From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755095Ab0KHRXD (ORCPT ); Mon, 8 Nov 2010 12:23:03 -0500 Received: from mail-wy0-f174.google.com ([74.125.82.174]:43130 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752034Ab0KHRXB convert rfc822-to-8bit (ORCPT ); Mon, 8 Nov 2010 12:23:01 -0500 MIME-Version: 1.0 X-Originating-IP: [172.22.89.164] In-Reply-To: <1289236230.15376.7.camel@edumazet-laptop> References: <20100604092025.GA96690@trillian.comsick.at> <1275656014.2482.169.camel@edumazet-laptop> <20100604161644.GA98048@trillian.local> <20100606095640.GA4436@trillian.comsick.at> <1275820945.5238.987.camel@edumazet-laptop> <1282769089.2681.159.camel@edumazet-laptop>

<1283718304.3402.370.camel@edumazet-laptop> <1289236230.15376.7.camel@edumazet-laptop> From: =?UTF-8?B?TmlraGlsIFNldGhpICjgpKjgpL/gpJbgpL/gpLIg4KS44KWH4KSg4KWAKQ==?= Date: Mon, 8 Nov 2010 09:22:18 -0800 Message-ID: Subject: Re: [2.6.35-rc1] page alloc failure order:1, mode:0x4020 To: Eric Dumazet Cc: Michael Guntsche , linux-kernel , netdev , Hugh Dickins Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org As I said, this seems like a regression in 2.6.36 from 2.6.35 (which is why I emailed after 2 months :) ). You mentioned earlier in the thread that you were going to submit the patch to head, if there is a separate bug/thread tracking that, I can send followups to that. I believe I have the right patch: *** 225,234 **** int error = 0, i; u32 size; ! ! common->rx_bufsize = roundup(IEEE80211_MAX_MPDU_LEN + ! ah->caps.rx_status_len, ! min(common->cachelsz, (u16)64)); ath9k_hw_set_rx_bufsize(ah, common->rx_bufsize - ah->caps.rx_status_len); --- 225,234 ---- int error = 0, i; u32 size; ! size = roundup(IEEE80211_MAX_MPDU_LEN + ah->caps.rx_status_len, ! min(common->cachelsz, (u16)64)); ! common->rx_bufsize = min_t(u32, size, ! SKB_MAX_ORDER(NET_SKB_PAD + common->cachelsz, 0)); ath9k_hw_set_rx_bufsize(ah, common->rx_bufsize - ah->caps.rx_status_len); 2010/11/8 Eric Dumazet : > Le lundi 08 novembre 2010 à 08:25 -0800, Nikhil Sethi (निखिल सेठी) a > écrit : >> Thanks Eric, for all the help. >> I get very occasional errors with vanilla 2.6.36 kernel with your >> patch. Error messages are slightly different, and very rare compared >> to without your patch. 2.6.35.7 seems fine, and does not show this >> error. >> >> rsync: page allocation failure. order:1, mode:0x4020 >> Pid: 31479, comm: rsync Not tainted 2.6.36-rc1 #1 >> Call Trace: >> [] ? __alloc_pages_nodemask+0x3f1/0x52e >> [] ? __slab_alloc+0x40f/0x45a >> [] ? __kmalloc_track_caller+0x91/0x97 >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? __alloc_skb+0x57/0x100 >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? ath_rx_tasklet+0x680/0xcfe [ath9k] >> [] ? __queue_work+0xe4/0x1a2 >> [] ? ath9k_tasklet+0xd0/0x134 [ath9k] >> [] ? tasklet_action+0x5f/0x65 >> [] ? __do_softirq+0x60/0xc6 >> [] ? do_softirq+0x2e/0x30 >> [] ? irq_exit+0x54/0x56 >> [] ? do_IRQ+0x3a/0x72 >> [] ? common_interrupt+0x29/0x30 >> [] ? cfq_may_queue+0x0/0x92 >> [] ? get_request+0x121/0x23e >> [] ? get_request_wait+0x20/0xfd >> [] ? cfq_merge+0x0/0x69 >> [] ? elv_merge+0x14b/0x170 >> [] ? __make_request+0x71/0x364 >> [] ? generic_make_request+0x14f/0x318 >> [] ? mempool_alloc+0x35/0xb9 >> [] ? submit_bio+0x3e/0x90 >> [] ? bio_alloc_bioset+0x33/0x9e >> [] ? submit_bh+0xbc/0xec >> [] ? ll_rw_block+0x72/0x74 >> [] ? __breadahead+0x20/0x30 >> [] ? __ext4_get_inode_loc+0x308/0x416 >> [] ? ext4_iget+0x52/0x652 >> [] ? ext4_lookup+0x65/0xbf >> [] ? d_alloc_and_lookup+0x30/0x58 >> [] ? do_lookup+0xc5/0xfe >> [] ? link_path_walk+0x4d1/0x8d6 >> [] ? path_walk+0x48/0xa9 >> [] ? do_path_lookup+0x3b/0x3f >> [] ? user_path_at+0x30/0x64 >> [] ? cp_new_stat64+0xee/0x100 >> [] ? vfs_fstatat+0x25/0x63 >> [] ? vfs_lstat+0x13/0x15 >> [] ? sys_lstat64+0xf/0x23 >> [] ? switched_to_idle+0x1a/0x43 >> [] ? syscall_call+0x7/0xb >> [] ? quirk_ich7_lpc+0x46/0x4d >> Mem-Info: >> DMA per-cpu: >> CPU 0: hi: 0, btch: 1 usd: 0 >> Normal per-cpu: >> CPU 0: hi: 90, btch: 15 usd: 84 >> active_anon:14957 inactive_anon:15137 isolated_anon:0 >> active_file:11820 inactive_file:11640 isolated_file:0 >> unevictable:470 dirty:1378 writeback:0 unstable:0 >> free:975 slab_reclaimable:5606 slab_unreclaimable:2343 >> mapped:2786 shmem:72 pagetables:394 bounce:0 >> DMA free:1000kB min:124kB low:152kB high:184kB active_anon:2896kB >> inactive_anon:3552kB active_file:2116kB inactive_file:1768kB >> unevictable:348kB isolated(anon):0kB isolated(file):0kB >> present:15864kB mlocked:348kB dirty:16kB writeback:0kB mapped:228kB >> shmem:32kB slab_reclaimable:1136kB slab_unreclaimable:608kB >> kernel_stack:144kB pagetables:52kB unstable:0kB bounce:0kB >> writeback_tmp:0kB pages_scanned:32 all_unreclaimable? no >> lowmem_reserve[]: 0 238 238 >> Normal free:2900kB min:1908kB low:2384kB high:2860kB >> active_anon:56932kB inactive_anon:56996kB active_file:45164kB >> inactive_file:44792kB unevictable:1532kB isolated(anon):0kB >> isolated(file):0kB present:243840kB mlocked:1532kB dirty:5496kB >> writeback:0kB mapped:10916kB shmem:256kB slab_reclaimable:21288kB >> slab_unreclaimable:8764kB kernel_stack:1056kB pagetables:1524kB >> unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 >> all_unreclaimable? no >> lowmem_reserve[]: 0 0 0 >> DMA: 6*4kB 14*8kB 16*16kB 1*32kB 1*64kB 0*128kB 0*256kB 1*512kB >> 0*1024kB 0*2048kB 0*4096kB = 1000kB >> Normal: 691*4kB 17*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB >> 0*1024kB 0*2048kB 0*4096kB = 2900kB >> 28310 total pagecache pages >> 4385 pages in swap cache >> Swap cache stats: add 144387, delete 140002, find 98398/115667 >> Free swap = 889116kB >> Total swap = 1023996kB >> 65535 pages RAM >> 1245 pages reserved >> 27369 pages shared >> 42219 pages non-shared >> SLUB: Unable to allocate memory on node -1 (gfp=0x20) >> cache: kmalloc-8192, object size: 8192, buffer size: 8192, default >> order: 3, min order: 1 >> node 0: slabs: 133, objs: 529, free: 0 >> skbuff alloc of size 3872 failed >> rsync: page allocation failure. order:1, mode:0x4020 >> Pid: 31479, comm: rsync Not tainted 2.6.36-rc1 #1 >> Call Trace: >> [] ? __alloc_pages_nodemask+0x3f1/0x52e >> [] ? __slab_alloc+0x40f/0x45a >> [] ? __kmalloc_track_caller+0x91/0x97 >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? __alloc_skb+0x57/0x100 >> [] ? ath_rxbuf_alloc+0x1a/0x78 [ath] >> [] ? ath_rx_tasklet+0x680/0xcfe [ath9k] >> [] ? __queue_work+0xe4/0x1a2 >> [] ? ath9k_tasklet+0xd0/0x134 [ath9k] >> [] ? tasklet_action+0x5f/0x65 >> [] ? __do_softirq+0x60/0xc6 >> [] ? do_softirq+0x2e/0x30 >> [] ? irq_exit+0x54/0x56 >> [] ? do_IRQ+0x3a/0x72 >> [] ? common_interrupt+0x29/0x30 >> [] ? cfq_may_queue+0x0/0x92 >> [] ? get_request+0x121/0x23e >> [] ? get_request_wait+0x20/0xfd >> [] ? cfq_merge+0x0/0x69 >> [] ? elv_merge+0x14b/0x170 >> [] ? __make_request+0x71/0x364 >> [] ? generic_make_request+0x14f/0x318 >> [] ? mempool_alloc+0x35/0xb9 >> [] ? submit_bio+0x3e/0x90 >> [] ? bio_alloc_bioset+0x33/0x9e >> [] ? submit_bh+0xbc/0xec >> [] ? ll_rw_block+0x72/0x74 >> [] ? __breadahead+0x20/0x30 >> [] ? __ext4_get_inode_loc+0x308/0x416 >> [] ? ext4_iget+0x52/0x652 >> [] ? ext4_lookup+0x65/0xbf >> [] ? d_alloc_and_lookup+0x30/0x58 >> [] ? do_lookup+0xc5/0xfe >> [] ? link_path_walk+0x4d1/0x8d6 >> [] ? path_walk+0x48/0xa9 >> [] ? do_path_lookup+0x3b/0x3f >> [] ? user_path_at+0x30/0x64 >> [] ? cp_new_stat64+0xee/0x100 >> [] ? vfs_fstatat+0x25/0x63 >> [] ? vfs_lstat+0x13/0x15 >> [] ? sys_lstat64+0xf/0x23 >> [] ? switched_to_idle+0x1a/0x43 >> [] ? syscall_call+0x7/0xb >> [] ? quirk_ich7_lpc+0x46/0x4d >> Mem-Info: >> DMA per-cpu: >> CPU 0: hi: 0, btch: 1 usd: 0 >> Normal per-cpu: >> CPU 0: hi: 90, btch: 15 usd: 84 >> active_anon:14957 inactive_anon:15137 isolated_anon:0 >> active_file:11820 inactive_file:11640 isolated_file:0 >> unevictable:470 dirty:1378 writeback:0 unstable:0 >> free:975 slab_reclaimable:5606 slab_unreclaimable:2343 >> mapped:2786 shmem:72 pagetables:394 bounce:0 >> DMA free:1000kB min:124kB low:152kB high:184kB active_anon:2896kB >> inactive_anon:3552kB active_file:2116kB inactive_file:1768kB >> unevictable:348kB isolated(anon):0kB isolated(file):0kB >> present:15864kB mlocked:348kB dirty:16kB writeback:0kB mapped:228kB >> shmem:32kB slab_reclaimable:1136kB slab_unreclaimable:608kB >> kernel_stack:144kB pagetables:52kB unstable:0kB bounce:0kB >> writeback_tmp:0kB pages_scanned:32 all_unreclaimable? no >> lowmem_reserve[]: 0 238 238 >> Normal free:2900kB min:1908kB low:2384kB high:2860kB >> active_anon:56932kB inactive_anon:56996kB active_file:45164kB >> inactive_file:44792kB unevictable:1532kB isolated(anon):0kB >> isolated(file):0kB present:243840kB mlocked:1532kB dirty:5496kB >> writeback:0kB mapped:10916kB shmem:256kB slab_reclaimable:21288kB >> slab_unreclaimable:8764kB kernel_stack:1056kB pagetables:1524kB >> unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 >> all_unreclaimable? no >> lowmem_reserve[]: 0 0 0 >> DMA: 6*4kB 14*8kB 16*16kB 1*32kB 1*64kB 0*128kB 0*256kB 1*512kB >> 0*1024kB 0*2048kB 0*4096kB = 1000kB >> Normal: 691*4kB 17*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB >> 0*1024kB 0*2048kB 0*4096kB = 2900kB >> 28310 total pagecache pages >> 4385 pages in swap cache >> Swap cache stats: add 144387, delete 140002, find 98398/115667 >> Free swap = 889116kB >> Total swap = 1023996kB >> 65535 pages RAM >> 1245 pages reserved >> 27369 pages shared >> 42219 pages non-shared >> SLUB: Unable to allocate memory on node -1 (gfp=0x20) >> cache: kmalloc-8192, object size: 8192, buffer size: 8192, default >> order: 3, min order: 1 >> node 0: slabs: 133, objs: 529, free: 0 >> skbuff alloc of size 3872 failed >> >> 2010/9/5 Eric Dumazet >> > >> > Le dimanche 05 septembre 2010 à 08:51 -0700, Nikhil Sethi (निखिल सेठी) a >> > écrit : >> > > This came back. Here is the dmesg output. It might be the problem only >> > > happens if I have wmm_enabled=1 in my hostapd.conf. That is the only >> > > thing that I changed yesterday, and today I saw these messages in my >> > > logs. I will try to conform this. >> > > >> > > >> > > I am running 2.6.35.4 with this patch: >> > > >> > > >> > > *** 225,234 **** >> > > int error = 0, i; >> > > u32 size; >> > > >> > > ! >> > > ! common->rx_bufsize = roundup(IEEE80211_MAX_MPDU_LEN + >> > > ! ah->caps.rx_status_len, >> > > ! min(common->cachelsz, (u16)64)); >> > > >> > > ath9k_hw_set_rx_bufsize(ah, common->rx_bufsize - >> > > ah->caps.rx_status_len); >> > > --- 225,234 ---- >> > > int error = 0, i; >> > > u32 size; >> > > >> > > ! size = roundup(IEEE80211_MAX_MPDU_LEN + ah->caps.rx_status_len, >> > > ! min(common->cachelsz, (u16)64)); >> > > ! common->rx_bufsize = min_t(u32, size, >> > > ! SKB_MAX_ORDER(NET_SKB_PAD + >> > > common->cachelsz, 0)); > > > Its very hard to follow this thread, with a message every two months. > > > As I said, this patch got a min_t() instead of max_t() > > http://kerneltrap.org/mailarchive/linux-kernel/2010/8/25/4611322 > > If you still have kmalloc-8192 allocations, I suspect you dont use right > patch. > > > >