This patch fixes commit 779750d20b93 ("shmem: split huge pages
beyond i_size under memory pressure").
iput out of sbinfo->shrinklist_lock will let shmem_evict_inode grab
and delete the inode, which will berak the consistency between
shrinklist_len and shrinklist. The simultaneous deletion of adjacent
elements in the local list "list" by shmem_unused_huge_shrink and
shmem_evict_inode will also break the list.
iput must in lock or after lock, but shrinklist_lock is a spinlock
which can not sleep and iput may sleep.[1]
Fix it by changing shrinklist_lock from spinlock to mutex and moving iput
into this lock.
[1]. Link: http://lkml.kernel.org/r/[email protected]
Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure")
Signed-off-by: Gang Li <[email protected]>
---
include/linux/shmem_fs.h | 2 +-
mm/shmem.c | 16 +++++++---------
2 files changed, 8 insertions(+), 10 deletions(-)
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 166158b6e917..65804fd264d0 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -41,7 +41,7 @@ struct shmem_sb_info {
ino_t next_ino; /* The next per-sb inode number to use */
ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */
struct mempolicy *mpol; /* default memory policy for mappings */
- spinlock_t shrinklist_lock; /* Protects shrinklist */
+ struct mutex shrinklist_mutex;/* Protects shrinklist */
struct list_head shrinklist; /* List of shinkable inodes */
unsigned long shrinklist_len; /* Length of shrinklist */
};
diff --git a/mm/shmem.c b/mm/shmem.c
index 18f93c2d68f1..2165a28631c5 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -559,7 +559,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
if (list_empty(&sbinfo->shrinklist))
return SHRINK_STOP;
- spin_lock(&sbinfo->shrinklist_lock);
+ mutex_lock(&sbinfo->shrinklist_mutex);
list_for_each_safe(pos, next, &sbinfo->shrinklist) {
info = list_entry(pos, struct shmem_inode_info, shrinklist);
@@ -586,7 +586,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
if (!--batch)
break;
}
- spin_unlock(&sbinfo->shrinklist_lock);
list_for_each_safe(pos, next, &to_remove) {
info = list_entry(pos, struct shmem_inode_info, shrinklist);
@@ -643,10 +642,9 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
iput(inode);
}
- spin_lock(&sbinfo->shrinklist_lock);
list_splice_tail(&list, &sbinfo->shrinklist);
sbinfo->shrinklist_len -= removed;
- spin_unlock(&sbinfo->shrinklist_lock);
+ mutex_unlock(&sbinfo->shrinklist_mutex);
return split;
}
@@ -1137,12 +1135,12 @@ static void shmem_evict_inode(struct inode *inode)
inode->i_size = 0;
shmem_truncate_range(inode, 0, (loff_t)-1);
if (!list_empty(&info->shrinklist)) {
- spin_lock(&sbinfo->shrinklist_lock);
+ mutex_lock(&sbinfo->shrinklist_mutex);
if (!list_empty(&info->shrinklist)) {
list_del_init(&info->shrinklist);
sbinfo->shrinklist_len--;
}
- spin_unlock(&sbinfo->shrinklist_lock);
+ mutex_unlock(&sbinfo->shrinklist_mutex);
}
while (!list_empty(&info->swaplist)) {
/* Wait while shmem_unuse() is scanning this inode... */
@@ -1954,7 +1952,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
* Part of the huge page is beyond i_size: subject
* to shrink under memory pressure.
*/
- spin_lock(&sbinfo->shrinklist_lock);
+ mutex_lock(&sbinfo->shrinklist_mutex);
/*
* _careful to defend against unlocked access to
* ->shrink_list in shmem_unused_huge_shrink()
@@ -1964,7 +1962,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
&sbinfo->shrinklist);
sbinfo->shrinklist_len++;
}
- spin_unlock(&sbinfo->shrinklist_lock);
+ mutex_unlock(&sbinfo->shrinklist_mutex);
}
/*
@@ -3652,7 +3650,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
raw_spin_lock_init(&sbinfo->stat_lock);
if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
goto failed;
- spin_lock_init(&sbinfo->shrinklist_lock);
+ mutex_init(&sbinfo->shrinklist_mutex);
INIT_LIST_HEAD(&sbinfo->shrinklist);
sb->s_maxbytes = MAX_LFS_FILESIZE;
--
2.20.1
On Mon, Nov 22, 2021 at 2:41 PM Gang Li <[email protected]> wrote:
>
> This patch fixes commit 779750d20b93 ("shmem: split huge pages
> beyond i_size under memory pressure").
>
> iput out of sbinfo->shrinklist_lock will let shmem_evict_inode grab
> and delete the inode, which will berak the consistency between
> shrinklist_len and shrinklist. The simultaneous deletion of adjacent
> elements in the local list "list" by shmem_unused_huge_shrink and
> shmem_evict_inode will also break the list.
>
> iput must in lock or after lock, but shrinklist_lock is a spinlock
> which can not sleep and iput may sleep.[1]
>
> Fix it by changing shrinklist_lock from spinlock to mutex and moving iput
> into this lock.
>
> [1]. Link: http://lkml.kernel.org/r/[email protected]
> Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure")
> Signed-off-by: Gang Li <[email protected]>
> ---
> include/linux/shmem_fs.h | 2 +-
> mm/shmem.c | 16 +++++++---------
> 2 files changed, 8 insertions(+), 10 deletions(-)
>
> diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
> index 166158b6e917..65804fd264d0 100644
> --- a/include/linux/shmem_fs.h
> +++ b/include/linux/shmem_fs.h
> @@ -41,7 +41,7 @@ struct shmem_sb_info {
> ino_t next_ino; /* The next per-sb inode number to use */
> ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */
> struct mempolicy *mpol; /* default memory policy for mappings */
> - spinlock_t shrinklist_lock; /* Protects shrinklist */
> + struct mutex shrinklist_mutex;/* Protects shrinklist */
> struct list_head shrinklist; /* List of shinkable inodes */
> unsigned long shrinklist_len; /* Length of shrinklist */
> };
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 18f93c2d68f1..2165a28631c5 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -559,7 +559,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
> if (list_empty(&sbinfo->shrinklist))
> return SHRINK_STOP;
>
> - spin_lock(&sbinfo->shrinklist_lock);
> + mutex_lock(&sbinfo->shrinklist_mutex);
> list_for_each_safe(pos, next, &sbinfo->shrinklist) {
> info = list_entry(pos, struct shmem_inode_info, shrinklist);
>
> @@ -586,7 +586,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
> if (!--batch)
> break;
> }
> - spin_unlock(&sbinfo->shrinklist_lock);
>
> list_for_each_safe(pos, next, &to_remove) {
> info = list_entry(pos, struct shmem_inode_info, shrinklist);
> @@ -643,10 +642,9 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
> iput(inode);
It could lead to deadlock, since we could be the last user
of @inode, then shmem_evict_inode() will be called and
try to acquire the mutex lock. Notice that the mutex is already
held here.
Thanks.
> }
>
> - spin_lock(&sbinfo->shrinklist_lock);
> list_splice_tail(&list, &sbinfo->shrinklist);
> sbinfo->shrinklist_len -= removed;
> - spin_unlock(&sbinfo->shrinklist_lock);
> + mutex_unlock(&sbinfo->shrinklist_mutex);
>
> return split;
> }
> @@ -1137,12 +1135,12 @@ static void shmem_evict_inode(struct inode *inode)
> inode->i_size = 0;
> shmem_truncate_range(inode, 0, (loff_t)-1);
> if (!list_empty(&info->shrinklist)) {
> - spin_lock(&sbinfo->shrinklist_lock);
> + mutex_lock(&sbinfo->shrinklist_mutex);
> if (!list_empty(&info->shrinklist)) {
> list_del_init(&info->shrinklist);
> sbinfo->shrinklist_len--;
> }
> - spin_unlock(&sbinfo->shrinklist_lock);
> + mutex_unlock(&sbinfo->shrinklist_mutex);
> }
> while (!list_empty(&info->swaplist)) {
> /* Wait while shmem_unuse() is scanning this inode... */
> @@ -1954,7 +1952,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
> * Part of the huge page is beyond i_size: subject
> * to shrink under memory pressure.
> */
> - spin_lock(&sbinfo->shrinklist_lock);
> + mutex_lock(&sbinfo->shrinklist_mutex);
> /*
> * _careful to defend against unlocked access to
> * ->shrink_list in shmem_unused_huge_shrink()
> @@ -1964,7 +1962,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
> &sbinfo->shrinklist);
> sbinfo->shrinklist_len++;
> }
> - spin_unlock(&sbinfo->shrinklist_lock);
> + mutex_unlock(&sbinfo->shrinklist_mutex);
> }
>
> /*
> @@ -3652,7 +3650,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
> raw_spin_lock_init(&sbinfo->stat_lock);
> if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
> goto failed;
> - spin_lock_init(&sbinfo->shrinklist_lock);
> + mutex_init(&sbinfo->shrinklist_mutex);
> INIT_LIST_HEAD(&sbinfo->shrinklist);
>
> sb->s_maxbytes = MAX_LFS_FILESIZE;
> --
> 2.20.1
>
Hi Gang,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on hnaz-mm/master]
[also build test WARNING on linux/master linus/master v5.16-rc2 next-20211125]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Gang-Li/shmem-change-shrinklist_lock-form-spinlock-to-mutex-and-move-iput-into-it/20211122-144228
base: https://github.com/hnaz/linux-mm master
config: i386-randconfig-m021-20211124 (https://download.01.org/0day-ci/archive/20211126/[email protected]/config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
smatch warnings:
mm/shmem.c:1139 shmem_evict_inode() warn: inconsistent indenting
vim +1139 mm/shmem.c
^1da177e4c3f41 Linus Torvalds 2005-04-16 1127
1f895f75dc0881 Al Viro 2010-06-05 1128 static void shmem_evict_inode(struct inode *inode)
^1da177e4c3f41 Linus Torvalds 2005-04-16 1129 {
^1da177e4c3f41 Linus Torvalds 2005-04-16 1130 struct shmem_inode_info *info = SHMEM_I(inode);
779750d20b93bb Kirill A. Shutemov 2016-07-26 1131 struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
^1da177e4c3f41 Linus Torvalds 2005-04-16 1132
30e6a51dbb0594 Hui Su 2020-12-14 1133 if (shmem_mapping(inode->i_mapping)) {
^1da177e4c3f41 Linus Torvalds 2005-04-16 1134 shmem_unacct_size(info->flags, inode->i_size);
^1da177e4c3f41 Linus Torvalds 2005-04-16 1135 inode->i_size = 0;
3889e6e76f66b7 Nicholas Piggin 2010-05-27 1136 shmem_truncate_range(inode, 0, (loff_t)-1);
779750d20b93bb Kirill A. Shutemov 2016-07-26 1137 if (!list_empty(&info->shrinklist)) {
713e6a98816b68 Gang Li 2021-11-22 1138 mutex_lock(&sbinfo->shrinklist_mutex);
779750d20b93bb Kirill A. Shutemov 2016-07-26 @1139 if (!list_empty(&info->shrinklist)) {
779750d20b93bb Kirill A. Shutemov 2016-07-26 1140 list_del_init(&info->shrinklist);
779750d20b93bb Kirill A. Shutemov 2016-07-26 1141 sbinfo->shrinklist_len--;
779750d20b93bb Kirill A. Shutemov 2016-07-26 1142 }
713e6a98816b68 Gang Li 2021-11-22 1143 mutex_unlock(&sbinfo->shrinklist_mutex);
779750d20b93bb Kirill A. Shutemov 2016-07-26 1144 }
af53d3e9e04024 Hugh Dickins 2019-04-18 1145 while (!list_empty(&info->swaplist)) {
af53d3e9e04024 Hugh Dickins 2019-04-18 1146 /* Wait while shmem_unuse() is scanning this inode... */
af53d3e9e04024 Hugh Dickins 2019-04-18 1147 wait_var_event(&info->stop_eviction,
af53d3e9e04024 Hugh Dickins 2019-04-18 1148 !atomic_read(&info->stop_eviction));
cb5f7b9a47963d Hugh Dickins 2008-02-04 1149 mutex_lock(&shmem_swaplist_mutex);
af53d3e9e04024 Hugh Dickins 2019-04-18 1150 /* ...but beware of the race if we peeked too early */
af53d3e9e04024 Hugh Dickins 2019-04-18 1151 if (!atomic_read(&info->stop_eviction))
^1da177e4c3f41 Linus Torvalds 2005-04-16 1152 list_del_init(&info->swaplist);
cb5f7b9a47963d Hugh Dickins 2008-02-04 1153 mutex_unlock(&shmem_swaplist_mutex);
^1da177e4c3f41 Linus Torvalds 2005-04-16 1154 }
3ed47db34f480d Al Viro 2016-01-22 1155 }
b09e0fa4b4ea66 Eric Paris 2011-05-24 1156
38f38657444d15 Aristeu Rozanski 2012-08-23 1157 simple_xattrs_free(&info->xattrs);
0f3c42f522dc1a Hugh Dickins 2012-11-16 1158 WARN_ON(inode->i_blocks);
5b04c6890f0dc7 Pavel Emelyanov 2008-02-04 1159 shmem_free_inode(inode->i_sb);
dbd5768f87ff6f Jan Kara 2012-05-03 1160 clear_inode(inode);
^1da177e4c3f41 Linus Torvalds 2005-04-16 1161 }
^1da177e4c3f41 Linus Torvalds 2005-04-16 1162
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]