen requirement. + */ + spin_unlock(&args->pag->pagb_lock); + trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, fbno, 0); + *rbno = fbno; + *rlen = 0; +} + +STATIC void +xfs_extent_busy_clear_one( + struct xfs_mount *mp, + struct xfs_perag *pag, + struct xfs_extent_busy *busyp) +{ + if (busyp->length) { + trace_xfs_extent_busy_clear(mp, busyp->agno, busyp->bno, + busyp->length); + rb_erase(&busyp->rb_node, &pag->pagb_tree); + } + + list_del_init(&busyp->list); + kmem_free(busyp); +} + +/* + * Remove all extents on the passed in list from the busy extents tree. + * If do_discard is set skip extents that need to be discarded, and mark + * these as undergoing a discard operation instead. + */ +void +xfs_extent_busy_clear( + struct xfs_mount *mp, + struct list_head *list, + bool do_discard) +{ + struct xfs_extent_busy *busyp, *n; + struct xfs_perag *pag = NULL; + xfs_agnumber_t agno = NULLAGNUMBER; + + list_for_each_entry_safe(busyp, n, list, list) { + if (busyp->agno != agno) { + if (pag) { + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); + } + pag = xfs_perag_get(mp, busyp->agno); + spin_lock(&pag->pagb_lock); + agno = busyp->agno; + } + + if (do_discard && busyp->length && + !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) + busyp->flags = XFS_EXTENT_BUSY_DISCARDED; + else + xfs_extent_busy_clear_one(mp, pag, busyp); + } + + if (pag) { + spin_unlock(&pag->pagb_lock); + xfs_perag_put(pag); + } +} + +/* + * Callback for list_sort to sort busy extents by the AG they reside in. + */ +int +xfs_extent_busy_ag_cmp( + void *priv, + struct list_head *a, + struct list_head *b) +{ + return container_of(a, struct xfs_extent_busy, list)->agno - + container_of(b, struct xfs_extent_busy, list)->agno; +} diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h new file mode 100644 index 00000000000..985412d65ba --- /dev/null +++ b/fs/xfs/xfs_extent_busy.h @@ -0,0 +1,69 @@ +/* + * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. + * Copyright (c) 2010 David Chinner. + * Copyright (c) 2011 Christoph Hellwig. + * All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it would be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write the Free Software Foundation, + * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ +#ifndef __XFS_EXTENT_BUSY_H__ +#define __XFS_EXTENT_BUSY_H__ + +/* + * Busy block/extent entry. Indexed by a rbtree in perag to mark blocks that + * have been freed but whose transactions aren't committed to disk yet. + * + * Note that we use the transaction ID to record the transaction, not the + * transaction structure itself. See xfs_extent_busy_insert() for details. + */ +struct xfs_extent_busy { + struct rb_node rb_node; /* ag by-bno indexed search tree */ + struct list_head list; /* transaction busy extent list */ + xfs_agnumber_t agno; + xfs_agblock_t bno; + xfs_extlen_t length; + unsigned int flags; +#define XFS_EXTENT_BUSY_DISCARDED 0x01 /* undergoing a discard op. */ +#define XFS_EXTENT_BUSY_SKIP_DISCARD 0x02 /* do not discard */ +}; + +void +xfs_extent_busy_insert(struct xfs_trans *tp, xfs_agnumber_t agno, + xfs_agblock_t bno, xfs_extlen_t len, unsigned int flags); + +void +xfs_extent_busy_clear(struct xfs_mount *mp, struct list_head *list, + bool do_discard); + +int +xfs_extent_busy_search(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_agblock_t bno, xfs_extlen_t len); + +void +xfs_extent_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno, + xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata); + +void +xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t bno, + xfs_extlen_t len, xfs_agblock_t *rbno, xfs_extlen_t *rlen); + +int +xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b); + +static inline void xfs_extent_busy_sort(struct list_head *list) +{ + list_sort(NULL, list, xfs_extent_busy_ag_cmp); +} + +#endif /* __XFS_EXTENT_BUSY_H__ */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 35c2aff38b2..feb36d7551a 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_buf_item.h" #include "xfs_sb.h" @@ -64,7 +63,8 @@ __xfs_efi_release( if (!test_and_clear_bit(XFS_EFI_COMMITTED, &efip->efi_flags)) { spin_lock(&ailp->xa_lock); /* xfs_trans_ail_delete() drops the AIL lock. */ - xfs_trans_ail_delete(ailp, &efip->efi_item); + xfs_trans_ail_delete(ailp, &efip->efi_item, + SHUTDOWN_LOG_IO_ERROR); xfs_efi_item_free(efip); } } @@ -147,22 +147,20 @@ xfs_efi_item_unpin( } /* - * Efi items have no locking or pushing. However, since EFIs are - * pulled from the AIL when their corresponding EFDs are committed - * to disk, their situation is very similar to being pinned. Return - * XFS_ITEM_PINNED so that the caller will eventually flush the log. - * This should help in getting the EFI out of the AIL. + * Efi items have no locking or pushing. However, since EFIs are pulled from + * the AIL when their corresponding EFDs are committed to disk, their situation + * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller + * will eventually flush the log. This should help in getting the EFI out of + * the AIL. */ STATIC uint -xfs_efi_item_trylock( - struct xfs_log_item *lip) +xfs_efi_item_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { return XFS_ITEM_PINNED; } -/* - * Efi items have no locking, so just return. - */ STATIC void xfs_efi_item_unlock( struct xfs_log_item *lip) @@ -190,17 +188,6 @@ xfs_efi_item_committed( } /* - * There isn't much you can do to push on an efi item. It is simply - * stuck waiting for all of its corresponding efd items to be - * committed to disk. - */ -STATIC void -xfs_efi_item_push( - struct xfs_log_item *lip) -{ -} - -/* * The EFI dependency tracking op doesn't do squat. It can't because * it doesn't know where the free extent is coming from. The dependency * tracking has to be handled by the "enclosing" metadata object. For @@ -222,7 +209,6 @@ static const struct xfs_item_ops xfs_efi_item_ops = { .iop_format = xfs_efi_item_format, .iop_pin = xfs_efi_item_pin, .iop_unpin = xfs_efi_item_unpin, - .iop_trylock = xfs_efi_item_trylock, .iop_unlock = xfs_efi_item_unlock, .iop_committed = xfs_efi_item_committed, .iop_push = xfs_efi_item_push, @@ -404,19 +390,17 @@ xfs_efd_item_unpin( } /* - * Efd items have no locking, so just return success. + * There isn't much you can do to push on an efd item. It is simply stuck + * waiting for the log to be flushed to disk. */ STATIC uint -xfs_efd_item_trylock( - struct xfs_log_item *lip) +xfs_efd_item_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { - return XFS_ITEM_LOCKED; + return XFS_ITEM_PINNED; } -/* - * Efd items have no locking or pushing, so return failure - * so that the caller doesn't bother with us. - */ STATIC void xfs_efd_item_unlock( struct xfs_log_item *lip) @@ -451,16 +435,6 @@ xfs_efd_item_committed( } /* - * There isn't much you can do to push on an efd item. It is simply - * stuck waiting for the log to be flushed to disk. - */ -STATIC void -xfs_efd_item_push( - struct xfs_log_item *lip) -{ -} - -/* * The EFD dependency tracking op doesn't do squat. It can't because * it doesn't know where the free extent is coming from. The dependency * tracking has to be handled by the "enclosing" metadata object. For @@ -482,7 +456,6 @@ static const struct xfs_item_ops xfs_efd_item_ops = { .iop_format = xfs_efd_item_format, .iop_pin = xfs_efd_item_pin, .iop_unpin = xfs_efd_item_unpin, - .iop_trylock = xfs_efd_item_trylock, .iop_unlock = xfs_efd_item_unlock, .iop_committed = xfs_efd_item_committed, .iop_push = xfs_efd_item_push, diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 54a67dd9ac0..9f7ec15a652 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_trans.h" @@ -396,114 +394,96 @@ xfs_file_splice_write( } /* - * This routine is called to handle zeroing any space in the last - * block of the file that is beyond the EOF. We do this since the - * size is being increased without writing anything to that block - * and we don't want anyone to read the garbage on the disk. + * This routine is called to handle zeroing any space in the last block of the + * file that is beyond the EOF. We do this since the size is being increased + * without writing anything to that block and we don't want to read the + * garbage on the disk. */ STATIC int /* error (positive) */ xfs_zero_last_block( - xfs_inode_t *ip, - xfs_fsize_t offset, - xfs_fsize_t isize) + struct xfs_inode *ip, + xfs_fsize_t offset, + xfs_fsize_t isize) { - xfs_fileoff_t last_fsb; - xfs_mount_t *mp = ip->i_mount; - int nimaps; - int zero_offset; - int zero_len; - int error = 0; - xfs_bmbt_irec_t imap; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - zero_offset = XFS_B_FSB_OFFSET(mp, isize); - if (zero_offset == 0) { - /* - * There are no extra bytes in the last block on disk to - * zero, so return. - */ - return 0; - } + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t last_fsb = XFS_B_TO_FSBT(mp, isize); + int zero_offset = XFS_B_FSB_OFFSET(mp, isize); + int zero_len; + int nimaps = 1; + int error = 0; + struct xfs_bmbt_irec imap; - last_fsb = XFS_B_TO_FSBT(mp, isize); - nimaps = 1; + xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_bmapi_read(ip, last_fsb, 1, &imap, &nimaps, 0); + xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) return error; + ASSERT(nimaps > 0); + /* * If the block underlying isize is just a hole, then there * is nothing to zero. */ - if (imap.br_startblock == HOLESTARTBLOCK) { + if (imap.br_startblock == HOLESTARTBLOCK) return 0; - } - /* - * Zero the part of the last block beyond the EOF, and write it - * out sync. We need to drop the ilock while we do this so we - * don't deadlock when the buffer cache calls back to us. - */ - xfs_iunlock(ip, XFS_ILOCK_EXCL); zero_len = mp->m_sb.sb_blocksize - zero_offset; if (isize + zero_len > offset) zero_len = offset - isize; - error = xfs_iozero(ip, isize, zero_len); - - xfs_ilock(ip, XFS_ILOCK_EXCL); - ASSERT(error >= 0); - return error; + return xfs_iozero(ip, isize, zero_len); } /* - * Zero any on disk space between the current EOF and the new, - * larger EOF. This handles the normal case of zeroing the remainder - * of the last block in the file and the unusual case of zeroing blocks - * out beyond the size of the file. This second case only happens - * with fixed size extents and when the system crashes before the inode - * size was updated but after blocks were allocated. If fill is set, - * then any holes in the range are filled and zeroed. If not, the holes - * are left alone as holes. + * Zero any on disk space between the current EOF and the new, larger EOF. + * + * This handles the normal case of zeroing the remainder of the last block in + * the file and the unusual case of zeroing blocks out beyond the size of the + * file. This second case only happens with fixed size extents and when the + * system crashes before the inode size was updated but after blocks were + * allocated. + * + * Expects the iolock to be held exclusive, and will take the ilock internally. */ - int /* error (positive) */ xfs_zero_eof( - xfs_inode_t *ip, - xfs_off_t offset, /* starting I/O offset */ - xfs_fsize_t isize) /* current inode size */ + struct xfs_inode *ip, + xfs_off_t offset, /* starting I/O offset */ + xfs_fsize_t isize) /* current inode size */ { - xfs_mount_t *mp = ip->i_mount; - xfs_fileoff_t start_zero_fsb; - xfs_fileoff_t end_zero_fsb; - xfs_fileoff_t zero_count_fsb; - xfs_fileoff_t last_fsb; - xfs_fileoff_t zero_off; - xfs_fsize_t zero_len; - int nimaps; - int error = 0; - xfs_bmbt_irec_t imap; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t start_zero_fsb; + xfs_fileoff_t end_zero_fsb; + xfs_fileoff_t zero_count_fsb; + xfs_fileoff_t last_fsb; + xfs_fileoff_t zero_off; + xfs_fsize_t zero_len; + int nimaps; + int error = 0; + struct xfs_bmbt_irec imap; + + ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(offset > isize); /* * First handle zeroing the block on which isize resides. + * * We only zero a part of that block so it is handled specially. */ - error = xfs_zero_last_block(ip, offset, isize); - if (error) { - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); - return error; + if (XFS_B_FSB_OFFSET(mp, isize) != 0) { + error = xfs_zero_last_block(ip, offset, isize); + if (error) + return error; } /* - * Calculate the range between the new size and the old - * where blocks needing to be zeroed may exist. To get the - * block where the last byte in the file currently resides, - * we need to subtract one from the size and truncate back - * to a block boundary. We subtract 1 in case the size is - * exactly on a block boundary. + * Calculate the range between the new size and the old where blocks + * needing to be zeroed may exist. + * + * To get the block where the last byte in the file currently resides, + * we need to subtract one from the size and truncate back to a block + * boundary. We subtract 1 in case the size is exactly on a block + * boundary. */ last_fsb = isize ? XFS_B_TO_FSBT(mp, isize - 1) : (xfs_fileoff_t)-1; start_zero_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize); @@ -521,23 +501,18 @@ xfs_zero_eof( while (start_zero_fsb <= end_zero_fsb) { nimaps = 1; zero_count_fsb = end_zero_fsb - start_zero_fsb + 1; + + xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_bmapi_read(ip, start_zero_fsb, zero_count_fsb, &imap, &nimaps, 0); - if (error) { - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL)); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + if (error) return error; - } + ASSERT(nimaps > 0); if (imap.br_state == XFS_EXT_UNWRITTEN || imap.br_startblock == HOLESTARTBLOCK) { - /* - * This loop handles initializing pages that were - * partially initialized by the code below this - * loop. It basically zeroes the part of the page - * that sits on a hole and sets the page as P_HOLE - * and calls remapf if it is a mapped file. - */ start_zero_fsb = imap.br_startoff + imap.br_blockcount; ASSERT(start_zero_fsb <= (end_zero_fsb + 1)); continue; @@ -545,11 +520,7 @@ xfs_zero_eof( /* * There are blocks we need to zero. - * Drop the inode lock while we're doing the I/O. - * We'll still have the iolock to protect us. */ - xfs_iunlock(ip, XFS_ILOCK_EXCL); - zero_off = XFS_FSB_TO_B(mp, start_zero_fsb); zero_len = XFS_FSB_TO_B(mp, imap.br_blockcount); @@ -557,22 +528,14 @@ xfs_zero_eof( zero_len = offset - zero_off; error = xfs_iozero(ip, zero_off, zero_len); - if (error) { - goto out_lock; - } + if (error) + return error; start_zero_fsb = imap.br_startoff + imap.br_blockcount; ASSERT(start_zero_fsb <= (end_zero_fsb + 1)); - - xfs_ilock(ip, XFS_ILOCK_EXCL); } return 0; - -out_lock: - xfs_ilock(ip, XFS_ILOCK_EXCL); - ASSERT(error >= 0); - return error; } /* @@ -593,35 +556,29 @@ xfs_file_aio_write_checks( struct xfs_inode *ip = XFS_I(inode); int error = 0; - xfs_rw_ilock(ip, XFS_ILOCK_EXCL); restart: error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode)); - if (error) { - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); + if (error) return error; - } /* * If the offset is beyond the size of the file, we need to zero any * blocks that fall between the existing EOF and the start of this * write. If zeroing is needed and we are currently holding the - * iolock shared, we need to update it to exclusive which involves - * dropping all locks and relocking to maintain correct locking order. - * If we do this, restart the function to ensure all checks and values - * are still valid. + * iolock shared, we need to update it to exclusive which implies + * having to redo all checks before. */ if (*pos > i_size_read(inode)) { if (*iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock); + xfs_rw_iunlock(ip, *iolock); *iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock); + xfs_rw_ilock(ip, *iolock); goto restart; } error = -xfs_zero_eof(ip, *pos, i_size_read(inode)); + if (error) + return error; } - xfs_rw_iunlock(ip, XFS_ILOCK_EXCL); - if (error) - return error; /* * Updating the timestamps will grab the ilock again from @@ -629,8 +586,11 @@ restart: * lock above. Eventually we should look into a way to avoid * the pointless lock roundtrip. */ - if (likely(!(file->f_mode & FMODE_NOCMTIME))) - file_update_time(file); + if (likely(!(file->f_mode & FMODE_NOCMTIME))) { + error = file_update_time(file); + if (error) + return error; + } /* * If we're writing the file then make sure to clear the setuid and @@ -638,7 +598,6 @@ restart: * people from modifying setuid and setgid binaries. */ return file_remove_suid(file); - } /* @@ -1007,8 +966,149 @@ xfs_vm_page_mkwrite( return block_page_mkwrite(vma, vmf, xfs_get_blocks); } +STATIC loff_t +xfs_seek_data( + struct file *file, + loff_t start, + u32 type) +{ + struct inode *inode = file->f_mapping->host; + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + struct xfs_bmbt_irec map[2]; + int nmap = 2; + loff_t uninitialized_var(offset); + xfs_fsize_t isize; + xfs_fileoff_t fsbno; + xfs_filblks_t end; + uint lock; + int error; + + lock = xfs_ilock_map_shared(ip); + + isize = i_size_read(inode); + if (start >= isize) { + error = ENXIO; + goto out_unlock; + } + + fsbno = XFS_B_TO_FSBT(mp, start); + + /* + * Try to read extents from the first block indicated + * by fsbno to the end block of the file. + */ + end = XFS_B_TO_FSB(mp, isize); + + error = xfs_bmapi_read(ip, fsbno, end - fsbno, map, &nmap, + XFS_BMAPI_ENTIRE); + if (error) + goto out_unlock; + + /* + * Treat unwritten extent as data extent since it might + * contains dirty data in page cache. + */ + if (map[0].br_startblock != HOLESTARTBLOCK) { + offset = max_t(loff_t, start, + XFS_FSB_TO_B(mp, map[0].br_startoff)); + } else { + if (nmap == 1) { + error = ENXIO; + goto out_unlock; + } + + offset = max_t(loff_t, start, + XFS_FSB_TO_B(mp, map[1].br_startoff)); + } + + if (offset != file->f_pos) + file->f_pos = offset; + +out_unlock: + xfs_iunlock_map_shared(ip, lock); + + if (error) + return -error; + return offset; +} + +STATIC loff_t +xfs_seek_hole( + struct file *file, + loff_t start, + u32 type) +{ + struct inode *inode = file->f_mapping->host; + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + loff_t uninitialized_var(offset); + loff_t holeoff; + xfs_fsize_t isize; + xfs_fileoff_t fsbno; + uint lock; + int error; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -XFS_ERROR(EIO); + + lock = xfs_ilock_map_shared(ip); + + isize = i_size_read(inode); + if (start >= isize) { + error = ENXIO; + goto out_unlock; + } + + fsbno = XFS_B_TO_FSBT(mp, start); + error = xfs_bmap_first_unused(NULL, ip, 1, &fsbno, XFS_DATA_FORK); + if (error) + goto out_unlock; + + holeoff = XFS_FSB_TO_B(mp, fsbno); + if (holeoff <= start) + offset = start; + else { + /* + * xfs_bmap_first_unused() could return a value bigger than + * isize if there are no more holes past the supplied offset. + */ + offset = min_t(loff_t, holeoff, isize); + } + + if (offset != file->f_pos) + file->f_pos = offset; + +out_unlock: + xfs_iunlock_map_shared(ip, lock); + + if (error) + return -error; + return offset; +} + +STATIC loff_t +xfs_file_llseek( + struct file *file, + loff_t offset, + int origin) +{ + switch (origin) { + case SEEK_END: + case SEEK_CUR: + case SEEK_SET: + return generic_file_llseek(file, offset, origin); + case SEEK_DATA: + return xfs_seek_data(file, offset, origin); + case SEEK_HOLE: + return xfs_seek_hole(file, offset, origin); + default: + return -EINVAL; + } +} + const struct file_operations xfs_file_operations = { - .llseek = generic_file_llseek, + .llseek = xfs_file_llseek, .read = do_sync_read, .write = do_sync_write, .aio_read = xfs_file_aio_read, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 1c6fdeb702f..c25b094efbf 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -18,8 +18,6 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" -#include "xfs_inum.h" #include "xfs_log.h" #include "xfs_trans.h" #include "xfs_sb.h" @@ -39,7 +37,6 @@ #include "xfs_itable.h" #include "xfs_trans_space.h" #include "xfs_rtalloc.h" -#include "xfs_rw.h" #include "xfs_filestream.h" #include "xfs_trace.h" @@ -147,9 +144,9 @@ xfs_growfs_data_private( if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb))) return error; dpct = pct - mp->m_sb.sb_imax_pct; - bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, + bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1), - BBTOB(XFS_FSS_TO_BB(mp, 1)), 0); + XFS_FSS_TO_BB(mp, 1), 0); if (!bp) return EIO; xfs_buf_relse(bp); @@ -193,7 +190,7 @@ xfs_growfs_data_private( */ bp = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)), - XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED); + XFS_FSS_TO_BB(mp, 1), 0); if (!bp) { error = ENOMEM; goto error0; @@ -230,7 +227,7 @@ xfs_growfs_data_private( */ bp = xfs_buf_get(mp->m_ddev_targp, XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)), - XFS_FSS_TO_BB(mp, 1), XBF_LOCK | XBF_MAPPED); + XFS_FSS_TO_BB(mp, 1), 0); if (!bp) { error = ENOMEM; goto error0; @@ -259,8 +256,7 @@ xfs_growfs_data_private( */ bp = xfs_buf_get(mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)), - BTOBB(mp->m_sb.sb_blocksize), - XBF_LOCK | XBF_MAPPED); + BTOBB(mp->m_sb.sb_blocksize), 0); if (!bp) { error = ENOMEM; goto error0; @@ -286,8 +282,7 @@ xfs_growfs_data_private( */ bp = xfs_buf_get(mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)), - BTOBB(mp->m_sb.sb_blocksize), - XBF_LOCK | XBF_MAPPED); + BTOBB(mp->m_sb.sb_blocksize), 0); if (!bp) { error = ENOMEM; goto error0; @@ -314,8 +309,7 @@ xfs_growfs_data_private( */ bp = xfs_buf_get(mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)), - BTOBB(mp->m_sb.sb_blocksize), - XBF_LOCK | XBF_MAPPED); + BTOBB(mp->m_sb.sb_blocksize), 0); if (!bp) { error = ENOMEM; goto error0; @@ -405,7 +399,7 @@ xfs_growfs_data_private( /* update secondary superblocks. */ for (agno = 1; agno < nagcount; agno++) { - error = xfs_read_buf(mp, mp->m_ddev_targp, + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp); if (error) { @@ -693,3 +687,63 @@ xfs_fs_goingdown( return 0; } + +/* + * Force a shutdown of the filesystem instantly while keeping the filesystem + * consistent. We don't do an unmount here; just shutdown the shop, make sure + * that absolutely nothing persistent happens to this filesystem after this + * point. + */ +void +xfs_do_force_shutdown( + xfs_mount_t *mp, + int flags, + char *fname, + int lnnum) +{ + int logerror; + + logerror = flags & SHUTDOWN_LOG_IO_ERROR; + + if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { + xfs_notice(mp, + "%s(0x%x) called from line %d of file %s. Return address = 0x%p", + __func__, flags, lnnum, fname, __return_address); + } + /* + * No need to duplicate efforts. + */ + if (XFS_FORCED_SHUTDOWN(mp) && !logerror) + return; + + /* + * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't + * queue up anybody new on the log reservations, and wakes up + * everybody who's sleeping on log reservations to tell them + * the bad news. + */ + if (xfs_log_force_umount(mp, logerror)) + return; + + if (flags & SHUTDOWN_CORRUPT_INCORE) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT, + "Corruption of in-memory data detected. Shutting down filesystem"); + if (XFS_ERRLEVEL_HIGH <= xfs_error_level) + xfs_stack_trace(); + } else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { + if (logerror) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR, + "Log I/O Error Detected. Shutting down filesystem"); + } else if (flags & SHUTDOWN_DEVICE_REQ) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, + "All device paths lost. Shutting down filesystem"); + } else if (!(flags & SHUTDOWN_REMOTE_REQ)) { + xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, + "I/O Error Detected. Shutting down filesystem"); + } + } + if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { + xfs_alert(mp, + "Please umount the filesystem and rectify the problem(s)"); + } +} diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index dad1a31aa4f..177a21a7ac4 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -200,8 +200,7 @@ xfs_ialloc_inode_init( */ d = XFS_AGB_TO_DADDR(mp, agno, agbno + (j * blks_per_cluster)); fbuf = xfs_trans_get_buf(tp, mp->m_ddev_targp, d, - mp->m_bsize * blks_per_cluster, - XBF_LOCK); + mp->m_bsize * blks_per_cluster, 0); if (!fbuf) return ENOMEM; /* @@ -610,6 +609,13 @@ xfs_ialloc_get_rec( /* * Visible inode allocation functions. */ +/* + * Find a free (set) bit in the inode bitmask. + */ +static inline int xfs_ialloc_find_free(xfs_inofree_t *fp) +{ + return xfs_lowbit64(*fp); +} /* * Allocate an inode on disk. diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h index 666a037398d..65ac57c8063 100644 --- a/fs/xfs/xfs_ialloc.h +++ b/fs/xfs/xfs_ialloc.h @@ -47,15 +47,6 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o) } /* - * Find a free (set) bit in the inode bitmask. - */ -static inline int xfs_ialloc_find_free(xfs_inofree_t *fp) -{ - return xfs_lowbit64(*fp); -} - - -/* * Allocate an inode on disk. * Mode is used to tell whether the new inode will need space, and whether * it is a directory. diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c index c6a75815aea..2b8b7a37aa1 100644 --- a/fs/xfs/xfs_ialloc_btree.c +++ b/fs/xfs/xfs_ialloc_btree.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c index bcc6c249b2c..1bb4365e8c2 100644 --- a/fs/xfs/xfs_iget.c +++ b/fs/xfs/xfs_iget.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_acl.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" @@ -123,23 +122,7 @@ xfs_inode_free( xfs_idestroy_fork(ip, XFS_ATTR_FORK); if (ip->i_itemp) { - /* - * Only if we are shutting down the fs will we see an - * inode still in the AIL. If it is there, we should remove - * it to prevent a use-after-free from occurring. - */ - xfs_log_item_t *lip = &ip->i_itemp->ili_item; - struct xfs_ail *ailp = lip->li_ailp; - - ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) || - XFS_FORCED_SHUTDOWN(ip->i_mount)); - if (lip->li_flags & XFS_LI_IN_AIL) { - spin_lock(&ailp->xa_lock); - if (lip->li_flags & XFS_LI_IN_AIL) - xfs_trans_ail_delete(ailp, lip); - else - spin_unlock(&ailp->xa_lock); - } + ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL)); xfs_inode_item_destroy(ip); ip->i_itemp = NULL; } @@ -334,9 +317,10 @@ xfs_iget_cache_miss( /* * Preload the radix tree so we can insert safely under the * write spinlock. Note that we cannot sleep inside the preload - * region. + * region. Since we can be called from transaction context, don't + * recurse into the file system. */ - if (radix_tree_preload(GFP_KERNEL)) { + if (radix_tree_preload(GFP_NOFS)) { error = EAGAIN; goto out_destroy; } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index bc46c0a133d..a59eea09930 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -20,7 +20,6 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" @@ -61,6 +60,20 @@ STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int); STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int); STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int); +/* + * helper function to extract extent size hint from inode + */ +xfs_extlen_t +xfs_get_extsz_hint( + struct xfs_inode *ip) +{ + if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize) + return ip->i_d.di_extsize; + if (XFS_IS_REALTIME_INODE(ip)) + return ip->i_mount->m_sb.sb_rextsize; + return 0; +} + #ifdef DEBUG /* * Make sure that the extents in the given memory buffer @@ -137,6 +150,7 @@ xfs_imap_to_bp( int ni; xfs_buf_t *bp; + buf_flags |= XBF_UNMAPPED; error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno, (int)imap->im_len, buf_flags, &bp); if (error) { @@ -226,7 +240,7 @@ xfs_inotobp( if (error) return error; - error = xfs_imap_to_bp(mp, tp, &imap, &bp, XBF_LOCK, imap_flags); + error = xfs_imap_to_bp(mp, tp, &imap, &bp, 0, imap_flags); if (error) return error; @@ -782,8 +796,7 @@ xfs_iread( /* * Get pointers to the on-disk inode and the buffer containing it. */ - error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, - XBF_LOCK, iget_flags); + error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, 0, iget_flags); if (error) return error; dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset); @@ -1342,7 +1355,7 @@ xfs_iunlink( * Here we put the head pointer into our next pointer, * and then we fall through to point the head at us. */ - error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK); + error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0); if (error) return error; @@ -1423,7 +1436,7 @@ xfs_iunlink_remove( * of dealing with the buffer when there is no need to * change it. */ - error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK); + error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0); if (error) { xfs_warn(mp, "%s: xfs_itobp() returned error %d.", __func__, error); @@ -1484,7 +1497,7 @@ xfs_iunlink_remove( * Now last_ibp points to the buffer previous to us on * the unlinked list. Pull us from the list. */ - error = xfs_itobp(mp, tp, ip, &dip, &ibp, XBF_LOCK); + error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0); if (error) { xfs_warn(mp, "%s: xfs_itobp(2) returned error %d.", __func__, error); @@ -1566,8 +1579,7 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * blks_per_cluster, - XBF_LOCK); + mp->m_bsize * blks_per_cluster, 0); if (!bp) return ENOMEM; @@ -1737,7 +1749,7 @@ xfs_ifree( xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XBF_LOCK); + error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0); if (error) return error; @@ -2347,11 +2359,11 @@ cluster_corrupt_out: */ rcu_read_unlock(); /* - * Clean up the buffer. If it was B_DELWRI, just release it -- + * Clean up the buffer. If it was delwri, just release it -- * brelse can handle it with no problems. If not, shut down the * filesystem before releasing the buffer. */ - bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp); + bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q); if (bufwasdelwri) xfs_buf_relse(bp); @@ -2377,30 +2389,29 @@ cluster_corrupt_out: /* * Unlocks the flush lock */ - xfs_iflush_abort(iq); + xfs_iflush_abort(iq, false); kmem_free(ilist); xfs_perag_put(pag); return XFS_ERROR(EFSCORRUPTED); } /* - * xfs_iflush() will write a modified inode's changes out to the - * inode's on disk home. The caller must have the inode lock held - * in at least shared mode and the inode flush completion must be - * active as well. The inode lock will still be held upon return from - * the call and the caller is free to unlock it. - * The inode flush will be completed when the inode reaches the disk. - * The flags indicate how the inode's buffer should be written out. + * Flush dirty inode metadata into the backing buffer. + * + * The caller must have the inode lock and the inode flush lock held. The + * inode lock will still be held upon return to the caller, and the inode + * flush lock will be released after the inode has reached the disk. + * + * The caller must write out the buffer returned in *bpp and release it. */ int xfs_iflush( - xfs_inode_t *ip, - uint flags) + struct xfs_inode *ip, + struct xfs_buf **bpp) { - xfs_inode_log_item_t *iip; - xfs_buf_t *bp; - xfs_dinode_t *dip; - xfs_mount_t *mp; + struct xfs_mount *mp = ip->i_mount; + struct xfs_buf *bp; + struct xfs_dinode *dip; int error; XFS_STATS_INC(xs_iflush_count); @@ -2410,25 +2421,8 @@ xfs_iflush( ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE || ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK)); - iip = ip->i_itemp; - mp = ip->i_mount; + *bpp = NULL; - /* - * We can't flush the inode until it is unpinned, so wait for it if we - * are allowed to block. We know no one new can pin it, because we are - * holding the inode lock shared and you need to hold it exclusively to - * pin the inode. - * - * If we are not allowed to block, force the log out asynchronously so - * that when we come back the inode will be unpinned. If other inodes - * in the same cluster are dirty, they will probably write the inode - * out for us if they occur after the log force completes. - */ - if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) { - xfs_iunpin(ip); - xfs_ifunlock(ip); - return EAGAIN; - } xfs_iunpin_wait(ip); /* @@ -2447,20 +2441,20 @@ xfs_iflush( /* * This may have been unpinned because the filesystem is shutting * down forcibly. If that's the case we must not write this inode - * to disk, because the log record didn't make it to disk! + * to disk, because the log record didn't make it to disk. + * + * We also have to remove the log item from the AIL in this case, + * as we wait for an empty AIL as part of the unmount process. */ if (XFS_FORCED_SHUTDOWN(mp)) { - if (iip) - iip->ili_fields = 0; - xfs_ifunlock(ip); - return XFS_ERROR(EIO); + error = XFS_ERROR(EIO); + goto abort_out; } /* * Get the buffer containing the on-disk inode. */ - error = xfs_itobp(mp, NULL, ip, &dip, &bp, - (flags & SYNC_TRYLOCK) ? XBF_TRYLOCK : XBF_LOCK); + error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK); if (error || !bp) { xfs_ifunlock(ip); return error; @@ -2488,23 +2482,20 @@ xfs_iflush( if (error) goto cluster_corrupt_out; - if (flags & SYNC_WAIT) - error = xfs_bwrite(bp); - else - xfs_buf_delwri_queue(bp); - - xfs_buf_relse(bp); - return error; + *bpp = bp; + return 0; corrupt_out: xfs_buf_relse(bp); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); cluster_corrupt_out: + error = XFS_ERROR(EFSCORRUPTED); +abort_out: /* * Unlocks the flush lock */ - xfs_iflush_abort(ip); - return XFS_ERROR(EFSCORRUPTED); + xfs_iflush_abort(ip, false); + return error; } @@ -2706,27 +2697,6 @@ corrupt_out: return XFS_ERROR(EFSCORRUPTED); } -void -xfs_promote_inode( - struct xfs_inode *ip) -{ - struct xfs_buf *bp; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)); - - bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno, - ip->i_imap.im_len, XBF_TRYLOCK); - if (!bp) - return; - - if (XFS_BUF_ISDELAYWRITE(bp)) { - xfs_buf_delwri_promote(bp); - wake_up_process(ip->i_mount->m_ddev_targp->bt_task); - } - - xfs_buf_relse(bp); -} - /* * Return a pointer to the extent record at file index idx. */ diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 7fee3387e1c..1efff36a75b 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -529,11 +529,12 @@ int xfs_iunlink(struct xfs_trans *, xfs_inode_t *); void xfs_iext_realloc(xfs_inode_t *, int, int); void xfs_iunpin_wait(xfs_inode_t *); -int xfs_iflush(xfs_inode_t *, uint); -void xfs_promote_inode(struct xfs_inode *); +int xfs_iflush(struct xfs_inode *, struct xfs_buf **); void xfs_lock_inodes(xfs_inode_t **, int, uint); void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint); +xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); + #define IHOLD(ip) \ do { \ ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \ diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 05d924efcea..d041d47d9d8 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -480,25 +478,16 @@ xfs_inode_item_unpin( wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } -/* - * This is called to attempt to lock the inode associated with this - * inode log item, in preparation for the push routine which does the actual - * iflush. Don't sleep on the inode lock or the flush lock. - * - * If the flush lock is already held, indicating that the inode has - * been or is in the process of being flushed, then (ideally) we'd like to - * see if the inode's buffer is still incore, and if so give it a nudge. - * We delay doing so until the pushbuf routine, though, to avoid holding - * the AIL lock across a call to the blackhole which is the buffer cache. - * Also we don't want to sleep in any device strategy routines, which can happen - * if we do the subsequent bawrite in here. - */ STATIC uint -xfs_inode_item_trylock( - struct xfs_log_item *lip) +xfs_inode_item_push( + struct xfs_log_item *lip, + struct list_head *buffer_list) { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; + struct xfs_buf *bp = NULL; + uint rval = XFS_ITEM_SUCCESS; + int error; if (xfs_ipincount(ip) > 0) return XFS_ITEM_PINNED; @@ -506,30 +495,49 @@ xfs_inode_item_trylock( if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) return XFS_ITEM_LOCKED; - if (!xfs_iflock_nowait(ip)) { - /* - * inode has already been flushed to the backing buffer, - * leave it locked in shared mode, pushbuf routine will - * unlock it. - */ - return XFS_ITEM_PUSHBUF; + /* + * Re-check the pincount now that we stabilized the value by + * taking the ilock. + */ + if (xfs_ipincount(ip) > 0) { + rval = XFS_ITEM_PINNED; + goto out_unlock; } - /* Stale items should force out the iclog */ + /* + * Stale inode items should force out the iclog. + */ if (ip->i_flags & XFS_ISTALE) { - xfs_ifunlock(ip); - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return XFS_ITEM_PINNED; + rval = XFS_ITEM_PINNED; + goto out_unlock; + } + + /* + * Someone else is already flushing the inode. Nothing we can do + * here but wait for the flush to finish and remove the item from + * the AIL. + */ + if (!xfs_iflock_nowait(ip)) { + rval = XFS_ITEM_FLUSHING; + goto out_unlock; } -#ifdef DEBUG - if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) { - ASSERT(iip->ili_fields != 0); - ASSERT(iip->ili_logged == 0); - ASSERT(lip->li_flags & XFS_LI_IN_AIL); + ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); + ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount)); + + spin_unlock(&lip->li_ailp->xa_lock); + + error = xfs_iflush(ip, &bp); + if (!error) { + if (!xfs_buf_delwri_queue(bp, buffer_list)) + rval = XFS_ITEM_FLUSHING; + xfs_buf_relse(bp); } -#endif - return XFS_ITEM_SUCCESS; + + spin_lock(&lip->li_ailp->xa_lock); +out_unlock: + xfs_iunlock(ip, XFS_ILOCK_SHARED); + return rval; } /* @@ -614,86 +622,6 @@ xfs_inode_item_committed( } /* - * This gets called by xfs_trans_push_ail(), when IOP_TRYLOCK - * failed to get the inode flush lock but did get the inode locked SHARED. - * Here we're trying to see if the inode buffer is incore, and if so whether it's - * marked delayed write. If that's the case, we'll promote it and that will - * allow the caller to write the buffer by triggering the xfsbufd to run. - */ -STATIC bool -xfs_inode_item_pushbuf( - struct xfs_log_item *lip) -{ - struct xfs_inode_log_item *iip = INODE_ITEM(lip); - struct xfs_inode *ip = iip->ili_inode; - struct xfs_buf *bp; - bool ret = true; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); - - /* - * If a flush is not in progress anymore, chances are that the - * inode was taken off the AIL. So, just get out. - */ - if (!xfs_isiflocked(ip) || - !(lip->li_flags & XFS_LI_IN_AIL)) { - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return true; - } - - bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno, - iip->ili_format.ilf_len, XBF_TRYLOCK); - - xfs_iunlock(ip, XFS_ILOCK_SHARED); - if (!bp) - return true; - if (XFS_BUF_ISDELAYWRITE(bp)) - xfs_buf_delwri_promote(bp); - if (xfs_buf_ispinned(bp)) - ret = false; - xfs_buf_relse(bp); - return ret; -} - -/* - * This is called to asynchronously write the inode associated with this - * inode log item out to disk. The inode will already have been locked by - * a successful call to xfs_inode_item_trylock(). - */ -STATIC void -xfs_inode_item_push( - struct xfs_log_item *lip) -{ - struct xfs_inode_log_item *iip = INODE_ITEM(lip); - struct xfs_inode *ip = iip->ili_inode; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED)); - ASSERT(xfs_isiflocked(ip)); - - /* - * Since we were able to lock the inode's flush lock and - * we found it on the AIL, the inode must be dirty. This - * is because the inode is removed from the AIL while still - * holding the flush lock in xfs_iflush_done(). Thus, if - * we found it in the AIL and were able to obtain the flush - * lock without sleeping, then there must not have been - * anyone in the process of flushing the inode. - */ - ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || iip->ili_fields != 0); - - /* - * Push the inode to it's backing buffer. This will not remove the - * inode from the AIL - a further push will be required to trigger a - * buffer push. However, this allows all the dirty inodes to be pushed - * to the buffer before it is pushed to disk. The buffer IO completion - * will pull the inode from the AIL, mark it clean and unlock the flush - * lock. - */ - (void) xfs_iflush(ip, SYNC_TRYLOCK); - xfs_iunlock(ip, XFS_ILOCK_SHARED); -} - -/* * XXX rcc - this one really has to do something. Probably needs * to stamp in a new field in the incore inode. */ @@ -713,11 +641,9 @@ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_format = xfs_inode_item_format, .iop_pin = xfs_inode_item_pin, .iop_unpin = xfs_inode_item_unpin, - .iop_trylock = xfs_inode_item_trylock, .iop_unlock = xfs_inode_item_unlock, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_pushbuf = xfs_inode_item_pushbuf, .iop_committing = xfs_inode_item_committing }; @@ -848,7 +774,8 @@ xfs_iflush_done( ASSERT(i <= need_ail); } /* xfs_trans_ail_delete_bulk() drops the AIL lock. */ - xfs_trans_ail_delete_bulk(ailp, log_items, i); + xfs_trans_ail_delete_bulk(ailp, log_items, i, + SHUTDOWN_CORRUPT_INCORE); } @@ -869,16 +796,15 @@ xfs_iflush_done( } /* - * This is the inode flushing abort routine. It is called - * from xfs_iflush when the filesystem is shutting down to clean - * up the inode state. - * It is responsible for removing the inode item - * from the AIL if it has not been re-logged, and unlocking the inode's - * flush lock. + * This is the inode flushing abort routine. It is called from xfs_iflush when + * the filesystem is shutting down to clean up the inode state. It is + * responsible for removing the inode item from the AIL if it has not been + * re-logged, and unlocking the inode's flush lock. */ void xfs_iflush_abort( - xfs_inode_t *ip) + xfs_inode_t *ip, + bool stale) { xfs_inode_log_item_t *iip = ip->i_itemp; @@ -888,7 +814,10 @@ xfs_iflush_abort( spin_lock(&ailp->xa_lock); if (iip->ili_item.li_flags & XFS_LI_IN_AIL) { /* xfs_trans_ail_delete() drops the AIL lock. */ - xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip); + xfs_trans_ail_delete(ailp, &iip->ili_item, + stale ? + SHUTDOWN_LOG_IO_ERROR : + SHUTDOWN_CORRUPT_INCORE); } else spin_unlock(&ailp->xa_lock); } @@ -915,7 +844,7 @@ xfs_istale_done( struct xfs_buf *bp, struct xfs_log_item *lip) { - xfs_iflush_abort(INODE_ITEM(lip)->ili_inode); + xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true); } /* diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h index 41d61c3b7a3..376d4d0b263 100644 --- a/fs/xfs/xfs_inode_item.h +++ b/fs/xfs/xfs_inode_item.h @@ -165,7 +165,7 @@ extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *); extern void xfs_inode_item_destroy(struct xfs_inode *); extern void xfs_iflush_done(struct xfs_buf *, struct xfs_log_item *); extern void xfs_istale_done(struct xfs_buf *, struct xfs_log_item *); -extern void xfs_iflush_abort(struct xfs_inode *); +extern void xfs_iflush_abort(struct xfs_inode *, bool); extern int xfs_inode_item_format_convert(xfs_log_iovec_t *, xfs_inode_log_format_t *); diff --git a/fs/xfs/xfs_inum.h b/fs/xfs/xfs_inum.h index b253c0ea5be..90efdaf1706 100644 --- a/fs/xfs/xfs_inum.h +++ b/fs/xfs/xfs_inum.h @@ -26,11 +26,6 @@ * high agno_log-agblklog-inopblog bits - 0 */ -typedef __uint32_t xfs_agino_t; /* within allocation grp inode number */ - -#define NULLFSINO ((xfs_ino_t)-1) -#define NULLAGINO ((xfs_agino_t)-1) - struct xfs_mount; #define XFS_INO_MASK(k) (__uint32_t)((1ULL << (k)) - 1) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 91f8ff547ab..3a05a41b5d7 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index a849a5473af..c4f2da0d2bf 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -22,9 +22,7 @@ #include <asm/uaccess.h> #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 71a464503c4..aadfce6681e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -37,7 +35,6 @@ #include "xfs_rtalloc.h" #include "xfs_error.h" #include "xfs_itable.h" -#include "xfs_rw.h" #include "xfs_attr.h" #include "xfs_buf_item.h" #include "xfs_trans_space.h" @@ -142,11 +139,7 @@ xfs_iomap_write_direct( int committed; int error; - /* - * Make sure that the dquots are there. This doesn't hold - * the ilock across a disk read. - */ - error = xfs_qm_dqattach_locked(ip, 0); + error = xfs_qm_dqattach(ip, 0); if (error) return XFS_ERROR(error); @@ -158,7 +151,7 @@ xfs_iomap_write_direct( if ((offset + count) > XFS_ISIZE(ip)) { error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb); if (error) - goto error_out; + return XFS_ERROR(error); } else { if (nmaps && (imap->br_startblock == HOLESTARTBLOCK)) last_fsb = MIN(last_fsb, (xfs_fileoff_t) @@ -190,7 +183,6 @@ xfs_iomap_write_direct( /* * Allocate and setup the transaction */ - xfs_iunlock(ip, XFS_ILOCK_EXCL); tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT); error = xfs_trans_reserve(tp, resblks, XFS_WRITE_LOG_RES(mp), resrtextents, @@ -199,15 +191,16 @@ xfs_iomap_write_direct( /* * Check for running out of space, note: need lock to return */ - if (error) + if (error) { xfs_trans_cancel(tp, 0); + return XFS_ERROR(error); + } + xfs_ilock(ip, XFS_ILOCK_EXCL); - if (error) - goto error_out; error = xfs_trans_reserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); if (error) - goto error1; + goto out_trans_cancel; xfs_trans_ijoin(tp, ip, 0); @@ -224,42 +217,39 @@ xfs_iomap_write_direct( error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb, bmapi_flag, &firstfsb, 0, imap, &nimaps, &free_list); if (error) - goto error0; + goto out_bmap_cancel; /* * Complete the transaction */ error = xfs_bmap_finish(&tp, &free_list, &committed); if (error) - goto error0; + goto out_bmap_cancel; error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES); if (error) - goto error_out; + goto out_unlock; /* * Copy any maps to caller's array and return any error. */ if (nimaps == 0) { - error = ENOSPC; - goto error_out; + error = XFS_ERROR(ENOSPC); + goto out_unlock; } - if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip))) { + if (!(imap->br_startblock || XFS_IS_REALTIME_INODE(ip))) error = xfs_alert_fsblock_zero(ip, imap); - goto error_out; - } - return 0; +out_unlock: + xfs_iunlock(ip, XFS_ILOCK_EXCL); + return error; -error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */ +out_bmap_cancel: xfs_bmap_cancel(&free_list); - xfs_trans_unreserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); - -error1: /* Just cancel transaction */ + xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); +out_trans_cancel: xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); - -error_out: - return XFS_ERROR(error); + goto out_unlock; } /* @@ -422,6 +412,15 @@ retry: return error; } + /* + * Make sure preallocation does not create extents beyond the range we + * actually support in this filesystem. + */ + if (last_fsb > XFS_B_TO_FSB(mp, mp->m_maxioffset)) + last_fsb = XFS_B_TO_FSB(mp, mp->m_maxioffset); + + ASSERT(last_fsb > offset_fsb); + nimaps = XFS_WRITE_IMAPS; error = xfs_bmapi_delay(ip, offset_fsb, last_fsb - offset_fsb, imap, &nimaps, XFS_BMAPI_ENTIRE); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 3011b879f85..1a25fd80279 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_acl.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -34,7 +32,6 @@ #include "xfs_rtalloc.h" #include "xfs_error.h" #include "xfs_itable.h" -#include "xfs_rw.h" #include "xfs_attr.h" #include "xfs_buf_item.h" #include "xfs_utils.h" @@ -700,7 +697,7 @@ xfs_setattr_size( xfs_off_t oldsize, newsize; struct xfs_trans *tp; int error; - uint lock_flags; + uint lock_flags = 0; uint commit_flags = 0; trace_xfs_setattr(ip); @@ -720,10 +717,10 @@ xfs_setattr_size( ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID| ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0); - lock_flags = XFS_ILOCK_EXCL; - if (!(flags & XFS_ATTR_NOLOCK)) + if (!(flags & XFS_ATTR_NOLOCK)) { lock_flags |= XFS_IOLOCK_EXCL; - xfs_ilock(ip, lock_flags); + xfs_ilock(ip, lock_flags); + } oldsize = inode->i_size; newsize = iattr->ia_size; @@ -746,7 +743,7 @@ xfs_setattr_size( /* * Make sure that the dquots are attached to the inode. */ - error = xfs_qm_dqattach_locked(ip, 0); + error = xfs_qm_dqattach(ip, 0); if (error) goto out_unlock; @@ -768,8 +765,6 @@ xfs_setattr_size( if (error) goto out_unlock; } - xfs_iunlock(ip, XFS_ILOCK_EXCL); - lock_flags &= ~XFS_ILOCK_EXCL; /* * We are going to log the inode size change in this transaction so diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index acc2bf264da..eff577a9b67 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -18,7 +18,6 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 6db1fef38bf..d90d4a38860 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -35,19 +33,26 @@ #include "xfs_trans_priv.h" #include "xfs_dinode.h" #include "xfs_inode.h" -#include "xfs_rw.h" #include "xfs_trace.h" kmem_zone_t *xfs_log_ticket_zone; /* Local miscellaneous function prototypes */ -STATIC int xlog_commit_record(struct log *log, struct xlog_ticket *ticket, - xlog_in_core_t **, xfs_lsn_t *); +STATIC int +xlog_commit_record( + struct xlog *log, + struct xlog_ticket *ticket, + struct xlog_in_core **iclog, + xfs_lsn_t *commitlsnp); + STATIC xlog_t * xlog_alloc_log(xfs_mount_t *mp, xfs_buftarg_t *log_target, xfs_daddr_t blk_offset, int num_bblks); -STATIC int xlog_space_left(struct log *log, atomic64_t *head); +STATIC int +xlog_space_left( + struct xlog *log, + atomic64_t *head); STATIC int xlog_sync(xlog_t *log, xlog_in_core_t *iclog); STATIC void xlog_dealloc_log(xlog_t *log); @@ -67,8 +72,10 @@ STATIC void xlog_state_switch_iclogs(xlog_t *log, int eventual_size); STATIC void xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog); -STATIC void xlog_grant_push_ail(struct log *log, - int need_bytes); +STATIC void +xlog_grant_push_ail( + struct xlog *log, + int need_bytes); STATIC void xlog_regrant_reserve_log_space(xlog_t *log, xlog_ticket_t *ticket); STATIC void xlog_ungrant_log_space(xlog_t *log, @@ -76,7 +83,9 @@ STATIC void xlog_ungrant_log_space(xlog_t *log, #if defined(DEBUG) STATIC void xlog_verify_dest_ptr(xlog_t *log, char *ptr); -STATIC void xlog_verify_grant_tail(struct log *log); +STATIC void +xlog_verify_grant_tail( + struct xlog *log); STATIC void xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog, int count, boolean_t syncing); STATIC void xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog, @@ -92,9 +101,9 @@ STATIC int xlog_iclogs_empty(xlog_t *log); static void xlog_grant_sub_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -118,9 +127,9 @@ xlog_grant_sub_space( static void xlog_grant_add_space( - struct log *log, - atomic64_t *head, - int bytes) + struct xlog *log, + atomic64_t *head, + int bytes) { int64_t head_val = atomic64_read(head); int64_t new, old; @@ -168,7 +177,7 @@ xlog_grant_head_wake_all( static inline int xlog_ticket_reservation( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic) { @@ -185,7 +194,7 @@ xlog_ticket_reservation( STATIC bool xlog_grant_head_wake( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, int *free_bytes) { @@ -207,7 +216,7 @@ xlog_grant_head_wake( STATIC int xlog_grant_head_wait( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int need_bytes) @@ -259,7 +268,7 @@ shutdown: */ STATIC int xlog_grant_head_check( - struct log *log, + struct xlog *log, struct xlog_grant_head *head, struct xlog_ticket *tic, int *need_bytes) @@ -326,7 +335,7 @@ xfs_log_regrant( struct xfs_mount *mp, struct xlog_ticket *tic) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int need_bytes; int error = 0; @@ -392,7 +401,7 @@ xfs_log_reserve( bool permanent, uint t_type) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_ticket *tic; int need_bytes; int error = 0; @@ -468,7 +477,7 @@ xfs_log_done( struct xlog_in_core **iclog, uint flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; xfs_lsn_t lsn = 0; if (XLOG_FORCED_SHUTDOWN(log) || @@ -813,6 +822,7 @@ xfs_log_unmount_write(xfs_mount_t *mp) void xfs_log_unmount(xfs_mount_t *mp) { + cancel_delayed_work_sync(&mp->m_sync_work); xfs_trans_ail_destroy(mp); xlog_dealloc_log(mp->m_log); } @@ -841,7 +851,7 @@ void xfs_log_space_wake( struct xfs_mount *mp) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int free_bytes; if (XLOG_FORCED_SHUTDOWN(log)) @@ -916,27 +926,42 @@ xfs_log_need_covered(xfs_mount_t *mp) * We may be holding the log iclog lock upon entering this routine. */ xfs_lsn_t -xlog_assign_tail_lsn( +xlog_assign_tail_lsn_locked( struct xfs_mount *mp) { + struct xlog *log = mp->m_log; + struct xfs_log_item *lip; xfs_lsn_t tail_lsn; - struct log *log = mp->m_log; + + assert_spin_locked(&mp->m_ail->xa_lock); /* * To make sure we always have a valid LSN for the log tail we keep * track of the last LSN which was committed in log->l_last_sync_lsn, - * and use that when the AIL was empty and xfs_ail_min_lsn returns 0. - * - * If the AIL has been emptied we also need to wake any process - * waiting for this condition. + * and use that when the AIL was empty. */ - tail_lsn = xfs_ail_min_lsn(mp->m_ail); - if (!tail_lsn) + lip = xfs_ail_min(mp->m_ail); + if (lip) + tail_lsn = lip->li_lsn; + else tail_lsn = atomic64_read(&log->l_last_sync_lsn); atomic64_set(&log->l_tail_lsn, tail_lsn); return tail_lsn; } +xfs_lsn_t +xlog_assign_tail_lsn( + struct xfs_mount *mp) +{ + xfs_lsn_t tail_lsn; + + spin_lock(&mp->m_ail->xa_lock); + tail_lsn = xlog_assign_tail_lsn_locked(mp); + spin_unlock(&mp->m_ail->xa_lock); + + return tail_lsn; +} + /* * Return the space in the log between the tail and the head. The head * is passed in the cycle/bytes formal parms. In the special case where @@ -953,7 +978,7 @@ xlog_assign_tail_lsn( */ STATIC int xlog_space_left( - struct log *log, + struct xlog *log, atomic64_t *head) { int free_bytes; @@ -1172,7 +1197,7 @@ xlog_alloc_log(xfs_mount_t *mp, xlog_get_iclog_buffer_size(mp, log); error = ENOMEM; - bp = xfs_buf_alloc(mp->m_logdev_targp, 0, log->l_iclog_size, 0); + bp = xfs_buf_alloc(mp->m_logdev_targp, 0, BTOBB(log->l_iclog_size), 0); if (!bp) goto out_free_log; bp->b_iodone = xlog_iodone; @@ -1182,9 +1207,6 @@ xlog_alloc_log(xfs_mount_t *mp, spin_lock_init(&log->l_icloglock); init_waitqueue_head(&log->l_flush_wait); - /* log record size must be multiple of BBSIZE; see xlog_rec_header_t */ - ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0); - iclogp = &log->l_iclog; /* * The amount of memory to allocate for the iclog structure is @@ -1204,7 +1226,7 @@ xlog_alloc_log(xfs_mount_t *mp, prev_iclog = iclog; bp = xfs_buf_get_uncached(mp->m_logdev_targp, - log->l_iclog_size, 0); + BTOBB(log->l_iclog_size), 0); if (!bp) goto out_free_iclog; @@ -1224,7 +1246,7 @@ xlog_alloc_log(xfs_mount_t *mp, head->h_fmt = cpu_to_be32(XLOG_FMT); memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t)); - iclog->ic_size = XFS_BUF_SIZE(bp) - log->l_iclog_hsize; + iclog->ic_size = BBTOB(bp->b_length) - log->l_iclog_hsize; iclog->ic_state = XLOG_STATE_ACTIVE; iclog->ic_log = log; atomic_set(&iclog->ic_refcnt, 0); @@ -1268,7 +1290,7 @@ out: */ STATIC int xlog_commit_record( - struct log *log, + struct xlog *log, struct xlog_ticket *ticket, struct xlog_in_core **iclog, xfs_lsn_t *commitlsnp) @@ -1302,7 +1324,7 @@ xlog_commit_record( */ STATIC void xlog_grant_push_ail( - struct log *log, + struct xlog *log, int need_bytes) { xfs_lsn_t threshold_lsn = 0; @@ -1475,7 +1497,7 @@ xlog_sync(xlog_t *log, } else { iclog->ic_bwritecnt = 1; } - XFS_BUF_SET_COUNT(bp, count); + bp->b_io_length = BTOBB(count); bp->b_fspriv = iclog; XFS_BUF_ZEROFLAGS(bp); XFS_BUF_ASYNC(bp); @@ -1573,7 +1595,7 @@ xlog_dealloc_log(xlog_t *log) * always need to ensure that the extra buffer does not point to memory * owned by another log buffer before we free it. */ - xfs_buf_set_empty(log->l_xbuf, log->l_iclog_size); + xfs_buf_set_empty(log->l_xbuf, BTOBB(log->l_iclog_size)); xfs_buf_free(log->l_xbuf); iclog = log->l_iclog; @@ -1781,7 +1803,7 @@ xlog_write_start_rec( static xlog_op_header_t * xlog_write_setup_ophdr( - struct log *log, + struct xlog *log, struct xlog_op_header *ophdr, struct xlog_ticket *ticket, uint flags) @@ -1864,7 +1886,7 @@ xlog_write_setup_copy( static int xlog_write_copy_finish( - struct log *log, + struct xlog *log, struct xlog_in_core *iclog, uint flags, int *record_cnt, @@ -1949,7 +1971,7 @@ xlog_write_copy_finish( */ int xlog_write( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket, xfs_lsn_t *start_lsn, @@ -2812,7 +2834,7 @@ _xfs_log_force( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; xfs_lsn_t lsn; @@ -2932,6 +2954,7 @@ xfs_log_force( { int error; + trace_xfs_log_force(mp, 0); error = _xfs_log_force(mp, flags, NULL); if (error) xfs_warn(mp, "%s: error %d returned.", __func__, error); @@ -2959,7 +2982,7 @@ _xfs_log_force_lsn( uint flags, int *log_flushed) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; struct xlog_in_core *iclog; int already_slept = 0; @@ -3080,6 +3103,7 @@ xfs_log_force_lsn( { int error; + trace_xfs_log_force(mp, lsn); error = _xfs_log_force_lsn(mp, lsn, flags, NULL); if (error) xfs_warn(mp, "%s: error %d returned.", __func__, error); @@ -3136,12 +3160,12 @@ xfs_log_ticket_get( */ xlog_ticket_t * xlog_ticket_alloc( - struct log *log, + struct xlog *log, int unit_bytes, int cnt, char client, bool permanent, - int alloc_flags) + xfs_km_flags_t alloc_flags) { struct xlog_ticket *tic; uint num_headers; @@ -3267,7 +3291,7 @@ xlog_ticket_alloc( */ void xlog_verify_dest_ptr( - struct log *log, + struct xlog *log, char *ptr) { int i; @@ -3296,7 +3320,7 @@ xlog_verify_dest_ptr( */ STATIC void xlog_verify_grant_tail( - struct log *log) + struct xlog *log) { int tail_cycle, tail_blocks; int cycle, space; diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h index 2c622bedb30..748d312850e 100644 --- a/fs/xfs/xfs_log.h +++ b/fs/xfs/xfs_log.h @@ -152,6 +152,7 @@ int xfs_log_mount(struct xfs_mount *mp, int num_bblocks); int xfs_log_mount_finish(struct xfs_mount *mp); xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp); +xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp); void xfs_log_space_wake(struct xfs_mount *mp); int xfs_log_notify(struct xfs_mount *mp, struct xlog_in_core *iclog, diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c index d4fadbe8ac9..ddc4529d07d 100644 --- a/fs/xfs/xfs_log_cil.c +++ b/fs/xfs/xfs_log_cil.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_trans_priv.h" #include "xfs_log_priv.h" @@ -29,61 +27,10 @@ #include "xfs_mount.h" #include "xfs_error.h" #include "xfs_alloc.h" +#include "xfs_extent_busy.h" #include "xfs_discard.h" /* - * Perform initial CIL structure initialisation. - */ -int -xlog_cil_init( - struct log *log) -{ - struct xfs_cil *cil; - struct xfs_cil_ctx *ctx; - - cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL); - if (!cil) - return ENOMEM; - - ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL); - if (!ctx) { - kmem_free(cil); - return ENOMEM; - } - - INIT_LIST_HEAD(&cil->xc_cil); - INIT_LIST_HEAD(&cil->xc_committing); - spin_lock_init(&cil->xc_cil_lock); - init_rwsem(&cil->xc_ctx_lock); - init_waitqueue_head(&cil->xc_commit_wait); - - INIT_LIST_HEAD(&ctx->committing); - INIT_LIST_HEAD(&ctx->busy_extents); - ctx->sequence = 1; - ctx->cil = cil; - cil->xc_ctx = ctx; - cil->xc_current_sequence = ctx->sequence; - - cil->xc_log = log; - log->l_cilp = cil; - return 0; -} - -void -xlog_cil_destroy( - struct log *log) -{ - if (log->l_cilp->xc_ctx) { - if (log->l_cilp->xc_ctx->ticket) - xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket); - kmem_free(log->l_cilp->xc_ctx); - } - - ASSERT(list_empty(&log->l_cilp->xc_cil)); - kmem_free(log->l_cilp); -} - -/* * Allocate a new ticket. Failing to get a new ticket makes it really hard to * recover, so we don't allow failure here. Also, we allocate in a context that * we don't want to be issuing transactions from, so we need to tell the @@ -97,7 +44,7 @@ xlog_cil_destroy( */ static struct xlog_ticket * xlog_cil_ticket_alloc( - struct log *log) + struct xlog *log) { struct xlog_ticket *tic; @@ -125,7 +72,7 @@ xlog_cil_ticket_alloc( */ void xlog_cil_init_post_recovery( - struct log *log) + struct xlog *log) { log->l_cilp->xc_ctx->ticket = xlog_cil_ticket_alloc(log); log->l_cilp->xc_ctx->sequence = 1; @@ -235,7 +182,7 @@ xlog_cil_prepare_log_vecs( */ STATIC void xfs_cil_prepare_item( - struct log *log, + struct xlog *log, struct xfs_log_vec *lv, int *len, int *diff_iovecs) @@ -284,7 +231,7 @@ xfs_cil_prepare_item( */ static void xlog_cil_insert_items( - struct log *log, + struct xlog *log, struct xfs_log_vec *log_vector, struct xlog_ticket *ticket) { @@ -390,8 +337,8 @@ xlog_cil_committed( xfs_trans_committed_bulk(ctx->cil->xc_log->l_ailp, ctx->lv_chain, ctx->start_lsn, abort); - xfs_alloc_busy_sort(&ctx->busy_extents); - xfs_alloc_busy_clear(mp, &ctx->busy_extents, + xfs_extent_busy_sort(&ctx->busy_extents); + xfs_extent_busy_clear(mp, &ctx->busy_extents, (mp->m_flags & XFS_MOUNT_DISCARD) && !abort); spin_lock(&ctx->cil->xc_cil_lock); @@ -404,7 +351,7 @@ xlog_cil_committed( ASSERT(mp->m_flags & XFS_MOUNT_DISCARD); xfs_discard_extents(mp, &ctx->busy_extents); - xfs_alloc_busy_clear(mp, &ctx->busy_extents, false); + xfs_extent_busy_clear(mp, &ctx->busy_extents, false); } kmem_free(ctx); @@ -426,8 +373,7 @@ xlog_cil_committed( */ STATIC int xlog_cil_push( - struct log *log, - xfs_lsn_t push_seq) + struct xlog *log) { struct xfs_cil *cil = log->l_cilp; struct xfs_log_vec *lv; @@ -443,39 +389,36 @@ xlog_cil_push( struct xfs_log_iovec lhdr; struct xfs_log_vec lvhdr = { NULL }; xfs_lsn_t commit_lsn; + xfs_lsn_t push_seq; if (!cil) return 0; - ASSERT(!push_seq || push_seq <= cil->xc_ctx->sequence); - new_ctx = kmem_zalloc(sizeof(*new_ctx), KM_SLEEP|KM_NOFS); new_ctx->ticket = xlog_cil_ticket_alloc(log); - /* - * Lock out transaction commit, but don't block for background pushes - * unless we are well over the CIL space limit. See the definition of - * XLOG_CIL_HARD_SPACE_LIMIT() for the full explanation of the logic - * used here. - */ - if (!down_write_trylock(&cil->xc_ctx_lock)) { - if (!push_seq && - cil->xc_ctx->space_used < XLOG_CIL_HARD_SPACE_LIMIT(log)) - goto out_free_ticket; - down_write(&cil->xc_ctx_lock); - } + down_write(&cil->xc_ctx_lock); ctx = cil->xc_ctx; - /* check if we've anything to push */ - if (list_empty(&cil->xc_cil)) - goto out_skip; + spin_lock(&cil->xc_cil_lock); + push_seq = cil->xc_push_seq; + ASSERT(push_seq <= ctx->sequence); - /* check for spurious background flush */ - if (!push_seq && cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) + /* + * Check if we've anything to push. If there is nothing, then we don't + * move on to a new sequence number and so we have to be able to push + * this sequence again later. + */ + if (list_empty(&cil->xc_cil)) { + cil->xc_push_seq = 0; + spin_unlock(&cil->xc_cil_lock); goto out_skip; + } + spin_unlock(&cil->xc_cil_lock); + /* check for a previously pushed seqeunce */ - if (push_seq && push_seq < cil->xc_ctx->sequence) + if (push_seq < cil->xc_ctx->sequence) goto out_skip; /* @@ -629,7 +572,6 @@ restart: out_skip: up_write(&cil->xc_ctx_lock); -out_free_ticket: xfs_log_ticket_put(new_ctx->ticket); kmem_free(new_ctx); return 0; @@ -641,6 +583,82 @@ out_abort: return XFS_ERROR(EIO); } +static void +xlog_cil_push_work( + struct work_struct *work) +{ + struct xfs_cil *cil = container_of(work, struct xfs_cil, + xc_push_work); + xlog_cil_push(cil->xc_log); +} + +/* + * We need to push CIL every so often so we don't cache more than we can fit in + * the log. The limit really is that a checkpoint can't be more than half the + * log (the current checkpoint is not allowed to overwrite the previous + * checkpoint), but commit latency and memory usage limit this to a smaller + * size. + */ +static void +xlog_cil_push_background( + struct xlog *log) +{ + struct xfs_cil *cil = log->l_cilp; + + /* + * The cil won't be empty because we are called while holding the + * context lock so whatever we added to the CIL will still be there + */ + ASSERT(!list_empty(&cil->xc_cil)); + + /* + * don't do a background push if we haven't used up all the + * space available yet. + */ + if (cil->xc_ctx->space_used < XLOG_CIL_SPACE_LIMIT(log)) + return; + + spin_lock(&cil->xc_cil_lock); + if (cil->xc_push_seq < cil->xc_current_sequence) { + cil->xc_push_seq = cil->xc_current_sequence; + queue_work(log->l_mp->m_cil_workqueue, &cil->xc_push_work); + } + spin_unlock(&cil->xc_cil_lock); + +} + +static void +xlog_cil_push_foreground( + struct xlog *log, + xfs_lsn_t push_seq) +{ + struct xfs_cil *cil = log->l_cilp; + + if (!cil) + return; + + ASSERT(push_seq && push_seq <= cil->xc_current_sequence); + + /* start on any pending background push to minimise wait time on it */ + flush_work(&cil->xc_push_work); + + /* + * If the CIL is empty or we've already pushed the sequence then + * there's no work we need to do. + */ + spin_lock(&cil->xc_cil_lock); + if (list_empty(&cil->xc_cil) || push_seq <= cil->xc_push_seq) { + spin_unlock(&cil->xc_cil_lock); + return; + } + + cil->xc_push_seq = push_seq; + spin_unlock(&cil->xc_cil_lock); + + /* do the push now */ + xlog_cil_push(log); +} + /* * Commit a transaction with the given vector to the Committed Item List. * @@ -665,9 +683,8 @@ xfs_log_commit_cil( xfs_lsn_t *commit_lsn, int flags) { - struct log *log = mp->m_log; + struct xlog *log = mp->m_log; int log_flags = 0; - int push = 0; struct xfs_log_vec *log_vector; if (flags & XFS_TRANS_RELEASE_LOG_RES) @@ -719,21 +736,9 @@ xfs_log_commit_cil( */ xfs_trans_free_items(tp, *commit_lsn, 0); - /* check for background commit before unlock */ - if (log->l_cilp->xc_ctx->space_used > XLOG_CIL_SPACE_LIMIT(log)) - push = 1; + xlog_cil_push_background(log); up_read(&log->l_cilp->xc_ctx_lock); - - /* - * We need to push CIL every so often so we don't cache more than we - * can fit in the log. The limit really is that a checkpoint can't be - * more than half the log (the current checkpoint is not allowed to - * overwrite the previous checkpoint), but commit latency and memory - * usage limit this to a smaller size in most cases. - */ - if (push) - xlog_cil_push(log, 0); return 0; } @@ -746,13 +751,10 @@ xfs_log_commit_cil( * * We return the current commit lsn to allow the callers to determine if a * iclog flush is necessary following this call. - * - * XXX: Initially, just push the CIL unconditionally and return whatever - * commit lsn is there. It'll be empty, so this is broken for now. */ xfs_lsn_t xlog_cil_force_lsn( - struct log *log, + struct xlog *log, xfs_lsn_t sequence) { struct xfs_cil *cil = log->l_cilp; @@ -766,8 +768,7 @@ xlog_cil_force_lsn( * xlog_cil_push() handles racing pushes for the same sequence, * so no need to deal with it here. */ - if (sequence == cil->xc_current_sequence) - xlog_cil_push(log, sequence); + xlog_cil_push_foreground(log, sequence); /* * See if we can find a previous sequence still committing. @@ -826,3 +827,57 @@ xfs_log_item_in_current_chkpt( return false; return true; } + +/* + * Perform initial CIL structure initialisation. + */ +int +xlog_cil_init( + struct xlog *log) +{ + struct xfs_cil *cil; + struct xfs_cil_ctx *ctx; + + cil = kmem_zalloc(sizeof(*cil), KM_SLEEP|KM_MAYFAIL); + if (!cil) + return ENOMEM; + + ctx = kmem_zalloc(sizeof(*ctx), KM_SLEEP|KM_MAYFAIL); + if (!ctx) { + kmem_free(cil); + return ENOMEM; + } + + INIT_WORK(&cil->xc_push_work, xlog_cil_push_work); + INIT_LIST_HEAD(&cil->xc_cil); + INIT_LIST_HEAD(&cil->xc_committing); + spin_lock_init(&cil->xc_cil_lock); + init_rwsem(&cil->xc_ctx_lock); + init_waitqueue_head(&cil->xc_commit_wait); + + INIT_LIST_HEAD(&ctx->committing); + INIT_LIST_HEAD(&ctx->busy_extents); + ctx->sequence = 1; + ctx->cil = cil; + cil->xc_ctx = ctx; + cil->xc_current_sequence = ctx->sequence; + + cil->xc_log = log; + log->l_cilp = cil; + return 0; +} + +void +xlog_cil_destroy( + struct xlog *log) +{ + if (log->l_cilp->xc_ctx) { + if (log->l_cilp->xc_ctx->ticket) + xfs_log_ticket_put(log->l_cilp->xc_ctx->ticket); + kmem_free(log->l_cilp->xc_ctx); + } + + ASSERT(list_empty(&log->l_cilp->xc_cil)); + kmem_free(log->l_cilp); +} + diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h index 2152900b79d..72eba2201b1 100644 --- a/fs/xfs/xfs_log_priv.h +++ b/fs/xfs/xfs_log_priv.h @@ -19,7 +19,7 @@ #define __XFS_LOG_PRIV_H__ struct xfs_buf; -struct log; +struct xlog; struct xlog_ticket; struct xfs_mount; @@ -352,7 +352,7 @@ typedef struct xlog_in_core { struct xlog_in_core *ic_next; struct xlog_in_core *ic_prev; struct xfs_buf *ic_bp; - struct log *ic_log; + struct xlog *ic_log; int ic_size; int ic_offset; int ic_bwritecnt; @@ -409,7 +409,7 @@ struct xfs_cil_ctx { * operations almost as efficient as the old logging methods. */ struct xfs_cil { - struct log *xc_log; + struct xlog *xc_log; struct list_head xc_cil; spinlock_t xc_cil_lock; struct xfs_cil_ctx *xc_ctx; @@ -417,6 +417,8 @@ struct xfs_cil { struct list_head xc_committing; wait_queue_head_t xc_commit_wait; xfs_lsn_t xc_current_sequence; + struct work_struct xc_push_work; + xfs_lsn_t xc_push_seq; }; /* @@ -485,7 +487,7 @@ struct xlog_grant_head { * overflow 31 bits worth of byte offset, so using a byte number will mean * that round off problems won't occur when releasing partial reservations. */ -typedef struct log { +typedef struct xlog { /* The following fields don't need locking */ struct xfs_mount *l_mp; /* mount point */ struct xfs_ail *l_ailp; /* AIL log is working with */ @@ -551,9 +553,14 @@ extern int xlog_recover_finish(xlog_t *log); extern void xlog_pack_data(xlog_t *log, xlog_in_core_t *iclog, int); extern kmem_zone_t *xfs_log_ticket_zone; -struct xlog_ticket *xlog_ticket_alloc(struct log *log, int unit_bytes, - int count, char client, bool permanent, - int alloc_flags); +struct xlog_ticket * +xlog_ticket_alloc( + struct xlog *log, + int unit_bytes, + int count, + char client, + bool permanent, + xfs_km_flags_t alloc_flags); static inline void @@ -565,9 +572,14 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes) } void xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket); -int xlog_write(struct log *log, struct xfs_log_vec *log_vector, - struct xlog_ticket *tic, xfs_lsn_t *start_lsn, - xlog_in_core_t **commit_iclog, uint flags); +int +xlog_write( + struct xlog *log, + struct xfs_log_vec *log_vector, + struct xlog_ticket *tic, + xfs_lsn_t *start_lsn, + struct xlog_in_core **commit_iclog, + uint flags); /* * When we crack an atomic LSN, we sample it first so that the value will not @@ -627,17 +639,23 @@ xlog_assign_grant_head(atomic64_t *head, int cycle, int space) /* * Committed Item List interfaces */ -int xlog_cil_init(struct log *log); -void xlog_cil_init_post_recovery(struct log *log); -void xlog_cil_destroy(struct log *log); +int +xlog_cil_init(struct xlog *log); +void +xlog_cil_init_post_recovery(struct xlog *log); +void +xlog_cil_destroy(struct xlog *log); /* * CIL force routines */ -xfs_lsn_t xlog_cil_force_lsn(struct log *log, xfs_lsn_t sequence); +xfs_lsn_t +xlog_cil_force_lsn( + struct xlog *log, + xfs_lsn_t sequence); static inline void -xlog_cil_force(struct log *log) +xlog_cil_force(struct xlog *log) { xlog_cil_force_lsn(log, log->l_cilp->xc_current_sequence); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 8ecad5bad66..a7be98abd6a 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -40,7 +40,6 @@ #include "xfs_extfree_item.h" #include "xfs_trans_priv.h" #include "xfs_quota.h" -#include "xfs_rw.h" #include "xfs_utils.h" #include "xfs_trace.h" @@ -120,7 +119,7 @@ xlog_get_bp( nbblks += log->l_sectBBsize; nbblks = round_up(nbblks, log->l_sectBBsize); - bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, BBTOB(nbblks), 0); + bp = xfs_buf_get_uncached(log->l_mp->m_logdev_targp, nbblks, 0); if (bp) xfs_buf_unlock(bp); return bp; @@ -146,7 +145,7 @@ xlog_align( { xfs_daddr_t offset = blk_no & ((xfs_daddr_t)log->l_sectBBsize - 1); - ASSERT(BBTOB(offset + nbblks) <= XFS_BUF_SIZE(bp)); + ASSERT(offset + nbblks <= bp->b_length); return bp->b_addr + BBTOB(offset); } @@ -174,11 +173,12 @@ xlog_bread_noalign( nbblks = round_up(nbblks, log->l_sectBBsize); ASSERT(nbblks > 0); - ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp)); + ASSERT(nbblks <= bp->b_length); XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); XFS_BUF_READ(bp); - XFS_BUF_SET_COUNT(bp, BBTOB(nbblks)); + bp->b_io_length = nbblks; + bp->b_error = 0; xfsbdstrat(log->l_mp, bp); error = xfs_buf_iowait(bp); @@ -218,7 +218,7 @@ xlog_bread_offset( xfs_caddr_t offset) { xfs_caddr_t orig_offset = bp->b_addr; - int orig_len = bp->b_buffer_length; + int orig_len = BBTOB(bp->b_length); int error, error2; error = xfs_buf_associate_memory(bp, offset, BBTOB(nbblks)); @@ -259,13 +259,14 @@ xlog_bwrite( nbblks = round_up(nbblks, log->l_sectBBsize); ASSERT(nbblks > 0); - ASSERT(BBTOB(nbblks) <= XFS_BUF_SIZE(bp)); + ASSERT(nbblks <= bp->b_length); XFS_BUF_SET_ADDR(bp, log->l_logBBstart + blk_no); XFS_BUF_ZEROFLAGS(bp); xfs_buf_hold(bp); xfs_buf_lock(bp); - XFS_BUF_SET_COUNT(bp, BBTOB(nbblks)); + bp->b_io_length = nbblks; + bp->b_error = 0; error = xfs_bwrite(bp); if (error) @@ -440,6 +441,8 @@ xlog_find_verify_cycle( * a log sector, or we're out of luck. */ bufblks = 1 << ffs(nbblks); + while (bufblks > log->l_logBBsize) + bufblks >>= 1; while (!(bp = xlog_get_bp(log, bufblks))) { bufblks >>= 1; if (bufblks < log->l_sectBBsize) @@ -1225,6 +1228,8 @@ xlog_write_log_records( * log sector, or we're out of luck. */ bufblks = 1 << ffs(blocks); + while (bufblks > log->l_logBBsize) + bufblks >>= 1; while (!(bp = xlog_get_bp(log, bufblks))) { bufblks >>= 1; if (bufblks < sectbb) @@ -1466,8 +1471,8 @@ xlog_recover_add_item( STATIC int xlog_recover_add_to_cont_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1512,8 +1517,8 @@ xlog_recover_add_to_cont_trans( */ STATIC int xlog_recover_add_to_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, xfs_caddr_t dp, int len) { @@ -1583,8 +1588,8 @@ xlog_recover_add_to_trans( */ STATIC int xlog_recover_reorder_trans( - struct log *log, - xlog_recover_t *trans, + struct xlog *log, + struct xlog_recover *trans, int pass) { xlog_recover_item_t *item, *n; @@ -1637,8 +1642,8 @@ xlog_recover_reorder_trans( */ STATIC int xlog_recover_buffer_pass1( - struct log *log, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover_item *item) { xfs_buf_log_format_t *buf_f = item->ri_buf[0].i_addr; struct list_head *bucket; @@ -1691,7 +1696,7 @@ xlog_recover_buffer_pass1( */ STATIC int xlog_check_buffer_cancelled( - struct log *log, + struct xlog *log, xfs_daddr_t blkno, uint len, ushort flags) @@ -1772,7 +1777,7 @@ xlog_recover_do_inode_buffer( trace_xfs_log_recover_buf_inode_buf(mp->m_log, buf_f); - inodes_per_buf = XFS_BUF_COUNT(bp) >> mp->m_sb.sb_inodelog; + inodes_per_buf = BBTOB(bp->b_io_length) >> mp->m_sb.sb_inodelog; for (i = 0; i < inodes_per_buf; i++) { next_unlinked_offset = (i * mp->m_sb.sb_inodesize) + offsetof(xfs_dinode_t, di_next_unlinked); @@ -1814,7 +1819,8 @@ xlog_recover_do_inode_buffer( ASSERT(item->ri_buf[item_index].i_addr != NULL); ASSERT((item->ri_buf[item_index].i_len % XFS_BLF_CHUNK) == 0); - ASSERT((reg_buf_offset + reg_buf_bytes) <= XFS_BUF_COUNT(bp)); + ASSERT((reg_buf_offset + reg_buf_bytes) <= + BBTOB(bp->b_io_length)); /* * The current logged region contains a copy of the @@ -1873,8 +1879,8 @@ xlog_recover_do_reg_buffer( ASSERT(nbits > 0); ASSERT(item->ri_buf[i].i_addr != NULL); ASSERT(item->ri_buf[i].i_len % XFS_BLF_CHUNK == 0); - ASSERT(XFS_BUF_COUNT(bp) >= - ((uint)bit << XFS_BLF_SHIFT)+(nbits<<XFS_BLF_SHIFT)); + ASSERT(BBTOB(bp->b_io_length) >= + ((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT)); /* * Do a sanity check if this is a dquot buffer. Just checking @@ -2103,6 +2109,7 @@ xlog_recover_do_dquot_buffer( STATIC int xlog_recover_buffer_pass2( xlog_t *log, + struct list_head *buffer_list, xlog_recover_item_t *item) { xfs_buf_log_format_t *buf_f = item->ri_buf[0].i_addr; @@ -2123,9 +2130,9 @@ xlog_recover_buffer_pass2( trace_xfs_log_recover_buf_recover(log, buf_f); - buf_flags = XBF_LOCK; - if (!(buf_f->blf_flags & XFS_BLF_INODE_BUF)) - buf_flags |= XBF_MAPPED; + buf_flags = 0; + if (buf_f->blf_flags & XFS_BLF_INODE_BUF) + buf_flags |= XBF_UNMAPPED; bp = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len, buf_flags); @@ -2166,14 +2173,14 @@ xlog_recover_buffer_pass2( */ if (XFS_DINODE_MAGIC == be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) && - (XFS_BUF_COUNT(bp) != MAX(log->l_mp->m_sb.sb_blocksize, + (BBTOB(bp->b_io_length) != MAX(log->l_mp->m_sb.sb_blocksize, (__uint32_t)XFS_INODE_CLUSTER_SIZE(log->l_mp)))) { xfs_buf_stale(bp); error = xfs_bwrite(bp); } else { ASSERT(bp->b_target->bt_mount == mp); bp->b_iodone = xlog_recover_iodone; - xfs_buf_delwri_queue(bp); + xfs_buf_delwri_queue(bp, buffer_list); } xfs_buf_relse(bp); @@ -2183,6 +2190,7 @@ xlog_recover_buffer_pass2( STATIC int xlog_recover_inode_pass2( xlog_t *log, + struct list_head *buffer_list, xlog_recover_item_t *item) { xfs_inode_log_format_t *in_f; @@ -2220,8 +2228,7 @@ xlog_recover_inode_pass2( } trace_xfs_log_recover_inode_recover(log, in_f); - bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, - XBF_LOCK); + bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0); if (!bp) { error = ENOMEM; goto error; @@ -2436,7 +2443,7 @@ xlog_recover_inode_pass2( write_inode_buffer: ASSERT(bp->b_target->bt_mount == mp); bp->b_iodone = xlog_recover_iodone; - xfs_buf_delwri_queue(bp); + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); error: if (need_free) @@ -2477,6 +2484,7 @@ xlog_recover_quotaoff_pass1( STATIC int xlog_recover_dquot_pass2( xlog_t *log, + struct list_head *buffer_list, xlog_recover_item_t *item) { xfs_mount_t *mp = log->l_mp; @@ -2530,14 +2538,11 @@ xlog_recover_dquot_pass2( return XFS_ERROR(EIO); ASSERT(dq_f->qlf_len == 1); - error = xfs_read_buf(mp, mp->m_ddev_targp, - dq_f->qlf_blkno, - XFS_FSB_TO_BB(mp, dq_f->qlf_len), - 0, &bp); - if (error) { - xfs_buf_ioerror_alert(bp, "xlog_recover_do..(read#3)"); + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dq_f->qlf_blkno, + XFS_FSB_TO_BB(mp, dq_f->qlf_len), 0, &bp); + if (error) return error; - } + ASSERT(bp); ddq = (xfs_disk_dquot_t *)xfs_buf_offset(bp, dq_f->qlf_boffset); @@ -2558,7 +2563,7 @@ xlog_recover_dquot_pass2( ASSERT(dq_f->qlf_size == 2); ASSERT(bp->b_target->bt_mount == mp); bp->b_iodone = xlog_recover_iodone; - xfs_buf_delwri_queue(bp); + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); return (0); @@ -2642,7 +2647,8 @@ xlog_recover_efd_pass2( * xfs_trans_ail_delete() drops the * AIL lock. */ - xfs_trans_ail_delete(ailp, lip); + xfs_trans_ail_delete(ailp, lip, + SHUTDOWN_CORRUPT_INCORE); xfs_efi_item_free(efip); spin_lock(&ailp->xa_lock); break; @@ -2683,9 +2689,9 @@ xlog_recover_free_trans( STATIC int xlog_recover_commit_pass1( - struct log *log, - struct xlog_recover *trans, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS1); @@ -2710,23 +2716,24 @@ xlog_recover_commit_pass1( STATIC int xlog_recover_commit_pass2( - struct log *log, - struct xlog_recover *trans, - xlog_recover_item_t *item) + struct xlog *log, + struct xlog_recover *trans, + struct list_head *buffer_list, + struct xlog_recover_item *item) { trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS2); switch (ITEM_TYPE(item)) { case XFS_LI_BUF: - return xlog_recover_buffer_pass2(log, item); + return xlog_recover_buffer_pass2(log, buffer_list, item); case XFS_LI_INODE: - return xlog_recover_inode_pass2(log, item); + return xlog_recover_inode_pass2(log, buffer_list, item); case XFS_LI_EFI: return xlog_recover_efi_pass2(log, item, trans->r_lsn); case XFS_LI_EFD: return xlog_recover_efd_pass2(log, item); case XFS_LI_DQUOT: - return xlog_recover_dquot_pass2(log, item); + return xlog_recover_dquot_pass2(log, buffer_list, item); case XFS_LI_QUOTAOFF: /* nothing to do in pass2 */ return 0; @@ -2746,12 +2753,13 @@ xlog_recover_commit_pass2( */ STATIC int xlog_recover_commit_trans( - struct log *log, + struct xlog *log, struct xlog_recover *trans, int pass) { - int error = 0; + int error = 0, error2; xlog_recover_item_t *item; + LIST_HEAD (buffer_list); hlist_del(&trans->r_list); @@ -2760,22 +2768,33 @@ xlog_recover_commit_trans( return error; list_for_each_entry(item, &trans->r_itemq, ri_list) { - if (pass == XLOG_RECOVER_PASS1) + switch (pass) { + case XLOG_RECOVER_PASS1: error = xlog_recover_commit_pass1(log, trans, item); - else - error = xlog_recover_commit_pass2(log, trans, item); + break; + case XLOG_RECOVER_PASS2: + error = xlog_recover_commit_pass2(log, trans, + &buffer_list, item); + break; + default: + ASSERT(0); + } + if (error) - return error; + goto out; } xlog_recover_free_trans(trans); - return 0; + +out: + error2 = xfs_buf_delwri_submit(&buffer_list); + return error ? error : error2; } STATIC int xlog_recover_unmount_trans( - struct log *log, - xlog_recover_t *trans) + struct xlog *log, + struct xlog_recover *trans) { /* Do nothing now */ xfs_warn(log->l_mp, "%s: Unmount LR", __func__); @@ -3079,7 +3098,7 @@ xlog_recover_process_one_iunlink( /* * Get the on disk inode to find the next inode in the bucket. */ - error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XBF_LOCK); + error = xfs_itobp(mp, NULL, ip, &dip, &ibp, 0); if (error) goto fail_iput; @@ -3639,11 +3658,8 @@ xlog_do_recover( * First replay the images in the log. */ error = xlog_do_log_recovery(log, head_blk, tail_blk); - if (error) { + if (error) return error; - } - - xfs_flush_buftarg(log->l_mp->m_ddev_targp, 1); /* * If IO errors happened during recovery, bail out. @@ -3670,7 +3686,6 @@ xlog_do_recover( bp = xfs_getsb(log->l_mp, 0); XFS_BUF_UNDONE(bp); ASSERT(!(XFS_BUF_ISWRITE(bp))); - ASSERT(!(XFS_BUF_ISDELAYWRITE(bp))); XFS_BUF_READ(bp); XFS_BUF_UNASYNC(bp); xfsbdstrat(log->l_mp, bp); diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index bd672def95a..331cd9f83a7 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 1ffead4b229..536021fb3d4 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -22,6 +22,7 @@ #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" +#include "xfs_trans_priv.h" #include "xfs_sb.h" #include "xfs_ag.h" #include "xfs_dir2.h" @@ -37,7 +38,6 @@ #include "xfs_rtalloc.h" #include "xfs_bmap.h" #include "xfs_error.h" -#include "xfs_rw.h" #include "xfs_quota.h" #include "xfs_fsops.h" #include "xfs_utils.h" @@ -683,8 +683,8 @@ xfs_readsb(xfs_mount_t *mp, int flags) sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); reread: - bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, - XFS_SB_DADDR, sector_size, 0); + bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, + BTOBB(sector_size), 0); if (!bp) { if (loud) xfs_warn(mp, "SB buffer read failed"); @@ -1032,9 +1032,9 @@ xfs_check_sizes(xfs_mount_t *mp) xfs_warn(mp, "filesystem size mismatch detected"); return XFS_ERROR(EFBIG); } - bp = xfs_buf_read_uncached(mp, mp->m_ddev_targp, + bp = xfs_buf_read_uncached(mp->m_ddev_targp, d - XFS_FSS_TO_BB(mp, 1), - BBTOB(XFS_FSS_TO_BB(mp, 1)), 0); + XFS_FSS_TO_BB(mp, 1), 0); if (!bp) { xfs_warn(mp, "last sector read failed"); return EIO; @@ -1047,9 +1047,9 @@ xfs_check_sizes(xfs_mount_t *mp) xfs_warn(mp, "log size mismatch detected"); return XFS_ERROR(EFBIG); } - bp = xfs_buf_read_uncached(mp, mp->m_logdev_targp, + bp = xfs_buf_read_uncached(mp->m_logdev_targp, d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_B(mp, 1), 0); + XFS_FSB_TO_BB(mp, 1), 0); if (!bp) { xfs_warn(mp, "log device read failed"); return EIO; @@ -1288,7 +1288,7 @@ xfs_mountfs( XFS_FSB_TO_BB(mp, sbp->sb_logblocks)); if (error) { xfs_warn(mp, "log mount failed"); - goto out_free_perag; + goto out_fail_wait; } /* @@ -1315,7 +1315,7 @@ xfs_mountfs( !mp->m_sb.sb_inprogress) { error = xfs_initialize_perag_data(mp, sbp->sb_agcount); if (error) - goto out_free_perag; + goto out_fail_wait; } /* @@ -1439,6 +1439,10 @@ xfs_mountfs( IRELE(rip); out_log_dealloc: xfs_log_unmount(mp); + out_fail_wait: + if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) + xfs_wait_buftarg(mp->m_logdev_targp); + xfs_wait_buftarg(mp->m_ddev_targp); out_free_perag: xfs_free_perag(mp); out_remove_uuid: @@ -1475,15 +1479,15 @@ xfs_unmountfs( xfs_log_force(mp, XFS_LOG_SYNC); /* - * Do a delwri reclaim pass first so that as many dirty inodes are - * queued up for IO as possible. Then flush the buffers before making - * a synchronous path to catch all the remaining inodes are reclaimed. - * This makes the reclaim process as quick as possible by avoiding - * synchronous writeout and blocking on inodes already in the delwri - * state as much as possible. + * Flush all pending changes from the AIL. + */ + xfs_ail_push_all_sync(mp->m_ail); + + /* + * And reclaim all inodes. At this point there should be no dirty + * inode, and none should be pinned or locked, but use synchronous + * reclaim just to be sure. */ - xfs_reclaim_inodes(mp, 0); - xfs_flush_buftarg(mp->m_ddev_targp, 1); xfs_reclaim_inodes(mp, SYNC_WAIT); xfs_qm_unmount(mp); @@ -1519,15 +1523,12 @@ xfs_unmountfs( if (error) xfs_warn(mp, "Unable to update superblock counters. " "Freespace may not be correct on next mount."); - xfs_unmountfs_writesb(mp); /* - * Make sure all buffers have been flushed and completed before - * unmounting the log. + * At this point we might have modified the superblock again and thus + * added an item to the AIL, thus flush it again. */ - error = xfs_flush_buftarg(mp->m_ddev_targp, 1); - if (error) - xfs_warn(mp, "%d busy buffers during unmount.", error); + xfs_ail_push_all_sync(mp->m_ail); xfs_wait_buftarg(mp->m_ddev_targp); xfs_log_unmount_write(mp); @@ -1588,36 +1589,6 @@ xfs_log_sbcount(xfs_mount_t *mp) return error; } -int -xfs_unmountfs_writesb(xfs_mount_t *mp) -{ - xfs_buf_t *sbp; - int error = 0; - - /* - * skip superblock write if fs is read-only, or - * if we are doing a forced umount. - */ - if (!((mp->m_flags & XFS_MOUNT_RDONLY) || - XFS_FORCED_SHUTDOWN(mp))) { - - sbp = xfs_getsb(mp, 0); - - XFS_BUF_UNDONE(sbp); - XFS_BUF_UNREAD(sbp); - xfs_buf_delwri_dequeue(sbp); - XFS_BUF_WRITE(sbp); - XFS_BUF_UNASYNC(sbp); - ASSERT(sbp->b_target == mp->m_ddev_targp); - xfsbdstrat(mp, sbp); - error = xfs_buf_iowait(sbp); - if (error) - xfs_buf_ioerror_alert(sbp, __func__); - xfs_buf_relse(sbp); - } - return error; -} - /* * xfs_mod_sb() can be used to copy arbitrary changes to the * in-core superblock into the superblock buffer to be logged. diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 9eba7388782..90c1fc9eaea 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -53,7 +53,7 @@ typedef struct xfs_trans_reservations { #include "xfs_sync.h" -struct log; +struct xlog; struct xfs_mount_args; struct xfs_inode; struct xfs_bmbt_irec; @@ -133,7 +133,7 @@ typedef struct xfs_mount { uint m_readio_blocks; /* min read size blocks */ uint m_writeio_log; /* min write size log bytes */ uint m_writeio_blocks; /* min write size blocks */ - struct log *m_log; /* log specific stuff */ + struct xlog *m_log; /* log specific stuff */ int m_logbufs; /* number of log buffers */ int m_logbsize; /* size of each log buffer */ uint m_rsumlevels; /* rt summary levels */ @@ -214,6 +214,7 @@ typedef struct xfs_mount { struct workqueue_struct *m_data_workqueue; struct workqueue_struct *m_unwritten_workqueue; + struct workqueue_struct *m_cil_workqueue; } xfs_mount_t; /* @@ -378,7 +379,6 @@ extern __uint64_t xfs_default_resblks(xfs_mount_t *mp); extern int xfs_mountfs(xfs_mount_t *mp); extern void xfs_unmountfs(xfs_mount_t *); -extern int xfs_unmountfs_writesb(xfs_mount_t *); extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int); extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *, uint, int); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 55c6afedc87..249db198776 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -65,7 +64,8 @@ STATIC int xfs_qm_dquot_walk( struct xfs_mount *mp, int type, - int (*execute)(struct xfs_dquot *dqp)) + int (*execute)(struct xfs_dquot *dqp, void *data), + void *data) { struct xfs_quotainfo *qi = mp->m_quotainfo; struct radix_tree_root *tree = XFS_DQUOT_TREE(qi, type); @@ -97,7 +97,7 @@ restart: next_index = be32_to_cpu(dqp->q_core.d_id) + 1; - error = execute(batch[i]); + error = execute(batch[i], data); if (error == EAGAIN) { skipped++; continue; @@ -129,7 +129,8 @@ restart: */ STATIC int xfs_qm_dqpurge( - struct xfs_dquot *dqp) + struct xfs_dquot *dqp, + void *data) { struct xfs_mount *mp = dqp->q_mount; struct xfs_quotainfo *qi = mp->m_quotainfo; @@ -153,21 +154,7 @@ xfs_qm_dqpurge( dqp->dq_flags |= XFS_DQ_FREEING; - /* - * If we're turning off quotas, we have to make sure that, for - * example, we don't delete quota disk blocks while dquots are - * in the process of getting written to those disk blocks. - * This dquot might well be on AIL, and we can't leave it there - * if we're turning off quotas. Basically, we need this flush - * lock, and are willing to block on it. - */ - if (!xfs_dqflock_nowait(dqp)) { - /* - * Block on the flush lock after nudging dquot buffer, - * if it is incore. - */ - xfs_dqflock_pushbuf_wait(dqp); - } + xfs_dqflock(dqp); /* * If we are turning this type of quotas off, we don't care @@ -175,16 +162,21 @@ xfs_qm_dqpurge( * we're unmounting, we do care, so we flush it and wait. */ if (XFS_DQ_IS_DIRTY(dqp)) { - int error; + struct xfs_buf *bp = NULL; + int error; /* * We don't care about getting disk errors here. We need * to purge this dquot anyway, so we go ahead regardless. */ - error = xfs_qm_dqflush(dqp, SYNC_WAIT); - if (error) + error = xfs_qm_dqflush(dqp, &bp); + if (error) { xfs_warn(mp, "%s: dquot %p flush failed", __func__, dqp); + } else { + error = xfs_bwrite(bp); + xfs_buf_relse(bp); + } xfs_dqflock(dqp); } @@ -226,11 +218,11 @@ xfs_qm_dqpurge_all( uint flags) { if (flags & XFS_QMOPT_UQUOTA) - xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge); + xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL); if (flags & XFS_QMOPT_GQUOTA) - xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge); + xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL); if (flags & XFS_QMOPT_PQUOTA) - xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge); + xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge, NULL); } /* @@ -483,6 +475,23 @@ done: xfs_dqunlock(udq); } +static bool +xfs_qm_need_dqattach( + struct xfs_inode *ip) +{ + struct xfs_mount *mp = ip->i_mount; + + if (!XFS_IS_QUOTA_RUNNING(mp)) + return false; + if (!XFS_IS_QUOTA_ON(mp)) + return false; + if (!XFS_NOT_DQATTACHED(mp, ip)) + return false; + if (ip->i_ino == mp->m_sb.sb_uquotino || + ip->i_ino == mp->m_sb.sb_gquotino) + return false; + return true; +} /* * Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON @@ -500,11 +509,7 @@ xfs_qm_dqattach_locked( uint nquotas = 0; int error = 0; - if (!XFS_IS_QUOTA_RUNNING(mp) || - !XFS_IS_QUOTA_ON(mp) || - !XFS_NOT_DQATTACHED(mp, ip) || - ip->i_ino == mp->m_sb.sb_uquotino || - ip->i_ino == mp->m_sb.sb_gquotino) + if (!xfs_qm_need_dqattach(ip)) return 0; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); @@ -575,6 +580,9 @@ xfs_qm_dqattach( { int error; + if (!xfs_qm_need_dqattach(ip)) + return 0; + xfs_ilock(ip, XFS_ILOCK_EXCL); error = xfs_qm_dqattach_locked(ip, flags); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -855,15 +863,16 @@ xfs_qm_reset_dqcounts( STATIC int xfs_qm_dqiter_bufs( - xfs_mount_t *mp, - xfs_dqid_t firstid, - xfs_fsblock_t bno, - xfs_filblks_t blkcnt, - uint flags) + struct xfs_mount *mp, + xfs_dqid_t firstid, + xfs_fsblock_t bno, + xfs_filblks_t blkcnt, + uint flags, + struct list_head *buffer_list) { - xfs_buf_t *bp; - int error; - int type; + struct xfs_buf *bp; + int error; + int type; ASSERT(blkcnt > 0); type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER : @@ -887,7 +896,7 @@ xfs_qm_dqiter_bufs( break; xfs_qm_reset_dqcounts(mp, bp, firstid, type); - xfs_buf_delwri_queue(bp); + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); /* * goto the next block. @@ -895,6 +904,7 @@ xfs_qm_dqiter_bufs( bno++; firstid += mp->m_quotainfo->qi_dqperchunk; } + return error; } @@ -904,11 +914,12 @@ xfs_qm_dqiter_bufs( */ STATIC int xfs_qm_dqiterate( - xfs_mount_t *mp, - xfs_inode_t *qip, - uint flags) + struct xfs_mount *mp, + struct xfs_inode *qip, + uint flags, + struct list_head *buffer_list) { - xfs_bmbt_irec_t *map; + struct xfs_bmbt_irec *map; int i, nmaps; /* number of map entries */ int error; /* return value */ xfs_fileoff_t lblkno; @@ -975,21 +986,17 @@ xfs_qm_dqiterate( * Iterate thru all the blks in the extent and * reset the counters of all the dquots inside them. */ - if ((error = xfs_qm_dqiter_bufs(mp, - firstid, - map[i].br_startblock, - map[i].br_blockcount, - flags))) { - break; - } + error = xfs_qm_dqiter_bufs(mp, firstid, + map[i].br_startblock, + map[i].br_blockcount, + flags, buffer_list); + if (error) + goto out; } - - if (error) - break; } while (nmaps > 0); +out: kmem_free(map); - return error; } @@ -1182,8 +1189,11 @@ error0: STATIC int xfs_qm_flush_one( - struct xfs_dquot *dqp) + struct xfs_dquot *dqp, + void *data) { + struct list_head *buffer_list = data; + struct xfs_buf *bp = NULL; int error = 0; xfs_dqlock(dqp); @@ -1192,11 +1202,13 @@ xfs_qm_flush_one( if (!XFS_DQ_IS_DIRTY(dqp)) goto out_unlock; - if (!xfs_dqflock_nowait(dqp)) - xfs_dqflock_pushbuf_wait(dqp); - - error = xfs_qm_dqflush(dqp, 0); + xfs_dqflock(dqp); + error = xfs_qm_dqflush(dqp, &bp); + if (error) + goto out_unlock; + xfs_buf_delwri_queue(bp, buffer_list); + xfs_buf_relse(bp); out_unlock: xfs_dqunlock(dqp); return error; @@ -1215,6 +1227,7 @@ xfs_qm_quotacheck( size_t structsz; xfs_inode_t *uip, *gip; uint flags; + LIST_HEAD (buffer_list); count = INT_MAX; structsz = 1; @@ -1233,7 +1246,8 @@ xfs_qm_quotacheck( */ uip = mp->m_quotainfo->qi_uquotaip; if (uip) { - error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA); + error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA, + &buffer_list); if (error) goto error_return; flags |= XFS_UQUOTA_CHKD; @@ -1242,7 +1256,8 @@ xfs_qm_quotacheck( gip = mp->m_quotainfo->qi_gquotaip; if (gip) { error = xfs_qm_dqiterate(mp, gip, XFS_IS_GQUOTA_ON(mp) ? - XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA); + XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA, + &buffer_list); if (error) goto error_return; flags |= XFS_OQUOTA_CHKD; @@ -1265,19 +1280,27 @@ xfs_qm_quotacheck( * We've made all the changes that we need to make incore. Flush them * down to disk buffers if everything was updated successfully. */ - if (XFS_IS_UQUOTA_ON(mp)) - error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one); + if (XFS_IS_UQUOTA_ON(mp)) { + error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one, + &buffer_list); + } if (XFS_IS_GQUOTA_ON(mp)) { - error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one); + error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one, + &buffer_list); if (!error) error = error2; } if (XFS_IS_PQUOTA_ON(mp)) { - error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one); + error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one, + &buffer_list); if (!error) error = error2; } + error2 = xfs_buf_delwri_submit(&buffer_list); + if (!error) + error = error2; + /* * We can get this error if we couldn't do a dquot allocation inside * xfs_qm_dqusage_adjust (via bulkstat). We don't care about the @@ -1291,15 +1314,6 @@ xfs_qm_quotacheck( } /* - * We didn't log anything, because if we crashed, we'll have to - * start the quotacheck from scratch anyway. However, we must make - * sure that our dquot changes are secure before we put the - * quotacheck'd stamp on the superblock. So, here we do a synchronous - * flush. - */ - xfs_flush_buftarg(mp->m_ddev_targp, 1); - - /* * If one type of quotas is off, then it will lose its * quotachecked status, since we won't be doing accounting for * that type anymore. @@ -1308,6 +1322,13 @@ xfs_qm_quotacheck( mp->m_qflags |= flags; error_return: + while (!list_empty(&buffer_list)) { + struct xfs_buf *bp = + list_first_entry(&buffer_list, struct xfs_buf, b_list); + list_del_init(&bp->b_list); + xfs_buf_relse(bp); + } + if (error) { xfs_warn(mp, "Quotacheck: Unsuccessful (Error %d): Disabling quotas.", @@ -1424,6 +1445,7 @@ xfs_qm_dqfree_one( STATIC void xfs_qm_dqreclaim_one( struct xfs_dquot *dqp, + struct list_head *buffer_list, struct list_head *dispose_list) { struct xfs_mount *mp = dqp->q_mount; @@ -1456,25 +1478,20 @@ xfs_qm_dqreclaim_one( if (!xfs_dqflock_nowait(dqp)) goto out_busy; - /* - * We have the flush lock so we know that this is not in the - * process of being flushed. So, if this is dirty, flush it - * DELWRI so that we don't get a freelist infested with - * dirty dquots. - */ if (XFS_DQ_IS_DIRTY(dqp)) { + struct xfs_buf *bp = NULL; + trace_xfs_dqreclaim_dirty(dqp); - /* - * We flush it delayed write, so don't bother releasing the - * freelist lock. - */ - error = xfs_qm_dqflush(dqp, 0); + error = xfs_qm_dqflush(dqp, &bp); if (error) { xfs_warn(mp, "%s: dquot %p flush failed", __func__, dqp); + goto out_busy; } + xfs_buf_delwri_queue(bp, buffer_list); + xfs_buf_relse(bp); /* * Give the dquot another try on the freelist, as the * flushing will take some time. @@ -1518,8 +1535,10 @@ xfs_qm_shake( struct xfs_quotainfo *qi = container_of(shrink, struct xfs_quotainfo, qi_shrinker); int nr_to_scan = sc->nr_to_scan; + LIST_HEAD (buffer_list); LIST_HEAD (dispose_list); struct xfs_dquot *dqp; + int error; if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT)) return 0; @@ -1532,15 +1551,20 @@ xfs_qm_shake( break; dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot, q_lru); - xfs_qm_dqreclaim_one(dqp, &dispose_list); + xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list); } mutex_unlock(&qi->qi_lru_lock); + error = xfs_buf_delwri_submit(&buffer_list); + if (error) + xfs_warn(NULL, "%s: dquot reclaim failed", __func__); + while (!list_empty(&dispose_list)) { dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru); list_del_init(&dqp->q_lru); xfs_qm_dqfree_one(dqp); } + out: return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure; } diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index e6986b5d80d..6b39115bf14 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c index c4f396e437a..858a3b18611 100644 --- a/fs/xfs/xfs_qm_syscalls.c +++ b/fs/xfs/xfs_qm_syscalls.c @@ -22,7 +22,6 @@ #include "xfs_fs.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c index 7e76f537abb..fed504fc299 100644 --- a/fs/xfs/xfs_quotaops.c +++ b/fs/xfs/xfs_quotaops.c @@ -17,7 +17,6 @@ */ #include "xfs.h" #include "xfs_sb.h" -#include "xfs_inum.h" #include "xfs_log.h" #include "xfs_ag.h" #include "xfs_mount.h" diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c index e44ef7ee8ce..30ff5f401d2 100644 --- a/fs/xfs/xfs_rename.c +++ b/fs/xfs/xfs_rename.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index ca4f31534a0..92d4331cd4f 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -20,7 +20,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -34,7 +33,6 @@ #include "xfs_rtalloc.h" #include "xfs_fsops.h" #include "xfs_error.h" -#include "xfs_rw.h" #include "xfs_inode_item.h" #include "xfs_trans_space.h" #include "xfs_utils.h" @@ -1872,9 +1870,9 @@ xfs_growfs_rt( /* * Read in the last block of the device, make sure it exists. */ - bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp, + bp = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, nrblocks - 1), - XFS_FSB_TO_B(mp, 1), 0); + XFS_FSB_TO_BB(mp, 1), 0); if (!bp) return EIO; xfs_buf_relse(bp); @@ -2219,9 +2217,9 @@ xfs_rtmount_init( (unsigned long long) mp->m_sb.sb_rblocks); return XFS_ERROR(EFBIG); } - bp = xfs_buf_read_uncached(mp, mp->m_rtdev_targp, + bp = xfs_buf_read_uncached(mp->m_rtdev_targp, d - XFS_FSB_TO_BB(mp, 1), - XFS_FSB_TO_B(mp, 1), 0); + XFS_FSB_TO_BB(mp, 1), 0); if (!bp) { xfs_warn(mp, "realtime device size check failed"); return EIO; diff --git a/fs/xfs/xfs_rw.c b/fs/xfs/xfs_rw.c deleted file mode 100644 index 597d044a09a..00000000000 --- a/fs/xfs/xfs_rw.c +++ /dev/null @@ -1,156 +0,0 @@ -/* - * Copyright (c) 2000-2006 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#include "xfs.h" -#include "xfs_fs.h" -#include "xfs_types.h" -#include "xfs_bit.h" -#include "xfs_log.h" -#include "xfs_inum.h" -#include "xfs_trans.h" -#include "xfs_sb.h" -#include "xfs_ag.h" -#include "xfs_mount.h" -#include "xfs_bmap_btree.h" -#include "xfs_dinode.h" -#include "xfs_inode.h" -#include "xfs_error.h" -#include "xfs_rw.h" - -/* - * Force a shutdown of the filesystem instantly while keeping - * the filesystem consistent. We don't do an unmount here; just shutdown - * the shop, make sure that absolutely nothing persistent happens to - * this filesystem after this point. - */ -void -xfs_do_force_shutdown( - xfs_mount_t *mp, - int flags, - char *fname, - int lnnum) -{ - int logerror; - - logerror = flags & SHUTDOWN_LOG_IO_ERROR; - - if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - xfs_notice(mp, - "%s(0x%x) called from line %d of file %s. Return address = 0x%p", - __func__, flags, lnnum, fname, __return_address); - } - /* - * No need to duplicate efforts. - */ - if (XFS_FORCED_SHUTDOWN(mp) && !logerror) - return; - - /* - * This flags XFS_MOUNT_FS_SHUTDOWN, makes sure that we don't - * queue up anybody new on the log reservations, and wakes up - * everybody who's sleeping on log reservations to tell them - * the bad news. - */ - if (xfs_log_force_umount(mp, logerror)) - return; - - if (flags & SHUTDOWN_CORRUPT_INCORE) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT, - "Corruption of in-memory data detected. Shutting down filesystem"); - if (XFS_ERRLEVEL_HIGH <= xfs_error_level) - xfs_stack_trace(); - } else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - if (logerror) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR, - "Log I/O Error Detected. Shutting down filesystem"); - } else if (flags & SHUTDOWN_DEVICE_REQ) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, - "All device paths lost. Shutting down filesystem"); - } else if (!(flags & SHUTDOWN_REMOTE_REQ)) { - xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR, - "I/O Error Detected. Shutting down filesystem"); - } - } - if (!(flags & SHUTDOWN_FORCE_UMOUNT)) { - xfs_alert(mp, - "Please umount the filesystem and rectify the problem(s)"); - } -} - -/* - * This isn't an absolute requirement, but it is - * just a good idea to call xfs_read_buf instead of - * directly doing a read_buf call. For one, we shouldn't - * be doing this disk read if we are in SHUTDOWN state anyway, - * so this stops that from happening. Secondly, this does all - * the error checking stuff and the brelse if appropriate for - * the caller, so the code can be a little leaner. - */ - -int -xfs_read_buf( - struct xfs_mount *mp, - xfs_buftarg_t *target, - xfs_daddr_t blkno, - int len, - uint flags, - xfs_buf_t **bpp) -{ - xfs_buf_t *bp; - int error; - - if (!flags) - flags = XBF_LOCK | XBF_MAPPED; - - bp = xfs_buf_read(target, blkno, len, flags); - if (!bp) - return XFS_ERROR(EIO); - error = bp->b_error; - if (!error && !XFS_FORCED_SHUTDOWN(mp)) { - *bpp = bp; - } else { - *bpp = NULL; - if (error) { - xfs_buf_ioerror_alert(bp, __func__); - } else { - error = XFS_ERROR(EIO); - } - if (bp) { - XFS_BUF_UNDONE(bp); - xfs_buf_stale(bp); - /* - * brelse clears B_ERROR and b_error - */ - xfs_buf_relse(bp); - } - } - return (error); -} - -/* - * helper function to extract extent size hint from inode - */ -xfs_extlen_t -xfs_get_extsz_hint( - struct xfs_inode *ip) -{ - if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize) - return ip->i_d.di_extsize; - if (XFS_IS_REALTIME_INODE(ip)) - return ip->i_mount->m_sb.sb_rextsize; - return 0; -} diff --git a/fs/xfs/xfs_rw.h b/fs/xfs/xfs_rw.h deleted file mode 100644 index bbdb9ad6a4b..00000000000 --- a/fs/xfs/xfs_rw.h +++ /dev/null @@ -1,47 +0,0 @@ -/* - * Copyright (c) 2000-2006 Silicon Graphics, Inc. - * All Rights Reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it would be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write the Free Software Foundation, - * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA - */ -#ifndef __XFS_RW_H__ -#define __XFS_RW_H__ - -struct xfs_buf; -struct xfs_inode; -struct xfs_mount; - -/* - * Convert the given file system block to a disk block. - * We have to treat it differently based on whether the - * file is a real time file or not, because the bmap code - * does. - */ -static inline xfs_daddr_t -xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb) -{ - return (XFS_IS_REALTIME_INODE(ip) ? \ - (xfs_daddr_t)XFS_FSB_TO_BB((ip)->i_mount, (fsb)) : \ - XFS_FSB_TO_DADDR((ip)->i_mount, (fsb))); -} - -/* - * Prototypes for functions in xfs_rw.c. - */ -extern int xfs_read_buf(struct xfs_mount *mp, xfs_buftarg_t *btp, - xfs_daddr_t blkno, int len, uint flags, - struct xfs_buf **bpp); -extern xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); - -#endif /* __XFS_RW_H__ */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index dab9a5f6dfd..0d9de41a715 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -17,7 +17,6 @@ */ #include "xfs.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" @@ -622,7 +621,7 @@ void xfs_blkdev_issue_flush( xfs_buftarg_t *buftarg) { - blkdev_issue_flush(buftarg->bt_bdev, GFP_KERNEL, NULL); + blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL); } STATIC void @@ -773,8 +772,14 @@ xfs_init_mount_workqueues( if (!mp->m_unwritten_workqueue) goto out_destroy_data_iodone_queue; + mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s", + WQ_MEM_RECLAIM, 0, mp->m_fsname); + if (!mp->m_cil_workqueue) + goto out_destroy_unwritten; return 0; +out_destroy_unwritten: + destroy_workqueue(mp->m_unwritten_workqueue); out_destroy_data_iodone_queue: destroy_workqueue(mp->m_data_workqueue); out: @@ -785,6 +790,7 @@ STATIC void xfs_destroy_mount_workqueues( struct xfs_mount *mp) { + destroy_workqueue(mp->m_cil_workqueue); destroy_workqueue(mp->m_data_workqueue); destroy_workqueue(mp->m_unwritten_workqueue); } @@ -926,7 +932,7 @@ xfs_fs_evict_inode( trace_xfs_evict_inode(ip); truncate_inode_pages(&inode->i_data, 0); - end_writeback(inode); + clear_inode(inode); XFS_STATS_INC(vn_rele); XFS_STATS_INC(vn_remove); XFS_STATS_DEC(vn_active); @@ -981,18 +987,9 @@ xfs_fs_put_super( { struct xfs_mount *mp = XFS_M(sb); - xfs_syncd_stop(mp); - - /* - * Blow away any referenced inode in the filestreams cache. - * This can and will cause log traffic as inodes go inactive - * here. - */ xfs_filestream_unmount(mp); - - xfs_flush_buftarg(mp->m_ddev_targp, 1); - xfs_unmountfs(mp); + xfs_syncd_stop(mp); xfs_freesb(mp); xfs_icsb_destroy_counters(mp); xfs_destroy_mount_workqueues(mp); @@ -1072,7 +1069,7 @@ xfs_fs_statfs( spin_unlock(&mp->m_sb_lock); - if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) || + if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) && ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_OQUOTA_ENFD)) xfs_qm_statvfs(ip, statp); @@ -1362,31 +1359,32 @@ xfs_fs_fill_super( sb->s_time_gran = 1; set_posix_acl_flag(sb); - error = xfs_mountfs(mp); + error = xfs_syncd_init(mp); if (error) goto out_filestream_unmount; - error = xfs_syncd_init(mp); + error = xfs_mountfs(mp); if (error) - goto out_unmount; + goto out_syncd_stop; root = igrab(VFS_I(mp->m_rootip)); if (!root) { error = ENOENT; - goto out_syncd_stop; + goto out_unmount; } if (is_bad_inode(root)) { error = EINVAL; - goto out_syncd_stop; + goto out_unmount; } sb->s_root = d_make_root(root); if (!sb->s_root) { error = ENOMEM; - goto out_syncd_stop; + goto out_unmount; } return 0; - + out_syncd_stop: + xfs_syncd_stop(mp); out_filestream_unmount: xfs_filestream_unmount(mp); out_free_sb: @@ -1403,19 +1401,10 @@ out_destroy_workqueues: out: return -error; - out_syncd_stop: - xfs_syncd_stop(mp); out_unmount: - /* - * Blow away any referenced inode in the filestreams cache. - * This can and will cause log traffic as inodes go inactive - * here. - */ xfs_filestream_unmount(mp); - - xfs_flush_buftarg(mp->m_ddev_targp, 1); - xfs_unmountfs(mp); + xfs_syncd_stop(mp); goto out_free_sb; } diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index 205ebcb34d9..1e9ee064dbb 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -18,7 +18,6 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" #include "xfs_inum.h" #include "xfs_trans.h" @@ -241,45 +240,6 @@ xfs_sync_inode_data( return error; } -STATIC int -xfs_sync_inode_attr( - struct xfs_inode *ip, - struct xfs_perag *pag, - int flags) -{ - int error = 0; - - xfs_ilock(ip, XFS_ILOCK_SHARED); - if (xfs_inode_clean(ip)) - goto out_unlock; - if (!xfs_iflock_nowait(ip)) { - if (!(flags & SYNC_WAIT)) - goto out_unlock; - xfs_iflock(ip); - } - - if (xfs_inode_clean(ip)) { - xfs_ifunlock(ip); - goto out_unlock; - } - - error = xfs_iflush(ip, flags); - - /* - * We don't want to try again on non-blocking flushes that can't run - * again immediately. If an inode really must be written, then that's - * what the SYNC_WAIT flag is for. - */ - if (error == EAGAIN) { - ASSERT(!(flags & SYNC_WAIT)); - error = 0; - } - - out_unlock: - xfs_iunlock(ip, XFS_ILOCK_SHARED); - return error; -} - /* * Write out pagecache data for the whole filesystem. */ @@ -300,19 +260,6 @@ xfs_sync_data( return 0; } -/* - * Write out inode metadata (attributes) for the whole filesystem. - */ -STATIC int -xfs_sync_attr( - struct xfs_mount *mp, - int flags) -{ - ASSERT((flags & ~SYNC_WAIT) == 0); - - return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags); -} - STATIC int xfs_sync_fsdata( struct xfs_mount *mp) @@ -350,7 +297,7 @@ xfs_sync_fsdata( * First stage of freeze - no writers will make progress now we are here, * so we flush delwri and delalloc buffers here, then wait for all I/O to * complete. Data is frozen at that point. Metadata is not frozen, - * transactions can still occur here so don't bother flushing the buftarg + * transactions can still occur here so don't bother emptying the AIL * because it'll just get dirty again. */ int @@ -365,47 +312,13 @@ xfs_quiesce_data( /* write superblock and hoover up shutdown errors */ error = xfs_sync_fsdata(mp); - /* make sure all delwri buffers are written out */ - xfs_flush_buftarg(mp->m_ddev_targp, 1); - /* mark the log as covered if needed */ if (xfs_log_need_covered(mp)) error2 = xfs_fs_log_dummy(mp); - /* flush data-only devices */ - if (mp->m_rtdev_targp) - xfs_flush_buftarg(mp->m_rtdev_targp, 1); - return error ? error : error2; } -STATIC void -xfs_quiesce_fs( - struct xfs_mount *mp) -{ - int count = 0, pincount; - - xfs_reclaim_inodes(mp, 0); - xfs_flush_buftarg(mp->m_ddev_targp, 0); - - /* - * This loop must run at least twice. The first instance of the loop - * will flush most meta data but that will generate more meta data - * (typically directory updates). Which then must be flushed and - * logged before we can write the unmount record. We also so sync - * reclaim of inodes to catch any that the above delwri flush skipped. - */ - do { - xfs_reclaim_inodes(mp, SYNC_WAIT); - xfs_sync_attr(mp, SYNC_WAIT); - pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1); - if (!pincount) { - delay(50); - count++; - } - } while (count < 2); -} - /* * Second stage of a quiesce. The data is already synced, now we have to take * care of the metadata. New transactions are already blocked, so we need to @@ -421,8 +334,12 @@ xfs_quiesce_attr( while (atomic_read(&mp->m_active_trans) > 0) delay(100); - /* flush inodes and push all remaining buffers out to disk */ - xfs_quiesce_fs(mp); + /* reclaim inodes to do any IO before the freeze completes */ + xfs_reclaim_inodes(mp, 0); + xfs_reclaim_inodes(mp, SYNC_WAIT); + + /* flush all pending changes from the AIL */ + xfs_ail_push_all_sync(mp->m_ail); /* * Just warn here till VFS can correctly support @@ -436,7 +353,12 @@ xfs_quiesce_attr( xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. " "Frozen image may not be consistent."); xfs_log_unmount_write(mp); - xfs_unmountfs_writesb(mp); + + /* + * At this point we might have modified the superblock again and thus + * added an item to the AIL, thus flush it again. + */ + xfs_ail_push_all_sync(mp->m_ail); } static void @@ -460,7 +382,17 @@ xfs_sync_worker( struct xfs_mount, m_sync_work); int error; - if (!(mp->m_flags & XFS_MOUNT_RDONLY)) { + /* + * We shouldn't write/force the log if we are in the mount/unmount + * process or on a read only filesystem. The workqueue still needs to be + * active in both cases, however, because it is used for inode reclaim + * during these times. Use the MS_ACTIVE flag to avoid doing anything + * during mount. Doing work during unmount is avoided by calling + * cancel_delayed_work_sync on this work queue before tearing down + * the ail and the log in xfs_log_unmount. + */ + if (!(mp->m_super->s_flags & MS_ACTIVE) && + !(mp->m_flags & XFS_MOUNT_RDONLY)) { /* dgc: errors ignored here */ if (mp->m_super->s_frozen == SB_UNFROZEN && xfs_log_need_covered(mp)) @@ -468,7 +400,8 @@ xfs_sync_worker( else xfs_log_force(mp, 0); - /* start pushing all the metadata that is currently dirty */ + /* start pushing all the metadata that is currently + * dirty */ xfs_ail_push_all(mp->m_ail); } @@ -488,14 +421,6 @@ xfs_syncd_queue_reclaim( struct xfs_mount *mp) { - /* - * We can have inodes enter reclaim after we've shut down the syncd - * workqueue during unmount, so don't allow reclaim work to be queued - * during unmount. - */ - if (!(mp->m_super->s_flags & MS_ACTIVE)) - return; - rcu_read_lock(); if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) { queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work, @@ -564,7 +489,6 @@ xfs_syncd_init( INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker); xfs_syncd_queue_sync(mp); - xfs_syncd_queue_reclaim(mp); return 0; } @@ -702,11 +626,8 @@ xfs_reclaim_inode_grab( } /* - * Inodes in different states need to be treated differently, and the return - * value of xfs_iflush is not sufficient to get this right. The following table - * lists the inode states and the reclaim actions necessary for non-blocking - * reclaim: - * + * Inodes in different states need to be treated differently. The following + * table lists the inode states and the reclaim actions necessary: * * inode state iflush ret required action * --------------- ---------- --------------- @@ -716,39 +637,31 @@ xfs_reclaim_inode_grab( * stale, unpinned 0 reclaim * clean, pinned(*) 0 requeue * stale, pinned EAGAIN requeue - * dirty, delwri ok 0 requeue - * dirty, delwri blocked EAGAIN requeue - * dirty, sync flush 0 reclaim + * dirty, async - requeue + * dirty, sync 0 reclaim * * (*) dgc: I don't think the clean, pinned state is possible but it gets * handled anyway given the order of checks implemented. * - * As can be seen from the table, the return value of xfs_iflush() is not - * sufficient to correctly decide the reclaim action here. The checks in - * xfs_iflush() might look like duplicates, but they are not. - * * Also, because we get the flush lock first, we know that any inode that has * been flushed delwri has had the flush completed by the time we check that - * the inode is clean. The clean inode check needs to be done before flushing - * the inode delwri otherwise we would loop forever requeuing clean inodes as - * we cannot tell apart a successful delwri flush and a clean inode from the - * return value of xfs_iflush(). + * the inode is clean. * - * Note that because the inode is flushed delayed write by background - * writeback, the flush lock may already be held here and waiting on it can - * result in very long latencies. Hence for sync reclaims, where we wait on the - * flush lock, the caller should push out delayed write inodes first before - * trying to reclaim them to minimise the amount of time spent waiting. For - * background relaim, we just requeue the inode for the next pass. + * Note that because the inode is flushed delayed write by AIL pushing, the + * flush lock may already be held here and waiting on it can result in very + * long latencies. Hence for sync reclaims, where we wait on the flush lock, + * the caller should push the AIL first before trying to reclaim inodes to + * minimise the amount of time spent waiting. For background relaim, we only + * bother to reclaim clean inodes anyway. * * Hence the order of actions after gaining the locks should be: * bad => reclaim * shutdown => unpin and reclaim - * pinned, delwri => requeue + * pinned, async => requeue * pinned, sync => unpin * stale => reclaim * clean => reclaim - * dirty, delwri => flush and requeue + * dirty, async => requeue * dirty, sync => flush, wait and reclaim */ STATIC int @@ -757,7 +670,8 @@ xfs_reclaim_inode( struct xfs_perag *pag, int sync_mode) { - int error; + struct xfs_buf *bp = NULL; + int error; restart: error = 0; @@ -765,17 +679,6 @@ restart: if (!xfs_iflock_nowait(ip)) { if (!(sync_mode & SYNC_WAIT)) goto out; - - /* - * If we only have a single dirty inode in a cluster there is - * a fair chance that the AIL push may have pushed it into - * the buffer, but xfsbufd won't touch it until 30 seconds - * from now, and thus we will lock up here. - * - * Promote the inode buffer to the front of the delwri list - * and wake up xfsbufd now. - */ - xfs_promote_inode(ip); xfs_iflock(ip); } @@ -783,13 +686,12 @@ restart: goto reclaim; if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { xfs_iunpin_wait(ip); + xfs_iflush_abort(ip, false); goto reclaim; } if (xfs_ipincount(ip)) { - if (!(sync_mode & SYNC_WAIT)) { - xfs_ifunlock(ip); - goto out; - } + if (!(sync_mode & SYNC_WAIT)) + goto out_ifunlock; xfs_iunpin_wait(ip); } if (xfs_iflags_test(ip, XFS_ISTALE)) @@ -798,60 +700,42 @@ restart: goto reclaim; /* + * Never flush out dirty data during non-blocking reclaim, as it would + * just contend with AIL pushing trying to do the same job. + */ + if (!(sync_mode & SYNC_WAIT)) + goto out_ifunlock; + + /* * Now we have an inode that needs flushing. * - * We do a nonblocking flush here even if we are doing a SYNC_WAIT - * reclaim as we can deadlock with inode cluster removal. + * Note that xfs_iflush will never block on the inode buffer lock, as * xfs_ifree_cluster() can lock the inode buffer before it locks the - * ip->i_lock, and we are doing the exact opposite here. As a result, - * doing a blocking xfs_itobp() to get the cluster buffer will result + * ip->i_lock, and we are doing the exact opposite here. As a result, + * doing a blocking xfs_itobp() to get the cluster buffer would result * in an ABBA deadlock with xfs_ifree_cluster(). * * As xfs_ifree_cluser() must gather all inodes that are active in the * cache to mark them stale, if we hit this case we don't actually want * to do IO here - we want the inode marked stale so we can simply - * reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush, - * just unlock the inode, back off and try again. Hopefully the next - * pass through will see the stale flag set on the inode. + * reclaim it. Hence if we get an EAGAIN error here, just unlock the + * inode, back off and try again. Hopefully the next pass through will + * see the stale flag set on the inode. */ - error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode); - if (sync_mode & SYNC_WAIT) { - if (error == EAGAIN) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - /* backoff longer than in xfs_ifree_cluster */ - delay(2); - goto restart; - } - xfs_iflock(ip); - goto reclaim; + error = xfs_iflush(ip, &bp); + if (error == EAGAIN) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + /* backoff longer than in xfs_ifree_cluster */ + delay(2); + goto restart; } - /* - * When we have to flush an inode but don't have SYNC_WAIT set, we - * flush the inode out using a delwri buffer and wait for the next - * call into reclaim to find it in a clean state instead of waiting for - * it now. We also don't return errors here - if the error is transient - * then the next reclaim pass will flush the inode, and if the error - * is permanent then the next sync reclaim will reclaim the inode and - * pass on the error. - */ - if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) { - xfs_warn(ip->i_mount, - "inode 0x%llx background reclaim flush failed with %d", - (long long)ip->i_ino, error); + if (!error) { + error = xfs_bwrite(bp); + xfs_buf_relse(bp); } -out: - xfs_iflags_clear(ip, XFS_IRECLAIM); - xfs_iunlock(ip, XFS_ILOCK_EXCL); - /* - * We could return EAGAIN here to make reclaim rescan the inode tree in - * a short while. However, this just burns CPU time scanning the tree - * waiting for IO to complete and xfssyncd never goes back to the idle - * state. Instead, return 0 to let the next scheduled background reclaim - * attempt to reclaim the inode again. - */ - return 0; + xfs_iflock(ip); reclaim: xfs_ifunlock(ip); xfs_iunlock(ip, XFS_ILOCK_EXCL); @@ -884,8 +768,21 @@ reclaim: xfs_iunlock(ip, XFS_ILOCK_EXCL); xfs_inode_free(ip); - return error; + +out_ifunlock: + xfs_ifunlock(ip); +out: + xfs_iflags_clear(ip, XFS_IRECLAIM); + xfs_iunlock(ip, XFS_ILOCK_EXCL); + /* + * We could return EAGAIN here to make reclaim rescan the inode tree in + * a short while. However, this just burns CPU time scanning the tree + * waiting for IO to complete and xfssyncd never goes back to the idle + * state. Instead, return 0 to let the next scheduled background reclaim + * attempt to reclaim the inode again. + */ + return 0; } /* diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 9010ce885e6..624bedd8135 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 06838c42b2a..caf5dabfd55 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -32,7 +32,7 @@ struct xfs_da_node_entry; struct xfs_dquot; struct xfs_log_item; struct xlog_ticket; -struct log; +struct xlog; struct xlog_recover; struct xlog_recover_item; struct xfs_buf_log_format; @@ -281,7 +281,7 @@ DECLARE_EVENT_CLASS(xfs_buf_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, bno) - __field(size_t, buffer_length) + __field(int, nblks) __field(int, hold) __field(int, pincount) __field(unsigned, lockval) @@ -291,18 +291,18 @@ DECLARE_EVENT_CLASS(xfs_buf_class, TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = bp->b_bn; - __entry->buffer_length = bp->b_buffer_length; + __entry->nblks = bp->b_length; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; __entry->caller_ip = caller_ip; ), - TP_printk("dev %d:%d bno 0x%llx len 0x%zx hold %d pincount %d " + TP_printk("dev %d:%d bno 0x%llx nblks 0x%x hold %d pincount %d " "lock %d flags %s caller %pf", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, - __entry->buffer_length, + __entry->nblks, __entry->hold, __entry->pincount, __entry->lockval, @@ -328,7 +328,7 @@ DEFINE_BUF_EVENT(xfs_buf_unlock); DEFINE_BUF_EVENT(xfs_buf_iowait); DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); -DEFINE_BUF_EVENT(xfs_buf_delwri_dequeue); +DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_bdstrat_shut); @@ -362,7 +362,7 @@ DECLARE_EVENT_CLASS(xfs_buf_flags_class, TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = bp->b_bn; - __entry->buffer_length = bp->b_buffer_length; + __entry->buffer_length = BBTOB(bp->b_length); __entry->flags = flags; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); @@ -406,7 +406,7 @@ TRACE_EVENT(xfs_buf_ioerror, TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = bp->b_bn; - __entry->buffer_length = bp->b_buffer_length; + __entry->buffer_length = BBTOB(bp->b_length); __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; @@ -450,7 +450,7 @@ DECLARE_EVENT_CLASS(xfs_buf_item_class, __entry->bli_recur = bip->bli_recur; __entry->bli_refcount = atomic_read(&bip->bli_refcount); __entry->buf_bno = bip->bli_buf->b_bn; - __entry->buf_len = bip->bli_buf->b_buffer_length; + __entry->buf_len = BBTOB(bip->bli_buf->b_length); __entry->buf_flags = bip->bli_buf->b_flags; __entry->buf_hold = atomic_read(&bip->bli_buf->b_hold); __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); @@ -486,12 +486,10 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_trylock); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pushbuf); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf_recur); DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb); @@ -764,7 +762,7 @@ DEFINE_DQUOT_EVENT(xfs_dqflush_force); DEFINE_DQUOT_EVENT(xfs_dqflush_done); DECLARE_EVENT_CLASS(xfs_loggrant_class, - TP_PROTO(struct log *log, struct xlog_ticket *tic), + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), TP_ARGS(log, tic), TP_STRUCT__entry( __field(dev_t, dev) @@ -832,7 +830,7 @@ DECLARE_EVENT_CLASS(xfs_loggrant_class, #define DEFINE_LOGGRANT_EVENT(name) \ DEFINE_EVENT(xfs_loggrant_class, name, \ - TP_PROTO(struct log *log, struct xlog_ticket *tic), \ + TP_PROTO(struct xlog *log, struct xlog_ticket *tic), \ TP_ARGS(log, tic)) DEFINE_LOGGRANT_EVENT(xfs_log_done_nonperm); DEFINE_LOGGRANT_EVENT(xfs_log_done_perm); @@ -876,15 +874,30 @@ DECLARE_EVENT_CLASS(xfs_log_item_class, __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) ) +TRACE_EVENT(xfs_log_force, + TP_PROTO(struct xfs_mount *mp, xfs_lsn_t lsn), + TP_ARGS(mp, lsn), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_lsn_t, lsn) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->lsn = lsn; + ), + TP_printk("dev %d:%d lsn 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->lsn) +) + #define DEFINE_LOG_ITEM_EVENT(name) \ DEFINE_EVENT(xfs_log_item_class, name, \ TP_PROTO(struct xfs_log_item *lip), \ TP_ARGS(lip)) DEFINE_LOG_ITEM_EVENT(xfs_ail_push); -DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf); -DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf_pinned); DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned); DEFINE_LOG_ITEM_EVENT(xfs_ail_locked); +DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing); DECLARE_EVENT_CLASS(xfs_file_class, @@ -1145,7 +1158,7 @@ TRACE_EVENT(xfs_bunmap, ); -DECLARE_EVENT_CLASS(xfs_busy_class, +DECLARE_EVENT_CLASS(xfs_extent_busy_class, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t len), TP_ARGS(mp, agno, agbno, len), @@ -1168,17 +1181,17 @@ DECLARE_EVENT_CLASS(xfs_busy_class, __entry->len) ); #define DEFINE_BUSY_EVENT(name) \ -DEFINE_EVENT(xfs_busy_class, name, \ +DEFINE_EVENT(xfs_extent_busy_class, name, \ TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \ xfs_agblock_t agbno, xfs_extlen_t len), \ TP_ARGS(mp, agno, agbno, len)) -DEFINE_BUSY_EVENT(xfs_alloc_busy); -DEFINE_BUSY_EVENT(xfs_alloc_busy_enomem); -DEFINE_BUSY_EVENT(xfs_alloc_busy_force); -DEFINE_BUSY_EVENT(xfs_alloc_busy_reuse); -DEFINE_BUSY_EVENT(xfs_alloc_busy_clear); +DEFINE_BUSY_EVENT(xfs_extent_busy); +DEFINE_BUSY_EVENT(xfs_extent_busy_enomem); +DEFINE_BUSY_EVENT(xfs_extent_busy_force); +DEFINE_BUSY_EVENT(xfs_extent_busy_reuse); +DEFINE_BUSY_EVENT(xfs_extent_busy_clear); -TRACE_EVENT(xfs_alloc_busy_trim, +TRACE_EVENT(xfs_extent_busy_trim, TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t len, xfs_agblock_t tbno, xfs_extlen_t tlen), @@ -1651,7 +1664,7 @@ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); DECLARE_EVENT_CLASS(xfs_log_recover_item_class, - TP_PROTO(struct log *log, struct xlog_recover *trans, + TP_PROTO(struct xlog *log, struct xlog_recover *trans, struct xlog_recover_item *item, int pass), TP_ARGS(log, trans, item, pass), TP_STRUCT__entry( @@ -1685,7 +1698,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_item_class, #define DEFINE_LOG_RECOVER_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_item_class, name, \ - TP_PROTO(struct log *log, struct xlog_recover *trans, \ + TP_PROTO(struct xlog *log, struct xlog_recover *trans, \ struct xlog_recover_item *item, int pass), \ TP_ARGS(log, trans, item, pass)) @@ -1696,7 +1709,7 @@ DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_tail); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_recover); DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), TP_ARGS(log, buf_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1726,7 +1739,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, #define DEFINE_LOG_RECOVER_BUF_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_buf_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_buf_log_format *buf_f), \ + TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), \ TP_ARGS(log, buf_f)) DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_not_cancel); @@ -1739,7 +1752,7 @@ DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_reg_buf); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_dquot_buf); DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), TP_ARGS(log, in_f), TP_STRUCT__entry( __field(dev_t, dev) @@ -1777,7 +1790,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, ) #define DEFINE_LOG_RECOVER_INO_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_ino_item_class, name, \ - TP_PROTO(struct log *log, struct xfs_inode_log_format *in_f), \ + TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), \ TP_ARGS(log, in_f)) DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 103b00c9000..fdf324508c5 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -19,9 +19,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -36,6 +34,7 @@ #include "xfs_btree.h" #include "xfs_ialloc.h" #include "xfs_alloc.h" +#include "xfs_extent_busy.h" #include "xfs_bmap.h" #include "xfs_quota.h" #include "xfs_trans_priv.h" @@ -585,7 +584,7 @@ xfs_trans_t * _xfs_trans_alloc( xfs_mount_t *mp, uint type, - uint memflags) + xfs_km_flags_t memflags) { xfs_trans_t *tp; @@ -608,8 +607,8 @@ STATIC void xfs_trans_free( struct xfs_trans *tp) { - xfs_alloc_busy_sort(&tp->t_busy); - xfs_alloc_busy_clear(tp->t_mountp, &tp->t_busy, false); + xfs_extent_busy_sort(&tp->t_busy); + xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false); atomic_dec(&tp->t_mountp->m_active_trans); xfs_trans_free_dqinfo(tp); diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index f6118703f20..7c37b533aa8 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -345,11 +345,9 @@ struct xfs_item_ops { void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *); void (*iop_pin)(xfs_log_item_t *); void (*iop_unpin)(xfs_log_item_t *, int remove); - uint (*iop_trylock)(xfs_log_item_t *); + uint (*iop_push)(struct xfs_log_item *, struct list_head *); void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); - void (*iop_push)(xfs_log_item_t *); - bool (*iop_pushbuf)(xfs_log_item_t *); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); }; @@ -357,20 +355,18 @@ struct xfs_item_ops { #define IOP_FORMAT(ip,vp) (*(ip)->li_ops->iop_format)(ip, vp) #define IOP_PIN(ip) (*(ip)->li_ops->iop_pin)(ip) #define IOP_UNPIN(ip, remove) (*(ip)->li_ops->iop_unpin)(ip, remove) -#define IOP_TRYLOCK(ip) (*(ip)->li_ops->iop_trylock)(ip) +#define IOP_PUSH(ip, list) (*(ip)->li_ops->iop_push)(ip, list) #define IOP_UNLOCK(ip) (*(ip)->li_ops->iop_unlock)(ip) #define IOP_COMMITTED(ip, lsn) (*(ip)->li_ops->iop_committed)(ip, lsn) -#define IOP_PUSH(ip) (*(ip)->li_ops->iop_push)(ip) -#define IOP_PUSHBUF(ip) (*(ip)->li_ops->iop_pushbuf)(ip) #define IOP_COMMITTING(ip, lsn) (*(ip)->li_ops->iop_committing)(ip, lsn) /* - * Return values for the IOP_TRYLOCK() routines. + * Return values for the IOP_PUSH() routines. */ -#define XFS_ITEM_SUCCESS 0 -#define XFS_ITEM_PINNED 1 -#define XFS_ITEM_LOCKED 2 -#define XFS_ITEM_PUSHBUF 3 +#define XFS_ITEM_SUCCESS 0 +#define XFS_ITEM_PINNED 1 +#define XFS_ITEM_LOCKED 2 +#define XFS_ITEM_FLUSHING 3 /* * This is the type of function which can be given to xfs_trans_callback() @@ -447,7 +443,7 @@ typedef struct xfs_trans { * XFS transaction mechanism exported interfaces. */ xfs_trans_t *xfs_trans_alloc(struct xfs_mount *, uint); -xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint, uint); +xfs_trans_t *_xfs_trans_alloc(struct xfs_mount *, uint, xfs_km_flags_t); xfs_trans_t *xfs_trans_dup(xfs_trans_t *); int xfs_trans_reserve(xfs_trans_t *, uint, uint, uint, uint, uint); diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 1dead07f092..9c514483e59 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -20,7 +20,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -79,7 +78,7 @@ xfs_ail_check( * Return a pointer to the first item in the AIL. If the AIL is empty, then * return NULL. */ -static xfs_log_item_t * +xfs_log_item_t * xfs_ail_min( struct xfs_ail *ailp) { @@ -364,30 +363,31 @@ xfsaild_push( xfs_log_item_t *lip; xfs_lsn_t lsn; xfs_lsn_t target; - long tout = 10; + long tout; int stuck = 0; + int flushing = 0; int count = 0; - int push_xfsbufd = 0; /* - * If last time we ran we encountered pinned items, force the log first - * and wait for it before pushing again. + * If we encountered pinned items or did not finish writing out all + * buffers the last time we ran, force the log first and wait for it + * before pushing again. */ - spin_lock(&ailp->xa_lock); - if (ailp->xa_last_pushed_lsn == 0 && ailp->xa_log_flush && - !list_empty(&ailp->xa_ail)) { + if (ailp->xa_log_flush && ailp->xa_last_pushed_lsn == 0 && + (!list_empty_careful(&ailp->xa_buf_list) || + xfs_ail_min_lsn(ailp))) { ailp->xa_log_flush = 0; - spin_unlock(&ailp->xa_lock); + XFS_STATS_INC(xs_push_ail_flush); xfs_log_force(mp, XFS_LOG_SYNC); - spin_lock(&ailp->xa_lock); } - target = ailp->xa_target; + spin_lock(&ailp->xa_lock); lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn); - if (!lip || XFS_FORCED_SHUTDOWN(mp)) { + if (!lip) { /* - * AIL is empty or our push has reached the end. + * If the AIL is empty or our push has reached the end we are + * done now. */ xfs_trans_ail_cursor_done(ailp, &cur); spin_unlock(&ailp->xa_lock); @@ -396,54 +396,42 @@ xfsaild_push( XFS_STATS_INC(xs_push_ail); - /* - * While the item we are looking at is below the given threshold - * try to flush it out. We'd like not to stop until we've at least - * tried to push on everything in the AIL with an LSN less than - * the given threshold. - * - * However, we will stop after a certain number of pushes and wait - * for a reduced timeout to fire before pushing further. This - * prevents use from spinning when we can't do anything or there is - * lots of contention on the AIL lists. - */ lsn = lip->li_lsn; + target = ailp->xa_target; while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) { int lock_result; + /* - * If we can lock the item without sleeping, unlock the AIL - * lock and flush the item. Then re-grab the AIL lock so we - * can look for the next item on the AIL. List changes are - * handled by the AIL lookup functions internally - * - * If we can't lock the item, either its holder will flush it - * or it is already being flushed or it is being relogged. In - * any of these case it is being taken care of and we can just - * skip to the next item in the list. + * Note that IOP_PUSH may unlock and reacquire the AIL lock. We + * rely on the AIL cursor implementation to be able to deal with + * the dropped lock. */ - lock_result = IOP_TRYLOCK(lip); - spin_unlock(&ailp->xa_lock); + lock_result = IOP_PUSH(lip, &ailp->xa_buf_list); switch (lock_result) { case XFS_ITEM_SUCCESS: XFS_STATS_INC(xs_push_ail_success); trace_xfs_ail_push(lip); - IOP_PUSH(lip); ailp->xa_last_pushed_lsn = lsn; break; - case XFS_ITEM_PUSHBUF: - XFS_STATS_INC(xs_push_ail_pushbuf); - trace_xfs_ail_pushbuf(lip); - - if (!IOP_PUSHBUF(lip)) { - trace_xfs_ail_pushbuf_pinned(lip); - stuck++; - ailp->xa_log_flush++; - } else { - ailp->xa_last_pushed_lsn = lsn; - } - push_xfsbufd = 1; + case XFS_ITEM_FLUSHING: + /* + * The item or its backing buffer is already beeing + * flushed. The typical reason for that is that an + * inode buffer is locked because we already pushed the + * updates to it as part of inode clustering. + * + * We do not want to to stop flushing just because lots + * of items are already beeing flushed, but we need to + * re-try the flushing relatively soon if most of the + * AIL is beeing flushed. + */ + XFS_STATS_INC(xs_push_ail_flushing); + trace_xfs_ail_flushing(lip); + + flushing++; + ailp->xa_last_pushed_lsn = lsn; break; case XFS_ITEM_PINNED: @@ -453,28 +441,22 @@ xfsaild_push( stuck++; ailp->xa_log_flush++; break; - case XFS_ITEM_LOCKED: XFS_STATS_INC(xs_push_ail_locked); trace_xfs_ail_locked(lip); + stuck++; break; - default: ASSERT(0); break; } - spin_lock(&ailp->xa_lock); - /* should we bother continuing? */ - if (XFS_FORCED_SHUTDOWN(mp)) - break; - ASSERT(mp->m_log); - count++; /* * Are there too many items we can't do anything with? + * * If we we are skipping too many items because we can't flush * them or they are already being flushed, we back off and * given them time to complete whatever operation is being @@ -496,42 +478,36 @@ xfsaild_push( xfs_trans_ail_cursor_done(ailp, &cur); spin_unlock(&ailp->xa_lock); - if (push_xfsbufd) { - /* we've got delayed write buffers to flush */ - wake_up_process(mp->m_ddev_targp->bt_task); - } + if (xfs_buf_delwri_submit_nowait(&ailp->xa_buf_list)) + ailp->xa_log_flush++; - /* assume we have more work to do in a short while */ + if (!count || XFS_LSN_CMP(lsn, target) >= 0) { out_done: - if (!count) { - /* We're past our target or empty, so idle */ - ailp->xa_last_pushed_lsn = 0; - ailp->xa_log_flush = 0; - - tout = 50; - } else if (XFS_LSN_CMP(lsn, target) >= 0) { /* - * We reached the target so wait a bit longer for I/O to - * complete and remove pushed items from the AIL before we - * start the next scan from the start of the AIL. + * We reached the target or the AIL is empty, so wait a bit + * longer for I/O to complete and remove pushed items from the + * AIL before we start the next scan from the start of the AIL. */ tout = 50; ailp->xa_last_pushed_lsn = 0; - } else if ((stuck * 100) / count > 90) { + } else if (((stuck + flushing) * 100) / count > 90) { /* - * Either there is a lot of contention on the AIL or we - * are stuck due to operations in progress. "Stuck" in this - * case is defined as >90% of the items we tried to push - * were stuck. + * Either there is a lot of contention on the AIL or we are + * stuck due to operations in progress. "Stuck" in this case + * is defined as >90% of the items we tried to push were stuck. * * Backoff a bit more to allow some I/O to complete before - * restarting from the start of the AIL. This prevents us - * from spinning on the same items, and if they are pinned will - * all the restart to issue a log force to unpin the stuck - * items. + * restarting from the start of the AIL. This prevents us from + * spinning on the same items, and if they are pinned will all + * the restart to issue a log force to unpin the stuck items. */ tout = 20; ailp->xa_last_pushed_lsn = 0; + } else { + /* + * Assume we have more work to do in a short while. + */ + tout = 10; } return tout; @@ -544,6 +520,8 @@ xfsaild( struct xfs_ail *ailp = data; long tout = 0; /* milliseconds */ + current->flags |= PF_MEMALLOC; + while (!kthread_should_stop()) { if (tout && tout <= 20) __set_current_state(TASK_KILLABLE); @@ -611,6 +589,30 @@ xfs_ail_push_all( } /* + * Push out all items in the AIL immediately and wait until the AIL is empty. + */ +void +xfs_ail_push_all_sync( + struct xfs_ail *ailp) +{ + struct xfs_log_item *lip; + DEFINE_WAIT(wait); + + spin_lock(&ailp->xa_lock); + while ((lip = xfs_ail_max(ailp)) != NULL) { + prepare_to_wait(&ailp->xa_empty, &wait, TASK_UNINTERRUPTIBLE); + ailp->xa_target = lip->li_lsn; + wake_up_process(ailp->xa_task); + spin_unlock(&ailp->xa_lock); + schedule(); + spin_lock(&ailp->xa_lock); + } + spin_unlock(&ailp->xa_lock); + + finish_wait(&ailp->xa_empty, &wait); +} + +/* * xfs_trans_ail_update - bulk AIL insertion operation. * * @xfs_trans_ail_update takes an array of log items that all need to be @@ -667,11 +669,15 @@ xfs_trans_ail_update_bulk( if (!list_empty(&tmp)) xfs_ail_splice(ailp, cur, &tmp, lsn); - spin_unlock(&ailp->xa_lock); - if (mlip_changed && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) { - xlog_assign_tail_lsn(ailp->xa_mount); + if (mlip_changed) { + if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) + xlog_assign_tail_lsn_locked(ailp->xa_mount); + spin_unlock(&ailp->xa_lock); + xfs_log_space_wake(ailp->xa_mount); + } else { + spin_unlock(&ailp->xa_lock); } } @@ -700,7 +706,8 @@ void xfs_trans_ail_delete_bulk( struct xfs_ail *ailp, struct xfs_log_item **log_items, - int nr_items) __releases(ailp->xa_lock) + int nr_items, + int shutdown_type) __releases(ailp->xa_lock) { xfs_log_item_t *mlip; int mlip_changed = 0; @@ -718,7 +725,7 @@ xfs_trans_ail_delete_bulk( xfs_alert_tag(mp, XFS_PTAG_AILDELETE, "%s: attempting to delete a log item that is not in the AIL", __func__); - xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + xfs_force_shutdown(mp, shutdown_type); } return; } @@ -729,28 +736,20 @@ xfs_trans_ail_delete_bulk( if (mlip == lip) mlip_changed = 1; } - spin_unlock(&ailp->xa_lock); - if (mlip_changed && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) { - xlog_assign_tail_lsn(ailp->xa_mount); + if (mlip_changed) { + if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) + xlog_assign_tail_lsn_locked(ailp->xa_mount); + if (list_empty(&ailp->xa_ail)) + wake_up_all(&ailp->xa_empty); + spin_unlock(&ailp->xa_lock); + xfs_log_space_wake(ailp->xa_mount); + } else { + spin_unlock(&ailp->xa_lock); } } -/* - * The active item list (AIL) is a doubly linked list of log - * items sorted by ascending lsn. The base of the list is - * a forw/back pointer pair embedded in the xfs mount structure. - * The base is initialized with both pointers pointing to the - * base. This case always needs to be distinguished, because - * the base has no lsn to look at. We almost always insert - * at the end of the list, so on inserts we search from the - * end of the list to find where the new item belongs. - */ - -/* - * Initialize the doubly linked list to point only to itself. - */ int xfs_trans_ail_init( xfs_mount_t *mp) @@ -765,6 +764,8 @@ xfs_trans_ail_init( INIT_LIST_HEAD(&ailp->xa_ail); INIT_LIST_HEAD(&ailp->xa_cursors); spin_lock_init(&ailp->xa_lock); + INIT_LIST_HEAD(&ailp->xa_buf_list); + init_waitqueue_head(&ailp->xa_empty); ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s", ailp->xa_mount->m_fsname); diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 1302d1d95a5..21c5a5e3700 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -33,7 +31,6 @@ #include "xfs_buf_item.h" #include "xfs_trans_priv.h" #include "xfs_error.h" -#include "xfs_rw.h" #include "xfs_trace.h" /* @@ -56,7 +53,7 @@ xfs_trans_buf_item_match( if (blip->bli_item.li_type == XFS_LI_BUF && blip->bli_buf->b_target == target && XFS_BUF_ADDR(blip->bli_buf) == blkno && - XFS_BUF_COUNT(blip->bli_buf) == len) + BBTOB(blip->bli_buf->b_length) == len) return blip->bli_buf; } @@ -141,15 +138,11 @@ xfs_trans_get_buf(xfs_trans_t *tp, xfs_buf_t *bp; xfs_buf_log_item_t *bip; - if (flags == 0) - flags = XBF_LOCK | XBF_MAPPED; - /* * Default to a normal get_buf() call if the tp is NULL. */ if (tp == NULL) - return xfs_buf_get(target_dev, blkno, len, - flags | XBF_DONT_BLOCK); + return xfs_buf_get(target_dev, blkno, len, flags); /* * If we find the buffer in the cache with this transaction @@ -165,14 +158,6 @@ xfs_trans_get_buf(xfs_trans_t *tp, XFS_BUF_DONE(bp); } - /* - * If the buffer is stale then it was binval'ed - * since last read. This doesn't matter since the - * caller isn't allowed to use the data anyway. - */ - else if (XFS_BUF_ISSTALE(bp)) - ASSERT(!XFS_BUF_ISDELAYWRITE(bp)); - ASSERT(bp->b_transp == tp); bip = bp->b_fspriv; ASSERT(bip != NULL); @@ -182,15 +167,7 @@ xfs_trans_get_buf(xfs_trans_t *tp, return (bp); } - /* - * We always specify the XBF_DONT_BLOCK flag within a transaction - * so that get_buf does not try to push out a delayed write buffer - * which might cause another transaction to take place (if the - * buffer was delayed alloc). Such recursive transactions can - * easily deadlock with our current transaction as well as cause - * us to run out of stack space. - */ - bp = xfs_buf_get(target_dev, blkno, len, flags | XBF_DONT_BLOCK); + bp = xfs_buf_get(target_dev, blkno, len, flags); if (bp == NULL) { return NULL; } @@ -282,14 +259,13 @@ xfs_trans_read_buf( xfs_buf_log_item_t *bip; int error; - if (flags == 0) - flags = XBF_LOCK | XBF_MAPPED; + *bpp = NULL; /* * Default to a normal get_buf() call if the tp is NULL. */ if (tp == NULL) { - bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK); + bp = xfs_buf_read(target, blkno, len, flags); if (!bp) return (flags & XBF_TRYLOCK) ? EAGAIN : XFS_ERROR(ENOMEM); @@ -297,6 +273,8 @@ xfs_trans_read_buf( if (bp->b_error) { error = bp->b_error; xfs_buf_ioerror_alert(bp, __func__); + XFS_BUF_UNDONE(bp); + xfs_buf_stale(bp); xfs_buf_relse(bp); return error; } @@ -371,15 +349,7 @@ xfs_trans_read_buf( return 0; } - /* - * We always specify the XBF_DONT_BLOCK flag within a transaction - * so that get_buf does not try to push out a delayed write buffer - * which might cause another transaction to take place (if the - * buffer was delayed alloc). Such recursive transactions can - * easily deadlock with our current transaction as well as cause - * us to run out of stack space. - */ - bp = xfs_buf_read(target, blkno, len, flags | XBF_DONT_BLOCK); + bp = xfs_buf_read(target, blkno, len, flags); if (bp == NULL) { *bpp = NULL; return (flags & XBF_TRYLOCK) ? @@ -418,19 +388,6 @@ xfs_trans_read_buf( return 0; shutdown_abort: - /* - * the theory here is that buffer is good but we're - * bailing out because the filesystem is being forcibly - * shut down. So we should leave the b_flags alone since - * the buffer's not staled and just get out. - */ -#if defined(DEBUG) - if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp)) - xfs_notice(mp, "about to pop assert, bp == 0x%p", bp); -#endif - ASSERT((bp->b_flags & (XBF_STALE|XBF_DELWRI)) != - (XBF_STALE|XBF_DELWRI)); - trace_xfs_trans_read_buf_shut(bp, _RET_IP_); xfs_buf_relse(bp); *bpp = NULL; @@ -606,7 +563,7 @@ xfs_trans_log_buf(xfs_trans_t *tp, ASSERT(bp->b_transp == tp); ASSERT(bip != NULL); - ASSERT((first <= last) && (last < XFS_BUF_COUNT(bp))); + ASSERT(first <= last && last < BBTOB(bp->b_length)); ASSERT(bp->b_iodone == NULL || bp->b_iodone == xfs_buf_iodone_callbacks); @@ -626,8 +583,6 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_iodone = xfs_buf_iodone_callbacks; bip->bli_item.li_cb = xfs_buf_iodone; - xfs_buf_delwri_queue(bp); - trace_xfs_trans_log_buf(bip); /* @@ -651,22 +606,33 @@ xfs_trans_log_buf(xfs_trans_t *tp, /* - * This called to invalidate a buffer that is being used within - * a transaction. Typically this is because the blocks in the - * buffer are being freed, so we need to prevent it from being - * written out when we're done. Allowing it to be written again - * might overwrite data in the free blocks if they are reallocated - * to a file. + * Invalidate a buffer that is being used within a transaction. + * + * Typically this is because the blocks in the buffer are being freed, so we + * need to prevent it from being written out when we're done. Allowing it + * to be written again might overwrite data in the free blocks if they are + * reallocated to a file. + * + * We prevent the buffer from being written out by marking it stale. We can't + * get rid of the buf log item at this point because the buffer may still be + * pinned by another transaction. If that is the case, then we'll wait until + * the buffer is committed to disk for the last time (we can tell by the ref + * count) and free it in xfs_buf_item_unpin(). Until that happens we will + * keep the buffer locked so that the buffer and buf log item are not reused. + * + * We also set the XFS_BLF_CANCEL flag in the buf log format structure and log + * the buf item. This will be used at recovery time to determine that copies + * of the buffer in the log before this should not be replayed. * - * We prevent the buffer from being written out by clearing the - * B_DELWRI flag. We can't always - * get rid of the buf log item at this point, though, because - * the buffer may still be pinned by another transaction. If that - * is the case, then we'll wait until the buffer is committed to - * disk for the last time (we can tell by the ref count) and - * free it in xfs_buf_item_unpin(). Until it is cleaned up we - * will keep the buffer locked so that the buffer and buf log item - * are not reused. + * We mark the item descriptor and the transaction dirty so that we'll hold + * the buffer until after the commit. + * + * Since we're invalidating the buffer, we also clear the state about which + * parts of the buffer have been logged. We also clear the flag indicating + * that this is an inode buffer since the data in the buffer will no longer + * be valid. + * + * We set the stale bit in the buffer as well since we're getting rid of it. */ void xfs_trans_binval( @@ -686,7 +652,6 @@ xfs_trans_binval( * If the buffer is already invalidated, then * just return. */ - ASSERT(!(XFS_BUF_ISDELAYWRITE(bp))); ASSERT(XFS_BUF_ISSTALE(bp)); ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY))); ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_INODE_BUF)); @@ -696,27 +661,8 @@ xfs_trans_binval( return; } - /* - * Clear the dirty bit in the buffer and set the STALE flag - * in the buf log item. The STALE flag will be used in - * xfs_buf_item_unpin() to determine if it should clean up - * when the last reference to the buf item is given up. - * We set the XFS_BLF_CANCEL flag in the buf log format structure - * and log the buf item. This will be used at recovery time - * to determine that copies of the buffer in the log before - * this should not be replayed. - * We mark the item descriptor and the transaction dirty so - * that we'll hold the buffer until after the commit. - * - * Since we're invalidating the buffer, we also clear the state - * about which parts of the buffer have been logged. We also - * clear the flag indicating that this is an inode buffer since - * the data in the buffer will no longer be valid. - * - * We set the stale bit in the buffer as well since we're getting - * rid of it. - */ xfs_buf_stale(bp); + bip->bli_flags |= XFS_BLI_STALE; bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY); bip->bli_format.blf_flags &= ~XFS_BLF_INODE_BUF; diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 279099717ed..bcb60542fcf 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -17,9 +17,7 @@ */ #include "xfs.h" #include "xfs_fs.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c index f7590f5bade..8d71b16ecca 100644 --- a/fs/xfs/xfs_trans_extfree.c +++ b/fs/xfs/xfs_trans_extfree.c @@ -19,7 +19,6 @@ #include "xfs_fs.h" #include "xfs_types.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 7a7442c03f2..d2eee20d5f5 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 8ab2ced415f..fb62377d1cb 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -71,6 +71,8 @@ struct xfs_ail { spinlock_t xa_lock; xfs_lsn_t xa_last_pushed_lsn; int xa_log_flush; + struct list_head xa_buf_list; + wait_queue_head_t xa_empty; }; /* @@ -90,18 +92,22 @@ xfs_trans_ail_update( } void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp, - struct xfs_log_item **log_items, int nr_items) + struct xfs_log_item **log_items, int nr_items, + int shutdown_type) __releases(ailp->xa_lock); static inline void xfs_trans_ail_delete( struct xfs_ail *ailp, - xfs_log_item_t *lip) __releases(ailp->xa_lock) + xfs_log_item_t *lip, + int shutdown_type) __releases(ailp->xa_lock) { - xfs_trans_ail_delete_bulk(ailp, &lip, 1); + xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type); } void xfs_ail_push(struct xfs_ail *, xfs_lsn_t); void xfs_ail_push_all(struct xfs_ail *); +void xfs_ail_push_all_sync(struct xfs_ail *); +struct xfs_log_item *xfs_ail_min(struct xfs_ail *ailp); xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp); struct xfs_log_item * xfs_trans_ail_cursor_first(struct xfs_ail *ailp, diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h index 65584b55607..398cf681d02 100644 --- a/fs/xfs/xfs_types.h +++ b/fs/xfs/xfs_types.h @@ -57,6 +57,7 @@ typedef __uint64_t __psunsigned_t; #endif /* __KERNEL__ */ typedef __uint32_t xfs_agblock_t; /* blockno in alloc. group */ +typedef __uint32_t xfs_agino_t; /* inode # within allocation grp */ typedef __uint32_t xfs_extlen_t; /* extent length in blocks */ typedef __uint32_t xfs_agnumber_t; /* allocation group number */ typedef __int32_t xfs_extnum_t; /* # of extents in a file */ @@ -101,6 +102,7 @@ typedef __uint64_t xfs_fileoff_t; /* block number in a file */ typedef __int64_t xfs_sfiloff_t; /* signed block number in a file */ typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ + /* * Null values for the types. */ @@ -120,6 +122,9 @@ typedef __uint64_t xfs_filblks_t; /* number of blocks in a file */ #define NULLCOMMITLSN ((xfs_lsn_t)-1) +#define NULLFSINO ((xfs_ino_t)-1) +#define NULLAGINO ((xfs_agino_t)-1) + /* * Max values for extlen, extnum, aextnum. */ diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c index 79c05ac85bf..4e5b9ad5cb9 100644 --- a/fs/xfs/xfs_utils.c +++ b/fs/xfs/xfs_utils.c @@ -18,9 +18,7 @@ #include "xfs.h" #include "xfs_fs.h" #include "xfs_types.h" -#include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c index 64981d7e737..b6a82d817a8 100644 --- a/fs/xfs/xfs_vnodeops.c +++ b/fs/xfs/xfs_vnodeops.c @@ -21,7 +21,6 @@ #include "xfs_types.h" #include "xfs_bit.h" #include "xfs_log.h" -#include "xfs_inum.h" #include "xfs_trans.h" #include "xfs_sb.h" #include "xfs_ag.h" @@ -39,7 +38,6 @@ #include "xfs_bmap.h" #include "xfs_acl.h" #include "xfs_attr.h" -#include "xfs_rw.h" #include "xfs_error.h" #include "xfs_quota.h" #include "xfs_utils.h" @@ -81,8 +79,7 @@ xfs_readlink_bmap( d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock); byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount); - bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), - XBF_LOCK | XBF_MAPPED | XBF_DONT_BLOCK); + bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0); if (!bp) return XFS_ERROR(ENOMEM); error = bp->b_error; @@ -1919,7 +1916,7 @@ xfs_alloc_file_space( error0: /* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */ xfs_bmap_cancel(&free_list); - xfs_trans_unreserve_quota_nblks(tp, ip, qblocks, 0, quota_flag); + xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag); error1: /* Just cancel transaction */ xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT); @@ -1966,7 +1963,7 @@ xfs_zero_remaining_bytes( bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp, - mp->m_sb.sb_blocksize, XBF_DONT_BLOCK); + BTOBB(mp->m_sb.sb_blocksize), 0); if (!bp) return XFS_ERROR(ENOMEM); @@ -2315,17 +2312,33 @@ xfs_change_file_space( case XFS_IOC_ALLOCSP64: case XFS_IOC_FREESP: case XFS_IOC_FREESP64: + /* + * These operations actually do IO when extending the file, but + * the allocation is done seperately to the zeroing that is + * done. This set of operations need to be serialised against + * other IO operations, such as truncate and buffered IO. We + * need to take the IOLOCK here to serialise the allocation and + * zeroing IO to prevent other IOLOCK holders (e.g. getbmap, + * truncate, direct IO) from racing against the transient + * allocated but not written state we can have here. + */ + xfs_ilock(ip, XFS_IOLOCK_EXCL); if (startoffset > fsize) { error = xfs_alloc_file_space(ip, fsize, - startoffset - fsize, 0, attr_flags); - if (error) + startoffset - fsize, 0, + attr_flags | XFS_ATTR_NOLOCK); + if (error) { + xfs_iunlock(ip, XFS_IOLOCK_EXCL); break; + } } iattr.ia_valid = ATTR_SIZE; iattr.ia_size = startoffset; - error = xfs_setattr_size(ip, &iattr, attr_flags); + error = xfs_setattr_size(ip, &iattr, + attr_flags | XFS_ATTR_NOLOCK); + xfs_iunlock(ip, XFS_IOLOCK_EXCL); if (error) return error; |