From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sander Eikelenboom Subject: Re: Xen-unstable Linux 3.14-rc3 and 3.13 Network troubles "bisected" Date: Thu, 27 Mar 2014 11:00:53 +0100 Message-ID: <1576628063.20140327110053__7697.74432196773$1395914570$gmane$org@eikelenboom.it> References: <1744594108.20140318162127@eikelenboom.it> <20140318160412.GB16807@zion.uk.xensource.com> <1701035622.20140318211402@eikelenboom.it> <722971844.20140318221859@eikelenboom.it> <1688396550.20140319001104@eikelenboom.it> <20140319113532.GD16807@zion.uk.xensource.com> <246793256.20140319220752@eikelenboom.it> <20140321164958.GA31766@zion.uk.xensource.com> <1334202265.20140321182727@eikelenboom.it> <1056661597.20140322192834@eikelenboom.it> <20140325151539.GG31766@zion.uk.xensource.com> <79975567.20140325162942@eikelenboom.it> <1972209744.20140326121116@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029AD94@AMSPEX01CL01.citrite.net> <1715463578.20140326162245@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029AFC1@AMSPEX01CL01.citrite.net> <799579453.20140326170641@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029B106@AMSPEX01CL01.citrite.net> <789809468.20140326175352@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029B277@AMSPEX01CL01.citrite.net> <966386043.20140326183304@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029B375@AMSPEX01CL01.citrite.net> <172833073.20140326205709@eikelenboom.it> <9AAE0902D5BC7E449B7C8E4E778ABCD029BF42@AMSPEX01CL01.citrite.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <9AAE0902D5BC7E449B7C8E4E778ABCD029BF42@AMSPEX01CL01.citrite.net> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Paul Durrant Cc: Wei Liu , Ian Campbell , "netdev@vger.kernel.org" , linux-kernel , "xen-devel@lists.xen.org" , annie li , Zoltan Kiss List-Id: xen-devel@lists.xenproject.org Thursday, March 27, 2014, 10:47:02 AM, you wrote: >> -----Original Message----- >> From: Sander Eikelenboom [mailto:linux@eikelenboom.it] >> Sent: 26 March 2014 19:57 >> To: Paul Durrant >> Cc: Wei Liu; annie li; Zoltan Kiss; xen-devel@lists.xen.org; Ian Campbell; linux- >> kernel; netdev@vger.kernel.org >> Subject: Re: [Xen-devel] Xen-unstable Linux 3.14-rc3 and 3.13 Network >> troubles "bisected" >> >> >> Wednesday, March 26, 2014, 6:48:15 PM, you wrote: >> >> >> -----Original Message----- >> >> From: Paul Durrant >> >> Sent: 26 March 2014 17:47 >> >> To: 'Sander Eikelenboom' >> >> Cc: Wei Liu; annie li; Zoltan Kiss; xen-devel@lists.xen.org; Ian Campbell; >> linux- >> >> kernel; netdev@vger.kernel.org >> >> Subject: RE: [Xen-devel] Xen-unstable Linux 3.14-rc3 and 3.13 Network >> >> troubles "bisected" >> >> >> >> Re-send shortened version... >> >> >> >> > -----Original Message----- >> >> > From: Sander Eikelenboom [mailto:linux@eikelenboom.it] >> >> > Sent: 26 March 2014 16:54 >> >> > To: Paul Durrant >> >> > Cc: Wei Liu; annie li; Zoltan Kiss; xen-devel@lists.xen.org; Ian Campbell; >> >> linux- >> >> > kernel; netdev@vger.kernel.org >> >> > Subject: Re: [Xen-devel] Xen-unstable Linux 3.14-rc3 and 3.13 Network >> >> > troubles "bisected" >> >> > >> >> [snip] >> >> > >> >> >> > >> - When processing an SKB we end up in "xenvif_gop_frag_copy" >> while >> >> > prod >> >> > >> == cons ... but we still have bytes and size left .. >> >> > >> - start_new_rx_buffer() has returned true .. >> >> > >> - so we end up in get_next_rx_buffer >> >> > >> - this does a RING_GET_REQUEST and ups cons .. >> >> > >> - and we end up with a bad grant reference. >> >> > >> >> >> > >> Sometimes we are saved by the bell .. since additional slots have >> >> become >> >> > >> free (you see cons become > prod in "get_next_rx_buffer" but >> shortly >> >> > after >> >> > >> that prod is increased .. >> >> > >> just in time to not cause a overrun). >> >> > >> >> >> > >> >> > > Ah, but hang on... There's a BUG_ON meta_slots_used > >> >> > max_slots_needed, so if we are overflowing the worst-case calculation >> >> then >> >> > why is that BUG_ON not firing? >> >> > >> >> > You mean: >> >> > sco = (struct skb_cb_overlay *)skb->cb; >> >> > sco->meta_slots_used = xenvif_gop_skb(skb, &npo); >> >> > BUG_ON(sco->meta_slots_used > max_slots_needed); >> >> > >> >> > in "get_next_rx_buffer" ? >> >> > >> >> >> >> That code excerpt is from net_rx_action(),isn't it? >> >> >> >> > I don't know .. at least now it doesn't crash dom0 and therefore not my >> >> > complete machine and since tcp is recovering from a failed packet :-) >> >> > >> >> >> >> Well, if the code calculating max_slots_needed were underestimating >> then >> >> the BUG_ON() should fire. If it is not firing in your case then this suggests >> >> your problem lies elsewhere, or that meta_slots_used is not equal to the >> >> number of ring slots consumed. >> >> >> >> > But probably because "npo->copy_prod++" seems to be used for the >> frags >> >> .. >> >> > and it isn't added to npo->meta_prod ? >> >> > >> >> >> >> meta_slots_used is calculated as the value of meta_prod at return (from >> >> xenvif_gop_skb()) minus the value on entry , and if you look back up the >> >> code then you can see that meta_prod is incremented every time >> >> RING_GET_REQUEST() is evaluated. So, we must be consuming a slot >> without >> >> evaluating RING_GET_REQUEST() and I think that's exactly what's >> >> happening... Right at the bottom of xenvif_gop_frag_copy() req_cons is >> >> simply incremented in the case of a GSO. So the BUG_ON() is indeed off >> by >> >> one. >> >> >> >> > Can you re-test with the following patch applied? >> >> > Paul >> >> > diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen- >> netback/netback >> > index 438d0c0..4f24220 100644 >> > --- a/drivers/net/xen-netback/netback.c >> > +++ b/drivers/net/xen-netback/netback.c >> > @@ -482,6 +482,8 @@ static void xenvif_rx_action(struct xenvif *vif) >> >> > while ((skb = skb_dequeue(&vif->rx_queue)) != NULL) { >> > RING_IDX max_slots_needed; >> > + RING_IDX old_req_cons; >> > + RING_IDX ring_slots_used; >> > int i; >> >> > /* We need a cheap worse case estimate for the number of >> > @@ -511,8 +513,12 @@ static void xenvif_rx_action(struct xenvif *vif) >> > vif->rx_last_skb_slots = 0; >> >> > sco = (struct skb_cb_overlay *)skb->cb; >> > + >> > + old_req_cons = vif->rx.req_cons; >> > sco->meta_slots_used = xenvif_gop_skb(skb, &npo); >> > - BUG_ON(sco->meta_slots_used > max_slots_needed); >> > + ring_slots_used = vif->rx.req_cons - old_req_cons; >> > + >> > + BUG_ON(ring_slots_used > max_slots_needed); >> >> > __skb_queue_tail(&rxq, skb); >> > } >> >> That blew pretty fast .. on that BUG_ON >> > Good. That's what should have happened :-) Yes .. and No .. We shouldn't be there in the first place :-) Since now every miscalculation in the needed slots leads to a nice remote DOS attack .. (since we now crash the vif kthread) it would be nice to have a worst case slot calculation .. with some theoretical guarantees -- Sander > Paul >> [ 290.218182] ------------[ cut here ]------------ >> [ 290.225425] kernel BUG at drivers/net/xen-netback/netback.c:664! >> [ 290.232717] invalid opcode: 0000 [#1] SMP >> [ 290.239875] Modules linked in: >> [ 290.246923] CPU: 0 PID: 10447 Comm: vif7.0 Not tainted 3.13.6-20140326- >> nbdebug35+ #1 >> [ 290.254040] Hardware name: MSI MS-7640/890FXA-GD70 (MS-7640) , BIOS >> V1.8B1 09/13/2010 >> [ 290.261313] task: ffff880055d16480 ti: ffff88004cb7e000 task.ti: >> ffff88004cb7e000 >> [ 290.268713] RIP: e030:[] [] >> xenvif_rx_action+0x1650/0x1670 >> [ 290.276193] RSP: e02b:ffff88004cb7fc28 EFLAGS: 00010202 >> [ 290.283555] RAX: 0000000000000006 RBX: ffff88004c630000 RCX: >> 3fffffffffffffff >> [ 290.290908] RDX: 00000000ffffffff RSI: ffff88004c630940 RDI: >> 0000000000048e7b >> [ 290.298325] RBP: ffff88004cb7fde8 R08: 0000000000007bc9 R09: >> 0000000000000005 >> [ 290.305809] R10: ffff88004cb7fd28 R11: ffffc90012690600 R12: >> 0000000000000004 >> [ 290.313217] R13: ffff8800536a84e0 R14: 0000000000000001 R15: >> ffff88004c637618 >> [ 290.320521] FS: 00007f1d3030c700(0000) GS:ffff88005f600000(0000) >> knlGS:0000000000000000 >> [ 290.327839] CS: e033 DS: 0000 ES: 0000 CR0: 000000008005003b >> [ 290.335216] CR2: ffffffffff600400 CR3: 0000000058537000 CR4: >> 0000000000000660 >> [ 290.342732] Stack: >> [ 290.350129] ffff88004cb7fd2c ffff880000000005 ffff88004cb7fd28 >> ffffffff810f7fc8 >> [ 290.357652] ffff880055d16b50 ffffffff00000407 ffff880000000000 >> ffffffff00000000 >> [ 290.365048] ffff880055d16b50 ffff880000000001 ffff880000000001 >> ffffffff00000000 >> [ 290.372461] Call Trace: >> [ 290.379806] [] ? __lock_acquire+0x418/0x2220 >> [ 290.387211] [] ? finish_task_switch+0x46/0xf0 >> [ 290.394552] [] xenvif_kthread+0x40/0x190 >> [ 290.401808] [] ? __init_waitqueue_head+0x60/0x60 >> [ 290.408993] [] ? xenvif_stop_queue+0x60/0x60 >> [ 290.416238] [] kthread+0xe4/0x100 >> [ 290.423428] [] ? _raw_spin_unlock_irq+0x30/0x50 >> [ 290.430615] [] ? __init_kthread_worker+0x70/0x70 >> [ 290.437793] [] ret_from_fork+0x7c/0xb0 >> [ 290.444945] [] ? __init_kthread_worker+0x70/0x70 >> [ 290.452091] Code: fd ff ff 48 8b b5 f0 fe ff ff 48 c7 c2 10 98 ce 81 31 c0 48 8b >> be c8 7c 00 00 48 c7 c6 f0 f1 fd 81 e8 35 be 24 00 e9 ba f8 ff ff <0f> 0b 0f 0b 41 >> bf 01 00 00 00 e9 55 f6 ff ff 0f 0b 66 66 66 66 >> [ 290.467121] RIP [] xenvif_rx_action+0x1650/0x1670 >> [ 290.474436] RSP >> [ 290.482400] ---[ end trace 2fcf9e9ae26950b3 ]---