[PATCH v5 13/35] mm, slub: do initial checks in ___slab_alloc() with irqs enabled

[Vlastimil Babka]

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.

Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
---
 include/linux/page-flags.h |  9 +++++++
 mm/slub.c                  | 54 +++++++++++++++++++++++++++++++-------
 2 files changed, 54 insertions(+), 9 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5922031ffab6..7fda4fb85bdc 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -815,6 +815,15 @@ static inline int PageSlabPfmemalloc(struct page *page)
 	return PageActive(page);
 }
 
+/*
+ * A version of PageSlabPfmemalloc() for opportunistic checks where the page
+ * might have been freed under us and not be a PageSlab anymore.
+ */
+static inline int __PageSlabPfmemalloc(struct page *page)
+{
+	return PageActive(page);
+}
+
 static inline void SetPageSlabPfmemalloc(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageSlab(page), page);
diff --git a/mm/slub.c b/mm/slub.c
index 31f946e03823..fcc38638c645 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2606,6 +2606,19 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
 	return true;
 }
 
+/*
+ * A variant of pfmemalloc_match() that tests page flags without asserting
+ * PageSlab. Intended for opportunistic checks before taking a lock and
+ * rechecking that nobody else freed the page under us.
+ */
+static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags)
+{
+	if (unlikely(__PageSlabPfmemalloc(page)))
+		return gfp_pfmemalloc_allowed(gfpflags);
+
+	return true;
+}
+
 /*
  * Check the page->freelist of a page and either transfer the freelist to the
  * per cpu freelist or deactivate the page.
@@ -2668,8 +2681,9 @@ 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 +2692,11 @@ 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 +2711,7 @@ 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;
 		}
 	}
 
@@ -2702,12 +2720,15 @@ 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_unsafe(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 +2744,9 @@ 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.
@@ -2734,11 +2758,23 @@ 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