| From foo@baz Thu Feb 27 20:11:26 PST 2014 |
| From: Eric Dumazet <edumazet@google.com> |
| Date: Thu, 6 Feb 2014 10:42:42 -0800 |
| Subject: net: use __GFP_NORETRY for high order allocations |
| |
| From: Eric Dumazet <edumazet@google.com> |
| |
| [ 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: |
| [<ffffffff8043766c>] dump_header+0xe1/0x23e |
| [<ffffffff80437a02>] oom_kill_process+0x6a/0x323 |
| [<ffffffff80438443>] out_of_memory+0x4b3/0x50d |
| [<ffffffff8043a4a6>] __alloc_pages_may_oom+0xa2/0xc7 |
| [<ffffffff80236f42>] __alloc_pages_nodemask+0x1002/0x17f0 |
| [<ffffffff8024bd23>] alloc_pages_current+0x103/0x2b0 |
| [<ffffffff8028567f>] sk_page_frag_refill+0x8f/0x160 |
| [<ffffffff80295fa0>] tcp_sendmsg+0x560/0xee0 |
| [<ffffffff802a5037>] inet_sendmsg+0x67/0x100 |
| [<ffffffff80283c9c>] __sock_sendmsg_nosec+0x6c/0x90 |
| [<ffffffff80283e85>] sock_sendmsg+0xc5/0xf0 |
| [<ffffffff802847b6>] __sys_sendmsg+0x136/0x430 |
| [<ffffffff80284ec8>] sys_sendmsg+0x88/0x110 |
| [<ffffffff80711472>] system_call_fastpath+0x16/0x1b |
| Out of Memory: Kill process 2856 (bash) score 9999 or sacrifice child |
| |
| Signed-off-by: Eric Dumazet <edumazet@google.com> |
| Acked-by: David Rientjes <rientjes@google.com> |
| Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> |
| Signed-off-by: David S. Miller <davem@davemloft.net> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| --- |
| 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; |