This is a note to let you know that I've just added the patch titled
ext4: make sure allocate pending entry not fail
to the 5.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
ext4-make-sure-allocate-pending-entry-not-fail.patch
and it can be found in the queue-5.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 0262a62c68892a5ee1e313efc8b92c7c9d77fee0
Author: Zhang Yi <yi.zhang@xxxxxxxxxx>
Date: Thu Aug 24 17:26:05 2023 +0800
ext4: make sure allocate pending entry not fail
[ 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@xxxxxxxxxx>
Cc: stable@xxxxxxxxxx
Link: https://lore.kernel.org/r/20230824092619.1327976-3-yi.zhang@xxxxxxxxxxxxxxx
Reviewed-by: Jan Kara <jack@xxxxxxx>
Signed-off-by: Theodore Ts'o <tytso@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 6c55ab427e650..cccbdfd49a86b 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)
{
@@ -450,6 +451,19 @@ 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.
@@ -841,11 +855,12 @@ 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;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return 0;
@@ -873,11 +888,17 @@ 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);
@@ -902,13 +923,18 @@ 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);
@@ -1316,7 +1342,7 @@ 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,
@@ -1913,11 +1939,13 @@ 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;
@@ -1943,10 +1971,15 @@ 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;
@@ -1976,7 +2009,7 @@ 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);
}
}
@@ -2037,10 +2070,10 @@ 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;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
return 0;
@@ -2060,6 +2093,8 @@ 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);
@@ -2082,11 +2117,18 @@ 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);
@@ -2192,21 +2234,24 @@ 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
@@ -2227,7 +2272,9 @@ 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;
@@ -2235,9 +2282,11 @@ 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 {
@@ -2245,18 +2294,24 @@ 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;
}
