Skip to contentSkip to conversation

Patch "net: do not deplete pfmemalloc reserve" has been added to the 3.19-stable tree

PATCH [email protected] 1 participant 1 message Apr 29, 2015

Subsystems (2)
lore
Share & tools
lore

[email protected]

author maintainer Applied
#0 lore raw

This is a note to let you know that I've just added the patch titled

net: do not deplete pfmemalloc reserve

to the 3.19-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
net-do-not-deplete-pfmemalloc-reserve.patch
and it can be found in the queue-3.19 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

Quoted 1 line

From foo@baz Wed Apr 29 12:00:18 CEST 2015

From: Eric Dumazet <[email protected]>
Date: Wed, 22 Apr 2015 07:33:36 -0700
Subject: net: do not deplete pfmemalloc reserve

From: Eric Dumazet <[email protected]>

[ Upstream commit 79930f5892e134c6da1254389577fffb8bd72c66 ]

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.

---
 net/core/skbuff.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
net/core/skbuff.c +7 -2
@@ -309,7 +309,11 @@ struct sk_buff *build_skb(void *data, un
 
 	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(s
 	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);
 	}

Patches currently in stable-queue which might be from [email protected] are

queue-3.19/net-fix-crash-in-build_skb.patch queue-3.19/tcp-avoid-looping-in-tcp_send_fin.patch queue-3.19/net-do-not-deplete-pfmemalloc-reserve.patch queue-3.19/tcp-fix-possible-deadlock-in-tcp_send_fin.patch