[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1334938265-3844-1-git-send-email-mlin@ss.pku.edu.cn>
Date: Sat, 21 Apr 2012 00:11:03 +0800
From: Lin Ming <mlin@...pku.edu.cn>
To: Konrad Rzeszutek Wilk <konrad.wilk@...cle.com>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Steven Noonan <steven@...inklabs.net>,
Ben Guthro <ben@...hro.net>,
Jeremy Fitzhardinge <jeremy@...p.org>,
Marcus Granado <marcus.granado@...rix.com>,
xen-devel@...ts.xen.org, linux-kernel@...r.kernel.org
Subject: [PATCH v2 0/2] fix "perf top" soft lockups under Xen
v2:
- fix compile issues if no CONFIG_SMP, Konrad Rzeszutek Wilk
- move inc_irq_stat after irq_work_run
These 2 patches fixed the "perf top" soft lockups under Xen
reported by Steven at: https://lkml.org/lkml/2012/2/9/506
Both Steven and I tested it and "perf top" works well now.
The soft lockup code path is:
__irq_work_queue
arch_irq_work_raise
apic->send_IPI_self(IRQ_WORK_VECTOR);
apic_send_IPI_self
__default_send_IPI_shortcut
__xapic_wait_icr_idle
static inline void __xapic_wait_icr_idle(void)
{
while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY)
cpu_relax();
}
The lockup happens at above while looop.
The cause is that Xen has not implemented the APIC IPI interface yet.
Xen has IPI interface: xen_send_IPI_one, but it's only used in
xen_smp_send_reschedule, xen_smp_send_call_function_ipi and
xen_smp_send_call_function_single_ipi, etc.
So we need to implement Xen's APIC IPI interface as Ben's patch does.
And implement Xen's IRQ_WORK_VECTOR handler.
Ben Guthro (1):
xen: implement apic ipi interface
Lin Ming (1):
xen: implement IRQ_WORK_VECTOR handler
arch/x86/include/asm/xen/events.h | 1 +
arch/x86/xen/enlighten.c | 9 +++
arch/x86/xen/smp.c | 111 +++++++++++++++++++++++++++++++++++-
arch/x86/xen/smp.h | 12 ++++
4 files changed, 129 insertions(+), 4 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists