linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vlastimil Babka <vbabka@suse.cz>
To: linux-mm@kvack.org, Christoph Lameter <cl@linux.com>,
	David Rientjes <rientjes@google.com>,
	Pekka Enberg <penberg@kernel.org>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org, Mike Galbraith <efault@gmx.de>,
	Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	Mel Gorman <mgorman@techsingularity.net>,
	Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH v6 28/33] mm: slub: move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context
Date: Sat,  4 Sep 2021 12:49:58 +0200	[thread overview]
Message-ID: <20210904105003.11688-29-vbabka@suse.cz> (raw)
In-Reply-To: <20210904105003.11688-1-vbabka@suse.cz>

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

flush_all() flushes a specific SLAB cache on each CPU (where the cache
is present). The deactivate_slab()/__free_slab() invocation happens
within IPI handler and is problematic for PREEMPT_RT.

The flush operation is not a frequent operation or a hot path. The
per-CPU flush operation can be moved to within a workqueue.

Because a workqueue handler, unlike IPI handler, does not disable irqs,
flush_slab() now has to disable them for working with the kmem_cache_cpu
fields. deactivate_slab() is safe to call with irqs enabled.

[vbabka@suse.cz: adapt to new SLUB changes]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c |  2 ++
 mm/slub.c        | 94 +++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 80 insertions(+), 16 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 1c673c323baf..ec2bb0beed75 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -502,6 +502,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	if (unlikely(!s))
 		return;
 
+	cpus_read_lock();
 	mutex_lock(&slab_mutex);
 
 	s->refcount--;
@@ -516,6 +517,7 @@ void kmem_cache_destroy(struct kmem_cache *s)
 	}
 out_unlock:
 	mutex_unlock(&slab_mutex);
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
diff --git a/mm/slub.c b/mm/slub.c
index fa9a366d2d9c..b7f8b9d34e46 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2496,16 +2496,25 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
-	void *freelist = c->freelist;
-	struct page *page = c->page;
+	unsigned long flags;
+	struct page *page;
+	void *freelist;
+
+	local_irq_save(flags);
+
+	page = c->page;
+	freelist = c->freelist;
 
 	c->page = NULL;
 	c->freelist = NULL;
 	c->tid = next_tid(c->tid);
 
-	deactivate_slab(s, page, freelist);
+	local_irq_restore(flags);
 
-	stat(s, CPUSLAB_FLUSH);
+	if (page) {
+		deactivate_slab(s, page, freelist);
+		stat(s, CPUSLAB_FLUSH);
+	}
 }
 
 static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
@@ -2526,15 +2535,27 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 	unfreeze_partials_cpu(s, c);
 }
 
+struct slub_flush_work {
+	struct work_struct work;
+	struct kmem_cache *s;
+	bool skip;
+};
+
 /*
  * Flush cpu slab.
  *
- * Called from IPI handler with interrupts disabled.
+ * Called from CPU work handler with migration disabled.
  */
-static void flush_cpu_slab(void *d)
+static void flush_cpu_slab(struct work_struct *w)
 {
-	struct kmem_cache *s = d;
-	struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
+	struct kmem_cache *s;
+	struct kmem_cache_cpu *c;
+	struct slub_flush_work *sfw;
+
+	sfw = container_of(w, struct slub_flush_work, work);
+
+	s = sfw->s;
+	c = this_cpu_ptr(s->cpu_slab);
 
 	if (c->page)
 		flush_slab(s, c);
@@ -2542,17 +2563,51 @@ static void flush_cpu_slab(void *d)
 	unfreeze_partials(s);
 }
 
-static bool has_cpu_slab(int cpu, void *info)
+static bool has_cpu_slab(int cpu, struct kmem_cache *s)
 {
-	struct kmem_cache *s = info;
 	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
 	return c->page || slub_percpu_partial(c);
 }
 
+static DEFINE_MUTEX(flush_lock);
+static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
+
+static void flush_all_cpus_locked(struct kmem_cache *s)
+{
+	struct slub_flush_work *sfw;
+	unsigned int cpu;
+
+	lockdep_assert_cpus_held();
+	mutex_lock(&flush_lock);
+
+	for_each_online_cpu(cpu) {
+		sfw = &per_cpu(slub_flush, cpu);
+		if (!has_cpu_slab(cpu, s)) {
+			sfw->skip = true;
+			continue;
+		}
+		INIT_WORK(&sfw->work, flush_cpu_slab);
+		sfw->skip = false;
+		sfw->s = s;
+		schedule_work_on(cpu, &sfw->work);
+	}
+
+	for_each_online_cpu(cpu) {
+		sfw = &per_cpu(slub_flush, cpu);
+		if (sfw->skip)
+			continue;
+		flush_work(&sfw->work);
+	}
+
+	mutex_unlock(&flush_lock);
+}
+
 static void flush_all(struct kmem_cache *s)
 {
-	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
+	cpus_read_lock();
+	flush_all_cpus_locked(s);
+	cpus_read_unlock();
 }
 
 /*
@@ -4097,7 +4152,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 	int node;
 	struct kmem_cache_node *n;
 
-	flush_all(s);
+	flush_all_cpus_locked(s);
 	/* Attempt to free all objects */
 	for_each_kmem_cache_node(s, node, n) {
 		free_partial(s, n);
@@ -4373,7 +4428,7 @@ EXPORT_SYMBOL(kfree);
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+static int __kmem_cache_do_shrink(struct kmem_cache *s)
 {
 	int node;
 	int i;
@@ -4385,7 +4440,6 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	unsigned long flags;
 	int ret = 0;
 
-	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
 		INIT_LIST_HEAD(&discard);
 		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
@@ -4435,13 +4489,21 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 	return ret;
 }
 
+int __kmem_cache_shrink(struct kmem_cache *s)
+{
+	flush_all(s);
+	return __kmem_cache_do_shrink(s);
+}
+
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+	list_for_each_entry(s, &slab_caches, list) {
+		flush_all_cpus_locked(s);
+		__kmem_cache_do_shrink(s);
+	}
 	mutex_unlock(&slab_mutex);
 
 	return 0;
-- 
2.33.0


  parent reply	other threads:[~2021-09-04 10:51 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-04 10:49 [PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 01/33] mm, slub: don't call flush_all() from slab_debug_trace_open() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 02/33] mm, slub: allocate private object map for debugfs listings Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 03/33] mm, slub: allocate private object map for validate_slab_cache() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 04/33] mm, slub: don't disable irq for debug_check_no_locks_freed() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 05/33] mm, slub: remove redundant unfreeze_partials() from put_cpu_partial() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 06/33] mm, slub: extract get_partial() from new_slab_objects() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 07/33] mm, slub: dissolve new_slab_objects() into ___slab_alloc() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 08/33] mm, slub: return slab page from get_partial() and set c->page afterwards Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 09/33] mm, slub: restructure new page checks in ___slab_alloc() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 10/33] mm, slub: simplify kmem_cache_cpu and tid setup Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 11/33] mm, slub: move disabling/enabling irqs to ___slab_alloc() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 12/33] mm, slub: do initial checks in ___slab_alloc() with irqs enabled Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 13/33] mm, slub: move disabling irqs closer to get_partial() in ___slab_alloc() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 14/33] mm, slub: restore irqs around calling new_slab() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 15/33] mm, slub: validate slab from partial list or page allocator before making it cpu slab Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 16/33] mm, slub: check new pages with restored irqs Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 17/33] mm, slub: stop disabling irqs around get_partial() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 18/33] mm, slub: move reset of c->page and freelist out of deactivate_slab() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 19/33] mm, slub: make locking in deactivate_slab() irq-safe Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 20/33] mm, slub: call deactivate_slab() without disabling irqs Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 21/33] mm, slub: move irq control into unfreeze_partials() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 22/33] mm, slub: discard slabs in unfreeze_partials() without irqs disabled Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 23/33] mm, slub: detach whole partial list at once in unfreeze_partials() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 24/33] mm, slub: separate detaching of partial list in unfreeze_partials() from unfreezing Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 25/33] mm, slub: only disable irq with spin_lock in __unfreeze_partials() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 26/33] mm, slub: don't disable irqs in slub_cpu_dead() Vlastimil Babka
2021-09-04 10:49 ` [PATCH v6 27/33] mm, slab: split out the cpu offline variant of flush_slab() Vlastimil Babka
2021-09-04 10:49 ` Vlastimil Babka [this message]
2021-09-04 10:49 ` [PATCH v6 29/33] mm: slub: make object_map_lock a raw_spinlock_t Vlastimil Babka
2021-09-04 10:50 ` [PATCH v6 30/33] mm, slub: make slab_lock() disable irqs with PREEMPT_RT Vlastimil Babka
2021-09-04 10:50 ` [PATCH v6 31/33] mm, slub: protect put_cpu_partial() with disabled irqs instead of cmpxchg Vlastimil Babka
2021-09-04 10:50 ` [PATCH v6 32/33] mm, slub: use migrate_disable() on PREEMPT_RT Vlastimil Babka
2021-09-04 10:50 ` [PATCH v6 33/33] mm, slub: convert kmem_cpu_slab protection to local_lock Vlastimil Babka
2021-09-05 14:16 ` [PATCH v6 00/33] SLUB: reduce irq disabled scope and make it RT compatible Mike Galbraith
2021-09-07  8:20 ` Mel Gorman

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=20210904105003.11688-29-vbabka@suse.cz \
    --to=vbabka@suse.cz \
    --cc=akpm@linux-foundation.org \
    --cc=bigeasy@linutronix.de \
    --cc=cl@linux.com \
    --cc=efault@gmx.de \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=penberg@kernel.org \
    --cc=rientjes@google.com \
    --cc=tglx@linutronix.de \
    --subject='Re: [PATCH v6 28/33] mm: slub: move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).