From: Felix Kuehling <Felix.Kuehling@amd.com> To: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org Cc: alex.sierra@amd.com, philip.yang@amd.com Subject: [PATCH 02/35] drm/amdgpu: replace per_device_list by array Date: Wed, 6 Jan 2021 22:00:54 -0500 [thread overview] Message-ID: <20210107030127.20393-3-Felix.Kuehling@amd.com> (raw) In-Reply-To: <20210107030127.20393-1-Felix.Kuehling@amd.com> From: Alex Sierra <alex.sierra@amd.com> Remove per_device_list from kfd_process and replace it with a kfd_process_device pointers array of MAX_GPU_INSTANCES size. This helps to manage the kfd_process_devices binded to a specific kfd_process. Also, functions used by kfd_chardev to iterate over the list were removed, since they are not valid anymore. Instead, it was replaced by a local loop iterating the array. Signed-off-by: Alex Sierra <alex.sierra@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 116 ++++++++---------- drivers/gpu/drm/amd/amdkfd/kfd_iommu.c | 8 +- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 20 +-- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 108 ++++++++-------- .../amd/amdkfd/kfd_process_queue_manager.c | 6 +- 5 files changed, 111 insertions(+), 147 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 8cc51cec988a..8c87afce12df 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -874,52 +874,47 @@ static int kfd_ioctl_get_process_apertures(struct file *filp, { struct kfd_ioctl_get_process_apertures_args *args = data; struct kfd_process_device_apertures *pAperture; - struct kfd_process_device *pdd; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); args->num_of_nodes = 0; mutex_lock(&p->mutex); + /* Run over all pdd of the process */ + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pAperture = + &args->process_apertures[args->num_of_nodes]; + pAperture->gpu_id = pdd->dev->id; + pAperture->lds_base = pdd->lds_base; + pAperture->lds_limit = pdd->lds_limit; + pAperture->gpuvm_base = pdd->gpuvm_base; + pAperture->gpuvm_limit = pdd->gpuvm_limit; + pAperture->scratch_base = pdd->scratch_base; + pAperture->scratch_limit = pdd->scratch_limit; - /*if the process-device list isn't empty*/ - if (kfd_has_process_device_data(p)) { - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pAperture = - &args->process_apertures[args->num_of_nodes]; - pAperture->gpu_id = pdd->dev->id; - pAperture->lds_base = pdd->lds_base; - pAperture->lds_limit = pdd->lds_limit; - pAperture->gpuvm_base = pdd->gpuvm_base; - pAperture->gpuvm_limit = pdd->gpuvm_limit; - pAperture->scratch_base = pdd->scratch_base; - pAperture->scratch_limit = pdd->scratch_limit; - - dev_dbg(kfd_device, - "node id %u\n", args->num_of_nodes); - dev_dbg(kfd_device, - "gpu id %u\n", pdd->dev->id); - dev_dbg(kfd_device, - "lds_base %llX\n", pdd->lds_base); - dev_dbg(kfd_device, - "lds_limit %llX\n", pdd->lds_limit); - dev_dbg(kfd_device, - "gpuvm_base %llX\n", pdd->gpuvm_base); - dev_dbg(kfd_device, - "gpuvm_limit %llX\n", pdd->gpuvm_limit); - dev_dbg(kfd_device, - "scratch_base %llX\n", pdd->scratch_base); - dev_dbg(kfd_device, - "scratch_limit %llX\n", pdd->scratch_limit); - - args->num_of_nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (args->num_of_nodes < NUM_OF_SUPPORTED_GPUS)); - } + dev_dbg(kfd_device, + "node id %u\n", args->num_of_nodes); + dev_dbg(kfd_device, + "gpu id %u\n", pdd->dev->id); + dev_dbg(kfd_device, + "lds_base %llX\n", pdd->lds_base); + dev_dbg(kfd_device, + "lds_limit %llX\n", pdd->lds_limit); + dev_dbg(kfd_device, + "gpuvm_base %llX\n", pdd->gpuvm_base); + dev_dbg(kfd_device, + "gpuvm_limit %llX\n", pdd->gpuvm_limit); + dev_dbg(kfd_device, + "scratch_base %llX\n", pdd->scratch_base); + dev_dbg(kfd_device, + "scratch_limit %llX\n", pdd->scratch_limit); + if (++args->num_of_nodes >= NUM_OF_SUPPORTED_GPUS) + break; + } mutex_unlock(&p->mutex); return 0; @@ -930,9 +925,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, { struct kfd_ioctl_get_process_apertures_new_args *args = data; struct kfd_process_device_apertures *pa; - struct kfd_process_device *pdd; - uint32_t nodes = 0; int ret; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); @@ -941,17 +935,7 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * sufficient memory */ mutex_lock(&p->mutex); - - if (!kfd_has_process_device_data(p)) - goto out_unlock; - - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - args->num_of_nodes++; - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd); - + args->num_of_nodes = p->n_pdds; goto out_unlock; } @@ -966,22 +950,23 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, mutex_lock(&p->mutex); - if (!kfd_has_process_device_data(p)) { + if (!p->n_pdds) { args->num_of_nodes = 0; kfree(pa); goto out_unlock; } /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pa[nodes].gpu_id = pdd->dev->id; - pa[nodes].lds_base = pdd->lds_base; - pa[nodes].lds_limit = pdd->lds_limit; - pa[nodes].gpuvm_base = pdd->gpuvm_base; - pa[nodes].gpuvm_limit = pdd->gpuvm_limit; - pa[nodes].scratch_base = pdd->scratch_base; - pa[nodes].scratch_limit = pdd->scratch_limit; + for (i = 0; i < min(p->n_pdds, args->num_of_nodes); i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pa[i].gpu_id = pdd->dev->id; + pa[i].lds_base = pdd->lds_base; + pa[i].lds_limit = pdd->lds_limit; + pa[i].gpuvm_base = pdd->gpuvm_base; + pa[i].gpuvm_limit = pdd->gpuvm_limit; + pa[i].scratch_base = pdd->scratch_base; + pa[i].scratch_limit = pdd->scratch_limit; dev_dbg(kfd_device, "gpu id %u\n", pdd->dev->id); @@ -997,17 +982,14 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, "scratch_base %llX\n", pdd->scratch_base); dev_dbg(kfd_device, "scratch_limit %llX\n", pdd->scratch_limit); - nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (nodes < args->num_of_nodes)); + } mutex_unlock(&p->mutex); - args->num_of_nodes = nodes; + args->num_of_nodes = i; ret = copy_to_user( (void __user *)args->kfd_process_device_apertures_ptr, pa, - (nodes * sizeof(struct kfd_process_device_apertures))); + (i * sizeof(struct kfd_process_device_apertures))); kfree(pa); return ret ? -EFAULT : 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 5a64915abaf7..1a266b78f0d8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -131,11 +131,11 @@ int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd) */ void kfd_iommu_unbind_process(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->bound == PDD_BOUND) - amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid); + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->bound == PDD_BOUND) + amd_iommu_unbind_pasid(p->pdds[i]->dev->pdev, p->pasid); } /* Callback for process shutdown invoked by the IOMMU driver */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index e2ebd5a1d4de..d9f8d3d48aac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -45,6 +45,7 @@ #include <linux/swap.h> #include "amd_shared.h" +#include "amdgpu.h" #define KFD_MAX_RING_ENTRY_SIZE 8 @@ -644,12 +645,6 @@ enum kfd_pdd_bound { /* Data that is per-process-per device. */ struct kfd_process_device { - /* - * List of all per-device data for a process. - * Starts from kfd_process.per_device_data. - */ - struct list_head per_device_list; - /* The device that owns this data. */ struct kfd_dev *dev; @@ -766,10 +761,11 @@ struct kfd_process { uint16_t pasid; /* - * List of kfd_process_device structures, + * Array of kfd_process_device pointers, * one for each device the process is using. */ - struct list_head per_device_data; + struct kfd_process_device *pdds[MAX_GPU_INSTANCE]; + uint32_t n_pdds; struct process_queue_manager pqm; @@ -867,14 +863,6 @@ void *kfd_process_device_translate_handle(struct kfd_process_device *p, void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd, int handle); -/* Process device data iterator */ -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p); -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd); -bool kfd_has_process_device_data(struct kfd_process *p); - /* PASIDs */ int kfd_pasid_init(void); void kfd_pasid_exit(void); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 2807e1c4d59b..031e752e3154 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -505,7 +505,7 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; if (!p) @@ -520,7 +520,8 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) * - proc/<pid>/stats_<gpuid>/evicted_ms * - proc/<pid>/stats_<gpuid>/cu_occupancy */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; struct kobject *kobj_stats; snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, @@ -571,7 +572,7 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) static int kfd_procfs_add_sysfs_files(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; if (!p) return -EINVAL; @@ -584,7 +585,9 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p) * - proc/<pid>/vram_<gpuid> * - proc/<pid>/sdma_<gpuid> */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u", pdd->dev->id); ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename); @@ -875,21 +878,23 @@ void kfd_unref_process(struct kfd_process *p) kref_put(&p->ref, kfd_process_ref_release); } + static void kfd_process_device_free_bos(struct kfd_process_device *pdd) { struct kfd_process *p = pdd->process; void *mem; int id; + int i; /* * Remove all handles from idr and release appropriate * local memory object */ idr_for_each_entry(&pdd->alloc_idr, mem, id) { - struct kfd_process_device *peer_pdd; - list_for_each_entry(peer_pdd, &p->per_device_data, - per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *peer_pdd = p->pdds[i]; + if (!peer_pdd->vm) continue; amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( @@ -903,18 +908,19 @@ static void kfd_process_device_free_bos(struct kfd_process_device *pdd) static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_device_free_bos(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_device_free_bos(p->pdds[i]); } static void kfd_process_destroy_pdds(struct kfd_process *p) { - struct kfd_process_device *pdd, *temp; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry_safe(pdd, temp, &p->per_device_data, - per_device_list) { pr_debug("Releasing pdd (topology id %d) for process (pasid 0x%x)\n", pdd->dev->id, p->pasid); @@ -927,8 +933,6 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) amdgpu_amdkfd_gpuvm_destroy_process_vm( pdd->dev->kgd, pdd->vm); - list_del(&pdd->per_device_list); - if (pdd->qpd.cwsr_kaddr && !pdd->qpd.cwsr_base) free_pages((unsigned long)pdd->qpd.cwsr_kaddr, get_order(KFD_CWSR_TBA_TMA_SIZE)); @@ -949,7 +953,9 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) } kfree(pdd); + p->pdds[i] = NULL; } + p->n_pdds = 0; } /* No process locking is needed in this function, because the process @@ -961,7 +967,7 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); - struct kfd_process_device *pdd; + int i; /* Remove the procfs files */ if (p->kobj) { @@ -970,7 +976,9 @@ static void kfd_process_wq_release(struct work_struct *work) kobject_put(p->kobj_queues); p->kobj_queues = NULL; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); sysfs_remove_file(p->kobj, &pdd->attr_evict); @@ -1020,7 +1028,7 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kfd_process *p; - struct kfd_process_device *pdd = NULL; + int i; /* * The kfd_process structure can not be free because the @@ -1044,8 +1052,8 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, * pdd is in debug mode, we should first force unregistration, * then we will be able to destroy the queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; mutex_lock(kfd_get_dbgmgr_mutex()); if (dev && dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) { @@ -1081,11 +1089,11 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep) { unsigned long offset; - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; - struct qcm_process_device *qpd = &pdd->qpd; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; + struct qcm_process_device *qpd = &p->pdds[i]->qpd; if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base) continue; @@ -1162,7 +1170,7 @@ static struct kfd_process *create_process(const struct task_struct *thread) mutex_init(&process->mutex); process->mm = thread->mm; process->lead_thread = thread->group_leader; - INIT_LIST_HEAD(&process->per_device_data); + process->n_pdds = 0; INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); process->last_restore_timestamp = get_jiffies_64(); @@ -1244,11 +1252,11 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd, struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev, struct kfd_process *p) { - struct kfd_process_device *pdd = NULL; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->dev == dev) - return pdd; + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->dev == dev) + return p->pdds[i]; return NULL; } @@ -1258,6 +1266,8 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, { struct kfd_process_device *pdd = NULL; + if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) + return NULL; pdd = kzalloc(sizeof(*pdd), GFP_KERNEL); if (!pdd) return NULL; @@ -1286,7 +1296,7 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, 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); + p->pdds[p->n_pdds++] = pdd; /* Init idr used for memory handle translation */ idr_init(&pdd->alloc_idr); @@ -1418,28 +1428,6 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev, return ERR_PTR(err); } -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p) -{ - return list_first_entry(&p->per_device_data, - struct kfd_process_device, - per_device_list); -} - -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd) -{ - if (list_is_last(&pdd->per_device_list, &p->per_device_data)) - return NULL; - return list_next_entry(pdd, per_device_list); -} - -bool kfd_has_process_device_data(struct kfd_process *p) -{ - return !(list_empty(&p->per_device_data)); -} - /* Create specific handle mapped to mem from process local memory idr * Assumes that the process lock is held. */ @@ -1515,11 +1503,13 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm) */ int kfd_process_evict_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r = 0; + int i; unsigned int n_evicted = 0; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { @@ -1535,7 +1525,9 @@ int kfd_process_evict_queues(struct kfd_process *p) /* To keep state consistent, roll back partial eviction by * restoring queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + if (n_evicted == 0) break; if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, @@ -1551,10 +1543,12 @@ int kfd_process_evict_queues(struct kfd_process *p) /* kfd_process_restore_queues - Restore all user queues of a process */ int kfd_process_restore_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r, ret = 0; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { r = pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index eb1635ac8988..95a6c36cea4c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -126,10 +126,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void kfd_process_dequeue_from_all_devices(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_dequeue_from_device(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_dequeue_from_device(p->pdds[i]); } int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) -- 2.29.2 _______________________________________________ dri-devel mailing list dri-devel@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/dri-devel
WARNING: multiple messages have this Message-ID (diff)
From: Felix Kuehling <Felix.Kuehling@amd.com> To: amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org Cc: alex.sierra@amd.com, philip.yang@amd.com Subject: [PATCH 02/35] drm/amdgpu: replace per_device_list by array Date: Wed, 6 Jan 2021 22:00:54 -0500 [thread overview] Message-ID: <20210107030127.20393-3-Felix.Kuehling@amd.com> (raw) In-Reply-To: <20210107030127.20393-1-Felix.Kuehling@amd.com> From: Alex Sierra <alex.sierra@amd.com> Remove per_device_list from kfd_process and replace it with a kfd_process_device pointers array of MAX_GPU_INSTANCES size. This helps to manage the kfd_process_devices binded to a specific kfd_process. Also, functions used by kfd_chardev to iterate over the list were removed, since they are not valid anymore. Instead, it was replaced by a local loop iterating the array. Signed-off-by: Alex Sierra <alex.sierra@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> --- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 116 ++++++++---------- drivers/gpu/drm/amd/amdkfd/kfd_iommu.c | 8 +- drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 20 +-- drivers/gpu/drm/amd/amdkfd/kfd_process.c | 108 ++++++++-------- .../amd/amdkfd/kfd_process_queue_manager.c | 6 +- 5 files changed, 111 insertions(+), 147 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 8cc51cec988a..8c87afce12df 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -874,52 +874,47 @@ static int kfd_ioctl_get_process_apertures(struct file *filp, { struct kfd_ioctl_get_process_apertures_args *args = data; struct kfd_process_device_apertures *pAperture; - struct kfd_process_device *pdd; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); args->num_of_nodes = 0; mutex_lock(&p->mutex); + /* Run over all pdd of the process */ + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pAperture = + &args->process_apertures[args->num_of_nodes]; + pAperture->gpu_id = pdd->dev->id; + pAperture->lds_base = pdd->lds_base; + pAperture->lds_limit = pdd->lds_limit; + pAperture->gpuvm_base = pdd->gpuvm_base; + pAperture->gpuvm_limit = pdd->gpuvm_limit; + pAperture->scratch_base = pdd->scratch_base; + pAperture->scratch_limit = pdd->scratch_limit; - /*if the process-device list isn't empty*/ - if (kfd_has_process_device_data(p)) { - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pAperture = - &args->process_apertures[args->num_of_nodes]; - pAperture->gpu_id = pdd->dev->id; - pAperture->lds_base = pdd->lds_base; - pAperture->lds_limit = pdd->lds_limit; - pAperture->gpuvm_base = pdd->gpuvm_base; - pAperture->gpuvm_limit = pdd->gpuvm_limit; - pAperture->scratch_base = pdd->scratch_base; - pAperture->scratch_limit = pdd->scratch_limit; - - dev_dbg(kfd_device, - "node id %u\n", args->num_of_nodes); - dev_dbg(kfd_device, - "gpu id %u\n", pdd->dev->id); - dev_dbg(kfd_device, - "lds_base %llX\n", pdd->lds_base); - dev_dbg(kfd_device, - "lds_limit %llX\n", pdd->lds_limit); - dev_dbg(kfd_device, - "gpuvm_base %llX\n", pdd->gpuvm_base); - dev_dbg(kfd_device, - "gpuvm_limit %llX\n", pdd->gpuvm_limit); - dev_dbg(kfd_device, - "scratch_base %llX\n", pdd->scratch_base); - dev_dbg(kfd_device, - "scratch_limit %llX\n", pdd->scratch_limit); - - args->num_of_nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (args->num_of_nodes < NUM_OF_SUPPORTED_GPUS)); - } + dev_dbg(kfd_device, + "node id %u\n", args->num_of_nodes); + dev_dbg(kfd_device, + "gpu id %u\n", pdd->dev->id); + dev_dbg(kfd_device, + "lds_base %llX\n", pdd->lds_base); + dev_dbg(kfd_device, + "lds_limit %llX\n", pdd->lds_limit); + dev_dbg(kfd_device, + "gpuvm_base %llX\n", pdd->gpuvm_base); + dev_dbg(kfd_device, + "gpuvm_limit %llX\n", pdd->gpuvm_limit); + dev_dbg(kfd_device, + "scratch_base %llX\n", pdd->scratch_base); + dev_dbg(kfd_device, + "scratch_limit %llX\n", pdd->scratch_limit); + if (++args->num_of_nodes >= NUM_OF_SUPPORTED_GPUS) + break; + } mutex_unlock(&p->mutex); return 0; @@ -930,9 +925,8 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, { struct kfd_ioctl_get_process_apertures_new_args *args = data; struct kfd_process_device_apertures *pa; - struct kfd_process_device *pdd; - uint32_t nodes = 0; int ret; + int i; dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid); @@ -941,17 +935,7 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, * sufficient memory */ mutex_lock(&p->mutex); - - if (!kfd_has_process_device_data(p)) - goto out_unlock; - - /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - args->num_of_nodes++; - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd); - + args->num_of_nodes = p->n_pdds; goto out_unlock; } @@ -966,22 +950,23 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, mutex_lock(&p->mutex); - if (!kfd_has_process_device_data(p)) { + if (!p->n_pdds) { args->num_of_nodes = 0; kfree(pa); goto out_unlock; } /* Run over all pdd of the process */ - pdd = kfd_get_first_process_device_data(p); - do { - pa[nodes].gpu_id = pdd->dev->id; - pa[nodes].lds_base = pdd->lds_base; - pa[nodes].lds_limit = pdd->lds_limit; - pa[nodes].gpuvm_base = pdd->gpuvm_base; - pa[nodes].gpuvm_limit = pdd->gpuvm_limit; - pa[nodes].scratch_base = pdd->scratch_base; - pa[nodes].scratch_limit = pdd->scratch_limit; + for (i = 0; i < min(p->n_pdds, args->num_of_nodes); i++) { + struct kfd_process_device *pdd = p->pdds[i]; + + pa[i].gpu_id = pdd->dev->id; + pa[i].lds_base = pdd->lds_base; + pa[i].lds_limit = pdd->lds_limit; + pa[i].gpuvm_base = pdd->gpuvm_base; + pa[i].gpuvm_limit = pdd->gpuvm_limit; + pa[i].scratch_base = pdd->scratch_base; + pa[i].scratch_limit = pdd->scratch_limit; dev_dbg(kfd_device, "gpu id %u\n", pdd->dev->id); @@ -997,17 +982,14 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp, "scratch_base %llX\n", pdd->scratch_base); dev_dbg(kfd_device, "scratch_limit %llX\n", pdd->scratch_limit); - nodes++; - - pdd = kfd_get_next_process_device_data(p, pdd); - } while (pdd && (nodes < args->num_of_nodes)); + } mutex_unlock(&p->mutex); - args->num_of_nodes = nodes; + args->num_of_nodes = i; ret = copy_to_user( (void __user *)args->kfd_process_device_apertures_ptr, pa, - (nodes * sizeof(struct kfd_process_device_apertures))); + (i * sizeof(struct kfd_process_device_apertures))); kfree(pa); return ret ? -EFAULT : 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 5a64915abaf7..1a266b78f0d8 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -131,11 +131,11 @@ int kfd_iommu_bind_process_to_device(struct kfd_process_device *pdd) */ void kfd_iommu_unbind_process(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->bound == PDD_BOUND) - amd_iommu_unbind_pasid(pdd->dev->pdev, p->pasid); + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->bound == PDD_BOUND) + amd_iommu_unbind_pasid(p->pdds[i]->dev->pdev, p->pasid); } /* Callback for process shutdown invoked by the IOMMU driver */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index e2ebd5a1d4de..d9f8d3d48aac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -45,6 +45,7 @@ #include <linux/swap.h> #include "amd_shared.h" +#include "amdgpu.h" #define KFD_MAX_RING_ENTRY_SIZE 8 @@ -644,12 +645,6 @@ enum kfd_pdd_bound { /* Data that is per-process-per device. */ struct kfd_process_device { - /* - * List of all per-device data for a process. - * Starts from kfd_process.per_device_data. - */ - struct list_head per_device_list; - /* The device that owns this data. */ struct kfd_dev *dev; @@ -766,10 +761,11 @@ struct kfd_process { uint16_t pasid; /* - * List of kfd_process_device structures, + * Array of kfd_process_device pointers, * one for each device the process is using. */ - struct list_head per_device_data; + struct kfd_process_device *pdds[MAX_GPU_INSTANCE]; + uint32_t n_pdds; struct process_queue_manager pqm; @@ -867,14 +863,6 @@ void *kfd_process_device_translate_handle(struct kfd_process_device *p, void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd, int handle); -/* Process device data iterator */ -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p); -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd); -bool kfd_has_process_device_data(struct kfd_process *p); - /* PASIDs */ int kfd_pasid_init(void); void kfd_pasid_exit(void); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 2807e1c4d59b..031e752e3154 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -505,7 +505,7 @@ static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; if (!p) @@ -520,7 +520,8 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) * - proc/<pid>/stats_<gpuid>/evicted_ms * - proc/<pid>/stats_<gpuid>/cu_occupancy */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; struct kobject *kobj_stats; snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, @@ -571,7 +572,7 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) static int kfd_procfs_add_sysfs_files(struct kfd_process *p) { int ret = 0; - struct kfd_process_device *pdd; + int i; if (!p) return -EINVAL; @@ -584,7 +585,9 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p) * - proc/<pid>/vram_<gpuid> * - proc/<pid>/sdma_<gpuid> */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u", pdd->dev->id); ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename); @@ -875,21 +878,23 @@ void kfd_unref_process(struct kfd_process *p) kref_put(&p->ref, kfd_process_ref_release); } + static void kfd_process_device_free_bos(struct kfd_process_device *pdd) { struct kfd_process *p = pdd->process; void *mem; int id; + int i; /* * Remove all handles from idr and release appropriate * local memory object */ idr_for_each_entry(&pdd->alloc_idr, mem, id) { - struct kfd_process_device *peer_pdd; - list_for_each_entry(peer_pdd, &p->per_device_data, - per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *peer_pdd = p->pdds[i]; + if (!peer_pdd->vm) continue; amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( @@ -903,18 +908,19 @@ static void kfd_process_device_free_bos(struct kfd_process_device *pdd) static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_device_free_bos(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_device_free_bos(p->pdds[i]); } static void kfd_process_destroy_pdds(struct kfd_process *p) { - struct kfd_process_device *pdd, *temp; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry_safe(pdd, temp, &p->per_device_data, - per_device_list) { pr_debug("Releasing pdd (topology id %d) for process (pasid 0x%x)\n", pdd->dev->id, p->pasid); @@ -927,8 +933,6 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) amdgpu_amdkfd_gpuvm_destroy_process_vm( pdd->dev->kgd, pdd->vm); - list_del(&pdd->per_device_list); - if (pdd->qpd.cwsr_kaddr && !pdd->qpd.cwsr_base) free_pages((unsigned long)pdd->qpd.cwsr_kaddr, get_order(KFD_CWSR_TBA_TMA_SIZE)); @@ -949,7 +953,9 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) } kfree(pdd); + p->pdds[i] = NULL; } + p->n_pdds = 0; } /* No process locking is needed in this function, because the process @@ -961,7 +967,7 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); - struct kfd_process_device *pdd; + int i; /* Remove the procfs files */ if (p->kobj) { @@ -970,7 +976,9 @@ static void kfd_process_wq_release(struct work_struct *work) kobject_put(p->kobj_queues); p->kobj_queues = NULL; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + sysfs_remove_file(p->kobj, &pdd->attr_vram); sysfs_remove_file(p->kobj, &pdd->attr_sdma); sysfs_remove_file(p->kobj, &pdd->attr_evict); @@ -1020,7 +1028,7 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kfd_process *p; - struct kfd_process_device *pdd = NULL; + int i; /* * The kfd_process structure can not be free because the @@ -1044,8 +1052,8 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn, * pdd is in debug mode, we should first force unregistration, * then we will be able to destroy the queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; mutex_lock(kfd_get_dbgmgr_mutex()); if (dev && dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) { @@ -1081,11 +1089,11 @@ static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = { static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep) { unsigned long offset; - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { - struct kfd_dev *dev = pdd->dev; - struct qcm_process_device *qpd = &pdd->qpd; + for (i = 0; i < p->n_pdds; i++) { + struct kfd_dev *dev = p->pdds[i]->dev; + struct qcm_process_device *qpd = &p->pdds[i]->qpd; if (!dev->cwsr_enabled || qpd->cwsr_kaddr || qpd->cwsr_base) continue; @@ -1162,7 +1170,7 @@ static struct kfd_process *create_process(const struct task_struct *thread) mutex_init(&process->mutex); process->mm = thread->mm; process->lead_thread = thread->group_leader; - INIT_LIST_HEAD(&process->per_device_data); + process->n_pdds = 0; INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); process->last_restore_timestamp = get_jiffies_64(); @@ -1244,11 +1252,11 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd, struct kfd_process_device *kfd_get_process_device_data(struct kfd_dev *dev, struct kfd_process *p) { - struct kfd_process_device *pdd = NULL; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - if (pdd->dev == dev) - return pdd; + for (i = 0; i < p->n_pdds; i++) + if (p->pdds[i]->dev == dev) + return p->pdds[i]; return NULL; } @@ -1258,6 +1266,8 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, { struct kfd_process_device *pdd = NULL; + if (WARN_ON_ONCE(p->n_pdds >= MAX_GPU_INSTANCE)) + return NULL; pdd = kzalloc(sizeof(*pdd), GFP_KERNEL); if (!pdd) return NULL; @@ -1286,7 +1296,7 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev, 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); + p->pdds[p->n_pdds++] = pdd; /* Init idr used for memory handle translation */ idr_init(&pdd->alloc_idr); @@ -1418,28 +1428,6 @@ struct kfd_process_device *kfd_bind_process_to_device(struct kfd_dev *dev, return ERR_PTR(err); } -struct kfd_process_device *kfd_get_first_process_device_data( - struct kfd_process *p) -{ - return list_first_entry(&p->per_device_data, - struct kfd_process_device, - per_device_list); -} - -struct kfd_process_device *kfd_get_next_process_device_data( - struct kfd_process *p, - struct kfd_process_device *pdd) -{ - if (list_is_last(&pdd->per_device_list, &p->per_device_data)) - return NULL; - return list_next_entry(pdd, per_device_list); -} - -bool kfd_has_process_device_data(struct kfd_process *p) -{ - return !(list_empty(&p->per_device_data)); -} - /* Create specific handle mapped to mem from process local memory idr * Assumes that the process lock is held. */ @@ -1515,11 +1503,13 @@ struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm) */ int kfd_process_evict_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r = 0; + int i; unsigned int n_evicted = 0; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + r = pdd->dev->dqm->ops.evict_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { @@ -1535,7 +1525,9 @@ int kfd_process_evict_queues(struct kfd_process *p) /* To keep state consistent, roll back partial eviction by * restoring queues */ - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; + if (n_evicted == 0) break; if (pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, @@ -1551,10 +1543,12 @@ int kfd_process_evict_queues(struct kfd_process *p) /* kfd_process_restore_queues - Restore all user queues of a process */ int kfd_process_restore_queues(struct kfd_process *p) { - struct kfd_process_device *pdd; int r, ret = 0; + int i; + + for (i = 0; i < p->n_pdds; i++) { + struct kfd_process_device *pdd = p->pdds[i]; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) { r = pdd->dev->dqm->ops.restore_process_queues(pdd->dev->dqm, &pdd->qpd); if (r) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index eb1635ac8988..95a6c36cea4c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -126,10 +126,10 @@ int pqm_set_gws(struct process_queue_manager *pqm, unsigned int qid, void kfd_process_dequeue_from_all_devices(struct kfd_process *p) { - struct kfd_process_device *pdd; + int i; - list_for_each_entry(pdd, &p->per_device_data, per_device_list) - kfd_process_dequeue_from_device(pdd); + for (i = 0; i < p->n_pdds; i++) + kfd_process_dequeue_from_device(p->pdds[i]); } int pqm_init(struct process_queue_manager *pqm, struct kfd_process *p) -- 2.29.2 _______________________________________________ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next prev parent reply other threads:[~2021-01-07 3:02 UTC|newest] Thread overview: 168+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-01-07 3:00 [PATCH 00/35] Add HMM-based SVM memory manager to KFD Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` [PATCH 01/35] drm/amdkfd: select kernel DEVICE_PRIVATE option Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling [this message] 2021-01-07 3:00 ` [PATCH 02/35] drm/amdgpu: replace per_device_list by array Felix Kuehling 2021-01-07 3:00 ` [PATCH 03/35] drm/amdkfd: helper to convert gpu id and idx Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` [PATCH 04/35] drm/amdkfd: add svm ioctl API Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` [PATCH 05/35] drm/amdkfd: Add SVM API support capability bits Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` [PATCH 06/35] drm/amdkfd: register svm range Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:00 ` [PATCH 07/35] drm/amdkfd: add svm ioctl GET_ATTR op Felix Kuehling 2021-01-07 3:00 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 08/35] drm/amdgpu: add common HMM get pages function Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 10:53 ` Christian König 2021-01-07 10:53 ` Christian König 2021-01-07 3:01 ` [PATCH 09/35] drm/amdkfd: validate svm range system memory Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 10/35] drm/amdkfd: register overlap system memory range Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 11/35] drm/amdkfd: deregister svm range Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 12/35] drm/amdgpu: export vm update mapping interface Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 10:54 ` Christian König 2021-01-07 10:54 ` Christian König 2021-01-07 3:01 ` [PATCH 13/35] drm/amdkfd: map svm range to GPUs Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 14/35] drm/amdkfd: svm range eviction and restore Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 15/35] drm/amdkfd: add xnack enabled flag to kfd_process Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 16/35] drm/amdkfd: add ioctl to configure and query xnack retries Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 17/35] drm/amdkfd: register HMM device private zone Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-03-01 8:32 ` Daniel Vetter 2021-03-01 8:32 ` Daniel Vetter 2021-03-01 8:46 ` Thomas Hellström (Intel) 2021-03-01 8:46 ` Thomas Hellström (Intel) 2021-03-01 8:58 ` Daniel Vetter 2021-03-01 8:58 ` Daniel Vetter 2021-03-01 9:30 ` Thomas Hellström (Intel) 2021-03-01 9:30 ` Thomas Hellström (Intel) 2021-03-04 17:58 ` Felix Kuehling 2021-03-04 17:58 ` Felix Kuehling 2021-03-11 12:24 ` Thomas Hellström (Intel) 2021-03-11 12:24 ` Thomas Hellström (Intel) 2021-01-07 3:01 ` [PATCH 18/35] drm/amdkfd: validate vram svm range from TTM Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 19/35] drm/amdkfd: support xgmi same hive mapping Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 20/35] drm/amdkfd: copy memory through gart table Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 21/35] drm/amdkfd: HMM migrate ram to vram Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 22/35] drm/amdkfd: HMM migrate vram to ram Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 23/35] drm/amdkfd: invalidate tables on page retry fault Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 24/35] drm/amdkfd: page table restore through svm API Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 25/35] drm/amdkfd: SVM API call to restore page tables Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 26/35] drm/amdkfd: add svm_bo reference for eviction fence Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 27/35] drm/amdgpu: add param bit flag to create SVM BOs Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 28/35] drm/amdkfd: add svm_bo eviction mechanism support Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 29/35] drm/amdgpu: svm bo enable_signal call condition Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 10:56 ` Christian König 2021-01-07 10:56 ` Christian König 2021-01-07 16:16 ` Felix Kuehling 2021-01-07 16:16 ` Felix Kuehling 2021-01-07 16:28 ` Christian König 2021-01-07 16:28 ` Christian König 2021-01-07 16:53 ` Felix Kuehling 2021-01-07 16:53 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 30/35] drm/amdgpu: add svm_bo eviction to enable_signal cb Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 31/35] drm/amdgpu: reserve fence slot to update page table Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 10:57 ` Christian König 2021-01-07 10:57 ` Christian König 2021-01-07 3:01 ` [PATCH 32/35] drm/amdgpu: enable retry fault wptr overflow Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 11:01 ` Christian König 2021-01-07 11:01 ` Christian König 2021-01-07 3:01 ` [PATCH 33/35] drm/amdkfd: refine migration policy with xnack on Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 34/35] drm/amdkfd: add svm range validate timestamp Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 3:01 ` [PATCH 35/35] drm/amdkfd: multiple gpu migrate vram to vram Felix Kuehling 2021-01-07 3:01 ` Felix Kuehling 2021-01-07 9:23 ` [PATCH 00/35] Add HMM-based SVM memory manager to KFD Daniel Vetter 2021-01-07 9:23 ` Daniel Vetter 2021-01-07 16:25 ` Felix Kuehling 2021-01-07 16:25 ` Felix Kuehling 2021-01-08 14:40 ` Daniel Vetter 2021-01-08 14:40 ` Daniel Vetter 2021-01-08 14:45 ` Christian König 2021-01-08 14:45 ` Christian König 2021-01-08 15:58 ` Felix Kuehling 2021-01-08 15:58 ` Felix Kuehling 2021-01-08 16:06 ` Daniel Vetter 2021-01-08 16:06 ` Daniel Vetter 2021-01-08 16:36 ` Felix Kuehling 2021-01-08 16:36 ` Felix Kuehling 2021-01-08 16:53 ` Daniel Vetter 2021-01-08 16:53 ` Daniel Vetter 2021-01-08 17:56 ` Felix Kuehling 2021-01-08 17:56 ` Felix Kuehling 2021-01-11 16:29 ` Daniel Vetter 2021-01-11 16:29 ` Daniel Vetter 2021-01-14 5:34 ` Felix Kuehling 2021-01-14 5:34 ` Felix Kuehling 2021-01-14 12:19 ` Christian König 2021-01-14 12:19 ` Christian König 2021-01-13 16:56 ` Jerome Glisse 2021-01-13 16:56 ` Jerome Glisse 2021-01-13 20:31 ` Daniel Vetter 2021-01-13 20:31 ` Daniel Vetter 2021-01-14 3:27 ` Jerome Glisse 2021-01-14 3:27 ` Jerome Glisse 2021-01-14 9:26 ` Daniel Vetter 2021-01-14 9:26 ` Daniel Vetter 2021-01-14 10:39 ` Daniel Vetter 2021-01-14 10:39 ` Daniel Vetter 2021-01-14 10:49 ` Christian König 2021-01-14 10:49 ` Christian König 2021-01-14 11:52 ` Daniel Vetter 2021-01-14 11:52 ` Daniel Vetter 2021-01-14 13:37 ` HMM fence (was Re: [PATCH 00/35] Add HMM-based SVM memory manager to KFD) Christian König 2021-01-14 13:37 ` Christian König 2021-01-14 13:57 ` Daniel Vetter 2021-01-14 13:57 ` Daniel Vetter 2021-01-14 14:13 ` Christian König 2021-01-14 14:13 ` Christian König 2021-01-14 14:23 ` Daniel Vetter 2021-01-14 14:23 ` Daniel Vetter 2021-01-14 15:08 ` Christian König 2021-01-14 15:08 ` Christian König 2021-01-14 15:40 ` Daniel Vetter 2021-01-14 15:40 ` Daniel Vetter 2021-01-14 16:01 ` Christian König 2021-01-14 16:01 ` Christian König 2021-01-14 16:36 ` Daniel Vetter 2021-01-14 16:36 ` Daniel Vetter 2021-01-14 19:08 ` Christian König 2021-01-14 19:08 ` Christian König 2021-01-14 20:09 ` Daniel Vetter 2021-01-14 20:09 ` Daniel Vetter 2021-01-14 16:51 ` Jerome Glisse 2021-01-14 16:51 ` Jerome Glisse 2021-01-14 21:13 ` Felix Kuehling 2021-01-14 21:13 ` Felix Kuehling 2021-01-15 7:47 ` Christian König 2021-01-15 7:47 ` Christian König 2021-01-13 16:47 ` [PATCH 00/35] Add HMM-based SVM memory manager to KFD Jerome Glisse 2021-01-13 16:47 ` Jerome Glisse 2021-01-14 0:06 ` Felix Kuehling 2021-01-14 0:06 ` Felix Kuehling
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20210107030127.20393-3-Felix.Kuehling@amd.com \ --to=felix.kuehling@amd.com \ --cc=alex.sierra@amd.com \ --cc=amd-gfx@lists.freedesktop.org \ --cc=dri-devel@lists.freedesktop.org \ --cc=philip.yang@amd.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.