From: Wei Liu Subject: Re: [PATCH v2] xen: credit1: fix tickling when it happens from a remote pCPU Date: Fri, 25 Sep 2015 12:05:13 +0100 Message-ID: <20150925110513.GD4967@zion.uk.xensource.com> References: <20150925074602.7275.97419.stgit@Solace.station> <1443168645.3276.46.camel@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Received: from mail6.bemta14.messagelabs.com ([193.109.254.103]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1ZfQoY-0003tV-GS for xen-devel@lists.xenproject.org; Fri, 25 Sep 2015 11:05:18 +0000 Content-Disposition: inline In-Reply-To: <1443168645.3276.46.camel@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Dario Faggioli Cc: Juergen Gross , George Dunlap , Wei Liu , Jan Beulich , xen-devel@lists.xenproject.org List-Id: xen-devel@lists.xenproject.org On Fri, Sep 25, 2015 at 10:10:45AM +0200, Dario Faggioli wrote: > Hey Wei, > > On Fri, 2015-09-25 at 09:46 +0200, Dario Faggioli wrote: > > > For instance, this can happen when an HVM domain runs in a cpupool, > > with a different scheduler than the default one, and issues IOREQs > > to Dom0, running in Pool-0 with the default scheduler. > > In fact, right in this case, the following crash can be observed: > > > (XEN) ----[ Xen-4.7-unstable x86_64 debug=y Tainted: C ]---- > > (XEN) CPU: 7 > > (XEN) RIP: e008:[] __runq_tickle+0x18f/0x430 > > (XEN) RFLAGS: 0000000000010086 CONTEXT: hypervisor (d1v0) > > (XEN) rax: 0000000000000001 rbx: ffff8303184fee00 rcx: > > 0000000000000000 > > (XEN) ... ... ... > > (XEN) Xen stack trace from rsp=ffff83031fa57a08: > > (XEN) ffff82d0801fe664 ffff82d08033c820 0000000100000002 > > 0000000a00000001 > > (XEN) 0000000000006831 0000000000000000 0000000000000000 > > 0000000000000000 > > (XEN) ... ... ... > > (XEN) Xen call trace: > > (XEN) [] __runq_tickle+0x18f/0x430 > > (XEN) [] csched_vcpu_wake+0x10b/0x110 > > (XEN) [] vcpu_wake+0x20a/0x3ce > > (XEN) [] vcpu_unblock+0x4b/0x4e > > (XEN) [] vcpu_kick+0x17/0x61 > > (XEN) [] vcpu_mark_events_pending+0x2c/0x2f > > (XEN) [] evtchn_fifo_set_pending+0x381/0x3f6 > > (XEN) [] notify_via_xen_event_channel+0xc9/0xd6 > > (XEN) [] hvm_send_ioreq+0x3e9/0x441 > > (XEN) [] hvmemul_do_io+0x23f/0x2d2 > > (XEN) [] hvmemul_do_io_buffer+0x33/0x64 > > (XEN) [] hvmemul_do_pio_buffer+0x35/0x37 > > (XEN) [] handle_pio+0x58/0x14c > > (XEN) [] vmx_vmexit_handler+0x16b3/0x1bea > > (XEN) [] vmx_asm_vmexit_handler+0x41/0xc0 > > > This patch is a bugfix, so I think it should be included in 4.6. > > I'm able to trigger the above Oops pretty reliably by running an HVM > guest in a cpupool that has a scheduler different than Credit (by, > e.g., starting some load in the guest itself, or even just simply doing > `xl shutdown' on it). > > It may not be the most common of the configurations, but I think it's > worth. > Release-acked-by: Wei Liu > Thanks and Regards, > Dario > -- > <> (Raistlin Majere) > ----------------------------------------------------------------- > Dario Faggioli, Ph.D, http://about.me/dario.faggioli > Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK) >