Re: [Xen-devel] [PATCH v2 3/6] x86: track when in #MC context

From: "Roger Pau Monné" <roger.pau@citrix.com>
To: Julien Grall <julien@xen.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>, Wei Liu <wl@xen.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	George Dunlap <George.Dunlap@eu.citrix.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	Jan Beulich <jbeulich@suse.com>,
	xen-devel@lists.xenproject.org
Subject: Re: [Xen-devel] [PATCH v2 3/6] x86: track when in #MC context
Date: Tue, 18 Feb 2020 10:45:34 +0100	[thread overview]
Message-ID: <20200218094534.GO4679@Air-de-Roger> (raw)
In-Reply-To: <69fbdc2a-e64b-ff93-6392-661ca71a88a7@xen.org>

On Mon, Feb 17, 2020 at 07:29:29PM +0000, Julien Grall wrote:
> Hi Roger,
> 
> On 17/02/2020 18:43, Roger Pau Monne wrote:
> > Add helpers to track when executing in #MC context. This is modeled
> > after the in_irq helpers.
> > 
> > Note that there are no users of in_mc() introduced by the change,
> > further users will be added by followup changes.
> > 
> > Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
> > ---
> >   xen/arch/x86/cpu/mcheck/mce.c | 2 ++
> >   xen/include/asm-x86/hardirq.h | 5 +++++
> >   xen/include/xen/irq_cpustat.h | 1 +
> >   3 files changed, 8 insertions(+)
> > 
> > diff --git a/xen/arch/x86/cpu/mcheck/mce.c b/xen/arch/x86/cpu/mcheck/mce.c
> > index d61e582af3..93ed5752ac 100644
> > --- a/xen/arch/x86/cpu/mcheck/mce.c
> > +++ b/xen/arch/x86/cpu/mcheck/mce.c
> > @@ -93,7 +93,9 @@ void x86_mce_vector_register(x86_mce_vector_t hdlr)
> >   void do_machine_check(const struct cpu_user_regs *regs)
> >   {
> > +    mc_enter();
> >       _machine_check_vector(regs);
> > +    mc_exit();
> >   }
> >   /*
> > diff --git a/xen/include/asm-x86/hardirq.h b/xen/include/asm-x86/hardirq.h
> > index 34e1b49260..af3eab6a4d 100644
> > --- a/xen/include/asm-x86/hardirq.h
> > +++ b/xen/include/asm-x86/hardirq.h
> > @@ -8,6 +8,7 @@ typedef struct {
> >   	unsigned int __softirq_pending;
> >   	unsigned int __local_irq_count;
> >   	unsigned int __nmi_count;
> > +	unsigned int mc_count;
> >   	bool_t __mwait_wakeup;
> >   } __cacheline_aligned irq_cpustat_t;
> > @@ -18,6 +19,10 @@ typedef struct {
> >   #define irq_enter()	(local_irq_count(smp_processor_id())++)
> >   #define irq_exit()	(local_irq_count(smp_processor_id())--)
> > +#define in_mc() 	(mc_count(smp_processor_id()) != 0)
> > +#define mc_enter()	(mc_count(smp_processor_id())++)
> > +#define mc_exit()	(mc_count(smp_processor_id())--)
> > +
> >   void ack_bad_irq(unsigned int irq);
> >   extern void apic_intr_init(void);
> > diff --git a/xen/include/xen/irq_cpustat.h b/xen/include/xen/irq_cpustat.h
> > index 73629f6ec8..12b932fc39 100644
> > --- a/xen/include/xen/irq_cpustat.h
> > +++ b/xen/include/xen/irq_cpustat.h
> > @@ -26,5 +26,6 @@ extern irq_cpustat_t irq_stat[];
> >   #define local_irq_count(cpu)	__IRQ_STAT((cpu), __local_irq_count)
> >   #define nmi_count(cpu)		__IRQ_STAT((cpu), __nmi_count)
> >   #define mwait_wakeup(cpu)	__IRQ_STAT((cpu), __mwait_wakeup)
> > +#define mc_count(cpu)		__IRQ_STAT((cpu), mc_count)
> 
> The header is only meant to contain arch-independent IRQ stats (see comment
> a few lines above). This is unlikely to be used on Arm, so can you move this
> into an x86 specific header?

Uh, sure. Sorry for not realizing this.

Thanks, Roger.

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xenproject.org
https://lists.xenproject.org/mailman/listinfo/xen-devel