On Wed, Sep 11, 2019 at 11:45:15AM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues
>
> This is similar to 942491c9e6d6 ("xfs: fix AIM7 regression")
> Apparently our current rwsem code doesn't like doing the trylock, then
> lock for real scheme. So change our read/write methods to just
This changes the way we acquire the inode semaphore when
the I/O is marked with IOCB_NOWAIT. The regression was discovered
in AIM7 and later by Andres in ext4. This has been fixed in
XFS by 942491c9e6d6 ("xfs: fix AIM7 regression")
I realized f2fs and btrfs also have the same code and need to
be
From: Goldwyn Rodrigues
This is similar to 942491c9e6d6 ("xfs: fix AIM7 regression")
Apparently our current rwsem code doesn't like doing the trylock, then
lock for real scheme. So change our read/write methods to just do the
trylock for the RWF_NOWAIT case.
Fixes: edf064e7c6fe ("btrfs: nowait
From: Goldwyn Rodrigues
This is similar to 942491c9e6d6 ("xfs: fix AIM7 regression")
Apparently our current rwsem code doesn't like doing the trylock, then
lock for real scheme. So change our read/write methods to just do the
trylock for the RWF_NOWAIT case.
We don't need a check for
From: Goldwyn Rodrigues
This is similar to 942491c9e6d6 ("xfs: fix AIM7 regression")
Apparently our current rwsem code doesn't like doing the trylock, then
lock for real scheme. So change our read/write methods to just do the
trylock for the RWF_NOWAIT case.
Fixes: 728fbc0e10b7 ("ext4: nowait