slab: allow NUMA restricted allocations to use percpu sheaves

Currently allocations asking for a specific node explicitly or via
mempolicy in strict_numa node bypass percpu sheaves. Since sheaves
contain mostly local objects, we can try allocating from them if the
local node happens to be the requested node or allowed by the mempolicy.
If we find the object from percpu sheaves is not from the expected node,
we skip the sheaves - this should be rare.

Reviewed-by: Harry Yoo <[e-mail]>
Reviewed-by: Suren Baghdasaryan <[e-mail]>
Signed-off-by: Vlastimil Babka <[e-mail]>

mm/slub.c

···
 }
 
 static __fastpath_inline
-void *alloc_from_pcs(struct kmem_cache *s, gfp_t gfp)
+void *alloc_from_pcs(struct kmem_cache *s, gfp_t gfp, int node)
 {
 	struct slub_percpu_sheaves *pcs;
+	bool node_requested;
 	void *object;
 
 #ifdef CONFIG_NUMA
-	if (static_branch_unlikely(&strict_numa)) {
-		if (current->mempolicy)
-			return NULL;
+	if (static_branch_unlikely(&strict_numa) &&
+			 node == NUMA_NO_NODE) {
+
+		struct mempolicy *mpol = current->mempolicy;
+
+		if (mpol) {
+			/*
+			 * Special BIND rule support. If the local node
+			 * is in permitted set then do not redirect
+			 * to a particular node.
+			 * Otherwise we apply the memory policy to get
+			 * the node we need to allocate on.
+			 */
+			if (mpol->mode != MPOL_BIND ||
+					!node_isset(numa_mem_id(), mpol->nodes))
+
+				node = mempolicy_slab_node();
+		}
 	}
 #endif
+
+	node_requested = IS_ENABLED(CONFIG_NUMA) && node != NUMA_NO_NODE;
+
+	/*
+	 * We assume the percpu sheaves contain only local objects although it's
+	 * not completely guaranteed, so we verify later.
+	 */
+	if (unlikely(node_requested && node != numa_mem_id()))
+		return NULL;
 
 	if (!local_trylock(&s->cpu_sheaves->lock))
 		return NULL;
···
 			return NULL;
 	}
 
-	object = pcs->main->objects[--pcs->main->size];
+	object = pcs->main->objects[pcs->main->size - 1];
+
+	if (unlikely(node_requested)) {
+		/*
+		 * Verify that the object was from the node we want. This could
+		 * be false because of cpu migration during an unlocked part of
+		 * the current allocation or previous freeing process.
+		 */
+		if (folio_nid(virt_to_folio(object)) != node) {
+			local_unlock(&s->cpu_sheaves->lock);
+			return NULL;
+		}
+	}
+
+	pcs->main->size--;
 
 	local_unlock(&s->cpu_sheaves->lock);
 
···
 	if (unlikely(object))
 		goto out;
 
-	if (s->cpu_sheaves && node == NUMA_NO_NODE)
-		object = alloc_from_pcs(s, gfpflags);
+	if (s->cpu_sheaves)
+		object = alloc_from_pcs(s, gfpflags, node);
 
 	if (!object)
 		object = __slab_alloc_node(s, gfpflags, node, addr, orig_size);