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@xxxxxxx>
---
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
