From: Ross Zwisler <[email protected]>
If the refcount of a page is lowered between the time that it is returned
by dax_busy_page() and when the refcount is again checked in
ext4_break_layouts() => ___wait_var_event(), the waiting function
ext4_wait_dax_page() will never be called. This means that
ext4_break_layouts() will still have 'retry' set to false, so we'll stop
looping and never check the refcount of other pages in this inode.
Instead, always continue looping as long as dax_layout_busy_page() gives us
a page which it found with an elevated refcount.
Note that this works around the race exposed by my unit test, but I think
that there is another race that needs to be addressed, probably with
additional synchronization added between direct I/O and
{ext4,xfs}_break_layouts().
Signed-off-by: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/[email protected]>
Reviewed-by: Jan Kara <[email protected]>
---
fs/ext4/inode.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8f6ad7667974..d2663a1e3ec2 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4191,9 +4191,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
return 0;
}
-static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+static void ext4_wait_dax_page(struct ext4_inode_info *ei)
{
- *did_unlock = true;
up_write(&ei->i_mmap_sem);
schedule();
down_write(&ei->i_mmap_sem);
@@ -4203,14 +4202,12 @@ int ext4_break_layouts(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct page *page;
- bool retry;
int error;
if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
return -EINVAL;
do {
- retry = false;
page = dax_layout_busy_page(inode->i_mapping);
if (!page)
return 0;
@@ -4218,8 +4215,8 @@ int ext4_break_layouts(struct inode *inode)
error = ___wait_var_event(&page->_refcount,
atomic_read(&page->_refcount) == 1,
TASK_INTERRUPTIBLE, 0, 0,
- ext4_wait_dax_page(ei, &retry));
- } while (error == 0 && retry);
+ ext4_wait_dax_page(ei));
+ } while (error == 0);
return error;
}
On Tue 07-08-18 15:11:37, Dave Jiang wrote:
> From: Ross Zwisler <[email protected]>
>
> If the refcount of a page is lowered between the time that it is returned
> by dax_busy_page() and when the refcount is again checked in
> ext4_break_layouts() => ___wait_var_event(), the waiting function
> ext4_wait_dax_page() will never be called. This means that
> ext4_break_layouts() will still have 'retry' set to false, so we'll stop
> looping and never check the refcount of other pages in this inode.
>
> Instead, always continue looping as long as dax_layout_busy_page() gives us
> a page which it found with an elevated refcount.
>
> Note that this works around the race exposed by my unit test, but I think
> that there is another race that needs to be addressed, probably with
> additional synchronization added between direct I/O and
> {ext4,xfs}_break_layouts().
I'd just note that the race Ross suspected should be properly handled by
dax_layout_busy_page() so I think this last paragraph from the changelog
can go.
Also Ted, this fixes a problem in the DAX truncate patches you currently
carry in your tree so you can consider just pushing it with them during the
merge window. It's not necessary though - the patches already make the
problematic behavior much less likely, this patch just hopefully completely
closes the race window.
> Signed-off-by: Ross Zwisler <ross.zwisler-VuQAYsv1563Yd54FQh9/[email protected]>
> Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/ext4/inode.c | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 8f6ad7667974..d2663a1e3ec2 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -4191,9 +4191,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
> return 0;
> }
>
> -static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
> +static void ext4_wait_dax_page(struct ext4_inode_info *ei)
> {
> - *did_unlock = true;
> up_write(&ei->i_mmap_sem);
> schedule();
> down_write(&ei->i_mmap_sem);
> @@ -4203,14 +4202,12 @@ int ext4_break_layouts(struct inode *inode)
> {
> struct ext4_inode_info *ei = EXT4_I(inode);
> struct page *page;
> - bool retry;
> int error;
>
> if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
> return -EINVAL;
>
> do {
> - retry = false;
> page = dax_layout_busy_page(inode->i_mapping);
> if (!page)
> return 0;
> @@ -4218,8 +4215,8 @@ int ext4_break_layouts(struct inode *inode)
> error = ___wait_var_event(&page->_refcount,
> atomic_read(&page->_refcount) == 1,
> TASK_INTERRUPTIBLE, 0, 0,
> - ext4_wait_dax_page(ei, &retry));
> - } while (error == 0 && retry);
> + ext4_wait_dax_page(ei));
> + } while (error == 0);
>
> return error;
> }
>
--
Jan Kara <jack-IBi9RG/[email protected]>
SUSE Labs, CR