From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 23 Aug 2021 23:58:56 +0000 (+1000)
Subject: mm, slub: do initial checks in ___slab_alloc() with irqs enabled
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=e9c2a5f0ca9c0f8475c92aab8a350e02d0479e67;p=users%2Fjedix%2Flinux-maple.git

mm, slub: do initial checks in ___slab_alloc() with irqs enabled

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.

Because we call pfmemalloc_match() as one of the checks, we might hit
VM_BUG_ON_PAGE(!PageSlab(page)) in PageSlabPfmemalloc in case we get
interrupted and the page is freed.  Thus introduce a
pfmemalloc_match_unsafe() variant that lacks the PageSlab check.

Link: https://lkml.kernel.org/r/20210805152000.12817-14-vbabka@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---

diff --git a/mm/slub.c b/mm/slub.c
index 31f946e03823..d1d39135d9f9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2668,8 +2668,9 @@ 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
@@ -2678,6 +2679,11 @@ 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:
@@ -2692,8 +2698,7 @@ redo:
 			goto redo;
 		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
-			deactivate_slab(s, page, c->freelist, c);
-			goto new_slab;
+			goto deactivate_slab;
 		}
 	}
 
@@ -2702,12 +2707,15 @@ redo:
 	 * 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;
@@ -2723,6 +2731,9 @@ redo:
 	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.
@@ -2734,11 +2745,23 @@ load_freelist:
 	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;
 	}