5.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhang Yi yi.zhang@huawei.com
[ Upstream commit 8e387c89e96b9543a339f84043cf9df15fed2632 ]
__insert_pending() allocate memory in atomic context, so the allocation could fail, but we are not handling that failure now. It could lead ext4_es_remove_extent() to get wrong reserved clusters, and the global data blocks reservation count will be incorrect. The same to extents_status entry preallocation, preallocate pending entry out of the i_es_lock with __GFP_NOFAIL, make sure __insert_pending() and __revise_pending() always succeeds.
Signed-off-by: Zhang Yi yi.zhang@huawei.com Cc: stable@kernel.org Link: https://lore.kernel.org/r/20230824092619.1327976-3-yi.zhang@huaweicloud.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/extents_status.c | 123 ++++++++++++++++++++++++++++----------- 1 file changed, 89 insertions(+), 34 deletions(-)
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 4b47bccc3834a..3346a9252063b 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -152,8 +152,9 @@ static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk, static int es_reclaim_extents(struct ext4_inode_info *ei, int *nr_to_scan); static int __es_shrink(struct ext4_sb_info *sbi, int nr_to_scan, struct ext4_inode_info *locked_ei); -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len); +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc);
int __init ext4_init_es(void) { @@ -441,6 +442,19 @@ static void ext4_es_list_del(struct inode *inode) spin_unlock(&sbi->s_es_lock); }
+static inline struct pending_reservation *__alloc_pending(bool nofail) +{ + if (!nofail) + return kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); + + return kmem_cache_zalloc(ext4_pending_cachep, GFP_KERNEL | __GFP_NOFAIL); +} + +static inline void __free_pending(struct pending_reservation *pr) +{ + kmem_cache_free(ext4_pending_cachep, pr); +} + /* * Returns true if we cannot fail to allocate memory for this extent_status * entry and cannot reclaim it until its status changes. @@ -832,11 +846,12 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, { struct extent_status newes; ext4_lblk_t end = lblk + len - 1; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL; + bool revise_pending = false;
es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n", lblk, len, pblk, status, inode->i_ino); @@ -861,11 +876,17 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_es_insert_extent_check(inode, &newes);
+ revise_pending = sbi->s_cluster_ratio > 1 && + test_opt(inode->i_sb, DELALLOC) && + (status & (EXTENT_STATUS_WRITTEN | + EXTENT_STATUS_UNWRITTEN)); retry: if (err1 && !es1) es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && revise_pending && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock);
err1 = __es_remove_extent(inode, lblk, end, NULL, es1); @@ -890,13 +911,18 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; }
- if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) && - (status & EXTENT_STATUS_WRITTEN || - status & EXTENT_STATUS_UNWRITTEN)) - __revise_pending(inode, lblk, len); + if (revise_pending) { + err3 = __revise_pending(inode, lblk, len, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry;
ext4_es_print_tree(inode); @@ -1298,7 +1324,7 @@ static unsigned int get_rsvd(struct inode *inode, ext4_lblk_t end, rc->ndelonly--; node = rb_next(&pr->rb_node); rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); if (!node) break; pr = rb_entry(node, struct pending_reservation, @@ -1892,11 +1918,13 @@ static struct pending_reservation *__get_pending(struct inode *inode, * * @inode - file containing the cluster * @lblk - logical block in the cluster to be added + * @prealloc - preallocated pending entry * * Returns 0 on successful insertion and -ENOMEM on failure. If the * pending reservation is already in the set, returns successfully. */ -static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) +static int __insert_pending(struct inode *inode, ext4_lblk_t lblk, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_pending_tree *tree = &EXT4_I(inode)->i_pending_tree; @@ -1922,10 +1950,15 @@ static int __insert_pending(struct inode *inode, ext4_lblk_t lblk) } }
- pr = kmem_cache_alloc(ext4_pending_cachep, GFP_ATOMIC); - if (pr == NULL) { - ret = -ENOMEM; - goto out; + if (likely(*prealloc == NULL)) { + pr = __alloc_pending(false); + if (!pr) { + ret = -ENOMEM; + goto out; + } + } else { + pr = *prealloc; + *prealloc = NULL; } pr->lclu = lclu;
@@ -1955,7 +1988,7 @@ static void __remove_pending(struct inode *inode, ext4_lblk_t lblk) if (pr != NULL) { tree = &EXT4_I(inode)->i_pending_tree; rb_erase(&pr->rb_node, &tree->root); - kmem_cache_free(ext4_pending_cachep, pr); + __free_pending(pr); } }
@@ -2016,10 +2049,10 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, bool allocated) { struct extent_status newes; - int err1 = 0; - int err2 = 0; + int err1 = 0, err2 = 0, err3 = 0; struct extent_status *es1 = NULL; struct extent_status *es2 = NULL; + struct pending_reservation *pr = NULL;
es_debug("add [%u/1) delayed to extent status tree of inode %lu\n", lblk, inode->i_ino); @@ -2036,6 +2069,8 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es1 = __es_alloc_extent(true); if ((err1 || err2) && !es2) es2 = __es_alloc_extent(true); + if ((err1 || err2 || err3) && allocated && !pr) + pr = __alloc_pending(true); write_lock(&EXT4_I(inode)->i_es_lock);
err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1); @@ -2058,11 +2093,18 @@ int ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk, es2 = NULL; }
- if (allocated) - __insert_pending(inode, lblk); + if (allocated) { + err3 = __insert_pending(inode, lblk, &pr); + if (err3 != 0) + goto error; + if (pr) { + __free_pending(pr); + pr = NULL; + } + } error: write_unlock(&EXT4_I(inode)->i_es_lock); - if (err1 || err2) + if (err1 || err2 || err3) goto retry;
ext4_es_print_tree(inode); @@ -2168,21 +2210,24 @@ unsigned int ext4_es_delayed_clu(struct inode *inode, ext4_lblk_t lblk, * @inode - file containing the range * @lblk - logical block defining the start of range * @len - length of range in blocks + * @prealloc - preallocated pending entry * * Used after a newly allocated extent is added to the extents status tree. * Requires that the extents in the range have either written or unwritten * status. Must be called while holding i_es_lock. */ -static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, - ext4_lblk_t len) +static int __revise_pending(struct inode *inode, ext4_lblk_t lblk, + ext4_lblk_t len, + struct pending_reservation **prealloc) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t end = lblk + len - 1; ext4_lblk_t first, last; bool f_del = false, l_del = false; + int ret = 0;
if (len == 0) - return; + return 0;
/* * Two cases - block range within single cluster and block range @@ -2203,7 +2248,9 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); if (f_del) { - __insert_pending(inode, first); + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; } else { last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; @@ -2211,9 +2258,11 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } } else { @@ -2221,18 +2270,24 @@ static void __revise_pending(struct inode *inode, ext4_lblk_t lblk, if (first != lblk) f_del = __es_scan_range(inode, &ext4_es_is_delonly, first, lblk - 1); - if (f_del) - __insert_pending(inode, first); - else + if (f_del) { + ret = __insert_pending(inode, first, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, first);
last = EXT4_LBLK_CMASK(sbi, end) + sbi->s_cluster_ratio - 1; if (last != end) l_del = __es_scan_range(inode, &ext4_es_is_delonly, end + 1, last); - if (l_del) - __insert_pending(inode, last); - else + if (l_del) { + ret = __insert_pending(inode, last, prealloc); + if (ret < 0) + goto out; + } else __remove_pending(inode, last); } +out: + return ret; }