search for: __kfree_skb

Hi, I try to build experimental networks with Xen and stumbled over the same problem that has been described quite well by Mark Doll in his posting "xen_net: Failed to connect all virtual interfaces: err=-100" here: http://lists.xensource.com/archives/html/xen-users/2005-04/msg00447.html As it was still present in 2.0.6, I tried 3.0-devel and found NR_PIRQS and NR_DYNIRQS had been

Hi, I try to build experimental networks with Xen and stumbled over the same problem that has been described quite well by Mark Doll in his posting "xen_net: Failed to connect all virtual interfaces: err=-100" here: http://lists.xensource.com/archives/html/xen-users/2005-04/msg00447.html As it was still present in 2.0.6, I tried 3.0-devel and found NR_PIRQS and NR_DYNIRQS had been

...lticast_forward+0x15/0x20 [bridge] [<ffffffffa04f4a34>] ? br_handle_frame_finish+0x144/0x2a0 [bridge] [<ffffffffa04fa938>] ? br_nf_pre_routing_finish+0x238/0x350 [bridge] [<ffffffffa04faedb>] ? br_nf_pre_routing+0x48b/0x7b0 [bridge] [<ffffffff8143ba57>] ? __kfree_skb+0x47/0xa0 [<ffffffff814734f9>] ? nf_iterate+0x69/0xb0 [<ffffffffa04f48f0>] ? br_handle_frame_finish+0x0/0x2a0 [bridge] [<ffffffff814736b6>] ? nf_hook_slow+0x76/0x120 [<ffffffffa04f48f0>] ? br_handle_frame_finish+0x0/0x2a0 [bridge] [<ffffffffa04f4d...

...local_bh_enable+0x40/0x87 [<ffffffff814236e5>] destroy_conntrack+0x78/0x9e [<ffffffff810bea55>] ? __kmalloc_track_caller+0xc3/0x135 [<ffffffff814203b4>] nf_conntrack_destroy+0x16/0x18 [<ffffffff813fadee>] skb_release_head_state+0x97/0xd9 [<ffffffff813fabbe>] __kfree_skb+0x11/0x7a [<ffffffff813fac4e>] consume_skb+0x27/0x29 [<ffffffff81402d3a>] dev_kfree_skb_irq+0x18/0x62 [<ffffffff8130a762>] xennet_tx_buf_gc+0xfc/0x192 [<ffffffff8130a8fb>] smart_poll_function+0x50/0x121 [<ffffffff8130a8ab>] ? smart_poll_function+0x0/0x121 [...

...m: smbd Tainted: G B 2.6.32-5-686 #1 [154590.284254] Call Trace: [154590.284269] [<c108a666>] ? bad_page+0xd7/0xeb [154590.284276] [<c108b94c>] ? get_page_from_freelist+0x2e7/0x3c7 [154590.284291] [<c10ac6e1>] ? add_partial+0xe/0x40 [154590.284297] [<c11d2317>] ? __kfree_skb+0xf/0x6e [154590.284302] [<c108bced>] ? __alloc_pages_nodemask+0xf3/0x4d9 [154590.284308] [<c126dd00>] ? _spin_lock_bh+0x8/0x1e [154590.284314] [<c11cebae>] ? release_sock+0xf/0x89 [154590.284319] [<c108d3c5>] ? __do_page_cache_readahead+0x98/0x16b [154590.284323] [<...

...TG3 kernel: d17e26c0 ce933c20 f468b1a0 cf473a80 ced743e0 ce933c20 cdf956c0 f468b1a0 Jul 16 01:45:34 ETG3 kernel: Call Trace: [<f8865eee>] .rodata.str1.1 [jbd] 0x26e Jul 16 01:45:34 ETG3 kernel: [<c01d8d0c>] kfree_skbmem [kernel] 0xc Jul 16 01:45:34 ETG3 kernel: [<c01d8ea7>] __kfree_skb [kernel] 0x137 Jul 16 01:45:34 ETG3 kernel: [<c01dd0f2>] net_tx_action [kernel] 0x62 Jul 16 01:45:34 ETG3 kernel: [<c0120f3b>] do_softirq [kernel] 0x7b Jul 16 01:45:34 ETG3 kernel: [<c0119048>] schedule [kernel] 0x348 Jul 16 01:45:34 ETG3 kernel: [<f88617d6>] kjournald [jbd]...

...2e93a0 task.ti=c030a000) Stack: c0212cc4 00000004 cc83f160 cd2130c0 cd215bc0 cd2130c0 cd215bc0 c021734b c030bdb4 c0307a60 0000000a cceee800 cceee800 cd215bc0 cd1f3160 00000000 c021896b c0307a60 cd215bc0 cd215bc0 cceee800 cd1f3160 c025f1c6 00000000 Call Trace: [<c0212cc4>] __kfree_skb+0x84/0xe0 [<c021734b>] dev_hard_start_xmit+0x1bb/0x1d0 [<c021896b>] dev_queue_xmit+0x11b/0x1b0 [<c025f1c6>] ip6_output2+0x276/0x2b0 [<c025ed30>] ip6_output_finish+0x0/0xf0 [<c025fc0a>] ip6_output+0x90a/0x940 [<c013e9e5>] cache_alloc_refill+0x2c5/0x3f0...

..."bad partial csum: csum=%u/%u len=%u\n", + start, off, skb->len); + return false; + } + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + start; + skb->csum_offset = off; + return true; +} + EXPORT_SYMBOL(___pskb_trim); EXPORT_SYMBOL(__kfree_skb); EXPORT_SYMBOL(kfree_skb); @@ -2250,3 +2278,4 @@ EXPORT_SYMBOL(skb_append_datato_frags); EXPORT_SYMBOL_GPL(skb_to_sgvec); EXPORT_SYMBOL_GPL(skb_cow_data); +EXPORT_SYMBOL_GPL(skb_partial_csum_set); diff -r 72be3d596d31 drivers/net/virtio_net.c --- a/drivers/net/virtio_net.c Wed Jan 09 15:57:40...

..."bad partial csum: csum=%u/%u len=%u\n", + start, off, skb->len); + return false; + } + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + start; + skb->csum_offset = off; + return true; +} + EXPORT_SYMBOL(___pskb_trim); EXPORT_SYMBOL(__kfree_skb); EXPORT_SYMBOL(kfree_skb); @@ -2250,3 +2278,4 @@ EXPORT_SYMBOL(skb_append_datato_frags); EXPORT_SYMBOL_GPL(skb_to_sgvec); EXPORT_SYMBOL_GPL(skb_cow_data); +EXPORT_SYMBOL_GPL(skb_partial_csum_set); diff -r 72be3d596d31 drivers/net/virtio_net.c --- a/drivers/net/virtio_net.c Wed Jan 09 15:57:40...

...nel: [<ffffffff81494d26>] ? tcp_check_req+0x226/0x460 Oct 18 03:10:52 backup kernel: [<ffffffff8148a6d6>] ? tcp_rcv_state_process+0x126/0xa10 Oct 18 03:10:52 backup kernel: [<ffffffff8149220b>] ? tcp_v4_do_rcv+0x35b/0x430 Oct 18 03:10:52 backup kernel: [<ffffffff8142fd97>] ? __kfree_skb+0x47/0xa0 Oct 18 03:10:52 backup kernel: [<ffffffff81493a4e>] ? tcp_v4_rcv+0x4fe/0x8d0 Oct 18 03:10:52 backup kernel: [<ffffffff81492193>] ? tcp_v4_do_rcv+0x2e3/0x430 Oct 18 03:10:52 backup kernel: [<ffffffff814716dd>] ? ip_local_deliver_finish+0xdd/0x2d0 Oct 18 03:10:52 backup ke...

...[<c01641e0>] [<c0105726>] [<c0164200>] Code: 8b 41 18 a9 00 40 00 00 75 14 ff 49 14 0f 94 c0 84 c0 74 0a >>EIP; c012e2d2 <__free_pages+2/30> <===== Trace; c01d865e <skb_release_data+3e/70> Trace; c01d869b <kfree_skbmem+b/70> Trace; c01d8809 <__kfree_skb+109/110> Trace; c020723c <arp_rcv+44c/460> Trace; c011ee90 <update_process_times+20/b0> Trace; c01dc7da <net_rx_action+12a/210> Trace; c010831a <handle_IRQ_event+3a/70> Trace; c011bca3 <do_softirq+53/a0> Trace; c01084cc <do_IRQ+9c/b0> Trace; c010a4e8 <call_...

...e/0x450 [nft_meta] Apr 02 14:23:03 helium kernel: nft_do_chain+0x102/0x4e0 [nf_tables] Apr 02 14:23:03 helium kernel: ? skb_free_head+0x21/0x30 Apr 02 14:23:03 helium kernel: ? skb_release_data+0x101/0x110 Apr 02 14:23:03 helium kernel: ? kfree_skbmem+0x59/0x60 Apr 02 14:23:03 helium kernel: ? __kfree_skb+0x1a/0x20 Apr 02 14:23:03 helium kernel: ? tcp_rcv_established+0x27b/0x6f0 Apr 02 14:23:03 helium kernel: ? sk_filter_trim_cap+0xb7/0x260 Apr 02 14:23:03 helium kernel: ? nft_do_chain_netdev+0x66/0x250 [nf_tables_netdev] Apr 02 14:23:03 helium kernel: ? cpuacct_charge+0x86/0xa0 Apr 02 14:23:03...

Hi, We are trying to validate Asterisk as a media gateway PRI <-> SIP with two T400P (8 T1s) per box. The first experience with BOX1 (Compaq, 2.53 GHz, 1 Gb RAM) and just one T400P was encouraging - on the load test with 3 T1s worth of calls we had on average 75% idle CPU. Not so with BOX2 (Dell, single 2.6 GHz Xeon, 1 Gb RAM, 2 T400P) and BOX3 (Dell, dual 2.6 GHz Xeon, 2 Gb RAM, 2 T400P,

...ce587b00 ffffffff8074b760 ffffc20000003ca0 ffffffff804a5e18 0000000000000000 ffff8800ce587b00 ffffc20000003cc0 ffffffff804a5636 Call Trace: <IRQ> <0> [<ffffffff804a57b6>] skb_release_data+0x9b/0xac [<ffffffff804a5e18>] skb_release_all+0x19/0x1e [<ffffffff804a5636>] __kfree_skb+0x11/0x78 [<ffffffff804a56c5>] kfree_skb+0x28/0x2a [<ffffffff804abc91>] netif_receive_skb+0x2c6/0x2eb [<ffffffff804ac067>] napi_gro_receive+0x26/0x3a [<ffffffffa000c1ab>] e1000_receive_skb+0x45/0x4d [e1000e] [<ffffffffa000f31d>] e1000_clean_rx_irq+0x225/0x2c5 [e10...

...t;ffffffff8149c383>] ? tcp_create_openreq_child+0x23/0x450 Jun 13 09:41:18 myhost kernel: [<ffffffff81499bed>] ? tcp_v4_syn_recv_sock+0x4d/0x310 Jun 13 09:41:18 myhost kernel: [<ffffffff8149c126>] ? tcp_check_req+0x226/0x460 Jun 13 09:41:18 myhost kernel: [<ffffffff81437087>] ? __kfree_skb+0x47/0xa0 Jun 13 09:41:18 myhost kernel: [<ffffffff8149960b>] ? tcp_v4_do_rcv+0x35b/0x430 Jun 13 09:41:18 myhost kernel: [<ffffffff8149ae4e>] ? tcp_v4_rcv+0x4fe/0x8d0 Jun 13 09:41:18 myhost kernel: [<ffffffff81432f6c>] ? sk_reset_timer+0x1c/0x30 Jun 13 09:41:18 myhost kernel: [&lt...

tun supports zero copy transmit since 0690899b4d4501b3505be069b9a687e68ccbe15b, however you can only enable this mode if you know your workload does not trigger heavy guest to host/host to guest traffic - otherwise you get a (minor) performance regression. This patchset addresses this problem by notifying the owner device when callback is invoked because of a data copy. This makes it possible to

tun supports zero copy transmit since 0690899b4d4501b3505be069b9a687e68ccbe15b, however you can only enable this mode if you know your workload does not trigger heavy guest to host/host to guest traffic - otherwise you get a (minor) performance regression. This patchset addresses this problem by notifying the owner device when callback is invoked because of a data copy. This makes it possible to

tun supports zero copy transmit since 0690899b4d4501b3505be069b9a687e68ccbe15b, however you can only enable this mode if you know your workload does not trigger heavy guest to host/host to guest traffic - otherwise you get a (minor) performance regression. This patchset addresses this problem by notifying the owner device when callback is invoked because of a data copy. This makes it possible to

tun supports zero copy transmit since 0690899b4d4501b3505be069b9a687e68ccbe15b, however you can only enable this mode if you know your workload does not trigger heavy guest to host/host to guest traffic - otherwise you get a (minor) performance regression. This patchset addresses this problem by notifying the owner device when callback is invoked because of a data copy. This makes it possible to

tun supports zero copy transmit since 0690899b4d4501b3505be069b9a687e68ccbe15b, however you can only enable this mode if you know your workload does not trigger heavy guest to host/host to guest traffic - otherwise you get a (minor) performance regression. This patchset addresses this problem by notifying the owner device when callback is invoked because of a data copy. This makes it possible to