* [PATCH] fs/dcache: optimize start_dir_add()
@ 2020-10-22 21:16 Davidlohr Bueso
2020-10-26 21:59 ` Dave Chinner
0 siblings, 1 reply; 3+ messages in thread
From: Davidlohr Bueso @ 2020-10-22 21:16 UTC (permalink / raw)
To: viro
Cc: akpm, peterz, linux-fsdevel, linux-kernel, Davidlohr Bueso,
Davidlohr Bueso
Considering both end_dir_add() and d_alloc_parallel(), the
dir->i_dir_seq wants acquire/release semantics, therefore
micro-optimize for ll/sc archs and use finer grained barriers
to provide (load)-ACQUIRE ordering (L->S + L->L). This comes
at no additional cost for most of x86, as sane tso models will
have a nop for smp_rmb/smp_acquire__after_ctrl_dep.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
Alternatively I guess we could just use cmpxchg_acquire().
fs/dcache.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index ea0485861d93..22738daccb9c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2502,13 +2502,18 @@ EXPORT_SYMBOL(d_rehash);
static inline unsigned start_dir_add(struct inode *dir)
{
+ unsigned n;
for (;;) {
- unsigned n = dir->i_dir_seq;
- if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
- return n;
+ n = READ_ONCE(dir->i_dir_seq);
+ if (!(n & 1) && cmpxchg_relaxed(&dir->i_dir_seq, n, n + 1) == n)
+ break;
cpu_relax();
}
+
+ /* create (load)-ACQUIRE ordering */
+ smp_acquire__after_ctrl_dep();
+ return n;
}
static inline void end_dir_add(struct inode *dir, unsigned n)
--
2.26.2
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] fs/dcache: optimize start_dir_add()
2020-10-22 21:16 [PATCH] fs/dcache: optimize start_dir_add() Davidlohr Bueso
@ 2020-10-26 21:59 ` Dave Chinner
2020-10-29 19:07 ` [PATCH v2] " Davidlohr Bueso
0 siblings, 1 reply; 3+ messages in thread
From: Dave Chinner @ 2020-10-26 21:59 UTC (permalink / raw)
To: Davidlohr Bueso
Cc: viro, akpm, peterz, linux-fsdevel, linux-kernel, Davidlohr Bueso
On Thu, Oct 22, 2020 at 02:16:50PM -0700, Davidlohr Bueso wrote:
> Considering both end_dir_add() and d_alloc_parallel(), the
> dir->i_dir_seq wants acquire/release semantics, therefore
> micro-optimize for ll/sc archs and use finer grained barriers
> to provide (load)-ACQUIRE ordering (L->S + L->L). This comes
> at no additional cost for most of x86, as sane tso models will
> have a nop for smp_rmb/smp_acquire__after_ctrl_dep.
>
> Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
> ---
> Alternatively I guess we could just use cmpxchg_acquire().
Please us cmpxchg_acquire() so that people who have no clue what the
hell smp_acquire__after_ctrl_dep() means or does have some hope of
understanding of what objects the ordering semantics in the function
actually apply to....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
^ permalink raw reply [flat|nested] 3+ messages in thread
* [PATCH v2] fs/dcache: optimize start_dir_add()
2020-10-26 21:59 ` Dave Chinner
@ 2020-10-29 19:07 ` Davidlohr Bueso
0 siblings, 0 replies; 3+ messages in thread
From: Davidlohr Bueso @ 2020-10-29 19:07 UTC (permalink / raw)
To: Dave Chinner
Cc: viro, akpm, peterz, linux-fsdevel, linux-kernel, Davidlohr Bueso
Considering both end_dir_add() and d_alloc_parallel(), the
dir->i_dir_seq wants acquire/release semantics, therefore
micro-optimize for ll/sc archs. Also add READ_ONCE around
the variable mostly for documentation purposes - either
the successful cmpxchg or the pause will avoid the tearing).
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
fs/dcache.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/dcache.c b/fs/dcache.c
index ea0485861d93..9177f0d08a5a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2504,8 +2504,8 @@ static inline unsigned start_dir_add(struct inode *dir)
{
for (;;) {
- unsigned n = dir->i_dir_seq;
- if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+ unsigned n = READ_ONCE(dir->i_dir_seq);
+ if (!(n & 1) && cmpxchg_acquire(&dir->i_dir_seq, n, n + 1) == n)
return n;
cpu_relax();
}
--
2.26.2
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-10-29 19:29 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-10-22 21:16 [PATCH] fs/dcache: optimize start_dir_add() Davidlohr Bueso
2020-10-26 21:59 ` Dave Chinner
2020-10-29 19:07 ` [PATCH v2] " Davidlohr Bueso
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).