From 7ed98e0168bd23d8ea3294e95254cc5b4000c948 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 10 Mar 2017 10:46:14 +0000 Subject: drivers/perf: arm_pmu: manage interrupts per-cpu When requesting or freeing interrupts, we use platform_get_irq() to find relevant irqs, backing this up with additional information in an optional irq_affinity table. This means that our irq request and free paths are tied to a platform_device, and our request path must jump through a number of hoops in order to determine the required affinity of each interrupt. Given that the affinity must be static, we can compute the affinity once up-front at probe time, simplifying the irq request and free paths. By recording interrupts in a per-cpu data structure, we simplify a few paths, and permit a subsequent rework of the request and free paths. Signed-off-by: Mark Rutland [will: rename local nr_irqs variable to avoid conflict with global] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 8462da266089..05a3eb447fc8 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -75,6 +75,8 @@ struct pmu_hw_events { * already have to allocate this struct per cpu. */ struct arm_pmu *percpu_pmu; + + int irq; }; enum armpmu_attr_groups { @@ -88,7 +90,6 @@ struct arm_pmu { struct pmu pmu; cpumask_t active_irqs; cpumask_t supported_cpus; - int *irq_affinity; char *name; irqreturn_t (*handle_irq)(int irq_num, void *dev); void (*enable)(struct perf_event *event); -- cgit v1.2.3 From c09adab01e4aeecfa3dfae0946409844400c5901 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 10 Mar 2017 10:46:15 +0000 Subject: drivers/perf: arm_pmu: split irq request from enable For historical reasons, we lazily request and free interrupts in the arm pmu driver. This requires us to refcount use of the pmu (by way of counting the active events) in order to request/free interrupts at the correct times, which complicates the driver somewhat. The existing logic is flawed, as it only considers currently online CPUs when requesting, freeing, or managing the affinity of interrupts. Intervening hotplug events can result in erroneous IRQ affinity, online CPUs for which interrupts have not been requested, or offline CPUs whose interrupts are still requested. To fix this, this patch splits the requesting of interrupts from any per-cpu management (i.e. per-cpu enable/disable, and configuration of cpu affinity). We now request all interrupts up-front at probe time (and never free them, since we never unregister PMUs). The management of affinity, and per-cpu enable/disable now happens in our cpu hotplug callback, ensuring it occurs consistently. This means that we must now invoke the CPU hotplug callback at boot time in order to configure IRQs, and since the callback also resets the PMU hardware, we can remove the duplicate reset in the probe path. This rework renders our event refcounting unnecessary, so this is removed. Signed-off-by: Mark Rutland [will: make armpmu_get_cpu_irq static] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 05a3eb447fc8..44f43fcf2524 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -105,12 +105,8 @@ struct arm_pmu { void (*start)(struct arm_pmu *); void (*stop)(struct arm_pmu *); void (*reset)(void *); - int (*request_irq)(struct arm_pmu *, irq_handler_t handler); - void (*free_irq)(struct arm_pmu *); int (*map_event)(struct perf_event *event); int num_events; - atomic_t active_events; - struct mutex reserve_mutex; u64 max_period; bool secure_access; /* 32-bit ARM only */ #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 -- cgit v1.2.3 From 3071f13d75f627ed8648535815a0506d50cbc6ed Mon Sep 17 00:00:00 2001 From: Agustin Vega-Frias Date: Fri, 31 Mar 2017 14:13:43 -0400 Subject: perf: qcom: Add L3 cache PMU driver This adds a new dynamic PMU to the Perf Events framework to program and control the L3 cache PMUs in some Qualcomm Technologies SOCs. The driver supports a distributed cache architecture where the overall cache for a socket is comprised of multiple slices each with its own PMU. Access to each individual PMU is provided even though all CPUs share all the slices. User space needs to aggregate to individual counts to provide a global picture. The driver exports formatting and event information to sysfs so it can be used by the perf user space tools with the syntaxes: perf stat -a -e l3cache_0_0/read-miss/ perf stat -a -e l3cache_0_0/event=0x21/ Acked-by: Mark Rutland Signed-off-by: Agustin Vega-Frias [will: fixed sparse issues] Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 62d240e962f0..cfcfab37d9c4 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -137,6 +137,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_CCN_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, + CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, CPUHP_AP_WORKQUEUE_ONLINE, CPUHP_AP_RCUTREE_ONLINE, CPUHP_AP_ONLINE_DYN, -- cgit v1.2.3 From 083c52144a19c69b7956aa53c913ba621f7c5ae2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:45 +0100 Subject: drivers/perf: arm_pmu: define armpmu_init_fn We expect an ARM PMU's init function to have a particular prototype, which we open-code in a few places. This is less than ideal, considering that we cast a void value to this type in one location, and a mismatch could easily be missed. Add a typedef so that we can ensure this is consistent. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 44f43fcf2524..4249914315a4 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -132,10 +132,12 @@ int armpmu_map_event(struct perf_event *event, [PERF_COUNT_HW_CACHE_RESULT_MAX], u32 raw_event_mask); +typedef int (*armpmu_init_fn)(struct arm_pmu *); + struct pmu_probe_info { unsigned int cpuid; unsigned int mask; - int (*init)(struct arm_pmu *); + armpmu_init_fn init; }; #define PMU_PROBE(_cpuid, _mask, _fn) \ -- cgit v1.2.3 From 18bfcfe51b8f60b69ab012888dea8061a9cd3381 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:53 +0100 Subject: drivers/perf: arm_pmu: split out platform device probe logic Now that we've split the pdev and DT probing logic from the runtime management, let's move the former into its own file. We gain a few lines due to the copyright header and includes, but this should keep the logic clearly separated, and paves the way for adding ACPI support in a similar fashion. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton [will: rename nr_irqs to avoid conflict with global variable] Signed-off-by: Will Deacon --- include/linux/perf/arm_pmu.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 4249914315a4..25556ebb1c7b 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -159,6 +159,13 @@ int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table); +/* Internal functions only for core arm_pmu code */ +struct arm_pmu *armpmu_alloc(void); +void armpmu_free(struct arm_pmu *pmu); +int armpmu_register(struct arm_pmu *pmu); +int armpmu_request_irqs(struct arm_pmu *armpmu); +void armpmu_free_irqs(struct arm_pmu *armpmu); + #define ARMV8_PMU_PDEV_NAME "armv8-pmu" #endif /* CONFIG_ARM_PMU */ -- cgit v1.2.3 From 45736a72fb79b204c1fbdb08a1e1a2aa52c7281a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 11 Apr 2017 09:39:55 +0100 Subject: drivers/perf: arm_pmu: add ACPI framework This patch adds framework code to handle parsing PMU data out of the MADT, sanity checking this, and managing the association of CPUs (and their interrupts) with appropriate logical PMUs. For the time being, we expect that only one PMU driver (PMUv3) will make use of this, and we simply pass in a single probe function. This is based on an earlier patch from Jeremy Linton. Signed-off-by: Mark Rutland Tested-by: Jeremy Linton Cc: Will Deacon Signed-off-by: Will Deacon --- include/linux/cpuhotplug.h | 1 + include/linux/perf/arm_pmu.h | 11 +++++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index cfcfab37d9c4..0f2a80377520 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -94,6 +94,7 @@ enum cpuhp_state { CPUHP_AP_ARM_VFP_STARTING, CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING, CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING, + CPUHP_AP_PERF_ARM_ACPI_STARTING, CPUHP_AP_PERF_ARM_STARTING, CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 25556ebb1c7b..1360dd6d5e61 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -117,6 +117,9 @@ struct arm_pmu { struct notifier_block cpu_pm_nb; /* the attr_groups array must be NULL-terminated */ const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1]; + + /* Only to be used by ACPI probing code */ + unsigned long acpi_cpuid; }; #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) @@ -159,12 +162,20 @@ int arm_pmu_device_probe(struct platform_device *pdev, const struct of_device_id *of_table, const struct pmu_probe_info *probe_table); +#ifdef CONFIG_ACPI +int arm_pmu_acpi_probe(armpmu_init_fn init_fn); +#else +static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } +#endif + /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); int armpmu_request_irqs(struct arm_pmu *armpmu); void armpmu_free_irqs(struct arm_pmu *armpmu); +int armpmu_request_irq(struct arm_pmu *armpmu, int cpu); +void armpmu_free_irq(struct arm_pmu *armpmu, int cpu); #define ARMV8_PMU_PDEV_NAME "armv8-pmu" -- cgit v1.2.3