From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Eric Dumazet , David Rientjes , "Eric W. Biederman" , "David S. Miller" Subject: [PATCH 3.13 062/172] net: use __GFP_NORETRY for high order allocations Date: Tue, 4 Mar 2014 12:02:26 -0800 Message-Id: <20140304200301.729511422@linuxfoundation.org> In-Reply-To: <20140304200259.626667112@linuxfoundation.org> References: <20140304200259.626667112@linuxfoundation.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: 3.13-stable review patch. If anyone has any objections, please let me know. ------------------ From: Eric Dumazet [ Upstream commit ed98df3361f059db42786c830ea96e2d18b8d4db ] sock_alloc_send_pskb() & sk_page_frag_refill() have a loop trying high order allocations to prepare skb with low number of fragments as this increases performance. Problem is that under memory pressure/fragmentation, this can trigger OOM while the intent was only to try the high order allocations, then fallback to order-0 allocations. We had various reports from unexpected regressions. According to David, setting __GFP_NORETRY should be fine, as the asynchronous compaction is still enabled, and this will prevent OOM from kicking as in : CFSClientEventm invoked oom-killer: gfp_mask=0x42d0, order=3, oom_adj=0, oom_score_adj=0, oom_score_badness=2 (enabled),memcg_scoring=disabled CFSClientEventm Call Trace: [] dump_header+0xe1/0x23e [] oom_kill_process+0x6a/0x323 [] out_of_memory+0x4b3/0x50d [] __alloc_pages_may_oom+0xa2/0xc7 [] __alloc_pages_nodemask+0x1002/0x17f0 [] alloc_pages_current+0x103/0x2b0 [] sk_page_frag_refill+0x8f/0x160 [] tcp_sendmsg+0x560/0xee0 [] inet_sendmsg+0x67/0x100 [] __sock_sendmsg_nosec+0x6c/0x90 [] sock_sendmsg+0xc5/0xf0 [] __sys_sendmsg+0x136/0x430 [] sys_sendmsg+0x88/0x110 [] system_call_fastpath+0x16/0x1b Out of Memory: Kill process 2856 (bash) score 9999 or sacrifice child Signed-off-by: Eric Dumazet Acked-by: David Rientjes Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- net/core/sock.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1800,7 +1800,9 @@ struct sk_buff *sock_alloc_send_pskb(str while (order) { if (npages >= 1 << order) { page = alloc_pages(sk->sk_allocation | - __GFP_COMP | __GFP_NOWARN, + __GFP_COMP | + __GFP_NOWARN | + __GFP_NORETRY, order); if (page) goto fill_page; @@ -1872,7 +1874,7 @@ bool skb_page_frag_refill(unsigned int s gfp_t gfp = prio; if (order) - gfp |= __GFP_COMP | __GFP_NOWARN; + gfp |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY; pfrag->page = alloc_pages(gfp, order); if (likely(pfrag->page)) { pfrag->offset = 0;