Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Vlastimil Babka <vbabka@suse.cz>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Christoph Lameter <cl@linux.com>,
        David Rientjes <rientjes@google.com>,
        Pekka Enberg <penberg@kernel.org>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc:     Mike Galbraith <efault@gmx.de>,
        Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
        Thomas Gleixner <tglx@linutronix.de>,
        Mel Gorman <mgorman@techsingularity.net>,
        Jesper Dangaard Brouer <brouer@redhat.com>,
        Jann Horn <jannh@google.com>, Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH v3 34/35] mm, slub: use migrate_disable() on PREEMPT_RT
Date:   Thu, 29 Jul 2021 15:21:31 +0200
Message-Id: <20210729132132.19691-35-vbabka@suse.cz>
In-Reply-To: <20210729132132.19691-1-vbabka@suse.cz>
References: <20210729132132.19691-1-vbabka@suse.cz>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We currently use preempt_disable() (directly or via get_cpu_ptr()) to stabilize
the pointer to kmem_cache_cpu. On PREEMPT_RT this would be incompatible with
the list_lock spinlock. We can use migrate_disable() instead, but that
increases overhead on !PREEMPT_RT as it's an unconditional function call.

In order to get the best available mechanism on both PREEMPT_RT and
!PREEMPT_RT, introduce private slub_get_cpu_ptr() and slub_put_cpu_ptr()
wrappers and use them.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slub.c | 39 ++++++++++++++++++++++++++++++---------
 1 file changed, 30 insertions(+), 9 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 0fd60d9ca27e..91e04e20cf60 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -118,6 +118,26 @@
  * 			the fast path and disables lockless freelists.
  */
 
+/*
+ * We could simply use migrate_disable()/enable() but as long as it's a
+ * function call even on !PREEMPT_RT, use inline preempt_disable() there.
+ */
+#ifndef CONFIG_PREEMPT_RT
+#define slub_get_cpu_ptr(var)	get_cpu_ptr(var)
+#define slub_put_cpu_ptr(var)	put_cpu_ptr(var)
+#else
+#define slub_get_cpu_ptr(var)		\
+({					\
+	migrate_disable();		\
+	this_cpu_ptr(var);		\
+})
+#define slub_put_cpu_ptr(var)		\
+do {					\
+	(void)(var);			\
+	migrate_enable();		\
+} while (0)
+#endif
+
 #ifdef CONFIG_SLUB_DEBUG
 #ifdef CONFIG_SLUB_DEBUG_ON
 DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
@@ -2805,7 +2825,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (unlikely(!pfmemalloc_match(page, gfpflags)))
 		goto deactivate_slab;
 
-	/* must check again c->page in case IRQ handler changed it */
+	/* must check again c->page in case we got preempted and it changed */
 	local_irq_save(flags);
 	if (unlikely(page != c->page)) {
 		local_irq_restore(flags);
@@ -2864,7 +2884,8 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 		}
 		if (unlikely(!slub_percpu_partial(c))) {
 			local_irq_restore(flags);
-			goto new_objects; /* stolen by an IRQ handler */
+			/* we were preempted and partial list got empty */
+			goto new_objects;
 		}
 
 		page = c->page = slub_percpu_partial(c);
@@ -2880,9 +2901,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	if (freelist)
 		goto check_new_page;
 
-	put_cpu_ptr(s->cpu_slab);
+	slub_put_cpu_ptr(s->cpu_slab);
 	page = new_slab(s, gfpflags, node);
-	c = get_cpu_ptr(s->cpu_slab);
+	c = slub_get_cpu_ptr(s->cpu_slab);
 
 	if (unlikely(!page)) {
 		slab_out_of_memory(s, gfpflags, node);
@@ -2965,12 +2986,12 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	 * cpu before disabling preemption. Need to reload cpu area
 	 * pointer.
 	 */
-	c = get_cpu_ptr(s->cpu_slab);
+	c = slub_get_cpu_ptr(s->cpu_slab);
 #endif
 
 	p = ___slab_alloc(s, gfpflags, node, addr, c);
 #ifdef CONFIG_PREEMPT_COUNT
-	put_cpu_ptr(s->cpu_slab);
+	slub_put_cpu_ptr(s->cpu_slab);
 #endif
 	return p;
 }
@@ -3491,7 +3512,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	 * IRQs, which protects against PREEMPT and interrupts
 	 * handlers invoking normal fastpath.
 	 */
-	c = get_cpu_ptr(s->cpu_slab);
+	c = slub_get_cpu_ptr(s->cpu_slab);
 	local_irq_disable();
 
 	for (i = 0; i < size; i++) {
@@ -3537,7 +3558,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();
-	put_cpu_ptr(s->cpu_slab);
+	slub_put_cpu_ptr(s->cpu_slab);
 
 	/*
 	 * memcg and kmem_cache debug support and memory initialization.
@@ -3547,7 +3568,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 				slab_want_init_on_alloc(flags, s));
 	return i;
 error:
-	put_cpu_ptr(s->cpu_slab);
+	slub_put_cpu_ptr(s->cpu_slab);
 	slab_post_alloc_hook(s, objcg, flags, i, p, false);
 	__kmem_cache_free_bulk(s, i, p);
 	return 0;
-- 
2.32.0