diff options
Diffstat (limited to 'fs')
78 files changed, 1025 insertions, 590 deletions
@@ -75,6 +75,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) unsigned int sz = sizeof(struct bio) + extra_size; struct kmem_cache *slab = NULL; struct bio_slab *bslab, *new_bio_slabs; + unsigned int new_bio_slab_max; unsigned int i, entry = -1; mutex_lock(&bio_slab_lock); @@ -97,12 +98,13 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) goto out_unlock; if (bio_slab_nr == bio_slab_max && entry == -1) { - bio_slab_max <<= 1; + new_bio_slab_max = bio_slab_max << 1; new_bio_slabs = krealloc(bio_slabs, - bio_slab_max * sizeof(struct bio_slab), + new_bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL); if (!new_bio_slabs) goto out_unlock; + bio_slab_max = new_bio_slab_max; bio_slabs = new_bio_slabs; } if (entry == -1) diff --git a/fs/block_dev.c b/fs/block_dev.c index b3c1d3d..a1e09b4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -70,19 +70,6 @@ static void bdev_inode_switch_bdi(struct inode *inode, spin_unlock(&dst->wb.list_lock); } -sector_t blkdev_max_block(struct block_device *bdev) -{ - sector_t retval = ~((sector_t)0); - loff_t sz = i_size_read(bdev->bd_inode); - - if (sz) { - unsigned int size = block_size(bdev); - unsigned int sizebits = blksize_bits(size); - retval = (sz >> sizebits); - } - return retval; -} - /* Kill _all_ buffers and pagecache , dirty or not.. */ void kill_bdev(struct block_device *bdev) { @@ -116,8 +103,6 @@ EXPORT_SYMBOL(invalidate_bdev); int set_blocksize(struct block_device *bdev, int size) { - struct address_space *mapping; - /* Size must be a power of two, and between 512 and PAGE_SIZE */ if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size)) return -EINVAL; @@ -126,19 +111,6 @@ int set_blocksize(struct block_device *bdev, int size) if (size < bdev_logical_block_size(bdev)) return -EINVAL; - /* Prevent starting I/O or mapping the device */ - percpu_down_write(&bdev->bd_block_size_semaphore); - - /* Check that the block device is not memory mapped */ - mapping = bdev->bd_inode->i_mapping; - mutex_lock(&mapping->i_mmap_mutex); - if (mapping_mapped(mapping)) { - mutex_unlock(&mapping->i_mmap_mutex); - percpu_up_write(&bdev->bd_block_size_semaphore); - return -EBUSY; - } - mutex_unlock(&mapping->i_mmap_mutex); - /* Don't change the size if it is same as current */ if (bdev->bd_block_size != size) { sync_blockdev(bdev); @@ -146,9 +118,6 @@ int set_blocksize(struct block_device *bdev, int size) bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } - - percpu_up_write(&bdev->bd_block_size_semaphore); - return 0; } @@ -181,52 +150,12 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { - if (iblock >= blkdev_max_block(I_BDEV(inode))) { - if (create) - return -EIO; - - /* - * for reads, we're just trying to fill a partial page. - * return a hole, they will have to call get_block again - * before they can fill it, and they will get -EIO at that - * time - */ - return 0; - } bh->b_bdev = I_BDEV(inode); bh->b_blocknr = iblock; set_buffer_mapped(bh); return 0; } -static int -blkdev_get_blocks(struct inode *inode, sector_t iblock, - struct buffer_head *bh, int create) -{ - sector_t end_block = blkdev_max_block(I_BDEV(inode)); - unsigned long max_blocks = bh->b_size >> inode->i_blkbits; - - if ((iblock + max_blocks) > end_block) { - max_blocks = end_block - iblock; - if ((long)max_blocks <= 0) { - if (create) - return -EIO; /* write fully beyond EOF */ - /* - * It is a read which is fully beyond EOF. We return - * a !buffer_mapped buffer - */ - max_blocks = 0; - } - } - - bh->b_bdev = I_BDEV(inode); - bh->b_blocknr = iblock; - bh->b_size = max_blocks << inode->i_blkbits; - if (max_blocks) - set_buffer_mapped(bh); - return 0; -} - static ssize_t blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) @@ -235,7 +164,7 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, struct inode *inode = file->f_mapping->host; return __blockdev_direct_IO(rw, iocb, inode, I_BDEV(inode), iov, offset, - nr_segs, blkdev_get_blocks, NULL, NULL, 0); + nr_segs, blkdev_get_block, NULL, NULL, 0); } int __sync_blockdev(struct block_device *bdev, int wait) @@ -459,12 +388,6 @@ static struct inode *bdev_alloc_inode(struct super_block *sb) struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL); if (!ei) return NULL; - - if (unlikely(percpu_init_rwsem(&ei->bdev.bd_block_size_semaphore))) { - kmem_cache_free(bdev_cachep, ei); - return NULL; - } - return &ei->vfs_inode; } @@ -473,8 +396,6 @@ static void bdev_i_callback(struct rcu_head *head) struct inode *inode = container_of(head, struct inode, i_rcu); struct bdev_inode *bdi = BDEV_I(inode); - percpu_free_rwsem(&bdi->bdev.bd_block_size_semaphore); - kmem_cache_free(bdev_cachep, bdi); } @@ -1593,22 +1514,6 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg) return blkdev_ioctl(bdev, mode, cmd, arg); } -ssize_t blkdev_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) -{ - ssize_t ret; - struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host); - - percpu_down_read(&bdev->bd_block_size_semaphore); - - ret = generic_file_aio_read(iocb, iov, nr_segs, pos); - - percpu_up_read(&bdev->bd_block_size_semaphore); - - return ret; -} -EXPORT_SYMBOL_GPL(blkdev_aio_read); - /* * Write data to the block device. Only intended for the block device itself * and the raw driver which basically is a fake block device. @@ -1620,16 +1525,12 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; - struct block_device *bdev = I_BDEV(file->f_mapping->host); struct blk_plug plug; ssize_t ret; BUG_ON(iocb->ki_pos != pos); blk_start_plug(&plug); - - percpu_down_read(&bdev->bd_block_size_semaphore); - ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; @@ -1638,29 +1539,11 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0 && ret > 0) ret = err; } - - percpu_up_read(&bdev->bd_block_size_semaphore); - blk_finish_plug(&plug); - return ret; } EXPORT_SYMBOL_GPL(blkdev_aio_write); -static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) -{ - int ret; - struct block_device *bdev = I_BDEV(file->f_mapping->host); - - percpu_down_read(&bdev->bd_block_size_semaphore); - - ret = generic_file_mmap(file, vma); - - percpu_up_read(&bdev->bd_block_size_semaphore); - - return ret; -} - /* * Try to release a page associated with block device when the system * is under memory pressure. @@ -1691,9 +1574,9 @@ const struct file_operations def_blk_fops = { .llseek = block_llseek, .read = do_sync_read, .write = do_sync_write, - .aio_read = blkdev_aio_read, + .aio_read = generic_file_aio_read, .aio_write = blkdev_aio_write, - .mmap = blkdev_mmap, + .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index f318793..208d8aa 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -283,9 +283,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; } - rcu_read_lock(); - root_level = btrfs_header_level(root->node); - rcu_read_unlock(); + root_level = btrfs_old_root_level(root, time_seq); if (root_level + 1 == level) goto out; @@ -1177,16 +1175,15 @@ int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid, return ret; } -static char *ref_to_path(struct btrfs_root *fs_root, - struct btrfs_path *path, - u32 name_len, unsigned long name_off, - struct extent_buffer *eb_in, u64 parent, - char *dest, u32 size) +char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, + u32 name_len, unsigned long name_off, + struct extent_buffer *eb_in, u64 parent, + char *dest, u32 size) { int slot; u64 next_inum; int ret; - s64 bytes_left = size - 1; + s64 bytes_left = ((s64)size) - 1; struct extent_buffer *eb = eb_in; struct btrfs_key found_key; int leave_spinning = path->leave_spinning; @@ -1266,10 +1263,10 @@ char *btrfs_iref_to_path(struct btrfs_root *fs_root, struct extent_buffer *eb_in, u64 parent, char *dest, u32 size) { - return ref_to_path(fs_root, path, - btrfs_inode_ref_name_len(eb_in, iref), - (unsigned long)(iref + 1), - eb_in, parent, dest, size); + return btrfs_ref_to_path(fs_root, path, + btrfs_inode_ref_name_len(eb_in, iref), + (unsigned long)(iref + 1), + eb_in, parent, dest, size); } /* @@ -1715,9 +1712,8 @@ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off, ipath->fspath->bytes_left - s_ptr : 0; fspath_min = (char *)ipath->fspath->val + (i + 1) * s_ptr; - fspath = ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len, - name_off, eb, inum, fspath_min, - bytes_left); + fspath = btrfs_ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len, + name_off, eb, inum, fspath_min, bytes_left); if (IS_ERR(fspath)) return PTR_ERR(fspath); diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index e755330..d61feca7 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -62,6 +62,10 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, char *btrfs_iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, struct btrfs_inode_ref *iref, struct extent_buffer *eb, u64 parent, char *dest, u32 size); +char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, + u32 name_len, unsigned long name_off, + struct extent_buffer *eb_in, u64 parent, + char *dest, u32 size); struct btrfs_data_container *init_data_container(u32 total_bytes); struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index b334362..cdfb4c4 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -596,6 +596,11 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info, if (tree_mod_dont_log(fs_info, eb)) return 0; + /* + * When we override something during the move, we log these removals. + * This can only happen when we move towards the beginning of the + * buffer, i.e. dst_slot < src_slot. + */ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) { ret = tree_mod_log_insert_key_locked(fs_info, eb, i + dst_slot, MOD_LOG_KEY_REMOVE_WHILE_MOVING); @@ -647,8 +652,6 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info, if (tree_mod_dont_log(fs_info, NULL)) return 0; - __tree_mod_log_free_eb(fs_info, old_root); - ret = tree_mod_alloc(fs_info, flags, &tm); if (ret < 0) goto out; @@ -926,12 +929,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, ret = btrfs_dec_ref(trans, root, buf, 1, 1); BUG_ON(ret); /* -ENOMEM */ } - /* - * don't log freeing in case we're freeing the root node, this - * is done by tree_mod_log_set_root_pointer later - */ - if (buf != root->node && btrfs_header_level(buf) != 0) - tree_mod_log_free_eb(root->fs_info, buf); + tree_mod_log_free_eb(root->fs_info, buf); clean_tree_block(trans, root, buf); *last_ref = 1; } @@ -1225,6 +1223,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb, free_extent_buffer(eb); __tree_mod_log_rewind(eb_rewin, time_seq, tm); + WARN_ON(btrfs_header_nritems(eb_rewin) > + BTRFS_NODEPTRS_PER_BLOCK(fs_info->fs_root)); return eb_rewin; } @@ -1241,9 +1241,11 @@ get_old_root(struct btrfs_root *root, u64 time_seq) { struct tree_mod_elem *tm; struct extent_buffer *eb; + struct extent_buffer *old; struct tree_mod_root *old_root = NULL; u64 old_generation = 0; u64 logical; + u32 blocksize; eb = btrfs_read_lock_root_node(root); tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq); @@ -1259,14 +1261,32 @@ get_old_root(struct btrfs_root *root, u64 time_seq) } tm = tree_mod_log_search(root->fs_info, logical, time_seq); - if (old_root) + if (old_root && tm && tm->op != MOD_LOG_KEY_REMOVE_WHILE_FREEING) { + btrfs_tree_read_unlock(root->node); + free_extent_buffer(root->node); + blocksize = btrfs_level_size(root, old_root->level); + old = read_tree_block(root, logical, blocksize, 0); + if (!old) { + pr_warn("btrfs: failed to read tree block %llu from get_old_root\n", + logical); + WARN_ON(1); + } else { + eb = btrfs_clone_extent_buffer(old); + free_extent_buffer(old); + } + } else if (old_root) { + btrfs_tree_read_unlock(root->node); + free_extent_buffer(root->node); eb = alloc_dummy_extent_buffer(logical, root->nodesize); - else + } else { eb = btrfs_clone_extent_buffer(root->node); - btrfs_tree_read_unlock(root->node); - free_extent_buffer(root->node); + btrfs_tree_read_unlock(root->node); + free_extent_buffer(root->node); + } + if (!eb) return NULL; + extent_buffer_get(eb); btrfs_tree_read_lock(eb); if (old_root) { btrfs_set_header_bytenr(eb, eb->start); @@ -1279,11 +1299,28 @@ get_old_root(struct btrfs_root *root, u64 time_seq) __tree_mod_log_rewind(eb, time_seq, tm); else WARN_ON(btrfs_header_level(eb) != 0); - extent_buffer_get(eb); + WARN_ON(btrfs_header_nritems(eb) > BTRFS_NODEPTRS_PER_BLOCK(root)); return eb; } +int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq) +{ + struct tree_mod_elem *tm; + int level; + + tm = __tree_mod_log_oldest_root(root->fs_info, root, time_seq); + if (tm && tm->op == MOD_LOG_ROOT_REPLACE) { + level = tm->old_root.level; + } else { + rcu_read_lock(); + level = btrfs_header_level(root->node); + rcu_read_unlock(); + } + + return level; +} + static inline int should_cow_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf) @@ -1725,6 +1762,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, goto enospc; } + tree_mod_log_free_eb(root->fs_info, root->node); tree_mod_log_set_root_pointer(root, child); rcu_assign_pointer(root->node, child); @@ -2970,8 +3008,10 @@ static int push_node_left(struct btrfs_trans_handle *trans, push_items * sizeof(struct btrfs_key_ptr)); if (push_items < src_nritems) { - tree_mod_log_eb_move(root->fs_info, src, 0, push_items, - src_nritems - push_items); + /* + * don't call tree_mod_log_eb_move here, key removal was already + * fully logged by tree_mod_log_eb_copy above. + */ memmove_extent_buffer(src, btrfs_node_key_ptr_offset(0), btrfs_node_key_ptr_offset(push_items), (src_nritems - push_items) * diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 926c9ff..c72ead8 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3120,6 +3120,7 @@ static inline u64 btrfs_inc_tree_mod_seq(struct btrfs_fs_info *fs_info) { return atomic_inc_return(&fs_info->tree_mod_seq); } +int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq); /* root-item.c */ int btrfs_find_root_ref(struct btrfs_root *tree_root, @@ -3338,6 +3339,8 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page, int btrfs_update_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); +int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct inode *inode); int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 8036d3a..472873a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4110,8 +4110,8 @@ struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len) return eb; err: - for (i--; i >= 0; i--) - __free_page(eb->pages[i]); + for (; i > 0; i--) + __free_page(eb->pages[i - 1]); __free_extent_buffer(eb); return NULL; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 85a1e50..95542a1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -94,8 +94,6 @@ static noinline int cow_file_range(struct inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, int unlock); -static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode); static int btrfs_init_inode_security(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir, @@ -2746,8 +2744,9 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, return btrfs_update_inode_item(trans, root, inode); } -static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct inode *inode) +noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, + struct btrfs_root *root, + struct inode *inode) { int ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 6116880..8fcf9a5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -343,7 +343,8 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) return -EOPNOTSUPP; if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; - if (range.start > total_bytes) + if (range.start > total_bytes || + range.len < fs_info->sb->s_blocksize) return -EINVAL; range.len = min(range.len, total_bytes - range.start); @@ -570,7 +571,8 @@ static int create_snapshot(struct btrfs_root *root, struct dentry *dentry, ret = btrfs_commit_transaction(trans, root->fs_info->extent_root); } - BUG_ON(ret); + if (ret) + goto fail; ret = pending_snapshot->error; if (ret) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 5039686..fe9d02c 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -790,8 +790,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans, } path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out_free_root; + } key.objectid = 0; key.type = BTRFS_QGROUP_STATUS_KEY; @@ -800,7 +802,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans, ret = btrfs_insert_empty_item(trans, quota_root, path, &key, sizeof(*ptr)); if (ret) - goto out; + goto out_free_path; leaf = path->nodes[0]; ptr = btrfs_item_ptr(leaf, path->slots[0], @@ -818,8 +820,15 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans, fs_info->quota_root = quota_root; fs_info->pending_quota_state = 1; spin_unlock(&fs_info->qgroup_lock); -out: +out_free_path: btrfs_free_path(path); +out_free_root: + if (ret) { + free_extent_buffer(quota_root->node); + free_extent_buffer(quota_root->commit_root); + kfree(quota_root); + } +out: return ret; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index c7beb54..e78b297 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -745,31 +745,36 @@ typedef int (*iterate_inode_ref_t)(int num, u64 dir, int index, void *ctx); /* - * Helper function to iterate the entries in ONE btrfs_inode_ref. + * Helper function to iterate the entries in ONE btrfs_inode_ref or + * btrfs_inode_extref. * The iterate callback may return a non zero value to stop iteration. This can * be a negative value for error codes or 1 to simply stop it. * - * path must point to the INODE_REF when called. + * path must point to the INODE_REF or INODE_EXTREF when called. */ static int iterate_inode_ref(struct send_ctx *sctx, struct btrfs_root *root, struct btrfs_path *path, struct btrfs_key *found_key, int resolve, iterate_inode_ref_t iterate, void *ctx) { - struct extent_buffer *eb; + struct extent_buffer *eb = path->nodes[0]; struct btrfs_item *item; struct btrfs_inode_ref *iref; + struct btrfs_inode_extref *extref; struct btrfs_path *tmp_path; struct fs_path *p; - u32 cur; - u32 len; + u32 cur = 0; u32 total; - int slot; + int slot = path->slots[0]; u32 name_len; char *start; int ret = 0; - int num; + int num = 0; int index; + u64 dir; + unsigned long name_off; + unsigned long elem_size; + unsigned long ptr; p = fs_path_alloc_reversed(sctx); if (!p) @@ -781,24 +786,40 @@ static int iterate_inode_ref(struct send_ctx *sctx, return -ENOMEM; } - eb = path->nodes[0]; - slot = path->slots[0]; - item = btrfs_item_nr(eb, slot); - iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); - cur = 0; - len = 0; - total = btrfs_item_size(eb, item); - num = 0; + if (found_key->type == BTRFS_INODE_REF_KEY) { + ptr = (unsigned long)btrfs_item_ptr(eb, slot, + struct btrfs_inode_ref); + item = btrfs_item_nr(eb, slot); + total = btrfs_item_size(eb, item); + elem_size = sizeof(*iref); + } else { + ptr = btrfs_item_ptr_offset(eb, slot); + total = btrfs_item_size_nr(eb, slot); + elem_size = sizeof(*extref); + } + while (cur < total) { fs_path_reset(p); - name_len = btrfs_inode_ref_name_len(eb, iref); - index = btrfs_inode_ref_index(eb, iref); + if (found_key->type == BTRFS_INODE_REF_KEY) { + iref = (struct btrfs_inode_ref *)(ptr + cur); + name_len = btrfs_inode_ref_name_len(eb, iref); + name_off = (unsigned long)(iref + 1); + index = btrfs_inode_ref_index(eb, iref); + dir = found_key->offset; + } else { + extref = (struct btrfs_inode_extref *)(ptr + cur); + name_len = btrfs_inode_extref_name_len(eb, extref); + name_off = (unsigned long)&extref->name; + index = btrfs_inode_extref_index(eb, extref); + dir = btrfs_inode_extref_parent(eb, extref); + } + if (resolve) { - start = btrfs_iref_to_path(root, tmp_path, iref, eb, - found_key->offset, p->buf, - p->buf_len); + start = btrfs_ref_to_path(root, tmp_path, name_len, + name_off, eb, dir, + p->buf, p->buf_len); if (IS_ERR(start)) { ret = PTR_ERR(start); goto out; @@ -809,9 +830,10 @@ static int iterate_inode_ref(struct send_ctx *sctx, p->buf_len + p->buf - start); if (ret < 0) goto out; - start = btrfs_iref_to_path(root, tmp_path, iref, - eb, found_key->offset, p->buf, - p->buf_len); + start = btrfs_ref_to_path(root, tmp_path, + name_len, name_off, + eb, dir, + p->buf, p->buf_len); if (IS_ERR(start)) { ret = PTR_ERR(start); goto out; @@ -820,21 +842,16 @@ static int iterate_inode_ref(struct send_ctx *sctx, } p->start = start; } else { - ret = fs_path_add_from_extent_buffer(p, eb, - (unsigned long)(iref + 1), name_len); + ret = fs_path_add_from_extent_buffer(p, eb, name_off, + name_len); if (ret < 0) goto out; } - - len = sizeof(*iref) + name_len; - iref = (struct btrfs_inode_ref *)((char *)iref + len); - cur += len; - - ret = iterate(num, found_key->offset, index, p, ctx); + cur += elem_size + name_len; + ret = iterate(num, dir, index, p, ctx); if (ret) goto out; - num++; } @@ -998,7 +1015,8 @@ static int get_inode_path(struct send_ctx *sctx, struct btrfs_root *root, } btrfs_item_key_to_cpu(p->nodes[0], &found_key, p->slots[0]); if (found_key.objectid != ino || - found_key.type != BTRFS_INODE_REF_KEY) { + (found_key.type != BTRFS_INODE_REF_KEY && + found_key.type != BTRFS_INODE_EXTREF_KEY)) { ret = -ENOENT; goto out; } @@ -1551,8 +1569,8 @@ static int get_first_ref(struct send_ctx *sctx, struct btrfs_key key; struct btrfs_key found_key; struct btrfs_path *path; - struct btrfs_inode_ref *iref; int len; + u64 parent_dir; path = alloc_path_for_send(); if (!path) @@ -1568,27 +1586,41 @@ static int get_first_ref(struct send_ctx *sctx, if (!ret) btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); - if (ret || found_key.objectid != key.objectid || - found_key.type != key.type) { + if (ret || found_key.objectid != ino || + (found_key.type != BTRFS_INODE_REF_KEY && + found_key.type != BTRFS_INODE_EXTREF_KEY)) { ret = -ENOENT; goto out; } - iref = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_ref); - len = btrfs_inode_ref_name_len(path->nodes[0], iref); - ret = fs_path_add_from_extent_buffer(name, path->nodes[0], - (unsigned long)(iref + 1), len); + if (key.type == BTRFS_INODE_REF_KEY) { + struct btrfs_inode_ref *iref; + iref = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_ref); + len = btrfs_inode_ref_name_len(path->nodes[0], iref); + ret = fs_path_add_from_extent_buffer(name, path->nodes[0], + (unsigned long)(iref + 1), + len); + parent_dir = found_key.offset; + } else { + struct btrfs_inode_extref *extref; + extref = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_extref); + len = btrfs_inode_extref_name_len(path->nodes[0], extref); + ret = fs_path_add_from_extent_buffer(name, path->nodes[0], + (unsigned long)&extref->name, len); + parent_dir = btrfs_inode_extref_parent(path->nodes[0], extref); + } if (ret < 0) goto out; btrfs_release_path(path); - ret = get_inode_info(root, found_key.offset, NULL, dir_gen, NULL, NULL, + ret = get_inode_info(root, parent_dir, NULL, dir_gen, NULL, NULL, NULL, NULL); if (ret < 0) goto out; - *dir = found_key.offset; + *dir = parent_dir; out: btrfs_free_path(path); @@ -2430,7 +2462,8 @@ verbose_printk("btrfs: send_create_inode %llu\n", ino); TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH_LINK, p); } else if (S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { - TLV_PUT_U64(sctx, BTRFS_SEND_A_RDEV, rdev); + TLV_PUT_U64(sctx, BTRFS_SEND_A_RDEV, new_encode_dev(rdev)); + TLV_PUT_U64(sctx, BTRFS_SEND_A_MODE, mode); } ret = send_cmd(sctx); @@ -3226,7 +3259,8 @@ static int process_all_refs(struct send_ctx *sctx, btrfs_item_key_to_cpu(eb, &found_key, slot); if (found_key.objectid != key.objectid || - found_key.type != key.type) + (found_key.type != BTRFS_INODE_REF_KEY && + found_key.type != BTRFS_INODE_EXTREF_KEY)) break; ret = iterate_inode_ref(sctx, root, path, &found_key, 0, cb, @@ -3987,7 +4021,7 @@ static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end) if (sctx->cur_ino == 0) goto out; if (!at_end && sctx->cur_ino == sctx->cmp_key->objectid && - sctx->cmp_key->type <= BTRFS_INODE_REF_KEY) + sctx->cmp_key->type <= BTRFS_INODE_EXTREF_KEY) goto out; if (list_empty(&sctx->new_refs) && list_empty(&sctx->deleted_refs)) goto out; @@ -4033,22 +4067,21 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret < 0) goto out; - if (!S_ISLNK(sctx->cur_inode_mode)) { - if (!sctx->parent_root || sctx->cur_inode_new) { + if (!sctx->parent_root || sctx->cur_inode_new) { + need_chown = 1; + if (!S_ISLNK(sctx->cur_inode_mode)) need_chmod = 1; - need_chown = 1; - } else { - ret = get_inode_info(sctx->parent_root, sctx->cur_ino, - NULL, NULL, &right_mode, &right_uid, - &right_gid, NULL); - if (ret < 0) - goto out; + } else { + ret = get_inode_info(sctx->parent_root, sctx->cur_ino, + NULL, NULL, &right_mode, &right_uid, + &right_gid, NULL); + if (ret < 0) + goto out; - if (left_uid != right_uid || left_gid != right_gid) - need_chown = 1; - if (left_mode != right_mode) - need_chmod = 1; - } + if (left_uid != right_uid || left_gid != right_gid) + need_chown = 1; + if (!S_ISLNK(sctx->cur_inode_mode) && left_mode != right_mode) + need_chmod = 1; } if (S_ISREG(sctx->cur_inode_mode)) { @@ -4335,7 +4368,8 @@ static int changed_cb(struct btrfs_root *left_root, if (key->type == BTRFS_INODE_ITEM_KEY) ret = changed_inode(sctx, result); - else if (key->type == BTRFS_INODE_REF_KEY) + else if (key->type == BTRFS_INODE_REF_KEY || + key->type == BTRFS_INODE_EXTREF_KEY) ret = changed_ref(sctx, result); else if (key->type == BTRFS_XATTR_ITEM_KEY) ret = changed_xattr(sctx, result); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 77db875..04bbfb1 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1200,7 +1200,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->i_size + dentry->d_name.len * 2); parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME; - ret = btrfs_update_inode(trans, parent_root, parent_inode); + ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode); if (ret) btrfs_abort_transaction(trans, root, ret); fail: diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 029b903..0f5ebb7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1819,6 +1819,13 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) "Failed to relocate sys chunks after " "device initialization. This can be fixed " "using the \"btrfs balance\" command."); + trans = btrfs_attach_transaction(root); + if (IS_ERR(trans)) { + if (PTR_ERR(trans) == -ENOENT) + return 0; + return PTR_ERR(trans); + } + ret = btrfs_commit_transaction(trans, root); } return ret; diff --git a/fs/buffer.c b/fs/buffer.c index b5f0442..ec0aca8 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -911,6 +911,18 @@ link_dev_buffers(struct page *page, struct buffer_head *head) attach_page_buffers(page, head); } +static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) +{ + sector_t retval = ~((sector_t)0); + loff_t sz = i_size_read(bdev->bd_inode); + + if (sz) { + unsigned int sizebits = blksize_bits(size); + retval = (sz >> sizebits); + } + return retval; +} + /* * Initialise the state of a blockdev page's buffers. */ @@ -921,7 +933,7 @@ init_page_buffers(struct page *page, struct block_device *bdev, struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); - sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode)); + sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); do { if (!buffer_mapped(bh)) { @@ -1553,6 +1565,28 @@ void unmap_underlying_metadata(struct block_device *bdev, sector_t block) EXPORT_SYMBOL(unmap_underlying_metadata); /* + * Size is a power-of-two in the range 512..PAGE_SIZE, + * and the case we care about most is PAGE_SIZE. + * + * So this *could* possibly be written with those + * constraints in mind (relevant mostly if some + * architecture has a slow bit-scan instruction) + */ +static inline int block_size_bits(unsigned int blocksize) +{ + return ilog2(blocksize); +} + +static struct buffer_head *create_page_buffers(struct page *page, struct inode *inode, unsigned int b_state) +{ + BUG_ON(!PageLocked(page)); + + if (!page_has_buffers(page)) + create_empty_buffers(page, 1 << ACCESS_ONCE(inode->i_blkbits), b_state); + return page_buffers(page); +} + +/* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning @@ -1589,19 +1623,13 @@ static int __block_write_full_page(struct inode *inode, struct page *page, sector_t block; sector_t last_block; struct buffer_head *bh, *head; - const unsigned blocksize = 1 << inode->i_blkbits; + unsigned int blocksize, bbits; int nr_underway = 0; int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE); - BUG_ON(!PageLocked(page)); - - last_block = (i_size_read(inode) - 1) >> inode->i_blkbits; - - if (!page_has_buffers(page)) { - create_empty_buffers(page, blocksize, + head = create_page_buffers(page, inode, (1 << BH_Dirty)|(1 << BH_Uptodate)); - } /* * Be very careful. We have no exclusion from __set_page_dirty_buffers @@ -1613,9 +1641,12 @@ static int __block_write_full_page(struct inode *inode, struct page *page, * handle that here by just cleaning them. */ - block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - head = page_buffers(page); bh = head; + blocksize = bh->b_size; + bbits = block_size_bits(blocksize); + + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + last_block = (i_size_read(inode) - 1) >> bbits; /* * Get all the dirty buffers mapped to disk addresses and @@ -1806,12 +1837,10 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len, BUG_ON(to > PAGE_CACHE_SIZE); BUG_ON(from > to); - blocksize = 1 << inode->i_blkbits; - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); - head = page_buffers(page); + head = create_page_buffers(page, inode, 0); + blocksize = head->b_size; + bbits = block_size_bits(blocksize); - bbits = inode->i_blkbits; block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); for(bh = head, block_start = 0; bh != head || !block_start; @@ -1881,11 +1910,11 @@ static int __block_commit_write(struct inode *inode, struct page *page, unsigned blocksize; struct buffer_head *bh, *head; - blocksize = 1 << inode->i_blkbits; + bh = head = page_buffers(page); + blocksize = bh->b_size; - for(bh = head = page_buffers(page), block_start = 0; - bh != head || !block_start; - block_start=block_end, bh = bh->b_this_page) { + block_start = 0; + do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) @@ -1895,7 +1924,10 @@ static int __block_commit_write(struct inode *inode, struct page *page, mark_buffer_dirty(bh); } clear_buffer_new(bh); - } + + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); /* * If this is a partial write which happened to make all buffers @@ -2020,7 +2052,6 @@ EXPORT_SYMBOL(generic_write_end); int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, unsigned long from) { - struct inode *inode = page->mapping->host; unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; @@ -2029,13 +2060,13 @@ int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, if (!page_has_buffers(page)) return 0; - blocksize = 1 << inode->i_blkbits; + head = page_buffers(page); + blocksize = head->b_size; to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count); to = from + to; if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) return 0; - head = page_buffers(page); bh = head; block_start = 0; do { @@ -2068,18 +2099,16 @@ int block_read_full_page(struct page *page, get_block_t *get_block) struct inode *inode = page->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *arr[MAX_BUF_PER_PAGE]; - unsigned int blocksize; + unsigned int blocksize, bbits; int nr, i; int fully_mapped = 1; - BUG_ON(!PageLocked(page)); - blocksize = 1 << inode->i_blkbits; - if (!page_has_buffers(page)) - create_empty_buffers(page, blocksize, 0); - head = page_buffers(page); + head = create_page_buffers(page, inode, 0); + blocksize = head->b_size; + bbits = block_size_bits(blocksize); - iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); - lblock = (i_size_read(inode)+blocksize-1) >> inode->i_blkbits; + iblock = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + lblock = (i_size_read(inode)+blocksize-1) >> bbits; bh = head; nr = 0; i = 0; @@ -2864,6 +2893,55 @@ static void end_bio_bh_io_sync(struct bio *bio, int err) bio_put(bio); } +/* + * This allows us to do IO even on the odd last sectors + * of a device, even if the bh block size is some multiple + * of the physical sector size. + * + * We'll just truncate the bio to the size of the device, + * and clear the end of the buffer head manually. + * + * Truly out-of-range accesses will turn into actual IO + * errors, this only handles the "we need to be able to + * do IO at the final sector" case. + */ +static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh) +{ + sector_t maxsector; + unsigned bytes; + + maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; + if (!maxsector) + return; + + /* + * If the *whole* IO is past the end of the device, + * let it through, and the IO layer will turn it into + * an EIO. + */ + if (unlikely(bio->bi_sector >= maxsector)) + return; + + maxsector -= bio->bi_sector; + bytes = bio->bi_size; + if (likely((bytes >> 9) <= maxsector)) + return; + + /* Uhhuh. We've got a bh that straddles the device size! */ + bytes = maxsector << 9; + + /* Truncate the bio.. */ + bio->bi_size = bytes; + bio->bi_io_vec[0].bv_len = bytes; + + /* ..and clear the end of the buffer for reads */ + if ((rw & RW_MASK) == READ) { + void *kaddr = kmap_atomic(bh->b_page); + memset(kaddr + bh_offset(bh) + bytes, 0, bh->b_size - bytes); + kunmap_atomic(kaddr); + } +} + int submit_bh(int rw, struct buffer_head * bh) { struct bio *bio; @@ -2900,6 +2978,9 @@ int submit_bh(int rw, struct buffer_head * bh) bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; + /* Take care of bh's that straddle the end of the device */ + guard_bh_eod(rw, bio, bh); + bio_get(bio); submit_bio(rw, bio); diff --git a/fs/ceph/export.c b/fs/ceph/export.c index 02ce909..9349bb3 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -90,6 +90,8 @@ static int ceph_encode_fh(struct inode *inode, u32 *rawfh, int *max_len, *max_len = handle_length; type = 255; } + if (dentry) + dput(dentry); return type; } diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index fc783e2..0fb15bb 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -225,6 +225,13 @@ sid_to_str(struct cifs_sid *sidptr, char *sidstr) } static void +cifs_copy_sid(struct cifs_sid *dst, const struct cifs_sid *src) +{ + memcpy(dst, src, sizeof(*dst)); + dst->num_subauth = min_t(u8, src->num_subauth, NUM_SUBAUTHS); +} + +static void id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr, struct cifs_sid_id **psidid, char *typestr) { @@ -248,7 +255,7 @@ id_rb_insert(struct rb_root *root, struct cifs_sid *sidptr, } } - memcpy(&(*psidid)->sid, sidptr, sizeof(struct cifs_sid)); + cifs_copy_sid(&(*psidid)->sid, sidptr); (*psidid)->time = jiffies - (SID_MAP_RETRY + 1); (*psidid)->refcount = 0; @@ -354,7 +361,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) * any fields of the node after a reference is put . */ if (test_bit(SID_ID_MAPPED, &psidid->state)) { - memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid)); + cifs_copy_sid(ssid, &psidid->sid); psidid->time = jiffies; /* update ts for accessing */ goto id_sid_out; } @@ -370,14 +377,14 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) if (IS_ERR(sidkey)) { rc = -EINVAL; cFYI(1, "%s: Can't map and id to a SID", __func__); + } else if (sidkey->datalen < sizeof(struct cifs_sid)) { + rc = -EIO; + cFYI(1, "%s: Downcall contained malformed key " + "(datalen=%hu)", __func__, sidkey->datalen); } else { lsid = (struct cifs_sid *)sidkey->payload.data; - memcpy(&psidid->sid, lsid, - sidkey->datalen < sizeof(struct cifs_sid) ? - sidkey->datalen : sizeof(struct cifs_sid)); - memcpy(ssid, &psidid->sid, - sidkey->datalen < sizeof(struct cifs_sid) ? - sidkey->datalen : sizeof(struct cifs_sid)); + cifs_copy_sid(&psidid->sid, lsid); + cifs_copy_sid(ssid, &psidid->sid); set_bit(SID_ID_MAPPED, &psidid->state); key_put(sidkey); kfree(psidid->sidstr); @@ -396,7 +403,7 @@ id_to_sid(unsigned long cid, uint sidtype, struct cifs_sid *ssid) return rc; } if (test_bit(SID_ID_MAPPED, &psidid->state)) - memcpy(ssid, &psidid->sid, sizeof(struct cifs_sid)); + cifs_copy_sid(ssid, &psidid->sid); else rc = -EINVAL; } @@ -675,8 +682,6 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid) static void copy_sec_desc(const struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, __u32 sidsoffset) { - int i; - struct cifs_sid *owner_sid_ptr, *group_sid_ptr; struct cifs_sid *nowner_sid_ptr, *ngroup_sid_ptr; @@ -692,26 +697,14 @@ static void copy_sec_desc(const struct cifs_ntsd *pntsd, owner_sid_ptr = (struct cifs_sid *)((char *)pntsd + le32_to_cpu(pntsd->osidoffset)); nowner_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset); - - nowner_sid_ptr->revision = owner_sid_ptr->revision; - nowner_sid_ptr->num_subauth = owner_sid_ptr->num_subauth; - for (i = 0; i < 6; i++) - nowner_sid_ptr->authority[i] = owner_sid_ptr->authority[i]; - for (i = 0; i < 5; i++) - nowner_sid_ptr->sub_auth[i] = owner_sid_ptr->sub_auth[i]; + cifs_copy_sid(nowner_sid_ptr, owner_sid_ptr); /* copy group sid */ group_sid_ptr = (struct cifs_sid *)((char *)pntsd + le32_to_cpu(pntsd->gsidoffset)); ngroup_sid_ptr = (struct cifs_sid *)((char *)pnntsd + sidsoffset + sizeof(struct cifs_sid)); - - ngroup_sid_ptr->revision = group_sid_ptr->revision; - ngroup_sid_ptr->num_subauth = group_sid_ptr->num_subauth; - for (i = 0; i < 6; i++) - ngroup_sid_ptr->authority[i] = group_sid_ptr->authority[i]; - for (i = 0; i < 5; i++) - ngroup_sid_ptr->sub_auth[i] = group_sid_ptr->sub_auth[i]; + cifs_copy_sid(ngroup_sid_ptr, group_sid_ptr); return; } @@ -1120,8 +1113,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, kfree(nowner_sid_ptr); return rc; } - memcpy(owner_sid_ptr, nowner_sid_ptr, - sizeof(struct cifs_sid)); + cifs_copy_sid(owner_sid_ptr, nowner_sid_ptr); kfree(nowner_sid_ptr); *aclflag = CIFS_ACL_OWNER; } @@ -1139,8 +1131,7 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd, kfree(ngroup_sid_ptr); return rc; } - memcpy(group_sid_ptr, ngroup_sid_ptr, - sizeof(struct cifs_sid)); + cifs_copy_sid(group_sid_ptr, ngroup_sid_ptr); kfree(ngroup_sid_ptr); *aclflag = CIFS_ACL_GROUP; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 7c0a812..d3671f2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -398,7 +398,16 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, * in network traffic in the other paths. */ if (!(oflags & O_CREAT)) { - struct dentry *res = cifs_lookup(inode, direntry, 0); + struct dentry *res; + + /* + * Check for hashed negative dentry. We have already revalidated + * the dentry and it is fine. No need to perform another lookup. + */ + if (!d_unhashed(direntry)) + return -ENOENT; + + res = cifs_lookup(inode, direntry, 0); if (IS_ERR(res)) return PTR_ERR(res); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index edb25b4..70b6f4c 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1794,7 +1794,6 @@ static int cifs_writepages(struct address_space *mapping, struct TCP_Server_Info *server; struct page *page; int rc = 0; - loff_t isize = i_size_read(mapping->host); /* * If wsize is smaller than the page cache size, default to writing @@ -1899,7 +1898,7 @@ retry: */ set_page_writeback(page); - if (page_offset(page) >= isize) { + if (page_offset(page) >= i_size_read(mapping->host)) { done = true; unlock_page(page); end_page_writeback(page); @@ -1932,7 +1931,8 @@ retry: wdata->offset = page_offset(wdata->pages[0]); wdata->pagesz = PAGE_CACHE_SIZE; wdata->tailsz = - min(isize - page_offset(wdata->pages[nr_pages - 1]), + min(i_size_read(mapping->host) - + page_offset(wdata->pages[nr_pages - 1]), (loff_t)PAGE_CACHE_SIZE); wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) + wdata->tailsz; diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index f9b5d3d..1c576e8 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -86,14 +86,17 @@ cifs_readdir_lookup(struct dentry *parent, struct qstr *name, dentry = d_lookup(parent, name); if (dentry) { + int err; inode = dentry->d_inode; /* update inode in place if i_ino didn't change */ if (inode && CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { cifs_fattr_to_inode(inode, fattr); return dentry; } - d_drop(dentry); + err = d_invalidate(dentry); dput(dentry); + if (err) + return NULL; } dentry = d_alloc(parent, name); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 56cc4be..34cea27 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -766,7 +766,6 @@ smb_set_file_info(struct inode *inode, const char *full_path, struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = NULL; struct cifs_tcon *tcon; - FILE_BASIC_INFO info_buf; /* if the file is already open for write, just use that fileid */ open_file = find_writable_file(cinode, true); @@ -817,7 +816,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, netpid = current->tgid; set_via_filehandle: - rc = CIFSSMBSetFileInfo(xid, tcon, &info_buf, netfid, netpid); + rc = CIFSSMBSetFileInfo(xid, tcon, buf, netfid, netpid); if (!rc) cinode->cifsAttrs = le32_to_cpu(buf->Attributes); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index f505402..4c6285f 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -210,6 +210,8 @@ static int do_video_set_spu_palette(unsigned int fd, unsigned int cmd, err = get_user(palp, &up->palette); err |= get_user(length, &up->length); + if (err) + return -EFAULT; up_native = compat_alloc_user_space(sizeof(struct video_spu_palette)); err = put_user(compat_ptr(palp), &up_native->palette); diff --git a/fs/direct-io.c b/fs/direct-io.c index f86c720..cf5b44b 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -540,6 +540,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, sector_t fs_endblk; /* Into file, in filesystem-sized blocks */ unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; + unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; /* * If there was a memory error and we've overwritten all the @@ -554,7 +555,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, fs_count = fs_endblk - fs_startblk + 1; map_bh->b_state = 0; - map_bh->b_size = fs_count << dio->inode->i_blkbits; + map_bh->b_size = fs_count << i_blkbits; /* * For writes inside i_size on a DIO_SKIP_HOLES filesystem we @@ -1053,7 +1054,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, int seg; size_t size; unsigned long addr; - unsigned blkbits = inode->i_blkbits; + 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; @@ -1149,7 +1151,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, dio->inode = inode; dio->rw = rw; sdio.blkbits = blkbits; - sdio.blkfactor = inode->i_blkbits - blkbits; + sdio.blkfactor = i_blkbits - blkbits; sdio.block_in_file = offset >> blkbits; sdio.get_block = get_block; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index da72250..cd96649 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -346,7 +346,7 @@ static inline struct epitem *ep_item_from_epqueue(poll_table *p) /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { - return op == EPOLL_CTL_ADD || op == EPOLL_CTL_MOD; + return op != EPOLL_CTL_DEL; } /* Initialize the poll safe wake up structure */ @@ -676,34 +676,6 @@ static int ep_remove(struct eventpoll *ep, struct epitem *epi) return 0; } -/* - * Disables a "struct epitem" in the eventpoll set. Returns -EBUSY if the item - * had no event flags set, indicating that another thread may be currently - * handling that item's events (in the case that EPOLLONESHOT was being - * used). Otherwise a zero result indicates that the item has been disabled - * from receiving events. A disabled item may be re-enabled via - * EPOLL_CTL_MOD. Must be called with "mtx" held. - */ -static int ep_disable(struct eventpoll *ep, struct epitem *epi) -{ - int result = 0; - unsigned long flags; - - spin_lock_irqsave(&ep->lock, flags); - if (epi->event.events & ~EP_PRIVATE_BITS) { - if (ep_is_linked(&epi->rdllink)) - list_del_init(&epi->rdllink); - /* Ensure ep_poll_callback will not add epi back onto ready - list: */ - epi->event.events &= EP_PRIVATE_BITS; - } - else - result = -EBUSY; - spin_unlock_irqrestore(&ep->lock, flags); - - return result; -} - static void ep_free(struct eventpoll *ep) { struct rb_node *rbp; @@ -1048,6 +1020,8 @@ static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) rb_insert_color(&epi->rbn, &ep->rbr); } + + #define PATH_ARR_SIZE 5 /* * These are the number paths of length 1 to 5, that we are allowing to emanate @@ -1813,12 +1787,6 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, } else error = -ENOENT; break; - case EPOLL_CTL_DISABLE: - if (epi) - error = ep_disable(ep, epi); - else - error = -ENOENT; - break; } mutex_unlock(&ep->mtx); @@ -1083,7 +1083,8 @@ int flush_old_exec(struct linux_binprm * bprm) bprm->mm = NULL; /* We're using it now */ set_fs(USER_DS); - current->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD); + current->flags &= + ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE); flush_thread(); current->personality &= ~bprm->per_clear; diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index 7320a66..22548f5 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -2101,8 +2101,9 @@ int ext3_trim_fs(struct super_block *sb, struct fstrim_range *range) end = start + (range->len >> sb->s_blocksize_bits) - 1; minlen = range->minlen >> sb->s_blocksize_bits; - if (unlikely(minlen > EXT3_BLOCKS_PER_GROUP(sb)) || - unlikely(start >= max_blks)) + if (minlen > EXT3_BLOCKS_PER_GROUP(sb) || + start >= max_blks || + range->len < sb->s_blocksize) return -EINVAL; if (end >= max_blks) end = max_blks - 1; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 4facdd2..3a100e7 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -725,6 +725,10 @@ repeat_in_this_group: "inode=%lu", ino + 1); continue; } + BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, inode_bitmap_bh); + if (err) + goto fail; ext4_lock_group(sb, group); ret2 = ext4_test_and_set_bit(ino, inode_bitmap_bh->b_data); ext4_unlock_group(sb, group); @@ -738,6 +742,11 @@ repeat_in_this_group: goto out; got: + BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); + err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); + if (err) + goto fail; + /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -771,11 +780,6 @@ got: goto fail; } - BUFFER_TRACE(inode_bitmap_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, inode_bitmap_bh); - if (err) - goto fail; - BUFFER_TRACE(group_desc_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, group_desc_bh); if (err) @@ -823,11 +827,6 @@ got: } ext4_unlock_group(sb, group); - BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata"); - err = ext4_handle_dirty_metadata(handle, NULL, inode_bitmap_bh); - if (err) - goto fail; - BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh); if (err) @@ -685,7 +685,6 @@ void do_close_on_exec(struct files_struct *files) struct fdtable *fdt; /* exec unshares first */ - BUG_ON(atomic_read(&files->count) != 1); spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; @@ -900,7 +899,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags) return __close_fd(files, fd); if (fd >= rlimit(RLIMIT_NOFILE)) - return -EMFILE; + return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); @@ -926,7 +925,7 @@ SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) - return -EMFILE; + return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); @@ -995,16 +994,18 @@ int iterate_fd(struct files_struct *files, unsigned n, const void *p) { struct fdtable *fdt; - struct file *file; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); - fdt = files_fdtable(files); - while (!res && n < fdt->max_fds) { - file = rcu_dereference_check_fdtable(files, fdt->fd[n++]); - if (file) - res = f(p, file, n); + for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { + struct file *file; + file = rcu_dereference_check_fdtable(files, fdt->fd[n]); + if (!file) + continue; + res = f(p, file, n); + if (res) + break; } spin_unlock(&files->file_lock); return res; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 51ea267..3e3422f 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -228,6 +228,8 @@ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; + /* If inode is clean an unused, put it into LRU now... */ + inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 0def050..e056b4c 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -516,15 +516,13 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma) struct gfs2_holder i_gh; int error; - gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh); - error = gfs2_glock_nq(&i_gh); - if (error == 0) { - file_accessed(file); - gfs2_glock_dq(&i_gh); - } - gfs2_holder_uninit(&i_gh); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, + &i_gh); if (error) return error; + /* grab lock to update inode */ + gfs2_glock_dq_uninit(&i_gh); + file_accessed(file); } vma->vm_ops = &gfs2_vm_ops; @@ -677,10 +675,8 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, size_t writesize = iov_length(iov, nr_segs); struct dentry *dentry = file->f_dentry; struct gfs2_inode *ip = GFS2_I(dentry->d_inode); - struct gfs2_sbd *sdp; int ret; - sdp = GFS2_SB(file->f_mapping->host); ret = gfs2_rs_alloc(ip); if (ret) return ret; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 8ff95a2..9ceccb1 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -393,12 +393,10 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct gfs2_meta_header *mh; struct gfs2_trans *tr; - lock_buffer(bd->bd_bh); - gfs2_log_lock(sdp); tr = current->journal_info; tr->tr_touched = 1; if (!list_empty(&bd->bd_list)) - goto out; + return; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); mh = (struct gfs2_meta_header *)bd->bd_bh->b_data; @@ -414,9 +412,6 @@ static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) sdp->sd_log_num_buf++; list_add(&bd->bd_list, &sdp->sd_log_le_buf); tr->tr_num_buf_new++; -out: - gfs2_log_unlock(sdp); - unlock_buffer(bd->bd_bh); } static void gfs2_check_magic(struct buffer_head *bh) @@ -621,7 +616,6 @@ static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) static void revoke_lo_before_commit(struct gfs2_sbd *sdp) { - struct gfs2_log_descriptor *ld; struct gfs2_meta_header *mh; unsigned int offset; struct list_head *head = &sdp->sd_log_le_revoke; @@ -634,7 +628,6 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp) length = gfs2_struct2blk(sdp, sdp->sd_log_num_revoke, sizeof(u64)); page = gfs2_get_log_desc(sdp, GFS2_LOG_DESC_REVOKE, length, sdp->sd_log_num_revoke); - ld = page_address(page); offset = sizeof(struct gfs2_log_descriptor); list_for_each_entry(bd, head, bd_list) { @@ -777,12 +770,10 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct address_space *mapping = bd->bd_bh->b_page->mapping; struct gfs2_inode *ip = GFS2_I(mapping->host); - lock_buffer(bd->bd_bh); - gfs2_log_lock(sdp); if (tr) tr->tr_touched = 1; if (!list_empty(&bd->bd_list)) - goto out; + return; set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags); set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags); if (gfs2_is_jdata(ip)) { @@ -793,9 +784,6 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) } else { list_add_tail(&bd->bd_list, &sdp->sd_log_le_ordered); } -out: - gfs2_log_unlock(sdp); - unlock_buffer(bd->bd_bh); } /** diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 40c4b0d..c5af8e1 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -497,8 +497,11 @@ int gfs2_quota_hold(struct gfs2_inode *ip, u32 uid, u32 gid) struct gfs2_quota_data **qd; int error; - if (ip->i_res == NULL) - gfs2_rs_alloc(ip); + if (ip->i_res == NULL) { + error = gfs2_rs_alloc(ip); + if (error) + return error; + } qd = ip->i_res->rs_qa_qd; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 3cc402c..38fe18f 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -553,7 +553,6 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd) */ int gfs2_rs_alloc(struct gfs2_inode *ip) { - int error = 0; struct gfs2_blkreserv *res; if (ip->i_res) @@ -561,7 +560,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS); if (!res) - error = -ENOMEM; + return -ENOMEM; RB_CLEAR_NODE(&res->rs_node); @@ -571,7 +570,7 @@ int gfs2_rs_alloc(struct gfs2_inode *ip) else ip->i_res = res; up_write(&ip->i_rw_mutex); - return error; + return 0; } static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs) @@ -1263,7 +1262,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) int ret = 0; u64 amt; u64 trimmed = 0; + u64 start, end, minlen; unsigned int x; + unsigned bs_shift = sdp->sd_sb.sb_bsize_shift; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -1271,19 +1272,25 @@ int gfs2_fitrim(struct file *filp, void __user *argp) if (!blk_queue_discard(q)) return -EOPNOTSUPP; - if (argp == NULL) { - r.start = 0; - r.len = ULLONG_MAX; - r.minlen = 0; - } else if (copy_from_user(&r, argp, sizeof(r))) + if (copy_from_user(&r, argp, sizeof(r))) return -EFAULT; ret = gfs2_rindex_update(sdp); if (ret) return ret; - rgd = gfs2_blk2rgrpd(sdp, r.start, 0); - rgd_end = gfs2_blk2rgrpd(sdp, r.start + r.len, 0); + start = r.start >> bs_shift; + end = start + (r.len >> bs_shift); + minlen = max_t(u64, r.minlen, + q->limits.discard_granularity) >> bs_shift; + + rgd = gfs2_blk2rgrpd(sdp, start, 0); + rgd_end = gfs2_blk2rgrpd(sdp, end - 1, 0); + + if (end <= start || + minlen > sdp->sd_max_rg_data || + start > rgd_end->rd_data0 + rgd_end->rd_data) + return -EINVAL; while (1) { @@ -1295,7 +1302,9 @@ int gfs2_fitrim(struct file *filp, void __user *argp) /* Trim each bitmap in the rgrp */ for (x = 0; x < rgd->rd_length; x++) { struct gfs2_bitmap *bi = rgd->rd_bits + x; - ret = gfs2_rgrp_send_discards(sdp, rgd->rd_data0, NULL, bi, r.minlen, &amt); + ret = gfs2_rgrp_send_discards(sdp, + rgd->rd_data0, NULL, bi, minlen, + &amt); if (ret) { gfs2_glock_dq_uninit(&gh); goto out; @@ -1324,7 +1333,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp) out: r.len = trimmed << 9; - if (argp && copy_to_user(argp, &r, sizeof(r))) + if (copy_to_user(argp, &r, sizeof(r))) return -EFAULT; return ret; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index bc73726..d648867 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -810,7 +810,8 @@ static void gfs2_dirty_inode(struct inode *inode, int flags) return; } need_unlock = 1; - } + } else if (WARN_ON_ONCE(ip->i_gl->gl_state != LM_ST_EXCLUSIVE)) + return; if (current->journal_info == NULL) { ret = gfs2_trans_begin(sdp, RES_DINODE, 0); diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index adbd278..4136270 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -155,14 +155,22 @@ void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta) struct gfs2_sbd *sdp = gl->gl_sbd; struct gfs2_bufdata *bd; + lock_buffer(bh); + gfs2_log_lock(sdp); bd = bh->b_private; if (bd) gfs2_assert(sdp, bd->bd_gl == gl); else { + gfs2_log_unlock(sdp); + unlock_buffer(bh); gfs2_attach_bufdata(gl, bh, meta); bd = bh->b_private; + lock_buffer(bh); + gfs2_log_lock(sdp); } lops_add(sdp, bd); + gfs2_log_unlock(sdp); + unlock_buffer(bh); } void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) @@ -408,6 +408,19 @@ static void inode_lru_list_add(struct inode *inode) spin_unlock(&inode->i_sb->s_inode_lru_lock); } +/* + * Add inode to LRU if needed (inode is unused and clean). + * + * Needs inode->i_lock held. + */ +void inode_add_lru(struct inode *inode) +{ + if (!(inode->i_state & (I_DIRTY | I_SYNC | I_FREEING | I_WILL_FREE)) && + !atomic_read(&inode->i_count) && inode->i_sb->s_flags & MS_ACTIVE) + inode_lru_list_add(inode); +} + + static void inode_lru_list_del(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_lru_lock); @@ -1390,8 +1403,7 @@ static void iput_final(struct inode *inode) if (!drop && (sb->s_flags & MS_ACTIVE)) { inode->i_state |= I_REFERENCED; - if (!(inode->i_state & (I_DIRTY|I_SYNC))) - inode_lru_list_add(inode); + inode_add_lru(inode); spin_unlock(&inode->i_lock); return; } diff --git a/fs/internal.h b/fs/internal.h index 916b7cb..2f6af7f 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -110,6 +110,7 @@ extern int open_check_o_direct(struct file *f); * inode.c */ extern spinlock_t inode_sb_list_lock; +extern void inode_add_lru(struct inode *inode); /* * fs-writeback.c diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index 78b7f84..7f5120b 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1961,7 +1961,9 @@ retry: spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); spin_unlock(&journal->j_state_lock); + unlock_buffer(bh); log_wait_commit(journal, tid); + lock_buffer(bh); goto retry; } /* diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index 60ef3fb..1506673 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -138,33 +138,39 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page *pg; struct inode *inode = mapping->host; struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode); + struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); + struct jffs2_raw_inode ri; + uint32_t alloc_len = 0; pgoff_t index = pos >> PAGE_CACHE_SHIFT; uint32_t pageofs = index << PAGE_CACHE_SHIFT; int ret = 0; + jffs2_dbg(1, "%s()\n", __func__); + + if (pageofs > inode->i_size) { + ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, + ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); + if (ret) + return ret; + } + + mutex_lock(&f->sem); pg = grab_cache_page_write_begin(mapping, index, flags); - if (!pg) + if (!pg) { + if (alloc_len) + jffs2_complete_reservation(c); + mutex_unlock(&f->sem); return -ENOMEM; + } *pagep = pg; - jffs2_dbg(1, "%s()\n", __func__); - - if (pageofs > inode->i_size) { + if (alloc_len) { /* Make new hole frag from old EOF to new page */ - struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); - struct jffs2_raw_inode ri; struct jffs2_full_dnode *fn; - uint32_t alloc_len; jffs2_dbg(1, "Writing new hole frag 0x%x-0x%x between current EOF and new page\n", (unsigned int)inode->i_size, pageofs); - ret = jffs2_reserve_space(c, sizeof(ri), &alloc_len, - ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE); - if (ret) - goto out_page; - - mutex_lock(&f->sem); memset(&ri, 0, sizeof(ri)); ri.magic = cpu_to_je16(JFFS2_MAGIC_BITMASK); @@ -191,7 +197,6 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, if (IS_ERR(fn)) { ret = PTR_ERR(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } ret = jffs2_add_full_dnode_to_inode(c, f, fn); @@ -206,12 +211,10 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, jffs2_mark_node_obsolete(c, fn->raw); jffs2_free_full_dnode(fn); jffs2_complete_reservation(c); - mutex_unlock(&f->sem); goto out_page; } jffs2_complete_reservation(c); inode->i_size = pageofs; - mutex_unlock(&f->sem); } /* @@ -220,18 +223,18 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, * case of a short-copy. */ if (!PageUptodate(pg)) { - mutex_lock(&f->sem); ret = jffs2_do_readpage_nolock(inode, pg); - mutex_unlock(&f->sem); if (ret) goto out_page; } + mutex_unlock(&f->sem); jffs2_dbg(1, "end write_begin(). pg->flags %lx\n", pg->flags); return ret; out_page: unlock_page(pg); page_cache_release(pg); + mutex_unlock(&f->sem); return ret; } diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c index e4fb3ba..3d7e09b 100644 --- a/fs/lockd/mon.c +++ b/fs/lockd/mon.c @@ -85,29 +85,38 @@ static struct rpc_clnt *nsm_create(struct net *net) return rpc_create(&args); } +static struct rpc_clnt *nsm_client_set(struct lockd_net *ln, + struct rpc_clnt *clnt) +{ + spin_lock(&ln->nsm_clnt_lock); + if (ln->nsm_users == 0) { + if (clnt == NULL) + goto out; + ln->nsm_clnt = clnt; + } + clnt = ln->nsm_clnt; + ln->nsm_users++; +out: + spin_unlock(&ln->nsm_clnt_lock); + return clnt; +} + static struct rpc_clnt *nsm_client_get(struct net *net) { - static DEFINE_MUTEX(nsm_create_mutex); - struct rpc_clnt *clnt; + struct rpc_clnt *clnt, *new; struct lockd_net *ln = net_generic(net, lockd_net_id); - spin_lock(&ln->nsm_clnt_lock); - if (ln->nsm_users) { - ln->nsm_users++; - clnt = ln->nsm_clnt; - spin_unlock(&ln->nsm_clnt_lock); + clnt = nsm_client_set(ln, NULL); + if (clnt != NULL) goto out; - } - spin_unlock(&ln->nsm_clnt_lock); - mutex_lock(&nsm_create_mutex); - clnt = nsm_create(net); - if (!IS_ERR(clnt)) { - ln->nsm_clnt = clnt; - smp_wmb(); - ln->nsm_users = 1; - } - mutex_unlock(&nsm_create_mutex); + clnt = new = nsm_create(net); + if (IS_ERR(clnt)) + goto out; + + clnt = nsm_client_set(ln, new); + if (clnt != new) + rpc_shutdown_client(new); out: return clnt; } @@ -115,18 +124,16 @@ out: static void nsm_client_put(struct net *net) { struct lockd_net *ln = net_generic(net, lockd_net_id); - struct rpc_clnt *clnt = ln->nsm_clnt; - int shutdown = 0; + struct rpc_clnt *clnt = NULL; spin_lock(&ln->nsm_clnt_lock); - if (ln->nsm_users) { - if (--ln->nsm_users) - ln->nsm_clnt = NULL; - shutdown = !ln->nsm_users; + ln->nsm_users--; + if (ln->nsm_users == 0) { + clnt = ln->nsm_clnt; + ln->nsm_clnt = NULL; } spin_unlock(&ln->nsm_clnt_lock); - - if (shutdown) + if (clnt != NULL) rpc_shutdown_client(clnt); } @@ -705,8 +705,8 @@ static inline void put_link(struct nameidata *nd, struct path *link, void *cooki path_put(link); } -int sysctl_protected_symlinks __read_mostly = 1; -int sysctl_protected_hardlinks __read_mostly = 1; +int sysctl_protected_symlinks __read_mostly = 0; +int sysctl_protected_hardlinks __read_mostly = 0; /** * may_follow_link - Check symlink following for unsafe situations @@ -2131,6 +2131,11 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) if (!len) return ERR_PTR(-EACCES); + if (unlikely(name[0] == '.')) { + if (len < 2 || (len == 2 && name[1] == '.')) + return ERR_PTR(-EACCES); + } + while (len--) { c = *(const unsigned char *)name++; if (c == '/' || c == '\0') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index ce8cb92..b9e66b7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -450,7 +450,8 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) nfs_refresh_inode(dentry->d_inode, entry->fattr); goto out; } else { - d_drop(dentry); + if (d_invalidate(dentry) != 0) + goto out; dput(dentry); } } @@ -1100,6 +1101,8 @@ out_set_verifier: out_zap_parent: nfs_zap_caches(dir); out_bad: + nfs_free_fattr(fattr); + nfs_free_fhandle(fhandle); nfs_mark_for_revalidate(dir); if (inode && S_ISDIR(inode->i_mode)) { /* Purge readdir caches. */ @@ -1112,8 +1115,6 @@ out_zap_parent: shrink_dcache_parent(dentry); } d_drop(dentry); - nfs_free_fattr(fattr); - nfs_free_fhandle(fhandle); dput(parent); dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n", __func__, dentry->d_parent->d_name.name, diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index 31c26c4..ca4b11e 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -217,7 +217,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) { char buf1[NFS_DNS_HOSTNAME_MAXLEN+1]; struct nfs_dns_ent key, *item; - unsigned long ttl; + unsigned int ttl; ssize_t len; int ret = -EINVAL; @@ -240,7 +240,8 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) key.namelen = len; memset(&key.h, 0, sizeof(key.h)); - ttl = get_expiry(&buf); + if (get_uint(&buf, &ttl) < 0) + goto out; if (ttl == 0) goto out; key.h.expiry_time = ttl + seconds_since_boot(); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 5c7325c..6fa01ae 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -685,7 +685,10 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) if (ctx->cred != NULL) put_rpccred(ctx->cred); dput(ctx->dentry); - nfs_sb_deactive(sb); + if (is_sync) + nfs_sb_deactive(sb); + else + nfs_sb_deactive_async(sb); kfree(ctx->mdsthreshold); kfree(ctx); } diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 59b133c..05521ca 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -351,10 +351,12 @@ extern int __init register_nfs_fs(void); extern void __exit unregister_nfs_fs(void); extern void nfs_sb_active(struct super_block *sb); extern void nfs_sb_deactive(struct super_block *sb); +extern void nfs_sb_deactive_async(struct super_block *sb); /* namespace.c */ +#define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, - char *buffer, ssize_t buflen); + char *buffer, ssize_t buflen, unsigned flags); extern struct vfsmount *nfs_d_automount(struct path *path); struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); @@ -498,7 +500,7 @@ static inline char *nfs_devname(struct dentry *dentry, char *buffer, ssize_t buflen) { char *dummy; - return nfs_path(&dummy, dentry, buffer, buflen); + return nfs_path(&dummy, dentry, buffer, buflen, NFS_PATH_CANONICAL); } /* diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 8e65c7f..015f71f 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -181,7 +181,7 @@ int nfs_mount(struct nfs_mount_request *info) else msg.rpc_proc = &mnt_clnt->cl_procinfo[MOUNTPROC_MNT]; - status = rpc_call_sync(mnt_clnt, &msg, 0); + status = rpc_call_sync(mnt_clnt, &msg, RPC_TASK_SOFT|RPC_TASK_TIMEOUT); rpc_shutdown_client(mnt_clnt); if (status < 0) diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 6559253..dd057bc 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -33,6 +33,7 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; * @dentry - pointer to dentry * @buffer - result buffer * @buflen - length of buffer + * @flags - options (see below) * * Helper function for constructing the server pathname * by arbitrary hashed dentry. @@ -40,8 +41,14 @@ int nfs_mountpoint_expiry_timeout = 500 * HZ; * This is mainly for use in figuring out the path on the * server side when automounting on top of an existing partition * and in generating /proc/mounts and friends. + * + * Supported flags: + * NFS_PATH_CANONICAL: ensure there is exactly one slash after + * the original device (export) name + * (if unset, the original name is returned verbatim) */ -char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen) +char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen, + unsigned flags) { char *end; int namelen; @@ -74,7 +81,7 @@ rename_retry: rcu_read_unlock(); goto rename_retry; } - if (*end != '/') { + if ((flags & NFS_PATH_CANONICAL) && *end != '/') { if (--buflen < 0) { spin_unlock(&dentry->d_lock); rcu_read_unlock(); @@ -91,9 +98,11 @@ rename_retry: return end; } namelen = strlen(base); - /* Strip off excess slashes in base string */ - while (namelen > 0 && base[namelen - 1] == '/') - namelen--; + if (flags & NFS_PATH_CANONICAL) { + /* Strip off excess slashes in base string */ + while (namelen > 0 && base[namelen - 1] == '/') + namelen--; + } buflen -= namelen; if (buflen < 0) { spin_unlock(&dentry->d_lock); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 79fbb61..1e09eb7 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -81,7 +81,8 @@ static char *nfs_path_component(const char *nfspath, const char *end) static char *nfs4_path(struct dentry *dentry, char *buffer, ssize_t buflen) { char *limit; - char *path = nfs_path(&limit, dentry, buffer, buflen); + char *path = nfs_path(&limit, dentry, buffer, buflen, + NFS_PATH_CANONICAL); if (!IS_ERR(path)) { char *path_component = nfs_path_component(path, limit); if (path_component) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 68b21d8..5eec442 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -339,8 +339,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc dprintk("%s ERROR: %d Reset session\n", __func__, errorcode); nfs4_schedule_session_recovery(clp->cl_session, errorcode); - exception->retry = 1; - break; + goto wait_on_recovery; #endif /* defined(CONFIG_NFS_V4_1) */ case -NFS4ERR_FILE_OPEN: if (exception->timeout > HZ) { @@ -1572,9 +1571,11 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) data->timestamp = jiffies; if (nfs4_setup_sequence(data->o_arg.server, &data->o_arg.seq_args, - &data->o_res.seq_res, task)) - return; - rpc_call_start(task); + &data->o_res.seq_res, + task) != 0) + nfs_release_seqid(data->o_arg.seqid); + else + rpc_call_start(task); return; unlock_no_action: rcu_read_unlock(); @@ -1748,7 +1749,7 @@ static int nfs4_opendata_access(struct rpc_cred *cred, /* even though OPEN succeeded, access is denied. Close the file */ nfs4_close_state(state, fmode); - return -NFS4ERR_ACCESS; + return -EACCES; } /* @@ -2196,7 +2197,7 @@ static void nfs4_free_closedata(void *data) nfs4_put_open_state(calldata->state); nfs_free_seqid(calldata->arg.seqid); nfs4_put_state_owner(sp); - nfs_sb_deactive(sb); + nfs_sb_deactive_async(sb); kfree(calldata); } @@ -2296,9 +2297,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) if (nfs4_setup_sequence(NFS_SERVER(inode), &calldata->arg.seq_args, &calldata->res.seq_res, - task)) - goto out; - rpc_call_start(task); + task) != 0) + nfs_release_seqid(calldata->arg.seqid); + else + rpc_call_start(task); out: dprintk("%s: done!\n", __func__); } @@ -4529,6 +4531,7 @@ static void nfs4_locku_done(struct rpc_task *task, void *data) if (nfs4_async_handle_error(task, calldata->server, NULL) == -EAGAIN) rpc_restart_call_prepare(task); } + nfs_release_seqid(calldata->arg.seqid); } static void nfs4_locku_prepare(struct rpc_task *task, void *data) @@ -4545,9 +4548,11 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data) calldata->timestamp = jiffies; if (nfs4_setup_sequence(calldata->server, &calldata->arg.seq_args, - &calldata->res.seq_res, task)) - return; - rpc_call_start(task); + &calldata->res.seq_res, + task) != 0) + nfs_release_seqid(calldata->arg.seqid); + else + rpc_call_start(task); } static const struct rpc_call_ops nfs4_locku_ops = { @@ -4692,7 +4697,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) /* Do we need to do an open_to_lock_owner? */ if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) { if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) - return; + goto out_release_lock_seqid; data->arg.open_stateid = &state->stateid; data->arg.new_lock_owner = 1; data->res.open_seqid = data->arg.open_seqid; @@ -4701,10 +4706,15 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata) data->timestamp = jiffies; if (nfs4_setup_sequence(data->server, &data->arg.seq_args, - &data->res.seq_res, task)) + &data->res.seq_res, + task) == 0) { + rpc_call_start(task); return; - rpc_call_start(task); - dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status); + } + nfs_release_seqid(data->arg.open_seqid); +out_release_lock_seqid: + nfs_release_seqid(data->arg.lock_seqid); + dprintk("%s: done!, ret = %d\n", __func__, task->tk_status); } static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata) @@ -5667,7 +5677,7 @@ static void nfs4_add_and_init_slots(struct nfs4_slot_table *tbl, tbl->slots = new; tbl->max_slots = max_slots; } - tbl->highest_used_slotid = -1; /* no slot is currently used */ + tbl->highest_used_slotid = NFS4_NO_SLOT; for (i = 0; i < tbl->max_slots; i++) tbl->slots[i].seq_nr = ivalue; spin_unlock(&tbl->slot_tbl_lock); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index fe624c9..2878f97 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -925,8 +925,8 @@ pnfs_find_alloc_layout(struct inode *ino, if (likely(nfsi->layout == NULL)) { /* Won the race? */ nfsi->layout = new; return new; - } - pnfs_free_layout_hdr(new); + } else if (new != NULL) + pnfs_free_layout_hdr(new); out_existing: pnfs_get_layout_hdr(nfsi->layout); return nfsi->layout; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index e831bce..652d3f7 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -54,6 +54,7 @@ #include <linux/parser.h> #include <linux/nsproxy.h> #include <linux/rcupdate.h> +#include <linux/kthread.h> #include <asm/uaccess.h> @@ -415,6 +416,54 @@ void nfs_sb_deactive(struct super_block *sb) } EXPORT_SYMBOL_GPL(nfs_sb_deactive); +static int nfs_deactivate_super_async_work(void *ptr) +{ + struct super_block *sb = ptr; + + deactivate_super(sb); + module_put_and_exit(0); + return 0; +} + +/* + * same effect as deactivate_super, but will do final unmount in kthread + * context + */ +static void nfs_deactivate_super_async(struct super_block *sb) +{ + struct task_struct *task; + char buf[INET6_ADDRSTRLEN + 1]; + struct nfs_server *server = NFS_SB(sb); + struct nfs_client *clp = server->nfs_client; + + if (!atomic_add_unless(&sb->s_active, -1, 1)) { + rcu_read_lock(); + snprintf(buf, sizeof(buf), + rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_ADDR)); + rcu_read_unlock(); + + __module_get(THIS_MODULE); + task = kthread_run(nfs_deactivate_super_async_work, sb, + "%s-deactivate-super", buf); + if (IS_ERR(task)) { + pr_err("%s: kthread_run: %ld\n", + __func__, PTR_ERR(task)); + /* make synchronous call and hope for the best */ + deactivate_super(sb); + module_put(THIS_MODULE); + } + } +} + +void nfs_sb_deactive_async(struct super_block *sb) +{ + struct nfs_server *server = NFS_SB(sb); + + if (atomic_dec_and_test(&server->active)) + nfs_deactivate_super_async(sb); +} +EXPORT_SYMBOL_GPL(nfs_sb_deactive_async); + /* * Deliver file system statistics to userspace */ @@ -771,7 +820,7 @@ int nfs_show_devname(struct seq_file *m, struct dentry *root) int err = 0; if (!page) return -ENOMEM; - devname = nfs_path(&dummy, root, page, PAGE_SIZE); + devname = nfs_path(&dummy, root, page, PAGE_SIZE, 0); if (IS_ERR(devname)) err = PTR_ERR(devname); else diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 13cea63..3f79c77 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -95,7 +95,7 @@ static void nfs_async_unlink_release(void *calldata) nfs_dec_sillycount(data->dir); nfs_free_unlinkdata(data); - nfs_sb_deactive(sb); + nfs_sb_deactive_async(sb); } static void nfs_unlink_prepare(struct rpc_task *task, void *calldata) diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index f35794b..a506360 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -21,6 +21,7 @@ static bool should_merge(struct fsnotify_event *old, struct fsnotify_event *new) if ((old->path.mnt == new->path.mnt) && (old->path.dentry == new->path.dentry)) return true; + break; case (FSNOTIFY_EVENT_NONE): return true; default: diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 721d692..6fcaeb8 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -258,7 +258,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (ret) goto out_close_fd; - fd_install(fd, f); + if (fd != FAN_NOFD) + fd_install(fd, f); return fanotify_event_metadata.event_len; out_close_fd: diff --git a/fs/proc/base.c b/fs/proc/base.c index 144a967..9e28356 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -873,6 +873,113 @@ static const struct file_operations proc_environ_operations = { .release = mem_release, }; +static ssize_t oom_adj_read(struct file *file, char __user *buf, size_t count, + loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + printk_once(KERN_WARNING "%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, +}; + static ssize_t oom_score_adj_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -1770,8 +1877,9 @@ static struct dentry *proc_map_files_lookup(struct inode *dir, if (!vma) goto out_no_vma; - result = proc_map_files_instantiate(dir, dentry, task, - (void *)(unsigned long)vma->vm_file->f_mode); + if (vma->vm_file) + result = proc_map_files_instantiate(dir, dentry, task, + (void *)(unsigned long)vma->vm_file->f_mode); out_no_vma: up_read(&mm->mmap_sem); @@ -2598,6 +2706,7 @@ static const struct pid_entry tgid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), @@ -2964,6 +3073,7 @@ static const struct pid_entry tid_base_stuff[] = { REG("cgroup", S_IRUGO, proc_cgroup_operations), #endif INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), #ifdef CONFIG_AUDITSYSCALL REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index a40da07..947fbe0 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -161,6 +161,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) while (s < e) { unsigned long flags; + u64 id; if (c > psinfo->bufsize) c = psinfo->bufsize; @@ -172,7 +173,7 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) spin_lock_irqsave(&psinfo->buf_lock, flags); } memcpy(psinfo->buf, s, c); - psinfo->write(PSTORE_TYPE_CONSOLE, 0, NULL, 0, c, psinfo); + psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f27f01a..d83736f 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1782,8 +1782,9 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, BUG_ON(!th->t_trans_id); - dquot_initialize(inode); + reiserfs_write_unlock(inode->i_sb); err = dquot_alloc_inode(inode); + reiserfs_write_lock(inode->i_sb); if (err) goto out_end_trans; if (!dir->i_nlink) { @@ -1979,8 +1980,10 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, out_end_trans: journal_end(th, th->t_super, th->t_blocks_allocated); + reiserfs_write_unlock(inode->i_sb); /* Drop can be outside and it needs more credits so it's better to have it outside */ dquot_drop(inode); + reiserfs_write_lock(inode->i_sb); inode->i_flags |= S_NOQUOTA; make_bad_inode(inode); @@ -3103,10 +3106,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) /* must be turned off for recursive notify_change calls */ ia_valid = attr->ia_valid &= ~(ATTR_KILL_SUID|ATTR_KILL_SGID); - depth = reiserfs_write_lock_once(inode->i_sb); if (is_quota_modification(inode, attr)) dquot_initialize(inode); - + depth = reiserfs_write_lock_once(inode->i_sb); if (attr->ia_valid & ATTR_SIZE) { /* version 2 items will be caught by the s_maxbytes check ** done for us in vmtruncate @@ -3170,7 +3172,9 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr) error = journal_begin(&th, inode->i_sb, jbegin_count); if (error) goto out; + reiserfs_write_unlock_once(inode->i_sb, depth); error = dquot_transfer(inode, attr); + depth = reiserfs_write_lock_once(inode->i_sb); if (error) { journal_end(&th, inode->i_sb, jbegin_count); goto out; diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c index f8afa4b..2f40a4c 100644 --- a/fs/reiserfs/stree.c +++ b/fs/reiserfs/stree.c @@ -1968,7 +1968,9 @@ int reiserfs_paste_into_item(struct reiserfs_transaction_handle *th, struct tree key2type(&(key->on_disk_key))); #endif + reiserfs_write_unlock(inode->i_sb); retval = dquot_alloc_space_nodirty(inode, pasted_size); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(search_path); return retval; @@ -2061,9 +2063,11 @@ int reiserfs_insert_item(struct reiserfs_transaction_handle *th, "reiserquota insert_item(): allocating %u id=%u type=%c", quota_bytes, inode->i_uid, head2type(ih)); #endif + reiserfs_write_unlock(inode->i_sb); /* We can't dirty inode here. It would be immediately written but * appropriate stat item isn't inserted yet... */ retval = dquot_alloc_space_nodirty(inode, quota_bytes); + reiserfs_write_lock(inode->i_sb); if (retval) { pathrelse(path); return retval; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 1078ae1..418bdc3 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -298,7 +298,9 @@ static int finish_unfinished(struct super_block *s) retval = remove_save_link_only(s, &save_link_key, 0); continue; } + reiserfs_write_unlock(s); dquot_initialize(inode); + reiserfs_write_lock(s); if (truncate && S_ISDIR(inode->i_mode)) { /* We got a truncate request for a dir which is impossible. @@ -1335,7 +1337,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) kfree(qf_names[i]); #endif err = -EINVAL; - goto out_err; + goto out_unlock; } #ifdef CONFIG_QUOTA handle_quota_files(s, qf_names, &qfmt); @@ -1379,7 +1381,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (blocks) { err = reiserfs_resize(s, blocks); if (err != 0) - goto out_err; + goto out_unlock; } if (*mount_flags & MS_RDONLY) { @@ -1389,9 +1391,15 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) /* it is read-only already */ goto out_ok; + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_suspend() without it. + */ + reiserfs_write_unlock(s); err = dquot_suspend(s, -1); if (err < 0) goto out_err; + reiserfs_write_lock(s); /* try to remount file system with read-only permissions */ if (sb_umount_state(rs) == REISERFS_VALID_FS @@ -1401,7 +1409,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mounting a rw partition read-only. */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1416,7 +1424,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) if (reiserfs_is_journal_aborted(journal)) { err = journal->j_errno; - goto out_err; + goto out_unlock; } handle_data_mode(s, mount_options); @@ -1425,7 +1433,7 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) s->s_flags &= ~MS_RDONLY; /* now it is safe to call journal_begin */ err = journal_begin(&th, s, 10); if (err) - goto out_err; + goto out_unlock; /* Mount a partition which is read-only, read-write */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); @@ -1442,10 +1450,16 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg) SB_JOURNAL(s)->j_must_wait = 1; err = journal_end(&th, s, 10); if (err) - goto out_err; + goto out_unlock; if (!(*mount_flags & MS_RDONLY)) { + /* + * Drop write lock. Quota will retake it when needed and lock + * ordering requires calling dquot_resume() without it. + */ + reiserfs_write_unlock(s); dquot_resume(s, -1); + reiserfs_write_lock(s); finish_unfinished(s); reiserfs_xattr_init(s, *mount_flags); } @@ -1455,9 +1469,10 @@ out_ok: reiserfs_write_unlock(s); return 0; +out_unlock: + reiserfs_write_unlock(s); out_err: kfree(new_opts); - reiserfs_write_unlock(s); return err; } @@ -2095,13 +2110,15 @@ static int reiserfs_write_dquot(struct dquot *dquot) REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_commit(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_TRANS_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2117,13 +2134,15 @@ static int reiserfs_acquire_dquot(struct dquot *dquot) REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (ret) goto out; + reiserfs_write_unlock(dquot->dq_sb); ret = dquot_acquire(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_INIT_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(dquot->dq_sb); return ret; } @@ -2137,19 +2156,21 @@ static int reiserfs_release_dquot(struct dquot *dquot) ret = journal_begin(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); + reiserfs_write_unlock(dquot->dq_sb); if (ret) { /* Release dquot anyway to avoid endless cycle in dqput() */ dquot_release(dquot); goto out; } ret = dquot_release(dquot); + reiserfs_write_lock(dquot->dq_sb); err = journal_end(&th, dquot->dq_sb, REISERFS_QUOTA_DEL_BLOCKS(dquot->dq_sb)); if (!ret && err) ret = err; - out: reiserfs_write_unlock(dquot->dq_sb); +out: return ret; } @@ -2174,11 +2195,13 @@ static int reiserfs_write_info(struct super_block *sb, int type) ret = journal_begin(&th, sb, 2); if (ret) goto out; + reiserfs_write_unlock(sb); ret = dquot_commit_info(sb, type); + reiserfs_write_lock(sb); err = journal_end(&th, sb, 2); if (!ret && err) ret = err; - out: +out: reiserfs_write_unlock(sb); return ret; } @@ -2203,8 +2226,11 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, struct reiserfs_transaction_handle th; int opt = type == USRQUOTA ? REISERFS_USRQUOTA : REISERFS_GRPQUOTA; - if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) - return -EINVAL; + reiserfs_write_lock(sb); + if (!(REISERFS_SB(sb)->s_mount_opt & (1 << opt))) { + err = -EINVAL; + goto out; + } /* Quotafile not on the same filesystem? */ if (path->dentry->d_sb != sb) { @@ -2246,8 +2272,10 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id, if (err) goto out; } - err = dquot_quota_on(sb, type, format_id, path); + reiserfs_write_unlock(sb); + return dquot_quota_on(sb, type, format_id, path); out: + reiserfs_write_unlock(sb); return err; } @@ -2320,7 +2348,9 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, tocopy = sb->s_blocksize - offset < towrite ? sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; + reiserfs_write_lock(sb); err = reiserfs_get_block(inode, blk, &tmp_bh, GET_BLOCK_CREATE); + reiserfs_write_unlock(sb); if (err) goto out; if (offset || tocopy != sb->s_blocksize) @@ -2336,10 +2366,12 @@ static ssize_t reiserfs_quota_write(struct super_block *sb, int type, flush_dcache_page(bh->b_page); set_buffer_uptodate(bh); unlock_buffer(bh); + reiserfs_write_lock(sb); reiserfs_prepare_for_journal(sb, bh, 1); journal_mark_dirty(current->journal_info, sb, bh); if (!journal_quota) reiserfs_add_ordered_list(inode, bh); + reiserfs_write_unlock(sb); brelse(bh); offset = 0; towrite -= tocopy; diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index 6b0bb00..2fbdff6 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -485,20 +485,18 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) /** * sysfs_pathname - return full path to sysfs dirent * @sd: sysfs_dirent whose path we want - * @path: caller allocated buffer + * @path: caller allocated buffer of size PATH_MAX * * Gives the name "/" to the sysfs_root entry; any path returned * is relative to wherever sysfs is mounted. - * - * XXX: does no error checking on @path size */ static char *sysfs_pathname(struct sysfs_dirent *sd, char *path) { if (sd->s_parent) { sysfs_pathname(sd->s_parent, path); - strcat(path, "/"); + strlcat(path, "/", PATH_MAX); } - strcat(path, sd->s_name); + strlcat(path, sd->s_name, PATH_MAX); return path; } @@ -531,9 +529,11 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd) char *path = kzalloc(PATH_MAX, GFP_KERNEL); WARN(1, KERN_WARNING "sysfs: cannot create duplicate filename '%s'\n", - (path == NULL) ? sd->s_name : - strcat(strcat(sysfs_pathname(acxt->parent_sd, path), "/"), - sd->s_name)); + (path == NULL) ? sd->s_name + : (sysfs_pathname(acxt->parent_sd, path), + strlcat(path, "/", PATH_MAX), + strlcat(path, sd->s_name, PATH_MAX), + path)); kfree(path); } diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c index 28ec13a..2dcf3d4 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -681,8 +681,16 @@ int ubifs_find_free_leb_for_idx(struct ubifs_info *c) if (!lprops) { lprops = ubifs_fast_find_freeable(c); if (!lprops) { - ubifs_assert(c->freeable_cnt == 0); - if (c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + /* + * The first condition means the following: go scan the + * LPT if there are uncategorized lprops, which means + * there may be freeable LEBs there (UBIFS does not + * store the information about freeable LEBs in the + * master node). + */ + if (c->in_a_category_cnt != c->main_lebs || + c->lst.empty_lebs - c->lst.taken_empty_lebs > 0) { + ubifs_assert(c->freeable_cnt == 0); lprops = scan_for_leb_for_idx(c); if (IS_ERR(lprops)) { err = PTR_ERR(lprops); diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index e5a2a35..46190a7 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -300,8 +300,11 @@ void ubifs_add_to_cat(struct ubifs_info *c, struct ubifs_lprops *lprops, default: ubifs_assert(0); } + lprops->flags &= ~LPROPS_CAT_MASK; lprops->flags |= cat; + c->in_a_category_cnt += 1; + ubifs_assert(c->in_a_category_cnt <= c->main_lebs); } /** @@ -334,6 +337,9 @@ static void ubifs_remove_from_cat(struct ubifs_info *c, default: ubifs_assert(0); } + + c->in_a_category_cnt -= 1; + ubifs_assert(c->in_a_category_cnt >= 0); } /** diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 5486346..d133c27 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1183,6 +1183,8 @@ struct ubifs_debug_info; * @freeable_list: list of freeable non-index LEBs (free + dirty == @leb_size) * @frdi_idx_list: list of freeable index LEBs (free + dirty == @leb_size) * @freeable_cnt: number of freeable LEBs in @freeable_list + * @in_a_category_cnt: count of lprops which are in a certain category, which + * basically meants that they were loaded from the flash * * @ltab_lnum: LEB number of LPT's own lprops table * @ltab_offs: offset of LPT's own lprops table @@ -1412,6 +1414,7 @@ struct ubifs_info { struct list_head freeable_list; struct list_head frdi_idx_list; int freeable_cnt; + int in_a_category_cnt; int ltab_lnum; int ltab_offs; diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c index 4f33c32..335206a 100644 --- a/fs/xfs/xfs_alloc.c +++ b/fs/xfs/xfs_alloc.c @@ -1866,6 +1866,7 @@ xfs_alloc_fix_freelist( /* * Initialize the args structure. */ + memset(&targs, 0, sizeof(targs)); targs.tp = tp; targs.mp = mp; targs.agbp = agbp; @@ -2207,7 +2208,7 @@ xfs_alloc_read_agf( * group or loop over the allocation groups to find the result. */ int /* error */ -__xfs_alloc_vextent( +xfs_alloc_vextent( xfs_alloc_arg_t *args) /* allocation argument structure */ { xfs_agblock_t agsize; /* allocation group size */ @@ -2417,46 +2418,6 @@ error0: return error; } -static void -xfs_alloc_vextent_worker( - struct work_struct *work) -{ - struct xfs_alloc_arg *args = container_of(work, - struct xfs_alloc_arg, work); - unsigned long pflags; - - /* we are in a transaction context here */ - current_set_flags_nested(&pflags, PF_FSTRANS); - - args->result = __xfs_alloc_vextent(args); - complete(args->done); - - current_restore_flags_nested(&pflags, PF_FSTRANS); -} - -/* - * Data allocation requests often come in with little stack to work on. Push - * them off to a worker thread so there is lots of stack to use. Metadata - * requests, OTOH, are generally from low stack usage paths, so avoid the - * context switch overhead here. - */ -int -xfs_alloc_vextent( - struct xfs_alloc_arg *args) -{ - DECLARE_COMPLETION_ONSTACK(done); - - if (!args->userdata) - return __xfs_alloc_vextent(args); - - - args->done = &done; - INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker); - queue_work(xfs_alloc_wq, &args->work); - wait_for_completion(&done); - return args->result; -} - /* * Free an extent. * Just break up the extent address and hand off to xfs_free_ag_extent diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h index 93be4a6..feacb06 100644 --- a/fs/xfs/xfs_alloc.h +++ b/fs/xfs/xfs_alloc.h @@ -120,9 +120,6 @@ typedef struct xfs_alloc_arg { char isfl; /* set if is freelist blocks - !acctg */ char userdata; /* set if this is user data */ xfs_fsblock_t firstblock; /* io first block allocated */ - struct completion *done; - struct work_struct work; - int result; } xfs_alloc_arg_t; /* diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c index f1647ca..f7876c6 100644 --- a/fs/xfs/xfs_alloc_btree.c +++ b/fs/xfs/xfs_alloc_btree.c @@ -121,6 +121,8 @@ xfs_allocbt_free_block( xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1, XFS_EXTENT_BUSY_SKIP_DISCARD); xfs_trans_agbtree_delta(cur->bc_tp, -1); + + xfs_trans_binval(cur->bc_tp, bp); return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index e562dd4..e57e2da 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -481,11 +481,17 @@ static inline int bio_add_buffer(struct bio *bio, struct buffer_head *bh) * * The fix is two passes across the ioend list - one to start writeback on the * buffer_heads, and then submit them for I/O on the second pass. + * + * If @fail is non-zero, it means that we have a situation where some part of + * the submission process has failed after we have marked paged for writeback + * and unlocked them. In this situation, we need to fail the ioend chain rather + * than submit it to IO. This typically only happens on a filesystem shutdown. */ STATIC void xfs_submit_ioend( struct writeback_control *wbc, - xfs_ioend_t *ioend) + xfs_ioend_t *ioend, + int fail) { xfs_ioend_t *head = ioend; xfs_ioend_t *next; @@ -506,6 +512,18 @@ xfs_submit_ioend( next = ioend->io_list; bio = NULL; + /* + * If we are failing the IO now, just mark the ioend with an + * error and finish it. This will run IO completion immediately + * as there is only one reference to the ioend at this point in + * time. + */ + if (fail) { + ioend->io_error = -fail; + xfs_finish_ioend(ioend); + continue; + } + for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) { if (!bio) { @@ -1060,7 +1078,18 @@ xfs_vm_writepage( xfs_start_page_writeback(page, 1, count); - if (ioend && imap_valid) { + /* if there is no IO to be submitted for this page, we are done */ + if (!ioend) + return 0; + + ASSERT(iohead); + + /* + * Any errors from this point onwards need tobe reported through the IO + * completion path as we have marked the initial page as under writeback + * and unlocked it. + */ + if (imap_valid) { xfs_off_t end_index; end_index = imap.br_startoff + imap.br_blockcount; @@ -1079,20 +1108,15 @@ xfs_vm_writepage( wbc, end_index); } - if (iohead) { - /* - * Reserve log space if we might write beyond the on-disk - * inode size. - */ - if (ioend->io_type != XFS_IO_UNWRITTEN && - xfs_ioend_is_append(ioend)) { - err = xfs_setfilesize_trans_alloc(ioend); - if (err) - goto error; - } - xfs_submit_ioend(wbc, iohead); - } + /* + * Reserve log space if we might write beyond the on-disk inode size. + */ + err = 0; + if (ioend->io_type != XFS_IO_UNWRITTEN && xfs_ioend_is_append(ioend)) + err = xfs_setfilesize_trans_alloc(ioend); + + xfs_submit_ioend(wbc, iohead, err); return 0; diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c index d330111..70eec18 100644 --- a/fs/xfs/xfs_attr_leaf.c +++ b/fs/xfs/xfs_attr_leaf.c @@ -1291,6 +1291,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, leaf2 = blk2->bp->b_addr; ASSERT(leaf1->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); ASSERT(leaf2->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC)); + ASSERT(leaf2->hdr.count == 0); args = state->args; trace_xfs_attr_leaf_rebalance(args); @@ -1361,6 +1362,7 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, * I assert that since all callers pass in an empty * second buffer, this code should never execute. */ + ASSERT(0); /* * Figure the total bytes to be added to the destination leaf. @@ -1422,10 +1424,24 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1, args->index2 = 0; args->blkno2 = blk2->blkno; } else { + /* + * On a double leaf split, the original attr location + * is already stored in blkno2/index2, so don't + * overwrite it overwise we corrupt the tree. + */ blk2->index = blk1->index - be16_to_cpu(leaf1->hdr.count); - args->index = args->index2 = blk2->index; - args->blkno = args->blkno2 = blk2->blkno; + args->index = blk2->index; + args->blkno = blk2->blkno; + if (!state->extravalid) { + /* + * set the new attr location to match the old + * one and let the higher level split code + * decide where in the leaf to place it. + */ + args->index2 = blk2->index; + args->blkno2 = blk2->blkno; + } } } else { ASSERT(state->inleaf == 1); diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c index 848ffa77..83d0cf3 100644 --- a/fs/xfs/xfs_bmap.c +++ b/fs/xfs/xfs_bmap.c @@ -2437,6 +2437,7 @@ xfs_bmap_btalloc( * Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned = 0; + memset(&args, 0, sizeof(args)); args.tp = ap->tp; args.mp = mp; args.fsbno = ap->blkno; @@ -3082,6 +3083,7 @@ xfs_bmap_extents_to_btree( * Convert to a btree with two levels, one record in root. */ XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE); + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = mp; args.firstblock = *firstblock; @@ -3237,6 +3239,7 @@ xfs_bmap_local_to_extents( xfs_buf_t *bp; /* buffer for extent block */ xfs_bmbt_rec_host_t *ep;/* extent record pointer */ + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = ip->i_mount; args.firstblock = *firstblock; @@ -4616,12 +4619,11 @@ xfs_bmapi_delay( STATIC int -xfs_bmapi_allocate( - struct xfs_bmalloca *bma, - int flags) +__xfs_bmapi_allocate( + struct xfs_bmalloca *bma) { struct xfs_mount *mp = bma->ip->i_mount; - int whichfork = (flags & XFS_BMAPI_ATTRFORK) ? + int whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ? XFS_ATTR_FORK : XFS_DATA_FORK; struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork); int tmp_logflags = 0; @@ -4654,24 +4656,27 @@ xfs_bmapi_allocate( * Indicate if this is the first user data in the file, or just any * user data. */ - if (!(flags & XFS_BMAPI_METADATA)) { + if (!(bma->flags & XFS_BMAPI_METADATA)) { bma->userdata = (bma->offset == 0) ? XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA; } - bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1; + bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1; /* * Only want to do the alignment at the eof if it is userdata and * allocation length is larger than a stripe unit. */ if (mp->m_dalign && bma->length >= mp->m_dalign && - !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) { + !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) { error = xfs_bmap_isaeof(bma, whichfork); if (error) return error; } + if (bma->flags & XFS_BMAPI_STACK_SWITCH) + bma->stack_switch = 1; + error = xfs_bmap_alloc(bma); if (error) return error; @@ -4706,7 +4711,7 @@ xfs_bmapi_allocate( * A wasdelay extent has been initialized, so shouldn't be flagged * as unwritten. */ - if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) && + if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) && xfs_sb_version_hasextflgbit(&mp->m_sb)) bma->got.br_state = XFS_EXT_UNWRITTEN; @@ -4734,6 +4739,45 @@ xfs_bmapi_allocate( return 0; } +static void +xfs_bmapi_allocate_worker( + struct work_struct *work) +{ + struct xfs_bmalloca *args = container_of(work, + struct xfs_bmalloca, work); + unsigned long pflags; + + /* we are in a transaction context here */ + current_set_flags_nested(&pflags, PF_FSTRANS); + + args->result = __xfs_bmapi_allocate(args); + complete(args->done); + + current_restore_flags_nested(&pflags, PF_FSTRANS); +} + +/* + * Some allocation requests often come in with little stack to work on. Push + * them off to a worker thread so there is lots of stack to use. Otherwise just + * call directly to avoid the context switch overhead here. + */ +int +xfs_bmapi_allocate( + struct xfs_bmalloca *args) +{ + DECLARE_COMPLETION_ONSTACK(done); + + if (!args->stack_switch) + return __xfs_bmapi_allocate(args); + + + args->done = &done; + INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker); + queue_work(xfs_alloc_wq, &args->work); + wait_for_completion(&done); + return args->result; +} + STATIC int xfs_bmapi_convert_unwritten( struct xfs_bmalloca *bma, @@ -4919,6 +4963,7 @@ xfs_bmapi_write( bma.conv = !!(flags & XFS_BMAPI_CONVERT); bma.wasdel = wasdelay; bma.offset = bno; + bma.flags = flags; /* * There's a 32/64 bit type mismatch between the @@ -4934,7 +4979,7 @@ xfs_bmapi_write( ASSERT(len > 0); ASSERT(bma.length > 0); - error = xfs_bmapi_allocate(&bma, flags); + error = xfs_bmapi_allocate(&bma); if (error) goto error0; if (bma.blkno == NULLFSBLOCK) diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h index 803b56d..5f469c3 100644 --- a/fs/xfs/xfs_bmap.h +++ b/fs/xfs/xfs_bmap.h @@ -77,6 +77,7 @@ typedef struct xfs_bmap_free * from written to unwritten, otherwise convert from unwritten to written. */ #define XFS_BMAPI_CONVERT 0x040 +#define XFS_BMAPI_STACK_SWITCH 0x080 #define XFS_BMAPI_FLAGS \ { XFS_BMAPI_ENTIRE, "ENTIRE" }, \ @@ -85,7 +86,8 @@ typedef struct xfs_bmap_free { XFS_BMAPI_PREALLOC, "PREALLOC" }, \ { XFS_BMAPI_IGSTATE, "IGSTATE" }, \ { XFS_BMAPI_CONTIG, "CONTIG" }, \ - { XFS_BMAPI_CONVERT, "CONVERT" } + { XFS_BMAPI_CONVERT, "CONVERT" }, \ + { XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" } static inline int xfs_bmapi_aflag(int w) @@ -133,6 +135,11 @@ typedef struct xfs_bmalloca { char userdata;/* set if is user data */ char aeof; /* allocated space at eof */ char conv; /* overwriting unwritten extents */ + char stack_switch; + int flags; + struct completion *done; + struct work_struct work; + int result; } xfs_bmalloca_t; /* diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 933b793..4b0b8dd 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1197,9 +1197,14 @@ xfs_buf_bio_end_io( { xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private; - xfs_buf_ioerror(bp, -error); + /* + * don't overwrite existing errors - otherwise we can lose errors on + * buffers that require multiple bios to complete. + */ + if (!bp->b_error) + xfs_buf_ioerror(bp, -error); - if (!error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) + if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ)) invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp)); _xfs_buf_ioend(bp, 1); @@ -1279,6 +1284,11 @@ next_chunk: if (size) goto next_chunk; } else { + /* + * This is guaranteed not to be the last io reference count + * because the caller (xfs_buf_iorequest) holds a count itself. + */ + atomic_dec(&bp->b_io_remaining); xfs_buf_ioerror(bp, EIO); bio_put(bio); } diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index a8d0ed9..becf4a9 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -526,7 +526,25 @@ xfs_buf_item_unpin( } xfs_buf_relse(bp); } else if (freed && remove) { + /* + * There are currently two references to the buffer - the active + * LRU reference and the buf log item. What we are about to do + * here - simulate a failed IO completion - requires 3 + * references. + * + * The LRU reference is removed by the xfs_buf_stale() call. The + * buf item reference is removed by the xfs_buf_iodone() + * callback that is run by xfs_buf_do_callbacks() during ioend + * processing (via the bp->b_iodone callback), and then finally + * the ioend processing will drop the IO reference if the buffer + * is marked XBF_ASYNC. + * + * Hence we need to take an additional reference here so that IO + * completion processing doesn't free the buffer prematurely. + */ xfs_buf_lock(bp); + xfs_buf_hold(bp); + bp->b_flags |= XBF_ASYNC; xfs_buf_ioerror(bp, EIO); XFS_BUF_UNDONE(bp); xfs_buf_stale(bp); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index c25b094..4beaede 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -399,9 +399,26 @@ xfs_growfs_data_private( /* update secondary superblocks. */ for (agno = 1; agno < nagcount; agno++) { - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, + error = 0; + /* + * new secondary superblocks need to be zeroed, not read from + * disk as the contents of the new area we are growing into is + * completely unknown. + */ + if (agno < oagcount) { + error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)), XFS_FSS_TO_BB(mp, 1), 0, &bp); + } else { + bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp, + XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)), + XFS_FSS_TO_BB(mp, 1), 0); + if (bp) + xfs_buf_zero(bp, 0, BBTOB(bp->b_length)); + else + error = ENOMEM; + } + if (error) { xfs_warn(mp, "error %d reading secondary superblock for ag %d", @@ -423,7 +440,7 @@ xfs_growfs_data_private( break; /* no point in continuing */ } } - return 0; + return error; error0: xfs_trans_cancel(tp, XFS_TRANS_ABORT); diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 445bf1a..c5c4ef4 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -250,6 +250,7 @@ xfs_ialloc_ag_alloc( /* boundary */ struct xfs_perag *pag; + memset(&args, 0, sizeof(args)); args.tp = tp; args.mp = tp->t_mountp; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2778258..1938b41 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1509,7 +1509,8 @@ xfs_ifree_cluster( * to mark all the active inodes on the buffer stale. */ bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno, - mp->m_bsize * blks_per_cluster, 0); + mp->m_bsize * blks_per_cluster, + XBF_UNMAPPED); if (!bp) return ENOMEM; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 8305f2a..c1df3c6 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -70,7 +70,7 @@ xfs_find_handle( int hsize; xfs_handle_t handle; struct inode *inode; - struct fd f; + struct fd f = {0}; struct path path; int error; struct xfs_inode *ip; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 973dff6..7f53766 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -584,7 +584,9 @@ xfs_iomap_write_allocate( * pointer that the caller gave to us. */ error = xfs_bmapi_write(tp, ip, map_start_fsb, - count_fsb, 0, &first_block, 1, + count_fsb, + XFS_BMAPI_STACK_SWITCH, + &first_block, 1, imap, &nimaps, &free_list); if (error) goto trans_cancel; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 7f4f937..4dad756 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -2387,14 +2387,27 @@ xlog_state_do_callback( /* - * update the last_sync_lsn before we drop the + * Completion of a iclog IO does not imply that + * a transaction has completed, as transactions + * can be large enough to span many iclogs. We + * cannot change the tail of the log half way + * through a transaction as this may be the only + * transaction in the log and moving th etail to + * point to the middle of it will prevent + * recovery from finding the start of the + * transaction. Hence we should only update the + * last_sync_lsn if this iclog contains + * transaction completion callbacks on it. + * + * We have to do this before we drop the * icloglock to ensure we are the only one that * can update it. */ ASSERT(XFS_LSN_CMP(atomic64_read(&log->l_last_sync_lsn), be64_to_cpu(iclog->ic_header.h_lsn)) <= 0); - atomic64_set(&log->l_last_sync_lsn, - be64_to_cpu(iclog->ic_header.h_lsn)); + if (iclog->ic_callback) + atomic64_set(&log->l_last_sync_lsn, + be64_to_cpu(iclog->ic_header.h_lsn)); } else ioerrors++; diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 5da3ace..d308749 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -3541,7 +3541,7 @@ xlog_do_recovery_pass( * - order is important. */ error = xlog_bread_offset(log, 0, - bblks - split_bblks, hbp, + bblks - split_bblks, dbp, offset + BBTOB(split_bblks)); if (error) goto bread_err2; |