X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=mm%2Fslub.c;h=76e56ce55d21ed395fc676f658ed1d77534cbf76;hb=94ef0304e2b8dc942f46c74a13841d6b61f61d2f;hp=f77d8cd79ef7f7d6855df7ae9bb4659001cee387;hpb=b7d184d37ecc99f87fc8e531c788f69084f8a95f;p=linux-2.6-microblaze.git

diff --git a/mm/slub.c b/mm/slub.c
index f77d8cd79ef7..76e56ce55d21 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -452,7 +452,19 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
 
 #ifdef CONFIG_SLUB_DEBUG
 static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
-static DEFINE_SPINLOCK(object_map_lock);
+static DEFINE_RAW_SPINLOCK(object_map_lock);
+
+static void __fill_map(unsigned long *obj_map, struct kmem_cache *s,
+		       struct page *page)
+{
+	void *addr = page_address(page);
+	void *p;
+
+	bitmap_zero(obj_map, page->objects);
+
+	for (p = page->freelist; p; p = get_freepointer(s, p))
+		set_bit(__obj_to_index(s, addr, p), obj_map);
+}
 
 #if IS_ENABLED(CONFIG_KUNIT)
 static bool slab_add_kunit_errors(void)
@@ -483,17 +495,11 @@ static inline bool slab_add_kunit_errors(void) { return false; }
 static unsigned long *get_map(struct kmem_cache *s, struct page *page)
 	__acquires(&object_map_lock)
 {
-	void *p;
-	void *addr = page_address(page);
-
 	VM_BUG_ON(!irqs_disabled());
 
-	spin_lock(&object_map_lock);
-
-	bitmap_zero(object_map, page->objects);
+	raw_spin_lock(&object_map_lock);
 
-	for (p = page->freelist; p; p = get_freepointer(s, p))
-		set_bit(__obj_to_index(s, addr, p), object_map);
+	__fill_map(object_map, s, page);
 
 	return object_map;
 }
@@ -501,7 +507,7 @@ static unsigned long *get_map(struct kmem_cache *s, struct page *page)
 static void put_map(unsigned long *map) __releases(&object_map_lock)
 {
 	VM_BUG_ON(map != object_map);
-	spin_unlock(&object_map_lock);
+	raw_spin_unlock(&object_map_lock);
 }
 
 static inline unsigned int size_from_object(struct kmem_cache *s)
@@ -1003,8 +1009,6 @@ static int check_slab(struct kmem_cache *s, struct page *page)
 {
 	int maxobj;
 
-	VM_BUG_ON(!irqs_disabled());
-
 	if (!PageSlab(page)) {
 		slab_err(s, page, "Not a valid slab page");
 		return 0;
@@ -1585,20 +1589,8 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
 {
 	kmemleak_free_recursive(x, s->flags);
 
-	/*
-	 * Trouble is that we may no longer disable interrupts in the fast path
-	 * So in order to make the debug calls that expect irqs to be
-	 * disabled we need to disable interrupts temporarily.
-	 */
-#ifdef CONFIG_LOCKDEP
-	{
-		unsigned long flags;
+	debug_check_no_locks_freed(x, s->object_size);
 
-		local_irq_save(flags);
-		debug_check_no_locks_freed(x, s->object_size);
-		local_irq_restore(flags);
-	}
-#endif
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(x, s->object_size);
 
@@ -1815,9 +1807,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	flags &= gfp_allowed_mask;
 
-	if (gfpflags_allow_blocking(flags))
-		local_irq_enable();
-
 	flags |= s->allocflags;
 
 	/*
@@ -1876,8 +1865,6 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	page->frozen = 1;
 
 out:
-	if (gfpflags_allow_blocking(flags))
-		local_irq_disable();
 	if (!page)
 		return NULL;
 
@@ -1891,6 +1878,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (unlikely(flags & GFP_SLAB_BUG_MASK))
 		flags = kmalloc_fix_flags(flags);
 
+	WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO));
+
 	return allocate_slab(s,
 		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
 }
@@ -2021,11 +2010,12 @@ static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
  * Try to allocate a partial slab from a specific node.
  */
 static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
-				struct kmem_cache_cpu *c, gfp_t flags)
+			      struct page **ret_page, gfp_t gfpflags)
 {
 	struct page *page, *page2;
 	void *object = NULL;
 	unsigned int available = 0;
+	unsigned long flags;
 	int objects;
 
 	/*
@@ -2037,11 +2027,11 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 	if (!n || !n->nr_partial)
 		return NULL;
 
-	spin_lock(&n->list_lock);
+	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, page2, &n->partial, slab_list) {
 		void *t;
 
-		if (!pfmemalloc_match(page, flags))
+		if (!pfmemalloc_match(page, gfpflags))
 			continue;
 
 		t = acquire_slab(s, n, page, object == NULL, &objects);
@@ -2050,7 +2040,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 		available += objects;
 		if (!object) {
-			c->page = page;
+			*ret_page = page;
 			stat(s, ALLOC_FROM_PARTIAL);
 			object = t;
 		} else {
@@ -2062,7 +2052,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 			break;
 
 	}
-	spin_unlock(&n->list_lock);
+	spin_unlock_irqrestore(&n->list_lock, flags);
 	return object;
 }
 
@@ -2070,7 +2060,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
  * Get a page from somewhere. Search in increasing NUMA distances.
  */
 static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
-		struct kmem_cache_cpu *c)
+			     struct page **ret_page)
 {
 #ifdef CONFIG_NUMA
 	struct zonelist *zonelist;
@@ -2112,7 +2102,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
 
 			if (n && cpuset_zone_allowed(zone, flags) &&
 					n->nr_partial > s->min_partial) {
-				object = get_partial_node(s, n, c, flags);
+				object = get_partial_node(s, n, ret_page, flags);
 				if (object) {
 					/*
 					 * Don't check read_mems_allowed_retry()
@@ -2134,7 +2124,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
  * Get a partial page, lock it and return it.
  */
 static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
-		struct kmem_cache_cpu *c)
+			 struct page **ret_page)
 {
 	void *object;
 	int searchnode = node;
@@ -2142,11 +2132,11 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
 	if (node == NUMA_NO_NODE)
 		searchnode = numa_mem_id();
 
-	object = get_partial_node(s, get_node(s, searchnode), c, flags);
+	object = get_partial_node(s, get_node(s, searchnode), ret_page, flags);
 	if (object || node != NUMA_NO_NODE)
 		return object;
 
-	return get_any_partial(s, flags, c);
+	return get_any_partial(s, flags, ret_page);
 }
 
 #ifdef CONFIG_PREEMPTION
@@ -2219,10 +2209,13 @@ static void init_kmem_cache_cpus(struct kmem_cache *s)
 }
 
 /*
- * Remove the cpu slab
+ * Finishes removing the cpu slab. Merges cpu's freelist with page's freelist,
+ * unfreezes the slabs and puts it on the proper list.
+ * Assumes the slab has been already safely taken away from kmem_cache_cpu
+ * by the caller.
  */
 static void deactivate_slab(struct kmem_cache *s, struct page *page,
-				void *freelist, struct kmem_cache_cpu *c)
+			    void *freelist)
 {
 	enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
@@ -2230,6 +2223,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
 	enum slab_modes l = M_NONE, m = M_NONE;
 	void *nextfree, *freelist_iter, *freelist_tail;
 	int tail = DEACTIVATE_TO_HEAD;
+	unsigned long flags = 0;
 	struct page new;
 	struct page old;
 
@@ -2305,7 +2299,7 @@ redo:
 			 * that acquire_slab() will see a slab page that
 			 * is frozen
 			 */
-			spin_lock(&n->list_lock);
+			spin_lock_irqsave(&n->list_lock, flags);
 		}
 	} else {
 		m = M_FULL;
@@ -2316,7 +2310,7 @@ redo:
 			 * slabs from diagnostic functions will not see
 			 * any frozen slabs.
 			 */
-			spin_lock(&n->list_lock);
+			spin_lock_irqsave(&n->list_lock, flags);
 		}
 	}
 
@@ -2333,14 +2327,14 @@ redo:
 	}
 
 	l = m;
-	if (!__cmpxchg_double_slab(s, page,
+	if (!cmpxchg_double_slab(s, page,
 				old.freelist, old.counters,
 				new.freelist, new.counters,
 				"unfreezing slab"))
 		goto redo;
 
 	if (lock)
-		spin_unlock(&n->list_lock);
+		spin_unlock_irqrestore(&n->list_lock, flags);
 
 	if (m == M_PARTIAL)
 		stat(s, tail);
@@ -2351,38 +2345,29 @@ redo:
 		discard_slab(s, page);
 		stat(s, FREE_SLAB);
 	}
-
-	c->page = NULL;
-	c->freelist = NULL;
 }
 
-/*
- * Unfreeze all the cpu partial slabs.
- *
- * This function must be called with interrupts disabled
- * for the cpu using c (or some other guarantee must be there
- * to guarantee no concurrent accesses).
- */
-static void unfreeze_partials(struct kmem_cache *s,
-		struct kmem_cache_cpu *c)
-{
 #ifdef CONFIG_SLUB_CPU_PARTIAL
+static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page)
+{
 	struct kmem_cache_node *n = NULL, *n2 = NULL;
 	struct page *page, *discard_page = NULL;
+	unsigned long flags = 0;
 
-	while ((page = slub_percpu_partial(c))) {
+	while (partial_page) {
 		struct page new;
 		struct page old;
 
-		slub_set_percpu_partial(c, page);
+		page = partial_page;
+		partial_page = page->next;
 
 		n2 = get_node(s, page_to_nid(page));
 		if (n != n2) {
 			if (n)
-				spin_unlock(&n->list_lock);
+				spin_unlock_irqrestore(&n->list_lock, flags);
 
 			n = n2;
-			spin_lock(&n->list_lock);
+			spin_lock_irqsave(&n->list_lock, flags);
 		}
 
 		do {
@@ -2411,7 +2396,7 @@ static void unfreeze_partials(struct kmem_cache *s,
 	}
 
 	if (n)
-		spin_unlock(&n->list_lock);
+		spin_unlock_irqrestore(&n->list_lock, flags);
 
 	while (discard_page) {
 		page = discard_page;
@@ -2421,9 +2406,45 @@ static void unfreeze_partials(struct kmem_cache *s,
 		discard_slab(s, page);
 		stat(s, FREE_SLAB);
 	}
-#endif	/* CONFIG_SLUB_CPU_PARTIAL */
 }
 
+/*
+ * Unfreeze all the cpu partial slabs.
+ */
+static void unfreeze_partials(struct kmem_cache *s)
+{
+	struct page *partial_page;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	partial_page = this_cpu_read(s->cpu_slab->partial);
+	this_cpu_write(s->cpu_slab->partial, NULL);
+	local_irq_restore(flags);
+
+	if (partial_page)
+		__unfreeze_partials(s, partial_page);
+}
+
+static void unfreeze_partials_cpu(struct kmem_cache *s,
+				  struct kmem_cache_cpu *c)
+{
+	struct page *partial_page;
+
+	partial_page = slub_percpu_partial(c);
+	c->partial = NULL;
+
+	if (partial_page)
+		__unfreeze_partials(s, partial_page);
+}
+
+#else	/* CONFIG_SLUB_CPU_PARTIAL */
+
+static inline void unfreeze_partials(struct kmem_cache *s) { }
+static inline void unfreeze_partials_cpu(struct kmem_cache *s,
+				  struct kmem_cache_cpu *c) { }
+
+#endif	/* CONFIG_SLUB_CPU_PARTIAL */
+
 /*
  * Put a page that was just frozen (in __slab_free|get_partial_node) into a
  * partial page slot if available.
@@ -2448,14 +2469,11 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 			pobjects = oldpage->pobjects;
 			pages = oldpage->pages;
 			if (drain && pobjects > slub_cpu_partial(s)) {
-				unsigned long flags;
 				/*
 				 * partial array is full. Move the existing
 				 * set to the per node partial list.
 				 */
-				local_irq_save(flags);
-				unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
-				local_irq_restore(flags);
+				unfreeze_partials(s);
 				oldpage = NULL;
 				pobjects = 0;
 				pages = 0;
@@ -2472,58 +2490,124 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page)
 								!= oldpage);
-	if (unlikely(!slub_cpu_partial(s))) {
-		unsigned long flags;
-
-		local_irq_save(flags);
-		unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
-		local_irq_restore(flags);
-	}
 	preempt_enable();
 #endif	/* CONFIG_SLUB_CPU_PARTIAL */
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 {
-	stat(s, CPUSLAB_FLUSH);
-	deactivate_slab(s, c->page, c->freelist, c);
+	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);
+
+	local_irq_restore(flags);
+
+	if (page) {
+		deactivate_slab(s, page, freelist);
+		stat(s, CPUSLAB_FLUSH);
+	}
+}
+
+static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
+{
+	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+	void *freelist = c->freelist;
+	struct page *page = c->page;
 
+	c->page = NULL;
+	c->freelist = NULL;
 	c->tid = next_tid(c->tid);
+
+	if (page) {
+		deactivate_slab(s, page, freelist);
+		stat(s, CPUSLAB_FLUSH);
+	}
+
+	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 inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
+static void flush_cpu_slab(struct work_struct *w)
 {
-	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+	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);
 
-	unfreeze_partials(s, c);
+	unfreeze_partials(s);
 }
 
-static void flush_cpu_slab(void *d)
+static bool has_cpu_slab(int cpu, struct kmem_cache *s)
 {
-	struct kmem_cache *s = d;
+	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
-	__flush_cpu_slab(s, smp_processor_id());
+	return c->page || slub_percpu_partial(c);
 }
 
-static bool has_cpu_slab(int cpu, void *info)
+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 kmem_cache *s = info;
-	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+	struct slub_flush_work *sfw;
+	unsigned int cpu;
 
-	return c->page || slub_percpu_partial(c);
+	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();
 }
 
 /*
@@ -2533,14 +2617,10 @@ static void flush_all(struct kmem_cache *s)
 static int slub_cpu_dead(unsigned int cpu)
 {
 	struct kmem_cache *s;
-	unsigned long flags;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list) {
-		local_irq_save(flags);
+	list_for_each_entry(s, &slab_caches, list)
 		__flush_cpu_slab(s, cpu);
-		local_irq_restore(flags);
-	}
 	mutex_unlock(&slab_mutex);
 	return 0;
 }
@@ -2623,44 +2703,22 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 #endif
 }
 
-static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
-			int node, struct kmem_cache_cpu **pc)
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
 {
-	void *freelist;
-	struct kmem_cache_cpu *c = *pc;
-	struct page *page;
-
-	WARN_ON_ONCE(s->ctor && (flags & __GFP_ZERO));
-
-	freelist = get_partial(s, flags, node, c);
-
-	if (freelist)
-		return freelist;
-
-	page = new_slab(s, flags, node);
-	if (page) {
-		c = raw_cpu_ptr(s->cpu_slab);
-		if (c->page)
-			flush_slab(s, c);
-
-		/*
-		 * No other reference to the page yet so we can
-		 * muck around with it freely without cmpxchg
-		 */
-		freelist = page->freelist;
-		page->freelist = NULL;
-
-		stat(s, ALLOC_SLAB);
-		c->page = page;
-		*pc = c;
-	}
+	if (unlikely(PageSlabPfmemalloc(page)))
+		return gfp_pfmemalloc_allowed(gfpflags);
 
-	return freelist;
+	return true;
 }
 
-static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
+/*
+ * 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)))
+	if (unlikely(__PageSlabPfmemalloc(page)))
 		return gfp_pfmemalloc_allowed(gfpflags);
 
 	return true;
@@ -2716,7 +2774,7 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page)
  * we need to allocate a new slab. This is the slowest path since it involves
  * a call to the page allocator and the setup of a new slab.
  *
- * Version of __slab_alloc to use when we know that interrupts are
+ * Version of __slab_alloc to use when we know that preemption is
  * already disabled (which is the case for bulk allocation).
  */
 static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
@@ -2724,10 +2782,13 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 {
 	void *freelist;
 	struct page *page;
+	unsigned long flags;
 
 	stat(s, ALLOC_SLOWPATH);
 
-	page = c->page;
+reread_page:
+
+	page = READ_ONCE(c->page);
 	if (!page) {
 		/*
 		 * if the node is not online or has no normal memory, just
@@ -2750,8 +2811,7 @@ redo:
 			goto redo;
 		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
-			deactivate_slab(s, page, c->freelist, c);
-			goto new_slab;
+			goto deactivate_slab;
 		}
 	}
 
@@ -2760,12 +2820,15 @@ 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_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;
@@ -2774,6 +2837,7 @@ redo:
 
 	if (!freelist) {
 		c->page = NULL;
+		local_irq_restore(flags);
 		stat(s, DEACTIVATE_BYPASS);
 		goto new_slab;
 	}
@@ -2781,6 +2845,9 @@ 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.
@@ -2789,59 +2856,140 @@ load_freelist:
 	VM_BUG_ON(!c->page->frozen);
 	c->freelist = get_freepointer(s, freelist);
 	c->tid = next_tid(c->tid);
+	local_irq_restore(flags);
 	return freelist;
 
+deactivate_slab:
+
+	local_irq_save(flags);
+	if (page != c->page) {
+		local_irq_restore(flags);
+		goto reread_page;
+	}
+	freelist = c->freelist;
+	c->page = NULL;
+	c->freelist = NULL;
+	local_irq_restore(flags);
+	deactivate_slab(s, page, freelist);
+
 new_slab:
 
 	if (slub_percpu_partial(c)) {
+		local_irq_save(flags);
+		if (unlikely(c->page)) {
+			local_irq_restore(flags);
+			goto reread_page;
+		}
+		if (unlikely(!slub_percpu_partial(c))) {
+			local_irq_restore(flags);
+			goto new_objects; /* stolen by an IRQ handler */
+		}
+
 		page = c->page = slub_percpu_partial(c);
 		slub_set_percpu_partial(c, page);
+		local_irq_restore(flags);
 		stat(s, CPU_PARTIAL_ALLOC);
 		goto redo;
 	}
 
-	freelist = new_slab_objects(s, gfpflags, node, &c);
+new_objects:
+
+	freelist = get_partial(s, gfpflags, node, &page);
+	if (freelist)
+		goto check_new_page;
+
+	put_cpu_ptr(s->cpu_slab);
+	page = new_slab(s, gfpflags, node);
+	c = get_cpu_ptr(s->cpu_slab);
 
-	if (unlikely(!freelist)) {
+	if (unlikely(!page)) {
 		slab_out_of_memory(s, gfpflags, node);
 		return NULL;
 	}
 
-	page = c->page;
-	if (likely(!kmem_cache_debug(s) && pfmemalloc_match(page, gfpflags)))
-		goto load_freelist;
+	/*
+	 * No other reference to the page yet so we can
+	 * muck around with it freely without cmpxchg
+	 */
+	freelist = page->freelist;
+	page->freelist = NULL;
 
-	/* Only entered in the debug case */
-	if (kmem_cache_debug(s) &&
-			!alloc_debug_processing(s, page, freelist, addr))
-		goto new_slab;	/* Slab failed checks. Next slab needed */
+	stat(s, ALLOC_SLAB);
+
+check_new_page:
+
+	if (kmem_cache_debug(s)) {
+		if (!alloc_debug_processing(s, page, freelist, addr)) {
+			/* Slab failed checks. Next slab needed */
+			goto new_slab;
+		} else {
+			/*
+			 * For debug case, we don't load freelist so that all
+			 * allocations go through alloc_debug_processing()
+			 */
+			goto return_single;
+		}
+	}
+
+	if (unlikely(!pfmemalloc_match(page, gfpflags)))
+		/*
+		 * For !pfmemalloc_match() case we don't load freelist so that
+		 * we don't make further mismatched allocations easier.
+		 */
+		goto return_single;
+
+retry_load_page:
+
+	local_irq_save(flags);
+	if (unlikely(c->page)) {
+		void *flush_freelist = c->freelist;
+		struct page *flush_page = c->page;
+
+		c->page = NULL;
+		c->freelist = NULL;
+		c->tid = next_tid(c->tid);
+
+		local_irq_restore(flags);
+
+		deactivate_slab(s, flush_page, flush_freelist);
+
+		stat(s, CPUSLAB_FLUSH);
+
+		goto retry_load_page;
+	}
+	c->page = page;
+
+	goto load_freelist;
 
-	deactivate_slab(s, page, get_freepointer(s, freelist), c);
+return_single:
+
+	deactivate_slab(s, page, get_freepointer(s, freelist));
 	return freelist;
 }
 
 /*
- * Another one that disabled interrupt and compensates for possible
- * cpu changes by refetching the per cpu area pointer.
+ * A wrapper for ___slab_alloc() for contexts where preemption is not yet
+ * disabled. Compensates for possible cpu changes by refetching the per cpu area
+ * pointer.
  */
 static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 			  unsigned long addr, struct kmem_cache_cpu *c)
 {
 	void *p;
-	unsigned long flags;
 
-	local_irq_save(flags);
-#ifdef CONFIG_PREEMPTION
+#ifdef CONFIG_PREEMPT_COUNT
 	/*
 	 * We may have been preempted and rescheduled on a different
-	 * cpu before disabling interrupts. Need to reload cpu area
+	 * cpu before disabling preemption. Need to reload cpu area
 	 * pointer.
 	 */
-	c = this_cpu_ptr(s->cpu_slab);
+	c = get_cpu_ptr(s->cpu_slab);
 #endif
 
 	p = ___slab_alloc(s, gfpflags, node, addr, c);
-	local_irq_restore(flags);
+#ifdef CONFIG_PREEMPT_COUNT
+	put_cpu_ptr(s->cpu_slab);
+#endif
 	return p;
 }
 
@@ -2892,15 +3040,14 @@ redo:
 	 * reading from one cpu area. That does not matter as long
 	 * as we end up on the original cpu again when doing the cmpxchg.
 	 *
-	 * We should guarantee that tid and kmem_cache are retrieved on
-	 * the same cpu. It could be different if CONFIG_PREEMPTION so we need
-	 * to check if it is matched or not.
+	 * We must guarantee that tid and kmem_cache_cpu are retrieved on the
+	 * same cpu. We read first the kmem_cache_cpu pointer and use it to read
+	 * the tid. If we are preempted and switched to another cpu between the
+	 * two reads, it's OK as the two are still associated with the same cpu
+	 * and cmpxchg later will validate the cpu.
 	 */
-	do {
-		tid = this_cpu_read(s->cpu_slab->tid);
-		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPTION) &&
-		 unlikely(tid != READ_ONCE(c->tid)));
+	c = raw_cpu_ptr(s->cpu_slab);
+	tid = READ_ONCE(c->tid);
 
 	/*
 	 * Irqless object alloc/free algorithm used here depends on sequence
@@ -3174,11 +3321,8 @@ redo:
 	 * data is retrieved via this pointer. If we are on the same cpu
 	 * during the cmpxchg then the free will succeed.
 	 */
-	do {
-		tid = this_cpu_read(s->cpu_slab->tid);
-		c = raw_cpu_ptr(s->cpu_slab);
-	} while (IS_ENABLED(CONFIG_PREEMPTION) &&
-		 unlikely(tid != READ_ONCE(c->tid)));
+	c = raw_cpu_ptr(s->cpu_slab);
+	tid = READ_ONCE(c->tid);
 
 	/* Same with comment on barrier() in slab_alloc_node() */
 	barrier();
@@ -3373,8 +3517,8 @@ 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);
 	local_irq_disable();
-	c = this_cpu_ptr(s->cpu_slab);
 
 	for (i = 0; i < size; i++) {
 		void *object = kfence_alloc(s, s->object_size, flags);
@@ -3395,6 +3539,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			 */
 			c->tid = next_tid(c->tid);
 
+			local_irq_enable();
+
 			/*
 			 * Invoking slow path likely have side-effect
 			 * of re-populating per CPU c->freelist
@@ -3407,6 +3553,8 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			c = this_cpu_ptr(s->cpu_slab);
 			maybe_wipe_obj_freeptr(s, p[i]);
 
+			local_irq_disable();
+
 			continue; /* goto for-loop */
 		}
 		c->freelist = get_freepointer(s, object);
@@ -3415,6 +3563,7 @@ 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);
 
 	/*
 	 * memcg and kmem_cache debug support and memory initialization.
@@ -3424,7 +3573,7 @@ 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:
-	local_irq_enable();
+	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;
@@ -4003,7 +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);
@@ -4279,7 +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;
@@ -4291,7 +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++)
@@ -4341,13 +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;
@@ -4673,11 +4829,11 @@ static int count_total(struct page *page)
 #endif
 
 #ifdef CONFIG_SLUB_DEBUG
-static void validate_slab(struct kmem_cache *s, struct page *page)
+static void validate_slab(struct kmem_cache *s, struct page *page,
+			  unsigned long *obj_map)
 {
 	void *p;
 	void *addr = page_address(page);
-	unsigned long *map;
 
 	slab_lock(page);
 
@@ -4685,21 +4841,20 @@ static void validate_slab(struct kmem_cache *s, struct page *page)
 		goto unlock;
 
 	/* Now we know that a valid freelist exists */
-	map = get_map(s, page);
+	__fill_map(obj_map, s, page);
 	for_each_object(p, s, addr, page->objects) {
-		u8 val = test_bit(__obj_to_index(s, addr, p), map) ?
+		u8 val = test_bit(__obj_to_index(s, addr, p), obj_map) ?
 			 SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
 
 		if (!check_object(s, page, p, val))
 			break;
 	}
-	put_map(map);
 unlock:
 	slab_unlock(page);
 }
 
 static int validate_slab_node(struct kmem_cache *s,
-		struct kmem_cache_node *n)
+		struct kmem_cache_node *n, unsigned long *obj_map)
 {
 	unsigned long count = 0;
 	struct page *page;
@@ -4708,7 +4863,7 @@ static int validate_slab_node(struct kmem_cache *s,
 	spin_lock_irqsave(&n->list_lock, flags);
 
 	list_for_each_entry(page, &n->partial, slab_list) {
-		validate_slab(s, page);
+		validate_slab(s, page, obj_map);
 		count++;
 	}
 	if (count != n->nr_partial) {
@@ -4721,7 +4876,7 @@ static int validate_slab_node(struct kmem_cache *s,
 		goto out;
 
 	list_for_each_entry(page, &n->full, slab_list) {
-		validate_slab(s, page);
+		validate_slab(s, page, obj_map);
 		count++;
 	}
 	if (count != atomic_long_read(&n->nr_slabs)) {
@@ -4740,10 +4895,17 @@ long validate_slab_cache(struct kmem_cache *s)
 	int node;
 	unsigned long count = 0;
 	struct kmem_cache_node *n;
+	unsigned long *obj_map;
+
+	obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL);
+	if (!obj_map)
+		return -ENOMEM;
 
 	flush_all(s);
 	for_each_kmem_cache_node(s, node, n)
-		count += validate_slab_node(s, n);
+		count += validate_slab_node(s, n, obj_map);
+
+	bitmap_free(obj_map);
 
 	return count;
 }
@@ -4879,17 +5041,17 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 }
 
 static void process_slab(struct loc_track *t, struct kmem_cache *s,
-		struct page *page, enum track_item alloc)
+		struct page *page, enum track_item alloc,
+		unsigned long *obj_map)
 {
 	void *addr = page_address(page);
 	void *p;
-	unsigned long *map;
 
-	map = get_map(s, page);
+	__fill_map(obj_map, s, page);
+
 	for_each_object(p, s, addr, page->objects)
-		if (!test_bit(__obj_to_index(s, addr, p), map))
+		if (!test_bit(__obj_to_index(s, addr, p), obj_map))
 			add_location(t, s, get_track(s, p, alloc));
-	put_map(map);
 }
 #endif  /* CONFIG_DEBUG_FS   */
 #endif	/* CONFIG_SLUB_DEBUG */
@@ -5816,17 +5978,21 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
 	struct loc_track *t = __seq_open_private(filep, &slab_debugfs_sops,
 						sizeof(struct loc_track));
 	struct kmem_cache *s = file_inode(filep)->i_private;
+	unsigned long *obj_map;
+
+	obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL);
+	if (!obj_map)
+		return -ENOMEM;
 
 	if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0)
 		alloc = TRACK_ALLOC;
 	else
 		alloc = TRACK_FREE;
 
-	if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL))
+	if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) {
+		bitmap_free(obj_map);
 		return -ENOMEM;
-
-	/* Push back cpu slabs */
-	flush_all(s);
+	}
 
 	for_each_kmem_cache_node(s, node, n) {
 		unsigned long flags;
@@ -5837,12 +6003,13 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
 
 		spin_lock_irqsave(&n->list_lock, flags);
 		list_for_each_entry(page, &n->partial, slab_list)
-			process_slab(t, s, page, alloc);
+			process_slab(t, s, page, alloc, obj_map);
 		list_for_each_entry(page, &n->full, slab_list)
-			process_slab(t, s, page, alloc);
+			process_slab(t, s, page, alloc, obj_map);
 		spin_unlock_irqrestore(&n->list_lock, flags);
 	}
 
+	bitmap_free(obj_map);
 	return 0;
 }