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:     Andrew Morton <akpm@linux-foundation.org>,
        Christoph Lameter <cl@linux.com>,
        David Rientjes <rientjes@google.com>,
        Pekka Enberg <penberg@kernel.org>,
        Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc:     linux-mm@kvack.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>,
        Jesper Dangaard Brouer <brouer@redhat.com>,
        Jann Horn <jannh@google.com>, Vlastimil Babka <vbabka@suse.cz>
Subject: [PATCH v4 13/35] mm, slub: do initial checks in ___slab_alloc() with irqs enabled
Date:   Thu,  5 Aug 2021 17:19:38 +0200
Message-Id: <20210805152000.12817-14-vbabka@suse.cz>
In-Reply-To: <20210805152000.12817-1-vbabka@suse.cz>
References: <20210805152000.12817-1-vbabka@suse.cz>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

As another step of shortening irq disabled sections in ___slab_alloc(), delay
disabling irqs until we pass the initial checks if there is a cached percpu
slab and it's suitable for our allocation.

Now we have to recheck c->page after actually disabling irqs as an allocation
in irq handler might have replaced it.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
---
 mm/slub.c | 41 ++++++++++++++++++++++++++++++++---------
 1 file changed, 32 insertions(+), 9 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index db03cb972c11..7eb06fe9d7a0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2665,8 +2665,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 
 	stat(s, ALLOC_SLOWPATH);
 
-	local_irq_save(flags);
-	page = c->page;
+reread_page:
+
+	page = READ_ONCE(c->page);
 	if (!page) {
 		/*
 		 * if the node is not online or has no normal memory, just
@@ -2675,6 +2676,11 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 		if (unlikely(node != NUMA_NO_NODE &&
 			     !node_isset(node, slab_nodes)))
 			node = NUMA_NO_NODE;
+		local_irq_save(flags);
+		if (unlikely(c->page)) {
+			local_irq_restore(flags);
+			goto reread_page;
+		}
 		goto new_slab;
 	}
 redo:
@@ -2689,8 +2695,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			goto redo;
 		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
-			deactivate_slab(s, page, c->freelist, c);
-			goto new_slab;
+			goto deactivate_slab;
 		}
 	}
 
@@ -2699,12 +2704,15 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	 * PFMEMALLOC but right now, we are losing the pfmemalloc
 	 * information when the page leaves the per-cpu allocator
 	 */
-	if (unlikely(!pfmemalloc_match(page, gfpflags))) {
-		deactivate_slab(s, page, c->freelist, c);
-		goto new_slab;
-	}
+	if (unlikely(!pfmemalloc_match(page, gfpflags)))
+		goto deactivate_slab;
 
-	/* must check again c->freelist in case of cpu migration or IRQ */
+	/* must check again c->page in case IRQ handler changed it */
+	local_irq_save(flags);
+	if (unlikely(page != c->page)) {
+		local_irq_restore(flags);
+		goto reread_page;
+	}
 	freelist = c->freelist;
 	if (freelist)
 		goto load_freelist;
@@ -2720,6 +2728,9 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	stat(s, ALLOC_REFILL);
 
 load_freelist:
+
+	lockdep_assert_irqs_disabled();
+
 	/*
 	 * freelist is pointing to the list of objects to be used.
 	 * page is pointing to the page from which the objects are obtained.
@@ -2731,11 +2742,23 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 	local_irq_restore(flags);
 	return freelist;
 
+deactivate_slab:
+
+	local_irq_save(flags);
+	if (page != c->page) {
+		local_irq_restore(flags);
+		goto reread_page;
+	}
+	deactivate_slab(s, page, c->freelist, c);
+
 new_slab:
 
+	lockdep_assert_irqs_disabled();
+
 	if (slub_percpu_partial(c)) {
 		page = c->page = slub_percpu_partial(c);
 		slub_set_percpu_partial(c, page);
+		local_irq_restore(flags);
 		stat(s, CPU_PARTIAL_ALLOC);
 		goto redo;
 	}
-- 
2.32.0