linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: chengming.zhou@linux.dev
To: cl@linux.com, penberg@kernel.org
Cc: rientjes@google.com, iamjoonsoo.kim@lge.com,
	akpm@linux-foundation.org, vbabka@suse.cz,
	roman.gushchin@linux.dev, 42.hyeyoo@gmail.com,
	willy@infradead.org, pcc@google.com, tytso@mit.edu,
	maz@kernel.org, ruansy.fnst@fujitsu.com, vishal.moola@gmail.com,
	lrh2000@pku.edu.cn, hughd@google.com,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	chengming.zhou@linux.dev,
	Chengming Zhou <zhouchengming@bytedance.com>
Subject: [RFC PATCH v2 5/6] slub: Introduce get_cpu_partial()
Date: Sat, 21 Oct 2023 14:43:16 +0000	[thread overview]
Message-ID: <20231021144317.3400916-6-chengming.zhou@linux.dev> (raw)
In-Reply-To: <20231021144317.3400916-1-chengming.zhou@linux.dev>

From: Chengming Zhou <zhouchengming@bytedance.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@bytedance.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



  parent reply	other threads:[~2023-10-21 14:44 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-21 14:43 [RFC PATCH v2 0/6] slub: Delay freezing of CPU partial slabs chengming.zhou
2023-10-21 14:43 ` [RFC PATCH v2 1/6] slub: Keep track of whether slub is on the per-node partial list chengming.zhou
2023-10-23 12:32   ` Matthew Wilcox
2023-10-23 16:22     ` Matthew Wilcox
2023-10-24  1:57       ` Chengming Zhou
2023-10-21 14:43 ` [RFC PATCH v2 2/6] slub: Prepare __slab_free() for unfrozen partial slab out of node " chengming.zhou
2023-10-21 14:43 ` [RFC PATCH v2 3/6] slub: Don't freeze slabs for cpu partial chengming.zhou
2023-10-23 16:00   ` Vlastimil Babka
2023-10-24  2:39     ` Chengming Zhou
2023-10-21 14:43 ` [RFC PATCH v2 4/6] slub: Simplify acquire_slab() chengming.zhou
2023-10-21 14:43 ` chengming.zhou [this message]
2023-10-21 14:43 ` [RFC PATCH v2 6/6] slub: Optimize deactivate_slab() chengming.zhou
2023-10-22 14:52 ` [RFC PATCH v2 0/6] slub: Delay freezing of CPU partial slabs Hyeonggon Yoo
2023-10-24  2:02   ` Chengming Zhou
2023-10-23 15:46 ` Vlastimil Babka
2023-10-23 17:00   ` Christoph Lameter (Ampere)
2023-10-23 18:44     ` Vlastimil Babka
2023-10-23 21:05       ` Christoph Lameter (Ampere)
2023-10-24  8:19         ` Vlastimil Babka
2023-10-24 11:03         ` Chengming Zhou
2023-10-24  2:20   ` Chengming Zhou
2023-10-24  8:20     ` Vlastimil Babka

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20231021144317.3400916-6-chengming.zhou@linux.dev \
    --to=chengming.zhou@linux.dev \
    --cc=42.hyeyoo@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux.com \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lrh2000@pku.edu.cn \
    --cc=maz@kernel.org \
    --cc=pcc@google.com \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=roman.gushchin@linux.dev \
    --cc=ruansy.fnst@fujitsu.com \
    --cc=tytso@mit.edu \
    --cc=vbabka@suse.cz \
    --cc=vishal.moola@gmail.com \
    --cc=willy@infradead.org \
    --cc=zhouchengming@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox