From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 9458BC5472F for ; Tue, 27 Aug 2024 16:43:14 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 5FE8A10E39E; Tue, 27 Aug 2024 16:43:14 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="LhMl6Rin"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.17]) by gabe.freedesktop.org (Postfix) with ESMTPS id F0E6910E39E for ; Tue, 27 Aug 2024 16:43:12 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1724776993; x=1756312993; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=wC78B57/Qw5ilZuozaP7me3dszwRXiDZG+oMk8a1wbU=; b=LhMl6RinD25W2M0G5o7r1Mr1hne/JnJ7+YFdoaC8KZs6X9xx089K/nkc Eee3pFCz/hLv/gc8zc2MyIENJEWcxlz1iBlJdSQVhUeoswSqy5nnbNzmv dqWzqse5PhvKGihTvkvS9ucaeaTNQ9kWp4ug0dmDerGkb1ugORqYYvoh0 yPbEiXR06+gFf3mRxkyLQKuViwm+axyvmelpOgv2/AXUuaK09HflZfJ6+ N7agVszp5BHSNgTirRpsu5G7ttl1fkgGel2eAF8Ja/HLaTAv0ed3sJy7E H1BM54Xci0uGuIhSIPdgksvRLOzVygmz05GCDXbcqtBhRNVtcPjaih+Om g==; X-CSE-ConnectionGUID: GGsi91aESfqg2ecehbYaDg== X-CSE-MsgGUID: 9RwmUhF7RuKONaAhjfanbA== X-IronPort-AV: E=McAfee;i="6700,10204,11177"; a="23143725" X-IronPort-AV: E=Sophos;i="6.10,180,1719903600"; d="scan'208";a="23143725" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by fmvoesa111.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Aug 2024 09:43:12 -0700 X-CSE-ConnectionGUID: 8dxT69MKQJq/717XPt493g== X-CSE-MsgGUID: +f54bf3GTDCEePaPCKFfDw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.10,180,1719903600"; d="scan'208";a="63424230" Received: from vbelgaum-ubuntu.fm.intel.com ([10.1.39.141]) by orviesa007.jf.intel.com with ESMTP; 27 Aug 2024 09:43:12 -0700 From: Vinay Belgaumkar To: intel-xe@lists.freedesktop.org Cc: Aravind Iddamsetty , Tvrtko Ursulin , Bommu Krishnaiah , Riana Tauro , Rodrigo Vivi , Vinay Belgaumkar Subject: [PATCH 1/4] drm/xe/pmu: Enable PMU interface Date: Tue, 27 Aug 2024 09:41:04 -0700 Message-Id: <20240827164107.47034-2-vinay.belgaumkar@intel.com> X-Mailer: git-send-email 2.38.1 In-Reply-To: <20240827164107.47034-1-vinay.belgaumkar@intel.com> References: <20240827164107.47034-1-vinay.belgaumkar@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" From: Aravind Iddamsetty Basic PMU enabling patch. Setup the basic framework for adding events/timers. This patch was previously reviewed here - https://patchwork.freedesktop.org/series/119504/ I have included the s-o-b names from that patch here. The difference now is the group engine busyness has been removed. Also, the patch has been split up into 2 chunks like the timer being setup in the next patch. The pmu base implementation is still from the i915 driver. events can be listed using: perf list and can be read using: perf stat -e -I 1000 Co-developed-by: Tvrtko Ursulin Signed-off-by: Tvrtko Ursulin Co-developed-by: Bommu Krishnaiah Signed-off-by: Bommu Krishnaiah Signed-off-by: Aravind Iddamsetty Signed-off-by: Riana Tauro Cc: Rodrigo Vivi Signed-off-by: Vinay Belgaumkar --- drivers/gpu/drm/xe/Makefile | 2 + drivers/gpu/drm/xe/xe_device.c | 2 + drivers/gpu/drm/xe/xe_device_types.h | 4 + drivers/gpu/drm/xe/xe_gt.c | 4 + drivers/gpu/drm/xe/xe_module.c | 5 + drivers/gpu/drm/xe/xe_pmu.c | 546 +++++++++++++++++++++++++++ drivers/gpu/drm/xe/xe_pmu.h | 28 ++ drivers/gpu/drm/xe/xe_pmu_types.h | 63 ++++ include/uapi/drm/xe_drm.h | 34 ++ 9 files changed, 688 insertions(+) create mode 100644 drivers/gpu/drm/xe/xe_pmu.c create mode 100644 drivers/gpu/drm/xe/xe_pmu.h create mode 100644 drivers/gpu/drm/xe/xe_pmu_types.h diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index b9670ae09a9e..05edccd85413 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -264,6 +264,8 @@ xe-$(CONFIG_DRM_XE_DISPLAY) += \ i915-display/skl_universal_plane.o \ i915-display/skl_watermark.o +xe-$(CONFIG_PERF_EVENTS) += xe_pmu.o + ifeq ($(CONFIG_ACPI),y) xe-$(CONFIG_DRM_XE_DISPLAY) += \ i915-display/intel_acpi.o \ diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index b6db7e082d88..978eca47cbc8 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -748,6 +748,8 @@ int xe_device_probe(struct xe_device *xe) for_each_gt(gt, xe, id) xe_gt_sanitize_freq(gt); + xe_pmu_register(&xe->pmu); + return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe); err_fini_display: diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 4ecd620921a3..eb34f4ee7d6a 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -19,6 +19,7 @@ #include "xe_memirq_types.h" #include "xe_oa.h" #include "xe_platform_types.h" +#include "xe_pmu.h" #include "xe_pt_types.h" #include "xe_sriov_types.h" #include "xe_step_types.h" @@ -483,6 +484,9 @@ struct xe_device { int mode; } wedged; + /** @pmu: performance monitoring unit */ + struct xe_pmu pmu; + #ifdef TEST_VM_OPS_ERROR /** * @vm_inject_error_position: inject errors at different places in VM diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 08a004d698d4..097a32ec807d 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -844,6 +844,8 @@ int xe_gt_suspend(struct xe_gt *gt) if (err) goto err_msg; + xe_pmu_suspend(gt); + err = xe_uc_suspend(>->uc); if (err) goto err_force_wake; @@ -898,6 +900,8 @@ int xe_gt_resume(struct xe_gt *gt) xe_gt_idle_enable_pg(gt); + xe_pmu_resume(gt); + XE_WARN_ON(xe_force_wake_put(gt_to_fw(gt), XE_FORCEWAKE_ALL)); xe_gt_dbg(gt, "resumed\n"); diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c index 923460119cec..a95c771e7fac 100644 --- a/drivers/gpu/drm/xe/xe_module.c +++ b/drivers/gpu/drm/xe/xe_module.c @@ -11,6 +11,7 @@ #include "xe_drv.h" #include "xe_hw_fence.h" #include "xe_pci.h" +#include "xe_pmu.h" #include "xe_observation.h" #include "xe_sched_job.h" @@ -78,6 +79,10 @@ static const struct init_funcs init_funcs[] = { .init = xe_sched_job_module_init, .exit = xe_sched_job_module_exit, }, + { + .init = xe_pmu_init, + .exit = xe_pmu_exit, + }, { .init = xe_register_pci_driver, .exit = xe_unregister_pci_driver, diff --git a/drivers/gpu/drm/xe/xe_pmu.c b/drivers/gpu/drm/xe/xe_pmu.c new file mode 100644 index 000000000000..33e7966f449c --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pmu.c @@ -0,0 +1,546 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2024 Intel Corporation + */ + +#include +#include +#include + +#include "regs/xe_gt_regs.h" +#include "xe_device.h" +#include "xe_force_wake.h" +#include "xe_gt_clock.h" +#include "xe_mmio.h" +#include "xe_macros.h" +#include "xe_pm.h" + +static cpumask_t xe_pmu_cpumask; +static unsigned int xe_pmu_target_cpu = -1; + +static unsigned int config_gt_id(const u64 config) +{ + return config >> __XE_PMU_GT_SHIFT; +} + +static u64 config_counter(const u64 config) +{ + return config & ~(~0ULL << __XE_PMU_GT_SHIFT); +} + +static void xe_pmu_event_destroy(struct perf_event *event) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + + drm_WARN_ON(&xe->drm, event->parent); + + drm_dev_put(&xe->drm); +} + +static int +config_status(struct xe_device *xe, u64 config) +{ + unsigned int gt_id = config_gt_id(config); + + if (gt_id >= XE_PMU_MAX_GT) + return -ENOENT; + + switch (config_counter(config)) { + default: + return -ENOENT; + } + + return 0; +} + +static int xe_pmu_event_init(struct perf_event *event) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + struct xe_pmu *pmu = &xe->pmu; + int ret; + + if (pmu->closed) + return -ENODEV; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* unsupported modes and filters */ + if (event->attr.sample_period) /* no sampling */ + return -EINVAL; + + if (has_branch_stack(event)) + return -EOPNOTSUPP; + + if (event->cpu < 0) + return -EINVAL; + + /* only allow running on one cpu at a time */ + if (!cpumask_test_cpu(event->cpu, &xe_pmu_cpumask)) + return -EINVAL; + + ret = config_status(xe, event->attr.config); + if (ret) + return ret; + + if (!event->parent) { + drm_dev_get(&xe->drm); + event->destroy = xe_pmu_event_destroy; + } + + return 0; +} + +static u64 __xe_pmu_event_read(struct perf_event *event) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + const unsigned int gt_id = config_gt_id(event->attr.config); + const u64 config = event->attr.config; + struct xe_gt *gt = xe_device_get_gt(xe, gt_id); + u64 val = 0; + + switch (config_counter(config)) { + default: + drm_warn(>->tile->xe->drm, "unknown pmu event\n"); + } + + return val; +} + +static void xe_pmu_event_read(struct perf_event *event) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + struct hw_perf_event *hwc = &event->hw; + struct xe_pmu *pmu = &xe->pmu; + u64 prev, new; + + if (pmu->closed) { + event->hw.state = PERF_HES_STOPPED; + return; + } +again: + prev = local64_read(&hwc->prev_count); + new = __xe_pmu_event_read(event); + + if (local64_cmpxchg(&hwc->prev_count, prev, new) != prev) + goto again; + + local64_add(new - prev, &event->count); +} + +static void xe_pmu_enable(struct perf_event *event) +{ + /* + * Store the current counter value so we can report the correct delta + * for all listeners. Even when the event was already enabled and has + * an existing non-zero value. + */ + local64_set(&event->hw.prev_count, __xe_pmu_event_read(event)); +} + +static void xe_pmu_event_start(struct perf_event *event, int flags) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + struct xe_pmu *pmu = &xe->pmu; + + if (pmu->closed) + return; + + xe_pmu_enable(event); + event->hw.state = 0; +} + +static void xe_pmu_event_stop(struct perf_event *event, int flags) +{ + if (flags & PERF_EF_UPDATE) + xe_pmu_event_read(event); + + event->hw.state = PERF_HES_STOPPED; +} + +static int xe_pmu_event_add(struct perf_event *event, int flags) +{ + struct xe_device *xe = + container_of(event->pmu, typeof(*xe), pmu.base); + struct xe_pmu *pmu = &xe->pmu; + + if (pmu->closed) + return -ENODEV; + + if (flags & PERF_EF_START) + xe_pmu_event_start(event, flags); + + return 0; +} + +static void xe_pmu_event_del(struct perf_event *event, int flags) +{ + xe_pmu_event_stop(event, PERF_EF_UPDATE); +} + +static int xe_pmu_event_event_idx(struct perf_event *event) +{ + return 0; +} + +struct xe_ext_attribute { + struct device_attribute attr; + unsigned long val; +}; + +static ssize_t xe_pmu_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct xe_ext_attribute *eattr; + + eattr = container_of(attr, struct xe_ext_attribute, attr); + return sprintf(buf, "config=0x%lx\n", eattr->val); +} + +static ssize_t cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &xe_pmu_cpumask); +} + +static DEVICE_ATTR_RO(cpumask); + +static struct attribute *xe_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static const struct attribute_group xe_pmu_cpumask_attr_group = { + .attrs = xe_cpumask_attrs, +}; + +#define __event(__counter, __name, __unit) \ +{ \ + .counter = (__counter), \ + .name = (__name), \ + .unit = (__unit), \ +} + +static struct xe_ext_attribute * +add_xe_attr(struct xe_ext_attribute *attr, const char *name, u64 config) +{ + sysfs_attr_init(&attr->attr.attr); + attr->attr.attr.name = name; + attr->attr.attr.mode = 0444; + attr->attr.show = xe_pmu_event_show; + attr->val = config; + + return ++attr; +} + +static struct perf_pmu_events_attr * +add_pmu_attr(struct perf_pmu_events_attr *attr, const char *name, + const char *str) +{ + sysfs_attr_init(&attr->attr.attr); + attr->attr.attr.name = name; + attr->attr.attr.mode = 0444; + attr->attr.show = perf_event_sysfs_show; + attr->event_str = str; + + return ++attr; +} + +static struct attribute ** +create_event_attributes(struct xe_pmu *pmu) +{ + struct xe_device *xe = container_of(pmu, typeof(*xe), pmu); + static const struct { + unsigned int counter; + const char *name; + const char *unit; + } events[] = { + }; + + struct perf_pmu_events_attr *pmu_attr = NULL, *pmu_iter; + struct xe_ext_attribute *xe_attr = NULL, *xe_iter; + struct attribute **attr = NULL, **attr_iter; + unsigned int count = 0; + unsigned int i, j; + struct xe_gt *gt; + + /* Count how many counters we will be exposing. */ + for_each_gt(gt, xe, j) { + for (i = 0; i < ARRAY_SIZE(events); i++) { + u64 config = ___XE_PMU_OTHER(j, events[i].counter); + + if (!config_status(xe, config)) + count++; + } + } + + /* Allocate attribute objects and table. */ + xe_attr = kcalloc(count, sizeof(*xe_attr), GFP_KERNEL); + if (!xe_attr) + goto err_alloc; + + pmu_attr = kcalloc(count, sizeof(*pmu_attr), GFP_KERNEL); + if (!pmu_attr) + goto err_alloc; + + /* Max one pointer of each attribute type plus a termination entry. */ + attr = kcalloc(count * 2 + 1, sizeof(*attr), GFP_KERNEL); + if (!attr) + goto err_alloc; + + xe_iter = xe_attr; + pmu_iter = pmu_attr; + attr_iter = attr; + + for_each_gt(gt, xe, j) { + for (i = 0; i < ARRAY_SIZE(events); i++) { + u64 config = ___XE_PMU_OTHER(j, events[i].counter); + char *str; + + if (config_status(xe, config)) + continue; + + str = kasprintf(GFP_KERNEL, "%s-gt%u", + events[i].name, j); + if (!str) + goto err; + + *attr_iter++ = &xe_iter->attr.attr; + xe_iter = add_xe_attr(xe_iter, str, config); + + if (events[i].unit) { + str = kasprintf(GFP_KERNEL, "%s-gt%u.unit", + events[i].name, j); + if (!str) + goto err; + + *attr_iter++ = &pmu_iter->attr.attr; + pmu_iter = add_pmu_attr(pmu_iter, str, + events[i].unit); + } + } + } + + pmu->xe_attr = xe_attr; + pmu->pmu_attr = pmu_attr; + + return attr; + +err: + for (attr_iter = attr; *attr_iter; attr_iter++) + kfree((*attr_iter)->name); + +err_alloc: + kfree(attr); + kfree(xe_attr); + kfree(pmu_attr); + + return NULL; +} + +static void free_event_attributes(struct xe_pmu *pmu) +{ + struct attribute **attr_iter = pmu->events_attr_group.attrs; + + for (; *attr_iter; attr_iter++) + kfree((*attr_iter)->name); + + kfree(pmu->events_attr_group.attrs); + kfree(pmu->xe_attr); + kfree(pmu->pmu_attr); + + pmu->events_attr_group.attrs = NULL; + pmu->xe_attr = NULL; + pmu->pmu_attr = NULL; +} + +static int xe_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) +{ + struct xe_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); + + XE_WARN_ON(!pmu->base.event_init); + + /* Select the first online CPU as a designated reader. */ + if (cpumask_empty(&xe_pmu_cpumask)) + cpumask_set_cpu(cpu, &xe_pmu_cpumask); + + return 0; +} + +static int xe_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) +{ + struct xe_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node); + unsigned int target = xe_pmu_target_cpu; + + /* + * Unregistering an instance generates a CPU offline event which we must + * ignore to avoid incorrectly modifying the shared xe_pmu_cpumask. + */ + if (pmu->closed) + return 0; + + if (cpumask_test_and_clear_cpu(cpu, &xe_pmu_cpumask)) { + target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu); + + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { + cpumask_set_cpu(target, &xe_pmu_cpumask); + xe_pmu_target_cpu = target; + } + } + + if (target < nr_cpu_ids && target != pmu->cpuhp.cpu) { + perf_pmu_migrate_context(&pmu->base, cpu, target); + pmu->cpuhp.cpu = target; + } + + return 0; +} + +static enum cpuhp_state cpuhp_slot = CPUHP_INVALID; + +int xe_pmu_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, + "perf/x86/intel/xe:online", + xe_pmu_cpu_online, + xe_pmu_cpu_offline); + if (ret < 0) + pr_notice("Failed to setup cpuhp state for xe PMU! (%d)\n", + ret); + else + cpuhp_slot = ret; + + return 0; +} + +void xe_pmu_exit(void) +{ + if (cpuhp_slot != CPUHP_INVALID) + cpuhp_remove_multi_state(cpuhp_slot); +} + +static int xe_pmu_register_cpuhp_state(struct xe_pmu *pmu) +{ + if (cpuhp_slot == CPUHP_INVALID) + return -EINVAL; + + return cpuhp_state_add_instance(cpuhp_slot, &pmu->cpuhp.node); +} + +static void xe_pmu_unregister_cpuhp_state(struct xe_pmu *pmu) +{ + cpuhp_state_remove_instance(cpuhp_slot, &pmu->cpuhp.node); +} + +void xe_pmu_suspend(struct xe_gt *gt) +{ +} + +void xe_pmu_resume(struct xe_gt *gt) +{ +} + +static void xe_pmu_unregister(void *arg) +{ + struct xe_pmu *pmu = arg; + + if (!pmu->base.event_init) + return; + + /* + * "Disconnect" the PMU callbacks - since all are atomic synchronize_rcu + * ensures all currently executing ones will have exited before we + * proceed with unregistration. + */ + pmu->closed = true; + synchronize_rcu(); + + xe_pmu_unregister_cpuhp_state(pmu); + + perf_pmu_unregister(&pmu->base); + pmu->base.event_init = NULL; + kfree(pmu->base.attr_groups); + kfree(pmu->name); + free_event_attributes(pmu); +} + +void xe_pmu_register(struct xe_pmu *pmu) +{ + struct xe_device *xe = container_of(pmu, typeof(*xe), pmu); + const struct attribute_group *attr_groups[] = { + &pmu->events_attr_group, + &xe_pmu_cpumask_attr_group, + NULL + }; + + int ret = -ENOMEM; + + spin_lock_init(&pmu->lock); + pmu->cpuhp.cpu = -1; + + pmu->name = kasprintf(GFP_KERNEL, + "xe_%s", + dev_name(xe->drm.dev)); + if (pmu->name) + /* tools/perf reserves colons as special. */ + strreplace((char *)pmu->name, ':', '_'); + + if (!pmu->name) + goto err; + + pmu->events_attr_group.name = "events"; + pmu->events_attr_group.attrs = create_event_attributes(pmu); + if (!pmu->events_attr_group.attrs) + goto err_name; + + pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups), + GFP_KERNEL); + if (!pmu->base.attr_groups) + goto err_attr; + + pmu->base.module = THIS_MODULE; + pmu->base.task_ctx_nr = perf_invalid_context; + pmu->base.event_init = xe_pmu_event_init; + pmu->base.add = xe_pmu_event_add; + pmu->base.del = xe_pmu_event_del; + pmu->base.start = xe_pmu_event_start; + pmu->base.stop = xe_pmu_event_stop; + pmu->base.read = xe_pmu_event_read; + pmu->base.event_idx = xe_pmu_event_event_idx; + + ret = perf_pmu_register(&pmu->base, pmu->name, -1); + if (ret) + goto err_groups; + + ret = xe_pmu_register_cpuhp_state(pmu); + if (ret) + goto err_unreg; + + ret = devm_add_action_or_reset(xe->drm.dev, xe_pmu_unregister, pmu); + if (ret) + goto err_cpuhp; + + return; + +err_cpuhp: + xe_pmu_unregister_cpuhp_state(pmu); +err_unreg: + perf_pmu_unregister(&pmu->base); +err_groups: + kfree(pmu->base.attr_groups); +err_attr: + pmu->base.event_init = NULL; + free_event_attributes(pmu); +err_name: + kfree(pmu->name); +err: + drm_notice(&xe->drm, "Failed to register PMU!\n"); +} diff --git a/drivers/gpu/drm/xe/xe_pmu.h b/drivers/gpu/drm/xe/xe_pmu.h new file mode 100644 index 000000000000..eef2cbcd9c26 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pmu.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef _XE_PMU_H_ +#define _XE_PMU_H_ + +#include "xe_pmu_types.h" + +struct xe_gt; + +#if IS_ENABLED(CONFIG_PERF_EVENTS) +int xe_pmu_init(void); +void xe_pmu_exit(void); +void xe_pmu_register(struct xe_pmu *pmu); +void xe_pmu_suspend(struct xe_gt *gt); +void xe_pmu_resume(struct xe_gt *gt); +#else +static inline int xe_pmu_init(void) { return 0; } +static inline void xe_pmu_exit(void) {} +static inline void xe_pmu_register(struct xe_pmu *pmu) {} +static inline void xe_pmu_suspend(struct xe_gt *gt) {} +static inline void xe_pmu_resume(struct xe_gt *gt) {} +#endif + +#endif + diff --git a/drivers/gpu/drm/xe/xe_pmu_types.h b/drivers/gpu/drm/xe/xe_pmu_types.h new file mode 100644 index 000000000000..ca0e7cbe2081 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_pmu_types.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2024 Intel Corporation + */ + +#ifndef _XE_PMU_TYPES_H_ +#define _XE_PMU_TYPES_H_ + +#include +#include +#include + +enum { + __XE_NUM_PMU_SAMPLERS +}; + +#define XE_PMU_MAX_GT 2 + +struct xe_pmu { + /** + * @cpuhp: Struct used for CPU hotplug handling. + */ + struct { + struct hlist_node node; + unsigned int cpu; + } cpuhp; + /** + * @base: PMU base. + */ + struct pmu base; + /** + * @closed: xe is unregistering. + */ + bool closed; + /** + * @name: Name as registered with perf core. + */ + const char *name; + /** + * @lock: Lock protecting enable mask and ref count handling. + */ + spinlock_t lock; + /** + * @sample: Current and previous (raw) counters. + * + * These counters are updated when the device is awake. + */ + u64 sample[XE_PMU_MAX_GT][__XE_NUM_PMU_SAMPLERS]; + /** + * @events_attr_group: Device events attribute group. + */ + struct attribute_group events_attr_group; + /** + * @xe_attr: Memory block holding device attributes. + */ + void *xe_attr; + /** + * @pmu_attr: Memory block holding device attributes. + */ + void *pmu_attr; +}; + +#endif diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index b6fbe4988f2e..de6f39db618c 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1389,6 +1389,40 @@ struct drm_xe_wait_user_fence { __u64 reserved[2]; }; +/** + * DOC: XE PMU event config IDs + * + * Check 'man perf_event_open' to use the ID's XE_PMU_XXXX listed in xe_drm.h + * in 'struct perf_event_attr' as part of perf_event_open syscall to read a + * particular event. + * + * For example to open the XE_PMU_RENDER_GROUP_BUSY(0): + * + * .. code-block:: C + * + * struct perf_event_attr attr; + * long long count; + * int cpu = 0; + * int fd; + * + * memset(&attr, 0, sizeof(struct perf_event_attr)); + * attr.type = type; // eg: /sys/bus/event_source/devices/xe_0000_56_00.0/type + * attr.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED; + * attr.use_clockid = 1; + * attr.clockid = CLOCK_MONOTONIC; + * attr.config = XE_PMU_RENDER_GROUP_BUSY(0); + * + * fd = syscall(__NR_perf_event_open, &attr, -1, cpu, -1, 0); + */ + +/* + * Top bits of every counter are GT id. + */ +#define __XE_PMU_GT_SHIFT (56) + +#define ___XE_PMU_OTHER(gt, x) \ + (((__u64)(x)) | ((__u64)(gt) << __XE_PMU_GT_SHIFT)) + /** * enum drm_xe_observation_type - Observation stream types */ -- 2.38.1