diff --git a/drivers/accel/ethosu/Makefile b/drivers/accel/ethosu/Makefile index 17db5a600416..598a388b7179 100644 --- a/drivers/accel/ethosu/Makefile +++ b/drivers/accel/ethosu/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_DRM_ACCEL_ARM_ETHOSU) := ethosu.o -ethosu-y += ethosu_drv.o ethosu_gem.o ethosu_job.o +ethosu-y += ethosu_drv.o ethosu_gem.o ethosu_job.o ethosu_perfmon.o diff --git a/drivers/accel/ethosu/ethosu_device.h b/drivers/accel/ethosu/ethosu_device.h index b189fa783d6a..3a1d07d94785 100644 --- a/drivers/accel/ethosu/ethosu_device.h +++ b/drivers/accel/ethosu/ethosu_device.h @@ -6,6 +6,7 @@ #include #include +#include #include #include @@ -43,6 +44,15 @@ struct gen_pool; #define NPU_REG_BASEP_HI(x) (0x0084 + (x) * 8) #define NPU_BASEP_REGION_MAX 8 +#define NPU_REG_PMCR 0x0180 +#define NPU_REG_PMCNTENSET 0x0184 +#define NPU_REG_PMCNTENCLR 0x0188 +#define NPU_REG_PMCCNTR_LO 0x01A0 +#define NPU_REG_PMCCNTR_HI 0x01A4 +#define NPU_REG_PMCCNTR_CFG 0x01A8 +#define NPU_REG_PMU_EVCNTR(x) (0x0300 + (x) * 4) +#define NPU_REG_PMU_EVTYPER(x) (0x0380 + (x) * 4) + #define ID_ARCH_MAJOR_MASK GENMASK(31, 28) #define ID_ARCH_MINOR_MASK GENMASK(27, 20) #define ID_ARCH_PATCH_MASK GENMASK(19, 16) @@ -67,6 +77,15 @@ struct gen_pool; #define PROT_ACTIVE_CSL BIT(1) +#define PMCR_NUM_EVENT_CNT_MASK GENMASK(15, 11) +#define PMCR_CYCLE_CNT_RST BIT(2) +#define PMCR_EVENT_CNT_RST BIT(1) +#define PMCR_CNT_EN BIT(0) + +#define PMU_EV_TYPE_NONE 0 +#define PMU_EV_TYPE_CYCLES 0x11 +#define PMU_EV_TYPE_IDLE 0x20 + enum ethosu_cmds { NPU_OP_CONV = 0x2, NPU_OP_DEPTHWISE = 0x3, @@ -152,6 +171,8 @@ enum ethosu_cmds { #define ETHOSU_SRAM_REGION 2 /* Matching Vela compiler */ +struct ethosu_perfmon; + /** * struct ethosu_device - Ethosu device */ @@ -161,6 +182,7 @@ struct ethosu_device { /** @iomem: CPU mapping of the registers. */ void __iomem *regs; + void __iomem *pmu_regs; void __iomem *sram; struct gen_pool *srampool; @@ -184,6 +206,17 @@ struct ethosu_device { struct mutex sched_lock; u64 fence_context; u64 emit_seqno; + + /* Tracks the performance monitor state. */ + struct { + /* Protects @active. */ + struct mutex lock; + + /* Perfmon currently programmed in HW (or NULL if none). */ + struct ethosu_perfmon *active; + } perfmon_state; + + struct ethosu_perfmon *global_perfmon; }; #define to_ethosu_device(drm_dev) \ diff --git a/drivers/accel/ethosu/ethosu_drv.c b/drivers/accel/ethosu/ethosu_drv.c index 9992193d7338..fef4713e8061 100644 --- a/drivers/accel/ethosu/ethosu_drv.c +++ b/drivers/accel/ethosu/ethosu_drv.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include "ethosu_drv.h" @@ -155,6 +156,7 @@ static int ethosu_open(struct drm_device *ddev, struct drm_file *file) if (ret) goto err_put_mod; + ethosu_perfmon_open_file(priv); file->driver_priv = no_free_ptr(priv); return 0; @@ -166,6 +168,7 @@ static int ethosu_open(struct drm_device *ddev, struct drm_file *file) static void ethosu_postclose(struct drm_device *ddev, struct drm_file *file) { ethosu_job_close(file->driver_priv); + ethosu_perfmon_close_file(file->driver_priv); kfree(file->driver_priv); module_put(THIS_MODULE); } @@ -180,6 +183,10 @@ static const struct drm_ioctl_desc ethosu_drm_driver_ioctls[] = { ETHOSU_IOCTL(BO_MMAP_OFFSET, bo_mmap_offset, 0), ETHOSU_IOCTL(CMDSTREAM_BO_CREATE, cmdstream_bo_create, 0), ETHOSU_IOCTL(SUBMIT, submit, 0), + ETHOSU_IOCTL(PERFMON_CREATE, perfmon_create, 0), + ETHOSU_IOCTL(PERFMON_DESTROY, perfmon_destroy, 0), + ETHOSU_IOCTL(PERFMON_GET_VALUES, perfmon_get_values, 0), + ETHOSU_IOCTL(PERFMON_SET_GLOBAL, perfmon_set_global, 0), }; DEFINE_DRM_ACCEL_FOPS(ethosu_drm_driver_fops); @@ -315,8 +322,14 @@ static int ethosu_init(struct ethosu_device *ethosudev) ethosu_sram_init(ethosudev); + if (!ethosu_is_u65(ethosudev)) + ethosudev->pmu_regs += 0x1000; + + ethosudev->npu_info.pmu_counters = FIELD_GET(PMCR_NUM_EVENT_CNT_MASK, + readl_relaxed(ethosudev->pmu_regs + NPU_REG_PMCR)); + dev_info(ethosudev->base.dev, - "Ethos-U NPU, arch v%ld.%ld.%ld, rev r%ldp%ld, cmd stream ver%ld, %d MACs, %dKB SRAM\n", + "Ethos-U NPU, arch v%ld.%ld.%ld, rev r%ldp%ld, cmd stream ver%ld, %d MACs, %dKB SRAM, %d PMU cntrs\n", FIELD_GET(ID_ARCH_MAJOR_MASK, id), FIELD_GET(ID_ARCH_MINOR_MASK, id), FIELD_GET(ID_ARCH_PATCH_MASK, id), @@ -324,7 +337,8 @@ static int ethosu_init(struct ethosu_device *ethosudev) FIELD_GET(ID_VER_MINOR_MASK, id), FIELD_GET(CONFIG_CMD_STREAM_VER_MASK, config), 1 << FIELD_GET(CONFIG_MACS_PER_CC_MASK, config), - ethosudev->npu_info.sram_size / 1024); + ethosudev->npu_info.sram_size / 1024, + ethosudev->npu_info.pmu_counters); return 0; } @@ -343,11 +357,16 @@ static int ethosu_probe(struct platform_device *pdev) dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)); ethosudev->regs = devm_platform_ioremap_resource(pdev, 0); + ethosudev->pmu_regs = ethosudev->regs; ethosudev->num_clks = devm_clk_bulk_get_all(&pdev->dev, ðosudev->clks); if (ethosudev->num_clks < 0) return ethosudev->num_clks; + ret = drmm_mutex_init(ðosudev->base, ðosudev->perfmon_state.lock); + if (ret) + return ret; + ret = ethosu_job_init(ethosudev); if (ret) return ret; diff --git a/drivers/accel/ethosu/ethosu_drv.h b/drivers/accel/ethosu/ethosu_drv.h index 9e21dfe94184..2193bc51d425 100644 --- a/drivers/accel/ethosu/ethosu_drv.h +++ b/drivers/accel/ethosu/ethosu_drv.h @@ -1,15 +1,74 @@ /* SPDX-License-Identifier: GPL-2.0-only OR MIT */ -/* Copyright 2025 Arm, Ltd. */ +/* Copyright 2025-2026 Arm, Ltd. */ #ifndef __ETHOSU_DRV_H__ #define __ETHOSU_DRV_H__ +#include +#include #include struct ethosu_device; +struct drm_device; +struct drm_file; struct ethosu_file_priv { struct ethosu_device *edev; struct drm_sched_entity sched_entity; + struct xarray perfmons; }; +/* Performance monitor object. The perfmon lifetime is controlled by userspace + * using perfmon related ioctls. A perfmon can be attached to a DRM_ETHOSU_SUBMIT + * request, and when this is the case, HW perf counters will be activated just + * before the job is submitted to the NPU and disabled when the job is + * done. This way, only events related to a specific job will be counted. + */ +struct ethosu_perfmon { + /* Tracks the number of users of the perfmon, when this counter reaches + * zero the perfmon is destroyed. + */ + refcount_t refcnt; + + /* Number of counters activated in this perfmon instance + * (should be less than or equal to DRM_ETHOSU_MAX_PERF_COUNTERS). + */ + u8 ncounters; + + /* Events counted by the HW perf counters. */ + u16 counters[DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS]; + + /* + * Storage for counter values. Counters are incremented by the HW + * perf counter values every time the perfmon is attached to an + * NPU job. This way, perfmon users don't have to retrieve the + * results after each job if they want to track events covering + * several submissions. Note that counter values can't be reset, + * but you can fake a reset by destroying the perfmon and + * creating a new one. + */ + u64 values[] __counted_by(ncounters); +}; + +/* ethosu_perfmon.c */ +void ethosu_perfmon_get(struct ethosu_perfmon *perfmon); +void ethosu_perfmon_put(struct ethosu_perfmon *perfmon); +void ethosu_perfmon_start(struct ethosu_device *ethosu, + struct ethosu_perfmon *perfmon); +void ethosu_perfmon_stop(struct ethosu_device *ethosu, + struct ethosu_perfmon *perfmon, bool capture); +void ethosu_perfmon_stop_locked(struct ethosu_device *ethosu, struct ethosu_perfmon *perfmon, + bool capture); +struct ethosu_perfmon *ethosu_perfmon_find(struct ethosu_file_priv *ethosu_priv, + int id); +void ethosu_perfmon_open_file(struct ethosu_file_priv *ethosu_priv); +void ethosu_perfmon_close_file(struct ethosu_file_priv *ethosu_priv); +int ethosu_ioctl_perfmon_create(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int ethosu_ioctl_perfmon_destroy(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int ethosu_ioctl_perfmon_get_values(struct drm_device *dev, void *data, + struct drm_file *file_priv); +int ethosu_ioctl_perfmon_set_global(struct drm_device *dev, void *data, + struct drm_file *file_priv); + #endif diff --git a/drivers/accel/ethosu/ethosu_job.c b/drivers/accel/ethosu/ethosu_job.c index b76924645aaa..99dec33f526b 100644 --- a/drivers/accel/ethosu/ethosu_job.c +++ b/drivers/accel/ethosu/ethosu_job.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only OR MIT /* Copyright 2024-2025 Tomeu Vizoso */ -/* Copyright 2025 Arm, Ltd. */ +/* Copyright 2025-2026 Arm, Ltd. */ #include #include @@ -147,6 +147,8 @@ static void ethosu_job_err_cleanup(struct ethosu_job *job) { unsigned int i; + ethosu_perfmon_put(job->perfmon); + for (i = 0; i < job->region_cnt; i++) drm_gem_object_put(job->region_bo[i]); @@ -181,6 +183,26 @@ static void ethosu_job_free(struct drm_sched_job *sched_job) ethosu_job_put(job); } +static void +ethosu_switch_perfmon(struct ethosu_device *ethosu, struct ethosu_job *job) +{ + struct ethosu_perfmon *perfmon; + + guard(mutex)(ðosu->perfmon_state.lock); + + perfmon = ethosu->global_perfmon; + if (!perfmon) + perfmon = job->perfmon; + + if (perfmon == ethosu->perfmon_state.active) + return; + + ethosu_perfmon_stop_locked(ethosu, ethosu->perfmon_state.active, true); + + if (perfmon) + ethosu_perfmon_start(ethosu, perfmon); +} + static struct dma_fence *ethosu_job_run(struct drm_sched_job *sched_job) { struct ethosu_job *job = to_ethosu_job(sched_job); @@ -194,6 +216,8 @@ static struct dma_fence *ethosu_job_run(struct drm_sched_job *sched_job) dev->fence_context, ++dev->emit_seqno); dma_fence_get(fence); + ethosu_switch_perfmon(dev, job); + scoped_guard(mutex, &dev->job_lock) { dev->in_flight_job = job; ethosu_job_hw_submit(dev, job); @@ -365,7 +389,8 @@ void ethosu_job_close(struct ethosu_file_priv *ethosu_priv) } static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file, - struct drm_ethosu_job *job) + struct drm_ethosu_job *job, + int perfmon_id) { struct ethosu_device *edev = to_ethosu_device(dev); struct ethosu_file_priv *file_priv = file->driver_priv; @@ -389,6 +414,9 @@ static int ethosu_ioctl_submit_job(struct drm_device *dev, struct drm_file *file ejob->dev = edev; ejob->sram_size = job->sram_size; + if (perfmon_id) + ejob->perfmon = ethosu_perfmon_find(file_priv, perfmon_id); + ejob->done_fence = kzalloc_obj(*ejob->done_fence); if (!ejob->done_fence) { ret = -ENOMEM; @@ -491,11 +519,6 @@ int ethosu_ioctl_submit(struct drm_device *dev, void *data, struct drm_file *fil int ret = 0; unsigned int i = 0; - if (args->pad) { - drm_dbg(dev, "Reserved field in drm_ethosu_submit struct should be 0.\n"); - return -EINVAL; - } - struct drm_ethosu_job __free(kvfree) *jobs = kvmalloc_objs(*jobs, args->job_count); if (!jobs) @@ -509,7 +532,7 @@ int ethosu_ioctl_submit(struct drm_device *dev, void *data, struct drm_file *fil } for (i = 0; i < args->job_count; i++) { - ret = ethosu_ioctl_submit_job(dev, file, &jobs[i]); + ret = ethosu_ioctl_submit_job(dev, file, &jobs[i], args->perfmon_id); if (ret) return ret; } diff --git a/drivers/accel/ethosu/ethosu_job.h b/drivers/accel/ethosu/ethosu_job.h index ff1cf448d094..8988edd00eed 100644 --- a/drivers/accel/ethosu/ethosu_job.h +++ b/drivers/accel/ethosu/ethosu_job.h @@ -21,6 +21,8 @@ struct ethosu_job { u8 region_cnt; u32 sram_size; + struct ethosu_perfmon *perfmon; + /* Fence to be signaled by drm-sched once its done with the job */ struct dma_fence *inference_done_fence; diff --git a/drivers/accel/ethosu/ethosu_perfmon.c b/drivers/accel/ethosu/ethosu_perfmon.c new file mode 100644 index 000000000000..26f625374f9d --- /dev/null +++ b/drivers/accel/ethosu/ethosu_perfmon.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* Copyright 2026 Arm, Ltd. */ +/* Based on v3d_perfmon.c, Copyright (C) 2021 Raspberry Pi */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +#include + +#include "ethosu_drv.h" +#include "ethosu_device.h" + +void ethosu_perfmon_get(struct ethosu_perfmon *perfmon) +{ + if (perfmon) + refcount_inc(&perfmon->refcnt); +} + +void ethosu_perfmon_put(struct ethosu_perfmon *perfmon) +{ + if (perfmon && refcount_dec_and_test(&perfmon->refcnt)) + kfree(perfmon); +} + +void ethosu_perfmon_start(struct ethosu_device *ethosu, struct ethosu_perfmon *perfmon) +{ + unsigned int i; + u8 ncounters; + u32 mask; + + lockdep_assert_held(ðosu->perfmon_state.lock); + + if (WARN_ON_ONCE(!perfmon || ethosu->perfmon_state.active)) + return; + + writel_relaxed(PMCR_CNT_EN, ethosu->pmu_regs + NPU_REG_PMCR); + writel_relaxed(PMU_EV_TYPE_CYCLES, ethosu->pmu_regs + NPU_REG_PMCCNTR_CFG); + + mask = 0x80000000; + ncounters = perfmon->ncounters - 1; + if (ncounters) + mask |= GENMASK(ncounters - 1, 0); + + for (i = 0; i < ncounters; i++) + writel_relaxed(perfmon->counters[i], ethosu->pmu_regs + NPU_REG_PMU_EVTYPER(i)); + + writel_relaxed(mask, ethosu->pmu_regs + NPU_REG_PMCNTENSET); + writel_relaxed(PMCR_CNT_EN | PMCR_EVENT_CNT_RST | PMCR_CYCLE_CNT_RST, + ethosu->pmu_regs + NPU_REG_PMCR); + ethosu->perfmon_state.active = perfmon; +} + +void ethosu_perfmon_stop_locked(struct ethosu_device *ethosu, struct ethosu_perfmon *perfmon, + bool capture) +{ + unsigned int i; + u8 ncounters; + u32 mask; + + lockdep_assert_held(ðosu->perfmon_state.lock); + + if (!perfmon || perfmon != ethosu->perfmon_state.active) + return; + + ncounters = perfmon->ncounters - 1; + + if (!pm_runtime_get_if_active(ethosu->base.dev)) { + ethosu->perfmon_state.active = NULL; + return; + } + + if (capture) { + for (i = 0; i < ncounters; i++) + perfmon->values[i] += readl_relaxed(ethosu->pmu_regs + NPU_REG_PMU_EVCNTR(i)); + + perfmon->values[ncounters] += + readl_relaxed(ethosu->pmu_regs + NPU_REG_PMCCNTR_LO) | + (u64)readl_relaxed(ethosu->pmu_regs + NPU_REG_PMCCNTR_HI) << 32; + } + + mask = 0x80000000; + if (ncounters) + mask |= GENMASK(ncounters - 1, 0); + writel_relaxed(mask, ethosu->pmu_regs + NPU_REG_PMCNTENCLR); + + writel_relaxed(0, ethosu->pmu_regs + NPU_REG_PMCR); + ethosu->perfmon_state.active = NULL; + + pm_runtime_put(ethosu->base.dev); +} + +void ethosu_perfmon_stop(struct ethosu_device *ethosu, struct ethosu_perfmon *perfmon, + bool capture) +{ + if (!perfmon) + return; + + guard(mutex)(ðosu->perfmon_state.lock); + ethosu_perfmon_stop_locked(ethosu, perfmon, capture); +} + +struct ethosu_perfmon *ethosu_perfmon_find(struct ethosu_file_priv *ethosu_priv, int id) +{ + struct ethosu_perfmon *perfmon; + + xa_lock(ðosu_priv->perfmons); + perfmon = xa_load(ðosu_priv->perfmons, id); + ethosu_perfmon_get(perfmon); + xa_unlock(ðosu_priv->perfmons); + + return perfmon; +} + +void ethosu_perfmon_open_file(struct ethosu_file_priv *ethosu_priv) +{ + xa_init_flags(ðosu_priv->perfmons, XA_FLAGS_ALLOC1); +} + +static void ethosu_perfmon_delete(struct ethosu_file_priv *ethosu_priv, + struct ethosu_perfmon *perfmon) +{ + struct ethosu_device *ethosu = ethosu_priv->edev; + + /* If the active perfmon is being destroyed, stop it first */ + scoped_guard(mutex, ðosu->perfmon_state.lock) { + /* If the global perfmon is being destroyed, set it to NULL */ + if (ethosu->global_perfmon == perfmon) { + ethosu->global_perfmon = NULL; + ethosu_perfmon_put(perfmon); + } + + ethosu_perfmon_stop_locked(ethosu, perfmon, false); + } + + ethosu_perfmon_put(perfmon); +} + +void ethosu_perfmon_close_file(struct ethosu_file_priv *ethosu_priv) +{ + struct ethosu_perfmon *perfmon; + unsigned long id; + + xa_for_each(ðosu_priv->perfmons, id, perfmon) + ethosu_perfmon_delete(ethosu_priv, perfmon); + + xa_destroy(ðosu_priv->perfmons); +} + +int ethosu_ioctl_perfmon_create(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct ethosu_file_priv *ethosu_priv = file_priv->driver_priv; + struct drm_ethosu_perfmon_create *req = data; + struct ethosu_device *ethosu = to_ethosu_device(dev); + struct ethosu_perfmon *perfmon; + unsigned int i, event_max; + int ret; + u32 id; + + /* Number of monitored counters cannot exceed HW limits. */ + if (req->ncounters > ethosu->npu_info.pmu_counters) + return -EINVAL; + + /* Make sure all counters are valid. */ + event_max = ethosu_is_u65(ethosu) ? 433 : 671; + for (i = 0; i < req->ncounters; i++) { + if (req->counters[i] > event_max) + return -EINVAL; + } + + /* Add 1 more counter for cycle counter */ + req->ncounters++; + + perfmon = kzalloc_flex(*perfmon, values, req->ncounters); + if (!perfmon) + return -ENOMEM; + + for (i = 0; i < req->ncounters - 1; i++) + perfmon->counters[i] = req->counters[i]; + + perfmon->ncounters = req->ncounters; + + refcount_set(&perfmon->refcnt, 1); + + ret = xa_alloc(ðosu_priv->perfmons, &id, perfmon, xa_limit_32b, + GFP_KERNEL); + + if (ret < 0) { + kfree(perfmon); + return ret; + } + + req->id = id; + + return 0; +} + +int ethosu_ioctl_perfmon_destroy(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct ethosu_file_priv *ethosu_priv = file_priv->driver_priv; + struct drm_ethosu_perfmon_destroy *req = data; + struct ethosu_perfmon *perfmon; + + perfmon = xa_erase(ðosu_priv->perfmons, req->id); + if (!perfmon) + return -EINVAL; + + ethosu_perfmon_delete(ethosu_priv, perfmon); + + return 0; +} + +int ethosu_ioctl_perfmon_get_values(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct ethosu_device *ethosu = to_ethosu_device(dev); + struct ethosu_file_priv *ethosu_priv = file_priv->driver_priv; + struct drm_ethosu_perfmon_get_values *req = data; + struct ethosu_perfmon *perfmon; + int ret = 0; + + if (req->pad != 0) + return -EINVAL; + + perfmon = ethosu_perfmon_find(ethosu_priv, req->id); + if (!perfmon) + return -EINVAL; + + ret = pm_runtime_resume_and_get(dev->dev); + if (ret) { + ethosu_perfmon_put(perfmon); + return ret; + } + ethosu_perfmon_stop(ethosu, perfmon, true); + + pm_runtime_put_autosuspend(dev->dev); + + if (copy_to_user(u64_to_user_ptr(req->values_ptr), perfmon->values, + perfmon->ncounters * sizeof(u64))) + ret = -EFAULT; + + ethosu_perfmon_put(perfmon); + + return ret; +} + +int ethosu_ioctl_perfmon_set_global(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct ethosu_file_priv *ethosu_priv = file_priv->driver_priv; + struct drm_ethosu_perfmon_set_global *req = data; + struct ethosu_device *ethosu = to_ethosu_device(dev); + struct ethosu_perfmon *perfmon; + + if (req->flags & ~DRM_ETHOSU_PERFMON_CLEAR_GLOBAL) + return -EINVAL; + + perfmon = ethosu_perfmon_find(ethosu_priv, req->id); + if (!perfmon) + return -EINVAL; + + /* If the request is to clear the global performance monitor */ + if (req->flags & DRM_ETHOSU_PERFMON_CLEAR_GLOBAL) { + struct ethosu_perfmon *old; + + scoped_guard(mutex, ðosu->perfmon_state.lock) { + old = ethosu->global_perfmon; + if (!old) { + ethosu_perfmon_put(perfmon); + return -EINVAL; + } + + ethosu->global_perfmon = NULL; + ethosu_perfmon_stop_locked(ethosu, old, true); + } + + ethosu_perfmon_put(old); + ethosu_perfmon_put(perfmon); + + return 0; + } + + scoped_guard(mutex, ðosu->perfmon_state.lock) { + if (ethosu->perfmon_state.active || ethosu->global_perfmon) { + ethosu_perfmon_put(perfmon); + return -EBUSY; + } + + ethosu->global_perfmon = perfmon; + } + + return 0; +} diff --git a/include/uapi/drm/ethosu_accel.h b/include/uapi/drm/ethosu_accel.h index af78bb4686d7..5b97d59a7806 100644 --- a/include/uapi/drm/ethosu_accel.h +++ b/include/uapi/drm/ethosu_accel.h @@ -43,6 +43,11 @@ enum drm_ethosu_ioctl_id { /** @DRM_ETHOSU_SUBMIT: Submit a job and BOs to run. */ DRM_ETHOSU_SUBMIT, + + DRM_ETHOSU_PERFMON_CREATE, + DRM_ETHOSU_PERFMON_DESTROY, + DRM_ETHOSU_PERFMON_GET_VALUES, + DRM_ETHOSU_PERFMON_SET_GLOBAL, }; /** @@ -79,6 +84,7 @@ struct drm_ethosu_npu_info { __u32 config; __u32 sram_size; + __u32 pmu_counters; }; /** @@ -220,10 +226,54 @@ struct drm_ethosu_submit { /** Input: Number of jobs passed in. */ __u32 job_count; - /** Reserved, must be zero. */ + /** Input: Id returned by DRM_ETHOSU_PERFMON_CREATE */ + __u32 perfmon_id; +}; + +#define DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS 8 +#define DRM_ETHOSU_MAX_PERF_COUNTERS \ + (DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS + 1) + +struct drm_ethosu_perfmon_create { + __u32 id; + __u32 ncounters; + __u16 counters[DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS]; +}; + +struct drm_ethosu_perfmon_destroy { + __u32 id; __u32 pad; }; +/* + * Returns the values of the performance counters tracked by this + * perfmon (as an array of (ncounters + 1) u64 values). + * + * No implicit synchronization is performed, so the user has to + * guarantee that any jobs using this perfmon have already been + * completed. + */ +struct drm_ethosu_perfmon_get_values { + __u32 id; + __u32 pad; + __u64 values_ptr; +}; + +#define DRM_ETHOSU_PERFMON_CLEAR_GLOBAL 0x0001 + +/** + * struct drm_ethosu_perfmon_set_global - ioctl to define a global performance + * monitor + * + * The global performance monitor will be used for all jobs. If a global + * performance monitor is defined, jobs with a self-defined performance + * monitor won't be allowed. + */ +struct drm_ethosu_perfmon_set_global { + __u32 flags; + __u32 id; +}; + /** * DRM_IOCTL_ETHOSU() - Build a ethosu IOCTL number * @__access: Access type. Must be R, W or RW. @@ -252,6 +302,14 @@ enum { DRM_IOCTL_ETHOSU(WR, CMDSTREAM_BO_CREATE, cmdstream_bo_create), DRM_IOCTL_ETHOSU_SUBMIT = DRM_IOCTL_ETHOSU(WR, SUBMIT, submit), + DRM_IOCTL_ETHOSU_PERFMON_CREATE = + DRM_IOCTL_ETHOSU(WR, PERFMON_CREATE, perfmon_create), + DRM_IOCTL_ETHOSU_PERFMON_DESTROY = + DRM_IOCTL_ETHOSU(WR, PERFMON_DESTROY, perfmon_destroy), + DRM_IOCTL_ETHOSU_PERFMON_GET_VALUES = + DRM_IOCTL_ETHOSU(WR, PERFMON_GET_VALUES, perfmon_get_values), + DRM_IOCTL_ETHOSU_PERFMON_SET_GLOBAL = + DRM_IOCTL_ETHOSU(WR, PERFMON_SET_GLOBAL, perfmon_set_global), }; #if defined(__cplusplus)