net: do not deplete pfmemalloc reserve

[ Upstream commit 79930f58 ]

build_skb() should look at the page pfmemalloc status.
If set, this means page allocator allocated this page in the
expectation it would help to free other pages. Networking
stack can do that only if skb->pfmemalloc is also set.

Also, we must refrain using high order pages from the pfmemalloc
reserve, so __page_frag_refill() must also use __GFP_NOMEMALLOC for
them. Under memory pressure, using order-0 pages is probably the best
strategy.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

net/core/skbuff.c

@@ -309,7 +309,11 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
+	if (frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -346,7 +350,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
 	gfp_t gfp = gfp_mask;
 
 	if (order) {
-		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+			    __GFP_NOMEMALLOC;
 		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 		nc->frag.size = PAGE_SIZE << (page ? order : 0);
 	}