diff options
Diffstat (limited to 'fs')
175 files changed, 3282 insertions, 2517 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index c71e88602ff..cc1cfae726b 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -259,8 +259,7 @@ static int v9fs_launder_page(struct page *page) * */ static ssize_t -v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t pos, unsigned long nr_segs) +v9fs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { /* * FIXME @@ -269,7 +268,7 @@ v9fs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, */ p9_debug(P9_DEBUG_VFS, "v9fs_direct_IO: v9fs_direct_IO (%s) off/no(%lld/%lu) EINVAL\n", iocb->ki_filp->f_path.dentry->d_name.name, - (long long)pos, nr_segs); + (long long)pos, iter->nr_segs); return -EINVAL; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 96e55076069..520c11c2dcc 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -692,7 +692,7 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count, { if (filp->f_flags & O_DIRECT) return v9fs_direct_read(filp, data, count, offset); - return do_sync_read(filp, data, count, offset); + return new_sync_read(filp, data, count, offset); } /** @@ -760,7 +760,7 @@ err_out: buff_write: mutex_unlock(&inode->i_mutex); - return do_sync_write(filp, data, count, offsetp); + return new_sync_write(filp, data, count, offsetp); } /** @@ -778,7 +778,7 @@ v9fs_cached_file_write(struct file *filp, const char __user * data, if (filp->f_flags & O_DIRECT) return v9fs_direct_write(filp, data, count, offset); - return do_sync_write(filp, data, count, offset); + return new_sync_write(filp, data, count, offset); } @@ -847,8 +847,8 @@ const struct file_operations v9fs_cached_file_operations = { .llseek = generic_file_llseek, .read = v9fs_cached_file_read, .write = v9fs_cached_file_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock, @@ -860,8 +860,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .llseek = generic_file_llseek, .read = v9fs_cached_file_read, .write = v9fs_cached_file_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .open = v9fs_file_open, .release = v9fs_dir_release, .lock = v9fs_file_lock_dotl, diff --git a/fs/adfs/file.c b/fs/adfs/file.c index a36da5382b4..07c9edce5aa 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -23,12 +23,12 @@ const struct file_operations adfs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .splice_read = generic_file_splice_read, }; diff --git a/fs/affs/file.c b/fs/affs/file.c index 0270303388e..a7fe57d2cd9 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -27,10 +27,10 @@ static int affs_file_release(struct inode *inode, struct file *filp); const struct file_operations affs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = affs_file_open, .release = affs_file_release, diff --git a/fs/afs/file.c b/fs/afs/file.c index 66d50fe2ee4..932ce07948b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -31,10 +31,10 @@ const struct file_operations afs_file_operations = { .open = afs_open, .release = afs_release, .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = afs_file_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = afs_file_write, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, .fsync = afs_fsync, diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 590b55f46d6..71d5982312f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -747,8 +747,7 @@ extern int afs_write_end(struct file *file, struct address_space *mapping, extern int afs_writepage(struct page *, struct writeback_control *); extern int afs_writepages(struct address_space *, struct writeback_control *); extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); -extern ssize_t afs_file_write(struct kiocb *, const struct iovec *, - unsigned long, loff_t); +extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *); extern int afs_writeback_all(struct afs_vnode *); extern int afs_fsync(struct file *, loff_t, loff_t, int); diff --git a/fs/afs/main.c b/fs/afs/main.c index 42dd2e499ed..35de0c04729 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -55,13 +55,13 @@ static int __init afs_get_client_UUID(void) afs_uuid.time_low = uuidtime; afs_uuid.time_mid = uuidtime >> 32; afs_uuid.time_hi_and_version = (uuidtime >> 48) & AFS_UUID_TIMEHI_MASK; - afs_uuid.time_hi_and_version = AFS_UUID_VERSION_TIME; + afs_uuid.time_hi_and_version |= AFS_UUID_VERSION_TIME; get_random_bytes(&clockseq, 2); afs_uuid.clock_seq_low = clockseq; afs_uuid.clock_seq_hi_and_reserved = (clockseq >> 8) & AFS_UUID_CLOCKHI_MASK; - afs_uuid.clock_seq_hi_and_reserved = AFS_UUID_VARIANT_STD; + afs_uuid.clock_seq_hi_and_reserved |= AFS_UUID_VARIANT_STD; _debug("AFS UUID: %08x-%04x-%04x-%02x%02x-%02x%02x%02x%02x%02x%02x", afs_uuid.time_low, diff --git a/fs/afs/write.c b/fs/afs/write.c index a890db4b989..ab6adfd5251 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -625,15 +625,14 @@ void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call) /* * write to an AFS file */ -ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct afs_vnode *vnode = AFS_FS_I(file_inode(iocb->ki_filp)); ssize_t result; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(from); - _enter("{%x.%u},{%zu},%lu,", - vnode->fid.vid, vnode->fid.vnode, count, nr_segs); + _enter("{%x.%u},{%zu},", + vnode->fid.vid, vnode->fid.vnode, count); if (IS_SWAPFILE(&vnode->vfs_inode)) { printk(KERN_INFO @@ -644,7 +643,7 @@ ssize_t afs_file_write(struct kiocb *iocb, const struct iovec *iov, if (!count) return 0; - result = generic_file_aio_write(iocb, iov, nr_segs, pos); + result = generic_file_write_iter(iocb, from); if (IS_ERR_VALUE(result)) { _leave(" = %zd", result); return result; @@ -477,7 +477,7 @@ void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) } EXPORT_SYMBOL(kiocb_set_cancel_fn); -static int kiocb_cancel(struct kioctx *ctx, struct kiocb *kiocb) +static int kiocb_cancel(struct kiocb *kiocb) { kiocb_cancel_fn *old, *cancel; @@ -538,7 +538,7 @@ static void free_ioctx_users(struct percpu_ref *ref) struct kiocb, ki_list); list_del_init(&req->ki_list); - kiocb_cancel(ctx, req); + kiocb_cancel(req); } spin_unlock_irq(&ctx->ctx_lock); @@ -727,42 +727,42 @@ err: * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ -static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, +static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, struct completion *requests_done) { - if (!atomic_xchg(&ctx->dead, 1)) { - struct kioctx_table *table; + struct kioctx_table *table; - spin_lock(&mm->ioctx_lock); - rcu_read_lock(); - table = rcu_dereference(mm->ioctx_table); + if (atomic_xchg(&ctx->dead, 1)) + return -EINVAL; - WARN_ON(ctx != table->table[ctx->id]); - table->table[ctx->id] = NULL; - rcu_read_unlock(); - spin_unlock(&mm->ioctx_lock); - /* percpu_ref_kill() will do the necessary call_rcu() */ - wake_up_all(&ctx->wait); + spin_lock(&mm->ioctx_lock); + rcu_read_lock(); + table = rcu_dereference(mm->ioctx_table); - /* - * It'd be more correct to do this in free_ioctx(), after all - * the outstanding kiocbs have finished - but by then io_destroy - * has already returned, so io_setup() could potentially return - * -EAGAIN with no ioctxs actually in use (as far as userspace - * could tell). - */ - aio_nr_sub(ctx->max_reqs); + WARN_ON(ctx != table->table[ctx->id]); + table->table[ctx->id] = NULL; + rcu_read_unlock(); + spin_unlock(&mm->ioctx_lock); - if (ctx->mmap_size) - vm_munmap(ctx->mmap_base, ctx->mmap_size); + /* percpu_ref_kill() will do the necessary call_rcu() */ + wake_up_all(&ctx->wait); - ctx->requests_done = requests_done; - percpu_ref_kill(&ctx->users); - } else { - if (requests_done) - complete(requests_done); - } + /* + * It'd be more correct to do this in free_ioctx(), after all + * the outstanding kiocbs have finished - but by then io_destroy + * has already returned, so io_setup() could potentially return + * -EAGAIN with no ioctxs actually in use (as far as userspace + * could tell). + */ + aio_nr_sub(ctx->max_reqs); + + if (ctx->mmap_size) + vm_munmap(ctx->mmap_base, ctx->mmap_size); + + ctx->requests_done = requests_done; + percpu_ref_kill(&ctx->users); + return 0; } /* wait_on_sync_kiocb: @@ -830,16 +830,20 @@ void exit_aio(struct mm_struct *mm) static void put_reqs_available(struct kioctx *ctx, unsigned nr) { struct kioctx_cpu *kcpu; + unsigned long flags; preempt_disable(); kcpu = this_cpu_ptr(ctx->cpu); + local_irq_save(flags); kcpu->reqs_available += nr; + while (kcpu->reqs_available >= ctx->req_batch * 2) { kcpu->reqs_available -= ctx->req_batch; atomic_add(ctx->req_batch, &ctx->reqs_available); } + local_irq_restore(flags); preempt_enable(); } @@ -847,10 +851,12 @@ static bool get_reqs_available(struct kioctx *ctx) { struct kioctx_cpu *kcpu; bool ret = false; + unsigned long flags; preempt_disable(); kcpu = this_cpu_ptr(ctx->cpu); + local_irq_save(flags); if (!kcpu->reqs_available) { int old, avail = atomic_read(&ctx->reqs_available); @@ -869,6 +875,7 @@ static bool get_reqs_available(struct kioctx *ctx) ret = true; kcpu->reqs_available--; out: + local_irq_restore(flags); preempt_enable(); return ret; } @@ -1021,6 +1028,7 @@ void aio_complete(struct kiocb *iocb, long res, long res2) /* everything turned out well, dispose of the aiocb. */ kiocb_free(iocb); + put_reqs_available(ctx, 1); /* * We have to order our ring_info tail store above and test @@ -1062,6 +1070,9 @@ static long aio_read_events_ring(struct kioctx *ctx, if (head == tail) goto out; + head %= ctx->nr_events; + tail %= ctx->nr_events; + while (ret < nr) { long avail; struct io_event *ev; @@ -1100,8 +1111,6 @@ static long aio_read_events_ring(struct kioctx *ctx, flush_dcache_page(ctx->ring_pages[0]); pr_debug("%li h%u t%u\n", ret, head, tail); - - put_reqs_available(ctx, ret); out: mutex_unlock(&ctx->ring_lock); @@ -1219,21 +1228,23 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) if (likely(NULL != ioctx)) { struct completion requests_done = COMPLETION_INITIALIZER_ONSTACK(requests_done); + int ret; /* Pass requests_done to kill_ioctx() where it can be set * in a thread-safe way. If we try to set it here then we have * a race condition if two io_destroy() called simultaneously. */ - kill_ioctx(current->mm, ioctx, &requests_done); + ret = kill_ioctx(current->mm, ioctx, &requests_done); percpu_ref_put(&ioctx->users); /* Wait until all IO for the context are done. Otherwise kernel * keep using user-space buffers even if user thinks the context * is destroyed. */ - wait_for_completion(&requests_done); + if (!ret) + wait_for_completion(&requests_done); - return 0; + return ret; } pr_debug("EINVAL: io_destroy: invalid context id\n"); return -EINVAL; @@ -1241,6 +1252,7 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) typedef ssize_t (aio_rw_op)(struct kiocb *, const struct iovec *, unsigned long, loff_t); +typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *); static ssize_t aio_setup_vectored_rw(struct kiocb *kiocb, int rw, char __user *buf, @@ -1298,7 +1310,9 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, int rw; fmode_t mode; aio_rw_op *rw_op; + rw_iter_op *iter_op; struct iovec inline_vec, *iovec = &inline_vec; + struct iov_iter iter; switch (opcode) { case IOCB_CMD_PREAD: @@ -1306,6 +1320,7 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, mode = FMODE_READ; rw = READ; rw_op = file->f_op->aio_read; + iter_op = file->f_op->read_iter; goto rw_common; case IOCB_CMD_PWRITE: @@ -1313,12 +1328,13 @@ static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, mode = FMODE_WRITE; rw = WRITE; rw_op = file->f_op->aio_write; + iter_op = file->f_op->write_iter; goto rw_common; rw_common: if (unlikely(!(file->f_mode & mode))) return -EBADF; - if (!rw_op) + if (!rw_op && !iter_op) return -EINVAL; ret = (opcode == IOCB_CMD_PREADV || @@ -1347,7 +1363,12 @@ rw_common: if (rw == WRITE) file_start_write(file); - ret = rw_op(req, iovec, nr_segs, req->ki_pos); + if (iter_op) { + iov_iter_init(&iter, rw, iovec, nr_segs, req->ki_nbytes); + ret = iter_op(req, &iter); + } else { + ret = rw_op(req, iovec, nr_segs, req->ki_pos); + } if (rw == WRITE) file_end_write(file); @@ -1585,7 +1606,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, kiocb = lookup_kiocb(ctx, iocb, key); if (kiocb) - ret = kiocb_cancel(ctx, kiocb); + ret = kiocb_cancel(kiocb); else ret = -EINVAL; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index d7bd395ab58..1c55388ae63 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -210,7 +210,7 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) int pipefd; struct autofs_sb_info *sbi; struct autofs_info *ino; - int pgrp; + int pgrp = 0; bool pgrp_set = false; int ret = -EINVAL; diff --git a/fs/bfs/file.c b/fs/bfs/file.c index ae289221833..e7f88ace1a2 100644 --- a/fs/bfs/file.c +++ b/fs/bfs/file.c @@ -23,10 +23,10 @@ const struct file_operations bfs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, }; diff --git a/fs/block_dev.c b/fs/block_dev.c index 83fba15cc39..6d7274619bf 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -165,14 +165,15 @@ blkdev_get_block(struct inode *inode, sector_t iblock, } static ssize_t -blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +blkdev_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset, - nr_segs, blkdev_get_block, NULL, NULL, 0); + return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iter, + offset, blkdev_get_block, + NULL, NULL, 0); } int __sync_blockdev(struct block_device *bdev, int wait) @@ -1571,43 +1572,38 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) * Does not take i_mutex for the write and thus is not for general purpose * use. */ -ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct blk_plug plug; ssize_t ret; - BUG_ON(iocb->ki_pos != pos); - blk_start_plug(&plug); - ret = __generic_file_aio_write(iocb, iov, nr_segs); + ret = __generic_file_write_iter(iocb, from); if (ret > 0) { ssize_t err; - - err = generic_write_sync(file, pos, ret); + err = generic_write_sync(file, iocb->ki_pos - ret, ret); if (err < 0) ret = err; } blk_finish_plug(&plug); return ret; } -EXPORT_SYMBOL_GPL(blkdev_aio_write); +EXPORT_SYMBOL_GPL(blkdev_write_iter); -static ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *bd_inode = file->f_mapping->host; loff_t size = i_size_read(bd_inode); + loff_t pos = iocb->ki_pos; if (pos >= size) return 0; size -= pos; - if (size < iocb->ki_nbytes) - nr_segs = iov_shorten((struct iovec *)iov, nr_segs, size); - return generic_file_aio_read(iocb, iov, nr_segs, pos); + iov_iter_truncate(to, size); + return generic_file_read_iter(iocb, to); } /* @@ -1639,10 +1635,10 @@ const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = blkdev_aio_read, - .aio_write = blkdev_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = blkdev_read_iter, + .write_iter = blkdev_write_iter, .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, @@ -1650,7 +1646,7 @@ const struct file_operations def_blk_fops = { .compat_ioctl = compat_blkdev_ioctl, #endif .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, }; int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 92371c41422..1daea0b4718 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -821,7 +821,7 @@ static void free_workspace(int type, struct list_head *workspace) spin_lock(workspace_lock); if (*num_workspace < num_online_cpus()) { - list_add_tail(workspace, idle_workspace); + list_add(workspace, idle_workspace); (*num_workspace)++; spin_unlock(workspace_lock); goto wake; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index b7e2c1c1ef3..be91397f4e9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1259,11 +1259,19 @@ struct btrfs_block_group_cache { spinlock_t lock; u64 pinned; u64 reserved; + u64 delalloc_bytes; u64 bytes_super; u64 flags; u64 sectorsize; u64 cache_generation; + /* + * It is just used for the delayed data space allocation because + * only the data space allocation and the relative metadata update + * can be done cross the transaction. + */ + struct rw_semaphore data_rwsem; + /* for raid56, this is a full stripe, without parity */ unsigned long full_stripe_len; @@ -3316,7 +3324,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_key *ins); int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, - struct btrfs_key *ins, int is_data); + struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, int full_backref, int no_quota); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -3330,7 +3338,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, u64 owner, u64 offset, int no_quota); -int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len); +int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len, + int delalloc); int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, u64 start, u64 len); void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 2af6e66fe78..eea26e1b2fd 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -36,6 +36,7 @@ #include "check-integrity.h" #include "rcu-string.h" #include "dev-replace.h" +#include "sysfs.h" static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret); @@ -562,6 +563,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, fs_info->fs_devices->latest_bdev = tgt_device->bdev; list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list); + /* replace the sysfs entry */ + btrfs_kobj_rm_device(fs_info, src_device); + btrfs_kobj_add_device(fs_info, tgt_device); + btrfs_rm_dev_replace_blocked(fs_info); btrfs_rm_dev_replace_srcdev(fs_info, src_device); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8bb4aa19898..08e65e9cf2a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -369,7 +369,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, &cached_state, GFP_NOFS); - btrfs_tree_read_unlock_blocking(eb); + if (need_lock) + btrfs_tree_read_unlock_blocking(eb); return ret; } @@ -2904,7 +2905,9 @@ retry_root_backup: if (ret) goto fail_qgroup; + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(tree_root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret < 0) { printk(KERN_WARNING "BTRFS: failed to recover relocation\n"); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index fafb3e53ecd..813537f362f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -105,7 +105,8 @@ static int find_next_key(struct btrfs_path *path, int level, static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve); + u64 num_bytes, int reserve, + int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); int btrfs_pin_extent(struct btrfs_root *root, @@ -3260,7 +3261,8 @@ again: spin_lock(&block_group->lock); if (block_group->cached != BTRFS_CACHE_FINISHED || - !btrfs_test_opt(root, SPACE_CACHE)) { + !btrfs_test_opt(root, SPACE_CACHE) || + block_group->delalloc_bytes) { /* * don't bother trying to write stuff out _if_ * a) we're not cached, @@ -5613,6 +5615,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log, * @cache: The cache we are manipulating * @num_bytes: The number of bytes in question * @reserve: One of the reservation enums + * @delalloc: The blocks are allocated for the delalloc write * * This is called by the allocator when it reserves space, or by somebody who is * freeing space that was never actually used on disk. For example if you @@ -5631,7 +5634,7 @@ int btrfs_exclude_logged_extents(struct btrfs_root *log, * succeeds. */ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve) + u64 num_bytes, int reserve, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; @@ -5650,12 +5653,18 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, num_bytes, 0); space_info->bytes_may_use -= num_bytes; } + + if (delalloc) + cache->delalloc_bytes += num_bytes; } } else { if (cache->ro) space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; + + if (delalloc) + cache->delalloc_bytes -= num_bytes; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); @@ -5669,7 +5678,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_caching_control *next; struct btrfs_caching_control *caching_ctl; struct btrfs_block_group_cache *cache; - struct btrfs_space_info *space_info; down_write(&fs_info->commit_root_sem); @@ -5692,9 +5700,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, up_write(&fs_info->commit_root_sem); - list_for_each_entry_rcu(space_info, &fs_info->space_info, list) - percpu_counter_set(&space_info->total_bytes_pinned, 0); - update_global_block_rsv(fs_info); } @@ -5732,6 +5737,7 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end) spin_lock(&cache->lock); cache->pinned -= len; space_info->bytes_pinned -= len; + percpu_counter_add(&space_info->total_bytes_pinned, -len); if (cache->ro) { space_info->bytes_readonly += len; readonly = true; @@ -6206,7 +6212,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); - btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE); + btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0); trace_btrfs_reserved_extent_free(root, buf->start, buf->len); pin = 0; } @@ -6365,6 +6371,70 @@ enum btrfs_loop_type { LOOP_NO_EMPTY_SIZE = 3, }; +static inline void +btrfs_lock_block_group(struct btrfs_block_group_cache *cache, + int delalloc) +{ + if (delalloc) + down_read(&cache->data_rwsem); +} + +static inline void +btrfs_grab_block_group(struct btrfs_block_group_cache *cache, + int delalloc) +{ + btrfs_get_block_group(cache); + if (delalloc) + down_read(&cache->data_rwsem); +} + +static struct btrfs_block_group_cache * +btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, + struct btrfs_free_cluster *cluster, + int delalloc) +{ + struct btrfs_block_group_cache *used_bg; + bool locked = false; +again: + spin_lock(&cluster->refill_lock); + if (locked) { + if (used_bg == cluster->block_group) + return used_bg; + + up_read(&used_bg->data_rwsem); + btrfs_put_block_group(used_bg); + } + + used_bg = cluster->block_group; + if (!used_bg) + return NULL; + + if (used_bg == block_group) + return used_bg; + + btrfs_get_block_group(used_bg); + + if (!delalloc) + return used_bg; + + if (down_read_trylock(&used_bg->data_rwsem)) + return used_bg; + + spin_unlock(&cluster->refill_lock); + down_read(&used_bg->data_rwsem); + locked = true; + goto again; +} + +static inline void +btrfs_release_block_group(struct btrfs_block_group_cache *cache, + int delalloc) +{ + if (delalloc) + up_read(&cache->data_rwsem); + btrfs_put_block_group(cache); +} + /* * walks the btree of allocated extents and find a hole of a given size. * The key ins is changed to record the hole: @@ -6379,7 +6449,7 @@ enum btrfs_loop_type { static noinline int find_free_extent(struct btrfs_root *orig_root, u64 num_bytes, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, - u64 flags) + u64 flags, int delalloc) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -6467,6 +6537,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, up_read(&space_info->groups_sem); } else { index = get_block_group_index(block_group); + btrfs_lock_block_group(block_group, delalloc); goto have_block_group; } } else if (block_group) { @@ -6481,7 +6552,7 @@ search: u64 offset; int cached; - btrfs_get_block_group(block_group); + btrfs_grab_block_group(block_group, delalloc); search_start = block_group->key.objectid; /* @@ -6529,16 +6600,16 @@ have_block_group: * the refill lock keeps out other * people trying to start a new cluster */ - spin_lock(&last_ptr->refill_lock); - used_block_group = last_ptr->block_group; - if (used_block_group != block_group && - (!used_block_group || - used_block_group->ro || - !block_group_bits(used_block_group, flags))) + used_block_group = btrfs_lock_cluster(block_group, + last_ptr, + delalloc); + if (!used_block_group) goto refill_cluster; - if (used_block_group != block_group) - btrfs_get_block_group(used_block_group); + if (used_block_group != block_group && + (used_block_group->ro || + !block_group_bits(used_block_group, flags))) + goto release_cluster; offset = btrfs_alloc_from_cluster(used_block_group, last_ptr, @@ -6552,16 +6623,15 @@ have_block_group: used_block_group, search_start, num_bytes); if (used_block_group != block_group) { - btrfs_put_block_group(block_group); + btrfs_release_block_group(block_group, + delalloc); block_group = used_block_group; } goto checks; } WARN_ON(last_ptr->block_group != used_block_group); - if (used_block_group != block_group) - btrfs_put_block_group(used_block_group); -refill_cluster: +release_cluster: /* If we are on LOOP_NO_EMPTY_SIZE, we can't * set up a new clusters, so lets just skip it * and let the allocator find whatever block @@ -6578,8 +6648,10 @@ refill_cluster: * succeeding in the unclustered * allocation. */ if (loop >= LOOP_NO_EMPTY_SIZE && - last_ptr->block_group != block_group) { + used_block_group != block_group) { spin_unlock(&last_ptr->refill_lock); + btrfs_release_block_group(used_block_group, + delalloc); goto unclustered_alloc; } @@ -6589,6 +6661,10 @@ refill_cluster: */ btrfs_return_cluster_to_free_space(NULL, last_ptr); + if (used_block_group != block_group) + btrfs_release_block_group(used_block_group, + delalloc); +refill_cluster: if (loop >= LOOP_NO_EMPTY_SIZE) { spin_unlock(&last_ptr->refill_lock); goto unclustered_alloc; @@ -6696,7 +6772,7 @@ checks: BUG_ON(offset > search_start); ret = btrfs_update_reserved_bytes(block_group, num_bytes, - alloc_type); + alloc_type, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -6708,13 +6784,13 @@ checks: trace_btrfs_reserve_extent(orig_root, block_group, search_start, num_bytes); - btrfs_put_block_group(block_group); + btrfs_release_block_group(block_group, delalloc); break; loop: failed_cluster_refill = false; failed_alloc = false; BUG_ON(index != get_block_group_index(block_group)); - btrfs_put_block_group(block_group); + btrfs_release_block_group(block_group, delalloc); } up_read(&space_info->groups_sem); @@ -6827,7 +6903,7 @@ again: int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, - struct btrfs_key *ins, int is_data) + struct btrfs_key *ins, int is_data, int delalloc) { bool final_tried = false; u64 flags; @@ -6837,7 +6913,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, again: WARN_ON(num_bytes < root->sectorsize); ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, - flags); + flags, delalloc); if (ret == -ENOSPC) { if (!final_tried && ins->offset) { @@ -6862,7 +6938,8 @@ again: } static int __btrfs_free_reserved_extent(struct btrfs_root *root, - u64 start, u64 len, int pin) + u64 start, u64 len, + int pin, int delalloc) { struct btrfs_block_group_cache *cache; int ret = 0; @@ -6881,7 +6958,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, pin_down_extent(root, cache, start, len, 1); else { btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE); + btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); } btrfs_put_block_group(cache); @@ -6891,15 +6968,15 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, } int btrfs_free_reserved_extent(struct btrfs_root *root, - u64 start, u64 len) + u64 start, u64 len, int delalloc) { - return __btrfs_free_reserved_extent(root, start, len, 0); + return __btrfs_free_reserved_extent(root, start, len, 0, delalloc); } int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, u64 start, u64 len) { - return __btrfs_free_reserved_extent(root, start, len, 1); + return __btrfs_free_reserved_extent(root, start, len, 1, 0); } static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans, @@ -7114,7 +7191,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, return -EINVAL; ret = btrfs_update_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT); + RESERVE_ALLOC_NO_ACCOUNT, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); @@ -7256,7 +7333,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, return ERR_CAST(block_rsv); ret = btrfs_reserve_extent(root, blocksize, blocksize, - empty_size, hint, &ins, 0); + empty_size, hint, &ins, 0, 0); if (ret) { unuse_block_rsv(root->fs_info, block_rsv, blocksize); return ERR_PTR(ret); @@ -8659,6 +8736,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size) start); atomic_set(&cache->count, 1); spin_lock_init(&cache->lock); + init_rwsem(&cache->data_rwsem); INIT_LIST_HEAD(&cache->list); INIT_LIST_HEAD(&cache->cluster_list); INIT_LIST_HEAD(&cache->new_bg_list); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f25a9092b94..a389820d158 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2354,7 +2354,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) { int uptodate = (err == 0); struct extent_io_tree *tree; - int ret; + int ret = 0; tree = &BTRFS_I(page->mapping->host)->io_tree; @@ -5068,6 +5068,43 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv, } } +int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dstv, + unsigned long start, + unsigned long len) +{ + size_t cur; + size_t offset; + struct page *page; + char *kaddr; + char __user *dst = (char __user *)dstv; + size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1); + unsigned long i = (start_offset + start) >> PAGE_CACHE_SHIFT; + int ret = 0; + + WARN_ON(start > eb->len); + WARN_ON(start + len > eb->start + eb->len); + + offset = (start_offset + start) & (PAGE_CACHE_SIZE - 1); + + while (len > 0) { + page = extent_buffer_page(eb, i); + + cur = min(len, (PAGE_CACHE_SIZE - offset)); + kaddr = page_address(page); + if (copy_to_user(dst, kaddr + offset, cur)) { + ret = -EFAULT; + break; + } + + dst += cur; + len -= cur; + offset = 0; + i++; + } + + return ret; +} + int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start, unsigned long min_len, char **map, unsigned long *map_start, diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 8b63f2d4651..ccc264e7bde 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -158,7 +158,6 @@ struct extent_buffer { * to unlock */ wait_queue_head_t read_lock_wq; - wait_queue_head_t lock_wq; struct page *pages[INLINE_EXTENT_BUFFER_PAGES]; #ifdef CONFIG_BTRFS_DEBUG struct list_head leak_list; @@ -304,6 +303,9 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv, void read_extent_buffer(struct extent_buffer *eb, void *dst, unsigned long start, unsigned long len); +int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst, + unsigned long start, + unsigned long len); void write_extent_buffer(struct extent_buffer *eb, const void *src, unsigned long start, unsigned long len); void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src, diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 1874aee69c8..225302b39af 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -75,6 +75,8 @@ void free_extent_map(struct extent_map *em) if (atomic_dec_and_test(&em->refs)) { WARN_ON(extent_map_in_tree(em)); WARN_ON(!list_empty(&em->list)); + if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags)) + kfree(em->bdev); kmem_cache_free(extent_map_cache, em); } } diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index e7fd8a56a14..b2991fd8583 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -15,6 +15,7 @@ #define EXTENT_FLAG_PREALLOC 3 /* pre-allocated extent */ #define EXTENT_FLAG_LOGGING 4 /* Logging this extent */ #define EXTENT_FLAG_FILLING 5 /* Filling in a preallocated extent */ +#define EXTENT_FLAG_FS_MAPPING 6 /* filesystem extent mapping type */ struct extent_map { struct rb_node rb_node; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index e472441feb5..1f2b99cb55e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -448,7 +448,7 @@ static noinline int btrfs_copy_from_user(loff_t pos, int num_pages, write_bytes -= copied; total_copied += copied; - /* Return to btrfs_file_aio_write to fault page */ + /* Return to btrfs_file_write_iter to fault page */ if (unlikely(copied == 0)) break; @@ -1675,27 +1675,22 @@ again: } static ssize_t __btrfs_direct_write(struct kiocb *iocb, - const struct iovec *iov, - unsigned long nr_segs, loff_t pos, - size_t count, size_t ocount) + struct iov_iter *from, + loff_t pos) { struct file *file = iocb->ki_filp; - struct iov_iter i; ssize_t written; ssize_t written_buffered; loff_t endbyte; int err; - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - count, ocount); + written = generic_file_direct_write(iocb, from, pos); - if (written < 0 || written == count) + if (written < 0 || !iov_iter_count(from)) return written; pos += written; - count -= written; - iov_iter_init(&i, iov, nr_segs, count, written); - written_buffered = __btrfs_buffered_write(file, &i, pos); + written_buffered = __btrfs_buffered_write(file, from, pos); if (written_buffered < 0) { err = written_buffered; goto out; @@ -1730,9 +1725,8 @@ static void update_time_for_write(struct inode *inode) inode_inc_iversion(inode); } -static ssize_t btrfs_file_aio_write(struct kiocb *iocb, - const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t btrfs_file_write_iter(struct kiocb *iocb, + struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); @@ -1741,18 +1735,12 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, u64 end_pos; ssize_t num_written = 0; ssize_t err = 0; - size_t count, ocount; + size_t count = iov_iter_count(from); bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); + loff_t pos = iocb->ki_pos; mutex_lock(&inode->i_mutex); - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) { - mutex_unlock(&inode->i_mutex); - goto out; - } - count = ocount; - current->backing_dev_info = inode->i_mapping->backing_dev_info; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) { @@ -1765,6 +1753,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, goto out; } + iov_iter_truncate(from, count); + err = file_remove_suid(file); if (err) { mutex_unlock(&inode->i_mutex); @@ -1806,14 +1796,9 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, atomic_inc(&BTRFS_I(inode)->sync_writers); if (unlikely(file->f_flags & O_DIRECT)) { - num_written = __btrfs_direct_write(iocb, iov, nr_segs, - pos, count, ocount); + num_written = __btrfs_direct_write(iocb, from, pos); } else { - struct iov_iter i; - - iov_iter_init(&i, iov, nr_segs, count, num_written); - - num_written = __btrfs_buffered_write(file, &i, pos); + num_written = __btrfs_buffered_write(file, from, pos); if (num_written > 0) iocb->ki_pos = pos + num_written; } @@ -2740,11 +2725,11 @@ out: const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, - .aio_write = btrfs_file_aio_write, + .write_iter = btrfs_file_write_iter, .mmap = btrfs_file_mmap, .open = generic_file_open, .release = btrfs_release_file, diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 372b05ff194..2b0a627cb5f 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -274,18 +274,32 @@ struct io_ctl { }; static int io_ctl_init(struct io_ctl *io_ctl, struct inode *inode, - struct btrfs_root *root) + struct btrfs_root *root, int write) { + int num_pages; + int check_crcs = 0; + + num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> + PAGE_CACHE_SHIFT; + + if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID) + check_crcs = 1; + + /* Make sure we can fit our crcs into the first page */ + if (write && check_crcs && + (num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) + return -ENOSPC; + memset(io_ctl, 0, sizeof(struct io_ctl)); - io_ctl->num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - io_ctl->pages = kzalloc(sizeof(struct page *) * io_ctl->num_pages, - GFP_NOFS); + + io_ctl->pages = kzalloc(sizeof(struct page *) * num_pages, GFP_NOFS); if (!io_ctl->pages) return -ENOMEM; + + io_ctl->num_pages = num_pages; io_ctl->root = root; - if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID) - io_ctl->check_crcs = 1; + io_ctl->check_crcs = check_crcs; + return 0; } @@ -666,6 +680,13 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, generation = btrfs_free_space_generation(leaf, header); btrfs_release_path(path); + if (!BTRFS_I(inode)->generation) { + btrfs_info(root->fs_info, + "The free space cache file (%llu) is invalid. skip it\n", + offset); + return 0; + } + if (BTRFS_I(inode)->generation != generation) { btrfs_err(root->fs_info, "free space inode generation (%llu) " @@ -677,7 +698,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, if (!num_entries) return 0; - ret = io_ctl_init(&io_ctl, inode, root); + ret = io_ctl_init(&io_ctl, inode, root, 0); if (ret) return ret; @@ -957,19 +978,18 @@ fail: } static noinline_for_stack int -add_ioctl_entries(struct btrfs_root *root, - struct inode *inode, - struct btrfs_block_group_cache *block_group, - struct io_ctl *io_ctl, - struct extent_state **cached_state, - struct list_head *bitmap_list, - int *entries) +write_pinned_extent_entries(struct btrfs_root *root, + struct btrfs_block_group_cache *block_group, + struct io_ctl *io_ctl, + int *entries) { u64 start, extent_start, extent_end, len; - struct list_head *pos, *n; struct extent_io_tree *unpin = NULL; int ret; + if (!block_group) + return 0; + /* * We want to add any pinned extents to our free space cache * so we don't leak the space @@ -979,23 +999,19 @@ add_ioctl_entries(struct btrfs_root *root, */ unpin = root->fs_info->pinned_extents; - if (block_group) - start = block_group->key.objectid; + start = block_group->key.objectid; - while (block_group && (start < block_group->key.objectid + - block_group->key.offset)) { + while (start < block_group->key.objectid + block_group->key.offset) { ret = find_first_extent_bit(unpin, start, &extent_start, &extent_end, EXTENT_DIRTY, NULL); - if (ret) { - ret = 0; - break; - } + if (ret) + return 0; /* This pinned extent is out of our range */ if (extent_start >= block_group->key.objectid + block_group->key.offset) - break; + return 0; extent_start = max(extent_start, start); extent_end = min(block_group->key.objectid + @@ -1005,11 +1021,20 @@ add_ioctl_entries(struct btrfs_root *root, *entries += 1; ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL); if (ret) - goto out_nospc; + return -ENOSPC; start = extent_end; } + return 0; +} + +static noinline_for_stack int +write_bitmap_entries(struct io_ctl *io_ctl, struct list_head *bitmap_list) +{ + struct list_head *pos, *n; + int ret; + /* Write out the bitmaps */ list_for_each_safe(pos, n, bitmap_list) { struct btrfs_free_space *entry = @@ -1017,36 +1042,24 @@ add_ioctl_entries(struct btrfs_root *root, ret = io_ctl_add_bitmap(io_ctl, entry->bitmap); if (ret) - goto out_nospc; + return -ENOSPC; list_del_init(&entry->list); } - /* Zero out the rest of the pages just to make sure */ - io_ctl_zero_remaining_pages(io_ctl); - - ret = btrfs_dirty_pages(root, inode, io_ctl->pages, io_ctl->num_pages, - 0, i_size_read(inode), cached_state); - io_ctl_drop_pages(io_ctl); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, - i_size_read(inode) - 1, cached_state, GFP_NOFS); + return 0; +} - if (ret) - goto fail; +static int flush_dirty_cache(struct inode *inode) +{ + int ret; ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); - if (ret) { + if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL, GFP_NOFS); - goto fail; - } - return 0; -fail: - return -1; - -out_nospc: - return -ENOSPC; + return ret; } static void noinline_for_stack @@ -1056,6 +1069,7 @@ cleanup_write_cache_enospc(struct inode *inode, struct list_head *bitmap_list) { struct list_head *pos, *n; + list_for_each_safe(pos, n, bitmap_list) { struct btrfs_free_space *entry = list_entry(pos, struct btrfs_free_space, list); @@ -1088,64 +1102,104 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode, { struct extent_state *cached_state = NULL; struct io_ctl io_ctl; - struct list_head bitmap_list; + LIST_HEAD(bitmap_list); int entries = 0; int bitmaps = 0; int ret; - int err = -1; - - INIT_LIST_HEAD(&bitmap_list); if (!i_size_read(inode)) return -1; - ret = io_ctl_init(&io_ctl, inode, root); + ret = io_ctl_init(&io_ctl, inode, root, 1); if (ret) return -1; + if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) { + down_write(&block_group->data_rwsem); + spin_lock(&block_group->lock); + if (block_group->delalloc_bytes) { + block_group->disk_cache_state = BTRFS_DC_WRITTEN; + spin_unlock(&block_group->lock); + up_write(&block_group->data_rwsem); + BTRFS_I(inode)->generation = 0; + ret = 0; + goto out; + } + spin_unlock(&block_group->lock); + } + /* Lock all pages first so we can lock the extent safely. */ io_ctl_prepare_pages(&io_ctl, inode, 0); lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, 0, &cached_state); - - /* Make sure we can fit our crcs into the first page */ - if (io_ctl.check_crcs && - (io_ctl.num_pages * sizeof(u32)) >= PAGE_CACHE_SIZE) - goto out_nospc; - io_ctl_set_generation(&io_ctl, trans->transid); + /* Write out the extent entries in the free space cache */ ret = write_cache_extent_entries(&io_ctl, ctl, block_group, &entries, &bitmaps, &bitmap_list); if (ret) goto out_nospc; - ret = add_ioctl_entries(root, inode, block_group, &io_ctl, - &cached_state, &bitmap_list, &entries); + /* + * Some spaces that are freed in the current transaction are pinned, + * they will be added into free space cache after the transaction is + * committed, we shouldn't lose them. + */ + ret = write_pinned_extent_entries(root, block_group, &io_ctl, &entries); + if (ret) + goto out_nospc; - if (ret == -ENOSPC) + /* At last, we write out all the bitmaps. */ + ret = write_bitmap_entries(&io_ctl, &bitmap_list); + if (ret) goto out_nospc; - else if (ret) + + /* Zero out the rest of the pages just to make sure */ + io_ctl_zero_remaining_pages(&io_ctl); + + /* Everything is written out, now we dirty the pages in the file. */ + ret = btrfs_dirty_pages(root, inode, io_ctl.pages, io_ctl.num_pages, + 0, i_size_read(inode), &cached_state); + if (ret) + goto out_nospc; + + if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) + up_write(&block_group->data_rwsem); + /* + * Release the pages and unlock the extent, we will flush + * them out later + */ + io_ctl_drop_pages(&io_ctl); + + unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, + i_size_read(inode) - 1, &cached_state, GFP_NOFS); + + /* Flush the dirty pages in the cache file. */ + ret = flush_dirty_cache(inode); + if (ret) goto out; - err = update_cache_item(trans, root, inode, path, offset, + /* Update the cache item to tell everyone this cache file is valid. */ + ret = update_cache_item(trans, root, inode, path, offset, entries, bitmaps); - out: io_ctl_free(&io_ctl); - if (err) { + if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; } btrfs_update_inode(trans, root, inode); - return err; + return ret; out_nospc: - cleanup_write_cache_enospc(inode, &io_ctl, &cached_state, &bitmap_list); + + if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) + up_write(&block_group->data_rwsem); + goto out; } @@ -1165,6 +1219,12 @@ int btrfs_write_out_cache(struct btrfs_root *root, spin_unlock(&block_group->lock); return 0; } + + if (block_group->delalloc_bytes) { + block_group->disk_cache_state = BTRFS_DC_WRITTEN; + spin_unlock(&block_group->lock); + return 0; + } spin_unlock(&block_group->lock); inode = lookup_free_space_inode(root, block_group, path); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7fa5f7fd7bc..3668048e16f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -693,7 +693,7 @@ retry: ret = btrfs_reserve_extent(root, async_extent->compressed_size, async_extent->compressed_size, - 0, alloc_hint, &ins, 1); + 0, alloc_hint, &ins, 1, 1); if (ret) { int i; @@ -794,7 +794,7 @@ retry: out: return ret; out_free_reserve: - btrfs_free_reserved_extent(root, ins.objectid, ins.offset); + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_free: extent_clear_unlock_delalloc(inode, async_extent->start, async_extent->start + @@ -917,7 +917,7 @@ static noinline int cow_file_range(struct inode *inode, cur_alloc_size = disk_num_bytes; ret = btrfs_reserve_extent(root, cur_alloc_size, root->sectorsize, 0, alloc_hint, - &ins, 1); + &ins, 1, 1); if (ret < 0) goto out_unlock; @@ -995,7 +995,7 @@ out: return ret; out_reserve: - btrfs_free_reserved_extent(root, ins.objectid, ins.offset); + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_unlock: extent_clear_unlock_delalloc(inode, start, end, locked_page, EXTENT_LOCKED | EXTENT_DO_ACCOUNTING | @@ -2599,6 +2599,21 @@ out_kfree: return NULL; } +static void btrfs_release_delalloc_bytes(struct btrfs_root *root, + u64 start, u64 len) +{ + struct btrfs_block_group_cache *cache; + + cache = btrfs_lookup_block_group(root->fs_info, start); + ASSERT(cache); + + spin_lock(&cache->lock); + cache->delalloc_bytes -= len; + spin_unlock(&cache->lock); + + btrfs_put_block_group(cache); +} + /* as ordered data IO finishes, this gets called so we can finish * an ordered extent if the range of bytes in the file it covers are * fully written. @@ -2698,6 +2713,10 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) logical_len, logical_len, compress_type, 0, 0, BTRFS_FILE_EXTENT_REG); + if (!ret) + btrfs_release_delalloc_bytes(root, + ordered_extent->start, + ordered_extent->disk_len); } unpin_extent_cache(&BTRFS_I(inode)->extent_tree, ordered_extent->file_offset, ordered_extent->len, @@ -2750,7 +2769,7 @@ out: !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) && !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) btrfs_free_reserved_extent(root, ordered_extent->start, - ordered_extent->disk_len); + ordered_extent->disk_len, 1); } @@ -6535,21 +6554,21 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, alloc_hint = get_extent_allocation_hint(inode, start, len); ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, - alloc_hint, &ins, 1); + alloc_hint, &ins, 1, 1); if (ret) return ERR_PTR(ret); em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, ins.offset, ins.offset, ins.offset, 0); if (IS_ERR(em)) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset); + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); return em; } ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, ins.offset, ins.offset, 0); if (ret) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset); + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); free_extent_map(em); return ERR_PTR(ret); } @@ -7437,7 +7456,7 @@ free_ordered: if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) && !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) btrfs_free_reserved_extent(root, ordered->start, - ordered->disk_len); + ordered->disk_len, 1); btrfs_put_ordered_extent(ordered); btrfs_put_ordered_extent(ordered); } @@ -7445,39 +7464,30 @@ free_ordered: } static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + const struct iov_iter *iter, loff_t offset) { int seg; int i; - size_t size; - unsigned long addr; unsigned blocksize_mask = root->sectorsize - 1; ssize_t retval = -EINVAL; - loff_t end = offset; if (offset & blocksize_mask) goto out; - /* Check the memory alignment. Blocks cannot straddle pages */ - for (seg = 0; seg < nr_segs; seg++) { - addr = (unsigned long)iov[seg].iov_base; - size = iov[seg].iov_len; - end += size; - if ((addr & blocksize_mask) || (size & blocksize_mask)) - goto out; - - /* If this is a write we don't need to check anymore */ - if (rw & WRITE) - continue; + if (iov_iter_alignment(iter) & blocksize_mask) + goto out; - /* - * Check to make sure we don't have duplicate iov_base's in this - * iovec, if so return EINVAL, otherwise we'll get csum errors - * when reading back. - */ - for (i = seg + 1; i < nr_segs; i++) { - if (iov[seg].iov_base == iov[i].iov_base) + /* If this is a write we don't need to check anymore */ + if (rw & WRITE) + return 0; + /* + * Check to make sure we don't have duplicate iov_base's in this + * iovec, if so return EINVAL, otherwise we'll get csum errors + * when reading back. + */ + for (seg = 0; seg < iter->nr_segs; seg++) { + for (i = seg + 1; i < iter->nr_segs; i++) { + if (iter->iov[seg].iov_base == iter->iov[i].iov_base) goto out; } } @@ -7487,8 +7497,7 @@ out: } static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -7498,8 +7507,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, bool relock = false; ssize_t ret; - if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov, - offset, nr_segs)) + if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iter, offset)) return 0; atomic_inc(&inode->i_dio_count); @@ -7511,7 +7519,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, * we need to flush the dirty pages again to make absolutely sure * that any outstanding dirty pages are on disk. */ - count = iov_length(iov, nr_segs); + count = iov_iter_count(iter); if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &BTRFS_I(inode)->runtime_flags)) filemap_fdatawrite_range(inode->i_mapping, offset, count); @@ -7538,7 +7546,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, ret = __blockdev_direct_IO(rw, iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, - iov, offset, nr_segs, btrfs_get_blocks_direct, NULL, + iter, offset, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (rw & WRITE) { if (ret < 0 && ret != -EIOCBQUEUED) @@ -8819,7 +8827,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, cur_bytes = min(num_bytes, 256ULL * 1024 * 1024); cur_bytes = max(cur_bytes, min_size); ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, - *alloc_hint, &ins, 1); + *alloc_hint, &ins, 1, 0); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); @@ -8833,7 +8841,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, BTRFS_FILE_EXTENT_PREALLOC); if (ret) { btrfs_free_reserved_extent(root, ins.objectid, - ins.offset); + ins.offset, 0); btrfs_abort_transaction(trans, root, ret); if (own_trans) btrfs_end_transaction(trans, root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 82c18ba12e3..47aceb494d1 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -136,19 +136,22 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags) void btrfs_update_iflags(struct inode *inode) { struct btrfs_inode *ip = BTRFS_I(inode); - - inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC); + unsigned int new_fl = 0; if (ip->flags & BTRFS_INODE_SYNC) - inode->i_flags |= S_SYNC; + new_fl |= S_SYNC; if (ip->flags & BTRFS_INODE_IMMUTABLE) - inode->i_flags |= S_IMMUTABLE; + new_fl |= S_IMMUTABLE; if (ip->flags & BTRFS_INODE_APPEND) - inode->i_flags |= S_APPEND; + new_fl |= S_APPEND; if (ip->flags & BTRFS_INODE_NOATIME) - inode->i_flags |= S_NOATIME; + new_fl |= S_NOATIME; if (ip->flags & BTRFS_INODE_DIRSYNC) - inode->i_flags |= S_DIRSYNC; + new_fl |= S_DIRSYNC; + + set_mask_bits(&inode->i_flags, + S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC, + new_fl); } /* @@ -1957,7 +1960,8 @@ static noinline int copy_to_sk(struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *key, struct btrfs_ioctl_search_key *sk, - char *buf, + size_t *buf_size, + char __user *ubuf, unsigned long *sk_offset, int *num_found) { @@ -1989,13 +1993,25 @@ static noinline int copy_to_sk(struct btrfs_root *root, if (!key_in_sk(key, sk)) continue; - if (sizeof(sh) + item_len > BTRFS_SEARCH_ARGS_BUFSIZE) + if (sizeof(sh) + item_len > *buf_size) { + if (*num_found) { + ret = 1; + goto out; + } + + /* + * return one empty item back for v1, which does not + * handle -EOVERFLOW + */ + + *buf_size = sizeof(sh) + item_len; item_len = 0; + ret = -EOVERFLOW; + } - if (sizeof(sh) + item_len + *sk_offset > - BTRFS_SEARCH_ARGS_BUFSIZE) { + if (sizeof(sh) + item_len + *sk_offset > *buf_size) { ret = 1; - goto overflow; + goto out; } sh.objectid = key->objectid; @@ -2005,20 +2021,33 @@ static noinline int copy_to_sk(struct btrfs_root *root, sh.transid = found_transid; /* copy search result header */ - memcpy(buf + *sk_offset, &sh, sizeof(sh)); + if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { + ret = -EFAULT; + goto out; + } + *sk_offset += sizeof(sh); if (item_len) { - char *p = buf + *sk_offset; + char __user *up = ubuf + *sk_offset; /* copy the item */ - read_extent_buffer(leaf, p, - item_off, item_len); + if (read_extent_buffer_to_user(leaf, up, + item_off, item_len)) { + ret = -EFAULT; + goto out; + } + *sk_offset += item_len; } (*num_found)++; - if (*num_found >= sk->nr_items) - break; + if (ret) /* -EOVERFLOW from above */ + goto out; + + if (*num_found >= sk->nr_items) { + ret = 1; + goto out; + } } advance_key: ret = 0; @@ -2033,22 +2062,37 @@ advance_key: key->objectid++; } else ret = 1; -overflow: +out: + /* + * 0: all items from this leaf copied, continue with next + * 1: * more items can be copied, but unused buffer is too small + * * all items were found + * Either way, it will stops the loop which iterates to the next + * leaf + * -EOVERFLOW: item was to large for buffer + * -EFAULT: could not copy extent buffer back to userspace + */ return ret; } static noinline int search_ioctl(struct inode *inode, - struct btrfs_ioctl_search_args *args) + struct btrfs_ioctl_search_key *sk, + size_t *buf_size, + char __user *ubuf) { struct btrfs_root *root; struct btrfs_key key; struct btrfs_path *path; - struct btrfs_ioctl_search_key *sk = &args->key; struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info; int ret; int num_found = 0; unsigned long sk_offset = 0; + if (*buf_size < sizeof(struct btrfs_ioctl_search_header)) { + *buf_size = sizeof(struct btrfs_ioctl_search_header); + return -EOVERFLOW; + } + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -2082,14 +2126,15 @@ static noinline int search_ioctl(struct inode *inode, ret = 0; goto err; } - ret = copy_to_sk(root, path, &key, sk, args->buf, + ret = copy_to_sk(root, path, &key, sk, buf_size, ubuf, &sk_offset, &num_found); btrfs_release_path(path); - if (ret || num_found >= sk->nr_items) + if (ret) break; } - ret = 0; + if (ret > 0) + ret = 0; err: sk->nr_items = num_found; btrfs_free_path(path); @@ -2099,22 +2144,73 @@ err: static noinline int btrfs_ioctl_tree_search(struct file *file, void __user *argp) { - struct btrfs_ioctl_search_args *args; - struct inode *inode; - int ret; + struct btrfs_ioctl_search_args __user *uargs; + struct btrfs_ioctl_search_key sk; + struct inode *inode; + int ret; + size_t buf_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - args = memdup_user(argp, sizeof(*args)); - if (IS_ERR(args)) - return PTR_ERR(args); + uargs = (struct btrfs_ioctl_search_args __user *)argp; + + if (copy_from_user(&sk, &uargs->key, sizeof(sk))) + return -EFAULT; + + buf_size = sizeof(uargs->buf); inode = file_inode(file); - ret = search_ioctl(inode, args); - if (ret == 0 && copy_to_user(argp, args, sizeof(*args))) + ret = search_ioctl(inode, &sk, &buf_size, uargs->buf); + + /* + * In the origin implementation an overflow is handled by returning a + * search header with a len of zero, so reset ret. + */ + if (ret == -EOVERFLOW) + ret = 0; + + if (ret == 0 && copy_to_user(&uargs->key, &sk, sizeof(sk))) ret = -EFAULT; - kfree(args); + return ret; +} + +static noinline int btrfs_ioctl_tree_search_v2(struct file *file, + void __user *argp) +{ + struct btrfs_ioctl_search_args_v2 __user *uarg; + struct btrfs_ioctl_search_args_v2 args; + struct inode *inode; + int ret; + size_t buf_size; + const size_t buf_limit = 16 * 1024 * 1024; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* copy search header and buffer size */ + uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp; + if (copy_from_user(&args, uarg, sizeof(args))) + return -EFAULT; + + buf_size = args.buf_size; + + if (buf_size < sizeof(struct btrfs_ioctl_search_header)) + return -EOVERFLOW; + + /* limit result size to 16MB */ + if (buf_size > buf_limit) + buf_size = buf_limit; + + inode = file_inode(file); + ret = search_ioctl(inode, &args.key, &buf_size, + (char *)(&uarg->buf[0])); + if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key))) + ret = -EFAULT; + else if (ret == -EOVERFLOW && + copy_to_user(&uarg->buf_size, &buf_size, sizeof(buf_size))) + ret = -EFAULT; + return ret; } @@ -3046,7 +3142,6 @@ out: static void clone_update_extent_map(struct inode *inode, const struct btrfs_trans_handle *trans, const struct btrfs_path *path, - struct btrfs_file_extent_item *fi, const u64 hole_offset, const u64 hole_len) { @@ -3061,7 +3156,11 @@ static void clone_update_extent_map(struct inode *inode, return; } - if (fi) { + if (path) { + struct btrfs_file_extent_item *fi; + + fi = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); btrfs_extent_item_to_extent_map(inode, path, fi, false, em); em->generation = -1; if (btrfs_file_extent_type(path->nodes[0], fi) == @@ -3415,18 +3514,15 @@ process_slot: btrfs_item_ptr_offset(leaf, slot), size); inode_add_bytes(inode, datal); - extent = btrfs_item_ptr(leaf, slot, - struct btrfs_file_extent_item); } /* If we have an implicit hole (NO_HOLES feature). */ if (drop_start < new_key.offset) clone_update_extent_map(inode, trans, - path, NULL, drop_start, + NULL, drop_start, new_key.offset - drop_start); - clone_update_extent_map(inode, trans, path, - extent, 0, 0); + clone_update_extent_map(inode, trans, path, 0, 0); btrfs_mark_buffer_dirty(leaf); btrfs_release_path(path); @@ -3469,12 +3565,10 @@ process_slot: btrfs_end_transaction(trans, root); goto out; } + clone_update_extent_map(inode, trans, NULL, last_dest_end, + destoff + len - last_dest_end); ret = clone_finish_inode_update(trans, inode, destoff + len, destoff, olen); - if (ret) - goto out; - clone_update_extent_map(inode, trans, path, NULL, last_dest_end, - destoff + len - last_dest_end); } out: @@ -5198,6 +5292,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_trans_end(file); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(file, argp); + case BTRFS_IOC_TREE_SEARCH_V2: + return btrfs_ioctl_tree_search_v2(file, argp); case BTRFS_IOC_INO_LOOKUP: return btrfs_ioctl_ino_lookup(file, argp); case BTRFS_IOC_INO_PATHS: diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 01277b8f237..5665d214924 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -33,14 +33,14 @@ static void btrfs_assert_tree_read_locked(struct extent_buffer *eb); */ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw) { - if (eb->lock_nested) { - read_lock(&eb->lock); - if (eb->lock_nested && current->pid == eb->lock_owner) { - read_unlock(&eb->lock); - return; - } - read_unlock(&eb->lock); - } + /* + * no lock is required. The lock owner may change if + * we have a read lock, but it won't change to or away + * from us. If we have the write lock, we are the owner + * and it'll never change. + */ + if (eb->lock_nested && current->pid == eb->lock_owner) + return; if (rw == BTRFS_WRITE_LOCK) { if (atomic_read(&eb->blocking_writers) == 0) { WARN_ON(atomic_read(&eb->spinning_writers) != 1); @@ -65,14 +65,15 @@ void btrfs_set_lock_blocking_rw(struct extent_buffer *eb, int rw) */ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) { - if (eb->lock_nested) { - read_lock(&eb->lock); - if (eb->lock_nested && current->pid == eb->lock_owner) { - read_unlock(&eb->lock); - return; - } - read_unlock(&eb->lock); - } + /* + * no lock is required. The lock owner may change if + * we have a read lock, but it won't change to or away + * from us. If we have the write lock, we are the owner + * and it'll never change. + */ + if (eb->lock_nested && current->pid == eb->lock_owner) + return; + if (rw == BTRFS_WRITE_LOCK_BLOCKING) { BUG_ON(atomic_read(&eb->blocking_writers) != 1); write_lock(&eb->lock); @@ -99,6 +100,9 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) void btrfs_tree_read_lock(struct extent_buffer *eb) { again: + BUG_ON(!atomic_read(&eb->blocking_writers) && + current->pid == eb->lock_owner); + read_lock(&eb->lock); if (atomic_read(&eb->blocking_writers) && current->pid == eb->lock_owner) { @@ -132,7 +136,9 @@ int btrfs_try_tree_read_lock(struct extent_buffer *eb) if (atomic_read(&eb->blocking_writers)) return 0; - read_lock(&eb->lock); + if (!read_trylock(&eb->lock)) + return 0; + if (atomic_read(&eb->blocking_writers)) { read_unlock(&eb->lock); return 0; @@ -151,7 +157,10 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) if (atomic_read(&eb->blocking_writers) || atomic_read(&eb->blocking_readers)) return 0; - write_lock(&eb->lock); + + if (!write_trylock(&eb->lock)) + return 0; + if (atomic_read(&eb->blocking_writers) || atomic_read(&eb->blocking_readers)) { write_unlock(&eb->lock); @@ -168,14 +177,15 @@ int btrfs_try_tree_write_lock(struct extent_buffer *eb) */ void btrfs_tree_read_unlock(struct extent_buffer *eb) { - if (eb->lock_nested) { - read_lock(&eb->lock); - if (eb->lock_nested && current->pid == eb->lock_owner) { - eb->lock_nested = 0; - read_unlock(&eb->lock); - return; - } - read_unlock(&eb->lock); + /* + * if we're nested, we have the write lock. No new locking + * is needed as long as we are the lock owner. + * The write unlock will do a barrier for us, and the lock_nested + * field only matters to the lock owner. + */ + if (eb->lock_nested && current->pid == eb->lock_owner) { + eb->lock_nested = 0; + return; } btrfs_assert_tree_read_locked(eb); WARN_ON(atomic_read(&eb->spinning_readers) == 0); @@ -189,14 +199,15 @@ void btrfs_tree_read_unlock(struct extent_buffer *eb) */ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) { - if (eb->lock_nested) { - read_lock(&eb->lock); - if (eb->lock_nested && current->pid == eb->lock_owner) { - eb->lock_nested = 0; - read_unlock(&eb->lock); - return; - } - read_unlock(&eb->lock); + /* + * if we're nested, we have the write lock. No new locking + * is needed as long as we are the lock owner. + * The write unlock will do a barrier for us, and the lock_nested + * field only matters to the lock owner. + */ + if (eb->lock_nested && current->pid == eb->lock_owner) { + eb->lock_nested = 0; + return; } btrfs_assert_tree_read_locked(eb); WARN_ON(atomic_read(&eb->blocking_readers) == 0); @@ -244,6 +255,7 @@ void btrfs_tree_unlock(struct extent_buffer *eb) BUG_ON(blockers > 1); btrfs_assert_tree_locked(eb); + eb->lock_owner = 0; atomic_dec(&eb->write_locks); if (blockers) { diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e12441c7cf1..7187b14faa6 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -484,8 +484,19 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid) log_list); list_del_init(&ordered->log_list); spin_unlock_irq(&log->log_extents_lock[index]); + + if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) && + !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + struct inode *inode = ordered->inode; + u64 start = ordered->file_offset; + u64 end = ordered->file_offset + ordered->len - 1; + + WARN_ON(!inode); + filemap_fdatawrite_range(inode->i_mapping, start, end); + } wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)); + btrfs_put_ordered_extent(ordered); spin_lock_irq(&log->log_extents_lock[index]); } diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index 6efd70d3b64..9626b4ad3b9 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -54,7 +54,7 @@ static void print_extent_data_ref(struct extent_buffer *eb, btrfs_extent_data_ref_count(eb, ref)); } -static void print_extent_item(struct extent_buffer *eb, int slot) +static void print_extent_item(struct extent_buffer *eb, int slot, int type) { struct btrfs_extent_item *ei; struct btrfs_extent_inline_ref *iref; @@ -63,7 +63,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot) struct btrfs_disk_key key; unsigned long end; unsigned long ptr; - int type; u32 item_size = btrfs_item_size_nr(eb, slot); u64 flags; u64 offset; @@ -88,7 +87,8 @@ static void print_extent_item(struct extent_buffer *eb, int slot) btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei), flags); - if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { + if ((type == BTRFS_EXTENT_ITEM_KEY) && + flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)(ei + 1); btrfs_tree_block_key(eb, info, &key); @@ -223,7 +223,8 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l) btrfs_disk_root_refs(l, ri)); break; case BTRFS_EXTENT_ITEM_KEY: - print_extent_item(l, i); + case BTRFS_METADATA_ITEM_KEY: + print_extent_item(l, i, type); break; case BTRFS_TREE_BLOCK_REF_KEY: printk(KERN_INFO "\t\ttree block backref\n"); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index cf5aead95a7..98cb6b2630f 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1798,8 +1798,10 @@ static int qgroup_shared_accounting(struct btrfs_trans_handle *trans, return -ENOMEM; tmp = ulist_alloc(GFP_NOFS); - if (!tmp) + if (!tmp) { + ulist_free(qgroups); return -ENOMEM; + } btrfs_get_tree_mod_seq(fs_info, &elem); ret = btrfs_find_all_roots(trans, fs_info, oper->bytenr, elem.seq, diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 4055291a523..4a88f073fdd 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1956,9 +1956,10 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) * pages are going to be uptodate. */ for (stripe = 0; stripe < bbio->num_stripes; stripe++) { - if (rbio->faila == stripe || - rbio->failb == stripe) + if (rbio->faila == stripe || rbio->failb == stripe) { + atomic_inc(&rbio->bbio->error); continue; + } for (pagenr = 0; pagenr < nr_pages; pagenr++) { struct page *p; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 30947f92362..09230cf3a24 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -428,8 +428,13 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root, continue; } if (!dev->bdev) { - /* cannot read ahead on missing device */ - continue; + /* + * cannot read ahead on missing device, but for RAID5/6, + * REQ_GET_READ_MIRRORS return 1. So don't skip missing + * device for such case. + */ + if (nzones > 1) + continue; } if (dev_replace_is_ongoing && dev == fs_info->dev_replace.tgtdev) { diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index ac80188eec8..b6d198f5181 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2725,11 +2725,8 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent); length = btrfs_dev_extent_length(l, dev_extent); - if (found_key.offset + length <= start) { - key.offset = found_key.offset + length; - btrfs_release_path(path); - continue; - } + if (found_key.offset + length <= start) + goto skip; chunk_tree = btrfs_dev_extent_chunk_tree(l, dev_extent); chunk_objectid = btrfs_dev_extent_chunk_objectid(l, dev_extent); @@ -2740,10 +2737,12 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, * the chunk from going away while we scrub it */ cache = btrfs_lookup_block_group(fs_info, chunk_offset); - if (!cache) { - ret = -ENOENT; - break; - } + + /* some chunks are removed but not committed to disk yet, + * continue scrubbing */ + if (!cache) + goto skip; + dev_replace->cursor_right = found_key.offset + length; dev_replace->cursor_left = found_key.offset; dev_replace->item_needs_writeback = 1; @@ -2802,7 +2801,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx, dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; - +skip: key.offset = found_key.offset + length; btrfs_release_path(path); } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 4662d92a4b7..8e16bca69c5 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -522,9 +522,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) case Opt_ssd_spread: btrfs_set_and_info(root, SSD_SPREAD, "use spread ssd allocation scheme"); + btrfs_set_opt(info->mount_opt, SSD); break; case Opt_nossd: - btrfs_clear_and_info(root, NOSSD, + btrfs_set_and_info(root, NOSSD, "not using ssd allocation scheme"); btrfs_clear_opt(info->mount_opt, SSD); break; @@ -1467,7 +1468,9 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; /* recover relocation */ + mutex_lock(&fs_info->cleaner_mutex); ret = btrfs_recover_relocation(root); + mutex_unlock(&fs_info->cleaner_mutex); if (ret) goto restore; @@ -1808,6 +1811,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) list_for_each_entry(dev, head, dev_list) { if (dev->missing) continue; + if (!dev->name) + continue; if (!first_dev || dev->devid < first_dev->devid) first_dev = dev; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index df39458f148..78699364f53 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -605,14 +605,37 @@ static void init_feature_attrs(void) } } -static int add_device_membership(struct btrfs_fs_info *fs_info) +int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *one_device) +{ + struct hd_struct *disk; + struct kobject *disk_kobj; + + if (!fs_info->device_dir_kobj) + return -EINVAL; + + if (one_device) { + disk = one_device->bdev->bd_part; + disk_kobj = &part_to_dev(disk)->kobj; + + sysfs_remove_link(fs_info->device_dir_kobj, + disk_kobj->name); + } + + return 0; +} + +int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *one_device) { int error = 0; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; struct btrfs_device *dev; - fs_info->device_dir_kobj = kobject_create_and_add("devices", + if (!fs_info->device_dir_kobj) + fs_info->device_dir_kobj = kobject_create_and_add("devices", &fs_info->super_kobj); + if (!fs_info->device_dir_kobj) return -ENOMEM; @@ -623,6 +646,9 @@ static int add_device_membership(struct btrfs_fs_info *fs_info) if (!dev->bdev) continue; + if (one_device && one_device != dev) + continue; + disk = dev->bdev->bd_part; disk_kobj = &part_to_dev(disk)->kobj; @@ -666,7 +692,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info) if (error) goto failure; - error = add_device_membership(fs_info); + error = btrfs_kobj_add_device(fs_info, NULL); if (error) goto failure; diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 9ab576318a8..ac46df37504 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -66,4 +66,8 @@ char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags); extern const char * const btrfs_feature_set_names[3]; extern struct kobj_type space_info_ktype; extern struct kobj_type btrfs_raid_ktype; +int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *one_device); +int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info, + struct btrfs_device *one_device); #endif /* _BTRFS_SYSFS_H_ */ diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index a5dcacb5df9..9626252ee6b 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -135,7 +135,7 @@ restart: radix_tree_for_each_slot(slot, &fs_info->buffer_radix, &iter, 0) { struct extent_buffer *eb; - eb = radix_tree_deref_slot(slot); + eb = radix_tree_deref_slot_protected(slot, &fs_info->buffer_lock); if (!eb) continue; /* Shouldn't happen but that kind of thinking creates CVE's */ diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index fa691b754aa..ec3dcb20235 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -415,6 +415,8 @@ int btrfs_test_qgroups(void) ret = -ENOMEM; goto out; } + btrfs_set_header_level(root->node, 0); + btrfs_set_header_nritems(root->node, 0); root->alloc_bytenr += 8192; tmp_root = btrfs_alloc_dummy_root(); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9630f10f8e1..5f379affdf2 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -386,11 +386,13 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, bool reloc_reserved = false; int ret; + /* Send isn't supposed to start transactions. */ + ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB); + if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) return ERR_PTR(-EROFS); - if (current->journal_info && - current->journal_info != (void *)BTRFS_SEND_TRANS_STUB) { + if (current->journal_info) { WARN_ON(type & TRANS_EXTWRITERS); h = current->journal_info; h->use_count++; @@ -491,6 +493,7 @@ again: smp_mb(); if (cur_trans->state >= TRANS_STATE_BLOCKED && may_wait_transaction(root, type)) { + current->journal_info = h; btrfs_commit_transaction(h, root); goto again; } @@ -1284,11 +1287,13 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, goto fail; } - pending->error = btrfs_qgroup_inherit(trans, fs_info, - root->root_key.objectid, - objectid, pending->inherit); - if (pending->error) - goto no_free_objectid; + ret = btrfs_qgroup_inherit(trans, fs_info, + root->root_key.objectid, + objectid, pending->inherit); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + goto fail; + } /* see comments in should_cow_block() */ set_bit(BTRFS_ROOT_FORCE_COW, &root->state); @@ -1613,11 +1618,6 @@ static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans, int ret; ret = btrfs_run_delayed_items(trans, root); - /* - * running the delayed items may have added new refs. account - * them now so that they hinder processing of more delayed refs - * as little as possible. - */ if (ret) return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ffeed6d6326..6cb82f62cb7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -40,6 +40,7 @@ #include "rcu-string.h" #include "math.h" #include "dev-replace.h" +#include "sysfs.h" static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -554,12 +555,14 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) * This is ok to do without rcu read locked because we hold the * uuid mutex so nothing we touch in here is going to disappear. */ - name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS); - if (!name) { - kfree(device); - goto error; + if (orig_dev->name) { + name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS); + if (!name) { + kfree(device); + goto error; + } + rcu_assign_pointer(device->name, name); } - rcu_assign_pointer(device->name, name); list_add(&device->dev_list, &fs_devices->devices); device->fs_devices = fs_devices; @@ -1677,8 +1680,11 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) if (device->bdev == root->fs_info->fs_devices->latest_bdev) root->fs_info->fs_devices->latest_bdev = next_device->bdev; - if (device->bdev) + if (device->bdev) { device->fs_devices->open_devices--; + /* remove sysfs entry */ + btrfs_kobj_rm_device(root->fs_info, device); + } call_rcu(&device->rcu, free_device); @@ -2143,9 +2149,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) total_bytes = btrfs_super_num_devices(root->fs_info->super_copy); btrfs_set_super_num_devices(root->fs_info->super_copy, total_bytes + 1); + + /* add sysfs device entry */ + btrfs_kobj_add_device(root->fs_info, device); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); if (seeding_dev) { + char fsid_buf[BTRFS_UUID_UNPARSED_SIZE]; ret = init_first_rw_device(trans, root, device); if (ret) { btrfs_abort_transaction(trans, root, ret); @@ -2156,6 +2167,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) btrfs_abort_transaction(trans, root, ret); goto error_trans; } + + /* Sprouting would change fsid of the mounted root, + * so rename the fsid on the sysfs + */ + snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU", + root->fs_info->fsid); + if (kobject_rename(&root->fs_info->super_kobj, fsid_buf)) + goto error_trans; } else { ret = btrfs_add_device(trans, root, device); if (ret) { @@ -2205,6 +2224,7 @@ error_trans: unlock_chunks(root); btrfs_end_transaction(trans, root); rcu_string_free(device->name); + btrfs_kobj_rm_device(root->fs_info, device); kfree(device); error: blkdev_put(bdev, FMODE_EXCL); @@ -2543,9 +2563,6 @@ static int btrfs_relocate_chunk(struct btrfs_root *root, remove_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); - kfree(map); - em->bdev = NULL; - /* once for the tree */ free_extent_map(em); /* once for us */ @@ -4301,9 +4318,11 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, em = alloc_extent_map(); if (!em) { + kfree(map); ret = -ENOMEM; goto error; } + set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); em->bdev = (struct block_device *)map; em->start = start; em->len = num_bytes; @@ -4346,7 +4365,6 @@ error_del_extent: /* One for the tree reference */ free_extent_map(em); error: - kfree(map); kfree(devices_info); return ret; } @@ -4558,7 +4576,6 @@ void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree) write_unlock(&tree->map_tree.lock); if (!em) break; - kfree(em->bdev); /* once for us */ free_extent_map(em); /* once for the tree */ @@ -5362,6 +5379,15 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } +static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err) +{ + if (likely(bbio->flags & BTRFS_BIO_ORIG_BIO_SUBMITTED)) + bio_endio_nodec(bio, err); + else + bio_endio(bio, err); + kfree(bbio); +} + static void btrfs_end_bio(struct bio *bio, int err) { struct btrfs_bio *bbio = bio->bi_private; @@ -5402,12 +5428,6 @@ static void btrfs_end_bio(struct bio *bio, int err) bio = bbio->orig_bio; } - /* - * We have original bio now. So increment bi_remaining to - * account for it in endio - */ - atomic_inc(&bio->bi_remaining); - bio->bi_private = bbio->private; bio->bi_end_io = bbio->end_io; btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; @@ -5424,9 +5444,8 @@ static void btrfs_end_bio(struct bio *bio, int err) set_bit(BIO_UPTODATE, &bio->bi_flags); err = 0; } - kfree(bbio); - bio_endio(bio, err); + btrfs_end_bbio(bbio, bio, err); } else if (!is_orig_bio) { bio_put(bio); } @@ -5589,12 +5608,15 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) { atomic_inc(&bbio->error); if (atomic_dec_and_test(&bbio->stripes_pending)) { + /* Shoud be the original bio. */ + WARN_ON(bio != bbio->orig_bio); + bio->bi_private = bbio->private; bio->bi_end_io = bbio->end_io; btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; bio->bi_iter.bi_sector = logical >> 9; - kfree(bbio); - bio_endio(bio, -EIO); + + btrfs_end_bbio(bbio, bio, -EIO); } } @@ -5681,6 +5703,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, BUG_ON(!bio); /* -ENOMEM */ } else { bio = first_bio; + bbio->flags |= BTRFS_BIO_ORIG_BIO_SUBMITTED; } submit_stripe_bio(root, bbio, bio, @@ -5822,6 +5845,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, return -ENOMEM; } + set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags); em->bdev = (struct block_device *)map; em->start = logical; em->len = length; @@ -5846,7 +5870,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, map->stripes[i].dev = btrfs_find_device(root->fs_info, devid, uuid, NULL); if (!map->stripes[i].dev && !btrfs_test_opt(root, DEGRADED)) { - kfree(map); free_extent_map(em); return -EIO; } @@ -5854,7 +5877,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, map->stripes[i].dev = add_missing_dev(root, devid, uuid); if (!map->stripes[i].dev) { - kfree(map); free_extent_map(em); return -EIO; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 1a15bbeb65e..2aaa00c4781 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -190,11 +190,14 @@ struct btrfs_bio_stripe { struct btrfs_bio; typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err); +#define BTRFS_BIO_ORIG_BIO_SUBMITTED 0x1 + struct btrfs_bio { atomic_t stripes_pending; struct btrfs_fs_info *fs_info; bio_end_io_t *end_io; struct bio *orig_bio; + unsigned long flags; void *private; atomic_t error; int max_errors; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 4f196314c0c..b67d8fc8127 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -136,7 +136,7 @@ static int zlib_compress_pages(struct list_head *ws, if (workspace->def_strm.total_in > 8192 && workspace->def_strm.total_in < workspace->def_strm.total_out) { - ret = -EIO; + ret = -E2BIG; goto out; } /* we need another page for writing out. Test this diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c index 21887d63dad..469f2e8657e 100644 --- a/fs/ceph/acl.c +++ b/fs/ceph/acl.c @@ -104,12 +104,6 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type) umode_t new_mode = inode->i_mode, old_mode = inode->i_mode; struct dentry *dentry; - if (acl) { - ret = posix_acl_valid(acl); - if (ret < 0) - goto out; - } - switch (type) { case ACL_TYPE_ACCESS: name = POSIX_ACL_XATTR_ACCESS; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 65a30e817dd..90b3954d48e 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -211,18 +211,15 @@ static int readpage_nounlock(struct file *filp, struct page *page) SetPageError(page); ceph_fscache_readpage_cancel(inode, page); goto out; - } else { - if (err < PAGE_CACHE_SIZE) { - /* zero fill remainder of page */ - zero_user_segment(page, err, PAGE_CACHE_SIZE); - } else { - flush_dcache_page(page); - } } - SetPageUptodate(page); + if (err < PAGE_CACHE_SIZE) + /* zero fill remainder of page */ + zero_user_segment(page, err, PAGE_CACHE_SIZE); + else + flush_dcache_page(page); - if (err >= 0) - ceph_readpage_to_fscache(inode, page); + SetPageUptodate(page); + ceph_readpage_to_fscache(inode, page); out: return err < 0 ? err : 0; @@ -1187,8 +1184,8 @@ static int ceph_write_end(struct file *file, struct address_space *mapping, * never get called. */ static ssize_t ceph_direct_io(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t pos, unsigned long nr_segs) + struct iov_iter *iter, + loff_t pos) { WARN_ON(1); return -EINVAL; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index c561b628ebc..1fde164b74b 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -221,8 +221,8 @@ int ceph_unreserve_caps(struct ceph_mds_client *mdsc, return 0; } -static struct ceph_cap *get_cap(struct ceph_mds_client *mdsc, - struct ceph_cap_reservation *ctx) +struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc, + struct ceph_cap_reservation *ctx) { struct ceph_cap *cap = NULL; @@ -508,15 +508,14 @@ static void __check_cap_issue(struct ceph_inode_info *ci, struct ceph_cap *cap, * it is < 0. (This is so we can atomically add the cap and add an * open file reference to it.) */ -int ceph_add_cap(struct inode *inode, - struct ceph_mds_session *session, u64 cap_id, - int fmode, unsigned issued, unsigned wanted, - unsigned seq, unsigned mseq, u64 realmino, int flags, - struct ceph_cap_reservation *caps_reservation) +void ceph_add_cap(struct inode *inode, + struct ceph_mds_session *session, u64 cap_id, + int fmode, unsigned issued, unsigned wanted, + unsigned seq, unsigned mseq, u64 realmino, int flags, + struct ceph_cap **new_cap) { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_cap *new_cap = NULL; struct ceph_cap *cap; int mds = session->s_mds; int actual_wanted; @@ -531,20 +530,10 @@ int ceph_add_cap(struct inode *inode, if (fmode >= 0) wanted |= ceph_caps_for_mode(fmode); -retry: - spin_lock(&ci->i_ceph_lock); cap = __get_cap_for_mds(ci, mds); if (!cap) { - if (new_cap) { - cap = new_cap; - new_cap = NULL; - } else { - spin_unlock(&ci->i_ceph_lock); - new_cap = get_cap(mdsc, caps_reservation); - if (new_cap == NULL) - return -ENOMEM; - goto retry; - } + cap = *new_cap; + *new_cap = NULL; cap->issued = 0; cap->implemented = 0; @@ -562,9 +551,6 @@ retry: session->s_nr_caps++; spin_unlock(&session->s_cap_lock); } else { - if (new_cap) - ceph_put_cap(mdsc, new_cap); - /* * auth mds of the inode changed. we received the cap export * message, but still haven't received the cap import message. @@ -626,7 +612,6 @@ retry: ci->i_auth_cap = cap; cap->mds_wanted = wanted; } - ci->i_cap_exporting_issued = 0; } else { WARN_ON(ci->i_auth_cap == cap); } @@ -648,9 +633,6 @@ retry: if (fmode >= 0) __ceph_get_fmode(ci, fmode); - spin_unlock(&ci->i_ceph_lock); - wake_up_all(&ci->i_cap_wq); - return 0; } /* @@ -685,7 +667,7 @@ static int __cap_is_valid(struct ceph_cap *cap) */ int __ceph_caps_issued(struct ceph_inode_info *ci, int *implemented) { - int have = ci->i_snap_caps | ci->i_cap_exporting_issued; + int have = ci->i_snap_caps; struct ceph_cap *cap; struct rb_node *p; @@ -900,7 +882,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci) */ static int __ceph_is_any_caps(struct ceph_inode_info *ci) { - return !RB_EMPTY_ROOT(&ci->i_caps) || ci->i_cap_exporting_issued; + return !RB_EMPTY_ROOT(&ci->i_caps); } int ceph_is_any_caps(struct inode *inode) @@ -2397,32 +2379,30 @@ static void invalidate_aliases(struct inode *inode) * actually be a revocation if it specifies a smaller cap set.) * * caller holds s_mutex and i_ceph_lock, we drop both. - * - * return value: - * 0 - ok - * 1 - check_caps on auth cap only (writeback) - * 2 - check_caps (ack revoke) */ -static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, +static void handle_cap_grant(struct ceph_mds_client *mdsc, + struct inode *inode, struct ceph_mds_caps *grant, + void *snaptrace, int snaptrace_len, + struct ceph_buffer *xattr_buf, struct ceph_mds_session *session, - struct ceph_cap *cap, - struct ceph_buffer *xattr_buf) - __releases(ci->i_ceph_lock) + struct ceph_cap *cap, int issued) + __releases(ci->i_ceph_lock) { struct ceph_inode_info *ci = ceph_inode(inode); int mds = session->s_mds; int seq = le32_to_cpu(grant->seq); int newcaps = le32_to_cpu(grant->caps); - int issued, implemented, used, wanted, dirty; + int used, wanted, dirty; u64 size = le64_to_cpu(grant->size); u64 max_size = le64_to_cpu(grant->max_size); struct timespec mtime, atime, ctime; int check_caps = 0; - int wake = 0; - int writeback = 0; - int queue_invalidate = 0; - int deleted_inode = 0; - int queue_revalidate = 0; + bool wake = 0; + bool writeback = 0; + bool queue_trunc = 0; + bool queue_invalidate = 0; + bool queue_revalidate = 0; + bool deleted_inode = 0; dout("handle_cap_grant inode %p cap %p mds%d seq %d %s\n", inode, cap, mds, seq, ceph_cap_string(newcaps)); @@ -2466,16 +2446,13 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, } /* side effects now are allowed */ - - issued = __ceph_caps_issued(ci, &implemented); - issued |= implemented | __ceph_caps_dirty(ci); - cap->cap_gen = session->s_cap_gen; cap->seq = seq; __check_cap_issue(ci, cap, newcaps); - if ((issued & CEPH_CAP_AUTH_EXCL) == 0) { + if ((newcaps & CEPH_CAP_AUTH_SHARED) && + (issued & CEPH_CAP_AUTH_EXCL) == 0) { inode->i_mode = le32_to_cpu(grant->mode); inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(grant->uid)); inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(grant->gid)); @@ -2484,7 +2461,8 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, from_kgid(&init_user_ns, inode->i_gid)); } - if ((issued & CEPH_CAP_LINK_EXCL) == 0) { + if ((newcaps & CEPH_CAP_AUTH_SHARED) && + (issued & CEPH_CAP_LINK_EXCL) == 0) { set_nlink(inode, le32_to_cpu(grant->nlink)); if (inode->i_nlink == 0 && (newcaps & (CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL))) @@ -2511,30 +2489,35 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, if ((issued & CEPH_CAP_FILE_CACHE) && ci->i_rdcache_gen > 1) queue_revalidate = 1; - /* size/ctime/mtime/atime? */ - ceph_fill_file_size(inode, issued, - le32_to_cpu(grant->truncate_seq), - le64_to_cpu(grant->truncate_size), size); - ceph_decode_timespec(&mtime, &grant->mtime); - ceph_decode_timespec(&atime, &grant->atime); - ceph_decode_timespec(&ctime, &grant->ctime); - ceph_fill_file_time(inode, issued, - le32_to_cpu(grant->time_warp_seq), &ctime, &mtime, - &atime); - - - /* file layout may have changed */ - ci->i_layout = grant->layout; - - /* max size increase? */ - if (ci->i_auth_cap == cap && max_size != ci->i_max_size) { - dout("max_size %lld -> %llu\n", ci->i_max_size, max_size); - ci->i_max_size = max_size; - if (max_size >= ci->i_wanted_max_size) { - ci->i_wanted_max_size = 0; /* reset */ - ci->i_requested_max_size = 0; + if (newcaps & CEPH_CAP_ANY_RD) { + /* ctime/mtime/atime? */ + ceph_decode_timespec(&mtime, &grant->mtime); + ceph_decode_timespec(&atime, &grant->atime); + ceph_decode_timespec(&ctime, &grant->ctime); + ceph_fill_file_time(inode, issued, + le32_to_cpu(grant->time_warp_seq), + &ctime, &mtime, &atime); + } + + if (newcaps & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR)) { + /* file layout may have changed */ + ci->i_layout = grant->layout; + /* size/truncate_seq? */ + queue_trunc = ceph_fill_file_size(inode, issued, + le32_to_cpu(grant->truncate_seq), + le64_to_cpu(grant->truncate_size), + size); + /* max size increase? */ + if (ci->i_auth_cap == cap && max_size != ci->i_max_size) { + dout("max_size %lld -> %llu\n", + ci->i_max_size, max_size); + ci->i_max_size = max_size; + if (max_size >= ci->i_wanted_max_size) { + ci->i_wanted_max_size = 0; /* reset */ + ci->i_requested_max_size = 0; + } + wake = 1; } - wake = 1; } /* check cap bits */ @@ -2595,6 +2578,23 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, spin_unlock(&ci->i_ceph_lock); + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_IMPORT) { + down_write(&mdsc->snap_rwsem); + ceph_update_snap_trace(mdsc, snaptrace, + snaptrace + snaptrace_len, false); + downgrade_write(&mdsc->snap_rwsem); + kick_flushing_inode_caps(mdsc, session, inode); + up_read(&mdsc->snap_rwsem); + if (newcaps & ~issued) + wake = 1; + } + + if (queue_trunc) { + ceph_queue_vmtruncate(inode); + ceph_queue_revalidate(inode); + } else if (queue_revalidate) + ceph_queue_revalidate(inode); + if (writeback) /* * queue inode for writeback: we can't actually call @@ -2606,8 +2606,6 @@ static void handle_cap_grant(struct inode *inode, struct ceph_mds_caps *grant, ceph_queue_invalidate(inode); if (deleted_inode) invalidate_aliases(inode); - if (queue_revalidate) - ceph_queue_revalidate(inode); if (wake) wake_up_all(&ci->i_cap_wq); @@ -2784,7 +2782,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, { struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_session *tsession = NULL; - struct ceph_cap *cap, *tcap; + struct ceph_cap *cap, *tcap, *new_cap = NULL; struct ceph_inode_info *ci = ceph_inode(inode); u64 t_cap_id; unsigned mseq = le32_to_cpu(ex->migrate_seq); @@ -2807,7 +2805,7 @@ static void handle_cap_export(struct inode *inode, struct ceph_mds_caps *ex, retry: spin_lock(&ci->i_ceph_lock); cap = __get_cap_for_mds(ci, mds); - if (!cap) + if (!cap || cap->cap_id != le64_to_cpu(ex->cap_id)) goto out_unlock; if (target < 0) { @@ -2846,15 +2844,14 @@ retry: } __ceph_remove_cap(cap, false); goto out_unlock; - } - - if (tsession) { - int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0; - spin_unlock(&ci->i_ceph_lock); + } else if (tsession) { /* add placeholder for the export tagert */ + int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0; ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0, - t_seq - 1, t_mseq, (u64)-1, flag, NULL); - goto retry; + t_seq - 1, t_mseq, (u64)-1, flag, &new_cap); + + __ceph_remove_cap(cap, false); + goto out_unlock; } spin_unlock(&ci->i_ceph_lock); @@ -2873,6 +2870,7 @@ retry: SINGLE_DEPTH_NESTING); } ceph_add_cap_releases(mdsc, tsession); + new_cap = ceph_get_cap(mdsc, NULL); } else { WARN_ON(1); tsession = NULL; @@ -2887,24 +2885,27 @@ out_unlock: mutex_unlock(&tsession->s_mutex); ceph_put_mds_session(tsession); } + if (new_cap) + ceph_put_cap(mdsc, new_cap); } /* - * Handle cap IMPORT. If there are temp bits from an older EXPORT, - * clean them up. + * Handle cap IMPORT. * - * caller holds s_mutex. + * caller holds s_mutex. acquires i_ceph_lock */ static void handle_cap_import(struct ceph_mds_client *mdsc, struct inode *inode, struct ceph_mds_caps *im, struct ceph_mds_cap_peer *ph, struct ceph_mds_session *session, - void *snaptrace, int snaptrace_len) + struct ceph_cap **target_cap, int *old_issued) + __acquires(ci->i_ceph_lock) { struct ceph_inode_info *ci = ceph_inode(inode); - struct ceph_cap *cap; + struct ceph_cap *cap, *ocap, *new_cap = NULL; int mds = session->s_mds; - unsigned issued = le32_to_cpu(im->caps); + int issued; + unsigned caps = le32_to_cpu(im->caps); unsigned wanted = le32_to_cpu(im->wanted); unsigned seq = le32_to_cpu(im->seq); unsigned mseq = le32_to_cpu(im->migrate_seq); @@ -2924,40 +2925,52 @@ static void handle_cap_import(struct ceph_mds_client *mdsc, dout("handle_cap_import inode %p ci %p mds%d mseq %d peer %d\n", inode, ci, mds, mseq, peer); +retry: spin_lock(&ci->i_ceph_lock); - cap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL; - if (cap && cap->cap_id == p_cap_id) { + cap = __get_cap_for_mds(ci, mds); + if (!cap) { + if (!new_cap) { + spin_unlock(&ci->i_ceph_lock); + new_cap = ceph_get_cap(mdsc, NULL); + goto retry; + } + cap = new_cap; + } else { + if (new_cap) { + ceph_put_cap(mdsc, new_cap); + new_cap = NULL; + } + } + + __ceph_caps_issued(ci, &issued); + issued |= __ceph_caps_dirty(ci); + + ceph_add_cap(inode, session, cap_id, -1, caps, wanted, seq, mseq, + realmino, CEPH_CAP_FLAG_AUTH, &new_cap); + + ocap = peer >= 0 ? __get_cap_for_mds(ci, peer) : NULL; + if (ocap && ocap->cap_id == p_cap_id) { dout(" remove export cap %p mds%d flags %d\n", - cap, peer, ph->flags); + ocap, peer, ph->flags); if ((ph->flags & CEPH_CAP_FLAG_AUTH) && - (cap->seq != le32_to_cpu(ph->seq) || - cap->mseq != le32_to_cpu(ph->mseq))) { + (ocap->seq != le32_to_cpu(ph->seq) || + ocap->mseq != le32_to_cpu(ph->mseq))) { pr_err("handle_cap_import: mismatched seq/mseq: " "ino (%llx.%llx) mds%d seq %d mseq %d " "importer mds%d has peer seq %d mseq %d\n", - ceph_vinop(inode), peer, cap->seq, - cap->mseq, mds, le32_to_cpu(ph->seq), + ceph_vinop(inode), peer, ocap->seq, + ocap->mseq, mds, le32_to_cpu(ph->seq), le32_to_cpu(ph->mseq)); } - ci->i_cap_exporting_issued = cap->issued; - __ceph_remove_cap(cap, (ph->flags & CEPH_CAP_FLAG_RELEASE)); + __ceph_remove_cap(ocap, (ph->flags & CEPH_CAP_FLAG_RELEASE)); } /* make sure we re-request max_size, if necessary */ ci->i_wanted_max_size = 0; ci->i_requested_max_size = 0; - spin_unlock(&ci->i_ceph_lock); - - down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, snaptrace, snaptrace+snaptrace_len, - false); - downgrade_write(&mdsc->snap_rwsem); - ceph_add_cap(inode, session, cap_id, -1, - issued, wanted, seq, mseq, realmino, CEPH_CAP_FLAG_AUTH, - NULL /* no caps context */); - kick_flushing_inode_caps(mdsc, session, inode); - up_read(&mdsc->snap_rwsem); + *old_issued = issued; + *target_cap = cap; } /* @@ -2977,7 +2990,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, struct ceph_mds_caps *h; struct ceph_mds_cap_peer *peer = NULL; int mds = session->s_mds; - int op; + int op, issued; u32 seq, mseq; struct ceph_vino vino; u64 cap_id; @@ -3069,7 +3082,10 @@ void ceph_handle_caps(struct ceph_mds_session *session, case CEPH_CAP_OP_IMPORT: handle_cap_import(mdsc, inode, h, peer, session, - snaptrace, snaptrace_len); + &cap, &issued); + handle_cap_grant(mdsc, inode, h, snaptrace, snaptrace_len, + msg->middle, session, cap, issued); + goto done_unlocked; } /* the rest require a cap */ @@ -3086,8 +3102,10 @@ void ceph_handle_caps(struct ceph_mds_session *session, switch (op) { case CEPH_CAP_OP_REVOKE: case CEPH_CAP_OP_GRANT: - case CEPH_CAP_OP_IMPORT: - handle_cap_grant(inode, h, session, cap, msg->middle); + __ceph_caps_issued(ci, &issued); + issued |= __ceph_caps_dirty(ci); + handle_cap_grant(mdsc, inode, h, NULL, 0, msg->middle, + session, cap, issued); goto done_unlocked; case CEPH_CAP_OP_FLUSH_ACK: diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 00d6af6a32e..8d7d782f438 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -169,7 +169,7 @@ static struct dentry *__get_parent(struct super_block *sb, return dentry; } -struct dentry *ceph_get_parent(struct dentry *child) +static struct dentry *ceph_get_parent(struct dentry *child) { /* don't re-export snaps */ if (ceph_snap(child->d_inode) != CEPH_NOSNAP) diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 88a6df4cbe6..302085100c2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -418,7 +418,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, struct page **pages; u64 off = iocb->ki_pos; int num_pages, ret; - size_t len = i->count; + size_t len = iov_iter_count(i); dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, @@ -436,25 +436,26 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, if (file->f_flags & O_DIRECT) { while (iov_iter_count(i)) { - void __user *data = i->iov[0].iov_base + i->iov_offset; - size_t len = i->iov[0].iov_len - i->iov_offset; + size_t start; + ssize_t n; - num_pages = calc_pages_for((unsigned long)data, len); - pages = ceph_get_direct_page_vector(data, - num_pages, true); - if (IS_ERR(pages)) - return PTR_ERR(pages); + n = iov_iter_get_pages_alloc(i, &pages, INT_MAX, &start); + if (n < 0) + return n; - ret = striped_read(inode, off, len, + num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; + + ret = striped_read(inode, off, n, pages, num_pages, checkeof, - 1, (unsigned long)data & ~PAGE_MASK); + 1, start); + ceph_put_page_vector(pages, num_pages, true); if (ret <= 0) break; off += ret; iov_iter_advance(i, ret); - if (ret < len) + if (ret < n) break; } } else { @@ -466,25 +467,14 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *i, num_pages, checkeof, 0, 0); if (ret > 0) { int l, k = 0; - size_t left = len = ret; + size_t left = ret; while (left) { - void __user *data = i->iov[0].iov_base - + i->iov_offset; - l = min(i->iov[0].iov_len - i->iov_offset, - left); - - ret = ceph_copy_page_vector_to_user(&pages[k], - data, off, - l); - if (ret > 0) { - iov_iter_advance(i, ret); - left -= ret; - off += ret; - k = calc_pages_for(iocb->ki_pos, - len - left + 1) - 1; - BUG_ON(k >= num_pages && left); - } else + int copy = min_t(size_t, PAGE_SIZE, left); + l = copy_page_to_iter(pages[k++], 0, copy, i); + off += l; + left -= l; + if (l < copy) break; } } @@ -541,8 +531,7 @@ static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe) * objects, rollback on failure, etc.) */ static ssize_t -ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, size_t count) +ceph_sync_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); @@ -556,11 +545,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, int written = 0; int flags; int check_caps = 0; - int page_align; int ret; struct timespec mtime = CURRENT_TIME; loff_t pos = iocb->ki_pos; - struct iov_iter i; + size_t count = iov_iter_count(from); if (ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; @@ -582,13 +570,10 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE; - iov_iter_init(&i, iov, nr_segs, count, 0); - - while (iov_iter_count(&i) > 0) { - void __user *data = i.iov->iov_base + i.iov_offset; - u64 len = i.iov->iov_len - i.iov_offset; - - page_align = (unsigned long)data & ~PAGE_MASK; + while (iov_iter_count(from) > 0) { + u64 len = iov_iter_single_seg_count(from); + size_t start; + ssize_t n; snapc = ci->i_snap_realm->cached_context; vino = ceph_vino(inode); @@ -604,20 +589,21 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, break; } - num_pages = calc_pages_for(page_align, len); - pages = ceph_get_direct_page_vector(data, num_pages, false); - if (IS_ERR(pages)) { - ret = PTR_ERR(pages); - goto out; + n = iov_iter_get_pages_alloc(from, &pages, len, &start); + if (unlikely(n < 0)) { + ret = n; + ceph_osdc_put_request(req); + break; } + num_pages = (n + start + PAGE_SIZE - 1) / PAGE_SIZE; /* * throw out any page cache pages in this range. this * may block. */ truncate_inode_pages_range(inode->i_mapping, pos, - (pos+len) | (PAGE_CACHE_SIZE-1)); - osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_align, + (pos+n) | (PAGE_CACHE_SIZE-1)); + osd_req_op_extent_osd_data_pages(req, 0, pages, n, start, false, false); /* BUG_ON(vino.snap != CEPH_NOSNAP); */ @@ -629,22 +615,20 @@ ceph_sync_direct_write(struct kiocb *iocb, const struct iovec *iov, ceph_put_page_vector(pages, num_pages, false); -out: ceph_osdc_put_request(req); - if (ret == 0) { - pos += len; - written += len; - iov_iter_advance(&i, (size_t)len); - - if (pos > i_size_read(inode)) { - check_caps = ceph_inode_set_size(inode, pos); - if (check_caps) - ceph_check_caps(ceph_inode(inode), - CHECK_CAPS_AUTHONLY, - NULL); - } - } else + if (ret) break; + pos += n; + written += n; + iov_iter_advance(from, n); + + if (pos > i_size_read(inode)) { + check_caps = ceph_inode_set_size(inode, pos); + if (check_caps) + ceph_check_caps(ceph_inode(inode), + CHECK_CAPS_AUTHONLY, + NULL); + } } if (ret != -EOLDSNAPC && written > 0) { @@ -662,8 +646,7 @@ out: * correct atomic write, we should e.g. take write locks on all * objects, rollback on failure, etc.) */ -static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, size_t count) +static ssize_t ceph_sync_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); @@ -681,7 +664,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov, int ret; struct timespec mtime = CURRENT_TIME; loff_t pos = iocb->ki_pos; - struct iov_iter i; + size_t count = iov_iter_count(from); if (ceph_snap(file_inode(file)) != CEPH_NOSNAP) return -EROFS; @@ -703,9 +686,7 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov, CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ACK; - iov_iter_init(&i, iov, nr_segs, count, 0); - - while ((len = iov_iter_count(&i)) > 0) { + while ((len = iov_iter_count(from)) > 0) { size_t left; int n; @@ -737,13 +718,12 @@ static ssize_t ceph_sync_write(struct kiocb *iocb, const struct iovec *iov, left = len; for (n = 0; n < num_pages; n++) { size_t plen = min_t(size_t, left, PAGE_SIZE); - ret = iov_iter_copy_from_user(pages[n], &i, 0, plen); + ret = copy_page_from_iter(pages[n], 0, plen, from); if (ret != plen) { ret = -EFAULT; break; } left -= ret; - iov_iter_advance(&i, ret); } if (ret < 0) { @@ -796,8 +776,7 @@ out: * * Hmm, the sync read case isn't actually async... should it be? */ -static ssize_t ceph_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *filp = iocb->ki_filp; struct ceph_file_info *fi = filp->private_data; @@ -823,40 +802,20 @@ again: if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 || (iocb->ki_filp->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) { - struct iov_iter i; dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n", inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); - if (!read) { - ret = generic_segment_checks(iov, &nr_segs, - &len, VERIFY_WRITE); - if (ret) - goto out; - } - - iov_iter_init(&i, iov, nr_segs, len, read); - /* hmm, this isn't really async... */ - ret = ceph_sync_read(iocb, &i, &checkeof); + ret = ceph_sync_read(iocb, to, &checkeof); } else { - /* - * We can't modify the content of iov, - * so we only read from beginning. - */ - if (read) { - iocb->ki_pos = pos; - len = iocb->ki_nbytes; - read = 0; - } dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n", - inode, ceph_vinop(inode), pos, (unsigned)len, + inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, ceph_cap_string(got)); - ret = generic_file_aio_read(iocb, iov, nr_segs, pos); + ret = generic_file_read_iter(iocb, to); } -out: dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n", inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret); ceph_put_cap_refs(ci, got); @@ -872,6 +831,7 @@ out: ", reading more\n", iocb->ki_pos, inode->i_size); + iov_iter_advance(to, ret); read += ret; len -= ret; checkeof = 0; @@ -895,8 +855,7 @@ out: * * If we are near ENOSPC, write synchronously. */ -static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct ceph_file_info *fi = file->private_data; @@ -904,18 +863,15 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_osd_client *osdc = &ceph_sb_to_client(inode->i_sb)->client->osdc; - ssize_t count, written = 0; + ssize_t count = iov_iter_count(from), written = 0; int err, want, got; + loff_t pos = iocb->ki_pos; if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; mutex_lock(&inode->i_mutex); - err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (err) - goto out; - /* We can write back this queue in page reclaim */ current->backing_dev_info = file->f_mapping->backing_dev_info; @@ -925,6 +881,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(from, count); err = file_remove_suid(file); if (err) @@ -956,23 +913,26 @@ retry_snap: if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 || (file->f_flags & O_DIRECT) || (fi->flags & CEPH_F_SYNC)) { + struct iov_iter data; mutex_unlock(&inode->i_mutex); + /* we might need to revert back to that point */ + data = *from; if (file->f_flags & O_DIRECT) - written = ceph_sync_direct_write(iocb, iov, - nr_segs, count); + written = ceph_sync_direct_write(iocb, &data); else - written = ceph_sync_write(iocb, iov, nr_segs, count); + written = ceph_sync_write(iocb, &data); if (written == -EOLDSNAPC) { dout("aio_write %p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n", inode, ceph_vinop(inode), - pos, (unsigned)iov->iov_len); + pos, (unsigned)count); mutex_lock(&inode->i_mutex); goto retry_snap; } + if (written > 0) + iov_iter_advance(from, written); } else { loff_t old_size = inode->i_size; - struct iov_iter from; /* * No need to acquire the i_truncate_mutex. Because * the MDS revokes Fwb caps before sending truncate @@ -980,8 +940,7 @@ retry_snap: * are pending vmtruncate. So write and vmtruncate * can not run at the same time */ - iov_iter_init(&from, iov, nr_segs, count, 0); - written = generic_perform_write(file, &from, pos); + written = generic_perform_write(file, from, pos); if (likely(written >= 0)) iocb->ki_pos = pos + written; if (inode->i_size > old_size) @@ -999,7 +958,7 @@ retry_snap: } dout("aio_write %p %llx.%llx %llu~%u dropping cap refs on %s\n", - inode, ceph_vinop(inode), pos, (unsigned)iov->iov_len, + inode, ceph_vinop(inode), pos, (unsigned)count, ceph_cap_string(got)); ceph_put_cap_refs(ci, got); @@ -1276,16 +1235,16 @@ const struct file_operations ceph_file_fops = { .open = ceph_open, .release = ceph_release, .llseek = ceph_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = ceph_aio_read, - .aio_write = ceph_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = ceph_read_iter, + .write_iter = ceph_write_iter, .mmap = ceph_mmap, .fsync = ceph_fsync, .lock = ceph_lock, .flock = ceph_flock, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .unlocked_ioctl = ceph_ioctl, .compat_ioctl = ceph_ioctl, .fallocate = ceph_fallocate, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index e4fff9ff1c2..04c89c266ce 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -10,6 +10,7 @@ #include <linux/writeback.h> #include <linux/vmalloc.h> #include <linux/posix_acl.h> +#include <linux/random.h> #include "super.h" #include "mds_client.h" @@ -179,9 +180,8 @@ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f) * specified, copy the frag delegation info to the caller if * it is present. */ -u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, - struct ceph_inode_frag *pfrag, - int *found) +static u32 __ceph_choose_frag(struct ceph_inode_info *ci, u32 v, + struct ceph_inode_frag *pfrag, int *found) { u32 t = ceph_frag_make(0, 0); struct ceph_inode_frag *frag; @@ -191,7 +191,6 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, if (found) *found = 0; - mutex_lock(&ci->i_fragtree_mutex); while (1) { WARN_ON(!ceph_frag_contains_value(t, v)); frag = __ceph_find_frag(ci, t); @@ -220,10 +219,19 @@ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, } dout("choose_frag(%x) = %x\n", v, t); - mutex_unlock(&ci->i_fragtree_mutex); return t; } +u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, + struct ceph_inode_frag *pfrag, int *found) +{ + u32 ret; + mutex_lock(&ci->i_fragtree_mutex); + ret = __ceph_choose_frag(ci, v, pfrag, found); + mutex_unlock(&ci->i_fragtree_mutex); + return ret; +} + /* * Process dirfrag (delegation) info from the mds. Include leaf * fragment in tree ONLY if ndist > 0. Otherwise, only @@ -237,11 +245,17 @@ static int ceph_fill_dirfrag(struct inode *inode, u32 id = le32_to_cpu(dirinfo->frag); int mds = le32_to_cpu(dirinfo->auth); int ndist = le32_to_cpu(dirinfo->ndist); + int diri_auth = -1; int i; int err = 0; + spin_lock(&ci->i_ceph_lock); + if (ci->i_auth_cap) + diri_auth = ci->i_auth_cap->mds; + spin_unlock(&ci->i_ceph_lock); + mutex_lock(&ci->i_fragtree_mutex); - if (ndist == 0) { + if (ndist == 0 && mds == diri_auth) { /* no delegation info needed. */ frag = __ceph_find_frag(ci, id); if (!frag) @@ -286,6 +300,75 @@ out: return err; } +static int ceph_fill_fragtree(struct inode *inode, + struct ceph_frag_tree_head *fragtree, + struct ceph_mds_reply_dirfrag *dirinfo) +{ + struct ceph_inode_info *ci = ceph_inode(inode); + struct ceph_inode_frag *frag; + struct rb_node *rb_node; + int i; + u32 id, nsplits; + bool update = false; + + mutex_lock(&ci->i_fragtree_mutex); + nsplits = le32_to_cpu(fragtree->nsplits); + if (nsplits) { + i = prandom_u32() % nsplits; + id = le32_to_cpu(fragtree->splits[i].frag); + if (!__ceph_find_frag(ci, id)) + update = true; + } else if (!RB_EMPTY_ROOT(&ci->i_fragtree)) { + rb_node = rb_first(&ci->i_fragtree); + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + if (frag->frag != ceph_frag_make(0, 0) || rb_next(rb_node)) + update = true; + } + if (!update && dirinfo) { + id = le32_to_cpu(dirinfo->frag); + if (id != __ceph_choose_frag(ci, id, NULL, NULL)) + update = true; + } + if (!update) + goto out_unlock; + + dout("fill_fragtree %llx.%llx\n", ceph_vinop(inode)); + rb_node = rb_first(&ci->i_fragtree); + for (i = 0; i < nsplits; i++) { + id = le32_to_cpu(fragtree->splits[i].frag); + frag = NULL; + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + if (ceph_frag_compare(frag->frag, id) >= 0) { + if (frag->frag != id) + frag = NULL; + else + rb_node = rb_next(rb_node); + break; + } + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + frag = NULL; + } + if (!frag) { + frag = __get_or_create_frag(ci, id); + if (IS_ERR(frag)) + continue; + } + frag->split_by = le32_to_cpu(fragtree->splits[i].by); + dout(" frag %x split by %d\n", frag->frag, frag->split_by); + } + while (rb_node) { + frag = rb_entry(rb_node, struct ceph_inode_frag, node); + rb_node = rb_next(rb_node); + rb_erase(&frag->node, &ci->i_fragtree); + kfree(frag); + } +out_unlock: + mutex_unlock(&ci->i_fragtree_mutex); + return 0; +} /* * initialize a newly allocated inode. @@ -341,7 +424,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb) INIT_LIST_HEAD(&ci->i_cap_snaps); ci->i_head_snapc = NULL; ci->i_snap_caps = 0; - ci->i_cap_exporting_issued = 0; for (i = 0; i < CEPH_FILE_MODE_NUM; i++) ci->i_nr_by_mode[i] = 0; @@ -407,7 +489,7 @@ void ceph_destroy_inode(struct inode *inode) /* * we may still have a snap_realm reference if there are stray - * caps in i_cap_exporting_issued or i_snap_caps. + * caps in i_snap_caps. */ if (ci->i_snap_realm) { struct ceph_mds_client *mdsc = @@ -582,22 +664,26 @@ static int fill_inode(struct inode *inode, unsigned long ttl_from, int cap_fmode, struct ceph_cap_reservation *caps_reservation) { + struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; struct ceph_mds_reply_inode *info = iinfo->in; struct ceph_inode_info *ci = ceph_inode(inode); - int i; - int issued = 0, implemented; + int issued = 0, implemented, new_issued; struct timespec mtime, atime, ctime; - u32 nsplits; - struct ceph_inode_frag *frag; - struct rb_node *rb_node; struct ceph_buffer *xattr_blob = NULL; + struct ceph_cap *new_cap = NULL; int err = 0; - int queue_trunc = 0; + bool wake = false; + bool queue_trunc = false; + bool new_version = false; dout("fill_inode %p ino %llx.%llx v %llu had %llu\n", inode, ceph_vinop(inode), le64_to_cpu(info->version), ci->i_version); + /* prealloc new cap struct */ + if (info->cap.caps && ceph_snap(inode) == CEPH_NOSNAP) + new_cap = ceph_get_cap(mdsc, caps_reservation); + /* * prealloc xattr data, if it looks like we'll need it. only * if len > 4 (meaning there are actually xattrs; the first 4 @@ -623,19 +709,23 @@ static int fill_inode(struct inode *inode, * 3 2 skip * 3 3 update */ - if (le64_to_cpu(info->version) > 0 && - (ci->i_version & ~1) >= le64_to_cpu(info->version)) - goto no_change; - + if (ci->i_version == 0 || + ((info->cap.flags & CEPH_CAP_FLAG_AUTH) && + le64_to_cpu(info->version) > (ci->i_version & ~1))) + new_version = true; + issued = __ceph_caps_issued(ci, &implemented); issued |= implemented | __ceph_caps_dirty(ci); + new_issued = ~issued & le32_to_cpu(info->cap.caps); /* update inode */ ci->i_version = le64_to_cpu(info->version); inode->i_version++; inode->i_rdev = le32_to_cpu(info->rdev); + inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; - if ((issued & CEPH_CAP_AUTH_EXCL) == 0) { + if ((new_version || (new_issued & CEPH_CAP_AUTH_SHARED)) && + (issued & CEPH_CAP_AUTH_EXCL) == 0) { inode->i_mode = le32_to_cpu(info->mode); inode->i_uid = make_kuid(&init_user_ns, le32_to_cpu(info->uid)); inode->i_gid = make_kgid(&init_user_ns, le32_to_cpu(info->gid)); @@ -644,23 +734,35 @@ static int fill_inode(struct inode *inode, from_kgid(&init_user_ns, inode->i_gid)); } - if ((issued & CEPH_CAP_LINK_EXCL) == 0) + if ((new_version || (new_issued & CEPH_CAP_LINK_SHARED)) && + (issued & CEPH_CAP_LINK_EXCL) == 0) set_nlink(inode, le32_to_cpu(info->nlink)); - /* be careful with mtime, atime, size */ - ceph_decode_timespec(&atime, &info->atime); - ceph_decode_timespec(&mtime, &info->mtime); - ceph_decode_timespec(&ctime, &info->ctime); - queue_trunc = ceph_fill_file_size(inode, issued, - le32_to_cpu(info->truncate_seq), - le64_to_cpu(info->truncate_size), - le64_to_cpu(info->size)); - ceph_fill_file_time(inode, issued, - le32_to_cpu(info->time_warp_seq), - &ctime, &mtime, &atime); - - ci->i_layout = info->layout; - inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; + if (new_version || (new_issued & CEPH_CAP_ANY_RD)) { + /* be careful with mtime, atime, size */ + ceph_decode_timespec(&atime, &info->atime); + ceph_decode_timespec(&mtime, &info->mtime); + ceph_decode_timespec(&ctime, &info->ctime); + ceph_fill_file_time(inode, issued, + le32_to_cpu(info->time_warp_seq), + &ctime, &mtime, &atime); + } + + if (new_version || + (new_issued & (CEPH_CAP_ANY_FILE_RD | CEPH_CAP_ANY_FILE_WR))) { + ci->i_layout = info->layout; + queue_trunc = ceph_fill_file_size(inode, issued, + le32_to_cpu(info->truncate_seq), + le64_to_cpu(info->truncate_size), + le64_to_cpu(info->size)); + /* only update max_size on auth cap */ + if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) && + ci->i_max_size != le64_to_cpu(info->max_size)) { + dout("max_size %lld -> %llu\n", ci->i_max_size, + le64_to_cpu(info->max_size)); + ci->i_max_size = le64_to_cpu(info->max_size); + } + } /* xattrs */ /* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */ @@ -745,58 +847,6 @@ static int fill_inode(struct inode *inode, dout(" marking %p complete (empty)\n", inode); __ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count)); } -no_change: - /* only update max_size on auth cap */ - if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) && - ci->i_max_size != le64_to_cpu(info->max_size)) { - dout("max_size %lld -> %llu\n", ci->i_max_size, - le64_to_cpu(info->max_size)); - ci->i_max_size = le64_to_cpu(info->max_size); - } - - spin_unlock(&ci->i_ceph_lock); - - /* queue truncate if we saw i_size decrease */ - if (queue_trunc) - ceph_queue_vmtruncate(inode); - - /* populate frag tree */ - /* FIXME: move me up, if/when version reflects fragtree changes */ - nsplits = le32_to_cpu(info->fragtree.nsplits); - mutex_lock(&ci->i_fragtree_mutex); - rb_node = rb_first(&ci->i_fragtree); - for (i = 0; i < nsplits; i++) { - u32 id = le32_to_cpu(info->fragtree.splits[i].frag); - frag = NULL; - while (rb_node) { - frag = rb_entry(rb_node, struct ceph_inode_frag, node); - if (ceph_frag_compare(frag->frag, id) >= 0) { - if (frag->frag != id) - frag = NULL; - else - rb_node = rb_next(rb_node); - break; - } - rb_node = rb_next(rb_node); - rb_erase(&frag->node, &ci->i_fragtree); - kfree(frag); - frag = NULL; - } - if (!frag) { - frag = __get_or_create_frag(ci, id); - if (IS_ERR(frag)) - continue; - } - frag->split_by = le32_to_cpu(info->fragtree.splits[i].by); - dout(" frag %x split by %d\n", frag->frag, frag->split_by); - } - while (rb_node) { - frag = rb_entry(rb_node, struct ceph_inode_frag, node); - rb_node = rb_next(rb_node); - rb_erase(&frag->node, &ci->i_fragtree); - kfree(frag); - } - mutex_unlock(&ci->i_fragtree_mutex); /* were we issued a capability? */ if (info->cap.caps) { @@ -809,30 +859,41 @@ no_change: le32_to_cpu(info->cap.seq), le32_to_cpu(info->cap.mseq), le64_to_cpu(info->cap.realm), - info->cap.flags, - caps_reservation); + info->cap.flags, &new_cap); + wake = true; } else { - spin_lock(&ci->i_ceph_lock); dout(" %p got snap_caps %s\n", inode, ceph_cap_string(le32_to_cpu(info->cap.caps))); ci->i_snap_caps |= le32_to_cpu(info->cap.caps); if (cap_fmode >= 0) __ceph_get_fmode(ci, cap_fmode); - spin_unlock(&ci->i_ceph_lock); } } else if (cap_fmode >= 0) { pr_warn("mds issued no caps on %llx.%llx\n", ceph_vinop(inode)); __ceph_get_fmode(ci, cap_fmode); } + spin_unlock(&ci->i_ceph_lock); + + if (wake) + wake_up_all(&ci->i_cap_wq); + + /* queue truncate if we saw i_size decrease */ + if (queue_trunc) + ceph_queue_vmtruncate(inode); + + /* populate frag tree */ + if (S_ISDIR(inode->i_mode)) + ceph_fill_fragtree(inode, &info->fragtree, dirinfo); /* update delegation info? */ if (dirinfo) ceph_fill_dirfrag(inode, dirinfo); err = 0; - out: + if (new_cap) + ceph_put_cap(mdsc, new_cap); if (xattr_blob) ceph_buffer_put(xattr_blob); return err; @@ -1485,7 +1546,7 @@ static void ceph_invalidate_work(struct work_struct *work) orig_gen = ci->i_rdcache_gen; spin_unlock(&ci->i_ceph_lock); - truncate_inode_pages(inode->i_mapping, 0); + truncate_pagecache(inode, 0); spin_lock(&ci->i_ceph_lock); if (orig_gen == ci->i_rdcache_gen && @@ -1588,7 +1649,7 @@ retry: ci->i_truncate_pending, to); spin_unlock(&ci->i_ceph_lock); - truncate_inode_pages(inode->i_mapping, to); + truncate_pagecache(inode, to); spin_lock(&ci->i_ceph_lock); if (to == ci->i_truncate_size) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 9a33b98cb00..92a2548278f 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1558,6 +1558,8 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode) init_completion(&req->r_safe_completion); INIT_LIST_HEAD(&req->r_unsafe_item); + req->r_stamp = CURRENT_TIME; + req->r_op = op; req->r_direct_mode = mode; return req; @@ -1783,7 +1785,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, } len = sizeof(*head) + - pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)); + pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) + + sizeof(struct timespec); /* calculate (max) length for cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -1800,6 +1803,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, goto out_free2; } + msg->hdr.version = 2; msg->hdr.tid = cpu_to_le64(req->r_tid); head = msg->front.iov_base; @@ -1836,6 +1840,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc, mds, req->r_old_inode_drop, req->r_old_inode_unless, 0); head->num_releases = cpu_to_le16(releases); + /* time stamp */ + ceph_encode_copy(&p, &req->r_stamp, sizeof(req->r_stamp)); + BUG_ON(p > end); msg->front.iov_len = p - msg->front.iov_base; msg->hdr.front_len = cpu_to_le32(msg->front.iov_len); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index e90cfccf93b..e00737cf523 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -194,6 +194,7 @@ struct ceph_mds_request { int r_fmode; /* file mode, if expecting cap */ kuid_t r_uid; kgid_t r_gid; + struct timespec r_stamp; /* for choosing which mds to send this request to */ int r_direct_mode; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index ead05cc1f44..12b20744e38 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -292,7 +292,6 @@ struct ceph_inode_info { struct ceph_snap_context *i_head_snapc; /* set if wr_buffer_head > 0 or dirty|flushing caps */ unsigned i_snap_caps; /* cap bits for snapped files */ - unsigned i_cap_exporting_issued; int i_nr_by_mode[CEPH_FILE_MODE_NUM]; /* open file counts */ @@ -775,11 +774,13 @@ static inline void ceph_forget_all_cached_acls(struct inode *inode) extern const char *ceph_cap_string(int c); extern void ceph_handle_caps(struct ceph_mds_session *session, struct ceph_msg *msg); -extern int ceph_add_cap(struct inode *inode, - struct ceph_mds_session *session, u64 cap_id, - int fmode, unsigned issued, unsigned wanted, - unsigned cap, unsigned seq, u64 realmino, int flags, - struct ceph_cap_reservation *caps_reservation); +extern struct ceph_cap *ceph_get_cap(struct ceph_mds_client *mdsc, + struct ceph_cap_reservation *ctx); +extern void ceph_add_cap(struct inode *inode, + struct ceph_mds_session *session, u64 cap_id, + int fmode, unsigned issued, unsigned wanted, + unsigned cap, unsigned seq, u64 realmino, int flags, + struct ceph_cap **new_cap); extern void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release); extern void ceph_put_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap); diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 0227b45ef00..15e9505aa35 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -290,7 +290,8 @@ int cifsConvertToUTF16(__le16 *target, const char *source, int srclen, const struct nls_table *cp, int mapChars) { - int i, j, charlen; + int i, charlen; + int j = 0; char src_char; __le16 dst_char; wchar_t tmp; @@ -298,12 +299,11 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, if (!mapChars) return cifs_strtoUTF16(target, source, PATH_MAX, cp); - for (i = 0, j = 0; i < srclen; j++) { + for (i = 0; i < srclen; j++) { src_char = source[i]; charlen = 1; switch (src_char) { case 0: - put_unaligned(0, &target[j]); goto ctoUTF16_out; case ':': dst_char = cpu_to_le16(UNI_COLON); @@ -350,6 +350,7 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, } ctoUTF16_out: + put_unaligned(0, &target[j]); /* Null terminate target unicode string */ return j; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 6aaa8112c53..88839806742 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -725,8 +725,20 @@ out_nls: goto out; } -static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t +cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) +{ + ssize_t rc; + struct inode *inode = file_inode(iocb->ki_filp); + + rc = cifs_revalidate_mapping(inode); + if (rc) + return rc; + + return generic_file_read_iter(iocb, iter); +} + +static ssize_t cifs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); struct cifsInodeInfo *cinode = CIFS_I(inode); @@ -737,14 +749,14 @@ static ssize_t cifs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (written) return written; - written = generic_file_aio_write(iocb, iov, nr_segs, pos); + written = generic_file_write_iter(iocb, from); if (CIFS_CACHE_WRITE(CIFS_I(inode))) goto out; rc = filemap_fdatawrite(inode->i_mapping); if (rc) - cifs_dbg(FYI, "cifs_file_aio_write: %d rc on %p inode\n", + cifs_dbg(FYI, "cifs_file_write_iter: %d rc on %p inode\n", rc, inode); out: @@ -880,10 +892,10 @@ const struct inode_operations cifs_symlink_inode_ops = { }; const struct file_operations cifs_file_ops = { - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = cifs_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_loose_read_iter, + .write_iter = cifs_file_write_iter, .open = cifs_open, .release = cifs_close, .lock = cifs_lock, @@ -899,10 +911,10 @@ const struct file_operations cifs_file_ops = { }; const struct file_operations cifs_file_strict_ops = { - .read = do_sync_read, - .write = do_sync_write, - .aio_read = cifs_strict_readv, - .aio_write = cifs_strict_writev, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_strict_readv, + .write_iter = cifs_strict_writev, .open = cifs_open, .release = cifs_close, .lock = cifs_lock, @@ -919,10 +931,10 @@ const struct file_operations cifs_file_strict_ops = { const struct file_operations cifs_file_direct_ops = { /* BB reevaluate whether they can be done with directio, no cache */ - .read = do_sync_read, - .write = do_sync_write, - .aio_read = cifs_user_readv, - .aio_write = cifs_user_writev, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_user_readv, + .write_iter = cifs_user_writev, .open = cifs_open, .release = cifs_close, .lock = cifs_lock, @@ -938,10 +950,10 @@ const struct file_operations cifs_file_direct_ops = { }; const struct file_operations cifs_file_nobrl_ops = { - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = cifs_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_loose_read_iter, + .write_iter = cifs_file_write_iter, .open = cifs_open, .release = cifs_close, .fsync = cifs_fsync, @@ -956,10 +968,10 @@ const struct file_operations cifs_file_nobrl_ops = { }; const struct file_operations cifs_file_strict_nobrl_ops = { - .read = do_sync_read, - .write = do_sync_write, - .aio_read = cifs_strict_readv, - .aio_write = cifs_strict_writev, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_strict_readv, + .write_iter = cifs_strict_writev, .open = cifs_open, .release = cifs_close, .fsync = cifs_strict_fsync, @@ -975,10 +987,10 @@ const struct file_operations cifs_file_strict_nobrl_ops = { const struct file_operations cifs_file_direct_nobrl_ops = { /* BB reevaluate whether they can be done with directio, no cache */ - .read = do_sync_read, - .write = do_sync_write, - .aio_read = cifs_user_readv, - .aio_write = cifs_user_writev, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = cifs_user_readv, + .write_iter = cifs_user_writev, .open = cifs_open, .release = cifs_close, .fsync = cifs_fsync, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 8fe51166d6e..70f178a7c75 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -95,14 +95,10 @@ extern const struct file_operations cifs_file_strict_nobrl_ops; extern int cifs_open(struct inode *inode, struct file *file); extern int cifs_close(struct inode *inode, struct file *file); extern int cifs_closedir(struct inode *inode, struct file *file); -extern ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -extern ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -extern ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); -extern ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos); +extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to); +extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to); +extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from); +extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from); extern int cifs_lock(struct file *, int, struct file_lock *); extern int cifs_fsync(struct file *, loff_t, loff_t, int); extern int cifs_strict_fsync(struct file *, loff_t, loff_t, int); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 208f56eca4b..e90a1e9aa62 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2385,14 +2385,12 @@ cifs_uncached_retry_writev(struct cifs_writedata *wdata) } static ssize_t -cifs_iovec_write(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *poffset) +cifs_iovec_write(struct file *file, struct iov_iter *from, loff_t *poffset) { unsigned long nr_pages, i; size_t bytes, copied, len, cur_len; ssize_t total_written = 0; loff_t offset; - struct iov_iter it; struct cifsFileInfo *open_file; struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb; @@ -2401,14 +2399,16 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, int rc; pid_t pid; - len = iov_length(iov, nr_segs); - if (!len) - return 0; - + len = iov_iter_count(from); rc = generic_write_checks(file, poffset, &len, 0); if (rc) return rc; + if (!len) + return 0; + + iov_iter_truncate(from, len); + INIT_LIST_HEAD(&wdata_list); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); open_file = file->private_data; @@ -2424,7 +2424,6 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, else pid = current->tgid; - iov_iter_init(&it, iov, nr_segs, len, 0); do { size_t save_len; @@ -2444,11 +2443,10 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, save_len = cur_len; for (i = 0; i < nr_pages; i++) { - bytes = min_t(const size_t, cur_len, PAGE_SIZE); - copied = iov_iter_copy_from_user(wdata->pages[i], &it, - 0, bytes); + bytes = min_t(size_t, cur_len, PAGE_SIZE); + copied = copy_page_from_iter(wdata->pages[i], 0, bytes, + from); cur_len -= copied; - iov_iter_advance(&it, copied); /* * If we didn't copy as much as we expected, then that * may mean we trod into an unmapped area. Stop copying @@ -2546,11 +2544,11 @@ restart_loop: return total_written ? total_written : (ssize_t)rc; } -ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) { ssize_t written; struct inode *inode; + loff_t pos = iocb->ki_pos; inode = file_inode(iocb->ki_filp); @@ -2560,7 +2558,7 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov, * write request. */ - written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos); + written = cifs_iovec_write(iocb->ki_filp, from, &pos); if (written > 0) { set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(inode)->flags); iocb->ki_pos = pos; @@ -2570,8 +2568,7 @@ ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov, } static ssize_t -cifs_writev(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +cifs_writev(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; @@ -2589,10 +2586,10 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); if (file->f_flags & O_APPEND) lock_pos = i_size_read(inode); - if (!cifs_find_lock_conflict(cfile, lock_pos, iov_length(iov, nr_segs), + if (!cifs_find_lock_conflict(cfile, lock_pos, iov_iter_count(from), server->vals->exclusive_lock_type, NULL, CIFS_WRITE_OP)) { - rc = __generic_file_aio_write(iocb, iov, nr_segs); + rc = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (rc > 0) { @@ -2610,8 +2607,7 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov, } ssize_t -cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); struct cifsInodeInfo *cinode = CIFS_I(inode); @@ -2629,11 +2625,10 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { - written = generic_file_aio_write( - iocb, iov, nr_segs, pos); + written = generic_file_write_iter(iocb, from); goto out; } - written = cifs_writev(iocb, iov, nr_segs, pos); + written = cifs_writev(iocb, from); goto out; } /* @@ -2642,7 +2637,7 @@ cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, * affected pages because it may cause a error with mandatory locks on * these pages but not on the region from pos to ppos+len-1. */ - written = cifs_user_writev(iocb, iov, nr_segs, pos); + written = cifs_user_writev(iocb, from); if (written > 0 && CIFS_CACHE_READ(cinode)) { /* * Windows 7 server can delay breaking level2 oplock if a write @@ -2831,32 +2826,25 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server, return total_read > 0 ? total_read : result; } -ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; ssize_t rc; size_t len, cur_len; ssize_t total_read = 0; - loff_t offset = pos; + loff_t offset = iocb->ki_pos; unsigned int npages; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; struct cifsFileInfo *open_file; struct cifs_readdata *rdata, *tmp; struct list_head rdata_list; - struct iov_iter to; pid_t pid; - if (!nr_segs) - return 0; - - len = iov_length(iov, nr_segs); + len = iov_iter_count(to); if (!len) return 0; - iov_iter_init(&to, iov, nr_segs, len, 0); - INIT_LIST_HEAD(&rdata_list); cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); open_file = file->private_data; @@ -2914,7 +2902,7 @@ error: if (!list_empty(&rdata_list)) rc = 0; - len = iov_iter_count(&to); + len = iov_iter_count(to); /* the loop below should proceed in the order of increasing offsets */ list_for_each_entry_safe(rdata, tmp, &rdata_list, list) { again: @@ -2931,7 +2919,7 @@ error: goto again; } } else { - rc = cifs_readdata_to_iov(rdata, &to); + rc = cifs_readdata_to_iov(rdata, to); } } @@ -2939,7 +2927,7 @@ error: kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - total_read = len - iov_iter_count(&to); + total_read = len - iov_iter_count(to); cifs_stats_bytes_read(tcon, total_read); @@ -2948,15 +2936,14 @@ error: rc = 0; if (total_read) { - iocb->ki_pos = pos + total_read; + iocb->ki_pos += total_read; return total_read; } return rc; } ssize_t -cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); struct cifsInodeInfo *cinode = CIFS_I(inode); @@ -2975,22 +2962,22 @@ cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov, * pos+len-1. */ if (!CIFS_CACHE_READ(cinode)) - return cifs_user_readv(iocb, iov, nr_segs, pos); + return cifs_user_readv(iocb, to); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) - return generic_file_aio_read(iocb, iov, nr_segs, pos); + return generic_file_read_iter(iocb, to); /* * We need to hold the sem to be sure nobody modifies lock list * with a brlock that prevents reading. */ down_read(&cinode->lock_sem); - if (!cifs_find_lock_conflict(cfile, pos, iov_length(iov, nr_segs), + if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(to), tcon->ses->server->vals->shared_lock_type, NULL, CIFS_READ_OP)) - rc = generic_file_aio_read(iocb, iov, nr_segs, pos); + rc = generic_file_read_iter(iocb, to); up_read(&cinode->lock_sem); return rc; } @@ -3703,8 +3690,8 @@ void cifs_oplock_break(struct work_struct *work) * Direct IO is not yet supported in the cached mode. */ static ssize_t -cifs_direct_io(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t pos, unsigned long nr_segs) +cifs_direct_io(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t pos) { /* * FIXME diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 264ece71bdb..68559fd557f 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -374,7 +374,7 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; oparms.create_options = create_options; - oparms.disposition = FILE_OPEN; + oparms.disposition = FILE_CREATE; oparms.path = path; oparms.fid = &fid; oparms.reconnect = false; diff --git a/fs/coredump.c b/fs/coredump.c index 0b2528fb640..a93f7e6ea4c 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -306,7 +306,7 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, if (unlikely(nr < 0)) return nr; - tsk->flags = PF_DUMPCORE; + tsk->flags |= PF_DUMPCORE; if (atomic_read(&mm->mm_users) == nr + 1) goto done; /* diff --git a/fs/dcache.c b/fs/dcache.c index 1792d6075b4..06f65857a85 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -532,10 +532,12 @@ static inline struct dentry *lock_parent(struct dentry *dentry) struct dentry *parent = dentry->d_parent; if (IS_ROOT(dentry)) return NULL; + if (unlikely((int)dentry->d_lockref.count < 0)) + return NULL; if (likely(spin_trylock(&parent->d_lock))) return parent; - spin_unlock(&dentry->d_lock); rcu_read_lock(); + spin_unlock(&dentry->d_lock); again: parent = ACCESS_ONCE(dentry->d_parent); spin_lock(&parent->d_lock); diff --git a/fs/direct-io.c b/fs/direct-io.c index 31ba0935e32..17e39b047de 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -71,13 +71,11 @@ struct dio_submit { been performed at the start of a write */ int pages_in_io; /* approximate total IO pages */ - size_t size; /* total request size (doesn't change)*/ sector_t block_in_file; /* Current offset into the underlying file in dio_block units. */ unsigned blocks_available; /* At block_in_file. changes */ int reap_counter; /* rate limit reaping */ sector_t final_block_in_request;/* doesn't change */ - unsigned first_block_in_page; /* doesn't change, Used only once */ int boundary; /* prev block is at a boundary */ get_block_t *get_block; /* block mapping function */ dio_submit_t *submit_io; /* IO submition function */ @@ -98,19 +96,14 @@ struct dio_submit { sector_t cur_page_block; /* Where it starts */ loff_t cur_page_fs_offset; /* Offset in file */ - /* - * Page fetching state. These variables belong to dio_refill_pages(). - */ - int curr_page; /* changes */ - int total_pages; /* doesn't change */ - unsigned long curr_user_address;/* changes */ - + struct iov_iter *iter; /* * Page queue. These variables belong to dio_refill_pages() and * dio_get_page(). */ unsigned head; /* next page to process */ unsigned tail; /* last valid page + 1 */ + size_t from, to; }; /* dio_state communicated between submission path and end_io */ @@ -163,15 +156,10 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio) */ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) { - int ret; - int nr_pages; + ssize_t ret; - nr_pages = min(sdio->total_pages - sdio->curr_page, DIO_PAGES); - ret = get_user_pages_fast( - sdio->curr_user_address, /* Where from? */ - nr_pages, /* How many pages? */ - dio->rw == READ, /* Write to memory? */ - &dio->pages[0]); /* Put results here */ + ret = iov_iter_get_pages(sdio->iter, dio->pages, DIO_PAGES * PAGE_SIZE, + &sdio->from); if (ret < 0 && sdio->blocks_available && (dio->rw & WRITE)) { struct page *page = ZERO_PAGE(0); @@ -186,18 +174,19 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio) dio->pages[0] = page; sdio->head = 0; sdio->tail = 1; - ret = 0; - goto out; + sdio->from = 0; + sdio->to = PAGE_SIZE; + return 0; } if (ret >= 0) { - sdio->curr_user_address += ret * PAGE_SIZE; - sdio->curr_page += ret; + iov_iter_advance(sdio->iter, ret); + ret += sdio->from; sdio->head = 0; - sdio->tail = ret; - ret = 0; + sdio->tail = (ret + PAGE_SIZE - 1) / PAGE_SIZE; + sdio->to = ((ret - 1) & (PAGE_SIZE - 1)) + 1; + return 0; } -out: return ret; } @@ -208,7 +197,7 @@ out: * L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, - struct dio_submit *sdio) + struct dio_submit *sdio) { if (dio_pages_present(sdio) == 0) { int ret; @@ -218,7 +207,7 @@ static inline struct page *dio_get_page(struct dio *dio, return ERR_PTR(ret); BUG_ON(dio_pages_present(sdio) == 0); } - return dio->pages[sdio->head++]; + return dio->pages[sdio->head]; } /** @@ -422,8 +411,8 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) */ static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio) { - while (dio_pages_present(sdio)) - page_cache_release(dio_get_page(dio, sdio)); + while (sdio->head < sdio->tail) + page_cache_release(dio->pages[sdio->head++]); } /* @@ -912,23 +901,22 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio, struct buffer_head *map_bh) { const unsigned blkbits = sdio->blkbits; - const unsigned blocks_per_page = PAGE_SIZE >> blkbits; - struct page *page; - unsigned block_in_page; int ret = 0; - /* The I/O can start at any block offset within the first page */ - block_in_page = sdio->first_block_in_page; - while (sdio->block_in_file < sdio->final_block_in_request) { + struct page *page; + size_t from, to; + page = dio_get_page(dio, sdio); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } + from = sdio->head ? 0 : sdio->from; + to = (sdio->head == sdio->tail - 1) ? sdio->to : PAGE_SIZE; + sdio->head++; - while (block_in_page < blocks_per_page) { - unsigned offset_in_page = block_in_page << blkbits; + while (from < to) { unsigned this_chunk_bytes; /* # of bytes mapped */ unsigned this_chunk_blocks; /* # of blocks */ unsigned u; @@ -999,10 +987,10 @@ do_holes: page_cache_release(page); goto out; } - zero_user(page, block_in_page << blkbits, - 1 << blkbits); + zero_user(page, from, 1 << blkbits); sdio->block_in_file++; - block_in_page++; + from += 1 << blkbits; + dio->result += 1 << blkbits; goto next_block; } @@ -1019,7 +1007,7 @@ do_holes: * can add to this page */ this_chunk_blocks = sdio->blocks_available; - u = (PAGE_SIZE - offset_in_page) >> blkbits; + u = (to - from) >> blkbits; if (this_chunk_blocks > u) this_chunk_blocks = u; u = sdio->final_block_in_request - sdio->block_in_file; @@ -1031,7 +1019,7 @@ do_holes: if (this_chunk_blocks == sdio->blocks_available) sdio->boundary = buffer_boundary(map_bh); ret = submit_page_section(dio, sdio, page, - offset_in_page, + from, this_chunk_bytes, sdio->next_block_for_io, map_bh); @@ -1042,7 +1030,8 @@ do_holes: sdio->next_block_for_io += this_chunk_blocks; sdio->block_in_file += this_chunk_blocks; - block_in_page += this_chunk_blocks; + from += this_chunk_bytes; + dio->result += this_chunk_bytes; sdio->blocks_available -= this_chunk_blocks; next_block: BUG_ON(sdio->block_in_file > sdio->final_block_in_request); @@ -1052,7 +1041,6 @@ next_block: /* Drop the ref which was taken in get_user_pages() */ page_cache_release(page); - block_in_page = 0; } out: return ret; @@ -1107,24 +1095,21 @@ static inline int drop_refcount(struct dio *dio) */ static inline ssize_t do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + struct block_device *bdev, struct iov_iter *iter, loff_t offset, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { - int seg; - size_t size; - unsigned long addr; unsigned i_blkbits = ACCESS_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; unsigned blocksize_mask = (1 << blkbits) - 1; ssize_t retval = -EINVAL; - loff_t end = offset; + size_t count = iov_iter_count(iter); + loff_t end = offset + count; struct dio *dio; struct dio_submit sdio = { 0, }; - unsigned long user_addr; - size_t bytes; struct buffer_head map_bh = { 0, }; struct blk_plug plug; + unsigned long align = offset | iov_iter_alignment(iter); if (rw & WRITE) rw = WRITE_ODIRECT; @@ -1134,32 +1119,16 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, * the early prefetch in the caller enough time. */ - if (offset & blocksize_mask) { + if (align & blocksize_mask) { if (bdev) blkbits = blksize_bits(bdev_logical_block_size(bdev)); blocksize_mask = (1 << blkbits) - 1; - if (offset & blocksize_mask) + if (align & blocksize_mask) goto out; } - /* Check the memory alignment. Blocks cannot straddle pages */ - for (seg = 0; seg < nr_segs; seg++) { - addr = (unsigned long)iov[seg].iov_base; - size = iov[seg].iov_len; - end += size; - if (unlikely((addr & blocksize_mask) || - (size & blocksize_mask))) { - if (bdev) - blkbits = blksize_bits( - bdev_logical_block_size(bdev)); - blocksize_mask = (1 << blkbits) - 1; - if ((addr & blocksize_mask) || (size & blocksize_mask)) - goto out; - } - } - /* watch out for a 0 len io from a tricksy fs */ - if (rw == READ && end == offset) + if (rw == READ && !iov_iter_count(iter)) return 0; dio = kmem_cache_alloc(dio_cache, GFP_KERNEL); @@ -1249,6 +1218,10 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; + sdio.iter = iter; + sdio.final_block_in_request = + (offset + iov_iter_count(iter)) >> blkbits; + /* * In case of non-aligned buffers, we may need 2 more * pages since we need to zero out first and last block. @@ -1256,47 +1229,13 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (unlikely(sdio.blkfactor)) sdio.pages_in_io = 2; - for (seg = 0; seg < nr_segs; seg++) { - user_addr = (unsigned long)iov[seg].iov_base; - sdio.pages_in_io += - ((user_addr + iov[seg].iov_len + PAGE_SIZE-1) / - PAGE_SIZE - user_addr / PAGE_SIZE); - } + sdio.pages_in_io += iov_iter_npages(iter, INT_MAX); blk_start_plug(&plug); - for (seg = 0; seg < nr_segs; seg++) { - user_addr = (unsigned long)iov[seg].iov_base; - sdio.size += bytes = iov[seg].iov_len; - - /* Index into the first page of the first block */ - sdio.first_block_in_page = (user_addr & ~PAGE_MASK) >> blkbits; - sdio.final_block_in_request = sdio.block_in_file + - (bytes >> blkbits); - /* Page fetching state */ - sdio.head = 0; - sdio.tail = 0; - sdio.curr_page = 0; - - sdio.total_pages = 0; - if (user_addr & (PAGE_SIZE-1)) { - sdio.total_pages++; - bytes -= PAGE_SIZE - (user_addr & (PAGE_SIZE - 1)); - } - sdio.total_pages += (bytes + PAGE_SIZE - 1) / PAGE_SIZE; - sdio.curr_user_address = user_addr; - - retval = do_direct_IO(dio, &sdio, &map_bh); - - dio->result += iov[seg].iov_len - - ((sdio.final_block_in_request - sdio.block_in_file) << - blkbits); - - if (retval) { - dio_cleanup(dio, &sdio); - break; - } - } /* end iovec loop */ + retval = do_direct_IO(dio, &sdio, &map_bh); + if (retval) + dio_cleanup(dio, &sdio); if (retval == -ENOTBLK) { /* @@ -1348,10 +1287,9 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, */ BUG_ON(retval == -EIOCBQUEUED); if (dio->is_async && retval == 0 && dio->result && - ((rw == READ) || (dio->result == sdio.size))) + (rw == READ || dio->result == count)) retval = -EIOCBQUEUED; - - if (retval != -EIOCBQUEUED) + else dio_await_completion(dio); if (drop_refcount(dio) == 0) { @@ -1365,8 +1303,8 @@ out: ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, - struct block_device *bdev, const struct iovec *iov, loff_t offset, - unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + struct block_device *bdev, struct iov_iter *iter, loff_t offset, + get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) { /* @@ -1381,9 +1319,8 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, prefetch(bdev->bd_queue); prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); - return do_blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset, - nr_segs, get_block, end_io, - submit_io, flags); + return do_blockdev_direct_IO(rw, iocb, inode, bdev, iter, offset, + get_block, end_io, submit_io, flags); } EXPORT_SYMBOL(__blockdev_direct_IO); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 1e5b4535950..d08e079ea5d 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -617,6 +617,11 @@ static void retry_failed_sctp_send(struct connection *recv_con, int nodeid = sn_send_failed->ssf_info.sinfo_ppid; log_print("Retry sending %d bytes to node id %d", len, nodeid); + + if (!nodeid) { + log_print("Shouldn't resend data via listening connection."); + return; + } con = nodeid2con(nodeid, 0); if (!con) { diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index b1eaa7a1f82..db0fad3269c 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -45,14 +45,13 @@ * The function to be used for directory reads is ecryptfs_read. */ static ssize_t ecryptfs_read_update_atime(struct kiocb *iocb, - const struct iovec *iov, - unsigned long nr_segs, loff_t pos) + struct iov_iter *to) { ssize_t rc; struct path *path; struct file *file = iocb->ki_filp; - rc = generic_file_aio_read(iocb, iov, nr_segs, pos); + rc = generic_file_read_iter(iocb, to); /* * Even though this is a async interface, we need to wait * for IO to finish to update atime @@ -352,10 +351,10 @@ const struct file_operations ecryptfs_dir_fops = { const struct file_operations ecryptfs_main_fops = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = ecryptfs_read_update_atime, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = ecryptfs_read_update_atime, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .iterate = ecryptfs_readdir, .unlocked_ioctl = ecryptfs_unlocked_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/eventpoll.c b/fs/eventpoll.c index b73e0621ce9..b10b48c2a7a 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -910,7 +910,7 @@ static const struct file_operations eventpoll_fops = { void eventpoll_release_file(struct file *file) { struct eventpoll *ep; - struct epitem *epi; + struct epitem *epi, *next; /* * We don't want to get "file->f_lock" because it is not @@ -926,7 +926,7 @@ void eventpoll_release_file(struct file *file) * Besides, ep_remove() acquires the lock, so we can't hold it here. */ mutex_lock(&epmutex); - list_for_each_entry_rcu(epi, &file->f_ep_links, fllink) { + list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) { ep = epi->ep; mutex_lock_nested(&ep->mtx, 0); ep_remove(ep, epi); diff --git a/fs/exec.c b/fs/exec.c index 238b7aa26f6..a3d33fe592d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1046,13 +1046,13 @@ EXPORT_SYMBOL_GPL(get_task_comm); * so that a new one can be started */ -void set_task_comm(struct task_struct *tsk, const char *buf) +void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strlcpy(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); - perf_event_comm(tsk); + perf_event_comm(tsk, exec); } int flush_old_exec(struct linux_binprm * bprm) @@ -1110,7 +1110,8 @@ void setup_new_exec(struct linux_binprm * bprm) else set_dumpable(current->mm, suid_dumpable); - set_task_comm(current, kbasename(bprm->filename)); + perf_event_exec(); + __set_task_comm(current, kbasename(bprm->filename), true); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 491c6c078e7..71bf8e4fb5d 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -67,17 +67,17 @@ static int exofs_flush(struct file *file, fl_owner_t id) const struct file_operations exofs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = generic_file_open, .release = exofs_release_file, .fsync = exofs_file_fsync, .flush = exofs_flush, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, }; const struct inode_operations exofs_file_inode_operations = { diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index d1c244d6766..3f9cafd7393 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -964,7 +964,7 @@ static void exofs_invalidatepage(struct page *page, unsigned int offset, /* TODO: Should be easy enough to do proprly */ static ssize_t exofs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { return 0; } diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 44c36e59076..7c87b22a722 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -62,10 +62,10 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ const struct file_operations ext2_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .unlocked_ioctl = ext2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext2_compat_ioctl, @@ -75,7 +75,7 @@ const struct file_operations ext2_file_operations = { .release = ext2_release_file, .fsync = ext2_fsync, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, }; #ifdef CONFIG_EXT2_FS_XIP diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b1d2a4675d4..36d35c36311 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -850,18 +850,18 @@ static sector_t ext2_bmap(struct address_space *mapping, sector_t block) } static ssize_t -ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +ext2_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - ext2_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext2_get_block); if (ret < 0 && (rw & WRITE)) - ext2_write_failed(mapping, offset + iov_length(iov, nr_segs)); + ext2_write_failed(mapping, offset + count); return ret; } diff --git a/fs/ext3/file.c b/fs/ext3/file.c index aad05311392..a062fa1e1b1 100644 --- a/fs/ext3/file.c +++ b/fs/ext3/file.c @@ -50,10 +50,10 @@ static int ext3_release_file (struct inode * inode, struct file * filp) const struct file_operations ext3_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .unlocked_ioctl = ext3_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext3_compat_ioctl, @@ -63,7 +63,7 @@ const struct file_operations ext3_file_operations = { .release = ext3_release_file, .fsync = ext3_sync_file, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, }; const struct inode_operations ext3_file_inode_operations = { diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 695abe738a2..2c6ccc49ba2 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1821,8 +1821,7 @@ static int ext3_releasepage(struct page *page, gfp_t wait) * VFS code falls back into buffered path in that case so we are safe. */ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1830,10 +1829,10 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); int retries = 0; - trace_ext3_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); + trace_ext3_direct_IO_enter(inode, offset, count, rw); if (rw == WRITE) { loff_t final_size = offset + count; @@ -1857,15 +1856,14 @@ static ssize_t ext3_direct_IO(int rw, struct kiocb *iocb, } retry: - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - ext3_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, ext3_get_block); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again. */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) ext3_truncate_failed_direct_write(inode); @@ -1910,8 +1908,7 @@ retry: ret = err; } out: - trace_ext3_direct_IO_exit(inode, offset, - iov_length(iov, nr_segs), rw, ret); + trace_ext3_direct_IO_exit(inode, offset, count, rw, ret); return ret; } diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 0762d143e25..fca382037dd 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -194,7 +194,16 @@ static void ext4_init_block_bitmap(struct super_block *sb, if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, gdp); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return; } @@ -359,6 +368,7 @@ static void ext4_validate_block_bitmap(struct super_block *sb, { ext4_fsblk_t blk; struct ext4_group_info *grp = ext4_get_group_info(sb, block_group); + struct ext4_sb_info *sbi = EXT4_SB(sb); if (buffer_verified(bh)) return; @@ -369,6 +379,9 @@ static void ext4_validate_block_bitmap(struct super_block *sb, ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: block %llu: invalid block bitmap", block_group, blk); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); return; } @@ -376,6 +389,9 @@ static void ext4_validate_block_bitmap(struct super_block *sb, desc, bh))) { ext4_unlock_group(sb, block_group); ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); return; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1479e2ae00d..7cc5a0e2368 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2140,8 +2140,7 @@ extern void ext4_da_update_reserve_space(struct inode *inode, extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags); extern ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs); + struct iov_iter *iter, loff_t offset); extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock); extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks); extern void ext4_ind_truncate(handle_t *, struct inode *inode); diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 3f5c188953a..0b7e28e7eaa 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -966,10 +966,10 @@ retry: continue; } - if (ei->i_es_lru_nr == 0 || ei == locked_ei) + if (ei->i_es_lru_nr == 0 || ei == locked_ei || + !write_trylock(&ei->i_es_lock)) continue; - write_lock(&ei->i_es_lock); shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); if (ei->i_es_lru_nr == 0) list_del_init(&ei->i_es_lru); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 4e8bc284ec0..8695f70af1e 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -74,26 +74,22 @@ static void ext4_unwritten_wait(struct inode *inode) * or one thread will zero the other's data, causing corruption. */ static int -ext4_unaligned_aio(struct inode *inode, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos) { struct super_block *sb = inode->i_sb; int blockmask = sb->s_blocksize - 1; - size_t count = iov_length(iov, nr_segs); - loff_t final_size = pos + count; if (pos >= i_size_read(inode)) return 0; - if ((pos & blockmask) || (final_size & blockmask)) + if ((pos | iov_iter_alignment(from)) & blockmask) return 1; return 0; } static ssize_t -ext4_file_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(iocb->ki_filp); @@ -101,10 +97,9 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, struct blk_plug plug; int o_direct = file->f_flags & O_DIRECT; int overwrite = 0; - size_t length = iov_length(iov, nr_segs); + size_t length = iov_iter_count(from); ssize_t ret; - - BUG_ON(iocb->ki_pos != pos); + loff_t pos = iocb->ki_pos; /* * Unaligned direct AIO must be serialized; see comment above @@ -114,7 +109,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) && !is_sync_kiocb(iocb) && (file->f_flags & O_APPEND || - ext4_unaligned_aio(inode, iov, nr_segs, pos))) { + ext4_unaligned_aio(inode, from, pos))) { aio_mutex = ext4_aio_mutex(inode); mutex_lock(aio_mutex); ext4_unwritten_wait(inode); @@ -138,10 +133,8 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, goto errout; } - if (pos + length > sbi->s_bitmap_maxbytes) { - nr_segs = iov_shorten((struct iovec *)iov, nr_segs, - sbi->s_bitmap_maxbytes - pos); - } + if (pos + length > sbi->s_bitmap_maxbytes) + iov_iter_truncate(from, sbi->s_bitmap_maxbytes - pos); } if (o_direct) { @@ -179,7 +172,7 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov, } } - ret = __generic_file_aio_write(iocb, iov, nr_segs); + ret = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (ret > 0) { @@ -594,10 +587,10 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int whence) const struct file_operations ext4_file_operations = { .llseek = ext4_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = ext4_file_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = ext4_file_write_iter, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, @@ -607,7 +600,7 @@ const struct file_operations ext4_file_operations = { .release = ext4_release_file, .fsync = ext4_sync_file, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = ext4_fallocate, }; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 0ee59a6644e..5b87fc36aab 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -71,6 +71,7 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, struct ext4_group_desc *gdp) { struct ext4_group_info *grp; + struct ext4_sb_info *sbi = EXT4_SB(sb); J_ASSERT_BH(bh, buffer_locked(bh)); /* If checksum is bad mark all blocks and inodes use to prevent @@ -78,7 +79,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb, if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); + if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, gdp); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return 0; } @@ -116,6 +126,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) struct buffer_head *bh = NULL; ext4_fsblk_t bitmap_blk; struct ext4_group_info *grp; + struct ext4_sb_info *sbi = EXT4_SB(sb); desc = ext4_get_group_desc(sb, block_group, NULL); if (!desc) @@ -185,6 +196,12 @@ verify: ext4_error(sb, "Corrupt inode bitmap - block_group = %u, " "inode_bitmap = %llu", block_group, bitmap_blk); grp = ext4_get_group_info(sb, block_group); + if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, desc); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); return NULL; } @@ -321,6 +338,12 @@ out: fatal = err; } else { ext4_error(sb, "bit already cleared for inode %lu", ino); + if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + int count; + count = ext4_free_inodes_count(sb, gdp); + percpu_counter_sub(&sbi->s_freeinodes_counter, + count); + } set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state); } @@ -851,6 +874,13 @@ got: goto out; } + BUFFER_TRACE(group_desc_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, group_desc_bh); + if (err) { + ext4_std_error(sb, err); + goto out; + } + /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -887,13 +917,6 @@ got: } } - BUFFER_TRACE(group_desc_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) { - ext4_std_error(sb, err); - goto out; - } - /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 594009f5f52..fd69da19482 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -389,7 +389,13 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode, return 0; failed: for (; i >= 0; i--) { - if (i != indirect_blks && branch[i].bh) + /* + * We want to ext4_forget() only freshly allocated indirect + * blocks. Buffer for new_blocks[i-1] is at branch[i].bh and + * buffer at branch[0].bh is indirect block / inode already + * existing before ext4_alloc_branch() was called. + */ + if (i > 0 && i != indirect_blks && branch[i].bh) ext4_forget(handle, 1, inode, branch[i].bh, branch[i].bh->b_blocknr); ext4_free_blocks(handle, inode, NULL, new_blocks[i], @@ -639,8 +645,7 @@ out: * VFS code falls back into buffered path in that case so we are safe. */ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -648,7 +653,7 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, handle_t *handle; ssize_t ret; int orphan = 0; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); int retries = 0; if (rw == WRITE) { @@ -687,18 +692,17 @@ retry: goto locked; } ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, + inode->i_sb->s_bdev, iter, offset, 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); + ret = blockdev_direct_IO(rw, iocb, inode, iter, + offset, ext4_get_block); if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) ext4_truncate_failed_write(inode); @@ -1312,16 +1316,24 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode, blk = *i_data; if (level > 0) { ext4_lblk_t first2; + ext4_lblk_t count2; + bh = sb_bread(inode->i_sb, le32_to_cpu(blk)); if (!bh) { EXT4_ERROR_INODE_BLOCK(inode, le32_to_cpu(blk), "Read failure"); return -EIO; } - first2 = (first > offset) ? first - offset : 0; + if (first > offset) { + first2 = first - offset; + count2 = count; + } else { + first2 = 0; + count2 = count - (offset - first); + } ret = free_hole_blocks(handle, inode, bh, (__le32 *)bh->b_data, level - 1, - first2, count - offset, + first2, count2, inode->i_sb->s_blocksize >> 2); if (ret) { brelse(bh); @@ -1331,8 +1343,8 @@ static int free_hole_blocks(handle_t *handle, struct inode *inode, if (level == 0 || (bh && all_zeroes((__le32 *)bh->b_data, (__le32 *)bh->b_data + addr_per_block))) { - ext4_free_data(handle, inode, parent_bh, &blk, &blk+1); - *i_data = 0; + ext4_free_data(handle, inode, parent_bh, + i_data, i_data + 1); } brelse(bh); bh = NULL; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7fcd68ee915..8a064734e6e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3093,13 +3093,12 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset, * */ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); int overwrite = 0; get_block_t *get_block_func = NULL; int dio_flags = 0; @@ -3108,7 +3107,7 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, /* Use the old path for reads and writes beyond i_size. */ if (rw != WRITE || final_size > inode->i_size) - return ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); + return ext4_ind_direct_IO(rw, iocb, iter, offset); BUG_ON(iocb->private == NULL); @@ -3175,8 +3174,8 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, dio_flags = DIO_LOCKING; } ret = __blockdev_direct_IO(rw, iocb, inode, - inode->i_sb->s_bdev, iov, - offset, nr_segs, + inode->i_sb->s_bdev, iter, + offset, get_block_func, ext4_end_io_dio, NULL, @@ -3230,11 +3229,11 @@ retake_lock: } static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; /* @@ -3247,13 +3246,12 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_has_inline_data(inode)) return 0; - trace_ext4_direct_IO_enter(inode, offset, iov_length(iov, nr_segs), rw); + trace_ext4_direct_IO_enter(inode, offset, count, rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - ret = ext4_ext_direct_IO(rw, iocb, iov, offset, nr_segs); + ret = ext4_ext_direct_IO(rw, iocb, iter, offset); else - ret = ext4_ind_direct_IO(rw, iocb, iov, offset, nr_segs); - trace_ext4_direct_IO_exit(inode, offset, - iov_length(iov, nr_segs), rw, ret); + ret = ext4_ind_direct_IO(rw, iocb, iter, offset); + trace_ext4_direct_IO_exit(inode, offset, count, rw, ret); return ret; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 59e31622cc6..2dcb936be90 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -722,6 +722,7 @@ void ext4_mb_generate_buddy(struct super_block *sb, void *buddy, void *bitmap, ext4_group_t group) { struct ext4_group_info *grp = ext4_get_group_info(sb, group); + struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t max = EXT4_CLUSTERS_PER_GROUP(sb); ext4_grpblk_t i = 0; ext4_grpblk_t first; @@ -751,14 +752,17 @@ void ext4_mb_generate_buddy(struct super_block *sb, if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, - "%u clusters in bitmap, %u in gd; " - "block bitmap corrupt.", + "block bitmap and bg descriptor " + "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor * corrupt and update bb_free using bitmap value */ grp->bb_free = free; + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + grp->bb_free); set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state); } mb_set_largest_free_order(sb, grp); @@ -1431,6 +1435,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, right_is_free = !mb_test_bit(last + 1, e4b->bd_bitmap); if (unlikely(block != -1)) { + struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; blocknr = ext4_group_first_block_no(sb, e4b->bd_group); @@ -1441,6 +1446,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, "freeing already freed block " "(bit %u); block bitmap corrupt.", block); + if (!EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)) + percpu_counter_sub(&sbi->s_freeclusters_counter, + e4b->bd_info->bb_free); /* Mark the block group as corrupt. */ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &e4b->bd_info->bb_state); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b9b9aabfb4d..6df7bc611db 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1525,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, arg = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * arg; } else if (token == Opt_max_batch_time) { - if (arg == 0) - arg = EXT4_DEF_MAX_BATCH_TIME; sbi->s_max_batch_time = arg; } else if (token == Opt_min_batch_time) { sbi->s_min_batch_time = arg; @@ -2809,10 +2807,11 @@ static void print_daily_error_info(unsigned long arg) es = sbi->s_es; if (es->s_error_count) - ext4_msg(sb, KERN_NOTICE, "error count: %u", + /* fsck newer than v1.41.13 is needed to clean this condition. */ + ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, @@ -2826,7 +2825,7 @@ static void print_daily_error_info(unsigned long arg) printk("\n"); } if (es->s_last_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, @@ -3880,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - - /* - * set up enough so that it can read an inode, - * and create new inode for buddy allocator - */ - sbi->s_gdb_count = db_count; - if (!test_opt(sb, NOLOAD) && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) - sb->s_op = &ext4_sops; - else - sb->s_op = &ext4_nojournal_sops; - - ext4_ext_init(sb); - err = ext4_mb_init(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", - err); - goto failed_mount2; - } - if (!ext4_check_descriptors(sb, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); - goto failed_mount2a; + goto failed_mount2; } if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); - goto failed_mount2a; + goto failed_mount2; } + sbi->s_gdb_count = db_count; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); @@ -3946,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_extent_max_zeroout_kb = 32; + /* + * set up enough so that it can read an inode + */ + if (!test_opt(sb, NOLOAD) && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) + sb->s_op = &ext4_sops; + else + sb->s_op = &ext4_nojournal_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_QUOTA @@ -4135,13 +4123,21 @@ no_journal: if (err) { ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " "reserved pool", ext4_calculate_resv_clusters(sb)); - goto failed_mount5; + goto failed_mount4a; } err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); + goto failed_mount4a; + } + + ext4_ext_init(sb); + err = ext4_mb_init(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", + err); goto failed_mount5; } @@ -4218,8 +4214,11 @@ failed_mount8: failed_mount7: ext4_unregister_li_request(sb); failed_mount6: - ext4_release_system_zone(sb); + ext4_mb_release(sb); failed_mount5: + ext4_ext_release(sb); + ext4_release_system_zone(sb); +failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: @@ -4243,14 +4242,11 @@ failed_mount3: percpu_counter_destroy(&sbi->s_extent_cache_cnt); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); -failed_mount2a: - ext4_mb_release(sb); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); failed_mount: - ext4_ext_release(sb); if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); if (sbi->s_proc) { diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c1fb6dd1091..f8cf619edb5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -608,8 +608,8 @@ static int __allocate_data_block(struct dnode_of_data *dn) * b. do not use extent cache for better performance * c. give the block addresses to blockdev */ -static int get_data_block(struct inode *inode, sector_t iblock, - struct buffer_head *bh_result, int create) +static int __get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create, bool fiemap) { struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb); unsigned int blkbits = inode->i_sb->s_blocksize_bits; @@ -637,7 +637,7 @@ static int get_data_block(struct inode *inode, sector_t iblock, err = 0; goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR) + if (dn.data_blkaddr == NEW_ADDR && !fiemap) goto put_out; if (dn.data_blkaddr != NULL_ADDR) { @@ -671,7 +671,7 @@ get_next: err = 0; goto unlock_out; } - if (dn.data_blkaddr == NEW_ADDR) + if (dn.data_blkaddr == NEW_ADDR && !fiemap) goto put_out; end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode)); @@ -708,10 +708,23 @@ out: return err; } +static int get_data_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return __get_data_block(inode, iblock, bh_result, create, false); +} + +static int get_data_block_fiemap(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + return __get_data_block(inode, iblock, bh_result, create, true); +} + int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { - return generic_block_fiemap(inode, fieinfo, start, len, get_data_block); + return generic_block_fiemap(inode, fieinfo, + start, len, get_data_block_fiemap); } static int f2fs_read_data_page(struct file *file, struct page *page) @@ -1017,10 +1030,9 @@ static int f2fs_write_end(struct file *file, } static int check_direct_IO(struct inode *inode, int rw, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; - int i; if (rw == READ) return 0; @@ -1028,14 +1040,14 @@ static int check_direct_IO(struct inode *inode, int rw, if (offset & blocksize_mask) return -EINVAL; - for (i = 0; i < nr_segs; i++) - if (iov[i].iov_len & blocksize_mask) - return -EINVAL; + if (iov_iter_alignment(iter) & blocksize_mask) + return -EINVAL; + return 0; } static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1044,14 +1056,14 @@ static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb, if (f2fs_has_inline_data(inode)) return 0; - if (check_direct_IO(inode, rw, iov, offset, nr_segs)) + if (check_direct_IO(inode, rw, iter, offset)) return 0; /* clear fsync mark to recover these blocks */ fsync_mark_clear(F2FS_SB(inode->i_sb), inode->i_ino); - return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - get_data_block); + return blockdev_direct_IO(rw, iocb, inode, iter, offset, + get_data_block); } static void f2fs_invalidate_data_page(struct page *page, unsigned int offset, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 966acb039e3..a4addd72ebb 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -376,11 +376,11 @@ static struct page *init_inode_metadata(struct inode *inode, put_error: f2fs_put_page(page, 1); +error: /* once the failed inode becomes a bad inode, i_mode is S_IFREG */ truncate_inode_pages(&inode->i_data, 0); truncate_blocks(inode, 0); remove_dirty_dir_inode(inode); -error: remove_inode_page(inode); return ERR_PTR(err); } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index e51c732b0dd..58df97e174d 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -342,9 +342,6 @@ struct f2fs_sm_info { struct dirty_seglist_info *dirty_info; /* dirty segment information */ struct curseg_info *curseg_array; /* active segment information */ - struct list_head wblist_head; /* list of under-writeback pages */ - spinlock_t wblist_lock; /* lock for checkpoint */ - block_t seg0_blkaddr; /* block address of 0'th segment */ block_t main_blkaddr; /* start block address of main area */ block_t ssa_blkaddr; /* start block address of SSA area */ @@ -644,7 +641,8 @@ static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) */ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { - WARN_ON((nid >= NM_I(sbi)->max_nid)); + if (unlikely(nid < F2FS_ROOT_INO(sbi))) + return -EINVAL; if (unlikely(nid >= NM_I(sbi)->max_nid)) return -EINVAL; return 0; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 9c49c593d8e..7d8b9627509 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -659,16 +659,19 @@ static int expand_inode_data(struct inode *inode, loff_t offset, off_start = offset & (PAGE_CACHE_SIZE - 1); off_end = (offset + len) & (PAGE_CACHE_SIZE - 1); + f2fs_lock_op(sbi); + for (index = pg_start; index <= pg_end; index++) { struct dnode_of_data dn; - f2fs_lock_op(sbi); + if (index == pg_end && !off_end) + goto noalloc; + set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_reserve_block(&dn, index); - f2fs_unlock_op(sbi); if (ret) break; - +noalloc: if (pg_start == pg_end) new_size = offset + len; else if (index == pg_start && off_start) @@ -683,8 +686,9 @@ static int expand_inode_data(struct inode *inode, loff_t offset, i_size_read(inode) < new_size) { i_size_write(inode, new_size); mark_inode_dirty(inode); - f2fs_write_inode(inode, NULL); + update_inode_page(inode); } + f2fs_unlock_op(sbi); return ret; } @@ -808,10 +812,10 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .open = generic_file_open, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, @@ -821,5 +825,5 @@ const struct file_operations f2fs_file_operations = { .compat_ioctl = f2fs_compat_ioctl, #endif .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, }; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index adc622c6bdc..2cf6962f6cc 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -78,6 +78,7 @@ static int do_read_inode(struct inode *inode) if (check_nid_range(sbi, inode->i_ino)) { f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu", (unsigned long) inode->i_ino); + WARN_ON(1); return -EINVAL; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 9138c32aa69..a6bdddc33ce 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -417,9 +417,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } f2fs_set_link(new_dir, new_entry, new_page, old_inode); - down_write(&F2FS_I(old_inode)->i_sem); - F2FS_I(old_inode)->i_pino = new_dir->i_ino; - up_write(&F2FS_I(old_inode)->i_sem); new_inode->i_ctime = CURRENT_TIME; down_write(&F2FS_I(new_inode)->i_sem); @@ -448,6 +445,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, } } + down_write(&F2FS_I(old_inode)->i_sem); + file_lost_pino(old_inode); + up_write(&F2FS_I(old_inode)->i_sem); + old_inode->i_ctime = CURRENT_TIME; mark_inode_dirty(old_inode); @@ -457,9 +458,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (old_dir != new_dir) { f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir); - down_write(&F2FS_I(old_inode)->i_sem); - F2FS_I(old_inode)->i_pino = new_dir->i_ino; - up_write(&F2FS_I(old_inode)->i_sem); update_inode_page(old_inode); } else { kunmap(old_dir_page); @@ -474,7 +472,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, return 0; put_out_dir: - f2fs_put_page(new_page, 1); + kunmap(new_page); + f2fs_put_page(new_page, 0); out_dir: if (old_dir_entry) { kunmap(old_dir_page); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9dfb9a042fd..4b697ccc9b0 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -42,6 +42,8 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type) mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> 12; res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 2); } else if (type == DIRTY_DENTS) { + if (sbi->sb->s_bdi->dirty_exceeded) + return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); res = mem_size < ((val.totalram * nm_i->ram_thresh / 100) >> 1); } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index f25f0e07e26..d04613df710 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -272,14 +272,15 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi) return -ENOMEM; spin_lock_init(&fcc->issue_lock); init_waitqueue_head(&fcc->flush_wait_queue); + sbi->sm_info->cmd_control_info = fcc; fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi, "f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(fcc->f2fs_issue_flush)) { err = PTR_ERR(fcc->f2fs_issue_flush); kfree(fcc); + sbi->sm_info->cmd_control_info = NULL; return err; } - sbi->sm_info->cmd_control_info = fcc; return err; } @@ -1885,8 +1886,6 @@ int build_segment_manager(struct f2fs_sb_info *sbi) /* init sm info */ sbi->sm_info = sm_info; - INIT_LIST_HEAD(&sm_info->wblist_head); - spin_lock_init(&sm_info->wblist_lock); sm_info->seg0_blkaddr = le32_to_cpu(raw_super->segment0_blkaddr); sm_info->main_blkaddr = le32_to_cpu(raw_super->main_blkaddr); sm_info->segment_count = le32_to_cpu(raw_super->segment_count); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index b2b18637cb9..8f96d9372ad 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -689,9 +689,7 @@ static struct inode *f2fs_nfs_get_inode(struct super_block *sb, struct f2fs_sb_info *sbi = F2FS_SB(sb); struct inode *inode; - if (unlikely(ino < F2FS_ROOT_INO(sbi))) - return ERR_PTR(-ESTALE); - if (unlikely(ino >= NM_I(sbi)->max_nid)) + if (check_nid_range(sbi, ino)) return ERR_PTR(-ESTALE); /* diff --git a/fs/fat/file.c b/fs/fat/file.c index 9b104f54305..85f79a89e74 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -170,10 +170,10 @@ int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = fat_file_release, .unlocked_ioctl = fat_generic_ioctl, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 9c83594d7fb..756aead10d9 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -247,12 +247,13 @@ static int fat_write_end(struct file *file, struct address_space *mapping, } static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; if (rw == WRITE) { @@ -265,7 +266,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * * Return 0, and fallback to normal buffered write. */ - loff_t size = offset + iov_length(iov, nr_segs); + loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } @@ -274,10 +275,9 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - fat_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block); if (ret < 0 && (rw & WRITE)) - fat_write_failed(mapping, offset + iov_length(iov, nr_segs)); + fat_write_failed(mapping, offset + count); return ret; } diff --git a/fs/file.c b/fs/file.c index 8f294cfac69..66923fe3176 100644 --- a/fs/file.c +++ b/fs/file.c @@ -44,15 +44,10 @@ static void *alloc_fdmem(size_t size) return vmalloc(size); } -static void free_fdmem(void *ptr) -{ - is_vmalloc_addr(ptr) ? vfree(ptr) : kfree(ptr); -} - static void __free_fdtable(struct fdtable *fdt) { - free_fdmem(fdt->fd); - free_fdmem(fdt->open_fds); + kvfree(fdt->fd); + kvfree(fdt->open_fds); kfree(fdt); } @@ -130,7 +125,7 @@ static struct fdtable * alloc_fdtable(unsigned int nr) return fdt; out_arr: - free_fdmem(fdt->fd); + kvfree(fdt->fd); out_fdt: kfree(fdt); out: diff --git a/fs/file_table.c b/fs/file_table.c index 40bf4660f0a..385bfd31512 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -175,6 +175,12 @@ struct file *alloc_file(struct path *path, fmode_t mode, file->f_path = *path; file->f_inode = path->dentry->d_inode; file->f_mapping = path->dentry->d_inode->i_mapping; + if ((mode & FMODE_READ) && + likely(fop->read || fop->aio_read || fop->read_iter)) + mode |= FMODE_CAN_READ; + if ((mode & FMODE_WRITE) && + likely(fop->write || fop->aio_write || fop->write_iter)) + mode |= FMODE_CAN_WRITE; file->f_mode = mode; file->f_op = fop; if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 13b691a8a7d..966ace8b243 100644 --- a/fs/fuse/cuse.c +++ b/fs/fuse/cuse.c @@ -94,8 +94,10 @@ static ssize_t cuse_read(struct file *file, char __user *buf, size_t count, loff_t pos = 0; struct iovec iov = { .iov_base = buf, .iov_len = count }; struct fuse_io_priv io = { .async = 0, .file = file }; + struct iov_iter ii; + iov_iter_init(&ii, READ, &iov, 1, count); - return fuse_direct_io(&io, &iov, 1, count, &pos, FUSE_DIO_CUSE); + return fuse_direct_io(&io, &ii, &pos, FUSE_DIO_CUSE); } static ssize_t cuse_write(struct file *file, const char __user *buf, @@ -104,12 +106,14 @@ static ssize_t cuse_write(struct file *file, const char __user *buf, loff_t pos = 0; struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = count }; struct fuse_io_priv io = { .async = 0, .file = file }; + struct iov_iter ii; + iov_iter_init(&ii, WRITE, &iov, 1, count); /* * No locking or generic_write_checks(), the server is * responsible for locking and sanity checks. */ - return fuse_direct_io(&io, &iov, 1, count, &pos, + return fuse_direct_io(&io, &ii, &pos, FUSE_DIO_WRITE | FUSE_DIO_CUSE); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 098f97bdcf1..ca887314aba 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -643,9 +643,8 @@ struct fuse_copy_state { unsigned long seglen; unsigned long addr; struct page *pg; - void *mapaddr; - void *buf; unsigned len; + unsigned offset; unsigned move_pages:1; }; @@ -666,23 +665,17 @@ static void fuse_copy_finish(struct fuse_copy_state *cs) if (cs->currbuf) { struct pipe_buffer *buf = cs->currbuf; - if (!cs->write) { - kunmap_atomic(cs->mapaddr); - } else { - kunmap_atomic(cs->mapaddr); + if (cs->write) buf->len = PAGE_SIZE - cs->len; - } cs->currbuf = NULL; - cs->mapaddr = NULL; - } else if (cs->mapaddr) { - kunmap_atomic(cs->mapaddr); + } else if (cs->pg) { if (cs->write) { flush_dcache_page(cs->pg); set_page_dirty_lock(cs->pg); } put_page(cs->pg); - cs->mapaddr = NULL; } + cs->pg = NULL; } /* @@ -691,7 +684,7 @@ static void fuse_copy_finish(struct fuse_copy_state *cs) */ static int fuse_copy_fill(struct fuse_copy_state *cs) { - unsigned long offset; + struct page *page; int err; unlock_request(cs->fc, cs->req); @@ -706,14 +699,12 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) BUG_ON(!cs->nr_segs); cs->currbuf = buf; - cs->mapaddr = kmap_atomic(buf->page); + cs->pg = buf->page; + cs->offset = buf->offset; cs->len = buf->len; - cs->buf = cs->mapaddr + buf->offset; cs->pipebufs++; cs->nr_segs--; } else { - struct page *page; - if (cs->nr_segs == cs->pipe->buffers) return -EIO; @@ -726,8 +717,8 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) buf->len = 0; cs->currbuf = buf; - cs->mapaddr = kmap_atomic(page); - cs->buf = cs->mapaddr; + cs->pg = page; + cs->offset = 0; cs->len = PAGE_SIZE; cs->pipebufs++; cs->nr_segs++; @@ -740,14 +731,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs) cs->iov++; cs->nr_segs--; } - err = get_user_pages_fast(cs->addr, 1, cs->write, &cs->pg); + err = get_user_pages_fast(cs->addr, 1, cs->write, &page); if (err < 0) return err; BUG_ON(err != 1); - offset = cs->addr % PAGE_SIZE; - cs->mapaddr = kmap_atomic(cs->pg); - cs->buf = cs->mapaddr + offset; - cs->len = min(PAGE_SIZE - offset, cs->seglen); + cs->pg = page; + cs->offset = cs->addr % PAGE_SIZE; + cs->len = min(PAGE_SIZE - cs->offset, cs->seglen); cs->seglen -= cs->len; cs->addr += cs->len; } @@ -760,15 +750,20 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) { unsigned ncpy = min(*size, cs->len); if (val) { + void *pgaddr = kmap_atomic(cs->pg); + void *buf = pgaddr + cs->offset; + if (cs->write) - memcpy(cs->buf, *val, ncpy); + memcpy(buf, *val, ncpy); else - memcpy(*val, cs->buf, ncpy); + memcpy(*val, buf, ncpy); + + kunmap_atomic(pgaddr); *val += ncpy; } *size -= ncpy; cs->len -= ncpy; - cs->buf += ncpy; + cs->offset += ncpy; return ncpy; } @@ -874,8 +869,8 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) out_fallback_unlock: unlock_page(newpage); out_fallback: - cs->mapaddr = kmap_atomic(buf->page); - cs->buf = cs->mapaddr + buf->offset; + cs->pg = buf->page; + cs->offset = buf->offset; err = lock_request(cs->fc, cs->req); if (err) diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 42198359fa1..0c6048247a3 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -198,7 +198,8 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) inode = ACCESS_ONCE(entry->d_inode); if (inode && is_bad_inode(inode)) goto invalid; - else if (fuse_dentry_time(entry) < get_jiffies_64()) { + else if (time_before64(fuse_dentry_time(entry), get_jiffies_64()) || + (flags & LOOKUP_REVAL)) { int err; struct fuse_entry_out outarg; struct fuse_req *req; @@ -814,13 +815,6 @@ static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, return err; } -static int fuse_rename(struct inode *olddir, struct dentry *oldent, - struct inode *newdir, struct dentry *newent) -{ - return fuse_rename_common(olddir, oldent, newdir, newent, 0, - FUSE_RENAME, sizeof(struct fuse_rename_in)); -} - static int fuse_rename2(struct inode *olddir, struct dentry *oldent, struct inode *newdir, struct dentry *newent, unsigned int flags) @@ -831,17 +825,30 @@ static int fuse_rename2(struct inode *olddir, struct dentry *oldent, if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) return -EINVAL; - if (fc->no_rename2 || fc->minor < 23) - return -EINVAL; + if (flags) { + if (fc->no_rename2 || fc->minor < 23) + return -EINVAL; - err = fuse_rename_common(olddir, oldent, newdir, newent, flags, - FUSE_RENAME2, sizeof(struct fuse_rename2_in)); - if (err == -ENOSYS) { - fc->no_rename2 = 1; - err = -EINVAL; + err = fuse_rename_common(olddir, oldent, newdir, newent, flags, + FUSE_RENAME2, + sizeof(struct fuse_rename2_in)); + if (err == -ENOSYS) { + fc->no_rename2 = 1; + err = -EINVAL; + } + } else { + err = fuse_rename_common(olddir, oldent, newdir, newent, 0, + FUSE_RENAME, + sizeof(struct fuse_rename_in)); } + return err; +} +static int fuse_rename(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent) +{ + return fuse_rename2(olddir, oldent, newdir, newent, 0); } static int fuse_link(struct dentry *entry, struct inode *newdir, @@ -985,7 +992,7 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, int err; bool r; - if (fi->i_time < get_jiffies_64()) { + if (time_before64(fi->i_time, get_jiffies_64())) { r = true; err = fuse_do_getattr(inode, stat, file); } else { @@ -1171,7 +1178,7 @@ static int fuse_permission(struct inode *inode, int mask) ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { struct fuse_inode *fi = get_fuse_inode(inode); - if (fi->i_time < get_jiffies_64()) { + if (time_before64(fi->i_time, get_jiffies_64())) { refreshed = true; err = fuse_perm_getattr(inode, mask); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 903cbc9cd6b..40ac2628ddc 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -933,8 +933,7 @@ out: return err; } -static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = iocb->ki_filp->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); @@ -945,14 +944,14 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, * i_size is up to date). */ if (fc->auto_inval_data || - (pos + iov_length(iov, nr_segs) > i_size_read(inode))) { + (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) { int err; err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); if (err) return err; } - return generic_file_aio_read(iocb, iov, nr_segs, pos); + return generic_file_read_iter(iocb, to); } static void fuse_write_fill(struct fuse_req *req, struct fuse_file *ff, @@ -1181,19 +1180,17 @@ static ssize_t fuse_perform_write(struct file *file, return res > 0 ? res : err; } -static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - size_t count = 0; - size_t ocount = 0; + size_t count = iov_iter_count(from); ssize_t written = 0; ssize_t written_buffered = 0; struct inode *inode = mapping->host; ssize_t err; - struct iov_iter i; loff_t endbyte = 0; + loff_t pos = iocb->ki_pos; if (get_fuse_conn(inode)->writeback_cache) { /* Update size (EOF optimization) and mode (SUID clearing) */ @@ -1201,17 +1198,9 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err) return err; - return generic_file_aio_write(iocb, iov, nr_segs, pos); + return generic_file_write_iter(iocb, from); } - WARN_ON(iocb->ki_pos != pos); - - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ @@ -1224,6 +1213,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(from, count); err = file_remove_suid(file); if (err) goto out; @@ -1233,16 +1223,13 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, goto out; if (file->f_flags & O_DIRECT) { - written = generic_file_direct_write(iocb, iov, &nr_segs, pos, - count, ocount); - if (written < 0 || written == count) + written = generic_file_direct_write(iocb, from, pos); + if (written < 0 || !iov_iter_count(from)) goto out; pos += written; - count -= written; - iov_iter_init(&i, iov, nr_segs, count, written); - written_buffered = fuse_perform_write(file, mapping, &i, pos); + written_buffered = fuse_perform_write(file, mapping, from, pos); if (written_buffered < 0) { err = written_buffered; goto out; @@ -1261,8 +1248,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, written += written_buffered; iocb->ki_pos = pos + written_buffered; } else { - iov_iter_init(&i, iov, nr_segs, count, 0); - written = fuse_perform_write(file, mapping, &i, pos); + written = fuse_perform_write(file, mapping, from, pos); if (written >= 0) iocb->ki_pos = pos + written; } @@ -1300,7 +1286,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, size_t nbytes = 0; /* # bytes already packed in req */ /* Special case for kernel I/O: can copy directly into the buffer */ - if (segment_eq(get_fs(), KERNEL_DS)) { + if (ii->type & ITER_KVEC) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); @@ -1316,35 +1302,26 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, while (nbytes < *nbytesp && req->num_pages < req->max_pages) { unsigned npages; - unsigned long user_addr = fuse_get_user_addr(ii); - unsigned offset = user_addr & ~PAGE_MASK; - size_t frag_size = fuse_get_frag_size(ii, *nbytesp - nbytes); - int ret; - + size_t start; unsigned n = req->max_pages - req->num_pages; - frag_size = min_t(size_t, frag_size, n << PAGE_SHIFT); - - npages = (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; - npages = clamp(npages, 1U, n); - - ret = get_user_pages_fast(user_addr, npages, !write, - &req->pages[req->num_pages]); + ssize_t ret = iov_iter_get_pages(ii, + &req->pages[req->num_pages], + n * PAGE_SIZE, &start); if (ret < 0) return ret; - npages = ret; - frag_size = min_t(size_t, frag_size, - (npages << PAGE_SHIFT) - offset); - iov_iter_advance(ii, frag_size); + iov_iter_advance(ii, ret); + nbytes += ret; + + ret += start; + npages = (ret + PAGE_SIZE - 1) / PAGE_SIZE; - req->page_descs[req->num_pages].offset = offset; + req->page_descs[req->num_pages].offset = start; fuse_page_descs_length_init(req, req->num_pages, npages); req->num_pages += npages; req->page_descs[req->num_pages - 1].length -= - (npages << PAGE_SHIFT) - offset - frag_size; - - nbytes += frag_size; + (PAGE_SIZE - ret) & (PAGE_SIZE - 1); } if (write) @@ -1359,24 +1336,11 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, static inline int fuse_iter_npages(const struct iov_iter *ii_p) { - struct iov_iter ii = *ii_p; - int npages = 0; - - while (iov_iter_count(&ii) && npages < FUSE_MAX_PAGES_PER_REQ) { - unsigned long user_addr = fuse_get_user_addr(&ii); - unsigned offset = user_addr & ~PAGE_MASK; - size_t frag_size = iov_iter_single_seg_count(&ii); - - npages += (frag_size + offset + PAGE_SIZE - 1) >> PAGE_SHIFT; - iov_iter_advance(&ii, frag_size); - } - - return min(npages, FUSE_MAX_PAGES_PER_REQ); + return iov_iter_npages(ii_p, FUSE_MAX_PAGES_PER_REQ); } -ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, - unsigned long nr_segs, size_t count, loff_t *ppos, - int flags) +ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, + loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; int cuse = flags & FUSE_DIO_CUSE; @@ -1386,18 +1350,16 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, struct fuse_conn *fc = ff->fc; size_t nmax = write ? fc->max_write : fc->max_read; loff_t pos = *ppos; + size_t count = iov_iter_count(iter); pgoff_t idx_from = pos >> PAGE_CACHE_SHIFT; pgoff_t idx_to = (pos + count - 1) >> PAGE_CACHE_SHIFT; ssize_t res = 0; struct fuse_req *req; - struct iov_iter ii; - - iov_iter_init(&ii, iov, nr_segs, count, 0); if (io->async) - req = fuse_get_req_for_background(fc, fuse_iter_npages(&ii)); + req = fuse_get_req_for_background(fc, fuse_iter_npages(iter)); else - req = fuse_get_req(fc, fuse_iter_npages(&ii)); + req = fuse_get_req(fc, fuse_iter_npages(iter)); if (IS_ERR(req)) return PTR_ERR(req); @@ -1413,7 +1375,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, size_t nres; fl_owner_t owner = current->files; size_t nbytes = min(count, nmax); - int err = fuse_get_user_pages(req, &ii, &nbytes, write); + int err = fuse_get_user_pages(req, iter, &nbytes, write); if (err) { res = err; break; @@ -1443,9 +1405,9 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, fuse_put_request(fc, req); if (io->async) req = fuse_get_req_for_background(fc, - fuse_iter_npages(&ii)); + fuse_iter_npages(iter)); else - req = fuse_get_req(fc, fuse_iter_npages(&ii)); + req = fuse_get_req(fc, fuse_iter_npages(iter)); if (IS_ERR(req)) break; } @@ -1460,9 +1422,8 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, EXPORT_SYMBOL_GPL(fuse_direct_io); static ssize_t __fuse_direct_read(struct fuse_io_priv *io, - const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos, - size_t count) + struct iov_iter *iter, + loff_t *ppos) { ssize_t res; struct file *file = io->file; @@ -1471,7 +1432,7 @@ static ssize_t __fuse_direct_read(struct fuse_io_priv *io, if (is_bad_inode(inode)) return -EIO; - res = fuse_direct_io(io, iov, nr_segs, count, ppos, 0); + res = fuse_direct_io(io, iter, ppos, 0); fuse_invalidate_attr(inode); @@ -1483,22 +1444,26 @@ static ssize_t fuse_direct_read(struct file *file, char __user *buf, { struct fuse_io_priv io = { .async = 0, .file = file }; struct iovec iov = { .iov_base = buf, .iov_len = count }; - return __fuse_direct_read(&io, &iov, 1, ppos, count); + struct iov_iter ii; + iov_iter_init(&ii, READ, &iov, 1, count); + return __fuse_direct_read(&io, &ii, ppos); } static ssize_t __fuse_direct_write(struct fuse_io_priv *io, - const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) + struct iov_iter *iter, + loff_t *ppos) { struct file *file = io->file; struct inode *inode = file_inode(file); - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); ssize_t res; + res = generic_write_checks(file, ppos, &count, 0); - if (!res) - res = fuse_direct_io(io, iov, nr_segs, count, ppos, - FUSE_DIO_WRITE); + if (!res) { + iov_iter_truncate(iter, count); + res = fuse_direct_io(io, iter, ppos, FUSE_DIO_WRITE); + } fuse_invalidate_attr(inode); @@ -1512,13 +1477,15 @@ static ssize_t fuse_direct_write(struct file *file, const char __user *buf, struct inode *inode = file_inode(file); ssize_t res; struct fuse_io_priv io = { .async = 0, .file = file }; + struct iov_iter ii; + iov_iter_init(&ii, WRITE, &iov, 1, count); if (is_bad_inode(inode)) return -EIO; /* Don't allow parallel writes to the same file */ mutex_lock(&inode->i_mutex); - res = __fuse_direct_write(&io, &iov, 1, ppos); + res = __fuse_direct_write(&io, &ii, ppos); if (res > 0) fuse_write_update_size(inode, *ppos); mutex_unlock(&inode->i_mutex); @@ -1720,7 +1687,7 @@ static int fuse_writepage_locked(struct page *page) error = -EIO; req->ff = fuse_write_file_get(fc, fi); if (!req->ff) - goto err_free; + goto err_nofile; fuse_write_fill(req, req->ff, page_offset(page), 0); @@ -1748,6 +1715,8 @@ static int fuse_writepage_locked(struct page *page) return 0; +err_nofile: + __free_page(tmp_page); err_free: fuse_request_free(req); err: @@ -1988,8 +1957,8 @@ static int fuse_writepages(struct address_space *mapping, data.ff = NULL; err = -ENOMEM; - data.orig_pages = kzalloc(sizeof(struct page *) * - FUSE_MAX_PAGES_PER_REQ, + data.orig_pages = kcalloc(FUSE_MAX_PAGES_PER_REQ, + sizeof(struct page *), GFP_NOFS); if (!data.orig_pages) goto out; @@ -2372,7 +2341,7 @@ static int fuse_ioctl_copy_user(struct page **pages, struct iovec *iov, if (!bytes) return 0; - iov_iter_init(&ii, iov, nr_segs, bytes, 0); + iov_iter_init(&ii, to_user ? READ : WRITE, iov, nr_segs, bytes); while (iov_iter_count(&ii)) { struct page *page = pages[page_idx++]; @@ -2894,8 +2863,8 @@ static inline loff_t fuse_round_up(loff_t off) } static ssize_t -fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +fuse_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { ssize_t ret = 0; struct file *file = iocb->ki_filp; @@ -2904,7 +2873,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); struct fuse_io_priv *io; pos = offset; @@ -2919,6 +2888,7 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, if (offset >= i_size) return 0; count = min_t(loff_t, count, fuse_round_up(i_size - offset)); + iov_iter_truncate(iter, count); } io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); @@ -2948,9 +2918,9 @@ fuse_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, io->async = false; if (rw == WRITE) - ret = __fuse_direct_write(io, iov, nr_segs, &pos); + ret = __fuse_direct_write(io, iter, &pos); else - ret = __fuse_direct_read(io, iov, nr_segs, &pos, count); + ret = __fuse_direct_read(io, iter, &pos); if (io->async) { fuse_aio_complete(io, ret < 0 ? ret : 0, -1); @@ -3061,10 +3031,10 @@ out: static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, - .read = do_sync_read, - .aio_read = fuse_file_aio_read, - .write = do_sync_write, - .aio_write = fuse_file_aio_write, + .read = new_sync_read, + .read_iter = fuse_file_read_iter, + .write = new_sync_write, + .write_iter = fuse_file_write_iter, .mmap = fuse_file_mmap, .open = fuse_open, .flush = fuse_flush, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 7aa5c75e0de..e8e47a6ab51 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -880,9 +880,8 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file, /** CUSE pass fuse_direct_io() a file which f_mapping->host is not from FUSE */ #define FUSE_DIO_CUSE (1 << 1) -ssize_t fuse_direct_io(struct fuse_io_priv *io, const struct iovec *iov, - unsigned long nr_segs, size_t count, loff_t *ppos, - int flags); +ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, + loff_t *ppos, int flags); long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, unsigned int flags); long fuse_ioctl_common(struct file *file, unsigned int cmd, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 754dcf23de8..03246cd9d47 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -478,6 +478,17 @@ static const match_table_t tokens = { {OPT_ERR, NULL} }; +static int fuse_match_uint(substring_t *s, unsigned int *res) +{ + int err = -ENOMEM; + char *buf = match_strdup(s); + if (buf) { + err = kstrtouint(buf, 10, res); + kfree(buf); + } + return err; +} + static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) { char *p; @@ -488,6 +499,7 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) while ((p = strsep(&opt, ",")) != NULL) { int token; int value; + unsigned uv; substring_t args[MAX_OPT_ARGS]; if (!*p) continue; @@ -511,18 +523,18 @@ static int parse_fuse_opt(char *opt, struct fuse_mount_data *d, int is_bdev) break; case OPT_USER_ID: - if (match_int(&args[0], &value)) + if (fuse_match_uint(&args[0], &uv)) return 0; - d->user_id = make_kuid(current_user_ns(), value); + d->user_id = make_kuid(current_user_ns(), uv); if (!uid_valid(d->user_id)) return 0; d->user_id_present = 1; break; case OPT_GROUP_ID: - if (match_int(&args[0], &value)) + if (fuse_match_uint(&args[0], &uv)) return 0; - d->group_id = make_kgid(current_user_ns(), value); + d->group_id = make_kgid(current_user_ns(), uv); if (!gid_valid(d->group_id)) return 0; d->group_id_present = 1; @@ -895,9 +907,6 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->writeback_cache = 1; if (arg->time_gran && arg->time_gran <= 1000000000) fc->sb->s_time_gran = arg->time_gran; - else - fc->sb->s_time_gran = 1000000000; - } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -926,7 +935,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA | FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO | - FUSE_WRITEBACK_CACHE; + FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); @@ -1006,7 +1015,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION); - if (!parse_fuse_opt((char *) data, &d, is_bdev)) + if (!parse_fuse_opt(data, &d, is_bdev)) goto err; if (is_bdev) { diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 492123cda64..805b37fed63 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1040,8 +1040,7 @@ static int gfs2_ok_for_dio(struct gfs2_inode *ip, int rw, loff_t offset) static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; @@ -1081,7 +1080,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, */ if (mapping->nrpages) { loff_t lstart = offset & (PAGE_CACHE_SIZE - 1); - loff_t len = iov_length(iov, nr_segs); + loff_t len = iov_iter_count(iter); loff_t end = PAGE_ALIGN(offset + len) - 1; rv = 0; @@ -1096,9 +1095,9 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb, truncate_inode_pages_range(mapping, lstart, end); } - rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, gfs2_get_block_direct, - NULL, NULL, 0); + rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, + iter, offset, + gfs2_get_block_direct, NULL, NULL, 0); out: gfs2_glock_dq(&gh); gfs2_holder_uninit(&gh); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 6ab0cfb2e89..26b3f952e6b 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -684,7 +684,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, } /** - * gfs2_file_aio_write - Perform a write to a file + * gfs2_file_write_iter - Perform a write to a file * @iocb: The io context * @iov: The data to write * @nr_segs: Number of @iov segments @@ -697,11 +697,9 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end, * */ -static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; - size_t writesize = iov_length(iov, nr_segs); struct gfs2_inode *ip = GFS2_I(file_inode(file)); int ret; @@ -709,7 +707,7 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (ret) return ret; - gfs2_size_hint(file, pos, writesize); + gfs2_size_hint(file, iocb->ki_pos, iov_iter_count(from)); if (file->f_flags & O_APPEND) { struct gfs2_holder gh; @@ -720,7 +718,7 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, gfs2_glock_dq_uninit(&gh); } - return generic_file_aio_write(iocb, iov, nr_segs, pos); + return generic_file_write_iter(iocb, from); } static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len, @@ -983,7 +981,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) int error = 0; state = (fl->fl_type == F_WRLCK) ? LM_ST_EXCLUSIVE : LM_ST_SHARED; - flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT | GL_NOCACHE; + flags = (IS_SETLKW(cmd) ? 0 : LM_FLAG_TRY) | GL_EXACT; mutex_lock(&fp->f_fl_mutex); @@ -993,7 +991,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl) goto out; flock_lock_file_wait(file, &(struct file_lock){.fl_type = F_UNLCK}); - gfs2_glock_dq_wait(fl_gh); + gfs2_glock_dq(fl_gh); gfs2_holder_reinit(state, flags, fl_gh); } else { error = gfs2_glock_get(GFS2_SB(&ip->i_inode), ip->i_no_addr, @@ -1058,10 +1056,10 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl) const struct file_operations gfs2_file_fops = { .llseek = gfs2_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = gfs2_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = gfs2_file_write_iter, .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, @@ -1070,7 +1068,7 @@ const struct file_operations gfs2_file_fops = { .lock = gfs2_lock, .flock = gfs2_flock, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .setlease = gfs2_setlease, .fallocate = gfs2_fallocate, }; @@ -1090,17 +1088,17 @@ const struct file_operations gfs2_dir_fops = { const struct file_operations gfs2_file_fops_nolock = { .llseek = gfs2_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = gfs2_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = gfs2_file_write_iter, .unlocked_ioctl = gfs2_ioctl, .mmap = gfs2_mmap, .open = gfs2_open, .release = gfs2_release, .fsync = gfs2_fsync, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .setlease = generic_setlease, .fallocate = gfs2_fallocate, }; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index c355f7320e4..ee4e04fe60f 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -731,14 +731,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, cachep = gfs2_glock_aspace_cachep; else cachep = gfs2_glock_cachep; - gl = kmem_cache_alloc(cachep, GFP_KERNEL); + gl = kmem_cache_alloc(cachep, GFP_NOFS); if (!gl) return -ENOMEM; memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb)); if (glops->go_flags & GLOF_LVB) { - gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_KERNEL); + gl->gl_lksb.sb_lvbptr = kzalloc(GFS2_MIN_LVB_SIZE, GFP_NOFS); if (!gl->gl_lksb.sb_lvbptr) { kmem_cache_free(cachep, gl); return -ENOMEM; @@ -1404,12 +1404,16 @@ __acquires(&lru_lock) gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); if (!spin_trylock(&gl->gl_spin)) { +add_back_to_lru: list_add(&gl->gl_lru, &lru_list); atomic_inc(&lru_count); continue; } + if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + spin_unlock(&gl->gl_spin); + goto add_back_to_lru; + } clear_bit(GLF_LRU, &gl->gl_flags); - spin_unlock(&lru_lock); gl->gl_lockref.count++; if (demote_ok(gl)) handle_callback(gl, LM_ST_UNLOCKED, 0, false); @@ -1417,7 +1421,7 @@ __acquires(&lru_lock) if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) gl->gl_lockref.count--; spin_unlock(&gl->gl_spin); - spin_lock(&lru_lock); + cond_resched_lock(&lru_lock); } } @@ -1442,7 +1446,7 @@ static long gfs2_scan_glock_lru(int nr) gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru); /* Test for being demotable */ - if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) { + if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); freed++; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index fc1100781bb..2ffc67dce87 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -234,8 +234,8 @@ static void inode_go_sync(struct gfs2_glock *gl) * inode_go_inval - prepare a inode glock to be released * @gl: the glock * @flags: - * - * Normally we invlidate everything, but if we are moving into + * + * Normally we invalidate everything, but if we are moving into * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we * can keep hold of the metadata, since it won't have changed. * diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 91f274de124..4fafea1c9ec 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -1036,8 +1036,8 @@ static int set_recover_size(struct gfs2_sbd *sdp, struct dlm_slot *slots, new_size = old_size + RECOVER_SIZE_INC; - submit = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS); - result = kzalloc(new_size * sizeof(uint32_t), GFP_NOFS); + submit = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS); + result = kcalloc(new_size, sizeof(uint32_t), GFP_NOFS); if (!submit || !result) { kfree(submit); kfree(result); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index db629d1bd1b..f4cb9c0d6bb 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -337,7 +337,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le /** * gfs2_free_extlen - Return extent length of free blocks - * @rbm: Starting position + * @rrbm: Starting position * @len: Max length to check * * Starting at the block specified by the rbm, see how many free blocks @@ -2522,7 +2522,7 @@ void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state) /** * gfs2_rlist_free - free a resource group list - * @list: the list of resource groups + * @rlist: the list of resource groups * */ diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9e2fecd62f6..d0929bc8178 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -125,15 +125,15 @@ static int hfs_releasepage(struct page *page, gfp_t mask) } static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - hfs_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfs_get_block); /* * In case of error extending write may have instantiated a few @@ -141,7 +141,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) hfs_write_failed(mapping, end); @@ -674,10 +674,10 @@ static int hfs_file_fsync(struct file *filp, loff_t start, loff_t end, static const struct file_operations hfs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, .fsync = hfs_file_fsync, diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index a4f45bd88a6..0cf786f2d04 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -123,14 +123,15 @@ static int hfsplus_releasepage(struct page *page, gfp_t mask) } static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file_inode(file)->i_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, hfsplus_get_block); /* @@ -139,7 +140,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) hfsplus_write_failed(mapping, end); @@ -340,10 +341,10 @@ static const struct inode_operations hfsplus_file_inode_operations = { static const struct file_operations hfsplus_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, .fsync = hfsplus_file_fsync, diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 9c470fde987..bb529f3b7f2 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -378,11 +378,11 @@ static int hostfs_fsync(struct file *file, loff_t start, loff_t end, static const struct file_operations hostfs_file_fops = { .llseek = generic_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .splice_read = generic_file_splice_read, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, - .write = do_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .write = new_sync_write, .mmap = generic_file_mmap, .open = hostfs_file_open, .release = hostfs_file_release, diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 67c1a61e095..7f54e5f76ce 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -197,10 +197,10 @@ const struct address_space_operations hpfs_aops = { const struct file_operations hpfs_file_ops = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = hpfs_file_release, .fsync = hpfs_file_fsync, diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 38cfcf5f6fc..6f0f590cc5a 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1588,9 +1588,12 @@ int jbd2_journal_stop(handle_t *handle) * to perform a synchronous write. We do this to detect the * case where a single process is doing a stream of sync * writes. No point in waiting for joiners in that case. + * + * Setting max_batch_time to 0 disables this completely. */ pid = current->pid; - if (handle->h_sync && journal->j_last_sync_writer != pid) { + if (handle->h_sync && journal->j_last_sync_writer != pid && + journal->j_max_batch_time) { u64 commit_time, trans_time; journal->j_last_sync_writer = pid; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 256cd19a3b7..64989ca9ba9 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -51,10 +51,10 @@ const struct file_operations jffs2_file_operations = { .llseek = generic_file_llseek, .open = generic_file_open, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .unlocked_ioctl=jffs2_ioctl, .mmap = generic_file_readonly_mmap, .fsync = jffs2_fsync, diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 794da944d5c..33aa0cc1f8b 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -151,13 +151,13 @@ const struct inode_operations jfs_file_inode_operations = { const struct file_operations jfs_file_operations = { .open = jfs_open, .llseek = generic_file_llseek, - .write = do_sync_write, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .write = new_sync_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .fsync = jfs_fsync, .release = jfs_release, .unlocked_ioctl = jfs_ioctl, diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 6f8fe72c2a7..bd3df1ca3c9 100644 --- a/fs/jfs/inode.c +++ b/fs/jfs/inode.c @@ -331,15 +331,15 @@ static sector_t jfs_bmap(struct address_space *mapping, sector_t block) } static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - jfs_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, jfs_get_block); /* * In case of error extending write may have instantiated a few @@ -347,7 +347,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) jfs_write_failed(mapping, end); diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index e3d37f607f9..d895b4b7b66 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -39,6 +39,19 @@ struct kernfs_open_node { struct list_head files; /* goes through kernfs_open_file.list */ }; +/* + * kernfs_notify() may be called from any context and bounces notifications + * through a work item. To minimize space overhead in kernfs_node, the + * pending queue is implemented as a singly linked list of kernfs_nodes. + * The list is terminated with the self pointer so that whether a + * kernfs_node is on the list or not can be determined by testing the next + * pointer for NULL. + */ +#define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) + +static DEFINE_SPINLOCK(kernfs_notify_lock); +static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; + static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; @@ -783,24 +796,25 @@ static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait) return DEFAULT_POLLMASK|POLLERR|POLLPRI; } -/** - * kernfs_notify - notify a kernfs file - * @kn: file to notify - * - * Notify @kn such that poll(2) on @kn wakes up. - */ -void kernfs_notify(struct kernfs_node *kn) +static void kernfs_notify_workfn(struct work_struct *work) { - struct kernfs_root *root = kernfs_root(kn); + struct kernfs_node *kn; struct kernfs_open_node *on; struct kernfs_super_info *info; - unsigned long flags; - - if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) +repeat: + /* pop one off the notify_list */ + spin_lock_irq(&kernfs_notify_lock); + kn = kernfs_notify_list; + if (kn == KERNFS_NOTIFY_EOL) { + spin_unlock_irq(&kernfs_notify_lock); return; + } + kernfs_notify_list = kn->attr.notify_next; + kn->attr.notify_next = NULL; + spin_unlock_irq(&kernfs_notify_lock); /* kick poll */ - spin_lock_irqsave(&kernfs_open_node_lock, flags); + spin_lock_irq(&kernfs_open_node_lock); on = kn->attr.open; if (on) { @@ -808,12 +822,12 @@ void kernfs_notify(struct kernfs_node *kn) wake_up_interruptible(&on->poll); } - spin_unlock_irqrestore(&kernfs_open_node_lock, flags); + spin_unlock_irq(&kernfs_open_node_lock); /* kick fsnotify */ mutex_lock(&kernfs_mutex); - list_for_each_entry(info, &root->supers, node) { + list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct inode *inode; struct dentry *dentry; @@ -833,6 +847,33 @@ void kernfs_notify(struct kernfs_node *kn) } mutex_unlock(&kernfs_mutex); + kernfs_put(kn); + goto repeat; +} + +/** + * kernfs_notify - notify a kernfs file + * @kn: file to notify + * + * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any + * context. + */ +void kernfs_notify(struct kernfs_node *kn) +{ + static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); + unsigned long flags; + + if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) + return; + + spin_lock_irqsave(&kernfs_notify_lock, flags); + if (!kn->attr.notify_next) { + kernfs_get(kn); + kn->attr.notify_next = kernfs_notify_list; + kernfs_notify_list = kn; + schedule_work(&kernfs_notify_work); + } + spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index d171b98a6cd..f973ae9b05f 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -211,6 +211,36 @@ void kernfs_kill_sb(struct super_block *sb) kernfs_put(root_kn); } +/** + * kernfs_pin_sb: try to pin the superblock associated with a kernfs_root + * @kernfs_root: the kernfs_root in question + * @ns: the namespace tag + * + * Pin the superblock so the superblock won't be destroyed in subsequent + * operations. This can be used to block ->kill_sb() which may be useful + * for kernfs users which dynamically manage superblocks. + * + * Returns NULL if there's no superblock associated to this kernfs_root, or + * -EINVAL if the superblock is being freed. + */ +struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns) +{ + struct kernfs_super_info *info; + struct super_block *sb = NULL; + + mutex_lock(&kernfs_mutex); + list_for_each_entry(info, &root->supers, node) { + if (info->ns == ns) { + sb = info->sb; + if (!atomic_inc_not_zero(&info->sb->s_active)) + sb = ERR_PTR(-EINVAL); + break; + } + } + mutex_unlock(&kernfs_mutex); + return sb; +} + void __init kernfs_init(void) { kernfs_node_cache = kmem_cache_create("kernfs_node_cache", diff --git a/fs/locks.c b/fs/locks.c index da57c9b7e84..717fbc404e6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -431,7 +431,7 @@ static int lease_init(struct file *filp, long type, struct file_lock *fl) if (assign_type(fl, type) != 0) return -EINVAL; - fl->fl_owner = (fl_owner_t)filp; + fl->fl_owner = (fl_owner_t)current->files; fl->fl_pid = current->tgid; fl->fl_file = filp; diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 57914fc32b6..8538752df2f 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -264,15 +264,15 @@ const struct inode_operations logfs_reg_iops = { }; const struct file_operations logfs_reg_fops = { - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .fsync = logfs_fsync, .unlocked_ioctl = logfs_ioctl, .llseek = generic_file_llseek, .mmap = generic_file_readonly_mmap, .open = generic_file_open, - .read = do_sync_read, - .write = do_sync_write, + .read = new_sync_read, + .write = new_sync_write, }; const struct address_space_operations logfs_reg_aops = { diff --git a/fs/mbcache.c b/fs/mbcache.c index bf166e388f0..187477ded6b 100644 --- a/fs/mbcache.c +++ b/fs/mbcache.c @@ -73,6 +73,7 @@ #include <linux/mbcache.h> #include <linux/init.h> #include <linux/blockgroup_lock.h> +#include <linux/log2.h> #ifdef MB_CACHE_DEBUG # define mb_debug(f...) do { \ @@ -93,7 +94,7 @@ #define MB_CACHE_WRITER ((unsigned short)~0U >> 1) -#define MB_CACHE_ENTRY_LOCK_BITS __builtin_log2(NR_BG_LOCKS) +#define MB_CACHE_ENTRY_LOCK_BITS ilog2(NR_BG_LOCKS) #define MB_CACHE_ENTRY_LOCK_INDEX(ce) \ (hash_long((unsigned long)ce, MB_CACHE_ENTRY_LOCK_BITS)) diff --git a/fs/minix/file.c b/fs/minix/file.c index adc6f549423..a967de085ac 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -14,10 +14,10 @@ */ const struct file_operations minix_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/namei.c b/fs/namei.c index 985c6f36848..9eb787e5c16 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2256,9 +2256,10 @@ done: goto out; } path->dentry = dentry; - path->mnt = mntget(nd->path.mnt); + path->mnt = nd->path.mnt; if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW)) return 1; + mntget(path->mnt); follow_mount(path); error = 0; out: diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4ad7bc38867..f11b9eed0de 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -212,20 +212,20 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq, * shunt off direct read and write requests before the VFS gets them, * so this method is only ever called for swap. */ -ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) +ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, loff_t pos) { #ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%pD) off/no(%Ld/%lu) EINVAL\n", - iocb->ki_filp, (long long) pos, nr_segs); + iocb->ki_filp, (long long) pos, iter->nr_segs); return -EINVAL; #else VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); if (rw == READ || rw == KERNEL_READ) - return nfs_file_direct_read(iocb, iov, nr_segs, pos, + return nfs_file_direct_read(iocb, iter, pos, rw == READ ? true : false); - return nfs_file_direct_write(iocb, iov, nr_segs, pos, + return nfs_file_direct_write(iocb, iter, pos, rw == WRITE ? true : false); #endif /* CONFIG_NFS_SWAP */ } @@ -414,60 +414,37 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { * handled automatically by nfs_direct_read_result(). Otherwise, if * no requests have been sent, just return an error. */ -static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, - const struct iovec *iov, - loff_t pos, bool uio) -{ - struct nfs_direct_req *dreq = desc->pg_dreq; - struct nfs_open_context *ctx = dreq->ctx; - struct inode *inode = ctx->dentry->d_inode; - unsigned long user_addr = (unsigned long)iov->iov_base; - size_t count = iov->iov_len; - size_t rsize = NFS_SERVER(inode)->rsize; - unsigned int pgbase; - int result; - ssize_t started = 0; - struct page **pagevec = NULL; - unsigned int npages; - - do { - size_t bytes; - int i; - pgbase = user_addr & ~PAGE_MASK; - bytes = min(max_t(size_t, rsize, PAGE_SIZE), count); +static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, + struct iov_iter *iter, + loff_t pos) +{ + struct nfs_pageio_descriptor desc; + struct inode *inode = dreq->inode; + ssize_t result = -EINVAL; + size_t requested_bytes = 0; + size_t rsize = max_t(size_t, NFS_SERVER(inode)->rsize, PAGE_SIZE); - result = -ENOMEM; - npages = nfs_page_array_len(pgbase, bytes); - if (!pagevec) - pagevec = kmalloc(npages * sizeof(struct page *), - GFP_KERNEL); - if (!pagevec) - break; - if (uio) { - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, - npages, 1, 0, pagevec, NULL); - up_read(¤t->mm->mmap_sem); - if (result < 0) - break; - } else { - WARN_ON(npages != 1); - result = get_kernel_page(user_addr, 1, pagevec); - if (WARN_ON(result != 1)) - break; - } + nfs_pageio_init_read(&desc, dreq->inode, false, + &nfs_direct_read_completion_ops); + get_dreq(dreq); + desc.pg_dreq = dreq; + atomic_inc(&inode->i_dio_count); - if ((unsigned)result < npages) { - bytes = result * PAGE_SIZE; - if (bytes <= pgbase) { - nfs_direct_release_pages(pagevec, result); - break; - } - bytes -= pgbase; - npages = result; - } + while (iov_iter_count(iter)) { + struct page **pagevec; + size_t bytes; + size_t pgbase; + unsigned npages, i; + result = iov_iter_get_pages_alloc(iter, &pagevec, + rsize, &pgbase); + if (result < 0) + break; + + bytes = result; + iov_iter_advance(iter, bytes); + npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; for (i = 0; i < npages; i++) { struct nfs_page *req; unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); @@ -480,56 +457,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de } req->wb_index = pos >> PAGE_SHIFT; req->wb_offset = pos & ~PAGE_MASK; - if (!nfs_pageio_add_request(desc, req)) { - result = desc->pg_error; + if (!nfs_pageio_add_request(&desc, req)) { + result = desc.pg_error; nfs_release_request(req); break; } pgbase = 0; bytes -= req_len; - started += req_len; - user_addr += req_len; + requested_bytes += req_len; pos += req_len; - count -= req_len; dreq->bytes_left -= req_len; } - /* The nfs_page now hold references to these pages */ nfs_direct_release_pages(pagevec, npages); - } while (count != 0 && result >= 0); - - kfree(pagevec); - - if (started) - return started; - return result < 0 ? (ssize_t) result : -EFAULT; -} - -static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, - const struct iovec *iov, - unsigned long nr_segs, - loff_t pos, bool uio) -{ - struct nfs_pageio_descriptor desc; - struct inode *inode = dreq->inode; - ssize_t result = -EINVAL; - size_t requested_bytes = 0; - unsigned long seg; - - nfs_pageio_init_read(&desc, dreq->inode, false, - &nfs_direct_read_completion_ops); - get_dreq(dreq); - desc.pg_dreq = dreq; - atomic_inc(&inode->i_dio_count); - - for (seg = 0; seg < nr_segs; seg++) { - const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio); + kvfree(pagevec); if (result < 0) break; - requested_bytes += result; - if ((size_t)result < vec->iov_len) - break; - pos += vec->iov_len; } nfs_pageio_complete(&desc); @@ -552,8 +494,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, /** * nfs_file_direct_read - file direct read operation for NFS files * @iocb: target I/O control block - * @iov: vector of user buffers into which to read data - * @nr_segs: size of iov vector + * @iter: vector of user buffers into which to read data * @pos: byte offset in file where reading starts * * We use this function for direct reads instead of calling @@ -570,8 +511,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, * client must read the updated atime from the server back into its * cache. */ -ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) +ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, + loff_t pos, bool uio) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -579,9 +520,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; ssize_t result = -EINVAL; - size_t count; - - count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count); dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n", @@ -604,7 +543,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, goto out_unlock; dreq->inode = inode; - dreq->bytes_left = iov_length(iov, nr_segs); + dreq->bytes_left = count; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); l_ctx = nfs_get_lock_context(dreq->ctx); if (IS_ERR(l_ctx)) { @@ -615,8 +554,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - NFS_I(inode)->read_io += iov_length(iov, nr_segs); - result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio); + NFS_I(inode)->read_io += count; + result = nfs_direct_read_schedule_iovec(dreq, iter, pos); mutex_unlock(&inode->i_mutex); @@ -772,108 +711,6 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode } #endif -/* - * NB: Return the value of the first error return code. Subsequent - * errors after the first one are ignored. - */ -/* - * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE - * operation. If nfs_writedata_alloc() or get_user_pages() fails, - * bail and stop sending more writes. Write length accounting is - * handled automatically by nfs_direct_write_result(). Otherwise, if - * no requests have been sent, just return an error. - */ -static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc, - const struct iovec *iov, - loff_t pos, bool uio) -{ - struct nfs_direct_req *dreq = desc->pg_dreq; - struct nfs_open_context *ctx = dreq->ctx; - struct inode *inode = ctx->dentry->d_inode; - unsigned long user_addr = (unsigned long)iov->iov_base; - size_t count = iov->iov_len; - size_t wsize = NFS_SERVER(inode)->wsize; - unsigned int pgbase; - int result; - ssize_t started = 0; - struct page **pagevec = NULL; - unsigned int npages; - - do { - size_t bytes; - int i; - - pgbase = user_addr & ~PAGE_MASK; - bytes = min(max_t(size_t, wsize, PAGE_SIZE), count); - - result = -ENOMEM; - npages = nfs_page_array_len(pgbase, bytes); - if (!pagevec) - pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL); - if (!pagevec) - break; - - if (uio) { - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, - npages, 0, 0, pagevec, NULL); - up_read(¤t->mm->mmap_sem); - if (result < 0) - break; - } else { - WARN_ON(npages != 1); - result = get_kernel_page(user_addr, 0, pagevec); - if (WARN_ON(result != 1)) - break; - } - - if ((unsigned)result < npages) { - bytes = result * PAGE_SIZE; - if (bytes <= pgbase) { - nfs_direct_release_pages(pagevec, result); - break; - } - bytes -= pgbase; - npages = result; - } - - for (i = 0; i < npages; i++) { - struct nfs_page *req; - unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); - - req = nfs_create_request(dreq->ctx, pagevec[i], NULL, - pgbase, req_len); - if (IS_ERR(req)) { - result = PTR_ERR(req); - break; - } - nfs_lock_request(req); - req->wb_index = pos >> PAGE_SHIFT; - req->wb_offset = pos & ~PAGE_MASK; - if (!nfs_pageio_add_request(desc, req)) { - result = desc->pg_error; - nfs_unlock_and_release_request(req); - break; - } - pgbase = 0; - bytes -= req_len; - started += req_len; - user_addr += req_len; - pos += req_len; - count -= req_len; - dreq->bytes_left -= req_len; - } - /* The nfs_page now hold references to these pages */ - nfs_direct_release_pages(pagevec, npages); - } while (count != 0 && result >= 0); - - kfree(pagevec); - - if (started) - return started; - return result < 0 ? (ssize_t) result : -EFAULT; -} - static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) { struct nfs_direct_req *dreq = hdr->dreq; @@ -919,7 +756,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) spin_unlock(&dreq->lock); while (!list_empty(&hdr->pages)) { - bool do_destroy = true; req = nfs_list_entry(hdr->pages.next); nfs_list_remove_request(req); @@ -928,7 +764,6 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr) case NFS_IOHDR_NEED_COMMIT: kref_get(&req->wb_kref); nfs_mark_request_commit(req, hdr->lseg, &cinfo); - do_destroy = false; } nfs_unlock_and_release_request(req); } @@ -956,16 +791,27 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { .completion = nfs_direct_write_completion, }; + +/* + * NB: Return the value of the first error return code. Subsequent + * errors after the first one are ignored. + */ +/* + * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE + * operation. If nfs_writedata_alloc() or get_user_pages() fails, + * bail and stop sending more writes. Write length accounting is + * handled automatically by nfs_direct_write_result(). Otherwise, if + * no requests have been sent, just return an error. + */ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, - const struct iovec *iov, - unsigned long nr_segs, - loff_t pos, bool uio) + struct iov_iter *iter, + loff_t pos) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; ssize_t result = 0; size_t requested_bytes = 0; - unsigned long seg; + size_t wsize = max_t(size_t, NFS_SERVER(inode)->wsize, PAGE_SIZE); nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, false, &nfs_direct_write_completion_ops); @@ -973,16 +819,49 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, get_dreq(dreq); atomic_inc(&inode->i_dio_count); - NFS_I(dreq->inode)->write_io += iov_length(iov, nr_segs); - for (seg = 0; seg < nr_segs; seg++) { - const struct iovec *vec = &iov[seg]; - result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio); + NFS_I(inode)->write_io += iov_iter_count(iter); + while (iov_iter_count(iter)) { + struct page **pagevec; + size_t bytes; + size_t pgbase; + unsigned npages, i; + + result = iov_iter_get_pages_alloc(iter, &pagevec, + wsize, &pgbase); if (result < 0) break; - requested_bytes += result; - if ((size_t)result < vec->iov_len) + + bytes = result; + iov_iter_advance(iter, bytes); + npages = (result + pgbase + PAGE_SIZE - 1) / PAGE_SIZE; + for (i = 0; i < npages; i++) { + struct nfs_page *req; + unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase); + + req = nfs_create_request(dreq->ctx, pagevec[i], NULL, + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + nfs_lock_request(req); + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(&desc, req)) { + result = desc.pg_error; + nfs_unlock_and_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + requested_bytes += req_len; + pos += req_len; + dreq->bytes_left -= req_len; + } + nfs_direct_release_pages(pagevec, npages); + kvfree(pagevec); + if (result < 0) break; - pos += vec->iov_len; } nfs_pageio_complete(&desc); @@ -1004,8 +883,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, /** * nfs_file_direct_write - file direct write operation for NFS files * @iocb: target I/O control block - * @iov: vector of user buffers from which to write data - * @nr_segs: size of iov vector + * @iter: vector of user buffers from which to write data * @pos: byte offset in file where writing starts * * We use this function for direct writes instead of calling @@ -1023,8 +901,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, * Note that O_APPEND is not supported for NFS direct writes, as there * is no atomic O_APPEND write facility in the NFS protocol. */ -ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos, bool uio) +ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, + loff_t pos, bool uio) { ssize_t result = -EINVAL; struct file *file = iocb->ki_filp; @@ -1033,9 +911,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, struct nfs_direct_req *dreq; struct nfs_lock_context *l_ctx; loff_t end; - size_t count; - - count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(iter); end = (pos + count - 1) >> PAGE_CACHE_SHIFT; nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count); @@ -1086,7 +962,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio); + result = nfs_direct_write_schedule_iovec(dreq, iter, pos); if (mapping->nrpages) { invalidate_inode_pages2_range(mapping, diff --git a/fs/nfs/file.c b/fs/nfs/file.c index c1edf733631..4042ff58fe3 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -165,22 +165,21 @@ nfs_file_flush(struct file *file, fl_owner_t id) EXPORT_SYMBOL_GPL(nfs_file_flush); ssize_t -nfs_file_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +nfs_file_read(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); ssize_t result; if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, iov, nr_segs, pos, true); + return nfs_file_direct_read(iocb, to, iocb->ki_pos, true); - dprintk("NFS: read(%pD2, %lu@%lu)\n", + dprintk("NFS: read(%pD2, %zu@%lu)\n", iocb->ki_filp, - (unsigned long) iov_length(iov, nr_segs), (unsigned long) pos); + iov_iter_count(to), (unsigned long) iocb->ki_pos); result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); if (!result) { - result = generic_file_aio_read(iocb, iov, nr_segs, pos); + result = generic_file_read_iter(iocb, to); if (result > 0) nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, result); } @@ -635,24 +634,24 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode) return 0; } -ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); unsigned long written = 0; ssize_t result; - size_t count = iov_length(iov, nr_segs); + size_t count = iov_iter_count(from); + loff_t pos = iocb->ki_pos; result = nfs_key_timeout_notify(file, inode); if (result) return result; if (file->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, iov, nr_segs, pos, true); + return nfs_file_direct_write(iocb, from, pos, true); - dprintk("NFS: write(%pD2, %lu@%Ld)\n", - file, (unsigned long) count, (long long) pos); + dprintk("NFS: write(%pD2, %zu@%Ld)\n", + file, count, (long long) pos); result = -EBUSY; if (IS_SWAPFILE(inode)) @@ -670,7 +669,7 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, if (!count) goto out; - result = generic_file_aio_write(iocb, iov, nr_segs, pos); + result = generic_file_write_iter(iocb, from); if (result > 0) written = result; @@ -691,36 +690,6 @@ out_swapfile: } EXPORT_SYMBOL_GPL(nfs_file_write); -ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, - struct file *filp, loff_t *ppos, - size_t count, unsigned int flags) -{ - struct inode *inode = file_inode(filp); - unsigned long written = 0; - ssize_t ret; - - dprintk("NFS splice_write(%pD2, %lu@%llu)\n", - filp, (unsigned long) count, (unsigned long long) *ppos); - - /* - * The combination of splice and an O_APPEND destination is disallowed. - */ - - ret = generic_file_splice_write(pipe, filp, ppos, count, flags); - if (ret > 0) - written = ret; - - if (ret >= 0 && nfs_need_sync_write(filp, inode)) { - int err = vfs_fsync(filp, 0); - if (err < 0) - ret = err; - } - if (ret > 0) - nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written); - return ret; -} -EXPORT_SYMBOL_GPL(nfs_file_splice_write); - static int do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) { @@ -935,10 +904,10 @@ EXPORT_SYMBOL_GPL(nfs_setlease); const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = nfs_file_read, + .write_iter = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs_file_open, .flush = nfs_file_flush, @@ -947,7 +916,7 @@ const struct file_operations nfs_file_operations = { .lock = nfs_lock, .flock = nfs_flock, .splice_read = nfs_file_splice_read, - .splice_write = nfs_file_splice_write, + .splice_write = iter_file_splice_write, .check_flags = nfs_check_flags, .setlease = nfs_setlease, }; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index c496f8a7463..9927913c97c 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -147,6 +147,17 @@ int nfs_sync_mapping(struct address_space *mapping) return ret; } +static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + if (inode->i_mapping->nrpages == 0) + flags &= ~NFS_INO_INVALID_DATA; + nfsi->cache_validity |= flags; + if (flags & NFS_INO_INVALID_DATA) + nfs_fscache_invalidate(inode); +} + /* * Invalidate the local caches */ @@ -162,17 +173,16 @@ static void nfs_zap_caches_locked(struct inode *inode) memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf)); if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) { - nfs_fscache_invalidate(inode); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL - | NFS_INO_REVAL_PAGECACHE; + | NFS_INO_REVAL_PAGECACHE); } else - nfsi->cache_validity |= NFS_INO_INVALID_ATTR + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL - | NFS_INO_REVAL_PAGECACHE; + | NFS_INO_REVAL_PAGECACHE); nfs_zap_label_cache_locked(nfsi); } @@ -187,8 +197,7 @@ void nfs_zap_mapping(struct inode *inode, struct address_space *mapping) { if (mapping->nrpages != 0) { spin_lock(&inode->i_lock); - NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA; - nfs_fscache_invalidate(inode); + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); spin_unlock(&inode->i_lock); } } @@ -209,7 +218,7 @@ EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { spin_lock(&inode->i_lock); - NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_invalidate_atime); @@ -369,7 +378,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_mode = fattr->mode; if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0 && nfs_server_capable(inode, NFS_CAP_MODE)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); /* Why so? Because we want revalidate for devices/FIFOs, and * that's precisely what we have in nfs_file_inode_operations. */ @@ -415,36 +424,36 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st if (fattr->valid & NFS_ATTR_FATTR_ATIME) inode->i_atime = fattr->atime; else if (nfs_server_capable(inode, NFS_CAP_ATIME)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_MTIME) inode->i_mtime = fattr->mtime; else if (nfs_server_capable(inode, NFS_CAP_MTIME)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CTIME) inode->i_ctime = fattr->ctime; else if (nfs_server_capable(inode, NFS_CAP_CTIME)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else - nfsi->cache_validity |= NFS_INO_INVALID_ATTR - | NFS_INO_REVAL_PAGECACHE; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE); if (fattr->valid & NFS_ATTR_FATTR_NLINK) set_nlink(inode, fattr->nlink); else if (nfs_server_capable(inode, NFS_CAP_NLINK)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_OWNER) inode->i_uid = fattr->uid; else if (nfs_server_capable(inode, NFS_CAP_OWNER)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_GROUP) inode->i_gid = fattr->gid; else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP)) - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED) inode->i_blocks = fattr->du.nfs2.blocks; if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) { @@ -550,6 +559,9 @@ static int nfs_vmtruncate(struct inode * inode, loff_t offset) spin_lock(&inode->i_lock); i_size_write(inode, offset); + /* Optimisation */ + if (offset == 0) + NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); truncate_pagecache(inode, offset); @@ -578,7 +590,8 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr) inode->i_uid = attr->ia_uid; if ((attr->ia_valid & ATTR_GID) != 0) inode->i_gid = attr->ia_gid; - NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL); spin_unlock(&inode->i_lock); } if ((attr->ia_valid & ATTR_SIZE) != 0) { @@ -1101,7 +1114,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr && inode->i_version == fattr->pre_change_attr) { inode->i_version = fattr->change_attr; if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_INVALID_DATA; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); ret |= NFS_INO_INVALID_ATTR; } /* If we have atomic WCC data, we may update some attributes */ @@ -1117,7 +1130,7 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime)); if (S_ISDIR(inode->i_mode)) - nfsi->cache_validity |= NFS_INO_INVALID_DATA; + nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); ret |= NFS_INO_INVALID_ATTR; } if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE) @@ -1128,9 +1141,6 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr ret |= NFS_INO_INVALID_ATTR; } - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); - return ret; } @@ -1189,7 +1199,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) - nfsi->cache_validity |= invalid; + nfs_set_cache_invalid(inode, invalid); nfsi->read_cache_jiffies = fattr->time_start; return 0; @@ -1402,13 +1412,11 @@ EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { - struct nfs_inode *nfsi = NFS_I(inode); + unsigned long invalid = NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; - nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; - if (S_ISDIR(inode->i_mode)) { - nfsi->cache_validity |= NFS_INO_INVALID_DATA; - nfs_fscache_invalidate(inode); - } + if (S_ISDIR(inode->i_mode)) + invalid |= NFS_INO_INVALID_DATA; + nfs_set_cache_invalid(inode, invalid); if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; return nfs_refresh_inode_locked(inode, fattr); @@ -1601,6 +1609,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if ((nfsi->npages == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; + invalid &= ~NFS_INO_REVAL_PAGECACHE; } dprintk("NFS: isize change on server for file %s/%ld " "(%Ld to %Ld)\n", @@ -1702,10 +1711,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid &= ~NFS_INO_INVALID_DATA; if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) || (save_cache_validity & NFS_INO_REVAL_FORCED)) - nfsi->cache_validity |= invalid; - - if (invalid & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); + nfs_set_cache_invalid(inode, invalid); return 0; out_err: diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 8b69cba1bb0..f415cbf9f6c 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -244,6 +244,7 @@ void nfs_pgio_data_release(struct nfs_pgio_data *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_data *, const struct rpc_call_ops *, int, int); +void nfs_free_request(struct nfs_page *req); static inline void nfs_iocounter_init(struct nfs_io_counter *c) { @@ -327,16 +328,14 @@ int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *) int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int); loff_t nfs_file_llseek(struct file *, loff_t, int); int nfs_file_flush(struct file *, fl_owner_t); -ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +ssize_t nfs_file_read(struct kiocb *, struct iov_iter *); ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int nfs_file_mmap(struct file *, struct vm_area_struct *); -ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); +ssize_t nfs_file_write(struct kiocb *, struct iov_iter *); int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); -ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, - size_t, unsigned int); int nfs_check_flags(int); int nfs_setlease(struct file *, long, struct file_lock **); diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 871d6eda8db..8f854dde415 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -247,3 +247,46 @@ const struct xattr_handler *nfs3_xattr_handlers[] = { &posix_acl_default_xattr_handler, NULL, }; + +static int +nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, + size_t size, ssize_t *result) +{ + struct posix_acl *acl; + char *p = data + *result; + + acl = get_acl(inode, type); + if (!acl) + return 0; + + posix_acl_release(acl); + + *result += strlen(name); + *result += 1; + if (!size) + return 0; + if (*result > size) + return -ERANGE; + + strcpy(p, name); + return 0; +} + +ssize_t +nfs3_listxattr(struct dentry *dentry, char *data, size_t size) +{ + struct inode *inode = dentry->d_inode; + ssize_t result = 0; + int error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_ACCESS, + POSIX_ACL_XATTR_ACCESS, data, size, &result); + if (error) + return error; + + error = nfs3_list_one_acl(inode, ACL_TYPE_DEFAULT, + POSIX_ACL_XATTR_DEFAULT, data, size, &result); + if (error) + return error; + return result; +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index e7daa42bbc8..f0afa291fd5 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -885,7 +885,7 @@ static const struct inode_operations nfs3_dir_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, @@ -899,7 +899,7 @@ static const struct inode_operations nfs3_file_inode_operations = { .getattr = nfs_getattr, .setattr = nfs_setattr, #ifdef CONFIG_NFS_V3_ACL - .listxattr = generic_listxattr, + .listxattr = nfs3_listxattr, .getxattr = generic_getxattr, .setxattr = generic_setxattr, .removexattr = generic_removexattr, diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index f63cb87cd73..ba2affa5194 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -230,7 +230,7 @@ int nfs_atomic_open(struct inode *, struct dentry *, struct file *, extern struct file_system_type nfs4_fs_type; /* nfs4namespace.c */ -struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); +struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, struct qstr *); struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); int nfs4_replace_transport(struct nfs_server *server, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 464db9dd631..a816f0627a6 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -117,10 +117,10 @@ nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) const struct file_operations nfs4_file_operations = { .llseek = nfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = nfs_file_read, + .write_iter = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs4_file_open, .flush = nfs_file_flush, @@ -129,7 +129,7 @@ const struct file_operations nfs4_file_operations = { .lock = nfs_lock, .flock = nfs_flock, .splice_read = nfs_file_splice_read, - .splice_write = nfs_file_splice_write, + .splice_write = iter_file_splice_write, .check_flags = nfs_check_flags, .setlease = nfs_setlease, }; diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 3d5dbf80d46..3d83cb1fdc7 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -139,16 +139,22 @@ static size_t nfs_parse_server_name(char *string, size_t len, * @server: NFS server struct * @flavors: List of security tuples returned by SECINFO procedure * - * Return the pseudoflavor of the first security mechanism in - * "flavors" that is locally supported. Return RPC_AUTH_UNIX if - * no matching flavor is found in the array. The "flavors" array + * Return an rpc client that uses the first security mechanism in + * "flavors" that is locally supported. The "flavors" array * is searched in the order returned from the server, per RFC 3530 - * recommendation. + * recommendation and each flavor is checked for membership in the + * sec= mount option list if it exists. + * + * Return -EPERM if no matching flavor is found in the array. + * + * Please call rpc_shutdown_client() when you are done with this rpc client. + * */ -static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server, +static struct rpc_clnt *nfs_find_best_sec(struct rpc_clnt *clnt, + struct nfs_server *server, struct nfs4_secinfo_flavors *flavors) { - rpc_authflavor_t pseudoflavor; + rpc_authflavor_t pflavor; struct nfs4_secinfo4 *secinfo; unsigned int i; @@ -159,62 +165,73 @@ static rpc_authflavor_t nfs_find_best_sec(struct nfs_server *server, case RPC_AUTH_NULL: case RPC_AUTH_UNIX: case RPC_AUTH_GSS: - pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor, + pflavor = rpcauth_get_pseudoflavor(secinfo->flavor, &secinfo->flavor_info); - /* make sure pseudoflavor matches sec= mount opt */ - if (pseudoflavor != RPC_AUTH_MAXFLAVOR && - nfs_auth_info_match(&server->auth_info, - pseudoflavor)) - return pseudoflavor; - break; + /* does the pseudoflavor match a sec= mount opt? */ + if (pflavor != RPC_AUTH_MAXFLAVOR && + nfs_auth_info_match(&server->auth_info, pflavor)) { + struct rpc_clnt *new; + struct rpc_cred *cred; + + /* Cloning creates an rpc_auth for the flavor */ + new = rpc_clone_client_set_auth(clnt, pflavor); + if (IS_ERR(new)) + continue; + /** + * Check that the user actually can use the + * flavor. This is mostly for RPC_AUTH_GSS + * where cr_init obtains a gss context + */ + cred = rpcauth_lookupcred(new->cl_auth, 0); + if (IS_ERR(cred)) { + rpc_shutdown_client(new); + continue; + } + put_rpccred(cred); + return new; + } } } - - /* if there were any sec= options then nothing matched */ - if (server->auth_info.flavor_len > 0) - return -EPERM; - - return RPC_AUTH_UNIX; + return ERR_PTR(-EPERM); } -static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name) +/** + * nfs4_negotiate_security - in response to an NFS4ERR_WRONGSEC on lookup, + * return an rpc_clnt that uses the best available security flavor with + * respect to the secinfo flavor list and the sec= mount options. + * + * @clnt: RPC client to clone + * @inode: directory inode + * @name: lookup name + * + * Please call rpc_shutdown_client() when you are done with this rpc client. + */ +struct rpc_clnt * +nfs4_negotiate_security(struct rpc_clnt *clnt, struct inode *inode, + struct qstr *name) { struct page *page; struct nfs4_secinfo_flavors *flavors; - rpc_authflavor_t flavor; + struct rpc_clnt *new; int err; page = alloc_page(GFP_KERNEL); if (!page) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + flavors = page_address(page); err = nfs4_proc_secinfo(inode, name, flavors); if (err < 0) { - flavor = err; + new = ERR_PTR(err); goto out; } - flavor = nfs_find_best_sec(NFS_SERVER(inode), flavors); + new = nfs_find_best_sec(clnt, NFS_SERVER(inode), flavors); out: put_page(page); - return flavor; -} - -/* - * Please call rpc_shutdown_client() when you are done with this client. - */ -struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *inode, - struct qstr *name) -{ - rpc_authflavor_t flavor; - - flavor = nfs4_negotiate_security(inode, name); - if ((int)flavor < 0) - return ERR_PTR((int)flavor); - - return rpc_clone_client_set_auth(clnt, flavor); + return new; } static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, @@ -397,11 +414,6 @@ struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry, if (client->cl_auth->au_flavor != flavor) flavor = client->cl_auth->au_flavor; - else { - rpc_authflavor_t new = nfs4_negotiate_security(dir, name); - if ((int)new >= 0) - flavor = new; - } mnt = nfs_do_submount(dentry, fh, fattr, flavor); out: rpc_shutdown_client(client); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 285ad533401..4bf3d97cc5a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3247,7 +3247,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, err = -EPERM; if (client != *clnt) goto out; - client = nfs4_create_sec_client(client, dir, name); + client = nfs4_negotiate_security(client, dir, name); if (IS_ERR(client)) return PTR_ERR(client); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index b6ee3a6ee96..17fab89f635 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -29,8 +29,6 @@ static struct kmem_cache *nfs_page_cachep; static const struct rpc_call_ops nfs_pgio_common_ops; -static void nfs_free_request(struct nfs_page *); - static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount) { p->npages = pagecount; @@ -239,20 +237,28 @@ nfs_page_group_init(struct nfs_page *req, struct nfs_page *prev) WARN_ON_ONCE(prev == req); if (!prev) { + /* a head request */ req->wb_head = req; req->wb_this_page = req; } else { + /* a subrequest */ WARN_ON_ONCE(prev->wb_this_page != prev->wb_head); WARN_ON_ONCE(!test_bit(PG_HEADLOCK, &prev->wb_head->wb_flags)); req->wb_head = prev->wb_head; req->wb_this_page = prev->wb_this_page; prev->wb_this_page = req; + /* All subrequests take a ref on the head request until + * nfs_page_group_destroy is called */ + kref_get(&req->wb_head->wb_kref); + /* grab extra ref if head request has extra ref from * the write/commit path to handle handoff between write * and commit lists */ - if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) + if (test_bit(PG_INODE_REF, &prev->wb_head->wb_flags)) { + set_bit(PG_INODE_REF, &req->wb_flags); kref_get(&req->wb_kref); + } } } @@ -269,6 +275,10 @@ nfs_page_group_destroy(struct kref *kref) struct nfs_page *req = container_of(kref, struct nfs_page, wb_kref); struct nfs_page *tmp, *next; + /* subrequests must release the ref on the head request */ + if (req->wb_head != req) + nfs_release_request(req->wb_head); + if (!nfs_page_group_sync_on_bit(req, PG_TEARDOWN)) return; @@ -394,7 +404,7 @@ static void nfs_clear_request(struct nfs_page *req) * * Note: Should never be called with the spinlock held! */ -static void nfs_free_request(struct nfs_page *req) +void nfs_free_request(struct nfs_page *req) { WARN_ON_ONCE(req->wb_this_page != req); @@ -925,7 +935,6 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_pageio_doio(desc); if (desc->pg_error < 0) return 0; - desc->pg_moreio = 0; if (desc->pg_recoalesce) return 0; /* retry add_request for this subreq */ @@ -972,6 +981,7 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) desc->pg_count = 0; desc->pg_base = 0; desc->pg_recoalesce = 0; + desc->pg_moreio = 0; while (!list_empty(&head)) { struct nfs_page *req; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 3ee5af4e738..5e2f1030454 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -46,6 +46,7 @@ static const struct rpc_call_ops nfs_commit_ops; static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; static const struct nfs_commit_completion_ops nfs_commit_completion_ops; static const struct nfs_rw_ops nfs_rw_write_ops; +static void nfs_clear_request_commit(struct nfs_page *req); static struct kmem_cache *nfs_wdata_cachep; static mempool_t *nfs_wdata_mempool; @@ -91,8 +92,15 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); } +/* + * nfs_page_find_head_request_locked - find head request associated with @page + * + * must be called while holding the inode lock. + * + * returns matching head request with reference held, or NULL if not found. + */ static struct nfs_page * -nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page) +nfs_page_find_head_request_locked(struct nfs_inode *nfsi, struct page *page) { struct nfs_page *req = NULL; @@ -104,25 +112,33 @@ nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page) /* Linearly search the commit list for the correct req */ list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) { if (freq->wb_page == page) { - req = freq; + req = freq->wb_head; break; } } } - if (req) + if (req) { + WARN_ON_ONCE(req->wb_head != req); + kref_get(&req->wb_kref); + } return req; } -static struct nfs_page *nfs_page_find_request(struct page *page) +/* + * nfs_page_find_head_request - find head request associated with @page + * + * returns matching head request with reference held, or NULL if not found. + */ +static struct nfs_page *nfs_page_find_head_request(struct page *page) { struct inode *inode = page_file_mapping(page)->host; struct nfs_page *req = NULL; spin_lock(&inode->i_lock); - req = nfs_page_find_request_locked(NFS_I(inode), page); + req = nfs_page_find_head_request_locked(NFS_I(inode), page); spin_unlock(&inode->i_lock); return req; } @@ -274,36 +290,246 @@ static void nfs_end_page_writeback(struct nfs_page *req) clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC); } -static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock) + +/* nfs_page_group_clear_bits + * @req - an nfs request + * clears all page group related bits from @req + */ +static void +nfs_page_group_clear_bits(struct nfs_page *req) +{ + clear_bit(PG_TEARDOWN, &req->wb_flags); + clear_bit(PG_UNLOCKPAGE, &req->wb_flags); + clear_bit(PG_UPTODATE, &req->wb_flags); + clear_bit(PG_WB_END, &req->wb_flags); + clear_bit(PG_REMOVE, &req->wb_flags); +} + + +/* + * nfs_unroll_locks_and_wait - unlock all newly locked reqs and wait on @req + * + * this is a helper function for nfs_lock_and_join_requests + * + * @inode - inode associated with request page group, must be holding inode lock + * @head - head request of page group, must be holding head lock + * @req - request that couldn't lock and needs to wait on the req bit lock + * @nonblock - if true, don't actually wait + * + * NOTE: this must be called holding page_group bit lock and inode spin lock + * and BOTH will be released before returning. + * + * returns 0 on success, < 0 on error. + */ +static int +nfs_unroll_locks_and_wait(struct inode *inode, struct nfs_page *head, + struct nfs_page *req, bool nonblock) + __releases(&inode->i_lock) +{ + struct nfs_page *tmp; + int ret; + + /* relinquish all the locks successfully grabbed this run */ + for (tmp = head ; tmp != req; tmp = tmp->wb_this_page) + nfs_unlock_request(tmp); + + WARN_ON_ONCE(test_bit(PG_TEARDOWN, &req->wb_flags)); + + /* grab a ref on the request that will be waited on */ + kref_get(&req->wb_kref); + + nfs_page_group_unlock(head); + spin_unlock(&inode->i_lock); + + /* release ref from nfs_page_find_head_request_locked */ + nfs_release_request(head); + + if (!nonblock) + ret = nfs_wait_on_request(req); + else + ret = -EAGAIN; + nfs_release_request(req); + + return ret; +} + +/* + * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests + * + * @destroy_list - request list (using wb_this_page) terminated by @old_head + * @old_head - the old head of the list + * + * All subrequests must be locked and removed from all lists, so at this point + * they are only "active" in this function, and possibly in nfs_wait_on_request + * with a reference held by some other context. + */ +static void +nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, + struct nfs_page *old_head) +{ + while (destroy_list) { + struct nfs_page *subreq = destroy_list; + + destroy_list = (subreq->wb_this_page == old_head) ? + NULL : subreq->wb_this_page; + + WARN_ON_ONCE(old_head != subreq->wb_head); + + /* make sure old group is not used */ + subreq->wb_head = subreq; + subreq->wb_this_page = subreq; + + nfs_clear_request_commit(subreq); + + /* subreq is now totally disconnected from page group or any + * write / commit lists. last chance to wake any waiters */ + nfs_unlock_request(subreq); + + if (!test_bit(PG_TEARDOWN, &subreq->wb_flags)) { + /* release ref on old head request */ + nfs_release_request(old_head); + + nfs_page_group_clear_bits(subreq); + + /* release the PG_INODE_REF reference */ + if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) + nfs_release_request(subreq); + else + WARN_ON_ONCE(1); + } else { + WARN_ON_ONCE(test_bit(PG_CLEAN, &subreq->wb_flags)); + /* zombie requests have already released the last + * reference and were waiting on the rest of the + * group to complete. Since it's no longer part of a + * group, simply free the request */ + nfs_page_group_clear_bits(subreq); + nfs_free_request(subreq); + } + } +} + +/* + * nfs_lock_and_join_requests - join all subreqs to the head req and return + * a locked reference, cancelling any pending + * operations for this page. + * + * @page - the page used to lookup the "page group" of nfs_page structures + * @nonblock - if true, don't block waiting for request locks + * + * This function joins all sub requests to the head request by first + * locking all requests in the group, cancelling any pending operations + * and finally updating the head request to cover the whole range covered by + * the (former) group. All subrequests are removed from any write or commit + * lists, unlinked from the group and destroyed. + * + * Returns a locked, referenced pointer to the head request - which after + * this call is guaranteed to be the only request associated with the page. + * Returns NULL if no requests are found for @page, or a ERR_PTR if an + * error was encountered. + */ +static struct nfs_page * +nfs_lock_and_join_requests(struct page *page, bool nonblock) { struct inode *inode = page_file_mapping(page)->host; - struct nfs_page *req; + struct nfs_page *head, *subreq; + struct nfs_page *destroy_list = NULL; + unsigned int total_bytes; int ret; +try_again: + total_bytes = 0; + + WARN_ON_ONCE(destroy_list); + spin_lock(&inode->i_lock); - for (;;) { - req = nfs_page_find_request_locked(NFS_I(inode), page); - if (req == NULL) - break; - if (nfs_lock_request(req)) - break; - /* Note: If we hold the page lock, as is the case in nfs_writepage, - * then the call to nfs_lock_request() will always - * succeed provided that someone hasn't already marked the - * request as dirty (in which case we don't care). - */ + + /* + * A reference is taken only on the head request which acts as a + * reference to the whole page group - the group will not be destroyed + * until the head reference is released. + */ + head = nfs_page_find_head_request_locked(NFS_I(inode), page); + + if (!head) { spin_unlock(&inode->i_lock); - if (!nonblock) - ret = nfs_wait_on_request(req); - else - ret = -EAGAIN; - nfs_release_request(req); - if (ret != 0) + return NULL; + } + + /* lock each request in the page group */ + nfs_page_group_lock(head); + subreq = head; + do { + /* + * Subrequests are always contiguous, non overlapping + * and in order. If not, it's a programming error. + */ + WARN_ON_ONCE(subreq->wb_offset != + (head->wb_offset + total_bytes)); + + /* keep track of how many bytes this group covers */ + total_bytes += subreq->wb_bytes; + + if (!nfs_lock_request(subreq)) { + /* releases page group bit lock and + * inode spin lock and all references */ + ret = nfs_unroll_locks_and_wait(inode, head, + subreq, nonblock); + + if (ret == 0) + goto try_again; + return ERR_PTR(ret); - spin_lock(&inode->i_lock); + } + + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* Now that all requests are locked, make sure they aren't on any list. + * Commit list removal accounting is done after locks are dropped */ + subreq = head; + do { + nfs_list_remove_request(subreq); + subreq = subreq->wb_this_page; + } while (subreq != head); + + /* unlink subrequests from head, destroy them later */ + if (head->wb_this_page != head) { + /* destroy list will be terminated by head */ + destroy_list = head->wb_this_page; + head->wb_this_page = head; + + /* change head request to cover whole range that + * the former page group covered */ + head->wb_bytes = total_bytes; } + + /* + * prepare head request to be added to new pgio descriptor + */ + nfs_page_group_clear_bits(head); + + /* + * some part of the group was still on the inode list - otherwise + * the group wouldn't be involved in async write. + * grab a reference for the head request, iff it needs one. + */ + if (!test_and_set_bit(PG_INODE_REF, &head->wb_flags)) + kref_get(&head->wb_kref); + + nfs_page_group_unlock(head); + + /* drop lock to clear_request_commit the head req and clean up + * requests on destroy list */ spin_unlock(&inode->i_lock); - return req; + + nfs_destroy_unlinked_subrequests(destroy_list, head); + + /* clean up commit list state */ + nfs_clear_request_commit(head); + + /* still holds ref on head from nfs_page_find_head_request_locked + * and still has lock on head from lock loop */ + return head; } /* @@ -316,7 +542,7 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, struct nfs_page *req; int ret = 0; - req = nfs_find_and_lock_request(page, nonblock); + req = nfs_lock_and_join_requests(page, nonblock); if (!req) goto out; ret = PTR_ERR(req); @@ -448,7 +674,9 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) set_page_private(req->wb_page, (unsigned long)req); } nfsi->npages++; - set_bit(PG_INODE_REF, &req->wb_flags); + /* this a head request for a page group - mark it as having an + * extra reference so sub groups can follow suit */ + WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); } @@ -474,7 +702,9 @@ static void nfs_inode_remove_request(struct nfs_page *req) nfsi->npages--; spin_unlock(&inode->i_lock); } - nfs_release_request(req); + + if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) + nfs_release_request(req); } static void @@ -638,7 +868,6 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) { struct nfs_commit_info cinfo; unsigned long bytes = 0; - bool do_destroy; if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) goto out; @@ -668,7 +897,6 @@ remove_req: next: nfs_unlock_request(req); nfs_end_page_writeback(req); - do_destroy = !test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags); nfs_release_request(req); } out: @@ -769,7 +997,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, spin_lock(&inode->i_lock); for (;;) { - req = nfs_page_find_request_locked(NFS_I(inode), page); + req = nfs_page_find_head_request_locked(NFS_I(inode), page); if (req == NULL) goto out_unlock; @@ -877,7 +1105,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) * dropped page. */ do { - req = nfs_page_find_request(page); + req = nfs_page_find_head_request(page); if (req == NULL) return 0; l_ctx = req->wb_lock_context; @@ -934,12 +1162,14 @@ static bool nfs_write_pageuptodate(struct page *page, struct inode *inode) if (nfs_have_delegated_attributes(inode)) goto out; - if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE)) + if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) return false; smp_rmb(); if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags)) return false; out: + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + return false; return PageUptodate(page) != 0; } @@ -1567,27 +1797,28 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) struct nfs_page *req; int ret = 0; - for (;;) { - wait_on_page_writeback(page); - req = nfs_page_find_request(page); - if (req == NULL) - break; - if (nfs_lock_request(req)) { - nfs_clear_request_commit(req); - nfs_inode_remove_request(req); - /* - * In case nfs_inode_remove_request has marked the - * page as being dirty - */ - cancel_dirty_page(page, PAGE_CACHE_SIZE); - nfs_unlock_and_release_request(req); - break; - } - ret = nfs_wait_on_request(req); - nfs_release_request(req); - if (ret < 0) - break; + wait_on_page_writeback(page); + + /* blocking call to cancel all requests and join to a single (head) + * request */ + req = nfs_lock_and_join_requests(page, false); + + if (IS_ERR(req)) { + ret = PTR_ERR(req); + } else if (req) { + /* all requests from this page have been cancelled by + * nfs_lock_and_join_requests, so just remove the head + * request from the inode / page_private pointer and + * release it */ + nfs_inode_remove_request(req); + /* + * In case nfs_inode_remove_request has marked the + * page as being dirty + */ + cancel_dirty_page(page, PAGE_CACHE_SIZE); + nfs_unlock_and_release_request(req); } + return ret; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 6851b003f2a..8f029db5d27 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -617,15 +617,6 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (create->cr_type) { case NF4LNK: - /* ugh! we have to null-terminate the linktext, or - * vfs_symlink() will choke. it is always safe to - * null-terminate by brute force, since at worst we - * will overwrite the first byte of the create namelen - * in the XDR buffer, which has already been extracted - * during XDR decode. - */ - create->cr_linkname[create->cr_linklen] = 0; - status = nfsd_symlink(rqstp, &cstate->current_fh, create->cr_name, create->cr_namelen, create->cr_linkname, create->cr_linklen, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c0d45cec995..2204e1fe572 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -41,6 +41,7 @@ #include <linux/ratelimit.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> +#include <linux/hash.h> #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -364,6 +365,79 @@ static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp) return openlockstateid(nfs4_alloc_stid(clp, stateid_slab)); } +/* + * When we recall a delegation, we should be careful not to hand it + * out again straight away. + * To ensure this we keep a pair of bloom filters ('new' and 'old') + * in which the filehandles of recalled delegations are "stored". + * If a filehandle appear in either filter, a delegation is blocked. + * When a delegation is recalled, the filehandle is stored in the "new" + * filter. + * Every 30 seconds we swap the filters and clear the "new" one, + * unless both are empty of course. + * + * Each filter is 256 bits. We hash the filehandle to 32bit and use the + * low 3 bytes as hash-table indices. + * + * 'state_lock', which is always held when block_delegations() is called, + * is used to manage concurrent access. Testing does not need the lock + * except when swapping the two filters. + */ +static struct bloom_pair { + int entries, old_entries; + time_t swap_time; + int new; /* index into 'set' */ + DECLARE_BITMAP(set[2], 256); +} blocked_delegations; + +static int delegation_blocked(struct knfsd_fh *fh) +{ + u32 hash; + struct bloom_pair *bd = &blocked_delegations; + + if (bd->entries == 0) + return 0; + if (seconds_since_boot() - bd->swap_time > 30) { + spin_lock(&state_lock); + if (seconds_since_boot() - bd->swap_time > 30) { + bd->entries -= bd->old_entries; + bd->old_entries = bd->entries; + memset(bd->set[bd->new], 0, + sizeof(bd->set[0])); + bd->new = 1-bd->new; + bd->swap_time = seconds_since_boot(); + } + spin_unlock(&state_lock); + } + hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0); + if (test_bit(hash&255, bd->set[0]) && + test_bit((hash>>8)&255, bd->set[0]) && + test_bit((hash>>16)&255, bd->set[0])) + return 1; + + if (test_bit(hash&255, bd->set[1]) && + test_bit((hash>>8)&255, bd->set[1]) && + test_bit((hash>>16)&255, bd->set[1])) + return 1; + + return 0; +} + +static void block_delegations(struct knfsd_fh *fh) +{ + u32 hash; + struct bloom_pair *bd = &blocked_delegations; + + hash = arch_fast_hash(&fh->fh_base, fh->fh_size, 0); + + __set_bit(hash&255, bd->set[bd->new]); + __set_bit((hash>>8)&255, bd->set[bd->new]); + __set_bit((hash>>16)&255, bd->set[bd->new]); + if (bd->entries == 0) + bd->swap_time = seconds_since_boot(); + bd->entries += 1; +} + static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh) { @@ -372,6 +446,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv dprintk("NFSD alloc_init_deleg\n"); if (num_delegations > max_delegations) return NULL; + if (delegation_blocked(¤t_fh->fh_handle)) + return NULL; dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab)); if (dp == NULL) return dp; @@ -2770,6 +2846,8 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) /* Only place dl_time is set; protected by i_lock: */ dp->dl_time = get_seconds(); + block_delegations(&dp->dl_fh); + nfsd4_cb_recall(dp); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2d305a121f3..944275c8f56 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -600,7 +600,18 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create READ_BUF(4); create->cr_linklen = be32_to_cpup(p++); READ_BUF(create->cr_linklen); - SAVEMEM(create->cr_linkname, create->cr_linklen); + /* + * The VFS will want a null-terminated string, and + * null-terminating in place isn't safe since this might + * end on a page boundary: + */ + create->cr_linkname = + kmalloc(create->cr_linklen + 1, GFP_KERNEL); + if (!create->cr_linkname) + return nfserr_jukebox; + memcpy(create->cr_linkname, p, create->cr_linklen); + create->cr_linkname[create->cr_linklen] = '\0'; + defer_free(argp, kfree, create->cr_linkname); break; case NF4BLK: case NF4CHR: @@ -2630,7 +2641,7 @@ nfsd4_encode_rdattr_error(struct xdr_stream *xdr, __be32 nfserr) { __be32 *p; - p = xdr_reserve_space(xdr, 6); + p = xdr_reserve_space(xdr, 20); if (!p) return NULL; *p++ = htonl(2); @@ -2687,6 +2698,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, nfserr = nfserr_toosmall; goto fail; case nfserr_noent: + xdr_truncate_encode(xdr, start_offset); goto skip_entry; default: /* @@ -2867,6 +2879,7 @@ again: * return the conflicting open: */ if (conf->len) { + kfree(conf->data); conf->len = 0; conf->data = NULL; goto again; @@ -2879,6 +2892,7 @@ again: if (conf->len) { p = xdr_encode_opaque_fixed(p, &ld->ld_clientid, 8); p = xdr_encode_opaque(p, conf->data, conf->len); + kfree(conf->data); } else { /* non - nfsv4 lock in conflict, no clientid nor owner */ p = xdr_encode_hyper(p, (u64)0); /* clientid */ *p++ = cpu_to_be32(0); /* length of owner name */ @@ -2895,7 +2909,7 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo nfserr = nfsd4_encode_stateid(xdr, &lock->lk_resp_stateid); else if (nfserr == nfserr_denied) nfserr = nfsd4_encode_lock_denied(xdr, &lock->lk_denied); - kfree(lock->lk_denied.ld_owner.data); + return nfserr; } @@ -3266,7 +3280,7 @@ nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd wire_count = htonl(maxcount); write_bytes_to_xdr_buf(xdr->buf, length_offset, &wire_count, 4); - xdr_truncate_encode(xdr, length_offset + 4 + maxcount); + xdr_truncate_encode(xdr, length_offset + 4 + ALIGN(maxcount, 4)); if (maxcount & 3) write_bytes_to_xdr_buf(xdr->buf, length_offset + 4 + maxcount, &zero, 4 - (maxcount&3)); diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index f3a82fbcae0..24978153c0c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -152,10 +152,10 @@ static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma) */ const struct file_operations nilfs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .unlocked_ioctl = nilfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = nilfs_compat_ioctl, diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index b9c5726120e..6252b173a46 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -298,19 +298,20 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping, } static ssize_t -nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +nilfs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t size; if (rw == WRITE) return 0; /* Needs synchronization with the cleaner */ - size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, + size = blockdev_direct_IO(rw, iocb, inode, iter, offset, nilfs_get_block); /* @@ -319,7 +320,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, */ if (unlikely((rw & WRITE) && size < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if (end > isize) nilfs_write_failed(mapping, end); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index 86ddab916b6..5c9e2c81cb1 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2090,10 +2090,7 @@ static ssize_t ntfs_file_aio_write_nolock(struct kiocb *iocb, size_t count; /* after file limit checks */ ssize_t written, err; - count = 0; - err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (err) - return err; + count = iov_length(iov, nr_segs); pos = *ppos; /* We can write back this queue in page reclaim. */ current->backing_dev_info = mapping->backing_dev_info; @@ -2202,8 +2199,8 @@ static int ntfs_file_fsync(struct file *filp, loff_t start, loff_t end, const struct file_operations ntfs_file_ops = { .llseek = generic_file_llseek, /* Seek inside file. */ - .read = do_sync_read, /* Read from file. */ - .aio_read = generic_file_aio_read, /* Async read from file. */ + .read = new_sync_read, /* Read from file. */ + .read_iter = generic_file_read_iter, /* Async read from file. */ #ifdef NTFS_RW .write = do_sync_write, /* Write to file. */ .aio_write = ntfs_file_aio_write, /* Async write to file. */ diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index d310d12a9ad..4a231a166cf 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -599,9 +599,8 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait) static ssize_t ocfs2_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file)->i_mapping->host; @@ -618,7 +617,7 @@ static ssize_t ocfs2_direct_IO(int rw, return 0; return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, - iov, offset, nr_segs, + iter, offset, ocfs2_direct_IO_get_blocks, ocfs2_dio_end_io, NULL, 0); } diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h index a106b3f2b22..fae17c640df 100644 --- a/fs/ocfs2/dlm/dlmcommon.h +++ b/fs/ocfs2/dlm/dlmcommon.h @@ -331,6 +331,7 @@ struct dlm_lock_resource u16 state; char lvb[DLM_LVB_LEN]; unsigned int inflight_locks; + unsigned int inflight_assert_workers; unsigned long refmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; }; @@ -910,6 +911,9 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res); +void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res); + void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock); void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock); void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock); diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 3087a21d32f..82abf0cc9a1 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -581,6 +581,7 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm, atomic_set(&res->asts_reserved, 0); res->migration_pending = 0; res->inflight_locks = 0; + res->inflight_assert_workers = 0; res->dlm = dlm; @@ -683,6 +684,43 @@ void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm, wake_up(&res->wq); } +void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + res->inflight_assert_workers++; + mlog(0, "%s:%.*s: inflight assert worker++: now %u\n", + dlm->name, res->lockname.len, res->lockname.name, + res->inflight_assert_workers); +} + +static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + spin_lock(&res->spinlock); + __dlm_lockres_grab_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); +} + +static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + assert_spin_locked(&res->spinlock); + BUG_ON(res->inflight_assert_workers == 0); + res->inflight_assert_workers--; + mlog(0, "%s:%.*s: inflight assert worker--: now %u\n", + dlm->name, res->lockname.len, res->lockname.name, + res->inflight_assert_workers); +} + +static void dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm, + struct dlm_lock_resource *res) +{ + spin_lock(&res->spinlock); + __dlm_lockres_drop_inflight_worker(dlm, res); + spin_unlock(&res->spinlock); +} + /* * lookup a lock resource by name. * may already exist in the hashtable. @@ -1603,7 +1641,8 @@ send_response: mlog(ML_ERROR, "failed to dispatch assert master work\n"); response = DLM_MASTER_RESP_ERROR; dlm_lockres_put(res); - } + } else + dlm_lockres_grab_inflight_worker(dlm, res); } else { if (res) dlm_lockres_put(res); @@ -2118,6 +2157,8 @@ static void dlm_assert_master_worker(struct dlm_work_item *item, void *data) dlm_lockres_release_ast(dlm, res); put: + dlm_lockres_drop_inflight_worker(dlm, res); + dlm_lockres_put(res); mlog(0, "finished with dlm_assert_master_worker\n"); @@ -3088,11 +3129,15 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm, /* remove it so that only one mle will be found */ __dlm_unlink_mle(dlm, tmp); __dlm_mle_detach_hb_events(dlm, tmp); - ret = DLM_MIGRATE_RESPONSE_MASTERY_REF; - mlog(0, "%s:%.*s: master=%u, newmaster=%u, " - "telling master to get ref for cleared out mle " - "during migration\n", dlm->name, namelen, name, - master, new_master); + if (tmp->type == DLM_MLE_MASTER) { + ret = DLM_MIGRATE_RESPONSE_MASTERY_REF; + mlog(0, "%s:%.*s: master=%u, newmaster=%u, " + "telling master to get ref " + "for cleared out mle during " + "migration\n", dlm->name, + namelen, name, master, + new_master); + } } spin_unlock(&tmp->spinlock); } diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 5de019437ea..45067faf569 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1708,7 +1708,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data, mlog_errno(-ENOMEM); /* retry!? */ BUG(); - } + } else + __dlm_lockres_grab_inflight_worker(dlm, res); } else /* put.. incase we are not the master */ dlm_lockres_put(res); spin_unlock(&res->spinlock); diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c index 9db869de829..69aac6f088a 100644 --- a/fs/ocfs2/dlm/dlmthread.c +++ b/fs/ocfs2/dlm/dlmthread.c @@ -259,12 +259,15 @@ static void dlm_run_purge_list(struct dlm_ctxt *dlm, * refs on it. */ unused = __dlm_lockres_unused(lockres); if (!unused || - (lockres->state & DLM_LOCK_RES_MIGRATING)) { + (lockres->state & DLM_LOCK_RES_MIGRATING) || + (lockres->inflight_assert_workers != 0)) { mlog(0, "%s: res %.*s is in use or being remastered, " - "used %d, state %d\n", dlm->name, - lockres->lockname.len, lockres->lockname.name, - !unused, lockres->state); - list_move_tail(&dlm->purge_list, &lockres->purge); + "used %d, state %d, assert master workers %u\n", + dlm->name, lockres->lockname.len, + lockres->lockname.name, + !unused, lockres->state, + lockres->inflight_assert_workers); + list_move_tail(&lockres->purge, &dlm->purge_list); spin_unlock(&lockres->spinlock); continue; } diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c index 5698b52cf5c..2e3c9dbab68 100644 --- a/fs/ocfs2/dlm/dlmunlock.c +++ b/fs/ocfs2/dlm/dlmunlock.c @@ -191,7 +191,9 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, DLM_UNLOCK_CLEAR_CONVERT_TYPE); } else if (status == DLM_RECOVERING || status == DLM_MIGRATING || - status == DLM_FORWARD) { + status == DLM_FORWARD || + status == DLM_NOLOCKMGR + ) { /* must clear the actions because this unlock * is about to be retried. cannot free or do * any list manipulation. */ @@ -200,7 +202,8 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm, res->lockname.name, status==DLM_RECOVERING?"recovering": (status==DLM_MIGRATING?"migrating": - "forward")); + (status == DLM_FORWARD ? "forward" : + "nolockmanager"))); actions = 0; } if (flags & LKM_CANCEL) @@ -364,7 +367,10 @@ static enum dlm_status dlm_send_remote_unlock_request(struct dlm_ctxt *dlm, * updated state to the recovery master. this thread * just needs to finish out the operation and call * the unlockast. */ - ret = DLM_NORMAL; + if (dlm_is_node_dead(dlm, owner)) + ret = DLM_NORMAL; + else + ret = DLM_NOLOCKMGR; } else { /* something bad. this will BUG in ocfs2 */ ret = dlm_err_to_dlm_status(tmpret); @@ -638,7 +644,9 @@ retry: if (status == DLM_RECOVERING || status == DLM_MIGRATING || - status == DLM_FORWARD) { + status == DLM_FORWARD || + status == DLM_NOLOCKMGR) { + /* We want to go away for a tiny bit to allow recovery * / migration to complete on this resource. I don't * know of any wait queue we could sleep on as this @@ -650,7 +658,7 @@ retry: msleep(50); mlog(0, "retrying unlock due to pending recovery/" - "migration/in-progress\n"); + "migration/in-progress/reconnect\n"); goto retry; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 8eb6e5732d3..2930e231f3f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2233,16 +2233,13 @@ out: return ret; } -static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, - const struct iovec *iov, - unsigned long nr_segs, - loff_t pos) +static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, + struct iov_iter *from) { int ret, direct_io, appending, rw_level, have_alloc_sem = 0; int can_do_direct, has_refcount = 0; ssize_t written = 0; - size_t ocount; /* original count */ - size_t count; /* after file limit checks */ + size_t count = iov_iter_count(from); loff_t old_size, *ppos = &iocb->ki_pos; u32 old_clusters; struct file *file = iocb->ki_filp; @@ -2256,7 +2253,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, (unsigned long long)OCFS2_I(inode)->ip_blkno, file->f_path.dentry->d_name.len, file->f_path.dentry->d_name.name, - (unsigned int)nr_segs); + (unsigned int)from->nr_segs); /* GRRRRR */ if (iocb->ki_nbytes == 0) return 0; @@ -2354,29 +2351,21 @@ relock: /* communicate with ocfs2_dio_end_io */ ocfs2_iocb_set_rw_locked(iocb, rw_level); - ret = generic_segment_checks(iov, &nr_segs, &ocount, - VERIFY_READ); - if (ret) - goto out_dio; - - count = ocount; ret = generic_write_checks(file, ppos, &count, S_ISBLK(inode->i_mode)); if (ret) goto out_dio; + iov_iter_truncate(from, count); if (direct_io) { - written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos, - count, ocount); + written = generic_file_direct_write(iocb, from, *ppos); if (written < 0) { ret = written; goto out_dio; } } else { - struct iov_iter from; - iov_iter_init(&from, iov, nr_segs, count, 0); current->backing_dev_info = file->f_mapping->backing_dev_info; - written = generic_perform_write(file, &from, *ppos); + written = generic_perform_write(file, from, *ppos); if (likely(written >= 0)) iocb->ki_pos = *ppos + written; current->backing_dev_info = NULL; @@ -2441,84 +2430,6 @@ out_sems: return ret; } -static int ocfs2_splice_to_file(struct pipe_inode_info *pipe, - struct file *out, - struct splice_desc *sd) -{ - int ret; - - ret = ocfs2_prepare_inode_for_write(out, &sd->pos, - sd->total_len, 0, NULL, NULL); - if (ret < 0) { - mlog_errno(ret); - return ret; - } - - return splice_from_pipe_feed(pipe, sd, pipe_to_file); -} - -static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe, - struct file *out, - loff_t *ppos, - size_t len, - unsigned int flags) -{ - int ret; - struct address_space *mapping = out->f_mapping; - struct inode *inode = mapping->host; - struct splice_desc sd = { - .total_len = len, - .flags = flags, - .pos = *ppos, - .u.file = out, - }; - - - trace_ocfs2_file_splice_write(inode, out, out->f_path.dentry, - (unsigned long long)OCFS2_I(inode)->ip_blkno, - out->f_path.dentry->d_name.len, - out->f_path.dentry->d_name.name, len); - - pipe_lock(pipe); - - splice_from_pipe_begin(&sd); - do { - ret = splice_from_pipe_next(pipe, &sd); - if (ret <= 0) - break; - - mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); - ret = ocfs2_rw_lock(inode, 1); - if (ret < 0) - mlog_errno(ret); - else { - ret = ocfs2_splice_to_file(pipe, out, &sd); - ocfs2_rw_unlock(inode, 1); - } - mutex_unlock(&inode->i_mutex); - } while (ret > 0); - splice_from_pipe_end(pipe, &sd); - - pipe_unlock(pipe); - - if (sd.num_spliced) - ret = sd.num_spliced; - - if (ret > 0) { - int err; - - err = generic_write_sync(out, *ppos, ret); - if (err) - ret = err; - else - *ppos += ret; - - balance_dirty_pages_ratelimited(mapping); - } - - return ret; -} - static ssize_t ocfs2_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, @@ -2534,7 +2445,7 @@ static ssize_t ocfs2_file_splice_read(struct file *in, in->f_path.dentry->d_name.name, len); /* - * See the comment in ocfs2_file_aio_read() + * See the comment in ocfs2_file_read_iter() */ ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level); if (ret < 0) { @@ -2549,10 +2460,8 @@ bail: return ret; } -static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, - const struct iovec *iov, - unsigned long nr_segs, - loff_t pos) +static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, + struct iov_iter *to) { int ret = 0, rw_level = -1, have_alloc_sem = 0, lock_level = 0; struct file *filp = iocb->ki_filp; @@ -2561,7 +2470,8 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, filp->f_path.dentry->d_name.len, - filp->f_path.dentry->d_name.name, nr_segs); + filp->f_path.dentry->d_name.name, + to->nr_segs); /* GRRRRR */ if (!inode) { @@ -2606,13 +2516,13 @@ static ssize_t ocfs2_file_aio_read(struct kiocb *iocb, } ocfs2_inode_unlock(inode, lock_level); - ret = generic_file_aio_read(iocb, iov, nr_segs, iocb->ki_pos); + ret = generic_file_read_iter(iocb, to); trace_generic_file_aio_read_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ BUG_ON(ret == -EIOCBQUEUED && !(filp->f_flags & O_DIRECT)); - /* see ocfs2_file_aio_write */ + /* see ocfs2_file_write_iter */ if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) { rw_level = -1; have_alloc_sem = 0; @@ -2705,14 +2615,14 @@ const struct inode_operations ocfs2_special_file_iops = { */ const struct file_operations ocfs2_fops = { .llseek = ocfs2_file_llseek, - .read = do_sync_read, - .write = do_sync_write, + .read = new_sync_read, + .write = new_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, - .aio_read = ocfs2_file_aio_read, - .aio_write = ocfs2_file_aio_write, + .read_iter = ocfs2_file_read_iter, + .write_iter = ocfs2_file_write_iter, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, @@ -2720,7 +2630,7 @@ const struct file_operations ocfs2_fops = { .lock = ocfs2_lock, .flock = ocfs2_flock, .splice_read = ocfs2_file_splice_read, - .splice_write = ocfs2_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, }; @@ -2753,21 +2663,21 @@ const struct file_operations ocfs2_dops = { */ const struct file_operations ocfs2_fops_no_plocks = { .llseek = ocfs2_file_llseek, - .read = do_sync_read, - .write = do_sync_write, + .read = new_sync_read, + .write = new_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, - .aio_read = ocfs2_file_aio_read, - .aio_write = ocfs2_file_aio_write, + .read_iter = ocfs2_file_read_iter, + .write_iter = ocfs2_file_write_iter, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ocfs2_compat_ioctl, #endif .flock = ocfs2_flock, .splice_read = ocfs2_file_splice_read, - .splice_write = ocfs2_file_splice_write, + .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, }; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 2060fc39844..8add6f1030d 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -205,6 +205,21 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) return inode; } +static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb, + struct dentry *dentry, struct inode *inode) +{ + struct ocfs2_dentry_lock *dl = dentry->d_fsdata; + + ocfs2_simple_drop_lockres(osb, &dl->dl_lockres); + ocfs2_lock_res_free(&dl->dl_lockres); + BUG_ON(dl->dl_count != 1); + spin_lock(&dentry_attach_lock); + dentry->d_fsdata = NULL; + spin_unlock(&dentry_attach_lock); + kfree(dl); + iput(inode); +} + static int ocfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -231,6 +246,7 @@ static int ocfs2_mknod(struct inode *dir, sigset_t oldset; int did_block_signals = 0; struct posix_acl *default_acl = NULL, *acl = NULL; + struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, @@ -423,6 +439,8 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + dl = dentry->d_fsdata; + status = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_fe_bh, &lookup); @@ -469,6 +487,9 @@ leave: * ocfs2_delete_inode will mutex_lock again. */ if ((status < 0) && inode) { + if (dl) + ocfs2_cleanup_add_entry_failure(osb, dentry, inode); + OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); @@ -991,6 +1012,65 @@ leave: return status; } +static int ocfs2_check_if_ancestor(struct ocfs2_super *osb, + u64 src_inode_no, u64 dest_inode_no) +{ + int ret = 0, i = 0; + u64 parent_inode_no = 0; + u64 child_inode_no = src_inode_no; + struct inode *child_inode; + +#define MAX_LOOKUP_TIMES 32 + while (1) { + child_inode = ocfs2_iget(osb, child_inode_no, 0, 0); + if (IS_ERR(child_inode)) { + ret = PTR_ERR(child_inode); + break; + } + + ret = ocfs2_inode_lock(child_inode, NULL, 0); + if (ret < 0) { + iput(child_inode); + if (ret != -ENOENT) + mlog_errno(ret); + break; + } + + ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2, + &parent_inode_no); + ocfs2_inode_unlock(child_inode, 0); + iput(child_inode); + if (ret < 0) { + ret = -ENOENT; + break; + } + + if (parent_inode_no == dest_inode_no) { + ret = 1; + break; + } + + if (parent_inode_no == osb->root_inode->i_ino) { + ret = 0; + break; + } + + child_inode_no = parent_inode_no; + + if (++i >= MAX_LOOKUP_TIMES) { + mlog(ML_NOTICE, "max lookup times reached, filesystem " + "may have nested directories, " + "src inode: %llu, dest inode: %llu.\n", + (unsigned long long)src_inode_no, + (unsigned long long)dest_inode_no); + ret = 0; + break; + } + } + + return ret; +} + /* * The only place this should be used is rename! * if they have the same id, then the 1st one is the only one locked. @@ -1002,6 +1082,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, struct inode *inode2) { int status; + int inode1_is_ancestor, inode2_is_ancestor; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); struct ocfs2_inode_info *oi2 = OCFS2_I(inode2); struct buffer_head **tmpbh; @@ -1015,9 +1096,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, if (*bh2) *bh2 = NULL; - /* we always want to lock the one with the lower lockid first. */ + /* we always want to lock the one with the lower lockid first. + * and if they are nested, we lock ancestor first */ if (oi1->ip_blkno != oi2->ip_blkno) { - if (oi1->ip_blkno < oi2->ip_blkno) { + inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno, + oi1->ip_blkno); + if (inode1_is_ancestor < 0) { + status = inode1_is_ancestor; + goto bail; + } + + inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno, + oi2->ip_blkno); + if (inode2_is_ancestor < 0) { + status = inode2_is_ancestor; + goto bail; + } + + if ((inode1_is_ancestor == 1) || + (oi1->ip_blkno < oi2->ip_blkno && + inode2_is_ancestor == 0)) { /* switch id1 and id2 around */ tmpbh = bh2; bh2 = bh1; @@ -1098,6 +1196,7 @@ static int ocfs2_rename(struct inode *old_dir, struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, }; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; struct ocfs2_dir_lookup_result target_insert = { NULL, }; + bool should_add_orphan = false; /* At some point it might be nice to break this function up a * bit. */ @@ -1134,6 +1233,21 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } rename_lock = 1; + + /* here we cannot guarantee the inodes haven't just been + * changed, so check if they are nested again */ + status = ocfs2_check_if_ancestor(osb, new_dir->i_ino, + old_inode->i_ino); + if (status < 0) { + mlog_errno(status); + goto bail; + } else if (status == 1) { + status = -EPERM; + trace_ocfs2_rename_not_permitted( + (unsigned long long)old_inode->i_ino, + (unsigned long long)new_dir->i_ino); + goto bail; + } } /* if old and new are the same, this'll just do one lock. */ @@ -1304,6 +1418,7 @@ static int ocfs2_rename(struct inode *old_dir, mlog_errno(status); goto bail; } + should_add_orphan = true; } } else { BUG_ON(new_dentry->d_parent->d_inode != new_dir); @@ -1348,17 +1463,6 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } - if (S_ISDIR(new_inode->i_mode) || - (ocfs2_read_links_count(newfe) == 1)) { - status = ocfs2_orphan_add(osb, handle, new_inode, - newfe_bh, orphan_name, - &orphan_insert, orphan_dir); - if (status < 0) { - mlog_errno(status); - goto bail; - } - } - /* change the dirent to point to the correct inode */ status = ocfs2_update_entry(new_dir, handle, &target_lookup_res, old_inode); @@ -1373,6 +1477,15 @@ static int ocfs2_rename(struct inode *old_dir, else ocfs2_add_links_count(newfe, -1); ocfs2_journal_dirty(handle, newfe_bh); + if (should_add_orphan) { + status = ocfs2_orphan_add(osb, handle, new_inode, + newfe_bh, orphan_name, + &orphan_insert, orphan_dir); + if (status < 0) { + mlog_errno(status); + goto bail; + } + } } else { /* if the name was not found in new_dir, add it now */ status = ocfs2_add_entry(handle, new_dentry, old_inode, @@ -1642,6 +1755,7 @@ static int ocfs2_symlink(struct inode *dir, struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; + struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_symlink_begin(dir, dentry, symname, dentry->d_name.len, dentry->d_name.name); @@ -1830,6 +1944,8 @@ static int ocfs2_symlink(struct inode *dir, goto bail; } + dl = dentry->d_fsdata; + status = ocfs2_add_entry(handle, dentry, inode, le64_to_cpu(fe->i_blkno), parent_fe_bh, &lookup); @@ -1864,6 +1980,9 @@ bail: if (xattr_ac) ocfs2_free_alloc_context(xattr_ac); if ((status < 0) && inode) { + if (dl) + ocfs2_cleanup_add_entry_failure(osb, dentry, inode); + OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h index 1b60c62aa9d..6cb019b7c6a 100644 --- a/fs/ocfs2/ocfs2_trace.h +++ b/fs/ocfs2/ocfs2_trace.h @@ -2292,6 +2292,8 @@ TRACE_EVENT(ocfs2_rename, __entry->new_len, __get_str(new_name)) ); +DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_rename_not_permitted); + TRACE_EVENT(ocfs2_rename_target_exists, TP_PROTO(int new_len, const char *new_name), TP_ARGS(new_len, new_name), diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 714e53b9cc6..636aab69ead 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4288,9 +4288,16 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, goto out; } + error = ocfs2_rw_lock(inode, 1); + if (error) { + mlog_errno(error); + goto out; + } + error = ocfs2_inode_lock(inode, &old_bh, 1); if (error) { mlog_errno(error); + ocfs2_rw_unlock(inode, 1); goto out; } @@ -4302,6 +4309,7 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, up_write(&OCFS2_I(inode)->ip_xattr_sem); ocfs2_inode_unlock(inode, 1); + ocfs2_rw_unlock(inode, 1); brelse(old_bh); if (error) { diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index c7a89cea5c5..ddb662b3244 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1925,15 +1925,11 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) ocfs2_shutdown_local_alloc(osb); + ocfs2_truncate_log_shutdown(osb); + /* This will disable recovery and flush any recovery work. */ ocfs2_recovery_exit(osb); - /* - * During dismount, when it recovers another node it will call - * ocfs2_recover_orphans and queue delayed work osb_truncate_log_wq. - */ - ocfs2_truncate_log_shutdown(osb); - ocfs2_journal_shutdown(osb); ocfs2_sync_blockdev(sb); diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 54d57d6ba68..902e88527fc 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -337,10 +337,10 @@ static sector_t omfs_bmap(struct address_space *mapping, sector_t block) const struct file_operations omfs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/open.c b/fs/open.c index 9d64679cec7..d6fd3acde13 100644 --- a/fs/open.c +++ b/fs/open.c @@ -263,11 +263,10 @@ int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EPERM; /* - * We can not allow to do any fallocate operation on an active - * swapfile + * We cannot allow any fallocate operation on an active swapfile */ if (IS_SWAPFILE(inode)) - ret = -ETXTBSY; + return -ETXTBSY; /* * Revalidate the write permissions, in case security policy has @@ -725,6 +724,12 @@ static int do_dentry_open(struct file *f, } if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) i_readcount_inc(inode); + if ((f->f_mode & FMODE_READ) && + likely(f->f_op->read || f->f_op->aio_read || f->f_op->read_iter)) + f->f_mode |= FMODE_CAN_READ; + if ((f->f_mode & FMODE_WRITE) && + likely(f->f_op->write || f->f_op->aio_write || f->f_op->write_iter)) + f->f_mode |= FMODE_CAN_WRITE; f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); diff --git a/fs/pipe.c b/fs/pipe.c index 034bffac3f9..21981e58e2a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -116,50 +116,6 @@ void pipe_wait(struct pipe_inode_info *pipe) pipe_lock(pipe); } -static int -pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len, - int atomic) -{ - unsigned long copy; - - while (len > 0) { - while (!iov->iov_len) - iov++; - copy = min_t(unsigned long, len, iov->iov_len); - - if (atomic) { - if (__copy_from_user_inatomic(to, iov->iov_base, copy)) - return -EFAULT; - } else { - if (copy_from_user(to, iov->iov_base, copy)) - return -EFAULT; - } - to += copy; - len -= copy; - iov->iov_base += copy; - iov->iov_len -= copy; - } - return 0; -} - -/* - * Pre-fault in the user memory, so we can use atomic copies. - */ -static void iov_fault_in_pages_read(struct iovec *iov, unsigned long len) -{ - while (!iov->iov_len) - iov++; - - while (len > 0) { - unsigned long this_len; - - this_len = min_t(unsigned long, len, iov->iov_len); - fault_in_pages_readable(iov->iov_base, this_len); - len -= this_len; - iov++; - } -} - static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -271,24 +227,18 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = { }; static ssize_t -pipe_read(struct kiocb *iocb, const struct iovec *_iov, - unsigned long nr_segs, loff_t pos) +pipe_read(struct kiocb *iocb, struct iov_iter *to) { + size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; int do_wakeup; ssize_t ret; - struct iovec *iov = (struct iovec *)_iov; - size_t total_len; - struct iov_iter iter; - total_len = iov_length(iov, nr_segs); /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; - iov_iter_init(&iter, iov, nr_segs, total_len, 0); - do_wakeup = 0; ret = 0; __pipe_lock(pipe); @@ -312,7 +262,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov, break; } - written = copy_page_to_iter(buf->page, buf->offset, chars, &iter); + written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; @@ -386,24 +336,19 @@ static inline int is_packetized(struct file *file) } static ssize_t -pipe_write(struct kiocb *iocb, const struct iovec *_iov, - unsigned long nr_segs, loff_t ppos) +pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; - ssize_t ret; - int do_wakeup; - struct iovec *iov = (struct iovec *)_iov; - size_t total_len; + ssize_t ret = 0; + int do_wakeup = 0; + size_t total_len = iov_iter_count(from); ssize_t chars; - total_len = iov_length(iov, nr_segs); /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; - do_wakeup = 0; - ret = 0; __pipe_lock(pipe); if (!pipe->readers) { @@ -422,38 +367,19 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov, int offset = buf->offset + buf->len; if (ops->can_merge && offset + chars <= PAGE_SIZE) { - int error, atomic = 1; - void *addr; - - error = ops->confirm(pipe, buf); + int error = ops->confirm(pipe, buf); if (error) goto out; - iov_fault_in_pages_read(iov, chars); -redo1: - if (atomic) - addr = kmap_atomic(buf->page); - else - addr = kmap(buf->page); - error = pipe_iov_copy_from_user(offset + addr, iov, - chars, atomic); - if (atomic) - kunmap_atomic(addr); - else - kunmap(buf->page); - ret = error; - do_wakeup = 1; - if (error) { - if (atomic) { - atomic = 0; - goto redo1; - } + ret = copy_page_from_iter(buf->page, offset, chars, from); + if (unlikely(ret < chars)) { + error = -EFAULT; goto out; } + do_wakeup = 1; buf->len += chars; - total_len -= chars; ret = chars; - if (!total_len) + if (!iov_iter_count(from)) goto out; } } @@ -472,8 +398,7 @@ redo1: int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1); struct pipe_buffer *buf = pipe->bufs + newbuf; struct page *page = pipe->tmp_page; - char *src; - int error, atomic = 1; + int copied; if (!page) { page = alloc_page(GFP_HIGHUSER); @@ -489,40 +414,19 @@ redo1: * FIXME! Is this really true? */ do_wakeup = 1; - chars = PAGE_SIZE; - if (chars > total_len) - chars = total_len; - - iov_fault_in_pages_read(iov, chars); -redo2: - if (atomic) - src = kmap_atomic(page); - else - src = kmap(page); - - error = pipe_iov_copy_from_user(src, iov, chars, - atomic); - if (atomic) - kunmap_atomic(src); - else - kunmap(page); - - if (unlikely(error)) { - if (atomic) { - atomic = 0; - goto redo2; - } + copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); + if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) - ret = error; + ret = -EFAULT; break; } - ret += chars; + ret += copied; /* Insert it into the buffer array */ buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; - buf->len = chars; + buf->len = copied; buf->flags = 0; if (is_packetized(filp)) { buf->ops = &packet_pipe_buf_ops; @@ -531,8 +435,7 @@ redo2: pipe->nrbufs = ++bufs; pipe->tmp_page = NULL; - total_len -= chars; - if (!total_len) + if (!iov_iter_count(from)) break; } if (bufs < pipe->buffers) @@ -1044,10 +947,10 @@ err: const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, - .write = do_sync_write, - .aio_write = pipe_write, + .read = new_sync_read, + .read_iter = pipe_read, + .write = new_sync_write, + .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 9d231e9e5f0..bf2d03f8fd3 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -184,29 +184,11 @@ static int show_stat(struct seq_file *p, void *v) static int stat_open(struct inode *inode, struct file *file) { - size_t size = 1024 + 128 * num_possible_cpus(); - char *buf; - struct seq_file *m; - int res; + size_t size = 1024 + 128 * num_online_cpus(); /* minimum size to display an interrupt count : 2 bytes */ size += 2 * nr_irqs; - - /* don't ask for more than the kmalloc() max size */ - if (size > KMALLOC_MAX_SIZE) - size = KMALLOC_MAX_SIZE; - buf = kmalloc(size, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - res = single_open(file, show_stat, NULL); - if (!res) { - m = file->private_data; - m->buf = buf; - m->size = ksize(buf); - } else - kfree(buf); - return res; + return single_open_size(file, show_stat, NULL, size); } static const struct file_operations proc_stat_operations = { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 9cd5f63715c..7f30bdc57d1 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -702,6 +702,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) struct dquot *dquot; unsigned long freed = 0; + spin_lock(&dq_list_lock); head = free_dquots.prev; while (head != &free_dquots && sc->nr_to_scan) { dquot = list_entry(head, struct dquot, dq_free); @@ -713,6 +714,7 @@ dqcache_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) freed++; head = free_dquots.prev; } + spin_unlock(&dq_list_lock); return freed; } diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 1e56a4e8cf7..4f56de822d2 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -31,14 +31,14 @@ #include "internal.h" const struct file_operations ramfs_file_operations = { - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = noop_fsync, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 0b3d8e4cb2f..dda012ad420 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -37,13 +37,13 @@ static int ramfs_nommu_mmap(struct file *file, struct vm_area_struct *vma); const struct file_operations ramfs_file_operations = { .mmap = ramfs_nommu_mmap, .get_unmapped_area = ramfs_nommu_get_unmapped_area, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .fsync = noop_fsync, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/read_write.c b/fs/read_write.c index 31c6efa4318..009d8542a88 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -25,11 +25,12 @@ typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); typedef ssize_t (*iov_fn_t)(struct kiocb *, const struct iovec *, unsigned long, loff_t); +typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *); const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, }; @@ -390,13 +391,34 @@ ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *pp EXPORT_SYMBOL(do_sync_read); +ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) +{ + struct iovec iov = { .iov_base = buf, .iov_len = len }; + struct kiocb kiocb; + struct iov_iter iter; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_nbytes = len; + iov_iter_init(&iter, READ, &iov, 1, len); + + ret = filp->f_op->read_iter(&kiocb, &iter); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + +EXPORT_SYMBOL(new_sync_read); + ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; - if (!file->f_op->read && !file->f_op->aio_read) + if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(VERIFY_WRITE, buf, count))) return -EFAULT; @@ -406,8 +428,10 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) count = ret; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); - else + else if (file->f_op->aio_read) ret = do_sync_read(file, buf, count, pos); + else + ret = new_sync_read(file, buf, count, pos); if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); @@ -439,13 +463,34 @@ ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, lof EXPORT_SYMBOL(do_sync_write); +ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) +{ + struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len }; + struct kiocb kiocb; + struct iov_iter iter; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_nbytes = len; + iov_iter_init(&iter, WRITE, &iov, 1, len); + + ret = filp->f_op->write_iter(&kiocb, &iter); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + +EXPORT_SYMBOL(new_sync_write); + ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t *pos) { mm_segment_t old_fs; const char __user *p; ssize_t ret; - if (!file->f_op->write && !file->f_op->aio_write) + if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; old_fs = get_fs(); @@ -455,8 +500,10 @@ ssize_t __kernel_write(struct file *file, const char *buf, size_t count, loff_t count = MAX_RW_COUNT; if (file->f_op->write) ret = file->f_op->write(file, p, count, pos); - else + else if (file->f_op->aio_write) ret = do_sync_write(file, p, count, pos); + else + ret = new_sync_write(file, p, count, pos); set_fs(old_fs); if (ret > 0) { fsnotify_modify(file); @@ -472,7 +519,7 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - if (!file->f_op->write && !file->f_op->aio_write) + if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(VERIFY_READ, buf, count))) return -EFAULT; @@ -483,8 +530,10 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); - else + else if (file->f_op->aio_write) ret = do_sync_write(file, buf, count, pos); + else + ret = new_sync_write(file, buf, count, pos); if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); @@ -601,6 +650,25 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) } EXPORT_SYMBOL(iov_shorten); +static ssize_t do_iter_readv_writev(struct file *filp, int rw, const struct iovec *iov, + unsigned long nr_segs, size_t len, loff_t *ppos, iter_fn_t fn) +{ + struct kiocb kiocb; + struct iov_iter iter; + ssize_t ret; + + init_sync_kiocb(&kiocb, filp); + kiocb.ki_pos = *ppos; + kiocb.ki_nbytes = len; + + iov_iter_init(&iter, rw, iov, nr_segs, len); + ret = fn(&kiocb, &iter); + if (ret == -EIOCBQUEUED) + ret = wait_on_sync_kiocb(&kiocb); + *ppos = kiocb.ki_pos; + return ret; +} + static ssize_t do_sync_readv_writev(struct file *filp, const struct iovec *iov, unsigned long nr_segs, size_t len, loff_t *ppos, iov_fn_t fn) { @@ -738,6 +806,7 @@ static ssize_t do_readv_writev(int type, struct file *file, ssize_t ret; io_fn_t fn; iov_fn_t fnv; + iter_fn_t iter_fn; ret = rw_copy_check_uvector(type, uvector, nr_segs, ARRAY_SIZE(iovstack), iovstack, &iov); @@ -753,13 +822,18 @@ static ssize_t do_readv_writev(int type, struct file *file, if (type == READ) { fn = file->f_op->read; fnv = file->f_op->aio_read; + iter_fn = file->f_op->read_iter; } else { fn = (io_fn_t)file->f_op->write; fnv = file->f_op->aio_write; + iter_fn = file->f_op->write_iter; file_start_write(file); } - if (fnv) + if (iter_fn) + ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, + pos, iter_fn); + else if (fnv) ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, pos, fnv); else @@ -785,7 +859,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_READ)) return -EBADF; - if (!file->f_op->aio_read && !file->f_op->read) + if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; return do_readv_writev(READ, file, vec, vlen, pos); @@ -798,7 +872,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; - if (!file->f_op->aio_write && !file->f_op->write) + if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; return do_readv_writev(WRITE, file, vec, vlen, pos); @@ -912,6 +986,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, ssize_t ret; io_fn_t fn; iov_fn_t fnv; + iter_fn_t iter_fn; ret = compat_rw_copy_check_uvector(type, uvector, nr_segs, UIO_FASTIOV, iovstack, &iov); @@ -927,13 +1002,18 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, if (type == READ) { fn = file->f_op->read; fnv = file->f_op->aio_read; + iter_fn = file->f_op->read_iter; } else { fn = (io_fn_t)file->f_op->write; fnv = file->f_op->aio_write; + iter_fn = file->f_op->write_iter; file_start_write(file); } - if (fnv) + if (iter_fn) + ret = do_iter_readv_writev(file, type, iov, nr_segs, tot_len, + pos, iter_fn); + else if (fnv) ret = do_sync_readv_writev(file, iov, nr_segs, tot_len, pos, fnv); else @@ -964,7 +1044,7 @@ static size_t compat_readv(struct file *file, goto out; ret = -EINVAL; - if (!file->f_op->aio_read && !file->f_op->read) + if (!(file->f_mode & FMODE_CAN_READ)) goto out; ret = compat_do_readv_writev(READ, file, vec, vlen, pos); @@ -1041,7 +1121,7 @@ static size_t compat_writev(struct file *file, goto out; ret = -EINVAL; - if (!file->f_op->aio_write && !file->f_op->write) + if (!(file->f_mode & FMODE_CAN_WRITE)) goto out; ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 5f6c32c668b..db9e80ba53a 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -243,8 +243,8 @@ drop_write_lock: } const struct file_operations reiserfs_file_operations = { - .read = do_sync_read, - .write = do_sync_write, + .read = new_sync_read, + .write = new_sync_write, .unlocked_ioctl = reiserfs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, @@ -253,10 +253,10 @@ const struct file_operations reiserfs_file_operations = { .open = reiserfs_file_open, .release = reiserfs_file_release, .fsync = reiserfs_sync_file, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, .llseek = generic_file_llseek, }; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index e3ca0489491..63b2b0ec49e 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3279,15 +3279,15 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) * to do in this section of the code. */ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, loff_t offset) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - reiserfs_get_blocks_direct_io); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, + reiserfs_get_blocks_direct_io); /* * In case of error extending write may have instantiated a few @@ -3295,7 +3295,7 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb, */ if (unlikely((rw & WRITE) && ret < 0)) { loff_t isize = i_size_read(inode); - loff_t end = offset + iov_length(iov, nr_segs); + loff_t end = offset + count; if ((end > isize) && inode_newsize_ok(inode, isize) == 0) { truncate_setsize(inode, isize); diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c index f373bde8f54..ea06c755486 100644 --- a/fs/romfs/mmap-nommu.c +++ b/fs/romfs/mmap-nommu.c @@ -72,8 +72,8 @@ static int romfs_mmap(struct file *file, struct vm_area_struct *vma) const struct file_operations romfs_ro_fops = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .mmap = romfs_mmap, .get_unmapped_area = romfs_get_unmapped_area, diff --git a/fs/seq_file.c b/fs/seq_file.c index 1d641bb108d..3857b720cb1 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -8,8 +8,10 @@ #include <linux/fs.h> #include <linux/export.h> #include <linux/seq_file.h> +#include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/cred.h> +#include <linux/mm.h> #include <asm/uaccess.h> #include <asm/page.h> @@ -30,6 +32,16 @@ static void seq_set_overflow(struct seq_file *m) m->count = m->size; } +static void *seq_buf_alloc(unsigned long size) +{ + void *buf; + + buf = kmalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!buf && size > PAGE_SIZE) + buf = vmalloc(size); + return buf; +} + /** * seq_open - initialize sequential file * @file: file we initialize @@ -96,7 +108,7 @@ static int traverse(struct seq_file *m, loff_t offset) return 0; } if (!m->buf) { - m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) return -ENOMEM; } @@ -135,9 +147,9 @@ static int traverse(struct seq_file *m, loff_t offset) Eoverflow: m->op->stop(m, p); - kfree(m->buf); + kvfree(m->buf); m->count = 0; - m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size <<= 1); return !m->buf ? -ENOMEM : -EAGAIN; } @@ -192,7 +204,7 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) /* grab buffer if we didn't have one */ if (!m->buf) { - m->buf = kmalloc(m->size = PAGE_SIZE, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size = PAGE_SIZE); if (!m->buf) goto Enomem; } @@ -232,9 +244,9 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) if (m->count < m->size) goto Fill; m->op->stop(m, p); - kfree(m->buf); + kvfree(m->buf); m->count = 0; - m->buf = kmalloc(m->size <<= 1, GFP_KERNEL); + m->buf = seq_buf_alloc(m->size <<= 1); if (!m->buf) goto Enomem; m->version = 0; @@ -350,7 +362,7 @@ EXPORT_SYMBOL(seq_lseek); int seq_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; - kfree(m->buf); + kvfree(m->buf); kfree(m); return 0; } @@ -605,13 +617,13 @@ EXPORT_SYMBOL(single_open); int single_open_size(struct file *file, int (*show)(struct seq_file *, void *), void *data, size_t size) { - char *buf = kmalloc(size, GFP_KERNEL); + char *buf = seq_buf_alloc(size); int ret; if (!buf) return -ENOMEM; ret = single_open(file, show, data); if (ret) { - kfree(buf); + kvfree(buf); return ret; } ((struct seq_file *)file->private_data)->buf = buf; diff --git a/fs/splice.c b/fs/splice.c index e246954ea48..f5cb9ba8451 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -32,6 +32,7 @@ #include <linux/gfp.h> #include <linux/socket.h> #include <linux/compat.h> +#include <linux/aio.h> #include "internal.h" /* @@ -717,63 +718,6 @@ static int pipe_to_sendpage(struct pipe_inode_info *pipe, sd->len, &pos, more); } -/* - * This is a little more tricky than the file -> pipe splicing. There are - * basically three cases: - * - * - Destination page already exists in the address space and there - * are users of it. For that case we have no other option that - * copying the data. Tough luck. - * - Destination page already exists in the address space, but there - * are no users of it. Make sure it's uptodate, then drop it. Fall - * through to last case. - * - Destination page does not exist, we can add the pipe page to - * the page cache and avoid the copy. - * - * If asked to move pages to the output file (SPLICE_F_MOVE is set in - * sd->flags), we attempt to migrate pages from the pipe to the output - * file address space page cache. This is possible if no one else has - * the pipe page referenced outside of the pipe and page cache. If - * SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create - * a new page in the output file page cache and fill/dirty that. - */ -int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf, - struct splice_desc *sd) -{ - struct file *file = sd->u.file; - struct address_space *mapping = file->f_mapping; - unsigned int offset, this_len; - struct page *page; - void *fsdata; - int ret; - - offset = sd->pos & ~PAGE_CACHE_MASK; - - this_len = sd->len; - if (this_len + offset > PAGE_CACHE_SIZE) - this_len = PAGE_CACHE_SIZE - offset; - - ret = pagecache_write_begin(file, mapping, sd->pos, this_len, - AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata); - if (unlikely(ret)) - goto out; - - if (buf->page != page) { - char *src = kmap_atomic(buf->page); - char *dst = kmap_atomic(page); - - memcpy(dst + offset, src + buf->offset, this_len); - flush_dcache_page(page); - kunmap_atomic(dst); - kunmap_atomic(src); - } - ret = pagecache_write_end(file, mapping, sd->pos, this_len, this_len, - page, fsdata); -out: - return ret; -} -EXPORT_SYMBOL(pipe_to_file); - static void wakeup_pipe_writers(struct pipe_inode_info *pipe) { smp_mb(); @@ -802,7 +746,7 @@ static void wakeup_pipe_writers(struct pipe_inode_info *pipe) * locking is required around copying the pipe buffers to the * destination. */ -int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, +static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, splice_actor *actor) { int ret; @@ -849,7 +793,6 @@ int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_desc *sd, return 1; } -EXPORT_SYMBOL(splice_from_pipe_feed); /** * splice_from_pipe_next - wait for some data to splice from @@ -861,7 +804,7 @@ EXPORT_SYMBOL(splice_from_pipe_feed); * value (one) if pipe buffers are available. It will return zero * or -errno if no more data needs to be spliced. */ -int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) +static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) { while (!pipe->nrbufs) { if (!pipe->writers) @@ -886,7 +829,6 @@ int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_desc *sd) return 1; } -EXPORT_SYMBOL(splice_from_pipe_next); /** * splice_from_pipe_begin - start splicing from pipe @@ -897,12 +839,11 @@ EXPORT_SYMBOL(splice_from_pipe_next); * splice_from_pipe_next() and splice_from_pipe_feed() to * initialize the necessary fields of @sd. */ -void splice_from_pipe_begin(struct splice_desc *sd) +static void splice_from_pipe_begin(struct splice_desc *sd) { sd->num_spliced = 0; sd->need_wakeup = false; } -EXPORT_SYMBOL(splice_from_pipe_begin); /** * splice_from_pipe_end - finish splicing from pipe @@ -914,12 +855,11 @@ EXPORT_SYMBOL(splice_from_pipe_begin); * be called after a loop containing splice_from_pipe_next() and * splice_from_pipe_feed(). */ -void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) +static void splice_from_pipe_end(struct pipe_inode_info *pipe, struct splice_desc *sd) { if (sd->need_wakeup) wakeup_pipe_writers(pipe); } -EXPORT_SYMBOL(splice_from_pipe_end); /** * __splice_from_pipe - splice data from a pipe to given actor @@ -985,7 +925,7 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, } /** - * generic_file_splice_write - splice data from a pipe to a file + * iter_file_splice_write - splice data from a pipe to a file * @pipe: pipe info * @out: file to write to * @ppos: position in @out @@ -995,40 +935,122 @@ ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out, * Description: * Will either move or copy pages (determined by @flags options) from * the given pipe inode to the given file. + * This one is ->write_iter-based. * */ ssize_t -generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, +iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { - struct address_space *mapping = out->f_mapping; - struct inode *inode = mapping->host; struct splice_desc sd = { .total_len = len, .flags = flags, .pos = *ppos, .u.file = out, }; + int nbufs = pipe->buffers; + struct bio_vec *array = kcalloc(nbufs, sizeof(struct bio_vec), + GFP_KERNEL); ssize_t ret; + if (unlikely(!array)) + return -ENOMEM; + pipe_lock(pipe); splice_from_pipe_begin(&sd); - do { + while (sd.total_len) { + struct iov_iter from; + struct kiocb kiocb; + size_t left; + int n, idx; + ret = splice_from_pipe_next(pipe, &sd); if (ret <= 0) break; - mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD); - ret = file_remove_suid(out); - if (!ret) { - ret = file_update_time(out); - if (!ret) - ret = splice_from_pipe_feed(pipe, &sd, - pipe_to_file); + if (unlikely(nbufs < pipe->buffers)) { + kfree(array); + nbufs = pipe->buffers; + array = kcalloc(nbufs, sizeof(struct bio_vec), + GFP_KERNEL); + if (!array) { + ret = -ENOMEM; + break; + } } - mutex_unlock(&inode->i_mutex); - } while (ret > 0); + + /* build the vector */ + left = sd.total_len; + for (n = 0, idx = pipe->curbuf; left && n < pipe->nrbufs; n++, idx++) { + struct pipe_buffer *buf = pipe->bufs + idx; + size_t this_len = buf->len; + + if (this_len > left) + this_len = left; + + if (idx == pipe->buffers - 1) + idx = -1; + + ret = buf->ops->confirm(pipe, buf); + if (unlikely(ret)) { + if (ret == -ENODATA) + ret = 0; + goto done; + } + + array[n].bv_page = buf->page; + array[n].bv_len = this_len; + array[n].bv_offset = buf->offset; + left -= this_len; + } + + /* ... iov_iter */ + from.type = ITER_BVEC | WRITE; + from.bvec = array; + from.nr_segs = n; + from.count = sd.total_len - left; + from.iov_offset = 0; + + /* ... and iocb */ + init_sync_kiocb(&kiocb, out); + kiocb.ki_pos = sd.pos; + kiocb.ki_nbytes = sd.total_len - left; + + /* now, send it */ + ret = out->f_op->write_iter(&kiocb, &from); + if (-EIOCBQUEUED == ret) + ret = wait_on_sync_kiocb(&kiocb); + + if (ret <= 0) + break; + + sd.num_spliced += ret; + sd.total_len -= ret; + *ppos = sd.pos = kiocb.ki_pos; + + /* dismiss the fully eaten buffers, adjust the partial one */ + while (ret) { + struct pipe_buffer *buf = pipe->bufs + pipe->curbuf; + if (ret >= buf->len) { + const struct pipe_buf_operations *ops = buf->ops; + ret -= buf->len; + buf->len = 0; + buf->ops = NULL; + ops->release(pipe, buf); + pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); + pipe->nrbufs--; + if (pipe->files) + sd.need_wakeup = true; + } else { + buf->offset += ret; + buf->len -= ret; + ret = 0; + } + } + } +done: + kfree(array); splice_from_pipe_end(pipe, &sd); pipe_unlock(pipe); @@ -1036,21 +1058,10 @@ generic_file_splice_write(struct pipe_inode_info *pipe, struct file *out, if (sd.num_spliced) ret = sd.num_spliced; - if (ret > 0) { - int err; - - err = generic_write_sync(out, *ppos, ret); - if (err) - ret = err; - else - *ppos += ret; - balance_dirty_pages_ratelimited(mapping); - } - return ret; } -EXPORT_SYMBOL(generic_file_splice_write); +EXPORT_SYMBOL(iter_file_splice_write); static int write_pipe_buf(struct pipe_inode_info *pipe, struct pipe_buffer *buf, struct splice_desc *sd) @@ -1549,7 +1560,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov, goto out; count = ret; - iov_iter_init(&iter, iov, nr_segs, count, 0); + iov_iter_init(&iter, READ, iov, nr_segs, count); sd.len = 0; sd.total_len = count; diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 9d4dc683179..b00811c75b2 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -21,10 +21,10 @@ */ const struct file_operations sysv_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 0ab7f7dfb98..b5b593c4527 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1364,17 +1364,17 @@ static inline int mctime_update_needed(const struct inode *inode, /** * update_ctime - update mtime and ctime of an inode. - * @c: UBIFS file-system description object * @inode: inode to update * * This function updates mtime and ctime of the inode if it is not equivalent to * current time. Returns zero in case of success and a negative error code in * case of failure. */ -static int update_mctime(struct ubifs_info *c, struct inode *inode) +static int update_mctime(struct inode *inode) { struct timespec now = ubifs_current_time(inode); struct ubifs_inode *ui = ubifs_inode(inode); + struct ubifs_info *c = inode->i_sb->s_fs_info; if (mctime_update_needed(inode, &now)) { int err, release; @@ -1397,18 +1397,13 @@ static int update_mctime(struct ubifs_info *c, struct inode *inode) return 0; } -static ssize_t ubifs_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +static ssize_t ubifs_write_iter(struct kiocb *iocb, struct iov_iter *from) { - int err; - struct inode *inode = iocb->ki_filp->f_mapping->host; - struct ubifs_info *c = inode->i_sb->s_fs_info; - - err = update_mctime(c, inode); + int err = update_mctime(file_inode(iocb->ki_filp)); if (err) return err; - return generic_file_aio_write(iocb, iov, nr_segs, pos); + return generic_file_write_iter(iocb, from); } static int ubifs_set_page_dirty(struct page *page) @@ -1582,15 +1577,15 @@ const struct inode_operations ubifs_symlink_inode_operations = { const struct file_operations ubifs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = ubifs_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = ubifs_write_iter, .mmap = ubifs_file_mmap, .fsync = ubifs_fsync, .unlocked_ioctl = ubifs_ioctl, .splice_read = generic_file_splice_read, - .splice_write = generic_file_splice_write, + .splice_write = iter_file_splice_write, #ifdef CONFIG_COMPAT .compat_ioctl = ubifs_compat_ioctl, #endif diff --git a/fs/udf/file.c b/fs/udf/file.c index d2c170f8b03..d80738fdf42 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -119,8 +119,8 @@ static int udf_adinicb_write_end(struct file *file, } static ssize_t udf_adinicb_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { /* Fallback to buffered I/O. */ return 0; @@ -134,8 +134,7 @@ const struct address_space_operations udf_adinicb_aops = { .direct_IO = udf_adinicb_direct_IO, }; -static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t ppos) +static ssize_t udf_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { ssize_t retval; struct file *file = iocb->ki_filp; @@ -150,7 +149,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (file->f_flags & O_APPEND) pos = inode->i_size; else - pos = ppos; + pos = iocb->ki_pos; if (inode->i_sb->s_blocksize < (udf_file_entry_alloc_offset(inode) + @@ -171,7 +170,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov, } else up_write(&iinfo->i_data_sem); - retval = __generic_file_aio_write(iocb, iov, nr_segs); + retval = __generic_file_write_iter(iocb, from); mutex_unlock(&inode->i_mutex); if (retval > 0) { @@ -252,13 +251,13 @@ static int udf_release_file(struct inode *inode, struct file *filp) } const struct file_operations udf_file_operations = { - .read = do_sync_read, - .aio_read = generic_file_aio_read, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .unlocked_ioctl = udf_ioctl, .open = generic_file_open, .mmap = generic_file_mmap, - .write = do_sync_write, - .aio_write = udf_file_aio_write, + .write = new_sync_write, + .write_iter = udf_file_write_iter, .release = udf_release_file, .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5d643706212..236cd48184c 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -217,18 +217,18 @@ static int udf_write_begin(struct file *file, struct address_space *mapping, } static ssize_t udf_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); ssize_t ret; - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - udf_get_block); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, udf_get_block); if (unlikely(ret < 0 && (rw & WRITE))) - udf_write_failed(mapping, offset + iov_length(iov, nr_segs)); + udf_write_failed(mapping, offset + count); return ret; } diff --git a/fs/ufs/file.c b/fs/ufs/file.c index 33afa20d450..c84ec010a67 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -35,10 +35,10 @@ const struct file_operations ufs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .aio_read = generic_file_aio_read, - .write = do_sync_write, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .read_iter = generic_file_read_iter, + .write = new_sync_write, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .open = generic_file_open, .fsync = generic_file_fsync, diff --git a/fs/xattr.c b/fs/xattr.c index 3377dff1840..c69e6d43a0d 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -843,7 +843,7 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) /* wrap around? */ len = sizeof(*new_xattr) + size; - if (len <= sizeof(*new_xattr)) + if (len < sizeof(*new_xattr)) return NULL; new_xattr = kmalloc(len, GFP_KERNEL); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e32640eedea..faaf716e208 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1486,9 +1486,8 @@ STATIC ssize_t xfs_vm_direct_IO( int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); @@ -1496,7 +1495,7 @@ xfs_vm_direct_IO( ssize_t ret; if (rw & WRITE) { - size_t size = iov_length(iov, nr_segs); + size_t size = iov_iter_count(iter); /* * We cannot preallocate a size update transaction here as we @@ -1508,17 +1507,15 @@ xfs_vm_direct_IO( if (offset + size > XFS_I(inode)->i_d.di_size) ioend->io_isdirect = 1; - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, - xfs_get_blocks_direct, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); if (ret != -EIOCBQUEUED && iocb->private) goto out_destroy_ioend; } else { - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, - xfs_get_blocks_direct, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, NULL, NULL, 0); } diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 96175df211b..75c3fe5f3d9 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -4298,8 +4298,8 @@ xfs_bmapi_delay( } -int -__xfs_bmapi_allocate( +static int +xfs_bmapi_allocate( struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; @@ -4578,9 +4578,6 @@ xfs_bmapi_write( bma.flist = flist; bma.firstblock = firstblock; - if (flags & XFS_BMAPI_STACK_SWITCH) - bma.stack_switch = 1; - while (bno < end && n < *nmap) { inhole = eof || bma.got.br_startoff > bno; wasdelay = !inhole && isnullstartblock(bma.got.br_startblock); diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 38ba36e9b2f..b879ca56a64 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -77,7 +77,6 @@ typedef struct xfs_bmap_free * from written to unwritten, otherwise convert from unwritten to written. */ #define XFS_BMAPI_CONVERT 0x040 -#define XFS_BMAPI_STACK_SWITCH 0x080 #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ @@ -86,8 +85,7 @@ typedef struct xfs_bmap_free { XFS_BMAPI_PREALLOC, "PREALLOC" }, \ { XFS_BMAPI_IGSTATE, "IGSTATE" }, \ { XFS_BMAPI_CONTIG, "CONTIG" }, \ - { XFS_BMAPI_CONVERT, "CONVERT" }, \ - { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" } + { XFS_BMAPI_CONVERT, "CONVERT" } static inline int xfs_bmapi_aflag(int w) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 703b3ec1796..64731ef3324 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -249,59 +249,6 @@ xfs_bmap_rtalloc( } /* - * Stack switching interfaces for allocation - */ -static void -xfs_bmapi_allocate_worker( - struct work_struct *work) -{ - struct xfs_bmalloca *args = container_of(work, - struct xfs_bmalloca, work); - unsigned long pflags; - unsigned long new_pflags = PF_FSTRANS; - - /* - * we are in a transaction context here, but may also be doing work - * in kswapd context, and hence we may need to inherit that state - * temporarily to ensure that we don't block waiting for memory reclaim - * in any way. - */ - if (args->kswapd) - new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; - - current_set_flags_nested(&pflags, new_pflags); - - args->result = __xfs_bmapi_allocate(args); - complete(args->done); - - current_restore_flags_nested(&pflags, new_pflags); -} - -/* - * Some allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Otherwise just - * call directly to avoid the context switch overhead here. - */ -int -xfs_bmapi_allocate( - struct xfs_bmalloca *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->stack_switch) - return __xfs_bmapi_allocate(args); - - - args->done = &done; - args->kswapd = current_is_kswapd(); - INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - destroy_work_on_stack(&args->work); - return args->result; -} - -/* * Check if the endoff is outside the last extent. If so the caller will grow * the allocation to a stripe unit boundary. All offsets are considered outside * the end of file for an empty fork, so 1 is returned in *eof in that case. diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 075f72232a6..2fdb72d2c90 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -55,8 +55,6 @@ struct xfs_bmalloca { bool userdata;/* set if is user data */ bool aeof; /* allocated space at eof */ bool conv; /* overwriting unwritten extents */ - bool stack_switch; - bool kswapd; /* allocation in kswapd context */ int flags; struct completion *done; struct work_struct work; @@ -66,8 +64,6 @@ struct xfs_bmalloca { int xfs_bmap_finish(struct xfs_trans **tp, struct xfs_bmap_free *flist, int *committed); int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); -int xfs_bmapi_allocate(struct xfs_bmalloca *args); -int __xfs_bmapi_allocate(struct xfs_bmalloca *args); int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c index bf810c6baf2..cf893bc1e37 100644 --- a/fs/xfs/xfs_btree.c +++ b/fs/xfs/xfs_btree.c @@ -33,6 +33,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_cksum.h" +#include "xfs_alloc.h" /* * Cursor allocation zone. @@ -2323,7 +2324,7 @@ error1: * record (to be inserted into parent). */ STATIC int /* error */ -xfs_btree_split( +__xfs_btree_split( struct xfs_btree_cur *cur, int level, union xfs_btree_ptr *ptrp, @@ -2503,6 +2504,85 @@ error0: return error; } +struct xfs_btree_split_args { + struct xfs_btree_cur *cur; + int level; + union xfs_btree_ptr *ptrp; + union xfs_btree_key *key; + struct xfs_btree_cur **curp; + int *stat; /* success/failure */ + int result; + bool kswapd; /* allocation in kswapd context */ + struct completion *done; + struct work_struct work; +}; + +/* + * Stack switching interfaces for allocation + */ +static void +xfs_btree_split_worker( + struct work_struct *work) +{ + struct xfs_btree_split_args *args = container_of(work, + struct xfs_btree_split_args, work); + unsigned long pflags; + unsigned long new_pflags = PF_FSTRANS; + + /* + * we are in a transaction context here, but may also be doing work + * in kswapd context, and hence we may need to inherit that state + * temporarily to ensure that we don't block waiting for memory reclaim + * in any way. + */ + if (args->kswapd) + new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; + + current_set_flags_nested(&pflags, new_pflags); + + args->result = __xfs_btree_split(args->cur, args->level, args->ptrp, + args->key, args->curp, args->stat); + complete(args->done); + + current_restore_flags_nested(&pflags, new_pflags); +} + +/* + * BMBT split requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. For the other + * btree types, just call directly to avoid the context switch overhead here. + */ +STATIC int /* error */ +xfs_btree_split( + struct xfs_btree_cur *cur, + int level, + union xfs_btree_ptr *ptrp, + union xfs_btree_key *key, + struct xfs_btree_cur **curp, + int *stat) /* success/failure */ +{ + struct xfs_btree_split_args args; + DECLARE_COMPLETION_ONSTACK(done); + + if (cur->bc_btnum != XFS_BTNUM_BMAP) + return __xfs_btree_split(cur, level, ptrp, key, curp, stat); + + args.cur = cur; + args.level = level; + args.ptrp = ptrp; + args.key = key; + args.curp = curp; + args.stat = stat; + args.done = &done; + args.kswapd = current_is_kswapd(); + INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker); + queue_work(xfs_alloc_wq, &args.work); + wait_for_completion(&done); + destroy_work_on_stack(&args.work); + return args.result; +} + + /* * Copy the old inode root contents into a real block and make the * broot point to it. diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1b8160dc04d..1f66779d7a4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -229,34 +229,27 @@ xfs_file_fsync( } STATIC ssize_t -xfs_file_aio_read( +xfs_file_read_iter( struct kiocb *iocb, - const struct iovec *iovp, - unsigned long nr_segs, - loff_t pos) + struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - size_t size = 0; + size_t size = iov_iter_count(to); ssize_t ret = 0; int ioflags = 0; xfs_fsize_t n; + loff_t pos = iocb->ki_pos; XFS_STATS_INC(xs_read_calls); - BUG_ON(iocb->ki_pos != pos); - if (unlikely(file->f_flags & O_DIRECT)) ioflags |= IO_ISDIRECT; if (file->f_mode & FMODE_NOCMTIME) ioflags |= IO_INVIS; - ret = generic_segment_checks(iovp, &nr_segs, &size, VERIFY_WRITE); - if (ret < 0) - return ret; - if (unlikely(ioflags & IO_ISDIRECT)) { xfs_buftarg_t *target = XFS_IS_REALTIME_INODE(ip) ? @@ -309,7 +302,7 @@ xfs_file_aio_read( trace_xfs_file_read(ip, size, pos, ioflags); - ret = generic_file_aio_read(iocb, iovp, nr_segs, pos); + ret = generic_file_read_iter(iocb, to); if (ret > 0) XFS_STATS_ADD(xs_read_bytes, ret); @@ -350,47 +343,6 @@ xfs_file_splice_read( } /* - * xfs_file_splice_write() does not use xfs_rw_ilock() because - * generic_file_splice_write() takes the i_mutex itself. This, in theory, - * couuld cause lock inversions between the aio_write path and the splice path - * if someone is doing concurrent splice(2) based writes and write(2) based - * writes to the same inode. The only real way to fix this is to re-implement - * the generic code here with correct locking orders. - */ -STATIC ssize_t -xfs_file_splice_write( - struct pipe_inode_info *pipe, - struct file *outfilp, - loff_t *ppos, - size_t count, - unsigned int flags) -{ - struct inode *inode = outfilp->f_mapping->host; - struct xfs_inode *ip = XFS_I(inode); - int ioflags = 0; - ssize_t ret; - - XFS_STATS_INC(xs_write_calls); - - if (outfilp->f_mode & FMODE_NOCMTIME) - ioflags |= IO_INVIS; - - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) - return -EIO; - - xfs_ilock(ip, XFS_IOLOCK_EXCL); - - trace_xfs_file_splice_write(ip, count, *ppos, ioflags); - - ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags); - if (ret > 0) - XFS_STATS_ADD(xs_write_bytes, ret); - - xfs_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; -} - -/* * This routine is called to handle zeroing any space in the last block of the * file that is beyond the EOF. We do this since the size is being increased * without writing anything to that block and we don't want to read the @@ -625,10 +577,7 @@ restart: STATIC ssize_t xfs_file_dio_aio_write( struct kiocb *iocb, - const struct iovec *iovp, - unsigned long nr_segs, - loff_t pos, - size_t ocount) + struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -636,9 +585,10 @@ xfs_file_dio_aio_write( struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; ssize_t ret = 0; - size_t count = ocount; int unaligned_io = 0; int iolock; + size_t count = iov_iter_count(from); + loff_t pos = iocb->ki_pos; struct xfs_buftarg *target = XFS_IS_REALTIME_INODE(ip) ? mp->m_rtdev_targp : mp->m_ddev_targp; @@ -677,6 +627,7 @@ xfs_file_dio_aio_write( ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock); if (ret) goto out; + iov_iter_truncate(from, count); if (mapping->nrpages) { ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, @@ -698,8 +649,7 @@ xfs_file_dio_aio_write( } trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0); - ret = generic_file_direct_write(iocb, iovp, - &nr_segs, pos, count, ocount); + ret = generic_file_direct_write(iocb, from, pos); out: xfs_rw_iunlock(ip, iolock); @@ -712,10 +662,7 @@ out: STATIC ssize_t xfs_file_buffered_aio_write( struct kiocb *iocb, - const struct iovec *iovp, - unsigned long nr_segs, - loff_t pos, - size_t count) + struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; @@ -724,7 +671,8 @@ xfs_file_buffered_aio_write( ssize_t ret; int enospc = 0; int iolock = XFS_IOLOCK_EXCL; - struct iov_iter from; + loff_t pos = iocb->ki_pos; + size_t count = iov_iter_count(from); xfs_rw_ilock(ip, iolock); @@ -732,13 +680,13 @@ xfs_file_buffered_aio_write( if (ret) goto out; - iov_iter_init(&from, iovp, nr_segs, count, 0); + iov_iter_truncate(from, count); /* We can write back this queue in page reclaim */ current->backing_dev_info = mapping->backing_dev_info; write_retry: trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0); - ret = generic_perform_write(file, &from, pos); + ret = generic_perform_write(file, from, pos); if (likely(ret >= 0)) iocb->ki_pos = pos + ret; /* @@ -759,40 +707,29 @@ out: } STATIC ssize_t -xfs_file_aio_write( +xfs_file_write_iter( struct kiocb *iocb, - const struct iovec *iovp, - unsigned long nr_segs, - loff_t pos) + struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct xfs_inode *ip = XFS_I(inode); ssize_t ret; - size_t ocount = 0; + size_t ocount = iov_iter_count(from); XFS_STATS_INC(xs_write_calls); - BUG_ON(iocb->ki_pos != pos); - - ret = generic_segment_checks(iovp, &nr_segs, &ocount, VERIFY_READ); - if (ret) - return ret; - if (ocount == 0) return 0; - if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { - ret = -EIO; - goto out; - } + if (XFS_FORCED_SHUTDOWN(ip->i_mount)) + return -EIO; if (unlikely(file->f_flags & O_DIRECT)) - ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount); + ret = xfs_file_dio_aio_write(iocb, from); else - ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos, - ocount); + ret = xfs_file_buffered_aio_write(iocb, from); if (ret > 0) { ssize_t err; @@ -804,8 +741,6 @@ xfs_file_aio_write( if (err < 0) ret = err; } - -out: return ret; } @@ -1461,12 +1396,12 @@ xfs_file_llseek( const struct file_operations xfs_file_operations = { .llseek = xfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = xfs_file_aio_read, - .aio_write = xfs_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = xfs_file_read_iter, + .write_iter = xfs_file_write_iter, .splice_read = xfs_file_splice_read, - .splice_write = xfs_file_splice_write, + .splice_write = iter_file_splice_write, .unlocked_ioctl = xfs_file_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = xfs_file_compat_ioctl, diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 6c5eb4c551e..6d3ec2b6ee2 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -749,8 +749,7 @@ xfs_iomap_write_allocate( * pointer that the caller gave to us. */ error = xfs_bmapi_write(tp, ip, map_start_fsb, - count_fsb, - XFS_BMAPI_STACK_SWITCH, + count_fsb, 0, &first_block, 1, imap, &nimaps, &free_list); if (error) diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c index c3453b11f56..7703fa6770f 100644 --- a/fs/xfs/xfs_sb.c +++ b/fs/xfs/xfs_sb.c @@ -483,10 +483,16 @@ xfs_sb_quota_to_disk( } /* - * GQUOTINO and PQUOTINO cannot be used together in versions - * of superblock that do not have pquotino. from->sb_flags - * tells us which quota is active and should be copied to - * disk. + * GQUOTINO and PQUOTINO cannot be used together in versions of + * superblock that do not have pquotino. from->sb_flags tells us which + * quota is active and should be copied to disk. If neither are active, + * make sure we write NULLFSINO to the sb_gquotino field as a quota + * inode value of "0" is invalid when the XFS_SB_VERSION_QUOTA feature + * bit is set. + * + * Note that we don't need to handle the sb_uquotino or sb_pquotino here + * as they do not require any translation. Hence the main sb field loop + * will write them appropriately from the in-core superblock. */ if ((*fields & XFS_SB_GQUOTINO) && (from->sb_qflags & XFS_GQUOTA_ACCT)) @@ -494,6 +500,17 @@ xfs_sb_quota_to_disk( else if ((*fields & XFS_SB_PQUOTINO) && (from->sb_qflags & XFS_PQUOTA_ACCT)) to->sb_gquotino = cpu_to_be64(from->sb_pquotino); + else { + /* + * We can't rely on just the fields being logged to tell us + * that it is safe to write NULLFSINO - we should only do that + * if quotas are not actually enabled. Hence only write + * NULLFSINO if both in-core quota inodes are NULL. + */ + if (from->sb_gquotino == NULLFSINO && + from->sb_pquotino == NULLFSINO) + to->sb_gquotino = cpu_to_be64(NULLFSINO); + } *fields &= ~(XFS_SB_PQUOTINO | XFS_SB_GQUOTINO); } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 6910458915c..152f8278263 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1118,7 +1118,6 @@ DEFINE_RW_EVENT(xfs_file_read); DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_splice_read); -DEFINE_RW_EVENT(xfs_file_splice_write); DECLARE_EVENT_CLASS(xfs_page_class, TP_PROTO(struct inode *inode, struct page *page, unsigned long off, |