Re: [PATCH 1/3] mm/slub: directly load freelist from cpu partial slab in the likely case

[Chengming Zhou]

On 2024/1/19 06:14, Christoph Lameter (Ampere) wrote:
> On Thu, 18 Jan 2024, Chengming Zhou wrote:
> 
>> So get_freelist() has two cases to handle: cpu slab and cpu partial list slab.
>> The latter is NOT frozen, so need to remove "VM_BUG_ON(!new.frozen)" from it.
> 
> Right so keep the check if it is the former?
> 

Ok, I get it. Maybe like this:

diff --git a/mm/slub.c b/mm/slub.c
index 2ef88bbf56a3..7fa9dbc2e938 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3313,7 +3313,7 @@ __update_cpu_freelist_fast(struct kmem_cache *s,
  *
  * If this function returns NULL then the slab has been unfrozen.
  */
-static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
+static inline void *get_freelist(struct kmem_cache *s, struct slab *slab, int frozen)
 {
        struct slab new;
        unsigned long counters;
@@ -3326,7 +3326,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
                counters = slab->counters;

                new.counters = counters;
-               VM_BUG_ON(!new.frozen);
+               VM_BUG_ON(frozen && !new.frozen);

                new.inuse = slab->objects;
                new.frozen = freelist != NULL;
@@ -3440,7 +3440,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
        if (freelist)
                goto load_freelist;

-       freelist = get_freelist(s, slab);
+       freelist = get_freelist(s, slab, 1);

        if (!freelist) {
                c->slab = NULL;
@@ -3498,18 +3498,19 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,

                slab = slub_percpu_partial(c);
                slub_set_percpu_partial(c, slab);
-               local_unlock_irqrestore(&s->cpu_slab->lock, flags);
-               stat(s, CPU_PARTIAL_ALLOC);

-               if (unlikely(!node_match(slab, node) ||
-                            !pfmemalloc_match(slab, gfpflags))) {
-                       slab->next = NULL;
-                       __put_partials(s, slab);
-                       continue;
+               if (likely(node_match(slab, node) &&
+                          pfmemalloc_match(slab, gfpflags))) {
+                       c->slab = slab;
+                       freelist = get_freelist(s, slab, 0);
+                       stat(s, CPU_PARTIAL_ALLOC);
+                       goto load_freelist;
                }

-               freelist = freeze_slab(s, slab);
-               goto retry_load_slab;
+               local_unlock_irqrestore(&s->cpu_slab->lock, flags);
+
+               slab->next = NULL;
+               __put_partials(s, slab);
        }
 #endif