pmu: armv7_a9_pmu_init() fails with -ENXIO
Hello,
On my (dual-core) system, armv7_a9_pmu_init() fails with -ENXIO (I'm running v4.2)
[ 0.090148] cpu=4 nr_cpu_ids=2 [ 0.090164] armv7_a9_pmu_init: ret=-6 [ 0.090171] hw perfevents: failed to probe PMU! [ 0.090175] hw perfevents: failed to register PMU devices!
armv7_a9_pmu_init() eventually calls generic_exec_single() which fails this test:
if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))
cpu = 4 looks fishy, doesn't it? <grasping@straws> I'm wondering if commit 0e3038d18adce or commit cc88116da0d18 might be related at all?
The value 4 comes from smp_call_function_any()
/* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask);
mask = &arm_pmu->supported_cpus
p arm_pmu->supported_cpus
$3 = {bits = {0}}
/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Returns >= nr_cpu_ids if no further cpus set in both. */
Shouldn't cpu_pmu->supported_cpus be cpu_present_mask or cpu_possible_mask? Shouldn't armv7pmu_init() set arm_pmu->supported_cpus?
Regards.
Quoted 35 lines · Mason
On my (dual-core) system,
armv7_a9_pmu_init()fails with-ENXIO(I'm running v4.2)[ 0.090148] cpu=4 nr_cpu_ids=2 [ 0.090164] armv7_a9_pmu_init: ret=-6 [ 0.090171] hw perfevents: failed to probe PMU! [ 0.090175] hw perfevents: failed to register PMU devices!
armv7_a9_pmu_init()eventually callsgeneric_exec_single()which fails this test:if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu))cpu = 4 looks fishy, doesn't it? <grasping@straws> I'm wondering if commit
0e3038d18adceor commitcc88116da0d18might be related at all?The value 4 comes from
smp_call_function_any()/* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask);mask =
&arm_pmu->supported_cpus
parm_pmu->supported_cpus
$3 = {bits = {0}}/**
*cpumask_next_and- get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Returns >=nr_cpu_idsif no further cpus set in both. */
Quoted 2 lines
Shouldn't
cpu_pmu->supported_cpusbecpu_present_maskorcpu_possible_mask? Shouldn'tarmv7pmu_init()setarm_pmu->supported_cpus?
Looking more closely at Documentation/devicetree/bindings/arm/pmu.txt I now see commit 71bbf038eaa44
- interrupt-affinity : Valid only when using SPIs, specifies a list of phandles to CPU nodes corresponding directly to the affinity of the SPIs listed in the interrupts property.
This property should be present when there is more than a single SPI.
I currently have
pmu {
compatible = "arm,cortex-a9-pmu";
interrupts =
<GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>;
};<confused> I wrote the above node by sampling other platforms, and they don't define any interrupt-affinity property, e.g.
exynos4415.dtsi:
pmu {
compatible = "arm,cortex-a9-pmu";
interrupts = <0 18 0>, <0 19 0>, <0 20 0>, <0 21 0>;
};exynos5440.dtsi:
arm-pmu {
compatible = "arm,cortex-a15-pmu", "arm,cortex-a9-pmu";
interrupts = <0 52 4>,
<0 53 4>,
<0 54 4>,
<0 55 4>;
};highbank.dts:
pmu {
compatible = "arm,cortex-a9-pmu";
interrupts = <0 76 4 0 75 4 0 74 4 0 73 4>;
};omap4460.dtsi:
pmu {
compatible = "arm,cortex-a9-pmu";
interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
ti,hwmods = "debugss";
};I also looked more closely at of_pmu_irq_cfg()
platform_get_irq(pdev, 0); returns -6pdev->num_resources is 0 therefore...
if (i == pdev->num_resources) {
pmu->irq_affinity = irqs;
} else {
kfree(irqs);
cpumask_setall(&pmu->supported_cpus);
}pmu->irq_affinity gets set to an invalid pointer (0x00000010) and cpumask_setall() is not called.
Something is not working as expected, right?
Regards.
On 21/10/15 14:46, Mason wrote:
[...]
Quoted 4 lines
I also looked more closely at
of_pmu_irq_cfg()
platform_get_irq(pdev, 0); returns -6
Won't it return here ? Though you must first check why is that returning error.
irq = platform_get_irq(pdev, 0);
if (irq >= 0 && irq_is_percpu(irq))
return 0;Quoted 9 lines
pdev->num_resourcesis 0 therefore...if (i == pdev->num_resources) { pmu->irq_affinity = irqs; } else { kfree(irqs); cpumask_setall(&pmu->supported_cpus); }
Quoted 5 lines
pmu->irq_affinitygets set to an invalid pointer (0x00000010) andcpumask_setall()is not called.Something is not working as expected, right?
So you won't execute this in that case.
Sorry if I missed something, I briefly checked v4.2 Code have been changed and even moved since then.
Signature · 2 lines
Regards, Sudeep
Quoted 4 lines · Sudeep Holla
Quoted 2 lines · Mason
I also looked more closely at
of_pmu_irq_cfg()
Quoted 8 lines
Quoted 1 line
platform_get_irq(pdev, 0); returns -6Won't it return here ?
Though you must first check why is that returning error.irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) return 0;
Thanks for prodding me in the right direction. platform_get_irq() was failing because I hadn't properly defined the node's interrupt-parent...
I've added
interrupt-parent = <&gic>;
at the root of my DT, and things now work as expected. (Haven't tested actually using the counters yet.)
[ 0.090058] irq=212 irqs=e7603400 pdev->num_resources=2 [ 0.090091] hw perfevents: Failed to parse /pmu/interrupt-affinity[0] [ 0.090103] armv7_a9_pmu_init: ret=0 [ 0.090145] hw perfevents: enabled with armv7_cortex_a9 PMU driver, 7 counters available
Thanks again.
Regards.
Quoted 11 lines · Mason
Quoted 9 lines · Sudeep Holla
Quoted 3 lines · Mason
I also looked more closely at
of_pmu_irq_cfg()
platform_get_irq(pdev, 0); returns -6Won't it return here ?
Though you must first check why is that returning error.
Quoted 8 lines
Quoted 3 lines
irq = platform_get_irq(pdev, 0); if (irq >= 0 && irq_is_percpu(irq)) return 0;Thanks for prodding me in the right direction.
platform_get_irq()was failing because I hadn't properly defined the node's interrupt-parent...
Yes that's what I guessed seeing of_irq_get.
Quoted 7 lines
I've added
interrupt-parent = <&gic>;
at the root of my DT, and things now work as expected. (Haven't tested actually using the counters yet.)[ 0.090058] irq=212 irqs=e7603400 pdev->num_resources=2 [ 0.090091] hw perfevents: Failed to parse /pmu/interrupt-affinity[0]
Better to add this property. It assigns the cpu affinity in logical order which might break if your logical and physical cpu ordering differs.(e.g. you boot on CPU#1 instead of CPU#0)
Quoted 3 lines
[ 0.090103] armv7_a9_pmu_init: ret=0 [ 0.090145] hw perfevents: enabled with armv7_cortex_a9 PMU driver, 7 counters available
Cool
Signature · 2 lines
Regards, Sudeep