diff options
Diffstat (limited to 'fs')
55 files changed, 1590 insertions, 970 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index dd6f7ee1e31..c2483e97bee 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -738,6 +738,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, static const struct vm_operations_struct v9fs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = v9fs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 28a64e76952..e800dec958c 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1123,7 +1123,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, if (always_dump_vma(vma)) goto whole; - if (vma->vm_flags & VM_NODUMP) + if (vma->vm_flags & VM_DONTDUMP) return 0; /* Hugetlb memory check */ @@ -1135,7 +1135,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma, } /* Do not dump I/O mapped devices or special mappings */ - if (vma->vm_flags & (VM_IO | VM_RESERVED)) + if (vma->vm_flags & VM_IO) return 0; /* By default, dump shared memory if mapped from an anonymous file. */ diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 08d812b3228..262db114ff0 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1205,7 +1205,7 @@ static int maydump(struct vm_area_struct *vma, unsigned long mm_flags) int dump_ok; /* Do not dump I/O mapped devices or special mappings */ - if (vma->vm_flags & (VM_IO | VM_RESERVED)) { + if (vma->vm_flags & VM_IO) { kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags); return 0; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5caf285c6e4..f6b40e86121 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1599,6 +1599,7 @@ out: static const struct vm_operations_struct btrfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = btrfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) @@ -1610,7 +1611,6 @@ static int btrfs_file_mmap(struct file *filp, struct vm_area_struct *vma) file_accessed(filp); vma->vm_ops = &btrfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/buffer.c b/fs/buffer.c index 58e2e7b7737..b5f044283ed 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2312,12 +2312,6 @@ int __block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, loff_t size; int ret; - /* - * Update file times before taking page lock. We may end up failing the - * fault so this update may be superfluous but who really cares... - */ - file_update_time(vma->vm_file); - lock_page(page); size = i_size_read(inode); if ((page->mapping != inode->i_mapping) || @@ -2355,6 +2349,13 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, struct super_block *sb = vma->vm_file->f_path.dentry->d_inode->i_sb; sb_start_pagefault(sb); + + /* + * Update file times before taking page lock. We may end up failing the + * fault so this update may be superfluous but who really cares... + */ + file_update_time(vma->vm_file); + ret = __block_page_mkwrite(vma, vmf, get_block); sb_end_pagefault(sb); return block_page_mkwrite_return(ret); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 452e71a1b75..6690269f5dd 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -205,7 +205,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout, - page->index << PAGE_CACHE_SHIFT, &len, + (u64) page_offset(page), &len, ci->i_truncate_seq, ci->i_truncate_size, &page, 1, 0); if (err == -ENOENT) @@ -286,7 +286,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) int nr_pages = 0; int ret; - off = page->index << PAGE_CACHE_SHIFT; + off = (u64) page_offset(page); /* count pages */ next_index = page->index; @@ -308,8 +308,8 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max) NULL, 0, ci->i_truncate_seq, ci->i_truncate_size, NULL, false, 1, 0); - if (!req) - return -ENOMEM; + if (IS_ERR(req)) + return PTR_ERR(req); /* build page vector */ nr_pages = len >> PAGE_CACHE_SHIFT; @@ -426,7 +426,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) struct ceph_inode_info *ci; struct ceph_fs_client *fsc; struct ceph_osd_client *osdc; - loff_t page_off = page->index << PAGE_CACHE_SHIFT; + loff_t page_off = page_offset(page); int len = PAGE_CACHE_SIZE; loff_t i_size; int err = 0; @@ -817,8 +817,7 @@ get_more_pages: /* ok */ if (locked_pages == 0) { /* prepare async write request */ - offset = (unsigned long long)page->index - << PAGE_CACHE_SHIFT; + offset = (u64) page_offset(page); len = wsize; req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, @@ -832,8 +831,8 @@ get_more_pages: ci->i_truncate_size, &inode->i_mtime, true, 1, 0); - if (!req) { - rc = -ENOMEM; + if (IS_ERR(req)) { + rc = PTR_ERR(req); unlock_page(page); break; } @@ -1180,7 +1179,7 @@ static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct inode *inode = vma->vm_file->f_dentry->d_inode; struct page *page = vmf->page; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - loff_t off = page->index << PAGE_CACHE_SHIFT; + loff_t off = page_offset(page); loff_t size, len; int ret; @@ -1225,6 +1224,7 @@ out: static struct vm_operations_struct ceph_vmops = { .fault = filemap_fault, .page_mkwrite = ceph_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ceph_mmap(struct file *file, struct vm_area_struct *vma) @@ -1235,6 +1235,5 @@ int ceph_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ceph_vmops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 620daad201d..3251e9cc640 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1005,7 +1005,7 @@ static void __queue_cap_release(struct ceph_mds_session *session, BUG_ON(msg->front.iov_len + sizeof(*item) > PAGE_CACHE_SIZE); head = msg->front.iov_base; - head->num = cpu_to_le32(le32_to_cpu(head->num) + 1); + le32_add_cpu(&head->num, 1); item = msg->front.iov_base + msg->front.iov_len; item->ino = cpu_to_le64(ino); item->cap_id = cpu_to_le64(cap_id); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index ecebbc09bfc..5840d2aaed1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -536,8 +536,8 @@ more: do_sync, ci->i_truncate_seq, ci->i_truncate_size, &mtime, false, 2, page_align); - if (!req) - return -ENOMEM; + if (IS_ERR(req)) + return PTR_ERR(req); if (file->f_flags & O_DIRECT) { pages = ceph_get_direct_page_vector(data, num_pages, false); diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 1396ceb4679..36549a46e31 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -187,14 +187,18 @@ static long ceph_ioctl_get_dataloc(struct file *file, void __user *arg) u64 tmp; struct ceph_object_layout ol; struct ceph_pg pgid; + int r; /* copy and validate */ if (copy_from_user(&dl, arg, sizeof(dl))) return -EFAULT; down_read(&osdc->map_sem); - ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len, - &dl.object_no, &dl.object_offset, &olen); + r = ceph_calc_file_object_mapping(&ci->i_layout, dl.file_offset, &len, + &dl.object_no, &dl.object_offset, + &olen); + if (r < 0) + return -EIO; dl.file_offset -= dl.object_offset; dl.object_size = ceph_file_layout_object_size(ci->i_layout); dl.block_size = ceph_file_layout_su(ci->i_layout); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index a5a735422aa..1bcf712655d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2625,7 +2625,8 @@ static void check_new_map(struct ceph_mds_client *mdsc, ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "", session_state_name(s->s_state)); - if (memcmp(ceph_mdsmap_get_addr(oldmap, i), + if (i >= newmap->m_max_mds || + memcmp(ceph_mdsmap_get_addr(oldmap, i), ceph_mdsmap_get_addr(newmap, i), sizeof(struct ceph_entity_addr))) { if (s->s_state == CEPH_MDS_SESSION_OPENING) { diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 3a42d932637..2eb43f21132 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -307,7 +307,10 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, { struct ceph_mount_options *fsopt; const char *dev_name_end; - int err = -ENOMEM; + int err; + + if (!dev_name || !*dev_name) + return -EINVAL; fsopt = kzalloc(sizeof(*fsopt), GFP_KERNEL); if (!fsopt) @@ -328,21 +331,33 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt, fsopt->max_readdir_bytes = CEPH_MAX_READDIR_BYTES_DEFAULT; fsopt->congestion_kb = default_congestion_kb(); - /* ip1[:port1][,ip2[:port2]...]:/subdir/in/fs */ + /* + * Distinguish the server list from the path in "dev_name". + * Internally we do not include the leading '/' in the path. + * + * "dev_name" will look like: + * <server_spec>[,<server_spec>...]:[<path>] + * where + * <server_spec> is <ip>[:<port>] + * <path> is optional, but if present must begin with '/' + */ + dev_name_end = strchr(dev_name, '/'); + if (dev_name_end) { + /* skip over leading '/' for path */ + *path = dev_name_end + 1; + } else { + /* path is empty */ + dev_name_end = dev_name + strlen(dev_name); + *path = dev_name_end; + } err = -EINVAL; - if (!dev_name) - goto out; - *path = strstr(dev_name, ":/"); - if (*path == NULL) { - pr_err("device name is missing path (no :/ in %s)\n", + dev_name_end--; /* back up to ':' separator */ + if (*dev_name_end != ':') { + pr_err("device name is missing path (no : separator in %s)\n", dev_name); goto out; } - dev_name_end = *path; dout("device name '%.*s'\n", (int)(dev_name_end - dev_name), dev_name); - - /* path on server */ - *path += 2; dout("server path '%s'\n", *path); *popt = ceph_parse_options(options, dev_name, dev_name_end, diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7d7bbdc4c8e..edb25b4bbb9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3003,6 +3003,7 @@ cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static struct vm_operations_struct cifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = cifs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/exec.c b/fs/exec.c index 9824473a7ec..4f2bebc276c 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -603,7 +603,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * process cleanup to remove whatever mess we made. */ if (length != move_page_tables(vma, old_start, - vma, new_start, length)) + vma, new_start, length, false)) return -ENOMEM; lru_add_drain(); @@ -878,9 +878,11 @@ static int de_thread(struct task_struct *tsk) sig->notify_count--; while (sig->notify_count) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); + if (unlikely(__fatal_signal_pending(tsk))) + goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock); @@ -898,9 +900,11 @@ static int de_thread(struct task_struct *tsk) write_lock_irq(&tasklist_lock); if (likely(leader->exit_state)) break; - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); schedule(); + if (unlikely(__fatal_signal_pending(tsk))) + goto killed; } /* @@ -994,6 +998,14 @@ no_thread_group: BUG_ON(!thread_group_leader(tsk)); return 0; + +killed: + /* protects against exit_notify() and __exit_signal() */ + read_lock(&tasklist_lock); + sig->group_exit_task = NULL; + sig->notify_count = 0; + read_unlock(&tasklist_lock); + return -EAGAIN; } char *get_task_comm(char *buf, struct task_struct *tsk) diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c index 5f376d14fdc..b963f38ac29 100644 --- a/fs/exofs/ore_raid.c +++ b/fs/exofs/ore_raid.c @@ -203,7 +203,7 @@ static unsigned _sp2d_min_pg(struct __stripe_pages_2d *sp2d) static unsigned _sp2d_max_pg(struct __stripe_pages_2d *sp2d) { - unsigned p; + int p; for (p = sp2d->pages_in_unit - 1; p >= 0; --p) { struct __1_page_stripe *_1ps = &sp2d->_1p_stripes[p]; diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c index 5a7b691e748..1b4f2f95fc3 100644 --- a/fs/exofs/sys.c +++ b/fs/exofs/sys.c @@ -80,8 +80,13 @@ static ssize_t uri_show(struct exofs_dev *edp, char *buf) static ssize_t uri_store(struct exofs_dev *edp, const char *buf, size_t len) { + uint8_t *new_uri; + edp->urilen = strlen(buf) + 1; - edp->uri = krealloc(edp->uri, edp->urilen, GFP_KERNEL); + new_uri = krealloc(edp->uri, edp->urilen, GFP_KERNEL); + if (new_uri == NULL) + return -ENOMEM; + edp->uri = new_uri; strncpy(edp->uri, buf, edp->urilen); return edp->urilen; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c3411d4ce2d..3ab2539b7b2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -186,7 +186,6 @@ struct mpage_da_data { #define EXT4_IO_END_ERROR 0x0002 #define EXT4_IO_END_QUEUED 0x0004 #define EXT4_IO_END_DIRECT 0x0008 -#define EXT4_IO_END_IN_FSYNC 0x0010 struct ext4_io_page { struct page *p_page; @@ -912,9 +911,7 @@ struct ext4_inode_info { struct list_head i_completed_io_list; spinlock_t i_completed_io_lock; atomic_t i_ioend_count; /* Number of outstanding io_end structs */ - /* current io_end structure for async DIO write*/ - ext4_io_end_t *cur_aio_dio; - atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */ + atomic_t i_unwritten; /* Nr. of inflight conversions pending */ spinlock_t i_block_reservation_lock; @@ -1233,6 +1230,7 @@ struct ext4_sb_info { spinlock_t s_md_lock; unsigned short *s_mb_offsets; unsigned int *s_mb_maxs; + unsigned int s_group_info_size; /* tunables */ unsigned long s_stripe; @@ -1243,6 +1241,7 @@ struct ext4_sb_info { unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; unsigned int s_max_writeback_mb_bump; + unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; @@ -1270,8 +1269,12 @@ struct ext4_sb_info { unsigned long s_sectors_written_start; u64 s_kbytes_written; + /* the size of zero-out chunk */ + unsigned int s_extent_max_zeroout_kb; + unsigned int s_log_groups_per_flex; struct flex_groups *s_flex_groups; + ext4_group_t s_flex_groups_allocated; /* workqueue for dio unwritten */ struct workqueue_struct *dio_unwritten_wq; @@ -1328,10 +1331,20 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode, { if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { io_end->flag |= EXT4_IO_END_UNWRITTEN; - atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + atomic_inc(&EXT4_I(inode)->i_unwritten); } } +static inline ext4_io_end_t *ext4_inode_aio(struct inode *inode) +{ + return inode->i_private; +} + +static inline void ext4_inode_aio_set(struct inode *inode, ext4_io_end_t *io) +{ + inode->i_private = io; +} + /* * Inode dynamic state flags */ @@ -1345,6 +1358,8 @@ enum { EXT4_STATE_DIO_UNWRITTEN, /* need convert on dio done*/ EXT4_STATE_NEWENTRY, /* File just added to dir */ EXT4_STATE_DELALLOC_RESERVED, /* blks already reserved for delalloc */ + EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read + nolocking */ }; #define EXT4_INODE_BIT_FNS(name, field, offset) \ @@ -1932,7 +1947,7 @@ extern void ext4_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ extern int ext4_sync_file(struct file *, loff_t, loff_t, int); -extern int ext4_flush_completed_IO(struct inode *); +extern int ext4_flush_unwritten_io(struct inode *); /* hash.c */ extern int ext4fs_dirhash(const char *name, int len, struct @@ -1966,6 +1981,8 @@ extern void ext4_exit_mballoc(void); extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); +extern int ext4_mb_alloc_groupinfo(struct super_block *sb, + ext4_group_t ngroups); extern int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t i, struct ext4_group_desc *desc); extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb, @@ -2051,6 +2068,8 @@ extern void ext4_superblock_csum_set(struct super_block *sb, 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); +extern int ext4_alloc_flex_bg_array(struct super_block *sb, + ext4_group_t ngroup); extern __printf(4, 5) void __ext4_error(struct super_block *, const char *, unsigned int, const char *, ...); @@ -2352,6 +2371,7 @@ extern const struct file_operations ext4_dir_operations; extern const struct inode_operations ext4_file_inode_operations; extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); +extern void ext4_unwritten_wait(struct inode *inode); /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; @@ -2400,11 +2420,11 @@ extern int ext4_move_extents(struct file *o_filp, struct file *d_filp, /* page-io.c */ extern int __init ext4_init_pageio(void); +extern void ext4_add_complete_io(ext4_io_end_t *io_end); extern void ext4_exit_pageio(void); extern void ext4_ioend_wait(struct inode *); extern void ext4_free_io_end(ext4_io_end_t *io); extern ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags); -extern int ext4_end_io_nolock(ext4_io_end_t *io); extern void ext4_io_submit(struct ext4_io_submit *io); extern int ext4_bio_write_page(struct ext4_io_submit *io, struct page *page, @@ -2452,6 +2472,21 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh) set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state); } +/* + * Disable DIO read nolock optimization, so new dioreaders will be forced + * to grab i_mutex + */ +static inline void ext4_inode_block_unlocked_dio(struct inode *inode) +{ + ext4_set_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); + smp_mb(); +} +static inline void ext4_inode_resume_unlocked_dio(struct inode *inode) +{ + smp_mb(); + ext4_clear_inode_state(inode, EXT4_STATE_DIOREAD_LOCK); +} + #define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1) /* For ioend & aio unwritten conversion wait queues */ diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index aabbb3f5368..1c94cca35ed 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -1177,7 +1177,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); - neh->eh_depth = cpu_to_le16(le16_to_cpu(neh->eh_depth) + 1); + le16_add_cpu(&neh->eh_depth, 1); ext4_mark_inode_dirty(handle, inode); out: brelse(bh); @@ -1656,16 +1656,60 @@ static int ext4_ext_try_to_merge_right(struct inode *inode, } /* + * This function does a very simple check to see if we can collapse + * an extent tree with a single extent tree leaf block into the inode. + */ +static void ext4_ext_try_to_merge_up(handle_t *handle, + struct inode *inode, + struct ext4_ext_path *path) +{ + size_t s; + unsigned max_root = ext4_ext_space_root(inode, 0); + ext4_fsblk_t blk; + + if ((path[0].p_depth != 1) || + (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || + (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) + return; + + /* + * We need to modify the block allocation bitmap and the block + * group descriptor to release the extent tree block. If we + * can't get the journal credits, give up. + */ + if (ext4_journal_extend(handle, 2)) + return; + + /* + * Copy the extent data up to the inode + */ + blk = ext4_idx_pblock(path[0].p_idx); + s = le16_to_cpu(path[1].p_hdr->eh_entries) * + sizeof(struct ext4_extent_idx); + s += sizeof(struct ext4_extent_header); + + memcpy(path[0].p_hdr, path[1].p_hdr, s); + path[0].p_depth = 0; + path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); + path[0].p_hdr->eh_max = cpu_to_le16(max_root); + + brelse(path[1].p_bh); + ext4_free_blocks(handle, inode, NULL, blk, 1, + EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); +} + +/* * This function tries to merge the @ex extent to neighbours in the tree. * return 1 if merge left else 0. */ -static int ext4_ext_try_to_merge(struct inode *inode, +static void ext4_ext_try_to_merge(handle_t *handle, + struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; - int ret = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); @@ -1675,9 +1719,9 @@ static int ext4_ext_try_to_merge(struct inode *inode, merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) - ret = ext4_ext_try_to_merge_right(inode, path, ex); + (void) ext4_ext_try_to_merge_right(inode, path, ex); - return ret; + ext4_ext_try_to_merge_up(handle, inode, path); } /* @@ -1893,7 +1937,7 @@ has_space: merge: /* try to merge extents */ if (!(flag & EXT4_GET_BLOCKS_PRE_IO)) - ext4_ext_try_to_merge(inode, path, nearex); + ext4_ext_try_to_merge(handle, inode, path, nearex); /* time to correct all indexes above */ @@ -1901,7 +1945,7 @@ merge: if (err) goto cleanup; - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); cleanup: if (npath) { @@ -2092,13 +2136,10 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, } /* - * ext4_ext_check_cache() + * ext4_ext_in_cache() * Checks to see if the given block is in the cache. * If it is, the cached extent is stored in the given - * cache extent pointer. If the cached extent is a hole, - * this routine should be used instead of - * ext4_ext_in_cache if the calling function needs to - * know the size of the hole. + * cache extent pointer. * * @inode: The files inode * @block: The block to look for in the cache @@ -2107,8 +2148,10 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path, * * Return 0 if cache is invalid; 1 if the cache is valid */ -static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block, - struct ext4_ext_cache *ex){ +static int +ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, + struct ext4_extent *ex) +{ struct ext4_ext_cache *cex; struct ext4_sb_info *sbi; int ret = 0; @@ -2125,7 +2168,9 @@ static int ext4_ext_check_cache(struct inode *inode, ext4_lblk_t block, goto errout; if (in_range(block, cex->ec_block, cex->ec_len)) { - memcpy(ex, cex, sizeof(struct ext4_ext_cache)); + ex->ee_block = cpu_to_le32(cex->ec_block); + ext4_ext_store_pblock(ex, cex->ec_start); + ex->ee_len = cpu_to_le16(cex->ec_len); ext_debug("%u cached by %u:%u:%llu\n", block, cex->ec_block, cex->ec_len, cex->ec_start); @@ -2138,37 +2183,6 @@ errout: } /* - * ext4_ext_in_cache() - * Checks to see if the given block is in the cache. - * If it is, the cached extent is stored in the given - * extent pointer. - * - * @inode: The files inode - * @block: The block to look for in the cache - * @ex: Pointer where the cached extent will be stored - * if it contains block - * - * Return 0 if cache is invalid; 1 if the cache is valid - */ -static int -ext4_ext_in_cache(struct inode *inode, ext4_lblk_t block, - struct ext4_extent *ex) -{ - struct ext4_ext_cache cex; - int ret = 0; - - if (ext4_ext_check_cache(inode, block, &cex)) { - ex->ee_block = cpu_to_le32(cex.ec_block); - ext4_ext_store_pblock(ex, cex.ec_start); - ex->ee_len = cpu_to_le16(cex.ec_len); - ret = 1; - } - - return ret; -} - - -/* * ext4_ext_rm_idx: * removes index from the index block. */ @@ -2274,10 +2288,13 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t pblk; - int flags = EXT4_FREE_BLOCKS_FORGET; + int flags = 0; if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) - flags |= EXT4_FREE_BLOCKS_METADATA; + flags |= EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; + else if (ext4_should_journal_data(inode)) + flags |= EXT4_FREE_BLOCKS_FORGET; + /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we make a note @@ -2572,7 +2589,7 @@ static int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, struct ext4_ext_path *path = NULL; ext4_fsblk_t partial_cluster = 0; handle_t *handle; - int i = 0, err; + int i = 0, err = 0; ext_debug("truncate since %u to %u\n", start, end); @@ -2604,12 +2621,16 @@ again: return PTR_ERR(path); } depth = ext_depth(inode); + /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; if (!ex) { - ext4_ext_drop_refs(path); - kfree(path); - path = NULL; - goto cont; + if (depth) { + EXT4_ERROR_INODE(inode, + "path[%d].p_hdr == NULL", + depth); + err = -EIO; + } + goto out; } ee_block = le32_to_cpu(ex->ee_block); @@ -2641,8 +2662,6 @@ again: goto out; } } -cont: - /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. @@ -2924,9 +2943,9 @@ static int ext4_split_extent_at(handle_t *handle, ext4_ext_mark_initialized(ex); if (!(flags & EXT4_GET_BLOCKS_PRE_IO)) - ext4_ext_try_to_merge(inode, path, ex); + ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } @@ -2958,8 +2977,8 @@ static int ext4_split_extent_at(handle_t *handle, goto fix_extent_len; /* update the extent length and mark as initialized */ ex->ee_len = cpu_to_le16(ee_len); - ext4_ext_try_to_merge(inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } else if (err) goto fix_extent_len; @@ -3041,7 +3060,6 @@ out: return err ? err : map->m_len; } -#define EXT4_EXT_ZERO_LEN 7 /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an uninitialized extent. It may result in splitting the uninitialized @@ -3067,13 +3085,14 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, struct ext4_map_blocks *map, struct ext4_ext_path *path) { + struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex; struct ext4_extent *ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth; - int allocated; + int allocated, max_zeroout = 0; int err = 0; int split_flag = 0; @@ -3081,6 +3100,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, "block %llu, max_blocks %u\n", inode->i_ino, (unsigned long long)map->m_lblk, map->m_len); + sbi = EXT4_SB(inode->i_sb); eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) @@ -3180,9 +3200,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; - /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */ - if (ee_len <= 2*EXT4_EXT_ZERO_LEN && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (EXT4_EXT_MAY_ZEROOUT & split_flag) + max_zeroout = sbi->s_extent_max_zeroout_kb >> + inode->i_sb->s_blocksize_bits; + + /* If extent is less than s_max_zeroout_kb, zeroout directly */ + if (max_zeroout && (ee_len <= max_zeroout)) { err = ext4_ext_zeroout(inode, ex); if (err) goto out; @@ -3191,8 +3214,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, if (err) goto out; ext4_ext_mark_initialized(ex); - ext4_ext_try_to_merge(inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + depth); + ext4_ext_try_to_merge(handle, inode, path, ex); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); goto out; } @@ -3206,9 +3229,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; - if (allocated > map->m_len) { - if (allocated <= EXT4_EXT_ZERO_LEN && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + if (max_zeroout && (allocated > map->m_len)) { + if (allocated <= max_zeroout) { /* case 3 */ zero_ex.ee_block = cpu_to_le32(map->m_lblk); @@ -3220,9 +3242,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, goto out; split_map.m_lblk = map->m_lblk; split_map.m_len = allocated; - } else if ((map->m_lblk - ee_block + map->m_len < - EXT4_EXT_ZERO_LEN) && - (EXT4_EXT_MAY_ZEROOUT & split_flag)) { + } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) { /* case 2 */ if (map->m_lblk != ee_block) { zero_ex.ee_block = ex->ee_block; @@ -3242,7 +3262,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, } allocated = ext4_split_extent(handle, inode, path, - &split_map, split_flag, 0); + &split_map, split_flag, 0); if (allocated < 0) err = allocated; @@ -3256,7 +3276,7 @@ out: * to an uninitialized extent. * * Writing to an uninitialized extent may result in splitting the uninitialized - * extent into multiple /initialized uninitialized extents (up to three) + * extent into multiple initialized/uninitialized extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be uninitialized * b> Splits in two extents: Write is happening at either end of the extent @@ -3333,10 +3353,10 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle, /* note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ - ext4_ext_try_to_merge(inode, path, ex); + ext4_ext_try_to_merge(handle, inode, path, ex); /* Mark modified extent as dirty */ - err = ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: ext4_ext_show_leaf(inode, path); return err; @@ -3600,7 +3620,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, { int ret = 0; int err = 0; - ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; + ext4_io_end_t *io = ext4_inode_aio(inode); ext_debug("ext4_ext_handle_uninitialized_extents: inode %lu, logical " "block %llu, max_blocks %u, flags %x, allocated %u\n", @@ -3615,6 +3635,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode, if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { ret = ext4_split_unwritten_extents(handle, inode, map, path, flags); + if (ret <= 0) + goto out; /* * Flag the inode(non aio case) or end_io struct (aio case) * that this IO needs to conversion to written when IO is @@ -3858,8 +3880,9 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; - ext4_io_end_t *io = EXT4_I(inode)->cur_aio_dio; + ext4_io_end_t *io = ext4_inode_aio(inode); ext4_lblk_t cluster_offset; + int set_unwritten = 0; ext_debug("blocks %u/%u requested for inode %lu\n", map->m_lblk, map->m_len, inode->i_ino); @@ -4082,13 +4105,8 @@ got_allocated_blocks: * For non asycn direct IO case, flag the inode state * that we need to perform conversion when IO is done. */ - if ((flags & EXT4_GET_BLOCKS_PRE_IO)) { - if (io) - ext4_set_io_unwritten_flag(inode, io); - else - ext4_set_inode_state(inode, - EXT4_STATE_DIO_UNWRITTEN); - } + if ((flags & EXT4_GET_BLOCKS_PRE_IO)) + set_unwritten = 1; if (ext4_should_dioread_nolock(inode)) map->m_flags |= EXT4_MAP_UNINIT; } @@ -4100,6 +4118,15 @@ got_allocated_blocks: if (!err) err = ext4_ext_insert_extent(handle, inode, path, &newex, flags); + + if (!err && set_unwritten) { + if (io) + ext4_set_io_unwritten_flag(inode, io); + else + ext4_set_inode_state(inode, + EXT4_STATE_DIO_UNWRITTEN); + } + if (err && free_on_err) { int fb_flags = flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE ? EXT4_FREE_BLOCKS_NO_QUOT_UPDATE : 0; @@ -4241,7 +4268,7 @@ void ext4_ext_truncate(struct inode *inode) * finish any pending end_io work so we won't run the risk of * converting any truncated blocks to initialized later */ - ext4_flush_completed_IO(inode); + ext4_flush_unwritten_io(inode); /* * probably first extent we're gonna free will be last in block @@ -4769,9 +4796,32 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) loff_t first_page_offset, last_page_offset; int credits, err = 0; + /* + * Write out all dirty pages to avoid race conditions + * Then release them. + */ + if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { + err = filemap_write_and_wait_range(mapping, + offset, offset + length - 1); + + if (err) + return err; + } + + mutex_lock(&inode->i_mutex); + /* It's not possible punch hole on append only file */ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { + err = -EPERM; + goto out_mutex; + } + if (IS_SWAPFILE(inode)) { + err = -ETXTBSY; + goto out_mutex; + } + /* No need to punch hole beyond i_size */ if (offset >= inode->i_size) - return 0; + goto out_mutex; /* * If the hole extends beyond i_size, set the hole @@ -4789,35 +4839,26 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) first_page_offset = first_page << PAGE_CACHE_SHIFT; last_page_offset = last_page << PAGE_CACHE_SHIFT; - /* - * Write out all dirty pages to avoid race conditions - * Then release them. - */ - if (mapping->nrpages && mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) { - err = filemap_write_and_wait_range(mapping, - offset, offset + length - 1); - - if (err) - return err; - } - /* Now release the pages */ if (last_page_offset > first_page_offset) { truncate_pagecache_range(inode, first_page_offset, last_page_offset - 1); } - /* finish any pending end_io work */ - ext4_flush_completed_IO(inode); + /* Wait all existing dio workers, newcomers will block on i_mutex */ + ext4_inode_block_unlocked_dio(inode); + err = ext4_flush_unwritten_io(inode); + if (err) + goto out_dio; + inode_dio_wait(inode); credits = ext4_writepage_trans_blocks(inode); handle = ext4_journal_start(inode, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_dio; + } - err = ext4_orphan_add(handle, inode); - if (err) - goto out; /* * Now we need to zero out the non-page-aligned data in the @@ -4903,10 +4944,13 @@ int ext4_ext_punch_hole(struct file *file, loff_t offset, loff_t length) up_write(&EXT4_I(inode)->i_data_sem); out: - ext4_orphan_del(handle, inode); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); +out_dio: + ext4_inode_resume_unlocked_dio(inode); +out_mutex: + mutex_unlock(&inode->i_mutex); return err; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3b0e3bdaabf..bf3966bccd3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -55,11 +55,11 @@ static int ext4_release_file(struct inode *inode, struct file *filp) return 0; } -static void ext4_aiodio_wait(struct inode *inode) +void ext4_unwritten_wait(struct inode *inode) { wait_queue_head_t *wq = ext4_ioend_wq(inode); - wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0)); + wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_unwritten) == 0)); } /* @@ -116,7 +116,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov, "performance will be poor.", inode->i_ino, current->comm); mutex_lock(ext4_aio_mutex(inode)); - ext4_aiodio_wait(inode); + ext4_unwritten_wait(inode); } BUG_ON(iocb->ki_pos != pos); @@ -207,6 +207,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, static const struct vm_operations_struct ext4_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ext4_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) @@ -217,7 +218,6 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma) return -ENOEXEC; file_accessed(file); vma->vm_ops = &ext4_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 2a1dcea4f12..be1d89f385b 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -34,87 +34,6 @@ #include <trace/events/ext4.h> -static void dump_completed_IO(struct inode * inode) -{ -#ifdef EXT4FS_DEBUG - struct list_head *cur, *before, *after; - ext4_io_end_t *io, *io0, *io1; - unsigned long flags; - - if (list_empty(&EXT4_I(inode)->i_completed_io_list)){ - ext4_debug("inode %lu completed_io list is empty\n", inode->i_ino); - return; - } - - ext4_debug("Dump inode %lu completed_io list \n", inode->i_ino); - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list){ - cur = &io->list; - before = cur->prev; - io0 = container_of(before, ext4_io_end_t, list); - after = cur->next; - io1 = container_of(after, ext4_io_end_t, list); - - ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", - io, inode->i_ino, io0, io1); - } - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); -#endif -} - -/* - * This function is called from ext4_sync_file(). - * - * When IO is completed, the work to convert unwritten extents to - * written is queued on workqueue but may not get immediately - * scheduled. When fsync is called, we need to ensure the - * conversion is complete before fsync returns. - * The inode keeps track of a list of pending/completed IO that - * might needs to do the conversion. This function walks through - * the list and convert the related unwritten extents for completed IO - * to written. - * The function return the number of pending IOs on success. - */ -int ext4_flush_completed_IO(struct inode *inode) -{ - ext4_io_end_t *io; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; - int ret = 0; - int ret2 = 0; - - dump_completed_IO(inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - while (!list_empty(&ei->i_completed_io_list)){ - io = list_entry(ei->i_completed_io_list.next, - ext4_io_end_t, list); - list_del_init(&io->list); - io->flag |= EXT4_IO_END_IN_FSYNC; - /* - * Calling ext4_end_io_nolock() to convert completed - * IO to written. - * - * When ext4_sync_file() is called, run_queue() may already - * about to flush the work corresponding to this io structure. - * It will be upset if it founds the io structure related - * to the work-to-be schedule is freed. - * - * Thus we need to keep the io structure still valid here after - * conversion finished. The io structure has a flag to - * avoid double converting from both fsync and background work - * queue work. - */ - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - ret = ext4_end_io_nolock(io); - if (ret < 0) - ret2 = ret; - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - io->flag &= ~EXT4_IO_END_IN_FSYNC; - } - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - return (ret2 < 0) ? ret2 : 0; -} - /* * If we're not journaling and this is a just-created file, we have to * sync our parent directory (if it was freshly created) since @@ -203,7 +122,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; - int ret; + int ret, err; tid_t commit_tid; bool needs_barrier = false; @@ -219,7 +138,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) if (inode->i_sb->s_flags & MS_RDONLY) goto out; - ret = ext4_flush_completed_IO(inode); + ret = ext4_flush_unwritten_io(inode); if (ret < 0) goto out; @@ -255,8 +174,11 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) needs_barrier = true; jbd2_log_start_commit(journal, commit_tid); ret = jbd2_log_wait_commit(journal, commit_tid); - if (needs_barrier) - blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (needs_barrier) { + err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL); + if (!ret) + ret = err; + } out: mutex_unlock(&inode->i_mutex); trace_ext4_sync_file_exit(inode, ret); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 26154b81b83..fa36372f3fd 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -697,6 +697,15 @@ got_group: if (!gdp) goto fail; + /* + * Check free inodes count before loading bitmap. + */ + if (ext4_free_inodes_count(sb, gdp) == 0) { + if (++group == ngroups) + group = 0; + continue; + } + brelse(inode_bitmap_bh); inode_bitmap_bh = ext4_read_inode_bitmap(sb, group); if (!inode_bitmap_bh) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 830e1b2bf14..792e388e7b4 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -807,16 +807,30 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, retry: if (rw == READ && ext4_should_dioread_nolock(inode)) { - if (unlikely(!list_empty(&ei->i_completed_io_list))) { + if (unlikely(atomic_read(&EXT4_I(inode)->i_unwritten))) { mutex_lock(&inode->i_mutex); - ext4_flush_completed_IO(inode); + ext4_flush_unwritten_io(inode); mutex_unlock(&inode->i_mutex); } + /* + * Nolock dioread optimization may be dynamically disabled + * via ext4_inode_block_unlocked_dio(). Check inode's state + * while holding extra i_dio_count ref. + */ + atomic_inc(&inode->i_dio_count); + smp_mb(); + if (unlikely(ext4_test_inode_state(inode, + EXT4_STATE_DIOREAD_LOCK))) { + inode_dio_done(inode); + goto locked; + } ret = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext4_get_block, NULL, NULL, 0); + inode_dio_done(inode); } else { +locked: ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, ext4_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index c862ee5fe79..b3c243b9afa 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -732,11 +732,13 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, err = ext4_map_blocks(handle, inode, &map, create ? EXT4_GET_BLOCKS_CREATE : 0); + /* ensure we send some value back into *errp */ + *errp = 0; + if (err < 0) *errp = err; if (err <= 0) return NULL; - *errp = 0; bh = sb_getblk(inode->i_sb, map.m_pblk); if (!bh) { @@ -1954,9 +1956,6 @@ out: return ret; } -static int ext4_set_bh_endio(struct buffer_head *bh, struct inode *inode); -static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); - /* * Note that we don't need to start a transaction unless we're journaling data * because we should have holes filled from ext4_page_mkwrite(). We even don't @@ -2463,6 +2462,16 @@ static int ext4_nonda_switch(struct super_block *sb) free_blocks = EXT4_C2B(sbi, percpu_counter_read_positive(&sbi->s_freeclusters_counter)); dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); + /* + * Start pushing delalloc when 1/2 of free blocks are dirty. + */ + if (dirty_blocks && (free_blocks < 2 * dirty_blocks) && + !writeback_in_progress(sb->s_bdi) && + down_read_trylock(&sb->s_umount)) { + writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); + up_read(&sb->s_umount); + } + if (2 * free_blocks < 3 * dirty_blocks || free_blocks < (dirty_blocks + EXT4_FREECLUSTERS_WATERMARK)) { /* @@ -2471,13 +2480,6 @@ static int ext4_nonda_switch(struct super_block *sb) */ return 1; } - /* - * Even if we don't switch but are nearing capacity, - * start pushing delalloc when 1/2 of free blocks are dirty. - */ - if (free_blocks < 2 * dirty_blocks) - writeback_inodes_sb_if_idle(sb, WB_REASON_FS_FREE_SPACE); - return 0; } @@ -2879,9 +2881,6 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, { struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode; ext4_io_end_t *io_end = iocb->private; - struct workqueue_struct *wq; - unsigned long flags; - struct ext4_inode_info *ei; /* if not async direct IO or dio with 0 bytes write, just return */ if (!io_end || !size) @@ -2910,24 +2909,14 @@ out: io_end->iocb = iocb; io_end->result = ret; } - wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; - /* Add the io_end to per-inode completed aio dio list*/ - ei = EXT4_I(io_end->inode); - spin_lock_irqsave(&ei->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &ei->i_completed_io_list); - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); } static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) { ext4_io_end_t *io_end = bh->b_private; - struct workqueue_struct *wq; struct inode *inode; - unsigned long flags; if (!test_clear_buffer_uninit(bh) || !io_end) goto out; @@ -2946,15 +2935,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) */ inode = io_end->inode; ext4_set_io_unwritten_flag(inode, io_end); - - /* Add the io_end to per-inode completed io list*/ - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); - - wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); out: bh->b_private = NULL; bh->b_end_io = NULL; @@ -3029,6 +3010,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, overwrite = *((int *)iocb->private); if (overwrite) { + atomic_inc(&inode->i_dio_count); down_read(&EXT4_I(inode)->i_data_sem); mutex_unlock(&inode->i_mutex); } @@ -3054,7 +3036,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * hook to the iocb. */ iocb->private = NULL; - EXT4_I(inode)->cur_aio_dio = NULL; + ext4_inode_aio_set(inode, NULL); if (!is_sync_kiocb(iocb)) { ext4_io_end_t *io_end = ext4_init_io_end(inode, GFP_NOFS); @@ -3071,7 +3053,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, * is a unwritten extents needs to be converted * when IO is completed. */ - EXT4_I(inode)->cur_aio_dio = iocb->private; + ext4_inode_aio_set(inode, io_end); } if (overwrite) @@ -3091,7 +3073,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, NULL, DIO_LOCKING); if (iocb->private) - EXT4_I(inode)->cur_aio_dio = NULL; + ext4_inode_aio_set(inode, NULL); /* * The io_end structure takes a reference to the inode, * that structure needs to be destroyed and the @@ -3126,6 +3108,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, retake_lock: /* take i_mutex locking again if we do a ovewrite dio */ if (overwrite) { + inode_dio_done(inode); up_read(&EXT4_I(inode)->i_data_sem); mutex_lock(&inode->i_mutex); } @@ -4052,6 +4035,7 @@ 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; + int need_datasync = 0; uid_t i_uid; gid_t i_gid; @@ -4102,7 +4086,10 @@ static int ext4_do_update_inode(handle_t *handle, raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); - ext4_isize_set(raw_inode, ei->i_disksize); + if (ei->i_disksize != ext4_isize(raw_inode)) { + ext4_isize_set(raw_inode, ei->i_disksize); + need_datasync = 1; + } if (ei->i_disksize > 0x7fffffffULL) { struct super_block *sb = inode->i_sb; if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, @@ -4155,7 +4142,7 @@ static int ext4_do_update_inode(handle_t *handle, err = rc; ext4_clear_inode_state(inode, EXT4_STATE_NEW); - ext4_update_inode_fsync_trans(handle, inode, 0); + ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: brelse(bh); ext4_std_error(inode->i_sb, err); @@ -4298,7 +4285,6 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - inode_dio_wait(inode); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); @@ -4347,8 +4333,17 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size != i_size_read(inode)) + if (attr->ia_size != i_size_read(inode)) { truncate_setsize(inode, attr->ia_size); + /* Inode size will be reduced, wait for dio in flight. + * Temporarily disable dioread_nolock to prevent + * livelock. */ + if (orphan) { + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + ext4_inode_resume_unlocked_dio(inode); + } + } ext4_truncate(inode); } @@ -4727,6 +4722,10 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return err; } + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(inode); + inode_dio_wait(inode); + jbd2_journal_lock_updates(journal); /* @@ -4746,6 +4745,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); + ext4_inode_resume_unlocked_dio(inode); /* Finally we can mark the inode as dirty. */ @@ -4780,6 +4780,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) int retries = 0; sb_start_pagefault(inode->i_sb); + file_update_time(vma->vm_file); /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_should_journal_data(inode) && diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 5439d6a56e9..5747f52f7c7 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -366,26 +366,11 @@ group_add_out: return -EOPNOTSUPP; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_META_BG)) { - ext4_msg(sb, KERN_ERR, - "Online resizing not (yet) supported with meta_bg"); - return -EOPNOTSUPP; - } - if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } - if (n_blocks_count > MAX_32_NUM && - !EXT4_HAS_INCOMPAT_FEATURE(sb, - EXT4_FEATURE_INCOMPAT_64BIT)) { - ext4_msg(sb, KERN_ERR, - "File system only supports 32-bit block numbers"); - return -EOPNOTSUPP; - } - err = ext4_resize_begin(sb); if (err) return err; @@ -420,13 +405,6 @@ resizefs_out: if (!blk_queue_discard(q)) return -EOPNOTSUPP; - if (EXT4_HAS_RO_COMPAT_FEATURE(sb, - EXT4_FEATURE_RO_COMPAT_BIGALLOC)) { - ext4_msg(sb, KERN_ERR, - "FITRIM not supported with bigalloc"); - return -EOPNOTSUPP; - } - if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 08778f6cdfe..f8b27bf80ac 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -24,6 +24,7 @@ #include "ext4_jbd2.h" #include "mballoc.h" #include <linux/debugfs.h> +#include <linux/log2.h> #include <linux/slab.h> #include <trace/events/ext4.h> @@ -1338,17 +1339,17 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); } -static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, +static int mb_find_extent(struct ext4_buddy *e4b, int block, int needed, struct ext4_free_extent *ex) { int next = block; - int max; + int max, order; void *buddy; assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group)); BUG_ON(ex == NULL); - buddy = mb_find_buddy(e4b, order, &max); + buddy = mb_find_buddy(e4b, 0, &max); BUG_ON(buddy == NULL); BUG_ON(block >= max); if (mb_test_bit(block, buddy)) { @@ -1358,12 +1359,9 @@ static int mb_find_extent(struct ext4_buddy *e4b, int order, int block, return 0; } - /* FIXME dorp order completely ? */ - if (likely(order == 0)) { - /* find actual order */ - order = mb_find_order_for_block(e4b, block); - block = block >> order; - } + /* find actual order */ + order = mb_find_order_for_block(e4b, block); + block = block >> order; ex->fe_len = 1 << order; ex->fe_start = block << order; @@ -1549,7 +1547,7 @@ static void ext4_mb_check_limits(struct ext4_allocation_context *ac, /* recheck chunk's availability - we don't know * when it was found (within this lock-unlock * period or not) */ - max = mb_find_extent(e4b, 0, bex->fe_start, gex->fe_len, &ex); + max = mb_find_extent(e4b, bex->fe_start, gex->fe_len, &ex); if (max >= gex->fe_len) { ext4_mb_use_best_found(ac, e4b); return; @@ -1641,7 +1639,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); - max = mb_find_extent(e4b, 0, ex.fe_start, ex.fe_len, &ex); + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { ac->ac_b_ex = ex; @@ -1662,17 +1660,20 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, int max; int err; struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); + struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct ext4_free_extent ex; if (!(ac->ac_flags & EXT4_MB_HINT_TRY_GOAL)) return 0; + if (grp->bb_free == 0) + return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); if (err) return err; ext4_lock_group(ac->ac_sb, group); - max = mb_find_extent(e4b, 0, ac->ac_g_ex.fe_start, + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); if (max >= ac->ac_g_ex.fe_len && ac->ac_g_ex.fe_len == sbi->s_stripe) { @@ -1788,7 +1789,7 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac, break; } - mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex); + mb_find_extent(e4b, i, ac->ac_g_ex.fe_len, &ex); BUG_ON(ex.fe_len <= 0); if (free < ex.fe_len) { ext4_grp_locked_error(sb, e4b->bd_group, 0, 0, @@ -1840,7 +1841,7 @@ void ext4_mb_scan_aligned(struct ext4_allocation_context *ac, while (i < EXT4_CLUSTERS_PER_GROUP(sb)) { if (!mb_test_bit(i, bitmap)) { - max = mb_find_extent(e4b, 0, i, sbi->s_stripe, &ex); + max = mb_find_extent(e4b, i, sbi->s_stripe, &ex); if (max >= sbi->s_stripe) { ac->ac_found++; ac->ac_b_ex = ex; @@ -1862,6 +1863,12 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); + free = grp->bb_free; + if (free == 0) + return 0; + if (cr <= 2 && free < ac->ac_g_ex.fe_len) + return 0; + /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { int ret = ext4_mb_init_group(ac->ac_sb, group); @@ -1869,10 +1876,7 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac, return 0; } - free = grp->bb_free; fragments = grp->bb_fragments; - if (free == 0) - return 0; if (fragments == 0) return 0; @@ -2163,6 +2167,39 @@ static struct kmem_cache *get_groupinfo_cache(int blocksize_bits) return cachep; } +/* + * Allocate the top-level s_group_info array for the specified number + * of groups + */ +int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + unsigned size; + struct ext4_group_info ***new_groupinfo; + + size = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> + EXT4_DESC_PER_BLOCK_BITS(sb); + if (size <= sbi->s_group_info_size) + return 0; + + size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size); + new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL); + if (!new_groupinfo) { + ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); + return -ENOMEM; + } + if (sbi->s_group_info) { + memcpy(new_groupinfo, sbi->s_group_info, + sbi->s_group_info_size * sizeof(*sbi->s_group_info)); + ext4_kvfree(sbi->s_group_info); + } + sbi->s_group_info = new_groupinfo; + sbi->s_group_info_size = size / sizeof(*sbi->s_group_info); + ext4_debug("allocated s_groupinfo array for %d meta_bg's\n", + sbi->s_group_info_size); + return 0; +} + /* Create and initialize ext4_group_info data for the given group. */ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, struct ext4_group_desc *desc) @@ -2195,12 +2232,11 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group, sbi->s_group_info[group >> EXT4_DESC_PER_BLOCK_BITS(sb)]; i = group & (EXT4_DESC_PER_BLOCK(sb) - 1); - meta_group_info[i] = kmem_cache_alloc(cachep, GFP_KERNEL); + meta_group_info[i] = kmem_cache_zalloc(cachep, GFP_KERNEL); if (meta_group_info[i] == NULL) { ext4_msg(sb, KERN_ERR, "can't allocate buddy mem"); goto exit_group_info; } - memset(meta_group_info[i], 0, kmem_cache_size(cachep)); set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(meta_group_info[i]->bb_state)); @@ -2252,49 +2288,14 @@ static int ext4_mb_init_backend(struct super_block *sb) ext4_group_t ngroups = ext4_get_groups_count(sb); ext4_group_t i; struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = sbi->s_es; - int num_meta_group_infos; - int num_meta_group_infos_max; - int array_size; + int err; struct ext4_group_desc *desc; struct kmem_cache *cachep; - /* This is the number of blocks used by GDT */ - num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); - - /* - * This is the total number of blocks used by GDT including - * the number of reserved blocks for GDT. - * The s_group_info array is allocated with this value - * to allow a clean online resize without a complex - * manipulation of pointer. - * The drawback is the unused memory when no resize - * occurs but it's very low in terms of pages - * (see comments below) - * Need to handle this properly when META_BG resizing is allowed - */ - num_meta_group_infos_max = num_meta_group_infos + - le16_to_cpu(es->s_reserved_gdt_blocks); + err = ext4_mb_alloc_groupinfo(sb, ngroups); + if (err) + return err; - /* - * array_size is the size of s_group_info array. We round it - * to the next power of two because this approximation is done - * internally by kmalloc so we can have some more memory - * for free here (e.g. may be used for META_BG resize). - */ - array_size = 1; - while (array_size < sizeof(*sbi->s_group_info) * - num_meta_group_infos_max) - array_size = array_size << 1; - /* An 8TB filesystem with 64-bit pointers requires a 4096 byte - * kmalloc. A 128kb malloc should suffice for a 256TB filesystem. - * So a two level scheme suffices for now. */ - sbi->s_group_info = ext4_kvzalloc(array_size, GFP_KERNEL); - if (sbi->s_group_info == NULL) { - ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group"); - return -ENOMEM; - } sbi->s_buddy_cache = new_inode(sb); if (sbi->s_buddy_cache == NULL) { ext4_msg(sb, KERN_ERR, "can't get new inode"); @@ -2322,7 +2323,7 @@ err_freebuddy: cachep = get_groupinfo_cache(sb->s_blocksize_bits); while (i-- > 0) kmem_cache_free(cachep, ext4_get_group_info(sb, i)); - i = num_meta_group_infos; + i = sbi->s_group_info_size; while (i-- > 0) kfree(sbi->s_group_info[i]); iput(sbi->s_buddy_cache); @@ -4008,7 +4009,6 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ - memset(ac, 0, sizeof(struct ext4_allocation_context)); ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; @@ -4291,7 +4291,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle, } } - ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS); + ac = kmem_cache_zalloc(ext4_ac_cachep, GFP_NOFS); if (!ac) { ar->len = 0; *errp = -ENOMEM; @@ -4657,6 +4657,8 @@ do_more: * with group lock held. generate_buddy look at * them with group lock_held */ + if (test_opt(sb, DISCARD)) + ext4_issue_discard(sb, block_group, bit, count); ext4_lock_group(sb, block_group); mb_clear_bits(bitmap_bh->b_data, bit, count_clusters); mb_free_blocks(inode, &e4b, bit, count_clusters); @@ -4988,7 +4990,8 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) start = range->start >> sb->s_blocksize_bits; end = start + (range->len >> sb->s_blocksize_bits) - 1; - minlen = range->minlen >> sb->s_blocksize_bits; + minlen = EXT4_NUM_B2C(EXT4_SB(sb), + range->minlen >> sb->s_blocksize_bits); if (unlikely(minlen > EXT4_CLUSTERS_PER_GROUP(sb)) || unlikely(start >= max_blks)) @@ -5048,6 +5051,6 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range) atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen); out: - range->len = trimmed * sb->s_blocksize; + range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits; return ret; } diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index c070618c21c..3ccd889ba95 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -65,11 +65,6 @@ extern u8 mb_enable_debug; #define MB_DEFAULT_MIN_TO_SCAN 10 /* - * How many groups mballoc will scan looking for the best chunk - */ -#define MB_DEFAULT_MAX_GROUPS_TO_SCAN 5 - -/* * with 'ext4_mb_stats' allocator will collect stats that will be * shown at umount. The collecting costs though! */ diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index c5826c623e7..292daeeed45 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -141,55 +141,21 @@ mext_next_extent(struct inode *inode, struct ext4_ext_path *path, } /** - * mext_check_null_inode - NULL check for two inodes - * - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. - */ -static int -mext_check_null_inode(struct inode *inode1, struct inode *inode2, - const char *function, unsigned int line) -{ - int ret = 0; - - if (inode1 == NULL) { - __ext4_error(inode2->i_sb, function, line, - "Both inodes should not be NULL: " - "inode1 NULL inode2 %lu", inode2->i_ino); - ret = -EIO; - } else if (inode2 == NULL) { - __ext4_error(inode1->i_sb, function, line, - "Both inodes should not be NULL: " - "inode1 %lu inode2 NULL", inode1->i_ino); - ret = -EIO; - } - return ret; -} - -/** * double_down_write_data_sem - Acquire two inodes' write lock of i_data_sem * - * @orig_inode: original inode structure - * @donor_inode: donor inode structure - * Acquire write lock of i_data_sem of the two inodes (orig and donor) by - * i_ino order. + * Acquire write lock of i_data_sem of the two inodes */ static void -double_down_write_data_sem(struct inode *orig_inode, struct inode *donor_inode) +double_down_write_data_sem(struct inode *first, struct inode *second) { - struct inode *first = orig_inode, *second = donor_inode; + if (first < second) { + down_write(&EXT4_I(first)->i_data_sem); + down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); + } else { + down_write(&EXT4_I(second)->i_data_sem); + down_write_nested(&EXT4_I(first)->i_data_sem, SINGLE_DEPTH_NESTING); - /* - * Use the inode number to provide the stable locking order instead - * of its address, because the C language doesn't guarantee you can - * compare pointers that don't come from the same array. - */ - if (donor_inode->i_ino < orig_inode->i_ino) { - first = donor_inode; - second = orig_inode; } - - down_write(&EXT4_I(first)->i_data_sem); - down_write_nested(&EXT4_I(second)->i_data_sem, SINGLE_DEPTH_NESTING); } /** @@ -604,9 +570,8 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, diff = donor_off - le32_to_cpu(tmp_dext->ee_block); ext4_ext_store_pblock(tmp_dext, ext4_ext_pblock(tmp_dext) + diff); - tmp_dext->ee_block = - cpu_to_le32(le32_to_cpu(tmp_dext->ee_block) + diff); - tmp_dext->ee_len = cpu_to_le16(le16_to_cpu(tmp_dext->ee_len) - diff); + le32_add_cpu(&tmp_dext->ee_block, diff); + le16_add_cpu(&tmp_dext->ee_len, -diff); if (max_count < ext4_ext_get_actual_len(tmp_dext)) tmp_dext->ee_len = cpu_to_le16(max_count); @@ -629,6 +594,43 @@ mext_calc_swap_extents(struct ext4_extent *tmp_dext, } /** + * mext_check_coverage - Check that all extents in range has the same type + * + * @inode: inode in question + * @from: block offset of inode + * @count: block count to be checked + * @uninit: extents expected to be uninitialized + * @err: pointer to save error value + * + * Return 1 if all extents in range has expected type, and zero otherwise. + */ +static int +mext_check_coverage(struct inode *inode, ext4_lblk_t from, ext4_lblk_t count, + int uninit, int *err) +{ + struct ext4_ext_path *path = NULL; + struct ext4_extent *ext; + ext4_lblk_t last = from + count; + while (from < last) { + *err = get_ext_path(inode, from, &path); + if (*err) + return 0; + ext = path[ext_depth(inode)].p_ext; + if (!ext) { + ext4_ext_drop_refs(path); + return 0; + } + if (uninit != ext4_ext_is_uninitialized(ext)) { + ext4_ext_drop_refs(path); + return 0; + } + from += ext4_ext_get_actual_len(ext); + ext4_ext_drop_refs(path); + } + return 1; +} + +/** * mext_replace_branches - Replace original extents with new extents * * @handle: journal handle @@ -663,9 +665,6 @@ mext_replace_branches(handle_t *handle, struct inode *orig_inode, int replaced_count = 0; int dext_alen; - /* Protect extent trees against block allocations via delalloc */ - double_down_write_data_sem(orig_inode, donor_inode); - /* Get the original extent for the block "orig_off" */ *err = get_ext_path(orig_inode, orig_off, &orig_path); if (*err) @@ -764,12 +763,122 @@ out: ext4_ext_invalidate_cache(orig_inode); ext4_ext_invalidate_cache(donor_inode); - double_up_write_data_sem(orig_inode, donor_inode); - return replaced_count; } /** + * mext_page_double_lock - Grab and lock pages on both @inode1 and @inode2 + * + * @inode1: the inode structure + * @inode2: the inode structure + * @index: page index + * @page: result page vector + * + * Grab two locked pages for inode's by inode order + */ +static int +mext_page_double_lock(struct inode *inode1, struct inode *inode2, + pgoff_t index, struct page *page[2]) +{ + struct address_space *mapping[2]; + unsigned fl = AOP_FLAG_NOFS; + + BUG_ON(!inode1 || !inode2); + if (inode1 < inode2) { + mapping[0] = inode1->i_mapping; + mapping[1] = inode2->i_mapping; + } else { + mapping[0] = inode2->i_mapping; + mapping[1] = inode1->i_mapping; + } + + page[0] = grab_cache_page_write_begin(mapping[0], index, fl); + if (!page[0]) + return -ENOMEM; + + page[1] = grab_cache_page_write_begin(mapping[1], index, fl); + if (!page[1]) { + unlock_page(page[0]); + page_cache_release(page[0]); + return -ENOMEM; + } + + if (inode1 > inode2) { + struct page *tmp; + tmp = page[0]; + page[0] = page[1]; + page[1] = tmp; + } + return 0; +} + +/* Force page buffers uptodate w/o dropping page's lock */ +static int +mext_page_mkuptodate(struct page *page, unsigned from, unsigned to) +{ + struct inode *inode = page->mapping->host; + sector_t block; + struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; + unsigned int blocksize, block_start, block_end; + int i, err, nr = 0, partial = 0; + BUG_ON(!PageLocked(page)); + BUG_ON(PageWriteback(page)); + + if (PageUptodate(page)) + return 0; + + blocksize = 1 << inode->i_blkbits; + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + + head = page_buffers(page); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (!buffer_uptodate(bh)) + partial = 1; + continue; + } + if (buffer_uptodate(bh)) + continue; + if (!buffer_mapped(bh)) { + int err = 0; + err = ext4_get_block(inode, block, bh, 0); + if (err) { + SetPageError(page); + return err; + } + if (!buffer_mapped(bh)) { + zero_user(page, block_start, blocksize); + if (!err) + set_buffer_uptodate(bh); + continue; + } + } + BUG_ON(nr >= MAX_BUF_PER_PAGE); + arr[nr++] = bh; + } + /* No io required */ + if (!nr) + goto out; + + for (i = 0; i < nr; i++) { + bh = arr[i]; + if (!bh_uptodate_or_lock(bh)) { + err = bh_submit_read(bh); + if (err) + return err; + } + } +out: + if (!partial) + SetPageUptodate(page); + return 0; +} + +/** * move_extent_per_page - Move extent data per page * * @o_filp: file structure of original file @@ -791,26 +900,24 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, int block_len_in_page, int uninit, int *err) { struct inode *orig_inode = o_filp->f_dentry->d_inode; - struct address_space *mapping = orig_inode->i_mapping; - struct buffer_head *bh; - struct page *page = NULL; - const struct address_space_operations *a_ops = mapping->a_ops; + struct page *pagep[2] = {NULL, NULL}; handle_t *handle; ext4_lblk_t orig_blk_offset; long long offs = orig_page_offset << PAGE_CACHE_SHIFT; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int w_flags = 0; unsigned int tmp_data_size, data_size, replaced_size; - void *fsdata; - int i, jblocks; - int err2 = 0; + int err2, jblocks, retries = 0; int replaced_count = 0; + int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; /* * It needs twice the amount of ordinary journal buffers because * inode and donor_inode may change each different metadata blocks. */ +again: + *err = 0; jblocks = ext4_writepage_trans_blocks(orig_inode) * 2; handle = ext4_journal_start(orig_inode, jblocks); if (IS_ERR(handle)) { @@ -824,19 +931,6 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, orig_blk_offset = orig_page_offset * blocks_per_page + data_offset_in_page; - /* - * If orig extent is uninitialized one, - * it's not necessary force the page into memory - * and then force it to be written out again. - * Just swap data blocks between orig and donor. - */ - if (uninit) { - replaced_count = mext_replace_branches(handle, orig_inode, - donor_inode, orig_blk_offset, - block_len_in_page, err); - goto out2; - } - offs = (long long)orig_blk_offset << orig_inode->i_blkbits; /* Calculate data_size */ @@ -858,75 +952,120 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, replaced_size = data_size; - *err = a_ops->write_begin(o_filp, mapping, offs, data_size, w_flags, - &page, &fsdata); + *err = mext_page_double_lock(orig_inode, donor_inode, orig_page_offset, + pagep); if (unlikely(*err < 0)) - goto out; - - if (!PageUptodate(page)) { - mapping->a_ops->readpage(o_filp, page); - lock_page(page); - } - + goto stop_journal; /* - * try_to_release_page() doesn't call releasepage in writeback mode. - * We should care about the order of writing to the same file - * by multiple move extent processes. - * It needs to call wait_on_page_writeback() to wait for the - * writeback of the page. + * If orig extent was uninitialized it can become initialized + * at any time after i_data_sem was dropped, in order to + * serialize with delalloc we have recheck extent while we + * hold page's lock, if it is still the case data copy is not + * necessary, just swap data blocks between orig and donor. */ - wait_on_page_writeback(page); + if (uninit) { + double_down_write_data_sem(orig_inode, donor_inode); + /* If any of extents in range became initialized we have to + * fallback to data copying */ + uninit = mext_check_coverage(orig_inode, orig_blk_offset, + block_len_in_page, 1, err); + if (*err) + goto drop_data_sem; - /* Release old bh and drop refs */ - try_to_release_page(page, 0); + uninit &= mext_check_coverage(donor_inode, orig_blk_offset, + block_len_in_page, 1, err); + if (*err) + goto drop_data_sem; + + if (!uninit) { + double_up_write_data_sem(orig_inode, donor_inode); + goto data_copy; + } + if ((page_has_private(pagep[0]) && + !try_to_release_page(pagep[0], 0)) || + (page_has_private(pagep[1]) && + !try_to_release_page(pagep[1], 0))) { + *err = -EBUSY; + goto drop_data_sem; + } + replaced_count = mext_replace_branches(handle, orig_inode, + donor_inode, orig_blk_offset, + block_len_in_page, err); + drop_data_sem: + double_up_write_data_sem(orig_inode, donor_inode); + goto unlock_pages; + } +data_copy: + *err = mext_page_mkuptodate(pagep[0], from, from + replaced_size); + if (*err) + goto unlock_pages; + + /* At this point all buffers in range are uptodate, old mapping layout + * is no longer required, try to drop it now. */ + if ((page_has_private(pagep[0]) && !try_to_release_page(pagep[0], 0)) || + (page_has_private(pagep[1]) && !try_to_release_page(pagep[1], 0))) { + *err = -EBUSY; + goto unlock_pages; + } replaced_count = mext_replace_branches(handle, orig_inode, donor_inode, - orig_blk_offset, block_len_in_page, - &err2); - if (err2) { + orig_blk_offset, + block_len_in_page, err); + if (*err) { if (replaced_count) { block_len_in_page = replaced_count; replaced_size = block_len_in_page << orig_inode->i_blkbits; } else - goto out; + goto unlock_pages; } + /* Perform all necessary steps similar write_begin()/write_end() + * but keeping in mind that i_size will not change */ + *err = __block_write_begin(pagep[0], from, from + replaced_size, + ext4_get_block); + if (!*err) + *err = block_commit_write(pagep[0], from, from + replaced_size); - if (!page_has_buffers(page)) - create_empty_buffers(page, 1 << orig_inode->i_blkbits, 0); - - bh = page_buffers(page); - for (i = 0; i < data_offset_in_page; i++) - bh = bh->b_this_page; - - for (i = 0; i < block_len_in_page; i++) { - *err = ext4_get_block(orig_inode, - (sector_t)(orig_blk_offset + i), bh, 0); - if (*err < 0) - goto out; - - if (bh->b_this_page != NULL) - bh = bh->b_this_page; - } - - *err = a_ops->write_end(o_filp, mapping, offs, data_size, replaced_size, - page, fsdata); - page = NULL; - -out: - if (unlikely(page)) { - if (PageLocked(page)) - unlock_page(page); - page_cache_release(page); - ext4_journal_stop(handle); - } -out2: + if (unlikely(*err < 0)) + goto repair_branches; + + /* Even in case of data=writeback it is reasonable to pin + * inode to transaction, to prevent unexpected data loss */ + *err = ext4_jbd2_file_inode(handle, orig_inode); + +unlock_pages: + unlock_page(pagep[0]); + page_cache_release(pagep[0]); + unlock_page(pagep[1]); + page_cache_release(pagep[1]); +stop_journal: ext4_journal_stop(handle); - - if (err2) - *err = err2; - + /* Buffer was busy because probably is pinned to journal transaction, + * force transaction commit may help to free it. */ + if (*err == -EBUSY && ext4_should_retry_alloc(orig_inode->i_sb, + &retries)) + goto again; return replaced_count; + +repair_branches: + /* + * This should never ever happen! + * Extents are swapped already, but we are not able to copy data. + * Try to swap extents to it's original places + */ + double_down_write_data_sem(orig_inode, donor_inode); + replaced_count = mext_replace_branches(handle, donor_inode, orig_inode, + orig_blk_offset, + block_len_in_page, &err2); + double_up_write_data_sem(orig_inode, donor_inode); + if (replaced_count != block_len_in_page) { + EXT4_ERROR_INODE_BLOCK(orig_inode, (sector_t)(orig_blk_offset), + "Unable to copy data block," + " data will be lost."); + *err = -EIO; + } + replaced_count = 0; + goto unlock_pages; } /** @@ -969,14 +1108,6 @@ mext_check_arguments(struct inode *orig_inode, return -EINVAL; } - /* Files should be in the same ext4 FS */ - if (orig_inode->i_sb != donor_inode->i_sb) { - ext4_debug("ext4 move extent: The argument files " - "should be in same FS [ino:orig %lu, donor %lu]\n", - orig_inode->i_ino, donor_inode->i_ino); - return -EINVAL; - } - /* Ext4 move extent supports only extent based file */ if (!(ext4_test_inode_flag(orig_inode, EXT4_INODE_EXTENTS))) { ext4_debug("ext4 move extent: orig file is not extents " @@ -1002,7 +1133,6 @@ mext_check_arguments(struct inode *orig_inode, } if ((orig_start >= EXT_MAX_BLOCKS) || - (donor_start >= EXT_MAX_BLOCKS) || (*len > EXT_MAX_BLOCKS) || (orig_start + *len >= EXT_MAX_BLOCKS)) { ext4_debug("ext4 move extent: Can't handle over [%u] blocks " @@ -1072,35 +1202,19 @@ mext_check_arguments(struct inode *orig_inode, * @inode1: the inode structure * @inode2: the inode structure * - * Lock two inodes' i_mutex by i_ino order. - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. + * Lock two inodes' i_mutex */ -static int +static void mext_inode_double_lock(struct inode *inode1, struct inode *inode2) { - int ret = 0; - - BUG_ON(inode1 == NULL && inode2 == NULL); - - ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__); - if (ret < 0) - goto out; - - if (inode1 == inode2) { - mutex_lock(&inode1->i_mutex); - goto out; - } - - if (inode1->i_ino < inode2->i_ino) { + BUG_ON(inode1 == inode2); + if (inode1 < inode2) { mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD); } else { mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT); mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD); } - -out: - return ret; } /** @@ -1109,28 +1223,13 @@ out: * @inode1: the inode that is released first * @inode2: the inode that is released second * - * If inode1 or inode2 is NULL, return -EIO. Otherwise, return 0. */ -static int +static void mext_inode_double_unlock(struct inode *inode1, struct inode *inode2) { - int ret = 0; - - BUG_ON(inode1 == NULL && inode2 == NULL); - - ret = mext_check_null_inode(inode1, inode2, __func__, __LINE__); - if (ret < 0) - goto out; - - if (inode1) - mutex_unlock(&inode1->i_mutex); - - if (inode2 && inode2 != inode1) - mutex_unlock(&inode2->i_mutex); - -out: - return ret; + mutex_unlock(&inode1->i_mutex); + mutex_unlock(&inode2->i_mutex); } /** @@ -1187,16 +1286,23 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, ext4_lblk_t block_end, seq_start, add_blocks, file_end, seq_blocks = 0; ext4_lblk_t rest_blocks; pgoff_t orig_page_offset = 0, seq_end_page; - int ret1, ret2, depth, last_extent = 0; + int ret, depth, last_extent = 0; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; int data_offset_in_page; int block_len_in_page; int uninit; - /* orig and donor should be different file */ - if (orig_inode->i_ino == donor_inode->i_ino) { + if (orig_inode->i_sb != donor_inode->i_sb) { + ext4_debug("ext4 move extent: The argument files " + "should be in same FS [ino:orig %lu, donor %lu]\n", + orig_inode->i_ino, donor_inode->i_ino); + return -EINVAL; + } + + /* orig and donor should be different inodes */ + if (orig_inode == donor_inode) { ext4_debug("ext4 move extent: The argument files should not " - "be same file [ino:orig %lu, donor %lu]\n", + "be same inode [ino:orig %lu, donor %lu]\n", orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } @@ -1208,18 +1314,27 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - + /* TODO: This is non obvious task to swap blocks for inodes with full + jornaling enabled */ + if (ext4_should_journal_data(orig_inode) || + ext4_should_journal_data(donor_inode)) { + return -EINVAL; + } /* Protect orig and donor inodes against a truncate */ - ret1 = mext_inode_double_lock(orig_inode, donor_inode); - if (ret1 < 0) - return ret1; + mext_inode_double_lock(orig_inode, donor_inode); + + /* Wait for all existing dio workers */ + ext4_inode_block_unlocked_dio(orig_inode); + ext4_inode_block_unlocked_dio(donor_inode); + inode_dio_wait(orig_inode); + inode_dio_wait(donor_inode); /* Protect extent tree against block allocations via delalloc */ double_down_write_data_sem(orig_inode, donor_inode); /* Check the filesystem environment whether move_extent can be done */ - ret1 = mext_check_arguments(orig_inode, donor_inode, orig_start, + ret = mext_check_arguments(orig_inode, donor_inode, orig_start, donor_start, &len); - if (ret1) + if (ret) goto out; file_end = (i_size_read(orig_inode) - 1) >> orig_inode->i_blkbits; @@ -1227,13 +1342,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (file_end < block_end) len -= block_end - file_end; - ret1 = get_ext_path(orig_inode, block_start, &orig_path); - if (ret1) + ret = get_ext_path(orig_inode, block_start, &orig_path); + if (ret) goto out; /* Get path structure to check the hole */ - ret1 = get_ext_path(orig_inode, block_start, &holecheck_path); - if (ret1) + ret = get_ext_path(orig_inode, block_start, &holecheck_path); + if (ret) goto out; depth = ext_depth(orig_inode); @@ -1252,13 +1367,13 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; goto out; } last_extent = mext_next_extent(orig_inode, orig_path, &ext_dummy); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; goto out; } seq_start = le32_to_cpu(ext_cur->ee_block); @@ -1272,7 +1387,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, if (le32_to_cpu(ext_cur->ee_block) > block_end) { ext4_debug("ext4 move extent: The specified range of file " "may be the hole\n"); - ret1 = -EINVAL; + ret = -EINVAL; goto out; } @@ -1292,7 +1407,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, last_extent = mext_next_extent(orig_inode, holecheck_path, &ext_cur); if (last_extent < 0) { - ret1 = last_extent; + ret = last_extent; break; } add_blocks = ext4_ext_get_actual_len(ext_cur); @@ -1349,18 +1464,18 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, orig_page_offset, data_offset_in_page, block_len_in_page, uninit, - &ret1); + &ret); /* Count how many blocks we have exchanged */ *moved_len += block_len_in_page; - if (ret1 < 0) + if (ret < 0) break; if (*moved_len > len) { EXT4_ERROR_INODE(orig_inode, "We replaced blocks too much! " "sum of replaced: %llu requested: %llu", *moved_len, len); - ret1 = -EIO; + ret = -EIO; break; } @@ -1374,22 +1489,22 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, } double_down_write_data_sem(orig_inode, donor_inode); - if (ret1 < 0) + if (ret < 0) break; /* Decrease buffer counter */ if (holecheck_path) ext4_ext_drop_refs(holecheck_path); - ret1 = get_ext_path(orig_inode, seq_start, &holecheck_path); - if (ret1) + ret = get_ext_path(orig_inode, seq_start, &holecheck_path); + if (ret) break; depth = holecheck_path->p_depth; /* Decrease buffer counter */ if (orig_path) ext4_ext_drop_refs(orig_path); - ret1 = get_ext_path(orig_inode, seq_start, &orig_path); - if (ret1) + ret = get_ext_path(orig_inode, seq_start, &orig_path); + if (ret) break; ext_cur = holecheck_path[depth].p_ext; @@ -1412,12 +1527,9 @@ out: kfree(holecheck_path); } double_up_write_data_sem(orig_inode, donor_inode); - ret2 = mext_inode_double_unlock(orig_inode, donor_inode); - - if (ret1) - return ret1; - else if (ret2) - return ret2; + ext4_inode_resume_unlocked_dio(orig_inode); + ext4_inode_resume_unlocked_dio(donor_inode); + mext_inode_double_unlock(orig_inode, donor_inode); - return 0; + return ret; } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2a42cc04466..6d600a69fc9 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -55,6 +55,13 @@ static struct buffer_head *ext4_append(handle_t *handle, { struct buffer_head *bh; + if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb && + ((inode->i_size >> 10) >= + EXT4_SB(inode->i_sb)->s_max_dir_size_kb))) { + *err = -ENOSPC; + return NULL; + } + *block = inode->i_size >> inode->i_sb->s_blocksize_bits; bh = ext4_bread(handle, inode, *block, 1, err); @@ -67,6 +74,12 @@ static struct buffer_head *ext4_append(handle_t *handle, bh = NULL; } } + if (!bh && !(*err)) { + *err = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } return bh; } @@ -594,8 +607,11 @@ dx_probe(const struct qstr *d_name, struct inode *dir, u32 hash; frame->bh = NULL; - if (!(bh = ext4_bread (NULL,dir, 0, 0, err))) + if (!(bh = ext4_bread(NULL, dir, 0, 0, err))) { + if (*err == 0) + *err = ERR_BAD_DX_DIR; goto fail; + } root = (struct dx_root *) bh->b_data; if (root->info.hash_version != DX_HASH_TEA && root->info.hash_version != DX_HASH_HALF_MD4 && @@ -696,8 +712,11 @@ dx_probe(const struct qstr *d_name, struct inode *dir, frame->entries = entries; frame->at = at; if (!indirect--) return frame; - if (!(bh = ext4_bread (NULL,dir, dx_get_block(at), 0, err))) + if (!(bh = ext4_bread(NULL, dir, dx_get_block(at), 0, err))) { + if (!(*err)) + *err = ERR_BAD_DX_DIR; goto fail2; + } at = entries = ((struct dx_node *) bh->b_data)->entries; if (!buffer_verified(bh) && @@ -807,8 +826,15 @@ static int ext4_htree_next_block(struct inode *dir, __u32 hash, */ while (num_frames--) { if (!(bh = ext4_bread(NULL, dir, dx_get_block(p->at), - 0, &err))) + 0, &err))) { + if (!err) { + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + return -EIO; + } return err; /* Failure */ + } if (!buffer_verified(bh) && !ext4_dx_csum_verify(dir, @@ -839,12 +865,19 @@ static int htree_dirblock_to_tree(struct file *dir_file, { struct buffer_head *bh; struct ext4_dir_entry_2 *de, *top; - int err, count = 0; + int err = 0, count = 0; dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n", (unsigned long)block)); - if (!(bh = ext4_bread (NULL, dir, block, 0, &err))) + if (!(bh = ext4_bread(NULL, dir, block, 0, &err))) { + if (!err) { + err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } return err; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -1267,8 +1300,15 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, const struct q return NULL; do { block = dx_get_block(frame->at); - if (!(bh = ext4_bread(NULL, dir, block, 0, err))) + if (!(bh = ext4_bread(NULL, dir, block, 0, err))) { + if (!(*err)) { + *err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } goto errout; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, @@ -1801,9 +1841,15 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, } blocks = dir->i_size >> sb->s_blocksize_bits; for (block = 0; block < blocks; block++) { - bh = ext4_bread(handle, dir, block, 0, &retval); - if(!bh) + if (!(bh = ext4_bread(handle, dir, block, 0, &retval))) { + if (!retval) { + retval = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } return retval; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -1860,8 +1906,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry, entries = frame->entries; at = frame->at; - if (!(bh = ext4_bread(handle,dir, dx_get_block(frame->at), 0, &err))) + if (!(bh = ext4_bread(handle, dir, dx_get_block(frame->at), 0, &err))) { + if (!err) { + err = -EIO; + ext4_error(dir->i_sb, + "Directory hole detected on inode %lu\n", + dir->i_ino); + } goto cleanup; + } if (!buffer_verified(bh) && !ext4_dirent_csum_verify(dir, (struct ext4_dir_entry *)bh->b_data)) @@ -2149,9 +2202,7 @@ retry: err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); -#ifdef CONFIG_EXT4_FS_XATTR inode->i_op = &ext4_special_inode_operations; -#endif err = ext4_add_nondir(handle, dentry, inode); } ext4_journal_stop(handle); @@ -2199,9 +2250,15 @@ retry: inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; inode->i_size = EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize; - dir_block = ext4_bread(handle, inode, 0, 1, &err); - if (!dir_block) + if (!(dir_block = ext4_bread(handle, inode, 0, 1, &err))) { + if (!err) { + err = -EIO; + ext4_error(inode->i_sb, + "Directory hole detected on inode %lu\n", + inode->i_ino); + } goto out_clear_inode; + } BUFFER_TRACE(dir_block, "get_write_access"); err = ext4_journal_get_write_access(handle, dir_block); if (err) @@ -2318,6 +2375,11 @@ static int empty_dir(struct inode *inode) EXT4_ERROR_INODE(inode, "error %d reading directory " "lblock %u", err, lblock); + else + ext4_warning(inode->i_sb, + "bad directory (dir #%lu) - no data block", + inode->i_ino); + offset += sb->s_blocksize; continue; } @@ -2362,7 +2424,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) struct ext4_iloc iloc; int err = 0, rc; - if (!ext4_handle_valid(handle)) + if (!EXT4_SB(sb)->s_journal) return 0; mutex_lock(&EXT4_SB(sb)->s_orphan_lock); @@ -2436,8 +2498,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) struct ext4_iloc iloc; int err = 0; - /* ext4_handle_valid() assumes a valid handle_t pointer */ - if (handle && !ext4_handle_valid(handle)) + if (!EXT4_SB(inode->i_sb)->s_journal) return 0; mutex_lock(&EXT4_SB(inode->i_sb)->s_orphan_lock); @@ -2456,7 +2517,7 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) * transaction handle with which to update the orphan list on * disk, but we still need to remove the inode from the linked * list in memory. */ - if (sbi->s_journal && !handle) + if (!handle) goto out; err = ext4_reserve_inode_write(handle, inode, &iloc); @@ -2826,9 +2887,15 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, goto end_rename; } retval = -EIO; - dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval); - if (!dir_bh) + if (!(dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval))) { + if (!retval) { + retval = -EIO; + ext4_error(old_inode->i_sb, + "Directory hole detected on inode %lu\n", + old_inode->i_ino); + } goto end_rename; + } if (!buffer_verified(dir_bh) && !ext4_dirent_csum_verify(old_inode, (struct ext4_dir_entry *)dir_bh->b_data)) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index dcdeef169a6..68e896e12a6 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -71,6 +71,9 @@ void ext4_free_io_end(ext4_io_end_t *io) int i; BUG_ON(!io); + BUG_ON(!list_empty(&io->list)); + BUG_ON(io->flag & EXT4_IO_END_UNWRITTEN); + if (io->page) put_page(io->page); for (i = 0; i < io->num_io_pages; i++) @@ -81,13 +84,8 @@ void ext4_free_io_end(ext4_io_end_t *io) kmem_cache_free(io_end_cachep, io); } -/* - * check a range of space and convert unwritten extents to written. - * - * Called with inode->i_mutex; we depend on this when we manipulate - * io->flag, since we could otherwise race with ext4_flush_completed_IO() - */ -int ext4_end_io_nolock(ext4_io_end_t *io) +/* check a range of space and convert unwritten extents to written. */ +static int ext4_end_io(ext4_io_end_t *io) { struct inode *inode = io->inode; loff_t offset = io->offset; @@ -106,63 +104,136 @@ int ext4_end_io_nolock(ext4_io_end_t *io) "(inode %lu, offset %llu, size %zd, error %d)", inode->i_ino, offset, size, ret); } - if (io->iocb) aio_complete(io->iocb, io->result, 0); if (io->flag & EXT4_IO_END_DIRECT) inode_dio_done(inode); /* Wake up anyone waiting on unwritten extent conversion */ - if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten)) + if (atomic_dec_and_test(&EXT4_I(inode)->i_unwritten)) wake_up_all(ext4_ioend_wq(io->inode)); return ret; } -/* - * work on completed aio dio IO, to convert unwritten extents to extents - */ -static void ext4_end_io_work(struct work_struct *work) +static void dump_completed_IO(struct inode *inode) +{ +#ifdef EXT4FS_DEBUG + struct list_head *cur, *before, *after; + ext4_io_end_t *io, *io0, *io1; + unsigned long flags; + + if (list_empty(&EXT4_I(inode)->i_completed_io_list)) { + ext4_debug("inode %lu completed_io list is empty\n", + inode->i_ino); + return; + } + + ext4_debug("Dump inode %lu completed_io list\n", inode->i_ino); + list_for_each_entry(io, &EXT4_I(inode)->i_completed_io_list, list) { + cur = &io->list; + before = cur->prev; + io0 = container_of(before, ext4_io_end_t, list); + after = cur->next; + io1 = container_of(after, ext4_io_end_t, list); + + ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n", + io, inode->i_ino, io0, io1); + } +#endif +} + +/* Add the io_end to per-inode completed end_io list. */ +void ext4_add_complete_io(ext4_io_end_t *io_end) { - ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); - struct inode *inode = io->inode; - struct ext4_inode_info *ei = EXT4_I(inode); - unsigned long flags; + struct ext4_inode_info *ei = EXT4_I(io_end->inode); + struct workqueue_struct *wq; + unsigned long flags; + + BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN)); + wq = EXT4_SB(io_end->inode->i_sb)->dio_unwritten_wq; spin_lock_irqsave(&ei->i_completed_io_lock, flags); - if (io->flag & EXT4_IO_END_IN_FSYNC) - goto requeue; - if (list_empty(&io->list)) { - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - goto free; + if (list_empty(&ei->i_completed_io_list)) { + io_end->flag |= EXT4_IO_END_QUEUED; + queue_work(wq, &io_end->work); } + list_add_tail(&io_end->list, &ei->i_completed_io_list); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); +} - if (!mutex_trylock(&inode->i_mutex)) { - bool was_queued; -requeue: - was_queued = !!(io->flag & EXT4_IO_END_QUEUED); - io->flag |= EXT4_IO_END_QUEUED; - spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - /* - * Requeue the work instead of waiting so that the work - * items queued after this can be processed. - */ - queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work); - /* - * To prevent the ext4-dio-unwritten thread from keeping - * requeueing end_io requests and occupying cpu for too long, - * yield the cpu if it sees an end_io request that has already - * been requeued. - */ - if (was_queued) - yield(); - return; +static int ext4_do_flush_completed_IO(struct inode *inode, + ext4_io_end_t *work_io) +{ + ext4_io_end_t *io; + struct list_head unwritten, complete, to_free; + unsigned long flags; + struct ext4_inode_info *ei = EXT4_I(inode); + int err, ret = 0; + + INIT_LIST_HEAD(&complete); + INIT_LIST_HEAD(&to_free); + + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + dump_completed_IO(inode); + list_replace_init(&ei->i_completed_io_list, &unwritten); + spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); + + while (!list_empty(&unwritten)) { + io = list_entry(unwritten.next, ext4_io_end_t, list); + BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN)); + list_del_init(&io->list); + + err = ext4_end_io(io); + if (unlikely(!ret && err)) + ret = err; + + list_add_tail(&io->list, &complete); + } + spin_lock_irqsave(&ei->i_completed_io_lock, flags); + while (!list_empty(&complete)) { + io = list_entry(complete.next, ext4_io_end_t, list); + io->flag &= ~EXT4_IO_END_UNWRITTEN; + /* end_io context can not be destroyed now because it still + * used by queued worker. Worker thread will destroy it later */ + if (io->flag & EXT4_IO_END_QUEUED) + list_del_init(&io->list); + else + list_move(&io->list, &to_free); + } + /* If we are called from worker context, it is time to clear queued + * flag, and destroy it's end_io if it was converted already */ + if (work_io) { + work_io->flag &= ~EXT4_IO_END_QUEUED; + if (!(work_io->flag & EXT4_IO_END_UNWRITTEN)) + list_add_tail(&work_io->list, &to_free); } - list_del_init(&io->list); spin_unlock_irqrestore(&ei->i_completed_io_lock, flags); - (void) ext4_end_io_nolock(io); - mutex_unlock(&inode->i_mutex); -free: - ext4_free_io_end(io); + + while (!list_empty(&to_free)) { + io = list_entry(to_free.next, ext4_io_end_t, list); + list_del_init(&io->list); + ext4_free_io_end(io); + } + return ret; +} + +/* + * work on completed aio dio IO, to convert unwritten extents to extents + */ +static void ext4_end_io_work(struct work_struct *work) +{ + ext4_io_end_t *io = container_of(work, ext4_io_end_t, work); + ext4_do_flush_completed_IO(io->inode, io); +} + +int ext4_flush_unwritten_io(struct inode *inode) +{ + int ret; + WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex) && + !(inode->i_state & I_FREEING)); + ret = ext4_do_flush_completed_IO(inode, NULL); + ext4_unwritten_wait(inode); + return ret; } ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags) @@ -195,9 +266,7 @@ static void buffer_io_error(struct buffer_head *bh) static void ext4_end_bio(struct bio *bio, int error) { ext4_io_end_t *io_end = bio->bi_private; - struct workqueue_struct *wq; struct inode *inode; - unsigned long flags; int i; sector_t bi_sector = bio->bi_sector; @@ -255,14 +324,7 @@ static void ext4_end_bio(struct bio *bio, int error) return; } - /* Add the io_end to per-inode completed io list*/ - spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); - list_add_tail(&io_end->list, &EXT4_I(inode)->i_completed_io_list); - spin_unlock_irqrestore(&EXT4_I(inode)->i_completed_io_lock, flags); - - wq = EXT4_SB(inode->i_sb)->dio_unwritten_wq; - /* queue the work to convert unwritten extents to written */ - queue_work(wq, &io_end->work); + ext4_add_complete_io(io_end); } void ext4_io_submit(struct ext4_io_submit *io) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 41f6ef68e2e..7a75e108696 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -45,6 +45,28 @@ void ext4_resize_end(struct super_block *sb) smp_mb__after_clear_bit(); } +static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb, + ext4_group_t group) { + return (group >> EXT4_DESC_PER_BLOCK_BITS(sb)) << + EXT4_DESC_PER_BLOCK_BITS(sb); +} + +static ext4_fsblk_t ext4_meta_bg_first_block_no(struct super_block *sb, + ext4_group_t group) { + group = ext4_meta_bg_first_group(sb, group); + return ext4_group_first_block_no(sb, group); +} + +static ext4_grpblk_t ext4_group_overhead_blocks(struct super_block *sb, + ext4_group_t group) { + ext4_grpblk_t overhead; + overhead = ext4_bg_num_gdb(sb, group); + if (ext4_bg_has_super(sb, group)) + overhead += 1 + + le16_to_cpu(EXT4_SB(sb)->s_es->s_reserved_gdt_blocks); + return overhead; +} + #define outside(b, first, last) ((b) < (first) || (b) >= (last)) #define inside(b, first, last) ((b) >= (first) && (b) < (last)) @@ -57,9 +79,7 @@ static int verify_group_input(struct super_block *sb, ext4_fsblk_t end = start + input->blocks_count; ext4_group_t group = input->group; ext4_fsblk_t itend = input->inode_table + sbi->s_itb_per_group; - unsigned overhead = ext4_bg_has_super(sb, group) ? - (1 + ext4_bg_num_gdb(sb, group) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + unsigned overhead = ext4_group_overhead_blocks(sb, group); ext4_fsblk_t metaend = start + overhead; struct buffer_head *bh = NULL; ext4_grpblk_t free_blocks_count, offset; @@ -200,13 +220,15 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) * be a partial of a flex group. * * @sb: super block of fs to which the groups belongs + * + * Returns 0 on a successful allocation of the metadata blocks in the + * block group. */ -static void ext4_alloc_group_tables(struct super_block *sb, +static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; - struct ext4_super_block *es = EXT4_SB(sb)->s_es; ext4_fsblk_t start_blk; ext4_fsblk_t last_blk; ext4_group_t src_group; @@ -226,23 +248,24 @@ static void ext4_alloc_group_tables(struct super_block *sb, (last_group & ~(flexbg_size - 1)))); next_group: group = group_data[0].group; + if (src_group >= group_data[0].group + flex_gd->count) + return -ENOSPC; start_blk = ext4_group_first_block_no(sb, src_group); last_blk = start_blk + group_data[src_group - group].blocks_count; - overhead = ext4_bg_has_super(sb, src_group) ? - (1 + ext4_bg_num_gdb(sb, src_group) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + overhead = ext4_group_overhead_blocks(sb, src_group); start_blk += overhead; - BUG_ON(src_group >= group_data[0].group + flex_gd->count); /* We collect contiguous blocks as much as possible. */ src_group++; - for (; src_group <= last_group; src_group++) - if (!ext4_bg_has_super(sb, src_group)) + for (; src_group <= last_group; src_group++) { + overhead = ext4_group_overhead_blocks(sb, src_group); + if (overhead != 0) last_blk += group_data[src_group - group].blocks_count; else break; + } /* Allocate block bitmaps */ for (; bb_index < flex_gd->count; bb_index++) { @@ -300,6 +323,7 @@ next_group: group_data[i].free_blocks_count); } } + return 0; } static struct buffer_head *bclean(handle_t *handle, struct super_block *sb, @@ -433,11 +457,13 @@ static int setup_new_flex_group_blocks(struct super_block *sb, ext4_group_t group, count; struct buffer_head *bh = NULL; int reserved_gdb, i, j, err = 0, err2; + int meta_bg; BUG_ON(!flex_gd->count || !group_data || group_data[0].group != sbi->s_groups_count); reserved_gdb = le16_to_cpu(es->s_reserved_gdt_blocks); + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); /* This transaction may be extended/restarted along the way */ handle = ext4_journal_start_sb(sb, EXT4_MAX_TRANS_DATA); @@ -447,12 +473,25 @@ static int setup_new_flex_group_blocks(struct super_block *sb, group = group_data[0].group; for (i = 0; i < flex_gd->count; i++, group++) { unsigned long gdblocks; + ext4_grpblk_t overhead; gdblocks = ext4_bg_num_gdb(sb, group); start = ext4_group_first_block_no(sb, group); + if (meta_bg == 0 && !ext4_bg_has_super(sb, group)) + goto handle_itb; + + if (meta_bg == 1) { + ext4_group_t first_group; + first_group = ext4_meta_bg_first_group(sb, group); + if (first_group != group + 1 && + first_group != group + EXT4_DESC_PER_BLOCK(sb) - 1) + goto handle_itb; + } + + block = start + ext4_bg_has_super(sb, group); /* Copy all of the GDT blocks into the backup in this group */ - for (j = 0, block = start + 1; j < gdblocks; j++, block++) { + for (j = 0; j < gdblocks; j++, block++) { struct buffer_head *gdb; ext4_debug("update backup group %#04llx\n", block); @@ -493,6 +532,7 @@ static int setup_new_flex_group_blocks(struct super_block *sb, goto out; } +handle_itb: /* Initialize group tables of the grop @group */ if (!(bg_flags[i] & EXT4_BG_INODE_ZEROED)) goto handle_bb; @@ -521,11 +561,11 @@ handle_bb: err = PTR_ERR(bh); goto out; } - if (ext4_bg_has_super(sb, group)) { + overhead = ext4_group_overhead_blocks(sb, group); + if (overhead != 0) { ext4_debug("mark backup superblock %#04llx (+0)\n", start); - ext4_set_bits(bh->b_data, 0, gdblocks + reserved_gdb + - 1); + ext4_set_bits(bh->b_data, 0, overhead); } ext4_mark_bitmap_end(group_data[i].blocks_count, sb->s_blocksize * 8, bh->b_data); @@ -822,6 +862,45 @@ exit_bh: } /* + * add_new_gdb_meta_bg is the sister of add_new_gdb. + */ +static int add_new_gdb_meta_bg(struct super_block *sb, + handle_t *handle, ext4_group_t group) { + ext4_fsblk_t gdblock; + struct buffer_head *gdb_bh; + struct buffer_head **o_group_desc, **n_group_desc; + unsigned long gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int err; + + gdblock = ext4_meta_bg_first_block_no(sb, group) + + ext4_bg_has_super(sb, group); + gdb_bh = sb_bread(sb, gdblock); + if (!gdb_bh) + return -EIO; + n_group_desc = ext4_kvmalloc((gdb_num + 1) * + sizeof(struct buffer_head *), + GFP_NOFS); + if (!n_group_desc) { + err = -ENOMEM; + ext4_warning(sb, "not enough memory for %lu groups", + gdb_num + 1); + return err; + } + + o_group_desc = EXT4_SB(sb)->s_group_desc; + memcpy(n_group_desc, o_group_desc, + EXT4_SB(sb)->s_gdb_count * sizeof(struct buffer_head *)); + n_group_desc[gdb_num] = gdb_bh; + EXT4_SB(sb)->s_group_desc = n_group_desc; + EXT4_SB(sb)->s_gdb_count++; + ext4_kvfree(o_group_desc); + err = ext4_journal_get_write_access(handle, gdb_bh); + if (unlikely(err)) + brelse(gdb_bh); + return err; +} + +/* * Called when we are adding a new group which has a backup copy of each of * the GDT blocks (i.e. sparse group) and there are reserved GDT blocks. * We need to add these reserved backup GDT blocks to the resize inode, so @@ -949,16 +1028,16 @@ exit_free: * do not copy the full number of backups at this time. The resize * which changed s_groups_count will backup again. */ -static void update_backups(struct super_block *sb, - int blk_off, char *data, int size) +static void update_backups(struct super_block *sb, int blk_off, char *data, + int size, int meta_bg) { struct ext4_sb_info *sbi = EXT4_SB(sb); - const ext4_group_t last = sbi->s_groups_count; + ext4_group_t last; const int bpg = EXT4_BLOCKS_PER_GROUP(sb); unsigned three = 1; unsigned five = 5; unsigned seven = 7; - ext4_group_t group; + ext4_group_t group = 0; int rest = sb->s_blocksize - size; handle_t *handle; int err = 0, err2; @@ -970,10 +1049,17 @@ static void update_backups(struct super_block *sb, goto exit_err; } - ext4_superblock_csum_set(sb, (struct ext4_super_block *)data); + if (meta_bg == 0) { + group = ext4_list_backups(sb, &three, &five, &seven); + last = sbi->s_groups_count; + } else { + group = ext4_meta_bg_first_group(sb, group) + 1; + last = (ext4_group_t)(group + EXT4_DESC_PER_BLOCK(sb) - 2); + } - while ((group = ext4_list_backups(sb, &three, &five, &seven)) < last) { + while (group < sbi->s_groups_count) { struct buffer_head *bh; + ext4_fsblk_t backup_block; /* Out of journal space, and can't get more - abort - so sad */ if (ext4_handle_valid(handle) && @@ -982,13 +1068,20 @@ static void update_backups(struct super_block *sb, (err = ext4_journal_restart(handle, EXT4_MAX_TRANS_DATA))) break; - bh = sb_getblk(sb, group * bpg + blk_off); + if (meta_bg == 0) + backup_block = group * bpg + blk_off; + else + backup_block = (ext4_group_first_block_no(sb, group) + + ext4_bg_has_super(sb, group)); + + bh = sb_getblk(sb, backup_block); if (!bh) { err = -EIO; break; } - ext4_debug("update metadata backup %#04lx\n", - (unsigned long)bh->b_blocknr); + ext4_debug("update metadata backup %llu(+%llu)\n", + backup_block, backup_block - + ext4_group_first_block_no(sb, group)); if ((err = ext4_journal_get_write_access(handle, bh))) break; lock_buffer(bh); @@ -1001,6 +1094,13 @@ static void update_backups(struct super_block *sb, if (unlikely(err)) ext4_std_error(sb, err); brelse(bh); + + if (meta_bg == 0) + group = ext4_list_backups(sb, &three, &five, &seven); + else if (group == last) + break; + else + group = last; } if ((err2 = ext4_journal_stop(handle)) && !err) err = err2; @@ -1043,7 +1143,9 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, struct ext4_super_block *es = sbi->s_es; struct buffer_head *gdb_bh; int i, gdb_off, gdb_num, err = 0; + int meta_bg; + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); for (i = 0; i < count; i++, group++) { int reserved_gdb = ext4_bg_has_super(sb, group) ? le16_to_cpu(es->s_reserved_gdt_blocks) : 0; @@ -1063,8 +1165,11 @@ static int ext4_add_new_descs(handle_t *handle, struct super_block *sb, if (!err && reserved_gdb && ext4_bg_num_gdb(sb, group)) err = reserve_backup_gdb(handle, resize_inode, group); - } else + } else if (meta_bg != 0) { + err = add_new_gdb_meta_bg(sb, handle, group); + } else { err = add_new_gdb(handle, resize_inode, group); + } if (err) break; } @@ -1076,17 +1181,12 @@ 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; + if (!bh_uptodate_or_lock(bh)) { + if (bh_submit_read(bh) < 0) { + brelse(bh); + return NULL; + } } - unlock_buffer(bh); return bh; } @@ -1161,6 +1261,9 @@ static int ext4_setup_new_descs(handle_t *handle, struct super_block *sb, 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)); + if (ext4_has_group_desc_csum(sb)) + ext4_itable_unused_set(sb, gdp, + EXT4_INODES_PER_GROUP(sb)); gdp->bg_flags = cpu_to_le16(*bg_flags); ext4_group_desc_csum_set(sb, group, gdp); @@ -1216,7 +1319,7 @@ static void ext4_update_super(struct super_block *sb, } reserved_blocks = ext4_r_blocks_count(es) * 100; - do_div(reserved_blocks, ext4_blocks_count(es)); + reserved_blocks = div64_u64(reserved_blocks, ext4_blocks_count(es)); reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); @@ -1227,6 +1330,7 @@ static void ext4_update_super(struct super_block *sb, le32_add_cpu(&es->s_free_inodes_count, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); + ext4_debug("free blocks count %llu", ext4_free_blocks_count(es)); /* * We need to protect s_groups_count against other CPUs seeing * inconsistent state in the superblock. @@ -1261,6 +1365,8 @@ static void ext4_update_super(struct super_block *sb, percpu_counter_add(&sbi->s_freeinodes_counter, EXT4_INODES_PER_GROUP(sb) * flex_gd->count); + ext4_debug("free blocks count %llu", + percpu_counter_read(&sbi->s_freeclusters_counter)); if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) && sbi->s_log_groups_per_flex) { @@ -1349,16 +1455,24 @@ exit_journal: err = err2; if (!err) { - int i; + int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); + int gdb_num_end = ((group + flex_gd->count - 1) / + EXT4_DESC_PER_BLOCK(sb)); + int meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, + EXT4_FEATURE_INCOMPAT_META_BG); + sector_t old_gdb = 0; + update_backups(sb, sbi->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block)); - for (i = 0; i < flex_gd->count; i++, group++) { + sizeof(struct ext4_super_block), 0); + for (; gdb_num <= gdb_num_end; gdb_num++) { struct buffer_head *gdb_bh; - int gdb_num; - gdb_num = group / EXT4_BLOCKS_PER_GROUP(sb); + gdb_bh = sbi->s_group_desc[gdb_num]; + if (old_gdb == gdb_bh->b_blocknr) + continue; update_backups(sb, gdb_bh->b_blocknr, gdb_bh->b_data, - gdb_bh->b_size); + gdb_bh->b_size, meta_bg); + old_gdb = gdb_bh->b_blocknr; } } exit: @@ -1402,9 +1516,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, group_data[i].group = group + i; group_data[i].blocks_count = blocks_per_group; - overhead = ext4_bg_has_super(sb, group + i) ? - (1 + ext4_bg_num_gdb(sb, group + i) + - le16_to_cpu(es->s_reserved_gdt_blocks)) : 0; + overhead = ext4_group_overhead_blocks(sb, group + i); group_data[i].free_blocks_count = blocks_per_group - overhead; if (ext4_has_group_desc_csum(sb)) flex_gd->bg_flags[i] = EXT4_BG_BLOCK_UNINIT | @@ -1492,6 +1604,14 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) if (err) goto out; + err = ext4_alloc_flex_bg_array(sb, input->group + 1); + if (err) + return err; + + err = ext4_mb_alloc_groupinfo(sb, input->group + 1); + if (err) + goto out; + flex_gd.count = 1; flex_gd.groups = input; flex_gd.bg_flags = &bg_flags; @@ -1544,11 +1664,13 @@ errout: err = err2; if (!err) { + ext4_fsblk_t first_block; + first_block = ext4_group_first_block_no(sb, 0); if (test_opt(sb, DEBUG)) printk(KERN_DEBUG "EXT4-fs: extended group to %llu " "blocks\n", ext4_blocks_count(es)); - update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr, (char *)es, - sizeof(struct ext4_super_block)); + update_backups(sb, EXT4_SB(sb)->s_sbh->b_blocknr - first_block, + (char *)es, sizeof(struct ext4_super_block), 0); } return err; } @@ -1631,6 +1753,94 @@ int ext4_group_extend(struct super_block *sb, struct ext4_super_block *es, return err; } /* ext4_group_extend */ + +static int num_desc_blocks(struct super_block *sb, ext4_group_t groups) +{ + return (groups + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); +} + +/* + * Release the resize inode and drop the resize_inode feature if there + * are no more reserved gdt blocks, and then convert the file system + * to enable meta_bg + */ +static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) +{ + handle_t *handle; + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct ext4_super_block *es = sbi->s_es; + struct ext4_inode_info *ei = EXT4_I(inode); + ext4_fsblk_t nr; + int i, ret, err = 0; + int credits = 1; + + ext4_msg(sb, KERN_INFO, "Converting file system to meta_bg"); + if (inode) { + if (es->s_reserved_gdt_blocks) { + ext4_error(sb, "Unexpected non-zero " + "s_reserved_gdt_blocks"); + return -EPERM; + } + + /* Do a quick sanity check of the resize inode */ + if (inode->i_blocks != 1 << (inode->i_blkbits - 9)) + goto invalid_resize_inode; + for (i = 0; i < EXT4_N_BLOCKS; i++) { + if (i == EXT4_DIND_BLOCK) { + if (ei->i_data[i]) + continue; + else + goto invalid_resize_inode; + } + if (ei->i_data[i]) + goto invalid_resize_inode; + } + credits += 3; /* block bitmap, bg descriptor, resize inode */ + } + + handle = ext4_journal_start_sb(sb, credits); + if (IS_ERR(handle)) + return PTR_ERR(handle); + + err = ext4_journal_get_write_access(handle, sbi->s_sbh); + if (err) + goto errout; + + EXT4_CLEAR_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE); + EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); + sbi->s_es->s_first_meta_bg = + cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + + err = ext4_handle_dirty_super(handle, sb); + if (err) { + ext4_std_error(sb, err); + goto errout; + } + + if (inode) { + nr = le32_to_cpu(ei->i_data[EXT4_DIND_BLOCK]); + ext4_free_blocks(handle, inode, NULL, nr, 1, + EXT4_FREE_BLOCKS_METADATA | + EXT4_FREE_BLOCKS_FORGET); + ei->i_data[EXT4_DIND_BLOCK] = 0; + inode->i_blocks = 0; + + err = ext4_mark_inode_dirty(handle, inode); + if (err) + ext4_std_error(sb, err); + } + +errout: + ret = ext4_journal_stop(handle); + if (!err) + err = ret; + return ret; + +invalid_resize_inode: + ext4_error(sb, "corrupted/inconsistent resize inode"); + return -EINVAL; +} + /* * ext4_resize_fs() resizes a fs to new size specified by @n_blocks_count * @@ -1643,21 +1853,31 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; struct buffer_head *bh; - struct inode *resize_inode; - ext4_fsblk_t o_blocks_count; - ext4_group_t o_group; - ext4_group_t n_group; - ext4_grpblk_t offset, add; + struct inode *resize_inode = NULL; + ext4_grpblk_t add, offset; unsigned long n_desc_blocks; unsigned long o_desc_blocks; - unsigned long desc_blocks; - int err = 0, flexbg_size = 1; + ext4_group_t o_group; + ext4_group_t n_group; + ext4_fsblk_t o_blocks_count; + ext4_fsblk_t n_blocks_count_retry = 0; + unsigned long last_update_time = 0; + int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int meta_bg; + /* See if the device is actually as big as what was requested */ + bh = sb_bread(sb, n_blocks_count - 1); + if (!bh) { + ext4_warning(sb, "can't read last block, resize aborted"); + return -ENOSPC; + } + brelse(bh); + +retry: o_blocks_count = ext4_blocks_count(es); - if (test_opt(sb, DEBUG)) - ext4_msg(sb, KERN_DEBUG, "resizing filesystem from %llu " - "to %llu blocks", o_blocks_count, n_blocks_count); + ext4_msg(sb, KERN_INFO, "resizing filesystem from %llu " + "to %llu blocks", o_blocks_count, n_blocks_count); if (n_blocks_count < o_blocks_count) { /* On-line shrinking not supported */ @@ -1672,32 +1892,49 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &offset); ext4_get_group_no_and_offset(sb, o_blocks_count - 1, &o_group, &offset); - n_desc_blocks = (n_group + EXT4_DESC_PER_BLOCK(sb)) / - EXT4_DESC_PER_BLOCK(sb); - o_desc_blocks = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / - EXT4_DESC_PER_BLOCK(sb); - desc_blocks = n_desc_blocks - o_desc_blocks; + n_desc_blocks = num_desc_blocks(sb, n_group + 1); + o_desc_blocks = num_desc_blocks(sb, sbi->s_groups_count); - if (desc_blocks && - (!EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE) || - le16_to_cpu(es->s_reserved_gdt_blocks) < desc_blocks)) { - ext4_warning(sb, "No reserved GDT blocks, can't resize"); - return -EPERM; - } + meta_bg = EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG); - resize_inode = ext4_iget(sb, EXT4_RESIZE_INO); - if (IS_ERR(resize_inode)) { - ext4_warning(sb, "Error opening resize inode"); - return PTR_ERR(resize_inode); + if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_RESIZE_INODE)) { + if (meta_bg) { + ext4_error(sb, "resize_inode and meta_bg enabled " + "simultaneously"); + return -EINVAL; + } + if (n_desc_blocks > o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks)) { + n_blocks_count_retry = n_blocks_count; + n_desc_blocks = o_desc_blocks + + le16_to_cpu(es->s_reserved_gdt_blocks); + n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); + n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb); + n_group--; /* set to last group number */ + } + + if (!resize_inode) + resize_inode = ext4_iget(sb, EXT4_RESIZE_INO); + if (IS_ERR(resize_inode)) { + ext4_warning(sb, "Error opening resize inode"); + return PTR_ERR(resize_inode); + } } - /* See if the device is actually as big as what was requested */ - bh = sb_bread(sb, n_blocks_count - 1); - if (!bh) { - ext4_warning(sb, "can't read last block, resize aborted"); - return -ENOSPC; + if ((!resize_inode && !meta_bg) || n_blocks_count == o_blocks_count) { + err = ext4_convert_meta_bg(sb, resize_inode); + if (err) + goto out; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + if (n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + goto retry; + } } - brelse(bh); /* extend the last group */ if (n_group == o_group) @@ -1710,12 +1947,15 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) goto out; } - if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG) && - es->s_log_groups_per_flex) - flexbg_size = 1 << es->s_log_groups_per_flex; + if (ext4_blocks_count(es) == n_blocks_count) + goto out; - o_blocks_count = ext4_blocks_count(es); - if (o_blocks_count == n_blocks_count) + err = ext4_alloc_flex_bg_array(sb, n_group + 1); + if (err) + return err; + + err = ext4_mb_alloc_groupinfo(sb, n_group + 1); + if (err) goto out; flex_gd = alloc_flex_gd(flexbg_size); @@ -1729,19 +1969,33 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) */ while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, flexbg_size)) { - ext4_alloc_group_tables(sb, flex_gd, flexbg_size); + if (jiffies - last_update_time > HZ * 10) { + if (last_update_time) + ext4_msg(sb, KERN_INFO, + "resized to %llu blocks", + ext4_blocks_count(es)); + last_update_time = jiffies; + } + if (ext4_alloc_group_tables(sb, flex_gd, flexbg_size) != 0) + break; err = ext4_flex_group_add(sb, resize_inode, flex_gd); if (unlikely(err)) break; } + if (!err && n_blocks_count_retry) { + n_blocks_count = n_blocks_count_retry; + n_blocks_count_retry = 0; + free_flex_gd(flex_gd); + flex_gd = NULL; + goto retry; + } + out: if (flex_gd) free_flex_gd(flex_gd); - - iput(resize_inode); - if (test_opt(sb, DEBUG)) - ext4_msg(sb, KERN_DEBUG, "resized filesystem from %llu " - "upto %llu blocks", o_blocks_count, n_blocks_count); + if (resize_inode != NULL) + iput(resize_inode); + ext4_msg(sb, KERN_INFO, "resized filesystem to %llu", n_blocks_count); return err; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 69c55d4e462..7265a036747 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -420,7 +420,7 @@ static void __save_error_info(struct super_block *sb, const char *func, */ if (!es->s_error_count) mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ); - es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1); + le32_add_cpu(&es->s_error_count, 1); } static void save_error_info(struct super_block *sb, const char *func, @@ -850,7 +850,6 @@ static void ext4_put_super(struct super_block *sb) flush_workqueue(sbi->dio_unwritten_wq); destroy_workqueue(sbi->dio_unwritten_wq); - lock_super(sb); if (sbi->s_journal) { err = jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; @@ -917,7 +916,6 @@ static void ext4_put_super(struct super_block *sb) * Now that we are completely done shutting down the * superblock, we need to actually destroy the kobject. */ - unlock_super(sb); kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); if (sbi->s_chksum_driver) @@ -956,11 +954,10 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->jinode = NULL; INIT_LIST_HEAD(&ei->i_completed_io_list); spin_lock_init(&ei->i_completed_io_lock); - ei->cur_aio_dio = NULL; ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); - atomic_set(&ei->i_aiodio_unwritten, 0); + atomic_set(&ei->i_unwritten, 0); return &ei->vfs_inode; } @@ -1224,6 +1221,7 @@ enum { Opt_inode_readahead_blks, Opt_journal_ioprio, Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, + Opt_max_dir_size_kb, }; static const match_table_t tokens = { @@ -1297,6 +1295,7 @@ static const match_table_t tokens = { {Opt_init_itable, "init_itable=%u"}, {Opt_init_itable, "init_itable"}, {Opt_noinit_itable, "noinit_itable"}, + {Opt_max_dir_size_kb, "max_dir_size_kb=%u"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1477,6 +1476,7 @@ static const struct mount_opts { {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, {Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT}, + {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_err, 0, 0} }; @@ -1592,6 +1592,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, if (!args->from) arg = EXT4_DEF_LI_WAIT_MULT; sbi->s_li_wait_mult = arg; + } else if (token == Opt_max_dir_size_kb) { + sbi->s_max_dir_size_kb = arg; } else if (token == Opt_stripe) { sbi->s_stripe = arg; } else if (m->flags & MOPT_DATAJ) { @@ -1664,7 +1666,7 @@ static int parse_options(char *options, struct super_block *sb, * Initialize args struct so we know whether arg was * found; some options take optional arguments. */ - args[0].to = args[0].from = 0; + args[0].to = args[0].from = NULL; token = match_token(p, tokens, args); if (handle_mount_opt(sb, p, token, args, journal_devnum, journal_ioprio, is_remount) < 0) @@ -1740,7 +1742,7 @@ static inline void ext4_show_quota_options(struct seq_file *seq, static const char *token2str(int token) { - static const struct match_token *t; + const struct match_token *t; for (t = tokens; t->token != Opt_err; t++) if (t->token == token && !strchr(t->pattern, '=')) @@ -1823,6 +1825,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, if (nodefs || (test_opt(sb, INIT_INODE_TABLE) && (sbi->s_li_wait_mult != EXT4_DEF_LI_WAIT_MULT))) SEQ_OPTS_PRINT("init_itable=%u", sbi->s_li_wait_mult); + if (nodefs || sbi->s_max_dir_size_kb) + SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); ext4_show_quota_options(seq, sb); return 0; @@ -1914,15 +1918,45 @@ done: return res; } +int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + struct flex_groups *new_groups; + int size; + + if (!sbi->s_log_groups_per_flex) + return 0; + + size = ext4_flex_group(sbi, ngroup - 1) + 1; + if (size <= sbi->s_flex_groups_allocated) + return 0; + + size = roundup_pow_of_two(size * sizeof(struct flex_groups)); + new_groups = ext4_kvzalloc(size, GFP_KERNEL); + if (!new_groups) { + ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups", + size / (int) sizeof(struct flex_groups)); + return -ENOMEM; + } + + if (sbi->s_flex_groups) { + memcpy(new_groups, sbi->s_flex_groups, + (sbi->s_flex_groups_allocated * + sizeof(struct flex_groups))); + ext4_kvfree(sbi->s_flex_groups); + } + sbi->s_flex_groups = new_groups; + sbi->s_flex_groups_allocated = size / sizeof(struct flex_groups); + return 0; +} + static int ext4_fill_flex_info(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; - ext4_group_t flex_group_count; ext4_group_t flex_group; unsigned int groups_per_flex = 0; - size_t size; - int i; + int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; if (sbi->s_log_groups_per_flex < 1 || sbi->s_log_groups_per_flex > 31) { @@ -1931,17 +1965,9 @@ static int ext4_fill_flex_info(struct super_block *sb) } groups_per_flex = 1 << sbi->s_log_groups_per_flex; - /* We allocate both existing and potentially added groups */ - flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) + - ((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) << - EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex; - size = flex_group_count * sizeof(struct flex_groups); - sbi->s_flex_groups = ext4_kvzalloc(size, GFP_KERNEL); - if (sbi->s_flex_groups == NULL) { - ext4_msg(sb, KERN_ERR, "not enough memory for %u flex groups", - flex_group_count); + err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); + if (err) goto failed; - } for (i = 0; i < sbi->s_groups_count; i++) { gdp = ext4_get_group_desc(sb, i, NULL); @@ -2144,10 +2170,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, } if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) { - if (es->s_last_orphan) + /* don't clear list on RO mount w/ errors */ + if (es->s_last_orphan && !(s_flags & MS_RDONLY)) { jbd_debug(1, "Errors on filesystem, " "clearing orphan list.\n"); - es->s_last_orphan = 0; + es->s_last_orphan = 0; + } jbd_debug(1, "Skipping orphan recovery on fs with errors.\n"); return; } @@ -2528,6 +2556,7 @@ 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_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error); static struct attribute *ext4_attrs[] = { @@ -2543,6 +2572,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), ATTR_LIST(max_writeback_mb_bump), + ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), NULL, }; @@ -2550,10 +2580,12 @@ static struct attribute *ext4_attrs[] = { /* Features this copy of ext4 supports */ EXT4_INFO_ATTR(lazy_itable_init); EXT4_INFO_ATTR(batched_discard); +EXT4_INFO_ATTR(meta_bg_resize); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), + ATTR_LIST(meta_bg_resize), NULL, }; @@ -3374,7 +3406,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) * enable delayed allocation by default * Use -o nodelalloc to turn it off */ - if (!IS_EXT3_SB(sb) && + if (!IS_EXT3_SB(sb) && !IS_EXT2_SB(sb) && ((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0)) set_opt(sb, DELALLOC); @@ -3743,6 +3775,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_max_writeback_mb_bump = 128; + sbi->s_extent_max_zeroout_kb = 32; /* * set up enough so that it can read an inode @@ -4519,11 +4552,9 @@ static int ext4_unfreeze(struct super_block *sb) if (sb->s_flags & MS_RDONLY) return 0; - lock_super(sb); /* Reset the needs_recovery flag before the fs is unlocked. */ EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER); ext4_commit_super(sb, 1); - unlock_super(sb); return 0; } @@ -4559,7 +4590,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) char *orig_data = kstrdup(data, GFP_KERNEL); /* Store the original options */ - lock_super(sb); old_sb_flags = sb->s_flags; old_opts.s_mount_opt = sbi->s_mount_opt; old_opts.s_mount_opt2 = sbi->s_mount_opt2; @@ -4701,7 +4731,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal == NULL) ext4_commit_super(sb, 1); - unlock_super(sb); #ifdef CONFIG_QUOTA /* Release old quota file names */ for (i = 0; i < MAXQUOTAS; i++) @@ -4714,10 +4743,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) else if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) { err = ext4_enable_quotas(sb); - if (err) { - lock_super(sb); + if (err) goto restore_opts; - } } } #endif @@ -4744,7 +4771,6 @@ restore_opts: sbi->s_qf_names[i] = old_opts.s_qf_names[i]; } #endif - unlock_super(sb); kfree(orig_data); return err; } @@ -5269,8 +5295,10 @@ static int __init ext4_init_fs(void) if (err) goto out6; ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj); - if (!ext4_kset) + if (!ext4_kset) { + err = -ENOMEM; goto out5; + } ext4_proc_root = proc_mkdir("fs/ext4", NULL); err = ext4_init_feat_adverts(); diff --git a/fs/fcntl.c b/fs/fcntl.c index 8f704291d4e..71a600a19f0 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -258,7 +258,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, err = f_dupfd(arg, filp, 0); break; case F_DUPFD_CLOEXEC: - err = f_dupfd(arg, filp, FD_CLOEXEC); + err = f_dupfd(arg, filp, O_CLOEXEC); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6d46c0d7833..401b6c6248a 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -63,6 +63,7 @@ int writeback_in_progress(struct backing_dev_info *bdi) { return test_bit(BDI_writeback_running, &bdi->state); } +EXPORT_SYMBOL(writeback_in_progress); static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { @@ -438,8 +439,7 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, * 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) +__writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; @@ -526,7 +526,7 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb, inode->i_state |= I_SYNC; spin_unlock(&inode->i_lock); - ret = __writeback_single_inode(inode, wb, wbc); + ret = __writeback_single_inode(inode, wbc); spin_lock(&wb->list_lock); spin_lock(&inode->i_lock); @@ -669,7 +669,7 @@ static long writeback_sb_inodes(struct super_block *sb, * 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); + __writeback_single_inode(inode, &wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote += write_chunk - wbc.nr_to_write; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index aba15f1b7ad..78d2837bc94 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1379,6 +1379,7 @@ static const struct vm_operations_struct fuse_file_vm_ops = { .close = fuse_vma_close, .fault = filemap_fault, .page_mkwrite = fuse_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 30e21997a1a..0def0504afc 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -492,6 +492,7 @@ out: static const struct vm_operations_struct gfs2_vm_ops = { .fault = filemap_fault, .page_mkwrite = gfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; /** @@ -526,7 +527,6 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) return error; } vma->vm_ops = &gfs2_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9460120a517..c5bc355d824 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) * way when do_mmap_pgoff unwinds (may be important on powerpc * and ia64). */ - vma->vm_flags |= VM_HUGETLB | VM_RESERVED; + vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &hugetlb_vm_ops; if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) @@ -397,17 +397,16 @@ static void hugetlbfs_evict_inode(struct inode *inode) } static inline void -hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff) +hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff) { struct vm_area_struct *vma; - struct prio_tree_iter iter; - vma_prio_tree_foreach(vma, &iter, root, pgoff, ULONG_MAX) { + vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) { unsigned long v_offset; /* * Can the expression below overflow on 32-bit arches? - * No, because the prio_tree returns us only those vmas + * No, because the interval tree returns us only those vmas * which overlap the truncated area starting at pgoff, * and no vma on a 32-bit arch can span beyond the 4GB. */ @@ -432,7 +431,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset) i_size_write(inode, offset); mutex_lock(&mapping->i_mmap_mutex); - if (!prio_tree_empty(&mapping->i_mmap)) + if (!RB_EMPTY_ROOT(&mapping->i_mmap)) hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff); mutex_unlock(&mapping->i_mmap_mutex); truncate_hugepages(inode, offset); diff --git a/fs/inode.c b/fs/inode.c index ac8d904b3f1..b03c7195724 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -348,7 +348,7 @@ void address_space_init_once(struct address_space *mapping) mutex_init(&mapping->i_mmap_mutex); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); - INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap); + mapping->i_mmap = RB_ROOT; INIT_LIST_HEAD(&mapping->i_mmap_nonlinear); } EXPORT_SYMBOL(address_space_init_once); diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index af5280fb579..3091d42992f 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -1014,17 +1014,35 @@ restart_loop: * there's no point in keeping a checkpoint record for * it. */ - /* A buffer which has been freed while still being - * journaled by a previous transaction may end up still - * being dirty here, but we want to avoid writing back - * that buffer in the future after the "add to orphan" - * operation been committed, That's not only a performance - * gain, it also stops aliasing problems if the buffer is - * left behind for writeback and gets reallocated for another - * use in a different page. */ - if (buffer_freed(bh) && !jh->b_next_transaction) { - clear_buffer_freed(bh); - clear_buffer_jbddirty(bh); + /* + * A buffer which has been freed while still being journaled by + * a previous transaction. + */ + if (buffer_freed(bh)) { + /* + * If the running transaction is the one containing + * "add to orphan" operation (b_next_transaction != + * NULL), we have to wait for that transaction to + * commit before we can really get rid of the buffer. + * So just clear b_modified to not confuse transaction + * credit accounting and refile the buffer to + * BJ_Forget of the running transaction. If the just + * committed transaction contains "add to orphan" + * operation, we can completely invalidate the buffer + * now. We are rather through in that since the + * buffer may be still accessible when blocksize < + * pagesize and it is attached to the last partial + * page. + */ + jh->b_modified = 0; + if (!jh->b_next_transaction) { + clear_buffer_freed(bh); + clear_buffer_jbddirty(bh); + clear_buffer_mapped(bh); + clear_buffer_new(bh); + clear_buffer_req(bh); + bh->b_bdev = NULL; + } } if (buffer_jbddirty(bh)) { diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e149b99a7ff..484b8d1c6cb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1354,6 +1354,11 @@ static void jbd2_mark_journal_empty(journal_t *journal) BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); read_lock(&journal->j_state_lock); + /* Is it already empty? */ + if (sb->s_start == 0) { + read_unlock(&journal->j_state_lock); + return; + } jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", journal->j_tail_sequence); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 0131e436253..626846bac32 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -289,8 +289,11 @@ int jbd2_journal_recover(journal_t *journal) if (!err) err = err2; /* Make sure all replayed data is on permanent storage */ - if (journal->j_flags & JBD2_BARRIER) - blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + if (journal->j_flags & JBD2_BARRIER) { + err2 = blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL); + if (!err) + err = err2; + } return err; } diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index fb1ab9533b6..a74ba465954 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1841,15 +1841,16 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction) * We're outside-transaction here. Either or both of j_running_transaction * and j_committing_transaction may be NULL. */ -static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) +static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh, + int partial_page) { transaction_t *transaction; struct journal_head *jh; int may_free = 1; - int ret; BUFFER_TRACE(bh, "entry"); +retry: /* * It is safe to proceed here without the j_list_lock because the * buffers cannot be stolen by try_to_free_buffers as long as we are @@ -1878,10 +1879,18 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * clear the buffer dirty bit at latest at the moment when the * transaction marking the buffer as freed in the filesystem * structures is committed because from that moment on the - * buffer can be reallocated and used by a different page. + * block can be reallocated and used by a different page. * Since the block hasn't been freed yet but the inode has * already been added to orphan list, it is safe for us to add * the buffer to BJ_Forget list of the newest transaction. + * + * Also we have to clear buffer_mapped flag of a truncated buffer + * because the buffer_head may be attached to the page straddling + * i_size (can happen only when blocksize < pagesize) and thus the + * buffer_head can be reused when the file is extended again. So we end + * up keeping around invalidated buffers attached to transactions' + * BJ_Forget list just to stop checkpointing code from cleaning up + * the transaction this buffer was modified in. */ transaction = jh->b_transaction; if (transaction == NULL) { @@ -1908,13 +1917,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * committed, the buffer won't be needed any * longer. */ JBUFFER_TRACE(jh, "checkpointed: add to BJ_Forget"); - ret = __dispose_buffer(jh, + may_free = __dispose_buffer(jh, journal->j_running_transaction); - jbd2_journal_put_journal_head(jh); - spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - write_unlock(&journal->j_state_lock); - return ret; + goto zap_buffer; } else { /* There is no currently-running transaction. So the * orphan record which we wrote for this file must have @@ -1922,13 +1927,9 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) * the committing transaction, if it exists. */ if (journal->j_committing_transaction) { JBUFFER_TRACE(jh, "give to committing trans"); - ret = __dispose_buffer(jh, + may_free = __dispose_buffer(jh, journal->j_committing_transaction); - jbd2_journal_put_journal_head(jh); - spin_unlock(&journal->j_list_lock); - jbd_unlock_bh_state(bh); - write_unlock(&journal->j_state_lock); - return ret; + goto zap_buffer; } else { /* The orphan record's transaction has * committed. We can cleanse this buffer */ @@ -1940,10 +1941,24 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) JBUFFER_TRACE(jh, "on committing transaction"); /* * The buffer is committing, we simply cannot touch - * it. So we just set j_next_transaction to the - * running transaction (if there is one) and mark - * buffer as freed so that commit code knows it should - * clear dirty bits when it is done with the buffer. + * it. If the page is straddling i_size we have to wait + * for commit and try again. + */ + if (partial_page) { + tid_t tid = journal->j_committing_transaction->t_tid; + + jbd2_journal_put_journal_head(jh); + spin_unlock(&journal->j_list_lock); + jbd_unlock_bh_state(bh); + write_unlock(&journal->j_state_lock); + jbd2_log_wait_commit(journal, tid); + goto retry; + } + /* + * OK, buffer won't be reachable after truncate. We just set + * j_next_transaction to the running transaction (if there is + * one) and mark buffer as freed so that commit code knows it + * should clear dirty bits when it is done with the buffer. */ set_buffer_freed(bh); if (journal->j_running_transaction && buffer_jbddirty(bh)) @@ -1966,6 +1981,15 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh) } zap_buffer: + /* + * This is tricky. Although the buffer is truncated, it may be reused + * if blocksize < pagesize and it is attached to the page straddling + * EOF. Since the buffer might have been added to BJ_Forget list of the + * running transaction, journal_get_write_access() won't clear + * b_modified and credit accounting gets confused. So clear b_modified + * here. + */ + jh->b_modified = 0; jbd2_journal_put_journal_head(jh); zap_buffer_no_jh: spin_unlock(&journal->j_list_lock); @@ -2017,7 +2041,8 @@ void jbd2_journal_invalidatepage(journal_t *journal, if (offset <= curr_off) { /* This block is wholly outside the truncation point */ lock_buffer(bh); - may_free &= journal_unmap_buffer(journal, bh); + may_free &= journal_unmap_buffer(journal, bh, + offset > 0); unlock_buffer(bh); } curr_off = next_off; diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c index 1ea349fff68..ae81b01e6fd 100644 --- a/fs/jffs2/readinode.c +++ b/fs/jffs2/readinode.c @@ -394,8 +394,11 @@ static int jffs2_add_tn_to_tree(struct jffs2_sb_info *c, } /* Trivial function to remove the last node in the tree. Which by definition - has no right-hand -- so can be removed just by making its only child (if - any) take its place under its parent. */ + has no right-hand child — so can be removed just by making its left-hand + child (if any) take its place under its parent. Since this is only done + when we're consuming the whole tree, there's no need to use rb_erase() + and let it worry about adjusting colours and balancing the tree. That + would just be a waste of time. */ static void eat_last(struct rb_root *root, struct rb_node *node) { struct rb_node *parent = rb_parent(node); @@ -412,12 +415,12 @@ static void eat_last(struct rb_root *root, struct rb_node *node) link = &parent->rb_right; *link = node->rb_left; - /* Colour doesn't matter now. Only the parent pointer. */ if (node->rb_left) - node->rb_left->rb_parent_color = node->rb_parent_color; + node->rb_left->__rb_parent_color = node->__rb_parent_color; } -/* We put this in reverse order, so we can just use eat_last */ +/* We put the version tree in reverse order, so we can use the same eat_last() + function that we use to consume the tmpnode tree (tn_root). */ static void ver_insert(struct rb_root *ver_root, struct jffs2_tmp_dnode_info *tn) { struct rb_node **link = &ver_root->rb_node; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 6a7fcab7ecb..f692be97676 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -578,6 +578,7 @@ out: static const struct vm_operations_struct nfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nfs_need_sync_write(struct file *filp, struct inode *inode) diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a4d56ac02e6..16f35f7423c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -116,6 +116,7 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (unlikely(ret)) goto out; + file_update_time(vma->vm_file); ret = __block_page_mkwrite(vma, vmf, nilfs_get_block); if (ret) { nilfs_transaction_abort(inode->i_sb); @@ -134,13 +135,13 @@ static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) static const struct vm_operations_struct nilfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = nilfs_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) { file_accessed(file); vma->vm_ops = &nilfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c index d150372fd81..47a87dda54c 100644 --- a/fs/ocfs2/mmap.c +++ b/fs/ocfs2/mmap.c @@ -173,6 +173,7 @@ out: static const struct vm_operations_struct ocfs2_file_vm_ops = { .fault = ocfs2_fault, .page_mkwrite = ocfs2_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) @@ -188,7 +189,6 @@ int ocfs2_mmap(struct file *file, struct vm_area_struct *vma) ocfs2_inode_unlock(file->f_dentry->d_inode, lock_level); out: vma->vm_ops = &ocfs2_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; return 0; } diff --git a/fs/proc/base.c b/fs/proc/base.c index d295af99367..ef5c84be66f 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -873,111 +873,6 @@ static const struct file_operations proc_environ_operations = { .release = mem_release, }; -static ssize_t oom_adjust_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); - char buffer[PROC_NUMBUF]; - size_t len; - int oom_adjust = OOM_DISABLE; - unsigned long flags; - - if (!task) - return -ESRCH; - - if (lock_task_sighand(task, &flags)) { - oom_adjust = task->signal->oom_adj; - unlock_task_sighand(task, &flags); - } - - put_task_struct(task); - - len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust); - - return simple_read_from_buffer(buf, count, ppos, buffer, len); -} - -static ssize_t oom_adjust_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct task_struct *task; - char buffer[PROC_NUMBUF]; - int oom_adjust; - unsigned long flags; - int err; - - memset(buffer, 0, sizeof(buffer)); - if (count > sizeof(buffer) - 1) - count = sizeof(buffer) - 1; - if (copy_from_user(buffer, buf, count)) { - err = -EFAULT; - goto out; - } - - err = kstrtoint(strstrip(buffer), 0, &oom_adjust); - if (err) - goto out; - if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && - oom_adjust != OOM_DISABLE) { - err = -EINVAL; - goto out; - } - - task = get_proc_task(file->f_path.dentry->d_inode); - if (!task) { - err = -ESRCH; - goto out; - } - - task_lock(task); - if (!task->mm) { - err = -EINVAL; - goto err_task_lock; - } - - if (!lock_task_sighand(task, &flags)) { - err = -ESRCH; - goto err_task_lock; - } - - if (oom_adjust < task->signal->oom_adj && !capable(CAP_SYS_RESOURCE)) { - err = -EACCES; - goto err_sighand; - } - - /* - * Warn that /proc/pid/oom_adj is deprecated, see - * Documentation/feature-removal-schedule.txt. - */ - printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", - current->comm, task_pid_nr(current), task_pid_nr(task), - task_pid_nr(task)); - task->signal->oom_adj = oom_adjust; - /* - * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum - * value is always attainable. - */ - if (task->signal->oom_adj == OOM_ADJUST_MAX) - task->signal->oom_score_adj = OOM_SCORE_ADJ_MAX; - else - task->signal->oom_score_adj = (oom_adjust * OOM_SCORE_ADJ_MAX) / - -OOM_DISABLE; - trace_oom_score_adj_update(task); -err_sighand: - unlock_task_sighand(task, &flags); -err_task_lock: - task_unlock(task); - put_task_struct(task); -out: - return err < 0 ? err : count; -} - -static const struct file_operations proc_oom_adjust_operations = { - .read = oom_adjust_read, - .write = oom_adjust_write, - .llseek = generic_file_llseek, -}; - static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -1051,15 +946,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) task->signal->oom_score_adj_min = oom_score_adj; trace_oom_score_adj_update(task); - /* - * Scale /proc/pid/oom_adj appropriately ensuring that OOM_DISABLE is - * always attainable. - */ - if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - task->signal->oom_adj = OOM_DISABLE; - else - task->signal->oom_adj = (oom_score_adj * OOM_ADJUST_MAX) / - OOM_SCORE_ADJ_MAX; + err_sighand: unlock_task_sighand(task, &flags); err_task_lock: @@ -2710,7 +2597,6 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), - REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), @@ -3077,7 +2963,6 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), - REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adjust_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), diff --git a/fs/proc/page.c b/fs/proc/page.c index 7fcd0d60a96..b8730d9ebae 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -115,7 +115,13 @@ u64 stable_page_flags(struct page *page) u |= 1 << KPF_COMPOUND_TAIL; if (PageHuge(page)) u |= 1 << KPF_HUGE; - else if (PageTransCompound(page)) + /* + * PageTransCompound can be true for non-huge compound pages (slab + * pages or pages allocated by drivers with __GFP_COMP) because it + * just checks PG_head/PG_tail, so we need to check PageLRU to make + * sure a given page is a thp, not a non-huge compound page. + */ + else if (PageTransCompound(page) && PageLRU(compound_trans_head(page))) u |= 1 << KPF_THP; /* diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index dcd56f84db7..a781bdf0669 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -142,6 +142,7 @@ static int insert_entry(struct ctl_table_header *head, struct ctl_table *entry) } rb_link_node(node, parent, p); + rb_insert_color(node, &head->parent->root); return 0; } @@ -168,10 +169,8 @@ static void init_header(struct ctl_table_header *head, head->node = node; if (node) { struct ctl_table *entry; - for (entry = table; entry->procname; entry++, node++) { - rb_init_node(&node->node); + for (entry = table; entry->procname; entry++, node++) node->header = head; - } } } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 4540b8f76f1..79827ce03e3 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -54,7 +54,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) "VmPTE:\t%8lu kB\n" "VmSwap:\t%8lu kB\n", hiwater_vm << (PAGE_SHIFT-10), - (total_vm - mm->reserved_vm) << (PAGE_SHIFT-10), + total_vm << (PAGE_SHIFT-10), mm->locked_vm << (PAGE_SHIFT-10), mm->pinned_vm << (PAGE_SHIFT-10), hiwater_rss << (PAGE_SHIFT-10), diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index d39bb5cce88..ca71db69da0 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -23,6 +23,7 @@ config PSTORE_FTRACE bool "Persistent function tracer" depends on PSTORE depends on FUNCTION_TRACER + depends on DEBUG_FS help With this option kernel traces function calls into a persistent ram buffer that can be decoded and dumped after reboot through diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c index a130d484b7d..2d57e1ac011 100644 --- a/fs/pstore/ftrace.c +++ b/fs/pstore/ftrace.c @@ -17,19 +17,113 @@ #include <linux/percpu.h> #include <linux/smp.h> #include <linux/atomic.h> +#include <linux/types.h> +#include <linux/mutex.h> +#include <linux/ftrace.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/cache.h> #include <asm/barrier.h> #include "internal.h" -void notrace pstore_ftrace_call(unsigned long ip, unsigned long parent_ip) +static void notrace pstore_ftrace_call(unsigned long ip, + unsigned long parent_ip) { + unsigned long flags; struct pstore_ftrace_record rec = {}; if (unlikely(oops_in_progress)) return; + local_irq_save(flags); + rec.ip = ip; rec.parent_ip = parent_ip; pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id()); psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec, sizeof(rec), psinfo); + + local_irq_restore(flags); +} + +static struct ftrace_ops pstore_ftrace_ops __read_mostly = { + .func = pstore_ftrace_call, +}; + +static DEFINE_MUTEX(pstore_ftrace_lock); +static bool pstore_ftrace_enabled; + +static ssize_t pstore_ftrace_knob_write(struct file *f, const char __user *buf, + size_t count, loff_t *ppos) +{ + u8 on; + ssize_t ret; + + ret = kstrtou8_from_user(buf, count, 2, &on); + if (ret) + return ret; + + mutex_lock(&pstore_ftrace_lock); + + if (!on ^ pstore_ftrace_enabled) + goto out; + + if (on) + ret = register_ftrace_function(&pstore_ftrace_ops); + else + ret = unregister_ftrace_function(&pstore_ftrace_ops); + if (ret) { + pr_err("%s: unable to %sregister ftrace ops: %zd\n", + __func__, on ? "" : "un", ret); + goto err; + } + + pstore_ftrace_enabled = on; +out: + ret = count; +err: + mutex_unlock(&pstore_ftrace_lock); + + return ret; +} + +static ssize_t pstore_ftrace_knob_read(struct file *f, char __user *buf, + size_t count, loff_t *ppos) +{ + char val[] = { '0' + pstore_ftrace_enabled, '\n' }; + + return simple_read_from_buffer(buf, count, ppos, val, sizeof(val)); +} + +static const struct file_operations pstore_knob_fops = { + .open = simple_open, + .read = pstore_ftrace_knob_read, + .write = pstore_ftrace_knob_write, +}; + +void pstore_register_ftrace(void) +{ + struct dentry *dir; + struct dentry *file; + + if (!psinfo->write_buf) + return; + + dir = debugfs_create_dir("pstore", NULL); + if (!dir) { + pr_err("%s: unable to create pstore directory\n", __func__); + return; + } + + file = debugfs_create_file("record_ftrace", 0600, dir, NULL, + &pstore_knob_fops); + if (!file) { + pr_err("%s: unable to create record_ftrace file\n", __func__); + goto err_file; + } + + return; +err_file: + debugfs_remove(dir); } diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h index 0d0d3b7d5f1..4847f588b7d 100644 --- a/fs/pstore/internal.h +++ b/fs/pstore/internal.h @@ -39,6 +39,12 @@ pstore_ftrace_decode_cpu(struct pstore_ftrace_record *rec) #endif } +#ifdef CONFIG_PSTORE_FTRACE +extern void pstore_register_ftrace(void); +#else +static inline void pstore_register_ftrace(void) {} +#endif + extern struct pstore_info *psinfo; extern void pstore_set_kmsg_bytes(int); diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 29996e8793a..a40da07e93d 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -164,7 +164,13 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) if (c > psinfo->bufsize) c = psinfo->bufsize; - spin_lock_irqsave(&psinfo->buf_lock, flags); + + if (oops_in_progress) { + if (!spin_trylock_irqsave(&psinfo->buf_lock, flags)) + break; + } else { + spin_lock_irqsave(&psinfo->buf_lock, flags); + } memcpy(psinfo->buf, s, c); psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); @@ -236,6 +242,7 @@ int pstore_register(struct pstore_info *psi) kmsg_dump_register(&pstore_dumper); pstore_register_console(); + pstore_register_ftrace(); if (pstore_update_ms >= 0) { pstore_timer.expires = jiffies + diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 0b311bc1891..1a4f6da58ea 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -32,6 +32,7 @@ #include <linux/ioport.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/compiler.h> #include <linux/pstore_ram.h> #define RAMOOPS_KERNMSG_HDR "====" @@ -181,12 +182,11 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz) return len; } - -static int ramoops_pstore_write_buf(enum pstore_type_id type, - enum kmsg_dump_reason reason, - u64 *id, unsigned int part, - const char *buf, size_t size, - struct pstore_info *psi) +static int notrace ramoops_pstore_write_buf(enum pstore_type_id type, + enum kmsg_dump_reason reason, + u64 *id, unsigned int part, + const char *buf, size_t size, + struct pstore_info *psi) { struct ramoops_context *cxt = psi->data; struct persistent_ram_zone *prz = cxt->przs[cxt->dump_write_cnt]; @@ -406,7 +406,7 @@ static int __devinit ramoops_probe(struct platform_device *pdev) goto fail_init_fprz; if (!cxt->przs && !cxt->cprz && !cxt->fprz) { - pr_err("memory size too small, minimum is %lu\n", + pr_err("memory size too small, minimum is %zu\n", cxt->console_size + cxt->record_size + cxt->ftrace_size); goto fail_cnt; @@ -414,13 +414,14 @@ static int __devinit ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Console can handle any buffer size, so prefer dumps buffer - * size since usually it is smaller. + * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we + * have to handle dumps, we must have at least record_size buffer. And + * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be + * ZERO_SIZE_PTR). */ - if (cxt->przs) - cxt->pstore.bufsize = cxt->przs[0]->buffer_size; - else - cxt->pstore.bufsize = cxt->cprz->buffer_size; + if (cxt->console_size) + cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */ + cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize); cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); spin_lock_init(&cxt->pstore.buf_lock); if (!cxt->pstore.buf) { @@ -537,6 +538,7 @@ postcore_initcall(ramoops_init); static void __exit ramoops_exit(void) { platform_driver_unregister(&ramoops_driver); + platform_device_unregister(dummy); kfree(dummy_data); } module_exit(ramoops_exit); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index ff48c5a8530..5bc77817f38 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1536,6 +1536,7 @@ out_unlock: static const struct vm_operations_struct ubifs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = ubifs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1eaeb8be3aa..aa473fa640a 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -940,7 +940,6 @@ xfs_file_mmap( struct vm_area_struct *vma) { vma->vm_ops = &xfs_file_vm_ops; - vma->vm_flags |= VM_CAN_NONLINEAR; file_accessed(filp); return 0; @@ -1443,4 +1442,5 @@ const struct file_operations xfs_dir_file_operations = { static const struct vm_operations_struct xfs_file_vm_ops = { .fault = filemap_fault, .page_mkwrite = xfs_vm_page_mkwrite, + .remap_pages = generic_file_remap_pages, }; |