net: do not deplete pfmemalloc reserve

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>

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d1967dab9cc697a4dad45838e1a94c2b5f9cf147..456ead534e10777c680bd0a48535e02362fb03ca 100644 (file)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -311,7 +311,11 @@ 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;
@@ -348,7 +352,8 @@ 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);
        }