diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 1181dfb279b8e0757933d8ee04cb20fdef6d5d6c..4412c2fc72ebe45cd35455d53790849b836b02b1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -761,6 +761,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm, pr_info_ratelimited("Evicting PASID 0x%x queues\n", pdd->process->pasid); + pdd->last_evict_timestamp = get_jiffies_64(); /* Mark all queues as evicted. Deactivate all active queues on * the qpd. */ @@ -826,6 +827,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm, qpd->mapped_gws_queue = false; } } + pdd->last_evict_timestamp = get_jiffies_64(); retval = execute_queues_cpsch(dqm, qpd->is_debug ? KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES : @@ -845,6 +847,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, struct mqd_manager *mqd_mgr; struct kfd_process_device *pdd; uint64_t pd_base; + uint64_t eviction_duration; int retval, ret = 0; pdd = qpd_to_pdd(qpd); @@ -912,6 +915,8 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm, ret = retval; } qpd->evicted = 0; + eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp; + atomic64_add(eviction_duration, &pdd->evict_duration_counter); out: if (mm) mmput(mm); @@ -925,6 +930,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, struct queue *q; struct kfd_process_device *pdd; uint64_t pd_base; + uint64_t eviction_duration; int retval = 0; pdd = qpd_to_pdd(qpd); @@ -963,6 +969,8 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0, USE_DEFAULT_GRACE_PERIOD); qpd->evicted = 0; + eviction_duration = get_jiffies_64() - pdd->last_evict_timestamp; + atomic64_add(eviction_duration, &pdd->evict_duration_counter); out: dqm_unlock(dqm); return retval; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 018c164c7c5c1c6d8290e999344f5b1a8883ea0d..5e18c27867302ddbb649c6c0d8555848b850ee53 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -723,7 +723,7 @@ enum kfd_pdd_bound { PDD_BOUND_SUSPENDED, }; -#define MAX_SYSFS_FILENAME_LEN 11 +#define MAX_SYSFS_FILENAME_LEN 15 /* * SDMA counter runs at 100MHz frequency. @@ -796,6 +796,13 @@ struct kfd_process_device { uint64_t sdma_past_activity_counter; struct attribute attr_sdma; char sdma_filename[MAX_SYSFS_FILENAME_LEN]; + + /* Eviction activity tracking */ + uint64_t last_evict_timestamp; + atomic64_t evict_duration_counter; + struct attribute attr_evict; + + struct kobject *kobj_stats; }; #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 0f1ae3fc26712bc07f6e51ba0e27af85de45e74d..1465c3ff2dce77675370bb955acea84851183b4b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -359,6 +359,26 @@ static ssize_t kfd_procfs_queue_show(struct kobject *kobj, return 0; } +static ssize_t kfd_procfs_stats_show(struct kobject *kobj, + struct attribute *attr, char *buffer) +{ + if (strcmp(attr->name, "evicted_ms") == 0) { + struct kfd_process_device *pdd = container_of(attr, + struct kfd_process_device, + attr_evict); + uint64_t evict_jiffies; + + evict_jiffies = atomic64_read(&pdd->evict_duration_counter); + + return snprintf(buffer, + PAGE_SIZE, + "%llu\n", + jiffies64_to_msecs(evict_jiffies)); + } else + pr_err("Invalid attribute"); + + return 0; +} static struct attribute attr_queue_size = { .name = "size", @@ -391,6 +411,19 @@ static struct kobj_type procfs_queue_type = { .default_attrs = procfs_queue_attrs, }; +static const struct sysfs_ops procfs_stats_ops = { + .show = kfd_procfs_stats_show, +}; + +static struct attribute *procfs_stats_attrs[] = { + NULL +}; + +static struct kobj_type procfs_stats_type = { + .sysfs_ops = &procfs_stats_ops, + .default_attrs = procfs_stats_attrs, +}; + int kfd_procfs_add_queue(struct queue *q) { struct kfd_process *proc; @@ -432,6 +465,58 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, return ret; } +static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) +{ + int ret = 0; + struct kfd_process_device *pdd; + char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; + + if (!p) + return -EINVAL; + + if (!p->kobj) + return -EFAULT; + + /* + * Create sysfs files for each GPU: + * - proc/<pid>/stats_<gpuid>/ + * - proc/<pid>/stats_<gpuid>/evicted_ms + */ + list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + struct kobject *kobj_stats; + + snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, + "stats_%u", pdd->dev->id); + kobj_stats = kfd_alloc_struct(kobj_stats); + if (!kobj_stats) + return -ENOMEM; + + ret = kobject_init_and_add(kobj_stats, + &procfs_stats_type, + p->kobj, + stats_dir_filename); + + if (ret) { + pr_warn("Creating KFD proc/stats_%s folder failed", + stats_dir_filename); + kobject_put(kobj_stats); + goto err; + } + + pdd->kobj_stats = kobj_stats; + pdd->attr_evict.name = "evicted_ms"; + pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE; + sysfs_attr_init(&pdd->attr_evict); + ret = sysfs_create_file(kobj_stats, &pdd->attr_evict); + if (ret) + pr_warn("Creating eviction stats for gpuid %d failed", + (int)pdd->dev->id); + } +err: + return ret; +} + + static int kfd_procfs_add_sysfs_files(struct kfd_process *p) { int ret = 0; @@ -680,6 +765,16 @@ struct kfd_process *kfd_create_process(struct task_struct *thread) if (!process->kobj_queues) pr_warn("Creating KFD proc/queues folder failed"); + ret = kfd_procfs_add_sysfs_stats(process); + if (ret) + pr_warn("Creating sysfs stats dir for pid %d failed", + (int)process->lead_thread->pid); + + ret = kfd_procfs_add_sysfs_stats(process); + if (ret) + pr_warn("Creating sysfs stats dir for pid %d failed", + (int)process->lead_thread->pid); + ret = kfd_procfs_add_sysfs_files(process); if (ret) pr_warn("Creating sysfs usage file for pid %d failed", @@ -864,6 +959,10 @@ static void kfd_process_wq_release(struct work_struct *work) list_for_each_entry(pdd, &p->per_device_data, per_device_list) { sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); + sysfs_remove_file(p->kobj, &pdd->attr_evict); + kobject_del(pdd->kobj_stats); + kobject_put(pdd->kobj_stats); + pdd->kobj_stats = NULL; } kobject_del(p->kobj); @@ -1228,6 +1327,7 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, pdd->runtime_inuse = false; pdd->vram_usage = 0; pdd->sdma_past_activity_counter = 0; + atomic64_set(&pdd->evict_duration_counter, 0); list_add(&pdd->per_device_list, &p->per_device_data); /* Init idr used for memory handle translation */