Re: [Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-26 Thread David Vrabel
On 23/01/15 18:58, Luis R. Rodriguez wrote: Its not just hypercalls though, this is all about the interactions with multicalls no? No. This applies to any preemptible hypercall and the toolstack doesn't use multicalls for most of its work. David -- To unsubscribe from this list: send the

Re: [Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-26 Thread Jan Beulich
On 23.01.15 at 19:58, mcg...@suse.com wrote: On Fri, Jan 23, 2015 at 11:45:06AM +, David Vrabel wrote: On 23/01/15 00:29, Luis R. Rodriguez wrote: @@ -1243,6 +1247,25 @@ void xen_evtchn_do_upcall(struct pt_regs *regs) set_irq_regs(old_regs); } +/* + * CONFIG_PREEMPT=n

Re: [Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-23 Thread Luis R. Rodriguez
On Fri, Jan 23, 2015 at 11:45:06AM +, David Vrabel wrote: On 23/01/15 00:29, Luis R. Rodriguez wrote: From: Luis R. Rodriguez mcg...@suse.com Xen has support for splitting heavy work work into a series of hypercalls, called multicalls, and preempting them through what Xen calls

Re: [Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-23 Thread Luis R. Rodriguez
On Fri, Jan 23, 2015 at 11:45:06AM +, David Vrabel wrote: + */ +void xen_end_upcall(struct pt_regs *regs) +{ + if (xen_is_preemptible_hypercall(regs)) { + int cpuid = smp_processor_id(); + if (_cond_resched()) +

Re: [Xen-devel] [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-23 Thread David Vrabel
On 23/01/15 00:29, Luis R. Rodriguez wrote: From: Luis R. Rodriguez mcg...@suse.com Xen has support for splitting heavy work work into a series of hypercalls, called multicalls, and preempting them through what Xen calls continuation [0]. Despite this though without CONFIG_PREEMPT

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-22 Thread Steven Rostedt
On Thu, 22 Jan 2015 17:40:27 -0800 Andy Lutomirski l...@amacapital.net wrote: +/* + * CONFIG_PREEMPT=n kernels can end up triggering the softlock + * TASK_UNINTERRUPTIBLE hanger check (default 120 seconds) + * when certain multicalls are used [0] on large systems, in + * that case we

[RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-22 Thread Luis R. Rodriguez
From: Luis R. Rodriguez mcg...@suse.com Xen has support for splitting heavy work work into a series of hypercalls, called multicalls, and preempting them through what Xen calls continuation [0]. Despite this though without CONFIG_PREEMPT preemption won't happen, without preemption a system can

Re: [RFC v4 2/2] x86/xen: allow privcmd hypercalls to be preempted

2015-01-22 Thread Andy Lutomirski
On Thu, Jan 22, 2015 at 4:29 PM, Luis R. Rodriguez mcg...@do-not-panic.com wrote: From: Luis R. Rodriguez mcg...@suse.com Xen has support for splitting heavy work work into a series of hypercalls, called multicalls, and preempting them through what Xen calls continuation [0]. Despite this