[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1452902519-2754-205-git-send-email-kamal@canonical.com>
Date: Fri, 15 Jan 2016 16:00:18 -0800
From: Kamal Mostafa <kamal@...onical.com>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org,
kernel-team@...ts.ubuntu.com
Cc: Marc Zyngier <marc.zyngier@....com>,
Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>,
Alexey Brodkin <abrodkin@...opsys.com>,
Vineet Gupta <vgupta@...opsys.com>,
Kamal Mostafa <kamal@...onical.com>
Subject: [PATCH 4.2.y-ckt 204/305] ARCv2: intc: Fix random perf irq disabling in SMP setup
4.2.8-ckt2 -stable review patch. If anyone has any objections, please let me know.
---8<------------------------------------------------------------
From: Vineet Gupta <vgupta@...opsys.com>
commit 8eb0984bf4fe82237f95481ff0afe514a676c717 upstream.
As part of fixing another perf issue, observed that after a perf run,
the interrupt got disabled on one/more cores.
Turns out that despite requesting perf irq as percpu, the flow handler
registered was not handle_percpu_irq()
Given that on ARCv2 cores, IRQs < 24 are always private to cpu, we
register the right handler at the very onset.
Before Fix
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 0 0 0 0 ARCv2 core Intc 20 ARC perf counters
|
| [ARCLinux]# perf record -c 20000 /sbin/hackbench
| Running with 10*40 (== 400) tasks.
|
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 0 522 8 51916 ARCv2 core Intc 20 ARC perf counters
|
| [ARCLinux]# perf record -c 20000 /sbin/hackbench
| Running with 10*40 (== 400) tasks.
|
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 0 522 8 104368 ARCv2 core Intc 20 ARC perf counters
After Fix
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 0 0 0 0 ARCv2 core Intc 20 ARC perf counters
|
| [ARCLinux]# perf record -c 20000 /sbin/hackbench
| Running with 10*40 (== 400) tasks.
|
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 64198 62012 62697 67803 ARCv2 core Intc 20 ARC perf counters
|
| [ARCLinux]# perf record -c 20000 /sbin/hackbench
| Running with 10*40 (== 400) tasks.
|
| [ARCLinux]# cat /proc/interrupts | grep perf
| 20: 126014 122792 123301 133654 ARCv2 core Intc 20 ARC perf counters
Cc: Marc Zyngier <marc.zyngier@....com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Alexey Brodkin <abrodkin@...opsys.com>
Cc: linux-kernel@...r.kernel.org
Signed-off-by: Vineet Gupta <vgupta@...opsys.com>
Signed-off-by: Kamal Mostafa <kamal@...onical.com>
---
arch/arc/kernel/intc-arcv2.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 26c1568..0394f9f 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = {
static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
irq_hw_number_t hw)
{
- if (irq == TIMER0_IRQ || irq == IPI_IRQ)
+ /*
+ * core intc IRQs [16, 23]:
+ * Statically assigned always private-per-core (Timers, WDT, IPI, PCT)
+ */
+ if (hw < 24) {
+ /*
+ * A subsequent request_percpu_irq() fails if percpu_devid is
+ * not set. That in turns sets NOAUTOEN, meaning each core needs
+ * to call enable_percpu_irq()
+ */
+ irq_set_percpu_devid(irq);
irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
- else
+ } else {
irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+ }
return 0;
}
--
1.9.1
Powered by blists - more mailing lists