From: Zhang Yi <yi.zhang@huawei.com>
In environments with a page size of 64KB, the maximum size of a folio
can reach up to 128MB. Consequently, during the write-back of folios,
the 'rsv_blocks' will be overestimated to 1,577, which can make
pressure on the journal space where the journal is small. This can
easily exceed the limit of a single transaction. Besides, an excessively
large folio is meaningless and will instead increase the overhead of
traversing the bhs within the folio. Therefore, limit the maximum order
of a folio to 2048 filesystem blocks.
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Reported-by: Joseph Qi <jiangqi903@gmail.com>
Closes: https://lore.kernel.org/linux-ext4/CA+G9fYsyYQ3ZL4xaSg1-Tt5Evto7Zd+hgNWZEa9cQLbahA1+xg@mail.gmail.com/
Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
fs/ext4/ext4.h | 2 +-
fs/ext4/ialloc.c | 3 +--
fs/ext4/inode.c | 22 +++++++++++++++++++---
3 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index f705046ba6c6..9ac0a7d4fa0c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3020,7 +3020,7 @@ int ext4_walk_page_buffers(handle_t *handle,
struct buffer_head *bh));
int do_journal_get_write_access(handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-bool ext4_should_enable_large_folio(struct inode *inode);
+void ext4_set_inode_mapping_order(struct inode *inode);
#define FALL_BACK_TO_NONDELALLOC 1
#define CONVERT_INLINE_DATA 2
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 79aa3df8d019..df4051613b29 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1335,8 +1335,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
}
}
- if (ext4_should_enable_large_folio(inode))
- mapping_set_large_folios(inode->i_mapping);
+ ext4_set_inode_mapping_order(inode);
ext4_update_inode_fsync_trans(handle, inode, 1);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4b679cb6c8bd..1bce9ebaedb7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5181,7 +5181,7 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
return -EFSCORRUPTED;
}
-bool ext4_should_enable_large_folio(struct inode *inode)
+static bool ext4_should_enable_large_folio(struct inode *inode)
{
struct super_block *sb = inode->i_sb;
@@ -5198,6 +5198,22 @@ bool ext4_should_enable_large_folio(struct inode *inode)
return true;
}
+/*
+ * Limit the maximum folio order to 2048 blocks to prevent overestimation
+ * of reserve handle credits during the folio writeback in environments
+ * where the PAGE_SIZE exceeds 4KB.
+ */
+#define EXT4_MAX_PAGECACHE_ORDER(i) \
+ min(MAX_PAGECACHE_ORDER, (11 + (i)->i_blkbits - PAGE_SHIFT))
+void ext4_set_inode_mapping_order(struct inode *inode)
+{
+ if (!ext4_should_enable_large_folio(inode))
+ return;
+
+ mapping_set_folio_order_range(inode->i_mapping, 0,
+ EXT4_MAX_PAGECACHE_ORDER(inode));
+}
+
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ext4_iget_flags flags, const char *function,
unsigned int line)
@@ -5515,8 +5531,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ret = -EFSCORRUPTED;
goto bad_inode;
}
- if (ext4_should_enable_large_folio(inode))
- mapping_set_large_folios(inode->i_mapping);
+
+ ext4_set_inode_mapping_order(inode);
ret = check_igot_inode(inode, flags, function, line);
/*
--
2.46.1On Mon, 7 Jul 2025 at 19:53, Zhang Yi <yi.zhang@huaweicloud.com> wrote:
>
> From: Zhang Yi <yi.zhang@huawei.com>
>
> In environments with a page size of 64KB, the maximum size of a folio
> can reach up to 128MB. Consequently, during the write-back of folios,
> the 'rsv_blocks' will be overestimated to 1,577, which can make
> pressure on the journal space where the journal is small. This can
> easily exceed the limit of a single transaction. Besides, an excessively
> large folio is meaningless and will instead increase the overhead of
> traversing the bhs within the folio. Therefore, limit the maximum order
> of a folio to 2048 filesystem blocks.
>
> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
> Reported-by: Joseph Qi <jiangqi903@gmail.com>
> Closes: https://lore.kernel.org/linux-ext4/CA+G9fYsyYQ3ZL4xaSg1-Tt5Evto7Zd+hgNWZEa9cQLbahA1+xg@mail.gmail.com/
> Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
I have applied this patch set on top of the Linux next tree and performed
testing. The previously reported regressions [a] are no longer observed.
Thank you for providing the fix.
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
Reference link:
[a] https://lore.kernel.org/all/CA+G9fYsyYQ3ZL4xaSg1-Tt5Evto7Zd+hgNWZEa9cQLbahA1+xg@mail.gmail.com/
> ---
> fs/ext4/ext4.h | 2 +-
> fs/ext4/ialloc.c | 3 +--
> fs/ext4/inode.c | 22 +++++++++++++++++++---
> 3 files changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index f705046ba6c6..9ac0a7d4fa0c 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3020,7 +3020,7 @@ int ext4_walk_page_buffers(handle_t *handle,
> struct buffer_head *bh));
> int do_journal_get_write_access(handle_t *handle, struct inode *inode,
> struct buffer_head *bh);
> -bool ext4_should_enable_large_folio(struct inode *inode);
> +void ext4_set_inode_mapping_order(struct inode *inode);
> #define FALL_BACK_TO_NONDELALLOC 1
> #define CONVERT_INLINE_DATA 2
>
> diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
> index 79aa3df8d019..df4051613b29 100644
> --- a/fs/ext4/ialloc.c
> +++ b/fs/ext4/ialloc.c
> @@ -1335,8 +1335,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
> }
> }
>
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> + ext4_set_inode_mapping_order(inode);
>
> ext4_update_inode_fsync_trans(handle, inode, 1);
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 4b679cb6c8bd..1bce9ebaedb7 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -5181,7 +5181,7 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
> return -EFSCORRUPTED;
> }
>
> -bool ext4_should_enable_large_folio(struct inode *inode)
> +static bool ext4_should_enable_large_folio(struct inode *inode)
> {
> struct super_block *sb = inode->i_sb;
>
> @@ -5198,6 +5198,22 @@ bool ext4_should_enable_large_folio(struct inode *inode)
> return true;
> }
>
> +/*
> + * Limit the maximum folio order to 2048 blocks to prevent overestimation
> + * of reserve handle credits during the folio writeback in environments
> + * where the PAGE_SIZE exceeds 4KB.
> + */
> +#define EXT4_MAX_PAGECACHE_ORDER(i) \
> + min(MAX_PAGECACHE_ORDER, (11 + (i)->i_blkbits - PAGE_SHIFT))
> +void ext4_set_inode_mapping_order(struct inode *inode)
> +{
> + if (!ext4_should_enable_large_folio(inode))
> + return;
> +
> + mapping_set_folio_order_range(inode->i_mapping, 0,
> + EXT4_MAX_PAGECACHE_ORDER(inode));
> +}
> +
> struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ext4_iget_flags flags, const char *function,
> unsigned int line)
> @@ -5515,8 +5531,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ret = -EFSCORRUPTED;
> goto bad_inode;
> }
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> +
> + ext4_set_inode_mapping_order(inode);
>
> ret = check_igot_inode(inode, flags, function, line);
> /*
> --
> 2.46.1
>
--
Linaro LKFT
https://lkft.linaro.org
On 2025/7/7 22:08, Zhang Yi wrote:
> From: Zhang Yi <yi.zhang@huawei.com>
>
> In environments with a page size of 64KB, the maximum size of a folio
> can reach up to 128MB. Consequently, during the write-back of folios,
> the 'rsv_blocks' will be overestimated to 1,577, which can make
> pressure on the journal space where the journal is small. This can
> easily exceed the limit of a single transaction. Besides, an excessively
> large folio is meaningless and will instead increase the overhead of
> traversing the bhs within the folio. Therefore, limit the maximum order
> of a folio to 2048 filesystem blocks.
>
> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
> Reported-by: Joseph Qi <jiangqi903@gmail.com>
> Closes: https://lore.kernel.org/linux-ext4/CA+G9fYsyYQ3ZL4xaSg1-Tt5Evto7Zd+hgNWZEa9cQLbahA1+xg@mail.gmail.com/
> Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Confirmed that this can fix the following jbd2 warning in start_this_handle():
"JBD2: kworker/u32:0 wants too many credits credits:32 rsv_credits:1577 max:2695"
Tested-by: Joseph Qi <joseph.qi@linux.alibaba.com>
> ---
> fs/ext4/ext4.h | 2 +-
> fs/ext4/ialloc.c | 3 +--
> fs/ext4/inode.c | 22 +++++++++++++++++++---
> 3 files changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index f705046ba6c6..9ac0a7d4fa0c 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3020,7 +3020,7 @@ int ext4_walk_page_buffers(handle_t *handle,
> struct buffer_head *bh));
> int do_journal_get_write_access(handle_t *handle, struct inode *inode,
> struct buffer_head *bh);
> -bool ext4_should_enable_large_folio(struct inode *inode);
> +void ext4_set_inode_mapping_order(struct inode *inode);
> #define FALL_BACK_TO_NONDELALLOC 1
> #define CONVERT_INLINE_DATA 2
>
> diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
> index 79aa3df8d019..df4051613b29 100644
> --- a/fs/ext4/ialloc.c
> +++ b/fs/ext4/ialloc.c
> @@ -1335,8 +1335,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
> }
> }
>
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> + ext4_set_inode_mapping_order(inode);
>
> ext4_update_inode_fsync_trans(handle, inode, 1);
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 4b679cb6c8bd..1bce9ebaedb7 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -5181,7 +5181,7 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
> return -EFSCORRUPTED;
> }
>
> -bool ext4_should_enable_large_folio(struct inode *inode)
> +static bool ext4_should_enable_large_folio(struct inode *inode)
> {
> struct super_block *sb = inode->i_sb;
>
> @@ -5198,6 +5198,22 @@ bool ext4_should_enable_large_folio(struct inode *inode)
> return true;
> }
>
> +/*
> + * Limit the maximum folio order to 2048 blocks to prevent overestimation
> + * of reserve handle credits during the folio writeback in environments
> + * where the PAGE_SIZE exceeds 4KB.
> + */
> +#define EXT4_MAX_PAGECACHE_ORDER(i) \
> + min(MAX_PAGECACHE_ORDER, (11 + (i)->i_blkbits - PAGE_SHIFT))
> +void ext4_set_inode_mapping_order(struct inode *inode)
> +{
> + if (!ext4_should_enable_large_folio(inode))
> + return;
> +
> + mapping_set_folio_order_range(inode->i_mapping, 0,
> + EXT4_MAX_PAGECACHE_ORDER(inode));
> +}
> +
> struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ext4_iget_flags flags, const char *function,
> unsigned int line)
> @@ -5515,8 +5531,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ret = -EFSCORRUPTED;
> goto bad_inode;
> }
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> +
> + ext4_set_inode_mapping_order(inode);
>
> ret = check_igot_inode(inode, flags, function, line);
> /*
On Mon 07-07-25 22:08:14, Zhang Yi wrote:
> From: Zhang Yi <yi.zhang@huawei.com>
>
> In environments with a page size of 64KB, the maximum size of a folio
> can reach up to 128MB. Consequently, during the write-back of folios,
> the 'rsv_blocks' will be overestimated to 1,577, which can make
> pressure on the journal space where the journal is small. This can
> easily exceed the limit of a single transaction. Besides, an excessively
> large folio is meaningless and will instead increase the overhead of
> traversing the bhs within the folio. Therefore, limit the maximum order
> of a folio to 2048 filesystem blocks.
>
> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
> Reported-by: Joseph Qi <jiangqi903@gmail.com>
> Closes: https://lore.kernel.org/linux-ext4/CA+G9fYsyYQ3ZL4xaSg1-Tt5Evto7Zd+hgNWZEa9cQLbahA1+xg@mail.gmail.com/
> Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Looks good. Feel free to add:
Reviewed-by: Jan Kara <jack@suse.cz>
Honza
> ---
> fs/ext4/ext4.h | 2 +-
> fs/ext4/ialloc.c | 3 +--
> fs/ext4/inode.c | 22 +++++++++++++++++++---
> 3 files changed, 21 insertions(+), 6 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index f705046ba6c6..9ac0a7d4fa0c 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -3020,7 +3020,7 @@ int ext4_walk_page_buffers(handle_t *handle,
> struct buffer_head *bh));
> int do_journal_get_write_access(handle_t *handle, struct inode *inode,
> struct buffer_head *bh);
> -bool ext4_should_enable_large_folio(struct inode *inode);
> +void ext4_set_inode_mapping_order(struct inode *inode);
> #define FALL_BACK_TO_NONDELALLOC 1
> #define CONVERT_INLINE_DATA 2
>
> diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
> index 79aa3df8d019..df4051613b29 100644
> --- a/fs/ext4/ialloc.c
> +++ b/fs/ext4/ialloc.c
> @@ -1335,8 +1335,7 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
> }
> }
>
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> + ext4_set_inode_mapping_order(inode);
>
> ext4_update_inode_fsync_trans(handle, inode, 1);
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 4b679cb6c8bd..1bce9ebaedb7 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -5181,7 +5181,7 @@ static int check_igot_inode(struct inode *inode, ext4_iget_flags flags,
> return -EFSCORRUPTED;
> }
>
> -bool ext4_should_enable_large_folio(struct inode *inode)
> +static bool ext4_should_enable_large_folio(struct inode *inode)
> {
> struct super_block *sb = inode->i_sb;
>
> @@ -5198,6 +5198,22 @@ bool ext4_should_enable_large_folio(struct inode *inode)
> return true;
> }
>
> +/*
> + * Limit the maximum folio order to 2048 blocks to prevent overestimation
> + * of reserve handle credits during the folio writeback in environments
> + * where the PAGE_SIZE exceeds 4KB.
> + */
> +#define EXT4_MAX_PAGECACHE_ORDER(i) \
> + min(MAX_PAGECACHE_ORDER, (11 + (i)->i_blkbits - PAGE_SHIFT))
> +void ext4_set_inode_mapping_order(struct inode *inode)
> +{
> + if (!ext4_should_enable_large_folio(inode))
> + return;
> +
> + mapping_set_folio_order_range(inode->i_mapping, 0,
> + EXT4_MAX_PAGECACHE_ORDER(inode));
> +}
> +
> struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ext4_iget_flags flags, const char *function,
> unsigned int line)
> @@ -5515,8 +5531,8 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
> ret = -EFSCORRUPTED;
> goto bad_inode;
> }
> - if (ext4_should_enable_large_folio(inode))
> - mapping_set_large_folios(inode->i_mapping);
> +
> + ext4_set_inode_mapping_order(inode);
>
> ret = check_igot_inode(inode, flags, function, line);
> /*
> --
> 2.46.1
>
--
Jan Kara <jack@suse.com>
SUSE Labs, CR
© 2016 - 2025 Red Hat, Inc.