[PATCH 1/2] percpu: Add __this_cpu_try_cmpxchg()

[PATCH 1/2] percpu: Add __this_cpu_try_cmpxchg()

[Uros Bizjak]

Add __this_cpu_try_cmpxchg() version of the percpu op.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
---
 include/linux/percpu-defs.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ec3573119923..8efce7414fad 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -475,6 +475,12 @@ do {									\
 	raw_cpu_cmpxchg(pcp, oval, nval);				\
 })
 
+#define __this_cpu_try_cmpxchg(pcp, ovalp, nval)			\
+({									\
+	__this_cpu_preempt_check("try_cmpxchg");			\
+	raw_cpu_try_cmpxchg(pcp, ovalp, nval);				\
+})
+
 #define __this_cpu_sub(pcp, val)	__this_cpu_add(pcp, -(typeof(pcp))(val))
 #define __this_cpu_inc(pcp)		__this_cpu_add(pcp, 1)
 #define __this_cpu_dec(pcp)		__this_cpu_sub(pcp, 1)
-- 
2.45.1

[PATCH 2/2] mm/vmalloc: Use __this_cpu_try_cmpxchg() in preload_this_cpu_lock()

[Uros Bizjak]

Use __this_cpu_try_cmpxchg() instead of
__this_cpu_cmpxchg (*ptr, old, new) == old in
preload_this_cpu_lock().  x86 CMPXCHG instruction returns
success in ZF flag, so this change saves a compare after cmpxchg.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
---
 mm/vmalloc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6641be0ca80b..0120faee5471 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1816,7 +1816,7 @@ static void free_vmap_area(struct vmap_area *va)
 static inline void
 preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
 {
-	struct vmap_area *va = NULL;
+	struct vmap_area *va = NULL, *tmp;
 
 	/*
 	 * Preload this CPU with one extra vmap_area object. It is used
@@ -1832,7 +1832,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node)
 
 	spin_lock(lock);
 
-	if (va && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, va))
+	tmp = NULL;
+	if (va && !__this_cpu_try_cmpxchg(ne_fit_preload_node, &tmp, va))
 		kmem_cache_free(vmap_area_cachep, va);
 }
 
-- 
2.45.1

Re: [PATCH 2/2] mm/vmalloc: Use __this_cpu_try_cmpxchg() in preload_this_cpu_lock()

[Uladzislau Rezki]

> Use __this_cpu_try_cmpxchg() instead of
> __this_cpu_cmpxchg (*ptr, old, new) == old in
> preload_this_cpu_lock().  x86 CMPXCHG instruction returns
> success in ZF flag, so this change saves a compare after cmpxchg.
> 
Just a small note. Can you also add a tiny difference in assembly
language where it is visible? I mean update a commit message.

--
Uladzislau Rezki