diff options
Diffstat (limited to 'fs')
104 files changed, 1170 insertions, 1405 deletions
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index c71e88602ff4..cc1cfae726b3 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 d8223209d4b1..b9b5f979a2ca 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -695,7 +695,7 @@ 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); } /** @@ -763,7 +763,7 @@ 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); } /** @@ -781,7 +781,7 @@ 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); } @@ -850,8 +850,8 @@ 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, @@ -863,8 +863,8 @@ 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 a36da5382b40..07c9edce5aa7 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 8669b6ecddee..9df23175e28b 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/affs/super.c b/fs/affs/super.c index 6d589f28bf9b..895ac7dc9dbf 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -340,8 +340,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) &blocksize,&sbi->s_prefix, sbi->s_volume, &mount_flags)) { printk(KERN_ERR "AFFS: Error parsing options\n"); - kfree(sbi->s_prefix); - kfree(sbi); return -EINVAL; } /* N.B. after this point s_prefix must be released */ diff --git a/fs/afs/file.c b/fs/afs/file.c index 66d50fe2ee45..26fd19bfccc3 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -31,9 +31,9 @@ const struct file_operations afs_file_operations = { .open = afs_open, .release = afs_release, .llseek = generic_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .aio_write = afs_file_write, .mmap = generic_file_readonly_mmap, .splice_read = generic_file_splice_read, @@ -112,6 +112,11 @@ struct kioctx { struct work_struct free_work; + /* + * signals when all in-flight requests are done + */ + struct completion *requests_done; + struct { /* * This counts the number of available slots in the ringbuffer, @@ -508,6 +513,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); + /* At this point we know that there are no any in-flight requests */ + if (ctx->requests_done) + complete(ctx->requests_done); + INIT_WORK(&ctx->free_work, free_ioctx); schedule_work(&ctx->free_work); } @@ -718,7 +727,8 @@ 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 void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, + struct completion *requests_done) { if (!atomic_xchg(&ctx->dead, 1)) { struct kioctx_table *table; @@ -747,7 +757,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx) if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); + ctx->requests_done = requests_done; percpu_ref_kill(&ctx->users); + } else { + if (requests_done) + complete(requests_done); } } @@ -809,7 +823,7 @@ void exit_aio(struct mm_struct *mm) */ ctx->mmap_size = 0; - kill_ioctx(mm, ctx); + kill_ioctx(mm, ctx, NULL); } } @@ -1185,7 +1199,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) - kill_ioctx(current->mm, ioctx); + kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } @@ -1203,8 +1217,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { - kill_ioctx(current->mm, ioctx); + struct completion requests_done = + COMPLETION_INITIALIZER_ONSTACK(requests_done); + + /* 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); 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); + return 0; } pr_debug("EINVAL: io_destroy: invalid context id\n"); @@ -1213,6 +1241,7 @@ 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, @@ -1270,7 +1299,9 @@ 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: @@ -1278,6 +1309,7 @@ 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: @@ -1285,12 +1317,13 @@ 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 || @@ -1299,10 +1332,8 @@ rw_common: &iovec, compat) : aio_setup_single_vector(req, rw, buf, &nr_segs, iovec); - if (ret) - return ret; - - ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); + if (!ret) + ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes); if (ret < 0) { if (iovec != &inline_vec) kfree(iovec); @@ -1321,7 +1352,12 @@ 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); diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index 2caf36ac3e93..cc87c1abac97 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -179,7 +179,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry) spin_lock(&active->d_lock); /* Already gone? */ - if (!d_count(active)) + if ((int) d_count(active) <= 0) goto next; qstr = &active->d_name; @@ -230,7 +230,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry) spin_lock(&expiring->d_lock); - /* Bad luck, we've already been dentry_iput */ + /* We've already been dentry_iput or unlinked */ if (!expiring->d_inode) goto next; diff --git a/fs/bfs/file.c b/fs/bfs/file.c index ae2892218335..e7f88ace1a25 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 552a8d13bc32..4e36b8ea8aa4 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) @@ -1508,43 +1509,38 @@ 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); } /* @@ -1576,10 +1572,10 @@ 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, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4c48df572bd6..ba6b88528dc7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2058,6 +2058,20 @@ struct btrfs_ioctl_defrag_range_args { #define btrfs_raw_test_opt(o, opt) ((o) & BTRFS_MOUNT_##opt) #define btrfs_test_opt(root, opt) ((root)->fs_info->mount_opt & \ BTRFS_MOUNT_##opt) +#define btrfs_set_and_info(root, opt, fmt, args...) \ +{ \ + if (!btrfs_test_opt(root, opt)) \ + btrfs_info(root->fs_info, fmt, ##args); \ + btrfs_set_opt(root->fs_info->mount_opt, opt); \ +} + +#define btrfs_clear_and_info(root, opt, fmt, args...) \ +{ \ + if (btrfs_test_opt(root, opt)) \ + btrfs_info(root->fs_info, fmt, ##args); \ + btrfs_clear_opt(root->fs_info->mount_opt, opt); \ +} + /* * Inode flags */ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 029d46c2e170..983314932af3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2861,7 +2861,7 @@ retry_root_backup: printk(KERN_ERR "BTRFS: failed to read log tree\n"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); - goto fail_trans_kthread; + goto fail_qgroup; } /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); @@ -2870,24 +2870,24 @@ retry_root_backup: "Failed to recover log tree"); free_extent_buffer(log_tree_root->node); kfree(log_tree_root); - goto fail_trans_kthread; + goto fail_qgroup; } if (sb->s_flags & MS_RDONLY) { ret = btrfs_commit_super(tree_root); if (ret) - goto fail_trans_kthread; + goto fail_qgroup; } } ret = btrfs_find_orphan_roots(tree_root); if (ret) - goto fail_trans_kthread; + goto fail_qgroup; if (!(sb->s_flags & MS_RDONLY)) { ret = btrfs_cleanup_fs_roots(fs_info); if (ret) - goto fail_trans_kthread; + goto fail_qgroup; ret = btrfs_recover_relocation(tree_root); if (ret < 0) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1306487c82cf..5590af92094b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1542,6 +1542,7 @@ again: ret = 0; } if (ret) { + key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; btrfs_release_path(path); @@ -3542,11 +3543,13 @@ static u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags) return extended_to_chunk(flags | tmp); } -static u64 get_alloc_profile(struct btrfs_root *root, u64 flags) +static u64 get_alloc_profile(struct btrfs_root *root, u64 orig_flags) { unsigned seq; + u64 flags; do { + flags = orig_flags; seq = read_seqbegin(&root->fs_info->profiles_lock); if (flags & BTRFS_BLOCK_GROUP_DATA) @@ -5719,6 +5722,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, if (ret > 0 && skinny_metadata) { skinny_metadata = false; + key.objectid = bytenr; key.type = BTRFS_EXTENT_ITEM_KEY; key.offset = num_bytes; btrfs_release_path(path); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index eb742c07e7a4..39014d5db9d5 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -800,7 +800,7 @@ next_slot: if (start > key.offset && end < extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { - ret = -EINVAL; + ret = -EOPNOTSUPP; break; } @@ -846,7 +846,7 @@ next_slot: */ if (start <= key.offset && end < extent_end) { if (extent_type == BTRFS_FILE_EXTENT_INLINE) { - ret = -EINVAL; + ret = -EOPNOTSUPP; break; } @@ -872,7 +872,7 @@ next_slot: if (start > key.offset && end >= extent_end) { BUG_ON(del_nr > 0); if (extent_type == BTRFS_FILE_EXTENT_INLINE) { - ret = -EINVAL; + ret = -EOPNOTSUPP; break; } @@ -1658,27 +1658,22 @@ 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; @@ -1724,17 +1719,14 @@ 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; bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host); + struct iov_iter i; 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; + count = iov_length(iov, nr_segs); + iov_iter_init(&i, WRITE, iov, nr_segs, count); current->backing_dev_info = inode->i_mapping->backing_dev_info; err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); @@ -1748,6 +1740,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, goto out; } + iov_iter_truncate(&i, count); + err = file_remove_suid(file); if (err) { mutex_unlock(&inode->i_mutex); @@ -1777,7 +1771,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, start_pos = round_down(pos, root->sectorsize); if (start_pos > i_size_read(inode)) { /* Expand hole size to cover write data, preventing empty gap */ - end_pos = round_up(pos + iov->iov_len, root->sectorsize); + end_pos = round_up(pos + count, root->sectorsize); err = btrfs_cont_expand(inode, i_size_read(inode), end_pos); if (err) { mutex_unlock(&inode->i_mutex); @@ -1789,13 +1783,8 @@ 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, &i, pos); } else { - struct iov_iter i; - - iov_iter_init(&i, iov, nr_segs, count, num_written); - num_written = __btrfs_buffered_write(file, &i, pos); if (num_written > 0) iocb->ki_pos = pos + num_written; @@ -2633,9 +2622,9 @@ out: const struct file_operations btrfs_file_operations = { .llseek = btrfs_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .splice_read = generic_file_splice_read, .aio_write = btrfs_file_aio_write, .mmap = btrfs_file_mmap, diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index cc8ca193d830..86935f5ae291 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -176,7 +176,11 @@ static void start_caching(struct btrfs_root *root) tsk = kthread_run(caching_kthread, root, "btrfs-ino-cache-%llu\n", root->root_key.objectid); - BUG_ON(IS_ERR(tsk)); /* -ENOMEM */ + if (IS_ERR(tsk)) { + btrfs_warn(root->fs_info, "failed to start inode caching task"); + btrfs_clear_and_info(root, CHANGE_INODE_CACHE, + "disabling inode map caching"); + } } int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid) @@ -205,24 +209,14 @@ again: void btrfs_return_ino(struct btrfs_root *root, u64 objectid) { - struct btrfs_free_space_ctl *ctl = root->free_ino_ctl; struct btrfs_free_space_ctl *pinned = root->free_ino_pinned; if (!btrfs_test_opt(root, INODE_MAP_CACHE)) return; - again: if (root->cached == BTRFS_CACHE_FINISHED) { - __btrfs_add_free_space(ctl, objectid, 1); + __btrfs_add_free_space(pinned, objectid, 1); } else { - /* - * If we are in the process of caching free ino chunks, - * to avoid adding the same inode number to the free_ino - * tree twice due to cross transaction, we'll leave it - * in the pinned tree until a transaction is committed - * or the caching work is done. - */ - down_write(&root->fs_info->commit_root_sem); spin_lock(&root->cache_lock); if (root->cached == BTRFS_CACHE_FINISHED) { @@ -234,11 +228,7 @@ again: start_caching(root); - if (objectid <= root->cache_progress || - objectid >= root->highest_objectid) - __btrfs_add_free_space(ctl, objectid, 1); - else - __btrfs_add_free_space(pinned, objectid, 1); + __btrfs_add_free_space(pinned, objectid, 1); up_write(&root->fs_info->commit_root_sem); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5f805bc944fa..c8386f1961f0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7391,39 +7391,30 @@ 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; } } @@ -7433,8 +7424,7 @@ 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; @@ -7444,8 +7434,7 @@ 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); @@ -7457,7 +7446,7 @@ 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); @@ -7484,7 +7473,7 @@ 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) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e79ff6b90cb7..2ad7de94efef 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3066,7 +3066,7 @@ process_slot: new_key.offset + datal, 1); if (ret) { - if (ret != -EINVAL) + if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, root, ret); btrfs_end_transaction(trans, root); @@ -3141,7 +3141,7 @@ process_slot: new_key.offset + datal, 1); if (ret) { - if (ret != -EINVAL) + if (ret != -EOPNOTSUPP) btrfs_abort_transaction(trans, root, ret); btrfs_end_transaction(trans, root); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 1ac3ca98c429..eb6537a08c1b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -349,6 +349,11 @@ static int fs_path_ensure_buf(struct fs_path *p, int len) if (p->buf_len >= len) return 0; + if (len > PATH_MAX) { + WARN_ON(1); + return -ENOMEM; + } + path_len = p->end - p->start; old_buf_len = p->buf_len; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 5011aadacab8..9601d25a4607 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -385,20 +385,6 @@ static match_table_t tokens = { {Opt_err, NULL}, }; -#define btrfs_set_and_info(root, opt, fmt, args...) \ -{ \ - if (!btrfs_test_opt(root, opt)) \ - btrfs_info(root->fs_info, fmt, ##args); \ - btrfs_set_opt(root->fs_info->mount_opt, opt); \ -} - -#define btrfs_clear_and_info(root, opt, fmt, args...) \ -{ \ - if (btrfs_test_opt(root, opt)) \ - btrfs_info(root->fs_info, fmt, ##args); \ - btrfs_clear_opt(root->fs_info->mount_opt, opt); \ -} - /* * Regular mount options parser. Everything that is needed only when * reading in a new superblock is parsed here. @@ -1186,7 +1172,6 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags, return ERR_PTR(-ENOMEM); mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs); - kfree(newargs); if (PTR_RET(mnt) == -EBUSY) { if (flags & MS_RDONLY) { @@ -1196,17 +1181,22 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags, int r; mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY, device_name, newargs); - if (IS_ERR(mnt)) + if (IS_ERR(mnt)) { + kfree(newargs); return ERR_CAST(mnt); + } r = btrfs_remount(mnt->mnt_sb, &flags, NULL); if (r < 0) { /* FIXME: release vfsmount mnt ??*/ + kfree(newargs); return ERR_PTR(r); } } } + kfree(newargs); + if (IS_ERR(mnt)) return ERR_CAST(mnt); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index b53278c9fd97..342ca5e423f9 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1187,8 +1187,8 @@ 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 2e5e648eb5c3..c561b628ebce 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3261,7 +3261,7 @@ int ceph_encode_inode_release(void **p, struct inode *inode, rel->seq = cpu_to_le32(cap->seq); rel->issue_seq = cpu_to_le32(cap->issue_seq), rel->mseq = cpu_to_le32(cap->mseq); - rel->caps = cpu_to_le32(cap->issued); + rel->caps = cpu_to_le32(cap->implemented); rel->wanted = cpu_to_le32(cap->mds_wanted); rel->dname_len = 0; rel->dname_seq = 0; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 766410a12c2c..c29d6ae68874 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -141,7 +141,7 @@ static int __dcache_readdir(struct file *file, struct dir_context *ctx, /* start at beginning? */ if (ctx->pos == 2 || last == NULL || - ctx->pos < ceph_dentry(last)->offset) { + fpos_cmp(ctx->pos, ceph_dentry(last)->offset) < 0) { if (list_empty(&parent->d_subdirs)) goto out_unlock; p = parent->d_subdirs.prev; @@ -182,9 +182,16 @@ more: spin_unlock(&dentry->d_lock); spin_unlock(&parent->d_lock); + /* make sure a dentry wasn't dropped while we didn't have parent lock */ + if (!ceph_dir_is_complete(dir)) { + dout(" lost dir complete on %p; falling back to mds\n", dir); + dput(dentry); + err = -EAGAIN; + goto out; + } + dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, ctx->pos, dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode); - ctx->pos = di->offset; if (!dir_emit(ctx, dentry->d_name.name, dentry->d_name.len, ceph_translate_ino(dentry->d_sb, dentry->d_inode->i_ino), @@ -198,19 +205,12 @@ more: return 0; } + ctx->pos = di->offset + 1; + if (last) dput(last); last = dentry; - ctx->pos++; - - /* make sure a dentry wasn't dropped while we didn't have parent lock */ - if (!ceph_dir_is_complete(dir)) { - dout(" lost dir complete on %p; falling back to mds\n", dir); - err = -EAGAIN; - goto out; - } - spin_lock(&parent->d_lock); p = p->prev; /* advance to next dentry */ goto more; @@ -296,6 +296,8 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) err = __dcache_readdir(file, ctx, shared_gen); if (err != -EAGAIN) return err; + frag = fpos_frag(ctx->pos); + off = fpos_off(ctx->pos); } else { spin_unlock(&ci->i_ceph_lock); } @@ -446,7 +448,6 @@ more: if (atomic_read(&ci->i_release_count) == fi->dir_release_count) { dout(" marking %p complete\n", inode); __ceph_dir_set_complete(ci, fi->dir_release_count); - ci->i_max_offset = ctx->pos; } spin_unlock(&ci->i_ceph_lock); @@ -935,14 +936,16 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry, * to do it here. */ - /* d_move screws up d_subdirs order */ - ceph_dir_clear_complete(new_dir); - d_move(old_dentry, new_dentry); /* ensure target dentry is invalidated, despite rehashing bug in vfs_rename_dir */ ceph_invalidate_dentry_lease(new_dentry); + + /* d_move screws up sibling dentries' offsets */ + ceph_dir_clear_complete(old_dir); + ceph_dir_clear_complete(new_dir); + } ceph_mdsc_put_request(req); return err; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 88a6df4cbe6d..c9a24ba98c9a 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -582,7 +582,7 @@ 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); + iov_iter_init(&i, WRITE, iov, nr_segs, count); while (iov_iter_count(&i) > 0) { void __user *data = i.iov->iov_base + i.iov_offset; @@ -703,7 +703,7 @@ 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); + iov_iter_init(&i, WRITE, iov, nr_segs, count); while ((len = iov_iter_count(&i)) > 0) { size_t left; @@ -737,13 +737,12 @@ 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, &i); if (ret != plen) { ret = -EFAULT; break; } left -= ret; - iov_iter_advance(&i, ret); } if (ret < 0) { @@ -796,8 +795,7 @@ 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 +821,20 @@ 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 +850,7 @@ out: ", reading more\n", iocb->ki_pos, inode->i_size); + iov_iter_advance(to, ret); read += ret; len -= ret; checkeof = 0; @@ -912,9 +891,7 @@ static ssize_t ceph_aio_write(struct kiocb *iocb, const struct iovec *iov, mutex_lock(&inode->i_mutex); - err = generic_segment_checks(iov, &nr_segs, &count, VERIFY_READ); - if (err) - goto out; + count = iov_length(iov, nr_segs); /* We can write back this queue in page reclaim */ current->backing_dev_info = file->f_mapping->backing_dev_info; @@ -980,7 +957,7 @@ 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); + iov_iter_init(&from, WRITE, iov, nr_segs, count); written = generic_perform_write(file, &from, pos); if (likely(written >= 0)) iocb->ki_pos = pos + written; @@ -1276,9 +1253,9 @@ const struct file_operations ceph_file_fops = { .open = ceph_open, .release = ceph_release, .llseek = ceph_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = ceph_aio_read, + .read_iter = ceph_read_iter, .aio_write = ceph_aio_write, .mmap = ceph_mmap, .fsync = ceph_fsync, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 0b0728e5be2d..233c6f96910a 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -744,7 +744,6 @@ static int fill_inode(struct inode *inode, !__ceph_dir_is_complete(ci)) { dout(" marking %p complete (empty)\n", inode); __ceph_dir_set_complete(ci, atomic_read(&ci->i_release_count)); - ci->i_max_offset = 2; } no_change: /* only update max_size on auth cap */ @@ -890,41 +889,6 @@ out_unlock: } /* - * Set dentry's directory position based on the current dir's max, and - * order it in d_subdirs, so that dcache_readdir behaves. - * - * Always called under directory's i_mutex. - */ -static void ceph_set_dentry_offset(struct dentry *dn) -{ - struct dentry *dir = dn->d_parent; - struct inode *inode = dir->d_inode; - struct ceph_inode_info *ci; - struct ceph_dentry_info *di; - - BUG_ON(!inode); - - ci = ceph_inode(inode); - di = ceph_dentry(dn); - - spin_lock(&ci->i_ceph_lock); - if (!__ceph_dir_is_complete(ci)) { - spin_unlock(&ci->i_ceph_lock); - return; - } - di->offset = ceph_inode(inode)->i_max_offset++; - spin_unlock(&ci->i_ceph_lock); - - spin_lock(&dir->d_lock); - spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); - list_move(&dn->d_u.d_child, &dir->d_subdirs); - dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset, - dn->d_u.d_child.prev, dn->d_u.d_child.next); - spin_unlock(&dn->d_lock); - spin_unlock(&dir->d_lock); -} - -/* * splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. * @@ -933,7 +897,7 @@ static void ceph_set_dentry_offset(struct dentry *dn) * the caller) if we fail. */ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, - bool *prehash, bool set_offset) + bool *prehash) { struct dentry *realdn; @@ -965,8 +929,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, } if ((!prehash || *prehash) && d_unhashed(dn)) d_rehash(dn); - if (set_offset) - ceph_set_dentry_offset(dn); out: return dn; } @@ -987,7 +949,6 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, { struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info; struct inode *in = NULL; - struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; struct ceph_fs_client *fsc = ceph_sb_to_client(sb); int err = 0; @@ -1161,6 +1122,9 @@ retry_lookup: /* rename? */ if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) { + struct inode *olddir = req->r_old_dentry_dir; + BUG_ON(!olddir); + dout(" src %p '%.*s' dst %p '%.*s'\n", req->r_old_dentry, req->r_old_dentry->d_name.len, @@ -1180,13 +1144,10 @@ retry_lookup: rehashing bug in vfs_rename_dir */ ceph_invalidate_dentry_lease(dn); - /* - * d_move() puts the renamed dentry at the end of - * d_subdirs. We need to assign it an appropriate - * directory offset so we can behave when dir is - * complete. - */ - ceph_set_dentry_offset(req->r_old_dentry); + /* d_move screws up sibling dentries' offsets */ + ceph_dir_clear_complete(dir); + ceph_dir_clear_complete(olddir); + dout("dn %p gets new offset %lld\n", req->r_old_dentry, ceph_dentry(req->r_old_dentry)->offset); @@ -1213,8 +1174,9 @@ retry_lookup: /* attach proper inode */ if (!dn->d_inode) { + ceph_dir_clear_complete(dir); ihold(in); - dn = splice_dentry(dn, in, &have_lease, true); + dn = splice_dentry(dn, in, &have_lease); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1235,17 +1197,16 @@ retry_lookup: (req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP)) { struct dentry *dn = req->r_dentry; + struct inode *dir = req->r_locked_dir; /* fill out a snapdir LOOKUPSNAP dentry */ BUG_ON(!dn); - BUG_ON(!req->r_locked_dir); - BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR); - ininfo = rinfo->targeti.in; - vino.ino = le64_to_cpu(ininfo->ino); - vino.snap = le64_to_cpu(ininfo->snapid); + BUG_ON(!dir); + BUG_ON(ceph_snap(dir) != CEPH_SNAPDIR); dout(" linking snapped dir %p to dn %p\n", in, dn); + ceph_dir_clear_complete(dir); ihold(in); - dn = splice_dentry(dn, in, NULL, true); + dn = splice_dentry(dn, in, NULL); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1407,7 +1368,7 @@ retry_lookup: } if (!dn->d_inode) { - dn = splice_dentry(dn, in, NULL, false); + dn = splice_dentry(dn, in, NULL); if (IS_ERR(dn)) { err = PTR_ERR(dn); dn = NULL; diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index fdf941b44ff1..a822a6e58290 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -109,6 +109,8 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) return PTR_ERR(req); req->r_inode = inode; ihold(inode); + req->r_num_caps = 1; + req->r_inode_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_EXCL; req->r_args.setlayout.layout.fl_stripe_unit = @@ -153,6 +155,7 @@ static long ceph_ioctl_set_layout_policy (struct file *file, void __user *arg) return PTR_ERR(req); req->r_inode = inode; ihold(inode); + req->r_num_caps = 1; req->r_args.setlayout.layout.fl_stripe_unit = cpu_to_le32(l.stripe_unit); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index d94ba0df9f4d..191398852a2e 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -45,6 +45,7 @@ static int ceph_lock_message(u8 lock_type, u16 operation, struct file *file, return PTR_ERR(req); req->r_inode = inode; ihold(inode); + req->r_num_caps = 1; /* mds requires start and length rather than start and end */ if (LLONG_MAX == fl->fl_end) diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 7866cd05a6bb..ead05cc1f447 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -266,7 +266,6 @@ struct ceph_inode_info { struct timespec i_rctime; u64 i_rbytes, i_rfiles, i_rsubdirs; u64 i_files, i_subdirs; - u64 i_max_offset; /* largest readdir offset, set with complete dir */ struct rb_root i_fragtree; struct mutex i_fragtree_mutex; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 5be1f997ecde..f0a567a344cf 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -888,9 +888,9 @@ const struct inode_operations cifs_symlink_inode_ops = { }; const struct file_operations cifs_file_ops = { - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .aio_write = cifs_file_aio_write, .open = cifs_open, .release = cifs_close, @@ -907,9 +907,9 @@ const struct file_operations cifs_file_ops = { }; const struct file_operations cifs_file_strict_ops = { - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = cifs_strict_readv, + .read_iter = cifs_strict_readv, .aio_write = cifs_strict_writev, .open = cifs_open, .release = cifs_close, @@ -927,9 +927,9 @@ 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, + .read = new_sync_read, .write = do_sync_write, - .aio_read = cifs_user_readv, + .read_iter = cifs_user_readv, .aio_write = cifs_user_writev, .open = cifs_open, .release = cifs_close, @@ -946,9 +946,9 @@ const struct file_operations cifs_file_direct_ops = { }; const struct file_operations cifs_file_nobrl_ops = { - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .aio_write = cifs_file_aio_write, .open = cifs_open, .release = cifs_close, @@ -964,9 +964,9 @@ const struct file_operations cifs_file_nobrl_ops = { }; const struct file_operations cifs_file_strict_nobrl_ops = { - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = cifs_strict_readv, + .read_iter = cifs_strict_readv, .aio_write = cifs_strict_writev, .open = cifs_open, .release = cifs_close, @@ -983,9 +983,9 @@ 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, + .read = new_sync_read, .write = do_sync_write, - .aio_read = cifs_user_readv, + .read_iter = cifs_user_readv, .aio_write = cifs_user_writev, .open = cifs_open, .release = cifs_close, diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 26a754f49ba1..d1ef0415c645 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -85,10 +85,8 @@ 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_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, const struct iovec *iov, unsigned long nr_segs, loff_t pos); extern ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 5ed03e0b8b40..2ec7fce6d350 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2424,7 +2424,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov, else pid = current->tgid; - iov_iter_init(&it, iov, nr_segs, len, 0); + iov_iter_init(&it, WRITE, iov, nr_segs, len); do { size_t save_len; @@ -2444,11 +2444,10 @@ 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, + &it); 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 @@ -2831,32 +2830,25 @@ 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 +2906,7 @@ 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 +2923,7 @@ error: goto again; } } else { - rc = cifs_readdata_to_iov(rdata, &to); + rc = cifs_readdata_to_iov(rdata, to); } } @@ -2939,7 +2931,7 @@ 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 +2940,14 @@ 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 +2966,22 @@ 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 +3694,8 @@ 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/compat.c b/fs/compat.c index ca926ad0430c..66d3d3c6b4b2 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -457,9 +457,9 @@ COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: - case F_GETLKP: - case F_SETLKP: - case F_SETLKPW: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: ret = get_compat_flock64(&f, compat_ptr(arg)); if (ret != 0) break; @@ -468,7 +468,7 @@ COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, conv_cmd = convert_fcntl_cmd(cmd); ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); set_fs(old_fs); - if ((conv_cmd == F_GETLK || conv_cmd == F_GETLKP) && ret == 0) { + if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { /* need to return lock information - see above for commentary */ if (f.l_start > COMPAT_LOFF_T_MAX) ret = -EOVERFLOW; @@ -493,9 +493,9 @@ COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: - case F_GETLKP: - case F_SETLKP: - case F_SETLKPW: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: return -EINVAL; } return compat_sys_fcntl64(fd, cmd, arg); diff --git a/fs/dcache.c b/fs/dcache.c index 40707d88a945..42ae01eefc07 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -246,16 +246,8 @@ static void __d_free(struct rcu_head *head) kmem_cache_free(dentry_cache, dentry); } -/* - * no locks, please. - */ -static void d_free(struct dentry *dentry) +static void dentry_free(struct dentry *dentry) { - BUG_ON((int)dentry->d_lockref.count > 0); - this_cpu_dec(nr_dentry); - if (dentry->d_op && dentry->d_op->d_release) - dentry->d_op->d_release(dentry); - /* if dentry was never visible to RCU, immediate free is OK */ if (!(dentry->d_flags & DCACHE_RCUACCESS)) __d_free(&dentry->d_u.d_rcu); @@ -403,56 +395,6 @@ static void dentry_lru_add(struct dentry *dentry) d_lru_add(dentry); } -/* - * Remove a dentry with references from the LRU. - * - * If we are on the shrink list, then we can get to try_prune_one_dentry() and - * lose our last reference through the parent walk. In this case, we need to - * remove ourselves from the shrink list, not the LRU. - */ -static void dentry_lru_del(struct dentry *dentry) -{ - if (dentry->d_flags & DCACHE_LRU_LIST) { - if (dentry->d_flags & DCACHE_SHRINK_LIST) - return d_shrink_del(dentry); - d_lru_del(dentry); - } -} - -/** - * d_kill - kill dentry and return parent - * @dentry: dentry to kill - * @parent: parent dentry - * - * The dentry must already be unhashed and removed from the LRU. - * - * If this is the root of the dentry tree, return NULL. - * - * dentry->d_lock and parent->d_lock must be held by caller, and are dropped by - * d_kill. - */ -static struct dentry *d_kill(struct dentry *dentry, struct dentry *parent) - __releases(dentry->d_lock) - __releases(parent->d_lock) - __releases(dentry->d_inode->i_lock) -{ - list_del(&dentry->d_u.d_child); - /* - * Inform d_walk() that we are no longer attached to the - * dentry tree - */ - dentry->d_flags |= DCACHE_DENTRY_KILLED; - if (parent) - spin_unlock(&parent->d_lock); - dentry_iput(dentry); - /* - * dentry_iput drops the locks, at which point nobody (except - * transient RCU lookups) can reach this dentry. - */ - d_free(dentry); - return parent; -} - /** * d_drop - drop a dentry * @dentry: dentry to drop @@ -510,7 +452,14 @@ dentry_kill(struct dentry *dentry, int unlock_on_failure) __releases(dentry->d_lock) { struct inode *inode; - struct dentry *parent; + struct dentry *parent = NULL; + bool can_free = true; + + if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) { + can_free = dentry->d_flags & DCACHE_MAY_FREE; + spin_unlock(&dentry->d_lock); + goto out; + } inode = dentry->d_inode; if (inode && !spin_trylock(&inode->i_lock)) { @@ -521,9 +470,7 @@ relock: } return dentry; /* try again with same dentry */ } - if (IS_ROOT(dentry)) - parent = NULL; - else + if (!IS_ROOT(dentry)) parent = dentry->d_parent; if (parent && !spin_trylock(&parent->d_lock)) { if (inode) @@ -543,10 +490,40 @@ relock: if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry)) dentry->d_op->d_prune(dentry); - dentry_lru_del(dentry); + if (dentry->d_flags & DCACHE_LRU_LIST) { + if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) + d_lru_del(dentry); + } /* if it was on the hash then remove it */ __d_drop(dentry); - return d_kill(dentry, parent); + list_del(&dentry->d_u.d_child); + /* + * Inform d_walk() that we are no longer attached to the + * dentry tree + */ + dentry->d_flags |= DCACHE_DENTRY_KILLED; + if (parent) + spin_unlock(&parent->d_lock); + dentry_iput(dentry); + /* + * dentry_iput drops the locks, at which point nobody (except + * transient RCU lookups) can reach this dentry. + */ + BUG_ON((int)dentry->d_lockref.count > 0); + this_cpu_dec(nr_dentry); + if (dentry->d_op && dentry->d_op->d_release) + dentry->d_op->d_release(dentry); + + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + dentry->d_flags |= DCACHE_MAY_FREE; + can_free = false; + } + spin_unlock(&dentry->d_lock); +out: + if (likely(can_free)) + dentry_free(dentry); + return parent; } /* @@ -815,65 +792,13 @@ restart: } EXPORT_SYMBOL(d_prune_aliases); -/* - * Try to throw away a dentry - free the inode, dput the parent. - * Requires dentry->d_lock is held, and dentry->d_count == 0. - * Releases dentry->d_lock. - * - * This may fail if locks cannot be acquired no problem, just try again. - */ -static struct dentry * try_prune_one_dentry(struct dentry *dentry) - __releases(dentry->d_lock) -{ - struct dentry *parent; - - parent = dentry_kill(dentry, 0); - /* - * If dentry_kill returns NULL, we have nothing more to do. - * if it returns the same dentry, trylocks failed. In either - * case, just loop again. - * - * Otherwise, we need to prune ancestors too. This is necessary - * to prevent quadratic behavior of shrink_dcache_parent(), but - * is also expected to be beneficial in reducing dentry cache - * fragmentation. - */ - if (!parent) - return NULL; - if (parent == dentry) - return dentry; - - /* Prune ancestors. */ - dentry = parent; - while (dentry) { - if (lockref_put_or_lock(&dentry->d_lockref)) - return NULL; - dentry = dentry_kill(dentry, 1); - } - return NULL; -} - static void shrink_dentry_list(struct list_head *list) { - struct dentry *dentry; + struct dentry *dentry, *parent; - rcu_read_lock(); - for (;;) { - dentry = list_entry_rcu(list->prev, struct dentry, d_lru); - if (&dentry->d_lru == list) - break; /* empty */ - - /* - * Get the dentry lock, and re-verify that the dentry is - * this on the shrinking list. If it is, we know that - * DCACHE_SHRINK_LIST and DCACHE_LRU_LIST are set. - */ + while (!list_empty(list)) { + dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); - if (dentry != list_entry(list->prev, struct dentry, d_lru)) { - spin_unlock(&dentry->d_lock); - continue; - } - /* * The dispose list is isolated and dentries are not accounted * to the LRU here, so we can simply remove it from the list @@ -885,30 +810,38 @@ static void shrink_dentry_list(struct list_head *list) * We found an inuse dentry which was not removed from * the LRU because of laziness during lookup. Do not free it. */ - if (dentry->d_lockref.count) { + if ((int)dentry->d_lockref.count > 0) { spin_unlock(&dentry->d_lock); continue; } - rcu_read_unlock(); + parent = dentry_kill(dentry, 0); /* - * If 'try_to_prune()' returns a dentry, it will - * be the same one we passed in, and d_lock will - * have been held the whole time, so it will not - * have been added to any other lists. We failed - * to get the inode lock. - * - * We just add it back to the shrink list. + * If dentry_kill returns NULL, we have nothing more to do. */ - dentry = try_prune_one_dentry(dentry); + if (!parent) + continue; - rcu_read_lock(); - if (dentry) { + if (unlikely(parent == dentry)) { + /* + * trylocks have failed and d_lock has been held the + * whole time, so it could not have been added to any + * other lists. Just add it back to the shrink list. + */ d_shrink_add(dentry, list); spin_unlock(&dentry->d_lock); + continue; } + /* + * We need to prune ancestors too. This is necessary to prevent + * quadratic behavior of shrink_dcache_parent(), but is also + * expected to be beneficial in reducing dentry cache + * fragmentation. + */ + dentry = parent; + while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) + dentry = dentry_kill(dentry, 1); } - rcu_read_unlock(); } static enum lru_status @@ -1261,34 +1194,23 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) if (data->start == dentry) goto out; - /* - * move only zero ref count dentries to the dispose list. - * - * Those which are presently on the shrink list, being processed - * by shrink_dentry_list(), shouldn't be moved. Otherwise the - * loop in shrink_dcache_parent() might not make any progress - * and loop forever. - */ - if (dentry->d_lockref.count) { - dentry_lru_del(dentry); - } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - /* - * We can't use d_lru_shrink_move() because we - * need to get the global LRU lock and do the - * LRU accounting. - */ - d_lru_del(dentry); - d_shrink_add(dentry, &data->dispose); + if (dentry->d_flags & DCACHE_SHRINK_LIST) { data->found++; - ret = D_WALK_NORETRY; + } else { + if (dentry->d_flags & DCACHE_LRU_LIST) + d_lru_del(dentry); + if (!dentry->d_lockref.count) { + d_shrink_add(dentry, &data->dispose); + data->found++; + } } /* * We can return to the caller if we have found some (this * ensures forward progress). We'll be coming back to find * the rest. */ - if (data->found && need_resched()) - ret = D_WALK_QUIT; + if (!list_empty(&data->dispose)) + ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; out: return ret; } @@ -1318,45 +1240,35 @@ void shrink_dcache_parent(struct dentry *parent) } EXPORT_SYMBOL(shrink_dcache_parent); -static enum d_walk_ret umount_collect(void *_data, struct dentry *dentry) +static enum d_walk_ret umount_check(void *_data, struct dentry *dentry) { - struct select_data *data = _data; - enum d_walk_ret ret = D_WALK_CONTINUE; + /* it has busy descendents; complain about those instead */ + if (!list_empty(&dentry->d_subdirs)) + return D_WALK_CONTINUE; - if (dentry->d_lockref.count) { - dentry_lru_del(dentry); - if (likely(!list_empty(&dentry->d_subdirs))) - goto out; - if (dentry == data->start && dentry->d_lockref.count == 1) - goto out; - printk(KERN_ERR - "BUG: Dentry %p{i=%lx,n=%s}" - " still in use (%d)" - " [unmount of %s %s]\n", + /* root with refcount 1 is fine */ + if (dentry == _data && dentry->d_lockref.count == 1) + return D_WALK_CONTINUE; + + printk(KERN_ERR "BUG: Dentry %p{i=%lx,n=%pd} " + " still in use (%d) [unmount of %s %s]\n", dentry, dentry->d_inode ? dentry->d_inode->i_ino : 0UL, - dentry->d_name.name, + dentry, dentry->d_lockref.count, dentry->d_sb->s_type->name, dentry->d_sb->s_id); - BUG(); - } else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) { - /* - * We can't use d_lru_shrink_move() because we - * need to get the global LRU lock and do the - * LRU accounting. - */ - if (dentry->d_flags & DCACHE_LRU_LIST) - d_lru_del(dentry); - d_shrink_add(dentry, &data->dispose); - data->found++; - ret = D_WALK_NORETRY; - } -out: - if (data->found && need_resched()) - ret = D_WALK_QUIT; - return ret; + WARN_ON(1); + return D_WALK_CONTINUE; +} + +static void do_one_tree(struct dentry *dentry) +{ + shrink_dcache_parent(dentry); + d_walk(dentry, dentry, umount_check, NULL); + d_drop(dentry); + dput(dentry); } /* @@ -1366,40 +1278,15 @@ void shrink_dcache_for_umount(struct super_block *sb) { struct dentry *dentry; - if (down_read_trylock(&sb->s_umount)) - BUG(); + WARN(down_read_trylock(&sb->s_umount), "s_umount should've been locked"); dentry = sb->s_root; sb->s_root = NULL; - for (;;) { - struct select_data data; - - INIT_LIST_HEAD(&data.dispose); - data.start = dentry; - data.found = 0; - - d_walk(dentry, &data, umount_collect, NULL); - if (!data.found) - break; - - shrink_dentry_list(&data.dispose); - cond_resched(); - } - d_drop(dentry); - dput(dentry); + do_one_tree(dentry); while (!hlist_bl_empty(&sb->s_anon)) { - struct select_data data; - dentry = hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash); - - INIT_LIST_HEAD(&data.dispose); - data.start = NULL; - data.found = 0; - - d_walk(dentry, &data, umount_collect, NULL); - if (data.found) - shrink_dentry_list(&data.dispose); - cond_resched(); + dentry = dget(hlist_bl_entry(hlist_bl_first(&sb->s_anon), struct dentry, d_hash)); + do_one_tree(dentry); } } @@ -1647,8 +1534,7 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) unsigned add_flags = d_flags_for_inode(inode); spin_lock(&dentry->d_lock); - dentry->d_flags &= ~DCACHE_ENTRY_TYPE; - dentry->d_flags |= add_flags; + __d_set_type(dentry, add_flags); if (inode) hlist_add_head(&dentry->d_alias, &inode->i_dentry); dentry->d_inode = inode; diff --git a/fs/direct-io.c b/fs/direct-io.c index 31ba0935e32e..98040ba388ac 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -77,7 +77,6 @@ struct dio_submit { 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 +97,14 @@ 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 +157,10 @@ 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 +175,19 @@ 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; } @@ -208,8 +198,9 @@ out: * L1 cache. */ static inline struct page *dio_get_page(struct dio *dio, - struct dio_submit *sdio) + struct dio_submit *sdio, size_t *from, size_t *to) { + int n; if (dio_pages_present(sdio) == 0) { int ret; @@ -218,7 +209,10 @@ 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++]; + n = sdio->head++; + *from = n ? 0 : sdio->from; + *to = (n == sdio->tail - 1) ? sdio->to : PAGE_SIZE; + return dio->pages[n]; } /** @@ -422,8 +416,8 @@ 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 +906,18 @@ 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) { - page = dio_get_page(dio, sdio); + struct page *page; + size_t from, to; + page = dio_get_page(dio, sdio, &from, &to); if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } - 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 +988,10 @@ 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 +1008,7 @@ 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 +1020,7 @@ 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 +1031,8 @@ 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 +1042,6 @@ 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 +1096,20 @@ 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; + loff_t end = offset + iov_iter_count(iter); 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) { /* @@ -1365,8 +1304,8 @@ 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 +1320,8 @@ __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/ecryptfs/file.c b/fs/ecryptfs/file.c index b1eaa7a1f82c..db0fad3269c0 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/exofs/file.c b/fs/exofs/file.c index 491c6c078e7f..5b7f6be5a2d5 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -67,10 +67,10 @@ 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, diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index d1c244d67667..3f9cafd73931 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 44c36e590765..970c6aca15cc 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, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index b1d2a4675d42..36d35c36311d 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 aad05311392a..c833b1226d4d 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, diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index f5157d0d1b43..4d32133a76c4 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1820,8 +1820,7 @@ 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; @@ -1829,10 +1828,10 @@ 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; @@ -1856,15 +1855,14 @@ 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); @@ -1909,8 +1907,7 @@ 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/ext4.h b/fs/ext4/ext4.h index 86c2cda208ea..eb37d76bf911 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2149,8 +2149,7 @@ 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/file.c b/fs/ext4/file.c index 7d55a591deba..86a13a514e4a 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -593,9 +593,9 @@ 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, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .aio_write = ext4_file_write, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 594009f5f523..8a57e9fcd1b9 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -639,8 +639,7 @@ 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 +647,7 @@ 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 +686,17 @@ 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); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7dfbcbba67d5..b2cee73c1437 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3086,13 +3086,12 @@ 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; @@ -3101,7 +3100,7 @@ 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); @@ -3168,8 +3167,8 @@ 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, @@ -3223,11 +3222,11 @@ 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; /* @@ -3240,13 +3239,12 @@ 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/f2fs/data.c b/fs/f2fs/data.c index 45abd60e2bff..1d2e7e9624d2 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -992,10 +992,9 @@ 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; @@ -1003,14 +1002,14 @@ 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; @@ -1019,11 +1018,11 @@ 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; - 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/file.c b/fs/f2fs/file.c index 60e7d5448a1d..22f4900dd8eb 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -679,10 +679,10 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) const struct file_operations f2fs_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, .open = generic_file_open, .mmap = f2fs_file_mmap, .fsync = f2fs_sync_file, diff --git a/fs/fat/file.c b/fs/fat/file.c index 9b104f543056..85f79a89e747 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 b3361fe2bcb5..385cce464e82 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -185,12 +185,13 @@ 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) { @@ -203,7 +204,7 @@ 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; } @@ -212,10 +213,9 @@ 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/fcntl.c b/fs/fcntl.c index 9ead1596399a..72c82f69b01b 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -274,15 +274,15 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ - case F_GETLKP: + case F_OFD_GETLK: #endif case F_GETLK: err = fcntl_getlk(filp, cmd, (struct flock __user *) arg); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ - case F_SETLKP: - case F_SETLKPW: + case F_OFD_SETLK: + case F_OFD_SETLKW: #endif /* Fallthrough */ case F_SETLK: @@ -399,13 +399,13 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, switch (cmd) { case F_GETLK64: - case F_GETLKP: + case F_OFD_GETLK: err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg); break; case F_SETLK64: case F_SETLKW64: - case F_SETLKP: - case F_SETLKPW: + case F_OFD_SETLK: + case F_OFD_SETLKW: err = fcntl_setlk64(fd, f.file, cmd, (struct flock64 __user *) arg); break; diff --git a/fs/file.c b/fs/file.c index 8f294cfac697..66923fe3176e 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 a374f5033e97..f8cc881fbbfb 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/control.c b/fs/fuse/control.c index a0b0855d00a9..205e0d5d5307 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -348,7 +348,7 @@ int __init fuse_ctl_init(void) return register_filesystem(&fuse_ctl_fs_type); } -void fuse_ctl_cleanup(void) +void __exit fuse_ctl_cleanup(void) { unregister_filesystem(&fuse_ctl_fs_type); } diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c index 13b691a8a7d2..966ace8b243f 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/dir.c b/fs/fuse/dir.c index 5b4e035b364c..42198359fa1b 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -679,6 +679,14 @@ static int fuse_symlink(struct inode *dir, struct dentry *entry, return create_new_entry(fc, req, dir, entry, S_IFLNK); } +static inline void fuse_update_ctime(struct inode *inode) +{ + if (!IS_NOCMTIME(inode)) { + inode->i_ctime = current_fs_time(inode->i_sb); + mark_inode_dirty_sync(inode); + } +} + static int fuse_unlink(struct inode *dir, struct dentry *entry) { int err; @@ -713,6 +721,7 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) fuse_invalidate_attr(inode); fuse_invalidate_attr(dir); fuse_invalidate_entry_cache(entry); + fuse_update_ctime(inode); } else if (err == -EINTR) fuse_invalidate_entry(entry); return err; @@ -743,23 +752,26 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) return err; } -static int fuse_rename(struct inode *olddir, struct dentry *oldent, - struct inode *newdir, struct dentry *newent) +static int fuse_rename_common(struct inode *olddir, struct dentry *oldent, + struct inode *newdir, struct dentry *newent, + unsigned int flags, int opcode, size_t argsize) { int err; - struct fuse_rename_in inarg; + struct fuse_rename2_in inarg; struct fuse_conn *fc = get_fuse_conn(olddir); - struct fuse_req *req = fuse_get_req_nopages(fc); + struct fuse_req *req; + req = fuse_get_req_nopages(fc); if (IS_ERR(req)) return PTR_ERR(req); - memset(&inarg, 0, sizeof(inarg)); + memset(&inarg, 0, argsize); inarg.newdir = get_node_id(newdir); - req->in.h.opcode = FUSE_RENAME; + inarg.flags = flags; + req->in.h.opcode = opcode; req->in.h.nodeid = get_node_id(olddir); req->in.numargs = 3; - req->in.args[0].size = sizeof(inarg); + req->in.args[0].size = argsize; req->in.args[0].value = &inarg; req->in.args[1].size = oldent->d_name.len + 1; req->in.args[1].value = oldent->d_name.name; @@ -771,15 +783,22 @@ static int fuse_rename(struct inode *olddir, struct dentry *oldent, if (!err) { /* ctime changes */ fuse_invalidate_attr(oldent->d_inode); + fuse_update_ctime(oldent->d_inode); + + if (flags & RENAME_EXCHANGE) { + fuse_invalidate_attr(newent->d_inode); + fuse_update_ctime(newent->d_inode); + } fuse_invalidate_attr(olddir); if (olddir != newdir) fuse_invalidate_attr(newdir); /* newent will end up negative */ - if (newent->d_inode) { + if (!(flags & RENAME_EXCHANGE) && newent->d_inode) { fuse_invalidate_attr(newent->d_inode); fuse_invalidate_entry_cache(newent); + fuse_update_ctime(newent->d_inode); } } else if (err == -EINTR) { /* If request was interrupted, DEITY only knows if the @@ -795,6 +814,36 @@ static int fuse_rename(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) +{ + struct fuse_conn *fc = get_fuse_conn(olddir); + int err; + + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + 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; + } + return err; + +} + static int fuse_link(struct dentry *entry, struct inode *newdir, struct dentry *newent) { @@ -829,6 +878,7 @@ static int fuse_link(struct dentry *entry, struct inode *newdir, inc_nlink(inode); spin_unlock(&fc->lock); fuse_invalidate_attr(inode); + fuse_update_ctime(inode); } else if (err == -EINTR) { fuse_invalidate_attr(inode); } @@ -846,6 +896,8 @@ static void fuse_fillattr(struct inode *inode, struct fuse_attr *attr, attr->size = i_size_read(inode); attr->mtime = inode->i_mtime.tv_sec; attr->mtimensec = inode->i_mtime.tv_nsec; + attr->ctime = inode->i_ctime.tv_sec; + attr->ctimensec = inode->i_ctime.tv_nsec; } stat->dev = inode->i_sb->s_dev; @@ -1504,7 +1556,7 @@ static bool update_mtime(unsigned ivalid, bool trust_local_mtime) } static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg, - bool trust_local_mtime) + bool trust_local_cmtime) { unsigned ivalid = iattr->ia_valid; @@ -1523,13 +1575,18 @@ static void iattr_to_fattr(struct iattr *iattr, struct fuse_setattr_in *arg, if (!(ivalid & ATTR_ATIME_SET)) arg->valid |= FATTR_ATIME_NOW; } - if ((ivalid & ATTR_MTIME) && update_mtime(ivalid, trust_local_mtime)) { + if ((ivalid & ATTR_MTIME) && update_mtime(ivalid, trust_local_cmtime)) { arg->valid |= FATTR_MTIME; arg->mtime = iattr->ia_mtime.tv_sec; arg->mtimensec = iattr->ia_mtime.tv_nsec; - if (!(ivalid & ATTR_MTIME_SET) && !trust_local_mtime) + if (!(ivalid & ATTR_MTIME_SET) && !trust_local_cmtime) arg->valid |= FATTR_MTIME_NOW; } + if ((ivalid & ATTR_CTIME) && trust_local_cmtime) { + arg->valid |= FATTR_CTIME; + arg->ctime = iattr->ia_ctime.tv_sec; + arg->ctimensec = iattr->ia_ctime.tv_nsec; + } } /* @@ -1597,39 +1654,38 @@ static void fuse_setattr_fill(struct fuse_conn *fc, struct fuse_req *req, /* * Flush inode->i_mtime to the server */ -int fuse_flush_mtime(struct file *file, bool nofail) +int fuse_flush_times(struct inode *inode, struct fuse_file *ff) { - struct inode *inode = file->f_mapping->host; - struct fuse_inode *fi = get_fuse_inode(inode); struct fuse_conn *fc = get_fuse_conn(inode); - struct fuse_req *req = NULL; + struct fuse_req *req; struct fuse_setattr_in inarg; struct fuse_attr_out outarg; int err; - if (nofail) { - req = fuse_get_req_nofail_nopages(fc, file); - } else { - req = fuse_get_req_nopages(fc); - if (IS_ERR(req)) - return PTR_ERR(req); - } + req = fuse_get_req_nopages(fc); + if (IS_ERR(req)) + return PTR_ERR(req); memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); - inarg.valid |= FATTR_MTIME; + inarg.valid = FATTR_MTIME; inarg.mtime = inode->i_mtime.tv_sec; inarg.mtimensec = inode->i_mtime.tv_nsec; - + if (fc->minor >= 23) { + inarg.valid |= FATTR_CTIME; + inarg.ctime = inode->i_ctime.tv_sec; + inarg.ctimensec = inode->i_ctime.tv_nsec; + } + if (ff) { + inarg.valid |= FATTR_FH; + inarg.fh = ff->fh; + } fuse_setattr_fill(fc, req, inode, &inarg, &outarg); fuse_request_send(fc, req); err = req->out.h.error; fuse_put_request(fc, req); - if (!err) - clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); - return err; } @@ -1653,7 +1709,7 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, bool is_wb = fc->writeback_cache; loff_t oldsize; int err; - bool trust_local_mtime = is_wb && S_ISREG(inode->i_mode); + bool trust_local_cmtime = is_wb && S_ISREG(inode->i_mode); if (!(fc->flags & FUSE_DEFAULT_PERMISSIONS)) attr->ia_valid |= ATTR_FORCE; @@ -1678,11 +1734,13 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, if (is_truncate) { fuse_set_nowrite(inode); set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); + if (trust_local_cmtime && attr->ia_size != inode->i_size) + attr->ia_valid |= ATTR_MTIME | ATTR_CTIME; } memset(&inarg, 0, sizeof(inarg)); memset(&outarg, 0, sizeof(outarg)); - iattr_to_fattr(attr, &inarg, trust_local_mtime); + iattr_to_fattr(attr, &inarg, trust_local_cmtime); if (file) { struct fuse_file *ff = file->private_data; inarg.valid |= FATTR_FH; @@ -1711,9 +1769,12 @@ int fuse_do_setattr(struct inode *inode, struct iattr *attr, spin_lock(&fc->lock); /* the kernel maintains i_mtime locally */ - if (trust_local_mtime && (attr->ia_valid & ATTR_MTIME)) { - inode->i_mtime = attr->ia_mtime; - clear_bit(FUSE_I_MTIME_DIRTY, &fi->state); + if (trust_local_cmtime) { + if (attr->ia_valid & ATTR_MTIME) + inode->i_mtime = attr->ia_mtime; + if (attr->ia_valid & ATTR_CTIME) + inode->i_ctime = attr->ia_ctime; + /* FIXME: clear I_DIRTY_SYNC? */ } fuse_change_attributes_common(inode, &outarg.attr, @@ -1810,8 +1871,10 @@ static int fuse_setxattr(struct dentry *entry, const char *name, fc->no_setxattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); + fuse_update_ctime(inode); + } return err; } @@ -1941,20 +2004,11 @@ static int fuse_removexattr(struct dentry *entry, const char *name) fc->no_removexattr = 1; err = -EOPNOTSUPP; } - if (!err) + if (!err) { fuse_invalidate_attr(inode); - return err; -} - -static int fuse_update_time(struct inode *inode, struct timespec *now, - int flags) -{ - if (flags & S_MTIME) { - inode->i_mtime = *now; - set_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state); - BUG_ON(!S_ISREG(inode->i_mode)); + fuse_update_ctime(inode); } - return 0; + return err; } static const struct inode_operations fuse_dir_inode_operations = { @@ -1964,6 +2018,7 @@ static const struct inode_operations fuse_dir_inode_operations = { .unlink = fuse_unlink, .rmdir = fuse_rmdir, .rename = fuse_rename, + .rename2 = fuse_rename2, .link = fuse_link, .setattr = fuse_setattr, .create = fuse_create, @@ -1996,7 +2051,6 @@ static const struct inode_operations fuse_common_inode_operations = { .getxattr = fuse_getxattr, .listxattr = fuse_listxattr, .removexattr = fuse_removexattr, - .update_time = fuse_update_time, }; static const struct inode_operations fuse_symlink_inode_operations = { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 13f8bdec5110..a25fa9059faa 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -223,6 +223,8 @@ void fuse_finish_open(struct inode *inode, struct file *file) i_size_write(inode, 0); spin_unlock(&fc->lock); fuse_invalidate_attr(inode); + if (fc->writeback_cache) + file_update_time(file); } if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache) fuse_link_write_file(file); @@ -232,18 +234,26 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir) { struct fuse_conn *fc = get_fuse_conn(inode); int err; + bool lock_inode = (file->f_flags & O_TRUNC) && + fc->atomic_o_trunc && + fc->writeback_cache; err = generic_file_open(inode, file); if (err) return err; + if (lock_inode) + mutex_lock(&inode->i_mutex); + err = fuse_do_open(fc, get_node_id(inode), file, isdir); - if (err) - return err; - fuse_finish_open(inode, file); + if (!err) + fuse_finish_open(inode, file); - return 0; + if (lock_inode) + mutex_unlock(&inode->i_mutex); + + return err; } static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode) @@ -314,10 +324,7 @@ static int fuse_release(struct inode *inode, struct file *file) /* see fuse_vma_close() for !writeback_cache case */ if (fc->writeback_cache) - filemap_write_and_wait(file->f_mapping); - - if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) - fuse_flush_mtime(file, true); + write_inode_now(inode, 1); fuse_release_common(file, FUSE_RELEASE); @@ -439,7 +446,7 @@ static int fuse_flush(struct file *file, fl_owner_t id) if (fc->no_flush) return 0; - err = filemap_write_and_wait(file->f_mapping); + err = write_inode_now(inode, 1); if (err) return err; @@ -480,13 +487,6 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, if (is_bad_inode(inode)) return -EIO; - err = filemap_write_and_wait_range(inode->i_mapping, start, end); - if (err) - return err; - - if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) - return 0; - mutex_lock(&inode->i_mutex); /* @@ -494,17 +494,17 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, * wait for all outstanding writes, before sending the FSYNC * request. */ - err = write_inode_now(inode, 0); + err = filemap_write_and_wait_range(inode->i_mapping, start, end); if (err) goto out; fuse_sync_writes(inode); + err = sync_inode_metadata(inode, 1); + if (err) + goto out; - if (test_bit(FUSE_I_MTIME_DIRTY, &get_fuse_inode(inode)->state)) { - int err = fuse_flush_mtime(file, false); - if (err) - goto out; - } + if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) + goto out; req = fuse_get_req_nopages(fc); if (IS_ERR(req)) { @@ -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, @@ -1188,8 +1187,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; - size_t count = 0; - size_t ocount = 0; + size_t count; ssize_t written = 0; ssize_t written_buffered = 0; struct inode *inode = mapping->host; @@ -1208,12 +1206,8 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, WARN_ON(iocb->ki_pos != pos); - ocount = 0; - err = generic_segment_checks(iov, &nr_segs, &ocount, VERIFY_READ); - if (err) - return err; - - count = ocount; + count = iov_length(iov, nr_segs); + iov_iter_init(&i, WRITE, iov, nr_segs, count); mutex_lock(&inode->i_mutex); /* We can write back this queue in page reclaim */ @@ -1226,6 +1220,7 @@ static ssize_t fuse_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; + iov_iter_truncate(&i, count); err = file_remove_suid(file); if (err) goto out; @@ -1235,15 +1230,12 @@ 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, &i, pos); + if (written < 0 || !iov_iter_count(&i)) goto out; pos += written; - count -= written; - iov_iter_init(&i, iov, nr_segs, count, written); written_buffered = fuse_perform_write(file, mapping, &i, pos); if (written_buffered < 0) { err = written_buffered; @@ -1263,7 +1255,6 @@ 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); if (written >= 0) iocb->ki_pos = pos + written; @@ -1302,7 +1293,7 @@ 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 & REQ_KERNEL) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); @@ -1318,35 +1309,26 @@ 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) @@ -1361,24 +1343,11 @@ 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; @@ -1388,18 +1357,16 @@ 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); @@ -1415,7 +1382,7 @@ 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; @@ -1445,9 +1412,9 @@ 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; } @@ -1462,9 +1429,8 @@ 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; @@ -1473,7 +1439,7 @@ 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); @@ -1485,22 +1451,26 @@ 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); @@ -1514,13 +1484,15 @@ 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); @@ -1659,13 +1631,13 @@ static void fuse_writepage_end(struct fuse_conn *fc, struct fuse_req *req) fuse_writepage_free(fc, req); } -static struct fuse_file *fuse_write_file_get(struct fuse_conn *fc, - struct fuse_inode *fi) +static struct fuse_file *__fuse_write_file_get(struct fuse_conn *fc, + struct fuse_inode *fi) { struct fuse_file *ff = NULL; spin_lock(&fc->lock); - if (!WARN_ON(list_empty(&fi->write_files))) { + if (!list_empty(&fi->write_files)) { ff = list_entry(fi->write_files.next, struct fuse_file, write_entry); fuse_file_get(ff); @@ -1675,6 +1647,29 @@ static struct fuse_file *fuse_write_file_get(struct fuse_conn *fc, return ff; } +static struct fuse_file *fuse_write_file_get(struct fuse_conn *fc, + struct fuse_inode *fi) +{ + struct fuse_file *ff = __fuse_write_file_get(fc, fi); + WARN_ON(!ff); + return ff; +} + +int fuse_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + struct fuse_inode *fi = get_fuse_inode(inode); + struct fuse_file *ff; + int err; + + ff = __fuse_write_file_get(fc, fi); + err = fuse_flush_times(inode, ff); + if (ff) + fuse_file_put(ff, 0); + + return err; +} + static int fuse_writepage_locked(struct page *page) { struct address_space *mapping = page->mapping; @@ -2352,7 +2347,7 @@ 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++]; @@ -2874,8 +2869,8 @@ 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; @@ -2884,7 +2879,7 @@ 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; @@ -2899,6 +2894,7 @@ 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); @@ -2928,9 +2924,9 @@ 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); @@ -2972,6 +2968,9 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) || (mode & FALLOC_FL_PUNCH_HOLE); + if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) + return -EOPNOTSUPP; + if (fc->no_fallocate) return -EOPNOTSUPP; @@ -3017,12 +3016,8 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE)) { bool changed = fuse_write_update_size(inode, offset + length); - if (changed && fc->writeback_cache) { - struct fuse_inode *fi = get_fuse_inode(inode); - - inode->i_mtime = current_fs_time(inode->i_sb); - set_bit(FUSE_I_MTIME_DIRTY, &fi->state); - } + if (changed && fc->writeback_cache) + file_update_time(file); } if (mode & FALLOC_FL_PUNCH_HOLE) @@ -3042,8 +3037,8 @@ out: static const struct file_operations fuse_file_operations = { .llseek = fuse_file_llseek, - .read = do_sync_read, - .aio_read = fuse_file_aio_read, + .read = new_sync_read, + .read_iter = fuse_file_read_iter, .write = do_sync_write, .aio_write = fuse_file_aio_write, .mmap = fuse_file_mmap, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index a257ed8ebee6..e8e47a6ab518 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -119,8 +119,6 @@ enum { FUSE_I_INIT_RDPLUS, /** An operation changing file size is in progress */ FUSE_I_SIZE_UNSTABLE, - /** i_mtime has been updated locally; a flush to userspace needed */ - FUSE_I_MTIME_DIRTY, }; struct fuse_conn; @@ -544,6 +542,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Is rename with flags implemented by fs? */ + unsigned no_rename2:1; + /** Use enhanced/automatic page cache invalidation. */ unsigned auto_inval_data:1; @@ -725,7 +726,7 @@ int fuse_dev_init(void); void fuse_dev_cleanup(void); int fuse_ctl_init(void); -void fuse_ctl_cleanup(void); +void __exit fuse_ctl_cleanup(void); /** * Allocate a request @@ -879,9 +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, @@ -891,7 +891,8 @@ int fuse_dev_release(struct inode *inode, struct file *file); bool fuse_write_update_size(struct inode *inode, loff_t pos); -int fuse_flush_mtime(struct file *file, bool nofail); +int fuse_flush_times(struct inode *inode, struct fuse_file *ff); +int fuse_write_inode(struct inode *inode, struct writeback_control *wbc); int fuse_do_setattr(struct inode *inode, struct iattr *attr, struct file *file); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 8d611696fcad..754dcf23de8a 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -175,9 +175,9 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) { inode->i_mtime.tv_sec = attr->mtime; inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; } - inode->i_ctime.tv_sec = attr->ctime; - inode->i_ctime.tv_nsec = attr->ctimensec; if (attr->blksize != 0) inode->i_blkbits = ilog2(attr->blksize); @@ -256,6 +256,8 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) inode->i_size = attr->size; inode->i_mtime.tv_sec = attr->mtime; inode->i_mtime.tv_nsec = attr->mtimensec; + inode->i_ctime.tv_sec = attr->ctime; + inode->i_ctime.tv_nsec = attr->ctimensec; if (S_ISREG(inode->i_mode)) { fuse_init_common(inode); fuse_init_file_inode(inode); @@ -303,7 +305,7 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, if ((inode->i_state & I_NEW)) { inode->i_flags |= S_NOATIME; - if (!fc->writeback_cache || !S_ISREG(inode->i_mode)) + if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; inode->i_data.backing_dev_info = &fc->bdi; @@ -788,6 +790,7 @@ static const struct super_operations fuse_super_operations = { .alloc_inode = fuse_alloc_inode, .destroy_inode = fuse_destroy_inode, .evict_inode = fuse_evict_inode, + .write_inode = fuse_write_inode, .drop_inode = generic_delete_inode, .remount_fs = fuse_remount_fs, .put_super = fuse_put_super, @@ -890,6 +893,11 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->async_dio = 1; if (arg->flags & FUSE_WRITEBACK_CACHE) 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; @@ -996,7 +1004,7 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_flags & MS_MANDLOCK) goto err; - sb->s_flags &= ~MS_NOSEC; + sb->s_flags &= ~(MS_NOSEC | MS_I_VERSION); if (!parse_fuse_opt((char *) data, &d, is_bdev)) goto err; diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index ce62dcac90b6..910838951d66 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -1041,8 +1041,7 @@ 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; @@ -1082,7 +1081,7 @@ 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; @@ -1097,9 +1096,9 @@ 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 80d67253623c..763c9a6287d2 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1058,8 +1058,8 @@ 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, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .write = do_sync_write, .aio_write = gfs2_file_aio_write, .unlocked_ioctl = gfs2_ioctl, @@ -1090,8 +1090,8 @@ 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, + .read = new_sync_read, + .read_iter = generic_file_read_iter, .write = do_sync_write, .aio_write = gfs2_file_aio_write, .unlocked_ioctl = gfs2_ioctl, diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 9e2fecd62f62..d0929bc81782 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 a4f45bd88a63..0cf786f2d046 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 9c470fde9878..bb529f3b7f2b 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 67c1a61e0955..7f54e5f76cec 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/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 204027520937..e19d4c0cacae 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1030,6 +1030,11 @@ static int __init init_hugetlbfs_fs(void) int error; int i; + if (!hugepages_supported()) { + pr_info("hugetlbfs: disabling because there are no supported hugepage sizes\n"); + return -ENOTSUPP; + } + error = bdi_init(&hugetlbfs_backing_dev_info); if (error) return error; diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 256cd19a3b78..64989ca9ba90 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 794da944d5cd..cc744ecaf51f 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -151,10 +151,10 @@ 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, diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c index 6f8fe72c2a7a..bd3df1ca3c9b 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/dir.c b/fs/kernfs/dir.c index 78f3403300af..ac127cd008bf 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -232,9 +232,6 @@ static int kernfs_link_sibling(struct kernfs_node *kn) struct rb_node **node = &kn->parent->dir.children.rb_node; struct rb_node *parent = NULL; - if (kernfs_type(kn) == KERNFS_DIR) - kn->parent->dir.subdirs++; - while (*node) { struct kernfs_node *pos; int result; @@ -249,9 +246,15 @@ static int kernfs_link_sibling(struct kernfs_node *kn) else return -EEXIST; } + /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); rb_insert_color(&kn->rb, &kn->parent->dir.children); + + /* successfully added, account subdir number */ + if (kernfs_type(kn) == KERNFS_DIR) + kn->parent->dir.subdirs++; + return 0; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 8034706a7af8..e01ea4a14a01 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -484,6 +484,8 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); + if (rc) + goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() diff --git a/fs/locks.c b/fs/locks.c index 13fc7a6d380a..e663aeac579e 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -135,7 +135,7 @@ #define IS_POSIX(fl) (fl->fl_flags & FL_POSIX) #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) #define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG)) -#define IS_FILE_PVT(fl) (fl->fl_flags & FL_FILE_PVT) +#define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) static bool lease_breaking(struct file_lock *fl) { @@ -564,7 +564,7 @@ static void __locks_insert_block(struct file_lock *blocker, BUG_ON(!list_empty(&waiter->fl_block)); waiter->fl_next = blocker; list_add_tail(&waiter->fl_block, &blocker->fl_block); - if (IS_POSIX(blocker) && !IS_FILE_PVT(blocker)) + if (IS_POSIX(blocker) && !IS_OFDLCK(blocker)) locks_insert_global_blocked(waiter); } @@ -759,12 +759,12 @@ EXPORT_SYMBOL(posix_test_lock); * of tasks (such as posix threads) sharing the same open file table. * To handle those cases, we just bail out after a few iterations. * - * For FL_FILE_PVT locks, the owner is the filp, not the files_struct. + * For FL_OFDLCK locks, the owner is the filp, not the files_struct. * Because the owner is not even nominally tied to a thread of * execution, the deadlock detection below can't reasonably work well. Just * skip it for those. * - * In principle, we could do a more limited deadlock detection on FL_FILE_PVT + * In principle, we could do a more limited deadlock detection on FL_OFDLCK * locks that just checks for the case where two tasks are attempting to * upgrade from read to write locks on the same inode. */ @@ -791,9 +791,9 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, /* * This deadlock detector can't reasonably detect deadlocks with - * FL_FILE_PVT locks, since they aren't owned by a process, per-se. + * FL_OFDLCK locks, since they aren't owned by a process, per-se. */ - if (IS_FILE_PVT(caller_fl)) + if (IS_OFDLCK(caller_fl)) return 0; while ((block_fl = what_owner_is_waiting_for(block_fl))) { @@ -1391,11 +1391,10 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) restart: break_time = flock->fl_break_time; - if (break_time != 0) { + if (break_time != 0) break_time -= jiffies; - if (break_time == 0) - break_time++; - } + if (break_time == 0) + break_time++; locks_insert_block(flock, new_fl); spin_unlock(&inode->i_lock); error = wait_event_interruptible_timeout(new_fl->fl_wait, @@ -1891,7 +1890,7 @@ EXPORT_SYMBOL_GPL(vfs_test_lock); static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { - flock->l_pid = IS_FILE_PVT(fl) ? -1 : fl->fl_pid; + flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via @@ -1913,7 +1912,7 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { - flock->l_pid = IS_FILE_PVT(fl) ? -1 : fl->fl_pid; + flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; @@ -1942,13 +1941,13 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) if (error) goto out; - if (cmd == F_GETLKP) { + if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_GETLK; - file_lock.fl_flags |= FL_FILE_PVT; + file_lock.fl_flags |= FL_OFDLCK; file_lock.fl_owner = (fl_owner_t)filp; } @@ -2074,25 +2073,25 @@ again: /* * If the cmd is requesting file-private locks, then set the - * FL_FILE_PVT flag and override the owner. + * FL_OFDLCK flag and override the owner. */ switch (cmd) { - case F_SETLKP: + case F_OFD_SETLK: error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_SETLK; - file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = (fl_owner_t)filp; break; - case F_SETLKPW: + case F_OFD_SETLKW: error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_SETLKW; - file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = (fl_owner_t)filp; /* Fallthrough */ case F_SETLKW: @@ -2144,13 +2143,13 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) if (error) goto out; - if (cmd == F_GETLKP) { + if (cmd == F_OFD_GETLK) { error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_GETLK64; - file_lock.fl_flags |= FL_FILE_PVT; + file_lock.fl_flags |= FL_OFDLCK; file_lock.fl_owner = (fl_owner_t)filp; } @@ -2209,25 +2208,25 @@ again: /* * If the cmd is requesting file-private locks, then set the - * FL_FILE_PVT flag and override the owner. + * FL_OFDLCK flag and override the owner. */ switch (cmd) { - case F_SETLKP: + case F_OFD_SETLK: error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_SETLK64; - file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = (fl_owner_t)filp; break; - case F_SETLKPW: + case F_OFD_SETLKW: error = -EINVAL; if (flock.l_pid != 0) goto out; cmd = F_SETLKW64; - file_lock->fl_flags |= FL_FILE_PVT; + file_lock->fl_flags |= FL_OFDLCK; file_lock->fl_owner = (fl_owner_t)filp; /* Fallthrough */ case F_SETLKW64: @@ -2413,8 +2412,8 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, if (IS_POSIX(fl)) { if (fl->fl_flags & FL_ACCESS) seq_printf(f, "ACCESS"); - else if (IS_FILE_PVT(fl)) - seq_printf(f, "FLPVT "); + else if (IS_OFDLCK(fl)) + seq_printf(f, "OFDLCK"); else seq_printf(f, "POSIX "); diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 57914fc32b62..8538752df2f6 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/minix/file.c b/fs/minix/file.c index adc6f5494231..a967de085ac0 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 c6157c894fce..80168273396b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1542,7 +1542,7 @@ static inline int walk_component(struct nameidata *nd, struct path *path, inode = path->dentry->d_inode; } err = -ENOENT; - if (!inode) + if (!inode || d_is_negative(path->dentry)) goto out_path_put; if (should_follow_link(path->dentry, follow)) { @@ -2249,7 +2249,7 @@ mountpoint_last(struct nameidata *nd, struct path *path) mutex_unlock(&dir->d_inode->i_mutex); done: - if (!dentry->d_inode) { + if (!dentry->d_inode || d_is_negative(dentry)) { error = -ENOENT; dput(dentry); goto out; @@ -2994,7 +2994,7 @@ retry_lookup: finish_lookup: /* we _can_ be in RCU mode here */ error = -ENOENT; - if (d_is_negative(path->dentry)) { + if (!inode || d_is_negative(path->dentry)) { path_to_nameidata(path, nd); goto out; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index b8797ae6831f..b122fe21fea0 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -121,20 +121,20 @@ static inline int put_dreq(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 */ } @@ -322,60 +322,37 @@ 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_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode, + &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); @@ -389,56 +366,21 @@ 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_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode, - &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); @@ -461,8 +403,7 @@ 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 @@ -479,8 +420,8 @@ 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; @@ -488,9 +429,7 @@ 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", @@ -513,7 +452,7 @@ 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)) { @@ -524,8 +463,8 @@ 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); @@ -681,109 +620,6 @@ 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, dreq->inode, - pagevec[i], - pgbase, req_len); - if (IS_ERR(req)) { - result = PTR_ERR(req); - break; - } - nfs_lock_request(req); - req->wb_index = pos >> PAGE_SHIFT; - req->wb_offset = pos & ~PAGE_MASK; - if (!nfs_pageio_add_request(desc, req)) { - result = desc->pg_error; - nfs_unlock_and_release_request(req); - break; - } - pgbase = 0; - bytes -= req_len; - started += req_len; - user_addr += req_len; - pos += req_len; - count -= req_len; - 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; @@ -863,16 +699,27 @@ 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_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE, &nfs_direct_write_completion_ops); @@ -880,16 +727,50 @@ 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, inode, + pagevec[i], + pgbase, req_len); + if (IS_ERR(req)) { + result = PTR_ERR(req); + break; + } + nfs_lock_request(req); + req->wb_index = pos >> PAGE_SHIFT; + req->wb_offset = pos & ~PAGE_MASK; + if (!nfs_pageio_add_request(&desc, req)) { + result = desc.pg_error; + nfs_unlock_and_release_request(req); + break; + } + pgbase = 0; + bytes -= req_len; + 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); @@ -911,8 +792,7 @@ 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 @@ -930,8 +810,8 @@ 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; @@ -940,9 +820,7 @@ 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); @@ -993,7 +871,7 @@ 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 284ca901fe16..200bdb0779f0 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); } @@ -643,16 +642,18 @@ ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, unsigned long written = 0; ssize_t result; size_t count = iov_length(iov, nr_segs); + struct iov_iter from; + iov_iter_init(&from, WRITE, iov, nr_segs, count); 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)) @@ -939,9 +940,9 @@ EXPORT_SYMBOL_GPL(nfs_setlease); const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = nfs_file_read, + .read_iter = nfs_file_read, .aio_write = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs_file_open, diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index dd8bfc2e2464..e598e4a852ad 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -320,7 +320,7 @@ 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 *); diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 8de3407e0360..37a998cae963 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -118,9 +118,9 @@ 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, + .read = new_sync_read, .write = do_sync_write, - .aio_read = nfs_file_read, + .read_iter = nfs_file_read, .aio_write = nfs_file_write, .mmap = nfs_file_mmap, .open = nfs4_file_open, diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 39c8ef875f91..2c73cae9899d 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -654,9 +654,11 @@ static struct rpc_clnt *create_backchannel_client(struct rpc_create_args *args) static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses) { + int maxtime = max_cb_time(clp->net); struct rpc_timeout timeparms = { - .to_initval = max_cb_time(clp->net), + .to_initval = maxtime, .to_retries = 0, + .to_maxval = maxtime, }; struct rpc_create_args args = { .net = clp->net, diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2723c1badd01..18881f34737a 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3627,14 +3627,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) /* nfsd4_check_resp_size guarantees enough room for error status */ if (!op->status) op->status = nfsd4_check_resp_size(resp, 0); - if (op->status == nfserr_resource && nfsd4_has_session(&resp->cstate)) { - struct nfsd4_slot *slot = resp->cstate.slot; - - if (slot->sl_flags & NFSD4_SLOT_CACHETHIS) - op->status = nfserr_rep_too_big_to_cache; - else - op->status = nfserr_rep_too_big; - } if (so) { so->so_replay.rp_status = op->status; so->so_replay.rp_buflen = (char *)resp->p - (char *)(statp+1); diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index f3a82fbcae02..24978153c0c4 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 b9c5726120e3..6252b173a465 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/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 4e565c814309..732648b270dc 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -698,6 +698,8 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) } group->overflow_event = &oevent->fse; + if (force_o_largefile()) + event_f_flags |= O_LARGEFILE; group->fanotify_data.f_flags = event_f_flags; #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS spin_lock_init(&group->fanotify_data.access_lock); diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index db9bd8a31725..89b4d6663775 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2091,10 +2091,7 @@ 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; @@ -2203,8 +2200,8 @@ 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 d310d12a9adc..4a231a166cf8 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/file.c b/fs/ocfs2/file.c index 8970dcf74de5..bfaaba5373b9 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2241,7 +2241,6 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, 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 */ loff_t old_size, *ppos = &iocb->ki_pos; u32 old_clusters; @@ -2251,6 +2250,10 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb, int full_coherency = !(osb->s_mount_opt & OCFS2_MOUNT_COHERENCY_BUFFERED); int unaligned_dio = 0; + struct iov_iter from; + + count = iov_length(iov, nr_segs); + iov_iter_init(&from, WRITE, iov, nr_segs, count); trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry, (unsigned long long)OCFS2_I(inode)->ip_blkno, @@ -2354,27 +2357,19 @@ 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); if (likely(written >= 0)) @@ -2534,7 +2529,7 @@ 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 +2544,8 @@ 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 +2554,8 @@ 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) { @@ -2606,7 +2600,7 @@ 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 */ @@ -2705,13 +2699,13 @@ const struct inode_operations ocfs2_special_file_iops = { */ const struct file_operations ocfs2_fops = { .llseek = ocfs2_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, - .aio_read = ocfs2_file_aio_read, + .read_iter = ocfs2_file_read_iter, .aio_write = ocfs2_file_aio_write, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT @@ -2753,13 +2747,13 @@ const struct file_operations ocfs2_dops = { */ const struct file_operations ocfs2_fops_no_plocks = { .llseek = ocfs2_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, .mmap = ocfs2_mmap, .fsync = ocfs2_sync_file, .release = ocfs2_file_release, .open = ocfs2_file_open, - .aio_read = ocfs2_file_aio_read, + .read_iter = ocfs2_file_read_iter, .aio_write = ocfs2_file_aio_write, .unlocked_ioctl = ocfs2_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 54d57d6ba68d..902e88527fce 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 9d64679cec73..36662d036237 100644 --- a/fs/open.c +++ b/fs/open.c @@ -725,6 +725,12 @@ 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 034bffac3f97..05ccb00cb407 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -271,24 +271,18 @@ 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 +306,7 @@ 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; @@ -1044,8 +1038,8 @@ err: const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, - .read = do_sync_read, - .aio_read = pipe_read, + .read = new_sync_read, + .read_iter = pipe_read, .write = do_sync_write, .aio_write = pipe_write, .poll = pipe_poll, diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 9e363e41dacc..0855f772cd41 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -246,6 +246,12 @@ posix_acl_equiv_mode(const struct posix_acl *acl, umode_t *mode_p) umode_t mode = 0; int not_equiv = 0; + /* + * A null ACL can always be presented as mode bits. + */ + if (!acl) + return 0; + FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 1e56a4e8cf7c..6ea0b9718a9d 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -31,10 +31,10 @@ #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, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 0b3d8e4cb2fa..9ed420f8f3ca 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -37,10 +37,10 @@ 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, diff --git a/fs/read_write.c b/fs/read_write.c index 31c6efa43183..009d8542a889 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 ed58d843d578..7c8ecd6468db 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -235,8 +235,8 @@ int reiserfs_commit_page(struct inode *inode, struct page *page, } 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, @@ -245,8 +245,8 @@ 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, .llseek = generic_file_llseek, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index bc8b8009897d..b8003e8dd1f4 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -3083,15 +3083,15 @@ static int reiserfs_releasepage(struct page *page, gfp_t unused_gfp_flags) /* We thank Mingming Cao for helping us understand in great detail what 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 @@ -3099,7 +3099,7 @@ 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 f373bde8f545..ea06c7554860 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/splice.c b/fs/splice.c index 9bc07d2b53cf..f99e420744c7 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1548,7 +1548,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov, if (ret <= 0) return 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 9d4dc6831792..b00811c75b24 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 4f34dbae823d..ab721529c57c 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1582,9 +1582,9 @@ const struct inode_operations ubifs_symlink_inode_operations = { const struct file_operations ubifs_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = generic_file_aio_read, + .read_iter = generic_file_read_iter, .aio_write = ubifs_aio_write, .mmap = ubifs_file_mmap, .fsync = ubifs_fsync, diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index a1266089eca1..a81c7b556896 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1556,7 +1556,7 @@ static int ubifs_remount_rw(struct ubifs_info *c) if (c->space_fixup) { err = ubifs_fixup_free_space(c); if (err) - return err; + goto out; } err = check_free_space(c); diff --git a/fs/udf/file.c b/fs/udf/file.c index d2c170f8b035..8a7c400b035f 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; @@ -252,8 +252,8 @@ 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, diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 5d643706212f..236cd48184c2 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 33afa20d4509..c84ec010a676 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/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 0479c32c5eb1..08d13e395252 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1449,9 +1449,8 @@ 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); @@ -1459,7 +1458,7 @@ 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 @@ -1471,17 +1470,15 @@ 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_file.c b/fs/xfs/xfs_file.c index 951a2321ee01..a1acd2fa57e8 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); @@ -625,10 +618,7 @@ 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 +626,10 @@ 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 +668,7 @@ 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 +690,7 @@ 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 +703,7 @@ 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 +712,8 @@ 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 +721,13 @@ 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; /* @@ -771,17 +760,16 @@ xfs_file_aio_write( struct xfs_inode *ip = XFS_I(inode); ssize_t ret; size_t ocount = 0; + struct iov_iter 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; - + ocount = iov_length(iovp, nr_segs); if (ocount == 0) return 0; + iov_iter_init(&from, WRITE, iovp, nr_segs, ocount); if (XFS_FORCED_SHUTDOWN(ip->i_mount)) { ret = -EIO; @@ -789,10 +777,9 @@ xfs_file_aio_write( } 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; @@ -1461,9 +1448,9 @@ xfs_file_llseek( const struct file_operations xfs_file_operations = { .llseek = xfs_file_llseek, - .read = do_sync_read, + .read = new_sync_read, .write = do_sync_write, - .aio_read = xfs_file_aio_read, + .read_iter = xfs_file_read_iter, .aio_write = xfs_file_aio_write, .splice_read = xfs_file_splice_read, .splice_write = xfs_file_splice_write, |