Call stack :
f2fs_write_checkpoint()
-> block_operations(sbi)
f2fs_lock_all(sbi);
down_write(&sbi->cp_rwsem); => write lock held
<>
-> f2fs_sync_node_pages()
if (is_inline_node(page))
flush_inline_data()
page = f2fs_pagecache_get_page()
if (!page)
goto iput_out;
iput_out:
iput(inode);
-> f2fs_evict_inode()
f2fs_truncate_blocks()
f2fs_lock_op()
down_read(&sbi->cp_rwsem); => read lock fail
Signed-off-by: Sayali Lokhande <[email protected]>
---
fs/f2fs/checkpoint.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 5ba649e..5c504cf 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1219,21 +1219,19 @@ static int block_operations(struct f2fs_sb_info *sbi)
goto retry_flush_quotas;
}
-retry_flush_nodes:
down_write(&sbi->node_write);
if (get_pages(sbi, F2FS_DIRTY_NODES)) {
up_write(&sbi->node_write);
+ f2fs_unlock_all(sbi);
atomic_inc(&sbi->wb_sync_req[NODE]);
err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
atomic_dec(&sbi->wb_sync_req[NODE]);
- if (err) {
- up_write(&sbi->node_change);
- f2fs_unlock_all(sbi);
+ up_write(&sbi->node_change);
+ if (err)
goto out;
- }
cond_resched();
- goto retry_flush_nodes;
+ goto retry_flush_quotas;
}
/*
--
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
a Linux Foundation Collaborative Project
Hi Sayali,
On 2020-4-23 18:13, Sayali Lokhande wrote:
> Call stack :
> f2fs_write_checkpoint()
> -> block_operations(sbi)
> f2fs_lock_all(sbi);
> down_write(&sbi->cp_rwsem); => write lock held
> <>
It looks the full race condition should be?
Thread B
- open()
- igrab()
- write() write inline data
- unlink()
> -> f2fs_sync_node_pages()
> if (is_inline_node(page))
> flush_inline_data()
ilookup()
> page = f2fs_pagecache_get_page()
> if (!page)
> goto iput_out;
> iput_out:
- close()
- iput()
> iput(inode);
> -> f2fs_evict_inode()
> f2fs_truncate_blocks()
> f2fs_lock_op()
> down_read(&sbi->cp_rwsem); => read lock fail
>
> Signed-off-by: Sayali Lokhande <[email protected]>
> ---
> fs/f2fs/checkpoint.c | 10 ++++------
> 1 file changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> index 5ba649e..5c504cf 100644
> --- a/fs/f2fs/checkpoint.c
> +++ b/fs/f2fs/checkpoint.c
> @@ -1219,21 +1219,19 @@ static int block_operations(struct f2fs_sb_info *sbi)
> goto retry_flush_quotas;
> }
>
> -retry_flush_nodes:
> down_write(&sbi->node_write);
>
> if (get_pages(sbi, F2FS_DIRTY_NODES)) {
> up_write(&sbi->node_write);
Call up_write(&sbi->node_change) here could wake up threads earlier who hang on
this lock, how do you think?
Thanks,
> + f2fs_unlock_all(sbi);
> atomic_inc(&sbi->wb_sync_req[NODE]);
> err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
> atomic_dec(&sbi->wb_sync_req[NODE]);
> - if (err) {
> - up_write(&sbi->node_change);
> - f2fs_unlock_all(sbi);
> + up_write(&sbi->node_change);
> + if (err)
> goto out;
> - }
> cond_resched();
> - goto retry_flush_nodes;
> + goto retry_flush_quotas;
> }
>
> /*
>
On 04/23, Sayali Lokhande wrote:
> Call stack :
> f2fs_write_checkpoint()
> -> block_operations(sbi)
> f2fs_lock_all(sbi);
> down_write(&sbi->cp_rwsem); => write lock held
> <>
> -> f2fs_sync_node_pages()
> if (is_inline_node(page))
> flush_inline_data()
> page = f2fs_pagecache_get_page()
> if (!page)
> goto iput_out;
> iput_out:
> iput(inode);
> -> f2fs_evict_inode()
> f2fs_truncate_blocks()
> f2fs_lock_op()
> down_read(&sbi->cp_rwsem); => read lock fail
How about this, since we don't actually need to flush inline_data?
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 4da0d8713df5c..9af8d5319fdd3 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -1871,7 +1871,7 @@ int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
}
/* flush inline_data */
- if (is_inline_node(page)) {
+ if (is_inline_node(page) && io_type != FS_CP_NODE_IO) {
clear_inline_node(page);
unlock_page(page);
flush_inline_data(sbi, ino_of_node(page));
>
> Signed-off-by: Sayali Lokhande <[email protected]>
> ---
> fs/f2fs/checkpoint.c | 10 ++++------
> 1 file changed, 4 insertions(+), 6 deletions(-)
>
> diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> index 5ba649e..5c504cf 100644
> --- a/fs/f2fs/checkpoint.c
> +++ b/fs/f2fs/checkpoint.c
> @@ -1219,21 +1219,19 @@ static int block_operations(struct f2fs_sb_info *sbi)
> goto retry_flush_quotas;
> }
>
> -retry_flush_nodes:
> down_write(&sbi->node_write);
>
> if (get_pages(sbi, F2FS_DIRTY_NODES)) {
> up_write(&sbi->node_write);
> + f2fs_unlock_all(sbi);
> atomic_inc(&sbi->wb_sync_req[NODE]);
> err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
> atomic_dec(&sbi->wb_sync_req[NODE]);
> - if (err) {
> - up_write(&sbi->node_change);
> - f2fs_unlock_all(sbi);
> + up_write(&sbi->node_change);
> + if (err)
> goto out;
> - }
> cond_resched();
> - goto retry_flush_nodes;
> + goto retry_flush_quotas;
> }
>
> /*
> --
> The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
> a Linux Foundation Collaborative Project
On 04/23, Jaegeuk Kim wrote:
> On 04/23, Sayali Lokhande wrote:
> > Call stack :
> > f2fs_write_checkpoint()
> > -> block_operations(sbi)
> > f2fs_lock_all(sbi);
> > down_write(&sbi->cp_rwsem); => write lock held
> > <>
> > -> f2fs_sync_node_pages()
> > if (is_inline_node(page))
> > flush_inline_data()
> > page = f2fs_pagecache_get_page()
> > if (!page)
> > goto iput_out;
> > iput_out:
> > iput(inode);
> > -> f2fs_evict_inode()
> > f2fs_truncate_blocks()
> > f2fs_lock_op()
> > down_read(&sbi->cp_rwsem); => read lock fail
>
> How about this, since we don't actually need to flush inline_data?
Hmm, nvm. This causes no space panic regressed during xfstests.
>
> diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
> index 4da0d8713df5c..9af8d5319fdd3 100644
> --- a/fs/f2fs/node.c
> +++ b/fs/f2fs/node.c
> @@ -1871,7 +1871,7 @@ int f2fs_sync_node_pages(struct f2fs_sb_info *sbi,
> }
>
> /* flush inline_data */
> - if (is_inline_node(page)) {
> + if (is_inline_node(page) && io_type != FS_CP_NODE_IO) {
> clear_inline_node(page);
> unlock_page(page);
> flush_inline_data(sbi, ino_of_node(page));
>
> >
> > Signed-off-by: Sayali Lokhande <[email protected]>
> > ---
> > fs/f2fs/checkpoint.c | 10 ++++------
> > 1 file changed, 4 insertions(+), 6 deletions(-)
> >
> > diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
> > index 5ba649e..5c504cf 100644
> > --- a/fs/f2fs/checkpoint.c
> > +++ b/fs/f2fs/checkpoint.c
> > @@ -1219,21 +1219,19 @@ static int block_operations(struct f2fs_sb_info *sbi)
> > goto retry_flush_quotas;
> > }
> >
> > -retry_flush_nodes:
> > down_write(&sbi->node_write);
> >
> > if (get_pages(sbi, F2FS_DIRTY_NODES)) {
> > up_write(&sbi->node_write);
> > + f2fs_unlock_all(sbi);
> > atomic_inc(&sbi->wb_sync_req[NODE]);
> > err = f2fs_sync_node_pages(sbi, &wbc, false, FS_CP_NODE_IO);
> > atomic_dec(&sbi->wb_sync_req[NODE]);
> > - if (err) {
> > - up_write(&sbi->node_change);
> > - f2fs_unlock_all(sbi);
> > + up_write(&sbi->node_change);
> > + if (err)
> > goto out;
> > - }
> > cond_resched();
> > - goto retry_flush_nodes;
> > + goto retry_flush_quotas;
> > }
> >
> > /*
> > --
> > The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
> > a Linux Foundation Collaborative Project
>
>
> _______________________________________________
> Linux-f2fs-devel mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/linux-f2fs-devel