diff options
Diffstat (limited to 'fs')
93 files changed, 715 insertions, 306 deletions
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index 5a0db6dec8d1..aaee1e6584e6 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -40,6 +40,9 @@ */ #define P9_LOCK_TIMEOUT (30*HZ) +/* flags for v9fs_stat2inode() & v9fs_stat2inode_dotl() */ +#define V9FS_STAT2INODE_KEEP_ISIZE 1 + extern struct file_system_type v9fs_fs_type; extern const struct address_space_operations v9fs_addr_operations; extern const struct file_operations v9fs_file_operations; @@ -61,8 +64,10 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t); void v9fs_evict_inode(struct inode *inode); ino_t v9fs_qid2ino(struct p9_qid *qid); -void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *); -void v9fs_stat2inode_dotl(struct p9_stat_dotl *, struct inode *); +void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, + struct super_block *sb, unsigned int flags); +void v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags); int v9fs_dir_release(struct inode *inode, struct file *filp); int v9fs_file_open(struct inode *inode, struct file *file); void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat); @@ -83,4 +88,18 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode) } int v9fs_open_to_dotl_flags(int flags); + +static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size) +{ + /* + * 32-bit need the lock, concurrent updates could break the + * sequences and make i_size_read() loop forever. + * 64-bit updates are atomic and can skip the locking. + */ + if (sizeof(i_size) > sizeof(long)) + spin_lock(&inode->i_lock); + i_size_write(inode, i_size); + if (sizeof(i_size) > sizeof(long)) + spin_unlock(&inode->i_lock); +} #endif diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 398a3eddb2df..2f035b15180e 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -442,7 +442,11 @@ v9fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) i_size = i_size_read(inode); if (iocb->ki_pos > i_size) { inode_add_bytes(inode, iocb->ki_pos - i_size); - i_size_write(inode, iocb->ki_pos); + /* + * Need to serialize against i_size_write() in + * v9fs_stat2inode() + */ + v9fs_i_size_write(inode, iocb->ki_pos); } return retval; } diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index f8ab4a66acaf..ddd1eb6aedee 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -538,7 +538,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode(st, inode, sb); + v9fs_stat2inode(st, inode, sb, 0); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; @@ -1078,7 +1078,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb); + v9fs_stat2inode(st, d_inode(dentry), dentry->d_sb, 0); generic_fillattr(d_inode(dentry), stat); p9stat_free(st); @@ -1156,12 +1156,13 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) * @stat: Plan 9 metadata (mistat) structure * @inode: inode to populate * @sb: superblock of filesystem + * @flags: control flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, - struct super_block *sb) + struct super_block *sb, unsigned int flags) { umode_t mode; char ext[32]; @@ -1202,10 +1203,11 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode = p9mode2perm(v9ses, stat); mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->length); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ - inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9; + inode->i_blocks = (stat->length + 512 - 1) >> 9; v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } @@ -1402,9 +1404,9 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) { int umode; dev_t rdev; - loff_t i_size; struct p9_wstat *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_stat(fid); @@ -1417,16 +1419,13 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (umode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode(st, inode, inode->i_sb); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode(st, inode, inode->i_sb, flags); out: p9stat_free(st); kfree(st); diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index c3dd0d42bb3a..425bc1a2b8c1 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -143,7 +143,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, if (retval) goto error; - v9fs_stat2inode_dotl(st, inode); + v9fs_stat2inode_dotl(st, inode, 0); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) @@ -496,7 +496,7 @@ v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry, if (IS_ERR(st)) return PTR_ERR(st); - v9fs_stat2inode_dotl(st, d_inode(dentry)); + v9fs_stat2inode_dotl(st, d_inode(dentry), 0); generic_fillattr(d_inode(dentry), stat); /* Change block size to what the server returned */ stat->blksize = st->st_blksize; @@ -607,11 +607,13 @@ int v9fs_vfs_setattr_dotl(struct dentry *dentry, struct iattr *iattr) * v9fs_stat2inode_dotl - populate an inode structure with stat info * @stat: stat structure * @inode: inode to populate + * @flags: ctrl flags (e.g. V9FS_STAT2INODE_KEEP_ISIZE) * */ void -v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) +v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, + unsigned int flags) { umode_t mode; struct v9fs_inode *v9inode = V9FS_I(inode); @@ -631,7 +633,8 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) + v9fs_i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; } else { if (stat->st_result_mask & P9_STATS_ATIME) { @@ -661,8 +664,9 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode) } if (stat->st_result_mask & P9_STATS_RDEV) inode->i_rdev = new_decode_dev(stat->st_rdev); - if (stat->st_result_mask & P9_STATS_SIZE) - i_size_write(inode, stat->st_size); + if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && + stat->st_result_mask & P9_STATS_SIZE) + v9fs_i_size_write(inode, stat->st_size); if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; } @@ -928,9 +932,9 @@ v9fs_vfs_get_link_dotl(struct dentry *dentry, int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) { - loff_t i_size; struct p9_stat_dotl *st; struct v9fs_session_info *v9ses; + unsigned int flags; v9ses = v9fs_inode2v9ses(inode); st = p9_client_getattr_dotl(fid, P9_STATS_ALL); @@ -942,16 +946,13 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) if ((inode->i_mode & S_IFMT) != (st->st_mode & S_IFMT)) goto out; - spin_lock(&inode->i_lock); /* * We don't want to refresh inode->i_size, * because we may have cached data */ - i_size = inode->i_size; - v9fs_stat2inode_dotl(st, inode); - if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) - inode->i_size = i_size; - spin_unlock(&inode->i_lock); + flags = (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) ? + V9FS_STAT2INODE_KEEP_ISIZE : 0; + v9fs_stat2inode_dotl(st, inode, flags); out: kfree(st); return 0; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index de3ed8629196..06ff1a9089e8 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -165,7 +165,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, goto release_sb; } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode_dotl(st, d_inode(root)); + v9fs_stat2inode_dotl(st, d_inode(root), 0); kfree(st); } else { struct p9_wstat *st = NULL; @@ -176,7 +176,7 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags, } d_inode(root)->i_ino = v9fs_qid2ino(&st->qid); - v9fs_stat2inode(st, d_inode(root), sb); + v9fs_stat2inode(st, d_inode(root), sb, 0); p9stat_free(st); kfree(st); @@ -40,6 +40,7 @@ #include <linux/ramfs.h> #include <linux/percpu-refcount.h> #include <linux/mount.h> +#include <linux/nospec.h> #include <asm/kmap_types.h> #include <asm/uaccess.h> @@ -1071,6 +1072,7 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id) if (!table || id >= table->nr) goto out; + id = array_index_nospec(id, table->nr); ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { if (percpu_ref_tryget_live(&ctx->users)) diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index d8e6d421c27f..2e1f50e467f1 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -563,7 +563,6 @@ int autofs4_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -576,6 +575,8 @@ int autofs4_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index ce0c6ea96a87..d9a3264909d0 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -259,8 +259,10 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs4_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; diff --git a/fs/block_dev.c b/fs/block_dev.c index cb936c90ae82..8a894cd4875b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -114,6 +114,20 @@ void invalidate_bdev(struct block_device *bdev) } EXPORT_SYMBOL(invalidate_bdev); +static void set_init_blocksize(struct block_device *bdev) +{ + unsigned bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_block_size = bsize; + bdev->bd_inode->i_blkbits = blksize_bits(bsize); +} + int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ @@ -1209,18 +1223,9 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { - unsigned bsize = bdev_logical_block_size(bdev); - inode_lock(bdev->bd_inode); i_size_write(bdev->bd_inode, size); inode_unlock(bdev->bd_inode); - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); } EXPORT_SYMBOL(bd_set_size); @@ -1297,8 +1302,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + set_init_blocksize(bdev); + } /* * If the device is invalidated, rescan partition @@ -1333,6 +1340,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + set_init_blocksize(bdev); } } else { if (bdev->bd_contains == bdev) { diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index b450adf65236..fb973cc0af66 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -350,6 +350,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name, break; case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED: case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED: + ASSERT(0); ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED; goto leave; } @@ -394,6 +395,10 @@ int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name, if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_dev_replace_lock(dev_replace, 1); + dev_replace->replace_state = + BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED; + dev_replace->srcdev = NULL; + dev_replace->tgtdev = NULL; goto leave; } @@ -415,8 +420,6 @@ int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name, return ret; leave: - dev_replace->srcdev = NULL; - dev_replace->tgtdev = NULL; btrfs_dev_replace_unlock(dev_replace, 1); btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device); return ret; @@ -784,6 +787,8 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info) "cannot continue dev_replace, tgtdev is missing"); btrfs_info(fs_info, "you may cancel the operation after 'mount -o degraded'"); + dev_replace->replace_state = + BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED; btrfs_dev_replace_unlock(dev_replace, 1); return 0; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 77b32415d9f2..9d3352fe8dc9 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4193,6 +4193,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->ordered_root_lock); } spin_unlock(&fs_info->ordered_root_lock); + + /* + * We need this here because if we've been flipped read-only we won't + * get sync() from the umount, so we need to make sure any ordered + * extents that haven't had their dirty pages IO start writeout yet + * actually get run and error out properly. + */ + btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1); } static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 793d4d571d8d..4d901200be13 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3018,11 +3018,11 @@ static int __do_readpage(struct extent_io_tree *tree, */ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->orig_start) + *prev_em_start != em->start) force_bio_submit = true; if (prev_em_start) - *prev_em_start = em->orig_start; + *prev_em_start = em->start; free_extent_map(em); em = NULL; @@ -4463,29 +4463,25 @@ try_submit_last: } /* - * Sanity check for fiemap cache + * Emit last fiemap cache * - * All fiemap cache should be submitted by emit_fiemap_extent() - * Iteration should be terminated either by last fiemap extent or - * fieinfo->fi_extents_max. - * So no cached fiemap should exist. + * The last fiemap cache may still be cached in the following case: + * 0 4k 8k + * |<- Fiemap range ->| + * |<------------ First extent ----------->| + * + * In this case, the first extent range will be cached but not emitted. + * So we must emit it before ending extent_fiemap(). */ -static int check_fiemap_cache(struct btrfs_fs_info *fs_info, - struct fiemap_extent_info *fieinfo, - struct fiemap_cache *cache) +static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info, + struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) { int ret; if (!cache->cached) return 0; - /* Small and recoverbale problem, only to info developer */ -#ifdef CONFIG_BTRFS_DEBUG - WARN_ON(1); -#endif - btrfs_warn(fs_info, - "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x", - cache->offset, cache->phys, cache->len, cache->flags); ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); cache->cached = false; @@ -4701,7 +4697,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } out_free: if (!ret) - ret = check_fiemap_cache(root->fs_info, fieinfo, &cache); + ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 79dc3ee1de58..a45f26ac5da7 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3349,7 +3349,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m) kfree(m); } -static void tail_append_pending_moves(struct pending_dir_move *moves, +static void tail_append_pending_moves(struct send_ctx *sctx, + struct pending_dir_move *moves, struct list_head *stack) { if (list_empty(&moves->list)) { @@ -3360,6 +3361,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves, list_add_tail(&moves->list, stack); list_splice_tail(&list, stack); } + if (!RB_EMPTY_NODE(&moves->node)) { + rb_erase(&moves->node, &sctx->pending_dir_moves); + RB_CLEAR_NODE(&moves->node); + } } static int apply_children_dir_moves(struct send_ctx *sctx) @@ -3374,7 +3379,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) return 0; INIT_LIST_HEAD(&stack); - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); while (!list_empty(&stack)) { pm = list_first_entry(&stack, struct pending_dir_move, list); @@ -3385,7 +3390,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) goto out; pm = get_pending_dir_moves(sctx, parent_ino); if (pm) - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); } return 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5aa2749eaf42..c063ac57c30e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6439,10 +6439,10 @@ static int btrfs_check_chunk_valid(struct btrfs_root *root, } if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) || - (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) || + (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) || (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) || (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) || - (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) || + (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) || ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 && num_stripes != 1)) { btrfs_err(root->fs_info, diff --git a/fs/buffer.c b/fs/buffer.c index 00590090a17d..e2d4a45ae135 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -207,6 +207,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -234,15 +235,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 5e3bc9de7a16..799b59d96fe2 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -537,7 +537,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -610,7 +613,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -963,11 +969,8 @@ error: void cachefiles_uncache_page(struct fscache_object *_object, struct page *page) { struct cachefiles_object *object; - struct cachefiles_cache *cache; object = container_of(_object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); _enter("%p,{%lu}", object, page->index); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 3e1c136aadb7..f916cd7b1918 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3343,7 +3343,6 @@ retry: tcap->cap_id = t_cap_id; tcap->seq = t_seq - 1; tcap->issue_seq = t_seq - 1; - tcap->mseq = t_mseq; tcap->issued |= issued; tcap->implemented |= issued; if (cap == ci->i_auth_cap) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 9ff5219d849e..411e9df0d40e 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -609,7 +609,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + if (list_empty(&ci->i_snap_flush_item)) + list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 441d434a48c1..33e65b71c49a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -48,6 +48,7 @@ #include "cifs_unicode.h" #include "cifs_debug.h" #include "cifs_fs_sb.h" +#include "dns_resolve.h" #include "ntlmssp.h" #include "nterr.h" #include "rfc1002pdu.h" @@ -307,6 +308,53 @@ static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, const char *devname); /* + * Resolve hostname and set ip addr in tcp ses. Useful for hostnames that may + * get their ip addresses changed at some point. + * + * This should be called with server->srv_mutex held. + */ +#ifdef CONFIG_CIFS_DFS_UPCALL +static int reconn_set_ipaddr(struct TCP_Server_Info *server) +{ + int rc; + int len; + char *unc, *ipaddr = NULL; + + if (!server->hostname) + return -EINVAL; + + len = strlen(server->hostname) + 3; + + unc = kmalloc(len, GFP_KERNEL); + if (!unc) { + cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__); + return -ENOMEM; + } + snprintf(unc, len, "\\\\%s", server->hostname); + + rc = dns_resolve_server_name_to_ip(unc, &ipaddr); + kfree(unc); + + if (rc < 0) { + cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", + __func__, server->hostname, rc); + return rc; + } + + rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr, + strlen(ipaddr)); + kfree(ipaddr); + + return !rc ? -1 : 0; +} +#else +static inline int reconn_set_ipaddr(struct TCP_Server_Info *server) +{ + return 0; +} +#endif + +/* * cifs tcp session reconnection * * mark tcp session as reconnecting so temporarily locked @@ -403,6 +451,11 @@ cifs_reconnect(struct TCP_Server_Info *server) rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); + rc = reconn_set_ipaddr(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } mutex_unlock(&server->srv_mutex); msleep(3000); } else { diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 331ddd07e505..e98e24eaa6a8 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -163,7 +163,7 @@ cifs_bp_rename_retry: cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath); memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1); - full_path[dfsplen] = '\\'; + full_path[dfsplen] = dirsep; for (i = 0; i < pplen-1; i++) if (full_path[dfsplen+1+i] == '/') full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 49eeed25f200..1c5099fffaec 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1118,14 +1118,18 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile) /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) { + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) { free_xid(xid); return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -1456,12 +1460,16 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < (sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE))) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb_hdr) + sizeof(LOCKING_ANDX_RANGE) > + PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf - sizeof(struct smb_hdr), + PAGE_SIZE); max_num = (max_buf - sizeof(struct smb_hdr)) / sizeof(LOCKING_ANDX_RANGE); buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); @@ -2789,14 +2797,16 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) * these pages but not on the region from pos to ppos+len-1. */ written = cifs_user_writev(iocb, from); - if (written > 0 && CIFS_CACHE_READ(cinode)) { + if (CIFS_CACHE_READ(cinode)) { /* - * Windows 7 server can delay breaking level2 oplock if a write - * request comes - break it on the client to prevent reading - * an old data. + * We have read level caching and we have just sent a write + * request to the server thus making data in the cache stale. + * Zap the cache and set oplock/lease level to NONE to avoid + * reading stale data from the cache. All subsequent read + * operations will read new data from the server. */ cifs_zap_mapping(inode); - cifs_dbg(FYI, "Set no oplock for inode=%p after a write operation\n", + cifs_dbg(FYI, "Set Oplock/Lease to NONE for inode=%p after write\n", inode); cinode->oplock = 0; } diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index ef24b4527459..68183872bf8b 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -655,7 +655,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* scan and find it */ int i; char *cur_ent; - char *end_of_smb = cfile->srch_inf.ntwrk_buf_start + + char *end_of_smb; + + if (cfile->srch_inf.ntwrk_buf_start == NULL) { + cifs_dbg(VFS, "ntwrk_buf_start is NULL during readdir\n"); + return -EIO; + } + + end_of_smb = cfile->srch_inf.ntwrk_buf_start + server->ops->calc_smb_size( cfile->srch_inf.ntwrk_buf_start); diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index b2aff0c6f22c..dee5250701de 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -123,12 +123,14 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, /* * Accessing maxBuf is racy with cifs_reconnect - need to store value - * and check it for zero before using. + * and check it before using. */ max_buf = tcon->ses->server->maxBuf; - if (!max_buf) + if (max_buf < sizeof(struct smb2_lock_element)) return -EINVAL; + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) @@ -265,6 +267,8 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile) return -EINVAL; } + BUILD_BUG_ON(sizeof(struct smb2_lock_element) > PAGE_SIZE); + max_buf = min_t(unsigned int, max_buf, PAGE_SIZE); max_num = max_buf / sizeof(struct smb2_lock_element); buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL); if (!buf) { diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index 8257a5a97cc0..98c25b969ab8 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -377,8 +377,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_NONEXISTENT_EA_ENTRY, -EIO, "STATUS_NONEXISTENT_EA_ENTRY"}, {STATUS_NO_EAS_ON_FILE, -ENODATA, "STATUS_NO_EAS_ON_FILE"}, {STATUS_EA_CORRUPT_ERROR, -EIO, "STATUS_EA_CORRUPT_ERROR"}, - {STATUS_FILE_LOCK_CONFLICT, -EIO, "STATUS_FILE_LOCK_CONFLICT"}, - {STATUS_LOCK_NOT_GRANTED, -EIO, "STATUS_LOCK_NOT_GRANTED"}, + {STATUS_FILE_LOCK_CONFLICT, -EACCES, "STATUS_FILE_LOCK_CONFLICT"}, + {STATUS_LOCK_NOT_GRANTED, -EACCES, "STATUS_LOCK_NOT_GRANTED"}, {STATUS_DELETE_PENDING, -ENOENT, "STATUS_DELETE_PENDING"}, {STATUS_CTL_FILE_NOT_SUPPORTED, -ENOSYS, "STATUS_CTL_FILE_NOT_SUPPORTED"}, diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index e96a74da756f..244d27bb8fba 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -474,7 +474,6 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, __u8 lease_state; struct list_head *tmp; struct cifsFileInfo *cfile; - struct TCP_Server_Info *server = tcon->ses->server; struct cifs_pending_open *open; struct cifsInodeInfo *cinode; int ack_req = le32_to_cpu(rsp->Flags & @@ -494,13 +493,25 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp, cifs_dbg(FYI, "lease key match, lease break 0x%x\n", le32_to_cpu(rsp->NewLeaseState)); - server->ops->set_oplock_level(cinode, lease_state, 0, NULL); - if (ack_req) cfile->oplock_break_cancelled = false; else cfile->oplock_break_cancelled = true; + set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags); + + /* + * Set or clear flags depending on the lease state being READ. + * HANDLE caching flag should be added when the client starts + * to defer closing remote file handles with HANDLE leases. + */ + if (lease_state & SMB2_LEASE_READ_CACHING_HE) + set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); + else + clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, + &cinode->flags); + queue_work(cifsoplockd_wq, &cfile->oplock_break); kfree(lw); return true; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 08c1c86c2ad9..97d8e2a3df9b 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -148,14 +148,14 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, scredits = server->credits; /* can deadlock with reopen */ - if (scredits == 1) { + if (scredits <= 8) { *num = SMB2_MAX_BUFFER_SIZE; *credits = 0; break; } - /* leave one credit for a possible reopen */ - scredits--; + /* leave some credits for reopen and other ops */ + scredits -= 8; *num = min_t(unsigned int, size, scredits * SMB2_MAX_BUFFER_SIZE); @@ -1377,6 +1377,15 @@ smb2_downgrade_oplock(struct TCP_Server_Info *server, } static void +smb21_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, bool set_level2) +{ + server->ops->set_oplock_level(cinode, + set_level2 ? SMB2_LEASE_READ_CACHING_HE : + 0, 0, NULL); +} + +static void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { @@ -1681,7 +1690,7 @@ struct smb_version_operations smb21_operations = { .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -1765,7 +1774,7 @@ struct smb_version_operations smb30_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -1855,7 +1864,7 @@ struct smb_version_operations smb311_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb2_downgrade_oplock, + .downgrade_oplock = smb21_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 50251a8af0ce..52b6e4a40748 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2686,8 +2686,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) { srch_inf->endOfSearch = true; rc = 0; - } - cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); + } else + cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 1e1449ad00e8..1af7afae3ad1 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ -#define MAX_SMB2_HDR_SIZE 0x00b0 +/* 52 transform hdr + 64 hdr + 88 create rsp */ +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index cc26d4138d70..de133eeebc8a 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -301,7 +301,7 @@ uncork: if (rc < 0 && rc != -EINTR) cifs_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else + else if (rc > 0) rc = 0; return rc; diff --git a/fs/dcache.c b/fs/dcache.c index f903b86b06e5..05bad55352bb 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1164,15 +1164,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, */ void shrink_dcache_sb(struct super_block *sb) { - long freed; - do { LIST_HEAD(dispose); - freed = list_lru_walk(&sb->s_dentry_lru, + list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); - - this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); cond_resched(); } while (list_lru_count(&sb->s_dentry_lru) > 0); @@ -1526,7 +1522,7 @@ static void check_and_drop(void *_data) { struct detach_data *data = _data; - if (!data->mountpoint && !data->select.found) + if (!data->mountpoint && list_empty(&data->select.dispose)) __d_drop(data->select.start); } @@ -1568,17 +1564,15 @@ void d_invalidate(struct dentry *dentry) d_walk(dentry, &data, detach_and_collect, check_and_drop); - if (data.select.found) + if (!list_empty(&data.select.dispose)) shrink_dentry_list(&data.select.dispose); + else if (!data.mountpoint) + return; if (data.mountpoint) { detach_mounts(data.mountpoint); dput(data.mountpoint); } - - if (!data.mountpoint && !data.select.found) - break; - cond_resched(); } } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 3d7de9f4f545..77e9cd7a0137 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -732,6 +732,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; + if (IS_ERR(old_dir)) + return old_dir; + if (IS_ERR(new_dir)) + return new_dir; + if (IS_ERR_OR_NULL(old_dentry)) + return old_dentry; + trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 108df2e3602c..81be3ba17cbf 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -396,6 +396,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent) s->s_blocksize_bits = 10; s->s_magic = DEVPTS_SUPER_MAGIC; s->s_op = &devpts_sops; + s->s_d_op = &simple_dentry_operations; s->s_time_gran = 1; error = -ENOMEM; diff --git a/fs/direct-io.c b/fs/direct-io.c index 07cc38ec66ca..fc90f0c33cbe 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -616,6 +616,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; + loff_t i_size; /* * If there was a memory error and we've overwritten all the @@ -645,8 +646,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, */ create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { - if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> - i_blkbits)) + i_size = i_size_read(dio->inode); + if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits) create = 0; } diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c index dcea1e37a1b7..f18619bc2e09 100644 --- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -290,6 +290,8 @@ void dlm_callback_suspend(struct dlm_ls *ls) flush_workqueue(ls->ls_callback_wq); } +#define MAX_CB_QUEUE 25 + void dlm_callback_resume(struct dlm_ls *ls) { struct dlm_lkb *lkb, *safe; @@ -300,15 +302,23 @@ void dlm_callback_resume(struct dlm_ls *ls) if (!ls->ls_callback_wq) return; +more: mutex_lock(&ls->ls_cb_mutex); list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) { list_del_init(&lkb->lkb_cb_list); queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); count++; + if (count == MAX_CB_QUEUE) + break; } mutex_unlock(&ls->ls_cb_mutex); if (count) log_rinfo(ls, "dlm_callback_resume %d", count); + if (count == MAX_CB_QUEUE) { + count = 0; + cond_resched(); + goto more; + } } diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c index 35502d4046f5..3a7f401e943c 100644 --- a/fs/dlm/lock.c +++ b/fs/dlm/lock.c @@ -1210,6 +1210,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret) if (rv < 0) { log_error(ls, "create_lkb idr error %d", rv); + dlm_free_lkb(lkb); return rv; } @@ -4177,6 +4178,7 @@ static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms) (unsigned long long)lkb->lkb_recover_seq, ms->m_header.h_nodeid, ms->m_lkid); error = -ENOENT; + dlm_put_lkb(lkb); goto fail; } @@ -4230,6 +4232,7 @@ static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms) lkb->lkb_id, lkb->lkb_remid, ms->m_header.h_nodeid, ms->m_lkid); error = -ENOENT; + dlm_put_lkb(lkb); goto fail; } @@ -5792,20 +5795,20 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, goto out; } } - - /* After ua is attached to lkb it will be freed by dlm_free_lkb(). - When DLM_IFL_USER is set, the dlm knows that this is a userspace - lock and that lkb_astparam is the dlm_user_args structure. */ - error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs, fake_astfn, ua, fake_bastfn, &args); - lkb->lkb_flags |= DLM_IFL_USER; - if (error) { + kfree(ua->lksb.sb_lvbptr); + ua->lksb.sb_lvbptr = NULL; + kfree(ua); __put_lkb(ls, lkb); goto out; } + /* After ua is attached to lkb it will be freed by dlm_free_lkb(). + When DLM_IFL_USER is set, the dlm knows that this is a userspace + lock and that lkb_astparam is the dlm_user_args structure. */ + lkb->lkb_flags |= DLM_IFL_USER; error = request_lock(ls, lkb, name, namelen, &args); switch (error) { diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index f3e72787e7f9..30e4e01db35a 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -673,11 +673,11 @@ static int new_lockspace(const char *name, const char *cluster, kfree(ls->ls_recover_buf); out_lkbidr: idr_destroy(&ls->ls_lkbidr); + out_rsbtbl: for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) { if (ls->ls_remove_names[i]) kfree(ls->ls_remove_names[i]); } - out_rsbtbl: vfree(ls->ls_rsbtbl); out_lsfree: if (do_unreg) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index d72d52b90433..280460fef066 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -20,8 +20,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -29,6 +34,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 3cbc30413add..a9c0bf8782f5 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1040,7 +1040,7 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ - if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) { + if (ep->ovflist != EP_UNACTIVE_PTR) { if (epi->next == EP_UNACTIVE_PTR) { epi->next = ep->ovflist; ep->ovflist = epi; diff --git a/fs/exec.c b/fs/exec.c index fcd8642ef2d2..81477116035d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -938,7 +938,7 @@ int kernel_read_file(struct file *file, void **buf, loff_t *size, i_size - pos); if (bytes < 0) { ret = bytes; - goto out; + goto out_free; } if (bytes == 0) diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index a4b531be9168..7a7bba7c2328 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -76,7 +76,7 @@ static bool dentry_connected(struct dentry *dentry) struct dentry *parent = dget_parent(dentry); dput(dentry); - if (IS_ROOT(dentry)) { + if (dentry == parent) { dput(parent); return false; } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 6cb042b53b5b..6fcb29b393d3 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -724,7 +724,8 @@ static loff_t ext2_max_size(int bits) { loff_t res = EXT2_NDIR_BLOCKS; int meta_blocks; - loff_t upper_limit; + unsigned int upper_limit; + unsigned int ppb = 1 << (bits-2); /* This is calculated to be the largest file size for a * dense, file such that the total number of @@ -738,24 +739,34 @@ static loff_t ext2_max_size(int bits) /* total blocks in file system block size */ upper_limit >>= (bits - 9); + /* Compute how many blocks we can address by block tree */ + res += 1LL << (bits-2); + res += 1LL << (2*(bits-2)); + res += 1LL << (3*(bits-2)); + /* Does block tree limit file size? */ + if (res < upper_limit) + goto check_lfs; + res = upper_limit; + /* How many metadata blocks are needed for addressing upper_limit? */ + upper_limit -= EXT2_NDIR_BLOCKS; /* indirect blocks */ meta_blocks = 1; + upper_limit -= ppb; /* double indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)); - /* tripple indirect blocks */ - meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2))); - - upper_limit -= meta_blocks; - upper_limit <<= bits; - - res += 1LL << (bits-2); - res += 1LL << (2*(bits-2)); - res += 1LL << (3*(bits-2)); + if (upper_limit < ppb * ppb) { + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb); + res -= meta_blocks; + goto check_lfs; + } + meta_blocks += 1 + ppb; + upper_limit -= ppb * ppb; + /* tripple indirect blocks for the rest */ + meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) + + DIV_ROUND_UP(upper_limit, ppb*ppb); + res -= meta_blocks; +check_lfs: res <<= bits; - if (res > upper_limit) - res = upper_limit; - if (res > MAX_LFS_FILESIZE) res = MAX_LFS_FILESIZE; diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index f97611171023..4b7cc1af03a0 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -391,7 +391,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle, { struct ext4_inode_info *ei = EXT4_I(inode); - if (ext4_handle_valid(handle)) { + if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) { ei->i_sync_tid = handle->h_transaction->t_tid; if (datasync) ei->i_datasync_tid = handle->h_transaction->t_tid; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 08fca4add1e2..fe76d0957a1f 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -79,7 +79,7 @@ ext4_unaligned_aio(struct inode *inode, struct iov_iter *from, loff_t pos) struct super_block *sb = inode->i_sb; int blockmask = sb->s_blocksize - 1; - if (pos >= i_size_read(inode)) + if (pos >= ALIGN(i_size_read(inode), sb->s_blocksize)) return 0; if ((pos | iov_iter_alignment(from)) & blockmask) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index 58229c1b4a3d..14007e621d2a 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -1385,10 +1385,14 @@ end_range: partial->p + 1, partial2->p, (chain+n-1) - partial); - BUFFER_TRACE(partial->bh, "call brelse"); - brelse(partial->bh); - BUFFER_TRACE(partial2->bh, "call brelse"); - brelse(partial2->bh); + while (partial > chain) { + BUFFER_TRACE(partial->bh, "call brelse"); + brelse(partial->bh); + } + while (partial2 > chain2) { + BUFFER_TRACE(partial2->bh, "call brelse"); + brelse(partial2->bh); + } return 0; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d06cfe372609..9a13f86fed62 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -702,8 +702,11 @@ int ext4_try_to_write_inline_data(struct address_space *mapping, if (!PageUptodate(page)) { ret = ext4_read_inline_page(inode, page); - if (ret < 0) + if (ret < 0) { + unlock_page(page); + put_page(page); goto out_up_read; + } } ret = 1; @@ -1856,12 +1859,12 @@ int ext4_inline_data_fiemap(struct inode *inode, physical += (char *)ext4_raw_inode(&iloc) - iloc.bh->b_data; physical += offsetof(struct ext4_inode, i_block); - if (physical) - error = fiemap_fill_next_extent(fieinfo, start, physical, - inline_len, flags); brelse(iloc.bh); out: up_read(&EXT4_I(inode)->xattr_sem); + if (physical) + error = fiemap_fill_next_extent(fieinfo, start, physical, + inline_len, flags); return (error < 0 ? error : 0); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index f62eca8cbde0..4815be26b15f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2698,7 +2698,8 @@ static int ext4_writepages(struct address_space *mapping, * We may need to convert up to one extent per block in * the page and we may dirty the inode. */ - rsv_blocks = 1 + (PAGE_SIZE >> inode->i_blkbits); + rsv_blocks = 1 + ext4_chunk_trans_blocks(inode, + PAGE_SIZE >> inode->i_blkbits); } /* diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9be605c63ae1..67b359629a66 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1600,7 +1600,7 @@ int ext4_group_add(struct super_block *sb, struct ext4_new_group_data *input) } if (reserved_gdb || gdb_off == 0) { - if (ext4_has_feature_resize_inode(sb) || + if (!ext4_has_feature_resize_inode(sb) || !le16_to_cpu(es->s_reserved_gdt_blocks)) { ext4_warning(sb, "No reserved GDT blocks, can't resize"); @@ -1928,7 +1928,8 @@ retry: le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); n_blocks_count = (ext4_fsblk_t)n_group * - EXT4_BLOCKS_PER_GROUP(sb); + EXT4_BLOCKS_PER_GROUP(sb) + + le32_to_cpu(es->s_first_data_block); n_group--; /* set to last group number */ } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 75177eb498ed..a6c7ace9cfd1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1076,6 +1076,16 @@ static struct dentry *ext4_fh_to_parent(struct super_block *sb, struct fid *fid, ext4_nfs_get_inode); } +static int ext4_nfs_commit_metadata(struct inode *inode) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL + }; + + trace_ext4_nfs_commit_metadata(inode); + return ext4_write_inode(inode, &wbc); +} + /* * Try to release metadata pages (indirect blocks, directories) which are * mapped via the block device. Since these pages could have journal heads @@ -1258,6 +1268,7 @@ static const struct export_operations ext4_export_ops = { .fh_to_dentry = ext4_fh_to_dentry, .fh_to_parent = ext4_fh_to_parent, .get_parent = ext4_get_parent, + .commit_metadata = ext4_nfs_commit_metadata, }; enum { @@ -4668,7 +4679,7 @@ static int ext4_commit_super(struct super_block *sb, int sync) ext4_superblock_csum_set(sb); if (sync) lock_buffer(sbh); - if (buffer_write_io_error(sbh)) { + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the * superblock failed. This could happen because the @@ -5425,9 +5436,9 @@ static int ext4_quota_enable(struct super_block *sb, int type, int format_id, qf_inode->i_flags |= S_NOQUOTA; lockdep_set_quota_inode(qf_inode, I_DATA_SEM_QUOTA); err = dquot_enable(qf_inode, type, format_id, flags); - iput(qf_inode); if (err) lockdep_set_quota_inode(qf_inode, I_DATA_SEM_NORMAL); + iput(qf_inode); return err; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 22f765069655..ec9beaa69abb 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1499,7 +1499,7 @@ retry: base = IFIRST(header); end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size; min_offs = end - base; - total_ino = sizeof(struct ext4_xattr_ibody_header); + total_ino = sizeof(struct ext4_xattr_ibody_header) + sizeof(u32); error = xattr_check_inode(inode, header, end); if (error) diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 55aa29c0c78d..a9894089d9dc 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -348,12 +348,14 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, return PTR_ERR(p); clone = f2fs_acl_clone(p, GFP_NOFS); - if (!clone) - goto no_mem; + if (!clone) { + ret = -ENOMEM; + goto release_acl; + } ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) - goto no_mem_clone; + goto release_clone; if (ret == 0) posix_acl_release(clone); @@ -367,11 +369,11 @@ static int f2fs_acl_create(struct inode *dir, umode_t *mode, return 0; -no_mem_clone: +release_clone: posix_acl_release(clone); -no_mem: +release_acl: posix_acl_release(p); - return -ENOMEM; + return ret; } int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 46646e47a2b0..1eeff387b524 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1885,10 +1885,19 @@ static inline bool is_dot_dotdot(const struct qstr *str) static inline bool f2fs_may_extent_tree(struct inode *inode) { - if (!test_opt(F2FS_I_SB(inode), EXTENT_CACHE) || + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (!test_opt(sbi, EXTENT_CACHE) || is_inode_flag_set(inode, FI_NO_EXTENT)) return false; + /* + * for recovered files during mount do not create extents + * if shrinker is not registered. + */ + if (list_empty(&sbi->s_list)) + return false; + return S_ISREG(inode->i_mode); } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index b768f495603e..f46ac1651bd5 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -198,6 +198,9 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, trace_f2fs_sync_file_enter(inode); + if (S_ISDIR(inode->i_mode)) + goto go_write; + /* if fdatasync is triggered, let's do in-place-update */ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(inode, FI_NEED_IPU); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index f4fe54047fb7..d87c48e4a9ba 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -656,6 +656,7 @@ static void truncate_node(struct dnode_of_data *dn) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; + pgoff_t index; get_node_info(sbi, dn->nid, &ni); if (dn->inode->i_blocks == 0) { @@ -678,10 +679,11 @@ invalidate: clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); + index = dn->node_page->index; f2fs_put_page(dn->node_page, 1); invalidate_mapping_pages(NODE_MAPPING(sbi), - dn->node_page->index, dn->node_page->index); + index, index); dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr); diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index ab4cbb4be423..e59eeaf02eaa 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -196,32 +196,6 @@ static void recover_inode(struct inode *inode, struct page *page) ino_of_node(page), name); } -static bool is_same_inode(struct inode *inode, struct page *ipage) -{ - struct f2fs_inode *ri = F2FS_INODE(ipage); - struct timespec disk; - - if (!IS_INODE(ipage)) - return true; - - disk.tv_sec = le64_to_cpu(ri->i_ctime); - disk.tv_nsec = le32_to_cpu(ri->i_ctime_nsec); - if (timespec_compare(&inode->i_ctime, &disk) > 0) - return false; - - disk.tv_sec = le64_to_cpu(ri->i_atime); - disk.tv_nsec = le32_to_cpu(ri->i_atime_nsec); - if (timespec_compare(&inode->i_atime, &disk) > 0) - return false; - - disk.tv_sec = le64_to_cpu(ri->i_mtime); - disk.tv_nsec = le32_to_cpu(ri->i_mtime_nsec); - if (timespec_compare(&inode->i_mtime, &disk) > 0) - return false; - - return true; -} - static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) { struct curseg_info *curseg; @@ -248,10 +222,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head) goto next; entry = get_fsync_inode(head, ino_of_node(page)); - if (entry) { - if (!is_same_inode(entry->inode, page)) - goto next; - } else { + if (!entry) { if (IS_INODE(page) && is_dent_dnode(page)) { err = recover_inode_page(sbi, page); if (err) diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 46c915425923..a40bfa7fafec 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -136,6 +136,6 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi) f2fs_shrink_extent_tree(sbi, __count_extent_cache(sbi)); spin_lock(&f2fs_list_lock); - list_del(&sbi->s_list); + list_del_init(&sbi->s_list); spin_unlock(&f2fs_list_lock); } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index c8f408d8a582..83a96334dc07 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1427,10 +1427,10 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, return 1; } - if (segment_count > (le32_to_cpu(raw_super->block_count) >> 9)) { + if (segment_count > (le64_to_cpu(raw_super->block_count) >> 9)) { f2fs_msg(sb, KERN_INFO, - "Wrong segment_count / block_count (%u > %u)", - segment_count, le32_to_cpu(raw_super->block_count)); + "Wrong segment_count / block_count (%u > %llu)", + segment_count, le64_to_cpu(raw_super->block_count)); return 1; } diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 7a182c87f378..ab1d7f35f6c2 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -715,6 +715,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob if (awaken) wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) + wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); + /* Prevent a race with our last child, which has to signal EV_CLEARED * before dropping our spinlock. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b4253181b5d4..411f16101d1a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1685,7 +1685,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.h.nodeid = outarg->nodeid; req->in.numargs = 2; req->in.argpages = 1; - req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; index = outarg->offset >> PAGE_SHIFT; @@ -1700,6 +1699,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; + req->page_descs[req->num_pages].offset = offset; req->page_descs[req->num_pages].length = this_num; req->num_pages++; @@ -2018,8 +2018,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); out: kfree(bufs); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1cd46e667e3d..30a607473621 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1772,7 +1772,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, spin_unlock(&fc->lock); dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(page, NR_WRITEBACK_TEMP); + dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index fe3f84995c48..bd6202b70447 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -740,17 +740,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, the gfs2 structures. */ if (default_acl) { error = __gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + if (error) + goto fail_gunlock3; posix_acl_release(default_acl); + default_acl = NULL; } if (acl) { - if (!error) - error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __gfs2_set_acl(inode, acl, ACL_TYPE_ACCESS); + if (error) + goto fail_gunlock3; posix_acl_release(acl); + acl = NULL; } - if (error) - goto fail_gunlock3; - error = security_inode_init_security(&ip->i_inode, &dip->i_inode, name, &gfs2_initxattrs, NULL); if (error) @@ -783,10 +785,8 @@ fail_free_inode: gfs2_glock_put(ip->i_gl); gfs2_rsqa_delete(ip, NULL); fail_free_acls: - if (default_acl) - posix_acl_release(default_acl); - if (acl) - posix_acl_release(acl); + posix_acl_release(default_acl); + posix_acl_release(acl); fail_gunlock: gfs2_dir_no_add(&da); gfs2_glock_dq_uninit(ghs); diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 37cdd955eceb..320f4372f172 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -328,13 +328,14 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index d9d1a36ba826..8d2256454efe 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -453,14 +453,15 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f53c139c312e..001487b230b5 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -861,6 +861,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + migrate_page_copy(newpage, page); return MIGRATEPAGE_SUCCESS; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index b320c1ba7fdc..799f96c67211 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1211,11 +1211,12 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh) struct journal_head *jh; char *committed_data = NULL; - JBUFFER_TRACE(jh, "entry"); if (jbd2_write_access_granted(handle, bh, true)) return 0; jh = jbd2_journal_add_journal_head(bh); + JBUFFER_TRACE(jh, "entry"); + /* * Do this first --- it can drop the journal lock, so we want to * make sure that obtaining the committed_data is done @@ -1326,15 +1327,17 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) if (is_handle_aborted(handle)) return -EROFS; - if (!buffer_jbd(bh)) { - ret = -EUCLEAN; - goto out; - } + if (!buffer_jbd(bh)) + return -EUCLEAN; + /* * We don't grab jh reference here since the buffer must be part * of the running transaction. */ jh = bh2jh(bh); + jbd_debug(5, "journal_head %p\n", jh); + JBUFFER_TRACE(jh, "entry"); + /* * This and the following assertions are unreliable since we may see jh * in inconsistent state unless we grab bh_state lock. But this is @@ -1368,9 +1371,6 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) } journal = transaction->t_journal; - jbd_debug(5, "journal_head %p\n", jh); - JBUFFER_TRACE(jh, "entry"); - jbd_lock_bh_state(bh); if (jh->b_modified == 0) { @@ -1568,14 +1568,21 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh) /* However, if the buffer is still owned by a prior * (committing) transaction, we can't drop it yet... */ JBUFFER_TRACE(jh, "belongs to older transaction"); - /* ... but we CAN drop it from the new transaction if we - * have also modified it since the original commit. */ + /* ... but we CAN drop it from the new transaction through + * marking the buffer as freed and set j_next_transaction to + * the new transaction, so that not only the commit code + * knows it should clear dirty bits when it is done with the + * buffer, but also the buffer can be checkpointed only + * after the new transaction commits. */ - if (jh->b_next_transaction) { - J_ASSERT(jh->b_next_transaction == transaction); + set_buffer_freed(bh); + + if (!jh->b_next_transaction) { spin_lock(&journal->j_list_lock); - jh->b_next_transaction = NULL; + jh->b_next_transaction = transaction; spin_unlock(&journal->j_list_lock); + } else { + J_ASSERT(jh->b_next_transaction == transaction); /* * only drop a reference if this transaction modified diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 79b0de846f21..226640563df3 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -101,7 +101,8 @@ static int jffs2_sync_fs(struct super_block *sb, int wait) struct jffs2_sb_info *c = JFFS2_SB_INFO(sb); #ifdef CONFIG_JFFS2_FS_WRITEBUFFER - cancel_delayed_work_sync(&c->wbuf_dwork); + if (jffs2_is_writebuffered(c)) + cancel_delayed_work_sync(&c->wbuf_dwork); #endif mutex_lock(&c->alloc_sem); diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 0a3f9b594602..37779ed3f790 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -233,7 +233,7 @@ ncp_get_charsets(struct ncp_server* server, struct ncp_nls_ioctl __user *arg) len = strlen(server->nls_vol->charset); if (len > NCP_IOCSNAME_LEN) len = NCP_IOCSNAME_LEN; - strncpy(user.codepage, server->nls_vol->charset, len); + strscpy(user.codepage, server->nls_vol->charset, NCP_IOCSNAME_LEN); user.codepage[len] = 0; } @@ -243,7 +243,7 @@ ncp_get_charsets(struct ncp_server* server, struct ncp_nls_ioctl __user *arg) len = strlen(server->nls_io->charset); if (len > NCP_IOCSNAME_LEN) len = NCP_IOCSNAME_LEN; - strncpy(user.iocharset, server->nls_io->charset, len); + strscpy(user.iocharset, server->nls_io->charset, NCP_IOCSNAME_LEN); user.iocharset[len] = 0; } mutex_unlock(&server->root_setup_lock); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 1ab91124a93e..53f0012ace42 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -98,8 +98,11 @@ struct nfs_direct_req { struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; + /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ + /* for read */ +#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ struct nfs_writeverf verf; /* unstable write verifier */ }; @@ -422,7 +425,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; - if (!PageCompound(page) && bytes < hdr->good_bytes) + if (!PageCompound(page) && bytes < hdr->good_bytes && + (dreq->flags == NFS_ODIRECT_SHOULD_DIRTY)) set_page_dirty(page); bytes += req->wb_bytes; nfs_list_remove_request(req); @@ -597,6 +601,9 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; + if (iter_is_iovec(iter)) + dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; + nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 892c88542ebd..fad4d5188aaf 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -975,6 +975,17 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) } } +static void +nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + LIST_HEAD(head); + + nfs_list_remove_request(req); + nfs_list_add_request(req, &head); + desc->pg_completion_ops->error_cleanup(&head); +} + /** * nfs_pageio_add_request - Attempt to coalesce a request into a page list. * @desc: destination io descriptor @@ -1012,10 +1023,8 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_page_group_unlock(req); desc->pg_moreio = 1; nfs_pageio_doio(desc); - if (desc->pg_error < 0) - return 0; - if (mirror->pg_recoalesce) - return 0; + if (desc->pg_error < 0 || mirror->pg_recoalesce) + goto out_cleanup_subreq; /* retry add_request for this subreq */ nfs_page_group_lock(req, false); continue; @@ -1048,6 +1057,10 @@ err_ptr: desc->pg_error = PTR_ERR(subreq); nfs_page_group_unlock(req); return 0; +out_cleanup_subreq: + if (req != subreq) + nfs_pageio_cleanup_request(desc, subreq); + return 0; } static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) @@ -1066,7 +1079,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) struct nfs_page *req; req = list_first_entry(&head, struct nfs_page, wb_list); - nfs_list_remove_request(req); if (__nfs_pageio_add_request(desc, req)) continue; if (desc->pg_error < 0) { @@ -1141,11 +1153,14 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (nfs_pgio_has_mirroring(desc)) desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) - goto out_failed; + goto out_cleanup_subreq; } return 1; +out_cleanup_subreq: + if (req != dupreq) + nfs_pageio_cleanup_request(desc, dupreq); out_failed: /* * We might have failed before sending any reqs over wire. @@ -1185,7 +1200,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); - if (!mirror->pg_recoalesce) + if (desc->pg_error < 0 || !mirror->pg_recoalesce) break; if (!nfs_do_recoalesce(desc)) break; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2fdb8f5a7b69..659ad12e33ba 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1904,6 +1904,11 @@ static int nfs_parse_devname(const char *dev_name, size_t len; char *end; + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); @@ -2403,8 +2408,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (b->auth_info.flavor_len > 0 && - clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) + if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; Ebusy: diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index d818e4ffd79f..00b472fe77c1 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -431,8 +431,19 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, &resp->common, nfs3svc_encode_entry); memcpy(resp->verf, argp->verf, 8); resp->count = resp->buffer - argp->buffer; - if (resp->offset) - xdr_encode_hyper(resp->offset, argp->cookie); + if (resp->offset) { + loff_t offset = argp->cookie; + + if (unlikely(resp->offset1)) { + /* we ended up with offset on a page boundary */ + *resp->offset = htonl(offset >> 32); + *resp->offset1 = htonl(offset & 0xffffffff); + resp->offset1 = NULL; + } else { + xdr_encode_hyper(resp->offset, offset); + } + resp->offset = NULL; + } RETURN_STATUS(nfserr); } @@ -500,6 +511,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp, } else { xdr_encode_hyper(resp->offset, offset); } + resp->offset = NULL; } RETURN_STATUS(nfserr); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 452334694a5d..7e50248ca432 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -899,6 +899,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen, } else { xdr_encode_hyper(cd->offset, offset64); } + cd->offset = NULL; } /* diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 12d780718b48..3656f87d11e3 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1472,8 +1472,10 @@ free_session_slots(struct nfsd4_session *ses) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + free_svc_cred(&ses->se_slots[i]->sl_cred); kfree(ses->se_slots[i]); + } } /* @@ -2344,14 +2346,18 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) dprintk("--> %s slot %p\n", __func__, slot); + slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; slot->sl_status = resp->cstate.status; + free_svc_cred(&slot->sl_cred); + copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); - slot->sl_flags |= NFSD4_SLOT_INITIALIZED; - if (nfsd4_not_cached(resp)) { - slot->sl_datalen = 0; + if (!nfsd4_cache_this(resp)) { + slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } + slot->sl_flags |= NFSD4_SLOT_CACHED; + base = resp->cstate.data_offset; slot->sl_datalen = buf->len - base; if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) @@ -2378,8 +2384,16 @@ nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, op = &args->ops[resp->opcnt - 1]; nfsd4_encode_operation(resp, op); - /* Return nfserr_retry_uncached_rep in next operation. */ - if (args->opcnt > 1 && !(slot->sl_flags & NFSD4_SLOT_CACHETHIS)) { + if (slot->sl_flags & NFSD4_SLOT_CACHED) + return op->status; + if (args->opcnt == 1) { + /* + * The original operation wasn't a solo sequence--we + * always cache those--so this retry must not match the + * original: + */ + op->status = nfserr_seq_false_retry; + } else { op = &args->ops[resp->opcnt++]; op->status = nfserr_retry_uncached_rep; nfsd4_encode_operation(resp, op); @@ -3039,6 +3053,34 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp, return xb->len > session->se_fchannel.maxreq_sz; } +static bool replay_matches_cache(struct svc_rqst *rqstp, + struct nfsd4_sequence *seq, struct nfsd4_slot *slot) +{ + struct nfsd4_compoundargs *argp = rqstp->rq_argp; + + if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) != + (bool)seq->cachethis) + return false; + /* + * If there's an error than the reply can have fewer ops than + * the call. But if we cached a reply with *more* ops than the + * call you're sending us now, then this new call is clearly not + * really a replay of the old one: + */ + if (slot->sl_opcnt < argp->opcnt) + return false; + /* This is the only check explicitly called by spec: */ + if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) + return false; + /* + * There may be more comparisons we could actually do, but the + * spec doesn't require us to catch every case where the calls + * don't match (that would require caching the call as well as + * the reply), so we don't bother. + */ + return true; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -3098,6 +3140,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) goto out_put_session; + status = nfserr_seq_false_retry; + if (!replay_matches_cache(rqstp, seq, slot)) + goto out_put_session; cstate->slot = slot; cstate->session = session; cstate->clp = clp; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 36b2af931e06..f704f90db36c 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1103,6 +1103,8 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': + if (!nn->nfsd_serv) + return -EBUSY; nfsd4_end_grace(nn); break; default: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 005c911b34ac..86aa92d200e1 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -169,11 +169,13 @@ static inline struct nfs4_delegation *delegstateid(struct nfs4_stid *s) struct nfsd4_slot { u32 sl_seqid; __be32 sl_status; + struct svc_cred sl_cred; u32 sl_datalen; u16 sl_opcnt; #define NFSD4_SLOT_INUSE (1 << 0) #define NFSD4_SLOT_CACHETHIS (1 << 1) #define NFSD4_SLOT_INITIALIZED (1 << 2) +#define NFSD4_SLOT_CACHED (1 << 3) u8 sl_flags; char sl_data[]; }; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 8fda4abdf3b1..448e74e32344 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -645,9 +645,18 @@ static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp) return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE; } -static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp) +/* + * The session reply cache only needs to cache replies that the client + * actually asked us to. But it's almost free for us to cache compounds + * consisting of only a SEQUENCE op, so we may as well cache those too. + * Also, the protocol doesn't give us a convenient response in the case + * of a replay of a solo SEQUENCE op that wasn't cached + * (RETRY_UNCACHED_REP can only be returned in the second op of a + * compound). + */ +static inline bool nfsd4_cache_this(struct nfsd4_compoundres *resp) { - return !(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS) + return (resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS) || nfsd4_is_solo_sequence(resp); } diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index a64adc2fced9..56b4f855fa9b 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -101,9 +101,9 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) parent = dget_parent(dentry); p_inode = parent->d_inode; - if (unlikely(!fsnotify_inode_watches_children(p_inode))) + if (unlikely(!fsnotify_inode_watches_children(p_inode))) { __fsnotify_update_child_dentry_flags(p_inode); - else if (p_inode->i_fsnotify_mask & mask) { + } else if (p_inode->i_fsnotify_mask & mask & ~FS_EVENT_ON_CHILD) { struct name_snapshot name; /* we are notifying a parent so come up with the new mask which @@ -207,6 +207,10 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, else mnt = NULL; + /* An event "on child" is not intended for a mount mark */ + if (mask & FS_EVENT_ON_CHILD) + mnt = NULL; + /* * Optimization: srcu_read_lock() has a memory barrier which can * be expensive. It protects walking the *_fsnotify_marks lists. diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 25c8b328c43d..935bac253991 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -151,7 +151,6 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, #endif } - clear_buffer_uptodate(bh); get_bh(bh); /* for end_buffer_read_sync() */ bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, 0, bh); @@ -305,7 +304,6 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, continue; } - clear_buffer_uptodate(bh); get_bh(bh); /* for end_buffer_read_sync() */ if (validate) set_buffer_needs_validate(bh); diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 827fc9809bc2..3494e220b510 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -125,10 +125,10 @@ check_err: check_gen: if (handle->ih_generation != inode->i_generation) { - iput(inode); trace_ocfs2_get_dentry_generation((unsigned long long)blkno, handle->ih_generation, inode->i_generation); + iput(inode); result = ERR_PTR(-ESTALE); goto bail; } diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index fe0d1f9571bb..5d53d0d63d19 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -345,13 +345,18 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb) if (num_used || alloc->id1.bitmap1.i_used || alloc->id1.bitmap1.i_total - || la->la_bm_off) - mlog(ML_ERROR, "Local alloc hasn't been recovered!\n" + || la->la_bm_off) { + mlog(ML_ERROR, "inconsistent detected, clean journal with" + " unrecovered local alloc, please run fsck.ocfs2!\n" "found = %u, set = %u, taken = %u, off = %u\n", num_used, le32_to_cpu(alloc->id1.bitmap1.i_used), le32_to_cpu(alloc->id1.bitmap1.i_total), OCFS2_LOCAL_ALLOC(alloc)->la_bm_off); + status = -EINVAL; + goto bail; + } + osb->local_alloc_bh = alloc_bh; osb->local_alloc_state = OCFS2_LA_ENABLED; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 4e8f32eb0bdb..c179afd0051a 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -156,18 +156,14 @@ out: } /* - * lock allocators, and reserving appropriate number of bits for - * meta blocks and data clusters. - * - * in some cases, we don't need to reserve clusters, just let data_ac - * be NULL. + * lock allocator, and reserve appropriate number of bits for + * meta blocks. */ -static int ocfs2_lock_allocators_move_extents(struct inode *inode, +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode, struct ocfs2_extent_tree *et, u32 clusters_to_move, u32 extents_to_split, struct ocfs2_alloc_context **meta_ac, - struct ocfs2_alloc_context **data_ac, int extra_blocks, int *credits) { @@ -192,13 +188,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, goto out; } - if (data_ac) { - ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac); - if (ret) { - mlog_errno(ret); - goto out; - } - } *credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el); @@ -260,10 +249,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1, - &context->meta_ac, - &context->data_ac, - extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + *len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; @@ -286,6 +275,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } + /* + * Make sure ocfs2_reserve_cluster is called after + * __ocfs2_flush_truncate_log, otherwise, dead lock may happen. + * + * If ocfs2_reserve_cluster is called + * before __ocfs2_flush_truncate_log, dead lock on global bitmap + * may happen. + * + */ + ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac); + if (ret) { + mlog_errno(ret); + goto out_unlock_mutex; + } + handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -606,9 +610,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1, - &context->meta_ac, - NULL, extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; diff --git a/fs/pipe.c b/fs/pipe.c index 34345535f63d..388e09a689de 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -238,6 +238,14 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = anon_pipe_buf_release, + .steal = anon_pipe_buf_steal, + .get = generic_pipe_buf_get, +}; + static const struct pipe_buf_operations packet_pipe_buf_ops = { .can_merge = 0, .confirm = generic_pipe_buf_confirm, @@ -246,6 +254,12 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = { .get = generic_pipe_buf_get, }; +void pipe_buf_mark_unmergeable(struct pipe_buffer *buf) +{ + if (buf->ops == &anon_pipe_buf_ops) + buf->ops = &anon_pipe_buf_nomerge_ops; +} + static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { diff --git a/fs/proc/array.c b/fs/proc/array.c index 94f83e74db24..712b44c63701 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -346,8 +346,9 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p) { #ifdef CONFIG_SECCOMP seq_put_decimal_ull(m, "Seccomp:\t", p->seccomp.mode); + seq_putc(m, '\n'); #endif - seq_printf(m, "\nSpeculation_Store_Bypass:\t"); + seq_printf(m, "Speculation_Store_Bypass:\t"); switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) { case -EINVAL: seq_printf(m, "unknown"); diff --git a/fs/proc/base.c b/fs/proc/base.c index 79702d405ba7..b9e41832315a 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1134,10 +1134,6 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { - pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n", - task_pid_nr(p), p->comm, - p->signal->oom_score_adj, oom_adj, - task_pid_nr(task), task->comm); p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 46cd2e1b055b..1999e85840d5 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -466,7 +466,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, inode = new_inode(sb); if (!inode) - goto out; + return ERR_PTR(-ENOMEM); inode->i_ino = get_next_ino(); @@ -476,8 +476,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (unlikely(head->unregistering)) { spin_unlock(&sysctl_lock); iput(inode); - inode = NULL; - goto out; + return ERR_PTR(-ENOENT); } ei->sysctl = head; ei->sysctl_entry = table; @@ -502,7 +501,6 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, if (root->set_ownership) root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); -out: return inode; } @@ -551,10 +549,11 @@ static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry, goto out; } - err = ERR_PTR(-ENOMEM); inode = proc_sys_make_inode(dir->i_sb, h ? h : head, p); - if (!inode) + if (IS_ERR(inode)) { + err = ERR_CAST(inode); goto out; + } err = NULL; d_set_d_op(dentry, &proc_sys_dentry_operations); @@ -687,7 +686,7 @@ static bool proc_sys_fill_cache(struct file *file, return false; if (d_in_lookup(child)) { inode = proc_sys_make_inode(dir->d_sb, head, table); - if (!inode) { + if (IS_ERR(inode)) { d_lookup_done(child); dput(child); return false; diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index 43033a3d66d5..2434bffbc6dd 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -584,8 +584,8 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c) } else { spin_lock_irqsave(&psinfo->buf_lock, flags); } - memcpy(psinfo->buf, s, c); - psinfo->write(PSTORE_TYPE_CONSOLE, 0, &id, 0, 0, 0, c, psinfo); + psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0, + s, 0, c, psinfo); spin_unlock_irqrestore(&psinfo->buf_lock, flags); s += c; c = e - s; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index ecdb3baa1283..11e558efd61e 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -488,6 +488,11 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, sig ^= PERSISTENT_RAM_SIG; if (prz->buffer->sig == sig) { + if (buffer_size(prz) == 0) { + pr_debug("found existing empty buffer\n"); + return 0; + } + if (buffer_size(prz) > prz->buffer_size || buffer_start(prz) > buffer_size(prz)) pr_info("found existing invalid buffer, size %zu, start %zu\n", diff --git a/fs/read_write.c b/fs/read_write.c index ba280596ec78..9819f7c6c8c5 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -392,8 +392,10 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos) iter->type |= WRITE; ret = file->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); - if (ret > 0) + if (ret > 0) { *ppos = kiocb.ki_pos; + fsnotify_modify(file); + } return ret; } EXPORT_SYMBOL(vfs_iter_write); diff --git a/fs/splice.c b/fs/splice.c index 8dd79ecfd383..01983bea760c 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1594,6 +1594,8 @@ retry: */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + obuf->len = len; opipe->nrbufs++; ibuf->offset += obuf->len; @@ -1668,6 +1670,8 @@ static int link_pipe(struct pipe_inode_info *ipipe, */ obuf->flags &= ~PIPE_BUF_FLAG_GIFT; + pipe_buf_mark_unmergeable(obuf); + if (obuf->len > len) obuf->len = len; diff --git a/fs/super.c b/fs/super.c index 7e9beab77259..abe2541fb28c 100644 --- a/fs/super.c +++ b/fs/super.c @@ -119,13 +119,23 @@ static unsigned long super_cache_count(struct shrinker *shrink, sb = container_of(shrink, struct super_block, s_shrink); /* - * Don't call trylock_super as it is a potential - * scalability bottleneck. The counts could get updated - * between super_cache_count and super_cache_scan anyway. - * Call to super_cache_count with shrinker_rwsem held - * ensures the safety of call to list_lru_shrink_count() and - * s_op->nr_cached_objects(). + * We don't call trylock_super() here as it is a scalability bottleneck, + * so we're exposed to partial setup state. The shrinker rwsem does not + * protect filesystem operations backing list_lru_shrink_count() or + * s_op->nr_cached_objects(). Counts can change between + * super_cache_count and super_cache_scan, so we really don't need locks + * here. + * + * However, if we are currently mounting the superblock, the underlying + * filesystem might be in a state of partial construction and hence it + * is dangerous to access it. trylock_super() uses a MS_BORN check to + * avoid this situation, so do the same here. The memory barrier is + * matched with the one in mount_fs() as we don't hold locks here. */ + if (!(sb->s_flags & MS_BORN)) + return 0; + smp_rmb(); + if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc); @@ -1193,6 +1203,14 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data) sb = root->d_sb; BUG_ON(!sb); WARN_ON(!sb->s_bdi); + + /* + * Write barrier is for super_cache_count(). We place it before setting + * MS_BORN as the data dependency between the two functions is the + * superblock structure contents that we just set up, not the MS_BORN + * flag. + */ + smp_wmb(); sb->s_flags |= MS_BORN; error = security_sb_kern_mount(sb, flags, secdata); diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index d62c423a5a2d..7b391b43bcf5 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait) } } brelse(bh); - return 0; + return err; } int sysv_write_inode(struct inode *inode, struct writeback_control *wbc) diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index fb0f44cd1e28..de7799a0a9d1 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -210,6 +210,38 @@ static int trun_remove_range(struct ubifs_info *c, struct replay_entry *r) } /** + * inode_still_linked - check whether inode in question will be re-linked. + * @c: UBIFS file-system description object + * @rino: replay entry to test + * + * O_TMPFILE files can be re-linked, this means link count goes from 0 to 1. + * This case needs special care, otherwise all references to the inode will + * be removed upon the first replay entry of an inode with link count 0 + * is found. + */ +static bool inode_still_linked(struct ubifs_info *c, struct replay_entry *rino) +{ + struct replay_entry *r; + + ubifs_assert(rino->deletion); + ubifs_assert(key_type(c, &rino->key) == UBIFS_INO_KEY); + + /* + * Find the most recent entry for the inode behind @rino and check + * whether it is a deletion. + */ + list_for_each_entry_reverse(r, &c->replay_list, list) { + ubifs_assert(r->sqnum >= rino->sqnum); + if (key_inum(c, &r->key) == key_inum(c, &rino->key)) + return r->deletion == 0; + + } + + ubifs_assert(0); + return false; +} + +/** * apply_replay_entry - apply a replay entry to the TNC. * @c: UBIFS file-system description object * @r: replay entry to apply @@ -239,6 +271,11 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r) { ino_t inum = key_inum(c, &r->key); + if (inode_still_linked(c, r)) { + err = 0; + break; + } + err = ubifs_tnc_remove_ino(c, inum); break; } diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 035943501b9f..fd817022cb9b 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1372,6 +1372,12 @@ reread: iinfo->i_alloc_type = le16_to_cpu(fe->icbTag.flags) & ICBTAG_FLAG_AD_MASK; + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_SHORT && + iinfo->i_alloc_type != ICBTAG_FLAG_AD_LONG && + iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { + ret = -EIO; + goto out; + } iinfo->i_unique = 0; iinfo->i_lenEAttr = 0; iinfo->i_lenExtents = 0; diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 42b8c57795cb..c6ce7503a329 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -260,6 +260,9 @@ void udf_truncate_extents(struct inode *inode) epos.block = eloc; epos.bh = udf_tread(sb, udf_get_lb_pblock(sb, &eloc, 0)); + /* Error reading indirect block? */ + if (!epos.bh) + return; if (elen) indirect_ext_len = (elen + sb->s_blocksize - 1) >> |