linux-kernel - [RFC PATCH v2 5/6] slub: Introduce get_cpu

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20231021144317.3400916-6-chengming.zhou@linux.dev>
Date:   Sat, 21 Oct 2023 14:43:16 +0000
From:   chengming.zhou@...ux.dev
To:     cl@...ux.com, penberg@...nel.org
Cc:     rientjes@...gle.com, iamjoonsoo.kim@....com,
        akpm@...ux-foundation.org, vbabka@...e.cz,
        roman.gushchin@...ux.dev, 42.hyeyoo@...il.com, willy@...radead.org,
        pcc@...gle.com, tytso@....edu, maz@...nel.org,
        ruansy.fnst@...itsu.com, vishal.moola@...il.com,
        lrh2000@....edu.cn, hughd@...gle.com, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, chengming.zhou@...ux.dev,
        Chengming Zhou <zhouchengming@...edance.com>
Subject: [RFC PATCH v2 5/6] slub: Introduce get_cpu_partial()

From: Chengming Zhou <zhouchengming@...edance.com>

Since the slabs on cpu partial list are not frozen anymore, we introduce
get_cpu_partial() to get a frozen slab with its freelist from cpu partial
list. It's now much like getting a frozen slab with its freelist from
node partial list.

Another change is about get_partial(), which can return no frozen slab
when all slabs are failed when acquire_slab(), but get some unfreeze slabs
in its cpu partial list, so we need to check this rare case to avoid
allocating a new slab.

Signed-off-by: Chengming Zhou <zhouchengming@...edance.com>
---
 mm/slub.c | 87 +++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 68 insertions(+), 19 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 9f0b80fefc70..7fae959c56eb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3055,6 +3055,68 @@ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
 	return freelist;
 }
 
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+
+static void *get_cpu_partial(struct kmem_cache *s, struct kmem_cache_cpu *c,
+			     struct slab **slabptr, int node, gfp_t gfpflags)
+{
+	unsigned long flags;
+	struct slab *slab;
+	struct slab new;
+	unsigned long counters;
+	void *freelist;
+
+	while (slub_percpu_partial(c)) {
+		local_lock_irqsave(&s->cpu_slab->lock, flags);
+		if (unlikely(!slub_percpu_partial(c))) {
+			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
+			/* we were preempted and partial list got empty */
+			return NULL;
+		}
+
+		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;
+			__unfreeze_partials(s, slab);
+			continue;
+		}
+
+		do {
+			freelist = slab->freelist;
+			counters = slab->counters;
+
+			new.counters = counters;
+			VM_BUG_ON(new.frozen);
+
+			new.inuse = slab->objects;
+			new.frozen = 1;
+		} while (!__slab_update_freelist(s, slab,
+			freelist, counters,
+			NULL, new.counters,
+			"get_cpu_partial"));
+
+		*slabptr = slab;
+		return freelist;
+	}
+
+	return NULL;
+}
+
+#else /* CONFIG_SLUB_CPU_PARTIAL */
+
+static void *get_cpu_partial(struct kmem_cache *s, struct kmem_cache_cpu *c,
+			     struct slab **slabptr, int node, gfp_t gfpflags)
+{
+	return NULL;
+}
+
+#endif
+
 /*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
@@ -3097,7 +3159,6 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			node = NUMA_NO_NODE;
 		goto new_slab;
 	}
-redo:
 
 	if (unlikely(!node_match(slab, node))) {
 		/*
@@ -3173,24 +3234,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 
 new_slab:
 
-	if (slub_percpu_partial(c)) {
-		local_lock_irqsave(&s->cpu_slab->lock, flags);
-		if (unlikely(c->slab)) {
-			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
-			goto reread_slab;
-		}
-		if (unlikely(!slub_percpu_partial(c))) {
-			local_unlock_irqrestore(&s->cpu_slab->lock, flags);
-			/* we were preempted and partial list got empty */
-			goto new_objects;
-		}
-
-		slab = c->slab = slub_percpu_partial(c);
-		slub_set_percpu_partial(c, slab);
-		local_unlock_irqrestore(&s->cpu_slab->lock, flags);
-		stat(s, CPU_PARTIAL_ALLOC);
-		goto redo;
-	}
+	freelist = get_cpu_partial(s, c, &slab, node, gfpflags);
+	if (freelist)
+		goto retry_load_slab;
 
 new_objects:
 
@@ -3201,6 +3247,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (freelist)
 		goto check_new_slab;
 
+	if (slub_percpu_partial(c))
+		goto new_slab;
+
 	slub_put_cpu_ptr(s->cpu_slab);
 	slab = new_slab(s, gfpflags, node);
 	c = slub_get_cpu_ptr(s->cpu_slab);
-- 
2.20.1