net: do not deplete pfmemalloc reserve

commit 79930f5892e134c6da1254389577fffb8bd72c66 upstream.

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>
[ luis: backported to 3.16: used davem's backport to 3.14 ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index fe07faaed256190a4b808d7e75de40796875062c..0f27eae2ccc1047164e43acbf27037107d7284a0 100644 (file)
--- a/net/core/skbuff.c
+++ b/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;
@@ -352,7 +356,8 @@ refill:
                        gfp_t gfp = gfp_mask;
 
                        if (order)
-                               gfp |= __GFP_COMP | __GFP_NOWARN;
+                               gfp |= __GFP_COMP | __GFP_NOWARN |
+                                      __GFP_NOMEMALLOC;
                        nc->frag.page = alloc_pages(gfp, order);
                        if (likely(nc->frag.page))
                                break;