OpenCloudOS-Kernel/drivers/gpu/drm/i915/i915_pmu.h

126 lines
3.1 KiB
C
Raw Normal View History

drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
/*
* SPDX-License-Identifier: MIT
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
*
* Copyright © 2017-2018 Intel Corporation
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
*/
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
#ifndef __I915_PMU_H__
#define __I915_PMU_H__
#include <linux/hrtimer.h>
#include <linux/perf_event.h>
#include <linux/spinlock_types.h>
#include <drm/i915_drm.h>
struct drm_i915_private;
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
enum {
__I915_SAMPLE_FREQ_ACT = 0,
__I915_SAMPLE_FREQ_REQ,
drm/i915/pmu: Fix sleep under atomic in RC6 readout We are not allowed to call intel_runtime_pm_get from the PMU counter read callback since the former can sleep, and the latter is running under IRQ context. To workaround this, we record the last known RC6 and while runtime suspended estimate its increase by querying the runtime PM core timestamps. Downside of this approach is that we can temporarily lose a chunk of RC6 time, from the last PMU read-out to runtime suspend entry, but that will eventually catch up, once device comes back online and in the presence of PMU queries. Also, we have to be careful not to overshoot the RC6 estimate, so once resumed after a period of approximation, we only update the counter once it catches up. With the observation that RC6 is increasing while the device is suspended, this should not pose a problem and can only cause slight inaccuracies due clock base differences. v2: Simplify by estimating on top of PM core counters. (Imre) Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104943 Fixes: 6060b6aec03c ("drm/i915/pmu: Add RC6 residency metrics") Testcase: igt/perf_pmu/rc6-runtime-pm Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Imre Deak <imre.deak@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20180206183311.17924-1-tvrtko.ursulin@linux.intel.com
2018-02-07 02:33:11 +08:00
__I915_SAMPLE_RC6,
__I915_SAMPLE_RC6_ESTIMATED,
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
__I915_NUM_PMU_SAMPLERS
};
/**
* How many different events we track in the global PMU mask.
*
* It is also used to know to needed number of event reference counters.
*/
#define I915_PMU_MASK_BITS \
((1 << I915_PMU_SAMPLE_BITS) + \
(I915_PMU_LAST + 1 - __I915_PMU_OTHER(0)))
#define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1)
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
struct i915_pmu_sample {
u64 cur;
};
struct i915_pmu {
/**
* @node: List node for CPU hotplug handling.
*/
struct hlist_node node;
/**
* @base: PMU base.
*/
struct pmu base;
/**
* @lock: Lock protecting enable mask and ref count handling.
*/
spinlock_t lock;
/**
* @timer: Timer for internal i915 PMU sampling.
*/
struct hrtimer timer;
/**
* @enable: Bitmask of all currently enabled events.
*
* Bits are derived from uAPI event numbers in a way that low 16 bits
* correspond to engine event _sample_ _type_ (I915_SAMPLE_QUEUED is
* bit 0), and higher bits correspond to other events (for instance
* I915_PMU_ACTUAL_FREQUENCY is bit 16 etc).
*
* In other words, low 16 bits are not per engine but per engine
* sampler type, while the upper bits are directly mapped to other
* event types.
*/
u64 enable;
/**
* @timer_last:
*
* Timestmap of the previous timer invocation.
*/
ktime_t timer_last;
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
/**
* @enable_count: Reference counts for the enabled events.
*
* Array indices are mapped in the same way as bits in the @enable field
* and they are used to control sampling on/off when multiple clients
* are using the PMU API.
*/
unsigned int enable_count[I915_PMU_MASK_BITS];
/**
* @timer_enabled: Should the internal sampling timer be running.
*/
bool timer_enabled;
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
/**
* @sample: Current and previous (raw) counters for sampling events.
*
* These counters are updated from the i915 PMU sampling timer.
*
* Only global counters are held here, while the per-engine ones are in
* struct intel_engine_cs.
*/
struct i915_pmu_sample sample[__I915_NUM_PMU_SAMPLERS];
drm/i915/pmu: Fix sleep under atomic in RC6 readout We are not allowed to call intel_runtime_pm_get from the PMU counter read callback since the former can sleep, and the latter is running under IRQ context. To workaround this, we record the last known RC6 and while runtime suspended estimate its increase by querying the runtime PM core timestamps. Downside of this approach is that we can temporarily lose a chunk of RC6 time, from the last PMU read-out to runtime suspend entry, but that will eventually catch up, once device comes back online and in the presence of PMU queries. Also, we have to be careful not to overshoot the RC6 estimate, so once resumed after a period of approximation, we only update the counter once it catches up. With the observation that RC6 is increasing while the device is suspended, this should not pose a problem and can only cause slight inaccuracies due clock base differences. v2: Simplify by estimating on top of PM core counters. (Imre) Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104943 Fixes: 6060b6aec03c ("drm/i915/pmu: Add RC6 residency metrics") Testcase: igt/perf_pmu/rc6-runtime-pm Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Imre Deak <imre.deak@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20180206183311.17924-1-tvrtko.ursulin@linux.intel.com
2018-02-07 02:33:11 +08:00
/**
* @suspended_time_last: Cached suspend time from PM core.
drm/i915/pmu: Fix sleep under atomic in RC6 readout We are not allowed to call intel_runtime_pm_get from the PMU counter read callback since the former can sleep, and the latter is running under IRQ context. To workaround this, we record the last known RC6 and while runtime suspended estimate its increase by querying the runtime PM core timestamps. Downside of this approach is that we can temporarily lose a chunk of RC6 time, from the last PMU read-out to runtime suspend entry, but that will eventually catch up, once device comes back online and in the presence of PMU queries. Also, we have to be careful not to overshoot the RC6 estimate, so once resumed after a period of approximation, we only update the counter once it catches up. With the observation that RC6 is increasing while the device is suspended, this should not pose a problem and can only cause slight inaccuracies due clock base differences. v2: Simplify by estimating on top of PM core counters. (Imre) Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104943 Fixes: 6060b6aec03c ("drm/i915/pmu: Add RC6 residency metrics") Testcase: igt/perf_pmu/rc6-runtime-pm Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Imre Deak <imre.deak@intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: David Airlie <airlied@linux.ie> Cc: intel-gfx@lists.freedesktop.org Cc: dri-devel@lists.freedesktop.org Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20180206183311.17924-1-tvrtko.ursulin@linux.intel.com
2018-02-07 02:33:11 +08:00
*/
u64 suspended_time_last;
/**
* @i915_attr: Memory block holding device attributes.
*/
void *i915_attr;
/**
* @pmu_attr: Memory block holding device attributes.
*/
void *pmu_attr;
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
};
#ifdef CONFIG_PERF_EVENTS
void i915_pmu_register(struct drm_i915_private *i915);
void i915_pmu_unregister(struct drm_i915_private *i915);
void i915_pmu_gt_parked(struct drm_i915_private *i915);
void i915_pmu_gt_unparked(struct drm_i915_private *i915);
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
#else
static inline void i915_pmu_register(struct drm_i915_private *i915) {}
static inline void i915_pmu_unregister(struct drm_i915_private *i915) {}
static inline void i915_pmu_gt_parked(struct drm_i915_private *i915) {}
static inline void i915_pmu_gt_unparked(struct drm_i915_private *i915) {}
drm/i915/pmu: Expose a PMU interface for perf queries From: Chris Wilson <chris@chris-wilson.co.uk> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> From: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> The first goal is to be able to measure GPU (and invidual ring) busyness without having to poll registers from userspace. (Which not only incurs holding the forcewake lock indefinitely, perturbing the system, but also runs the risk of hanging the machine.) As an alternative we can use the perf event counter interface to sample the ring registers periodically and send those results to userspace. Functionality we are exporting to userspace is via the existing perf PMU API and can be exercised via the existing tools. For example: perf stat -a -e i915/rcs0-busy/ -I 1000 Will print the render engine busynnes once per second. All the performance counters can be enumerated (perf list) and have their unit of measure correctly reported in sysfs. v1-v2 (Chris Wilson): v2: Use a common timer for the ring sampling. v3: (Tvrtko Ursulin) * Decouple uAPI from i915 engine ids. * Complete uAPI defines. * Refactor some code to helpers for clarity. * Skip sampling disabled engines. * Expose counters in sysfs. * Pass in fake regs to avoid null ptr deref in perf core. * Convert to class/instance uAPI. * Use shared driver code for rc6 residency, power and frequency. v4: (Dmitry Rogozhkin) * Register PMU with .task_ctx_nr=perf_invalid_context * Expose cpumask for the PMU with the single CPU in the mask * Properly support pmu->stop(): it should call pmu->read() * Properly support pmu->del(): it should call stop(event, PERF_EF_UPDATE) * Introduce refcounting of event subscriptions. * Make pmu.busy_stats a refcounter to avoid busy stats going away with some deleted event. * Expose cpumask for i915 PMU to avoid multiple events creation of the same type followed by counter aggregation by perf-stat. * Track CPUs getting online/offline to migrate perf context. If (likely) cpumask will initially set CPU0, CONFIG_BOOTPARAM_HOTPLUG_CPU0 will be needed to see effect of CPU status tracking. * End result is that only global events are supported and perf stat works correctly. * Deny perf driver level sampling - it is prohibited for uncore PMU. v5: (Tvrtko Ursulin) * Don't hardcode number of engine samplers. * Rewrite event ref-counting for correctness and simplicity. * Store initial counter value when starting already enabled events to correctly report values to all listeners. * Fix RC6 residency readout. * Comments, GPL header. v6: * Add missing entry to v4 changelog. * Fix accounting in CPU hotplug case by copying the approach from arch/x86/events/intel/cstate.c. (Dmitry Rogozhkin) v7: * Log failure message only on failure. * Remove CPU hotplug notification state on unregister. v8: * Fix error unwind on failed registration. * Checkpatch cleanup. v9: * Drop the energy metric, it is available via intel_rapl_perf. (Ville Syrjälä) * Use HAS_RC6(p). (Chris Wilson) * Handle unsupported non-engine events. (Dmitry Rogozhkin) * Rebase for intel_rc6_residency_ns needing caller managed runtime pm. * Drop HAS_RC6 checks from the read callback since creating those events will be rejected at init time already. * Add counter units to sysfs so perf stat output is nicer. * Cleanup the attribute tables for brevity and readability. v10: * Fixed queued accounting. v11: * Move intel_engine_lookup_user to intel_engine_cs.c * Commit update. (Joonas Lahtinen) v12: * More accurate sampling. (Chris Wilson) * Store and report frequency in MHz for better usability from perf stat. * Removed metrics: queued, interrupts, rc6 counters. * Sample engine busyness based on seqno difference only for less MMIO (and forcewake) on all platforms. (Chris Wilson) v13: * Comment spelling, use mul_u32_u32 to work around potential GCC issue and somne code alignment changes. (Chris Wilson) v14: * Rebase. v15: * Rebase for RPS refactoring. v16: * Use the dynamic slot in the CPU hotplug state machine so that we are free to setup our state as multi-instance. Previously we were re-using the CPUHP_AP_PERF_X86_UNCORE_ONLINE slot which is neither used as multi-instance, nor owned by our driver to start with. * Register the CPU hotplug handlers after the PMU, otherwise the callback will get called before the PMU is initialized which can end up in perf_pmu_migrate_context with an un-initialized base. * Added workaround for a probable bug in cpuhp core. v17: * Remove workaround for the cpuhp bug. v18: * Rebase for drm_i915_gem_engine_class getting upstream before us. v19: * Rebase. (trivial) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171121181852.16128-2-tvrtko.ursulin@linux.intel.com
2017-11-22 02:18:45 +08:00
#endif
#endif