diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 299 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 71 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 211 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c | 78 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 6 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 81 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 90 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 24 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 7 |
14 files changed, 362 insertions, 524 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig index b91e79c721e2..22d88f8ef527 100644 --- a/drivers/gpu/drm/amd/amdgpu/Kconfig +++ b/drivers/gpu/drm/amd/amdgpu/Kconfig @@ -21,6 +21,7 @@ config DRM_AMDGPU select INTERVAL_TREE select DRM_BUDDY select DRM_SUBALLOC_HELPER + select DRM_EXEC # amdgpu depends on ACPI_VIDEO when ACPI is enabled, for select to work # ACPI_VIDEO's dependencies must also be selected. select INPUT if ACPI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8eda1a8d79ab..035437d7d73a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -53,7 +53,6 @@ #include <drm/ttm/ttm_bo.h> #include <drm/ttm/ttm_placement.h> -#include <drm/ttm/ttm_execbuf_util.h> #include <drm/amdgpu_drm.h> #include <drm/drm_gem.h> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index b34418e3e006..082c9f4cfd34 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -25,6 +25,7 @@ #ifndef AMDGPU_AMDKFD_H_INCLUDED #define AMDGPU_AMDKFD_H_INCLUDED +#include <linux/list.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/kthread.h> @@ -32,7 +33,6 @@ #include <linux/mmu_notifier.h> #include <linux/memremap.h> #include <kgd_kfd_interface.h> -#include <drm/ttm/ttm_execbuf_util.h> #include "amdgpu_sync.h" #include "amdgpu_vm.h" #include "amdgpu_xcp.h" @@ -71,8 +71,7 @@ struct kgd_mem { struct hmm_range *range; struct list_head attachments; /* protected by amdkfd_process_info.lock */ - struct ttm_validate_buffer validate_list; - struct ttm_validate_buffer resv_list; + struct list_head validate_list; uint32_t domain; unsigned int mapped_to_gpu_memory; uint64_t va; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index d34c3ef8f3ed..a136fba9f29b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -27,6 +27,8 @@ #include <linux/sched/task.h> #include <drm/ttm/ttm_tt.h> +#include <drm/drm_exec.h> + #include "amdgpu_object.h" #include "amdgpu_gem.h" #include "amdgpu_vm.h" @@ -964,28 +966,20 @@ static void add_kgd_mem_to_kfd_bo_list(struct kgd_mem *mem, struct amdkfd_process_info *process_info, bool userptr) { - struct ttm_validate_buffer *entry = &mem->validate_list; - struct amdgpu_bo *bo = mem->bo; - - INIT_LIST_HEAD(&entry->head); - entry->num_shared = 1; - entry->bo = &bo->tbo; mutex_lock(&process_info->lock); if (userptr) - list_add_tail(&entry->head, &process_info->userptr_valid_list); + list_add_tail(&mem->validate_list, + &process_info->userptr_valid_list); else - list_add_tail(&entry->head, &process_info->kfd_bo_list); + list_add_tail(&mem->validate_list, &process_info->kfd_bo_list); mutex_unlock(&process_info->lock); } static void remove_kgd_mem_from_kfd_bo_list(struct kgd_mem *mem, struct amdkfd_process_info *process_info) { - struct ttm_validate_buffer *bo_list_entry; - - bo_list_entry = &mem->validate_list; mutex_lock(&process_info->lock); - list_del(&bo_list_entry->head); + list_del(&mem->validate_list); mutex_unlock(&process_info->lock); } @@ -1072,13 +1066,12 @@ out: * object can track VM updates. */ struct bo_vm_reservation_context { - struct amdgpu_bo_list_entry kfd_bo; /* BO list entry for the KFD BO */ - unsigned int n_vms; /* Number of VMs reserved */ - struct amdgpu_bo_list_entry *vm_pd; /* Array of VM BO list entries */ - struct ww_acquire_ctx ticket; /* Reservation ticket */ - struct list_head list, duplicates; /* BO lists */ - struct amdgpu_sync *sync; /* Pointer to sync object */ - bool reserved; /* Whether BOs are reserved */ + /* DRM execution context for the reservation */ + struct drm_exec exec; + /* Number of VMs reserved */ + unsigned int n_vms; + /* Pointer to sync object */ + struct amdgpu_sync *sync; }; enum bo_vm_match { @@ -1102,35 +1095,26 @@ static int reserve_bo_and_vm(struct kgd_mem *mem, WARN_ON(!vm); - ctx->reserved = false; ctx->n_vms = 1; ctx->sync = &mem->sync; - - INIT_LIST_HEAD(&ctx->list); - INIT_LIST_HEAD(&ctx->duplicates); - - ctx->vm_pd = kcalloc(ctx->n_vms, sizeof(*ctx->vm_pd), GFP_KERNEL); - if (!ctx->vm_pd) - return -ENOMEM; - - ctx->kfd_bo.priority = 0; - ctx->kfd_bo.tv.bo = &bo->tbo; - ctx->kfd_bo.tv.num_shared = 1; - list_add(&ctx->kfd_bo.tv.head, &ctx->list); - - amdgpu_vm_get_pd_bo(vm, &ctx->list, &ctx->vm_pd[0]); - - ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list, - false, &ctx->duplicates); - if (ret) { - pr_err("Failed to reserve buffers in ttm.\n"); - kfree(ctx->vm_pd); - ctx->vm_pd = NULL; - return ret; + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_until_all_locked(&ctx->exec) { + ret = amdgpu_vm_lock_pd(vm, &ctx->exec, 2); + drm_exec_retry_on_contention(&ctx->exec); + if (unlikely(ret)) + goto error; + + ret = drm_exec_lock_obj(&ctx->exec, &bo->tbo.base); + drm_exec_retry_on_contention(&ctx->exec); + if (unlikely(ret)) + goto error; } - - ctx->reserved = true; return 0; + +error: + pr_err("Failed to reserve buffers in ttm.\n"); + drm_exec_fini(&ctx->exec); + return ret; } /** @@ -1147,63 +1131,39 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem, struct amdgpu_vm *vm, enum bo_vm_match map_type, struct bo_vm_reservation_context *ctx) { - struct amdgpu_bo *bo = mem->bo; struct kfd_mem_attachment *entry; - unsigned int i; + struct amdgpu_bo *bo = mem->bo; int ret; - ctx->reserved = false; - ctx->n_vms = 0; - ctx->vm_pd = NULL; ctx->sync = &mem->sync; + drm_exec_init(&ctx->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_until_all_locked(&ctx->exec) { + ctx->n_vms = 0; + list_for_each_entry(entry, &mem->attachments, list) { + if ((vm && vm != entry->bo_va->base.vm) || + (entry->is_mapped != map_type + && map_type != BO_VM_ALL)) + continue; - INIT_LIST_HEAD(&ctx->list); - INIT_LIST_HEAD(&ctx->duplicates); - - list_for_each_entry(entry, &mem->attachments, list) { - if ((vm && vm != entry->bo_va->base.vm) || - (entry->is_mapped != map_type - && map_type != BO_VM_ALL)) - continue; - - ctx->n_vms++; - } - - if (ctx->n_vms != 0) { - ctx->vm_pd = kcalloc(ctx->n_vms, sizeof(*ctx->vm_pd), - GFP_KERNEL); - if (!ctx->vm_pd) - return -ENOMEM; - } - - ctx->kfd_bo.priority = 0; - ctx->kfd_bo.tv.bo = &bo->tbo; - ctx->kfd_bo.tv.num_shared = 1; - list_add(&ctx->kfd_bo.tv.head, &ctx->list); - - i = 0; - list_for_each_entry(entry, &mem->attachments, list) { - if ((vm && vm != entry->bo_va->base.vm) || - (entry->is_mapped != map_type - && map_type != BO_VM_ALL)) - continue; - - amdgpu_vm_get_pd_bo(entry->bo_va->base.vm, &ctx->list, - &ctx->vm_pd[i]); - i++; - } + ret = amdgpu_vm_lock_pd(entry->bo_va->base.vm, + &ctx->exec, 2); + drm_exec_retry_on_contention(&ctx->exec); + if (unlikely(ret)) + goto error; + ++ctx->n_vms; + } - ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list, - false, &ctx->duplicates); - if (ret) { - pr_err("Failed to reserve buffers in ttm.\n"); - kfree(ctx->vm_pd); - ctx->vm_pd = NULL; - return ret; + ret = drm_exec_prepare_obj(&ctx->exec, &bo->tbo.base, 1); + drm_exec_retry_on_contention(&ctx->exec); + if (unlikely(ret)) + goto error; } - - ctx->reserved = true; return 0; + +error: + pr_err("Failed to reserve buffers in ttm.\n"); + drm_exec_fini(&ctx->exec); + return ret; } /** @@ -1224,15 +1184,8 @@ static int unreserve_bo_and_vms(struct bo_vm_reservation_context *ctx, if (wait) ret = amdgpu_sync_wait(ctx->sync, intr); - if (ctx->reserved) - ttm_eu_backoff_reservation(&ctx->ticket, &ctx->list); - kfree(ctx->vm_pd); - + drm_exec_fini(&ctx->exec); ctx->sync = NULL; - - ctx->reserved = false; - ctx->vm_pd = NULL; - return ret; } @@ -1855,7 +1808,6 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( bool use_release_notifier = (mem->bo->kfd_bo == mem); struct kfd_mem_attachment *entry, *tmp; struct bo_vm_reservation_context ctx; - struct ttm_validate_buffer *bo_list_entry; unsigned int mapped_to_gpu_memory; int ret; bool is_imported = false; @@ -1883,9 +1835,8 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } /* Make sure restore workers don't access the BO any more */ - bo_list_entry = &mem->validate_list; mutex_lock(&process_info->lock); - list_del(&bo_list_entry->head); + list_del(&mem->validate_list); mutex_unlock(&process_info->lock); /* Cleanup user pages and MMU notifiers */ @@ -2452,14 +2403,14 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info, /* Move all invalidated BOs to the userptr_inval_list */ list_for_each_entry_safe(mem, tmp_mem, &process_info->userptr_valid_list, - validate_list.head) + validate_list) if (mem->invalid) - list_move_tail(&mem->validate_list.head, + list_move_tail(&mem->validate_list, &process_info->userptr_inval_list); /* Go through userptr_inval_list and update any invalid user_pages */ list_for_each_entry(mem, &process_info->userptr_inval_list, - validate_list.head) { + validate_list) { invalid = mem->invalid; if (!invalid) /* BO hasn't been invalidated since the last @@ -2539,50 +2490,41 @@ unlock_out: */ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) { - struct amdgpu_bo_list_entry *pd_bo_list_entries; - struct list_head resv_list, duplicates; - struct ww_acquire_ctx ticket; + struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_sync sync; + struct drm_exec exec; struct amdgpu_vm *peer_vm; struct kgd_mem *mem, *tmp_mem; struct amdgpu_bo *bo; - struct ttm_operation_ctx ctx = { false, false }; - int i, ret; - - pd_bo_list_entries = kcalloc(process_info->n_vms, - sizeof(struct amdgpu_bo_list_entry), - GFP_KERNEL); - if (!pd_bo_list_entries) { - pr_err("%s: Failed to allocate PD BO list entries\n", __func__); - ret = -ENOMEM; - goto out_no_mem; - } - - INIT_LIST_HEAD(&resv_list); - INIT_LIST_HEAD(&duplicates); + int ret; - /* Get all the page directory BOs that need to be reserved */ - i = 0; - list_for_each_entry(peer_vm, &process_info->vm_list_head, - vm_list_node) - amdgpu_vm_get_pd_bo(peer_vm, &resv_list, - &pd_bo_list_entries[i++]); - /* Add the userptr_inval_list entries to resv_list */ - list_for_each_entry(mem, &process_info->userptr_inval_list, - validate_list.head) { - list_add_tail(&mem->resv_list.head, &resv_list); - mem->resv_list.bo = mem->validate_list.bo; - mem->resv_list.num_shared = mem->validate_list.num_shared; - } + amdgpu_sync_create(&sync); + drm_exec_init(&exec, 0); /* Reserve all BOs and page tables for validation */ - ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates); - WARN(!list_empty(&duplicates), "Duplicates should be empty"); - if (ret) - goto out_free; + drm_exec_until_all_locked(&exec) { + /* Reserve all the page directories */ + list_for_each_entry(peer_vm, &process_info->vm_list_head, + vm_list_node) { + ret = amdgpu_vm_lock_pd(peer_vm, &exec, 2); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto unreserve_out; + } - amdgpu_sync_create(&sync); + /* Reserve the userptr_inval_list entries to resv_list */ + list_for_each_entry(mem, &process_info->userptr_inval_list, + validate_list) { + struct drm_gem_object *gobj; + + gobj = &mem->bo->tbo.base; + ret = drm_exec_prepare_obj(&exec, gobj, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto unreserve_out; + } + } ret = process_validate_vms(process_info); if (ret) @@ -2591,7 +2533,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) /* Validate BOs and update GPUVM page tables */ list_for_each_entry_safe(mem, tmp_mem, &process_info->userptr_inval_list, - validate_list.head) { + validate_list) { struct kfd_mem_attachment *attachment; bo = mem->bo; @@ -2633,12 +2575,9 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) ret = process_update_pds(process_info, &sync); unreserve_out: - ttm_eu_backoff_reservation(&ticket, &resv_list); + drm_exec_fini(&exec); amdgpu_sync_wait(&sync, false); amdgpu_sync_free(&sync); -out_free: - kfree(pd_bo_list_entries); -out_no_mem: return ret; } @@ -2654,7 +2593,7 @@ static int confirm_valid_user_pages_locked(struct amdkfd_process_info *process_i list_for_each_entry_safe(mem, tmp_mem, &process_info->userptr_inval_list, - validate_list.head) { + validate_list) { bool valid; /* keep mem without hmm range at userptr_inval_list */ @@ -2678,7 +2617,7 @@ static int confirm_valid_user_pages_locked(struct amdkfd_process_info *process_i continue; } - list_move_tail(&mem->validate_list.head, + list_move_tail(&mem->validate_list, &process_info->userptr_valid_list); } @@ -2788,50 +2727,44 @@ unlock_out: */ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) { - struct amdgpu_bo_list_entry *pd_bo_list; struct amdkfd_process_info *process_info = info; struct amdgpu_vm *peer_vm; struct kgd_mem *mem; - struct bo_vm_reservation_context ctx; struct amdgpu_amdkfd_fence *new_fence; - int ret = 0, i; struct list_head duplicate_save; struct amdgpu_sync sync_obj; unsigned long failed_size = 0; unsigned long total_size = 0; + struct drm_exec exec; + int ret; INIT_LIST_HEAD(&duplicate_save); - INIT_LIST_HEAD(&ctx.list); - INIT_LIST_HEAD(&ctx.duplicates); - - pd_bo_list = kcalloc(process_info->n_vms, - sizeof(struct amdgpu_bo_list_entry), - GFP_KERNEL); - if (!pd_bo_list) - return -ENOMEM; - i = 0; mutex_lock(&process_info->lock); - list_for_each_entry(peer_vm, &process_info->vm_list_head, - vm_list_node) - amdgpu_vm_get_pd_bo(peer_vm, &ctx.list, &pd_bo_list[i++]); - /* Reserve all BOs and page tables/directory. Add all BOs from - * kfd_bo_list to ctx.list - */ - list_for_each_entry(mem, &process_info->kfd_bo_list, - validate_list.head) { - - list_add_tail(&mem->resv_list.head, &ctx.list); - mem->resv_list.bo = mem->validate_list.bo; - mem->resv_list.num_shared = mem->validate_list.num_shared; - } + drm_exec_init(&exec, 0); + drm_exec_until_all_locked(&exec) { + list_for_each_entry(peer_vm, &process_info->vm_list_head, + vm_list_node) { + ret = amdgpu_vm_lock_pd(peer_vm, &exec, 2); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto ttm_reserve_fail; + } - ret = ttm_eu_reserve_buffers(&ctx.ticket, &ctx.list, - false, &duplicate_save); - if (ret) { - pr_debug("Memory eviction: TTM Reserve Failed. Try again\n"); - goto ttm_reserve_fail; + /* Reserve all BOs and page tables/directory. Add all BOs from + * kfd_bo_list to ctx.list + */ + list_for_each_entry(mem, &process_info->kfd_bo_list, + validate_list) { + struct drm_gem_object *gobj; + + gobj = &mem->bo->tbo.base; + ret = drm_exec_prepare_obj(&exec, gobj, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(ret)) + goto ttm_reserve_fail; + } } amdgpu_sync_create(&sync_obj); @@ -2849,7 +2782,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) /* Validate BOs and map them to GPUVM (update VM page tables). */ list_for_each_entry(mem, &process_info->kfd_bo_list, - validate_list.head) { + validate_list) { struct amdgpu_bo *bo = mem->bo; uint32_t domain = mem->domain; @@ -2925,8 +2858,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) *ef = dma_fence_get(&new_fence->base); /* Attach new eviction fence to all BOs except pinned ones */ - list_for_each_entry(mem, &process_info->kfd_bo_list, - validate_list.head) { + list_for_each_entry(mem, &process_info->kfd_bo_list, validate_list) { if (mem->bo->tbo.pin_count) continue; @@ -2945,11 +2877,10 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) } validate_map_fail: - ttm_eu_backoff_reservation(&ctx.ticket, &ctx.list); amdgpu_sync_free(&sync_obj); ttm_reserve_fail: + drm_exec_fini(&exec); mutex_unlock(&process_info->lock); - kfree(pd_bo_list); return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c index 252a876b0725..b6298e901cbd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c @@ -28,6 +28,7 @@ * Christian König <deathsimple@vodafone.de> */ +#include <linux/sort.h> #include <linux/uaccess.h> #include "amdgpu.h" @@ -50,13 +51,20 @@ static void amdgpu_bo_list_free(struct kref *ref) refcount); struct amdgpu_bo_list_entry *e; - amdgpu_bo_list_for_each_entry(e, list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + amdgpu_bo_list_for_each_entry(e, list) + amdgpu_bo_unref(&e->bo); + call_rcu(&list->rhead, amdgpu_bo_list_free_rcu); +} - amdgpu_bo_unref(&bo); - } +static int amdgpu_bo_list_entry_cmp(const void *_a, const void *_b) +{ + const struct amdgpu_bo_list_entry *a = _a, *b = _b; - call_rcu(&list->rhead, amdgpu_bo_list_free_rcu); + if (a->priority > b->priority) + return 1; + if (a->priority < b->priority) + return -1; + return 0; } int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, @@ -118,7 +126,7 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, entry->priority = min(info[i].bo_priority, AMDGPU_BO_LIST_MAX_PRIORITY); - entry->tv.bo = &bo->tbo; + entry->bo = bo; if (bo->preferred_domains == AMDGPU_GEM_DOMAIN_GDS) list->gds_obj = bo; @@ -133,6 +141,8 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, list->first_userptr = first_userptr; list->num_entries = num_entries; + sort(array, last_entry, sizeof(struct amdgpu_bo_list_entry), + amdgpu_bo_list_entry_cmp, NULL); trace_amdgpu_cs_bo_status(list->num_entries, total_size); @@ -141,16 +151,10 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp, return 0; error_free: - for (i = 0; i < last_entry; ++i) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo); - - amdgpu_bo_unref(&bo); - } - for (i = first_userptr; i < num_entries; ++i) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo); - - amdgpu_bo_unref(&bo); - } + for (i = 0; i < last_entry; ++i) + amdgpu_bo_unref(&array[i].bo); + for (i = first_userptr; i < num_entries; ++i) + amdgpu_bo_unref(&array[i].bo); kvfree(list); return r; @@ -182,41 +186,6 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id, return -ENOENT; } -void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, - struct list_head *validated) -{ - /* This is based on the bucket sort with O(n) time complexity. - * An item with priority "i" is added to bucket[i]. The lists are then - * concatenated in descending order. - */ - struct list_head bucket[AMDGPU_BO_LIST_NUM_BUCKETS]; - struct amdgpu_bo_list_entry *e; - unsigned i; - - for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++) - INIT_LIST_HEAD(&bucket[i]); - - /* Since buffers which appear sooner in the relocation list are - * likely to be used more often than buffers which appear later - * in the list, the sort mustn't change the ordering of buffers - * with the same priority, i.e. it must be stable. - */ - amdgpu_bo_list_for_each_entry(e, list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - unsigned priority = e->priority; - - if (!bo->parent) - list_add_tail(&e->tv.head, &bucket[priority]); - - e->user_pages = NULL; - e->range = NULL; - } - - /* Connect the sorted buckets in the output list. */ - for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++) - list_splice(&bucket[i], validated); -} - void amdgpu_bo_list_put(struct amdgpu_bo_list *list) { kref_put(&list->refcount, amdgpu_bo_list_free); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h index ededdc01ca28..26c01cb131f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h @@ -23,7 +23,6 @@ #ifndef __AMDGPU_BO_LIST_H__ #define __AMDGPU_BO_LIST_H__ -#include <drm/ttm/ttm_execbuf_util.h> #include <drm/amdgpu_drm.h> struct hmm_range; @@ -36,7 +35,7 @@ struct amdgpu_bo_va; struct amdgpu_fpriv; struct amdgpu_bo_list_entry { - struct ttm_validate_buffer tv; + struct amdgpu_bo *bo; struct amdgpu_bo_va *bo_va; uint32_t priority; struct page **user_pages; @@ -60,8 +59,6 @@ struct amdgpu_bo_list { int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id, struct amdgpu_bo_list **result); -void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list, - struct list_head *validated); void amdgpu_bo_list_put(struct amdgpu_bo_list *list); int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in, struct drm_amdgpu_bo_list_entry **info_param); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 040f4cb6ab2d..977e1804718d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -65,6 +65,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, } amdgpu_sync_create(&p->sync); + drm_exec_init(&p->exec, DRM_EXEC_INTERRUPTIBLE_WAIT); return 0; } @@ -125,7 +126,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, uint32_t *offset) { struct drm_gem_object *gobj; - struct amdgpu_bo *bo; unsigned long size; int r; @@ -133,18 +133,16 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, if (gobj == NULL) return -EINVAL; - bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj)); - p->uf_entry.priority = 0; - p->uf_entry.tv.bo = &bo->tbo; + p->uf_bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj)); drm_gem_object_put(gobj); - size = amdgpu_bo_size(bo); + size = amdgpu_bo_size(p->uf_bo); if (size != PAGE_SIZE || (data->offset + 8) > size) { r = -EINVAL; goto error_unref; } - if (amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) { + if (amdgpu_ttm_tt_get_usermm(p->uf_bo->tbo.ttm)) { r = -EINVAL; goto error_unref; } @@ -154,7 +152,7 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p, return 0; error_unref: - amdgpu_bo_unref(&bo); + amdgpu_bo_unref(&p->uf_bo); return r; } @@ -311,7 +309,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, goto free_all_kdata; } - if (p->uf_entry.tv.bo) + if (p->uf_bo) p->gang_leader->uf_addr = uf_offset; kvfree(chunk_array); @@ -356,7 +354,7 @@ static int amdgpu_cs_p2_ib(struct amdgpu_cs_parser *p, ib = &job->ibs[job->num_ibs++]; /* MM engine doesn't support user fences */ - if (p->uf_entry.tv.bo && ring->funcs->no_user_fence) + if (p->uf_bo && ring->funcs->no_user_fence) return -EINVAL; if (chunk_ib->ip_type == AMDGPU_HW_IP_GFX && @@ -841,55 +839,18 @@ retry: return r; } -static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p, - struct list_head *validated) -{ - struct ttm_operation_ctx ctx = { true, false }; - struct amdgpu_bo_list_entry *lobj; - int r; - - list_for_each_entry(lobj, validated, tv.head) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo); - struct mm_struct *usermm; - - usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm); - if (usermm && usermm != current->mm) - return -EPERM; - - if (amdgpu_ttm_tt_is_userptr(bo->tbo.ttm) && - lobj->user_invalidated && lobj->user_pages) { - amdgpu_bo_placement_from_domain(bo, - AMDGPU_GEM_DOMAIN_CPU); - r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); - if (r) - return r; - - amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm, - lobj->user_pages); - } - - r = amdgpu_cs_bo_validate(p, bo); - if (r) - return r; - - kvfree(lobj->user_pages); - lobj->user_pages = NULL; - } - return 0; -} - static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + struct ttm_operation_ctx ctx = { true, false }; struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; - struct list_head duplicates; + struct drm_gem_object *obj; + unsigned long index; unsigned int i; int r; - INIT_LIST_HEAD(&p->validated); - /* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */ if (cs->in.bo_list_handle) { if (p->bo_list) @@ -909,29 +870,13 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, mutex_lock(&p->bo_list->bo_list_mutex); - /* One for TTM and one for each CS job */ - amdgpu_bo_list_for_each_entry(e, p->bo_list) - e->tv.num_shared = 1 + p->gang_size; - p->uf_entry.tv.num_shared = 1 + p->gang_size; - - amdgpu_bo_list_get_list(p->bo_list, &p->validated); - - INIT_LIST_HEAD(&duplicates); - amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd); - - /* Two for VM updates, one for TTM and one for each CS job */ - p->vm_pd.tv.num_shared = 3 + p->gang_size; - - if (p->uf_entry.tv.bo && !ttm_to_amdgpu_bo(p->uf_entry.tv.bo)->parent) - list_add(&p->uf_entry.tv.head, &p->validated); - /* Get userptr backing pages. If pages are updated after registered * in amdgpu_gem_userptr_ioctl(), amdgpu_cs_list_validate() will do * amdgpu_ttm_backend_bind() to flush and invalidate new pages */ amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); bool userpage_invalidated = false; + struct amdgpu_bo *bo = e->bo; int i; e->user_pages = kvmalloc_array(bo->tbo.ttm->num_pages, @@ -959,18 +904,56 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, e->user_invalidated = userpage_invalidated; } - r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true, - &duplicates); - if (unlikely(r != 0)) { - if (r != -ERESTARTSYS) - DRM_ERROR("ttm_eu_reserve_buffers failed.\n"); - goto out_free_user_pages; + drm_exec_until_all_locked(&p->exec) { + r = amdgpu_vm_lock_pd(&fpriv->vm, &p->exec, 1 + p->gang_size); + drm_exec_retry_on_contention(&p->exec); + if (unlikely(r)) + goto out_free_user_pages; + + amdgpu_bo_list_for_each_entry(e, p->bo_list) { + /* One fence for TTM and one for each CS job */ + r = drm_exec_prepare_obj(&p->exec, &e->bo->tbo.base, + 1 + p->gang_size); + drm_exec_retry_on_contention(&p->exec); + if (unlikely(r)) + goto out_free_user_pages; + + e->bo_va = amdgpu_vm_bo_find(vm, e->bo); + } + + if (p->uf_bo) { + r = drm_exec_prepare_obj(&p->exec, &p->uf_bo->tbo.base, + 1 + p->gang_size); + drm_exec_retry_on_contention(&p->exec); + if (unlikely(r)) + goto out_free_user_pages; + } } - amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { + struct mm_struct *usermm; - e->bo_va = amdgpu_vm_bo_find(vm, bo); + usermm = amdgpu_ttm_tt_get_usermm(e->bo->tbo.ttm); + if (usermm && usermm != current->mm) { + r = -EPERM; + goto out_free_user_pages; + } + + if (amdgpu_ttm_tt_is_userptr(e->bo->tbo.ttm) && + e->user_invalidated && e->user_pages) { + amdgpu_bo_placement_from_domain(e->bo, + AMDGPU_GEM_DOMAIN_CPU); + r = ttm_bo_validate(&e->bo->tbo, &e->bo->placement, + &ctx); + if (r) + goto out_free_user_pages; + + amdgpu_ttm_tt_set_user_pages(e->bo->tbo.ttm, + e->user_pages); + } + + kvfree(e->user_pages); + e->user_pages = NULL; } amdgpu_cs_get_threshold_for_moves(p->adev, &p->bytes_moved_threshold, @@ -982,25 +965,21 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, amdgpu_cs_bo_validate, p); if (r) { DRM_ERROR("amdgpu_vm_validate_pt_bos() failed.\n"); - goto error_validate; + goto out_free_user_pages; } - r = amdgpu_cs_list_validate(p, &duplicates); - if (r) - goto error_validate; - - r = amdgpu_cs_list_validate(p, &p->validated); - if (r) - goto error_validate; - - if (p->uf_entry.tv.bo) { - struct amdgpu_bo *uf = ttm_to_amdgpu_bo(p->uf_entry.tv.bo); + drm_exec_for_each_locked_object(&p->exec, index, obj) { + r = amdgpu_cs_bo_validate(p, gem_to_amdgpu_bo(obj)); + if (unlikely(r)) + goto out_free_user_pages; + } - r = amdgpu_ttm_alloc_gart(&uf->tbo); - if (r) - goto error_validate; + if (p->uf_bo) { + r = amdgpu_ttm_alloc_gart(&p->uf_bo->tbo); + if (unlikely(r)) + goto out_free_user_pages; - p->gang_leader->uf_addr += amdgpu_bo_gpu_offset(uf); + p->gang_leader->uf_addr += amdgpu_bo_gpu_offset(p->uf_bo); } amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved, @@ -1012,12 +991,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p, p->bo_list->oa_obj); return 0; -error_validate: - ttm_eu_backoff_reservation(&p->ticket, &p->validated); - out_free_user_pages: amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + struct amdgpu_bo *bo = e->bo; if (!e->user_pages) continue; @@ -1123,7 +1099,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) struct amdgpu_vm *vm = &fpriv->vm; struct amdgpu_bo_list_entry *e; struct amdgpu_bo_va *bo_va; - struct amdgpu_bo *bo; unsigned int i; int r; @@ -1152,11 +1127,6 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) } amdgpu_bo_list_for_each_entry(e, p->bo_list) { - /* ignore duplicates */ - bo = ttm_to_amdgpu_bo(e->tv.bo); - if (!bo) - continue; - bo_va = e->bo_va; if (bo_va == NULL) continue; @@ -1194,7 +1164,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (amdgpu_vm_debug) { /* Invalidate all BOs to test for userspace bugs */ amdgpu_bo_list_for_each_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + struct amdgpu_bo *bo = e->bo; /* ignore duplicates */ if (!bo) @@ -1211,8 +1181,9 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; struct drm_gpu_scheduler *sched; - struct amdgpu_bo_list_entry *e; + struct drm_gem_object *obj; struct dma_fence *fence; + unsigned long index; unsigned int i; int r; @@ -1223,8 +1194,9 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) return r; } - list_for_each_entry(e, &p->validated, tv.head) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); + drm_exec_for_each_locked_object(&p->exec, index, obj) { + struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + struct dma_resv *resv = bo->tbo.base.resv; enum amdgpu_sync_mode sync_mode; @@ -1288,6 +1260,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, struct amdgpu_fpriv *fpriv = p->filp->driver_priv; struct amdgpu_job *leader = p->gang_leader; struct amdgpu_bo_list_entry *e; + struct drm_gem_object *gobj; + unsigned long index; unsigned int i; uint64_t seq; int r; @@ -1326,9 +1300,8 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, */ r = 0; amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { - struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); - - r |= !amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm, e->range); + r |= !amdgpu_ttm_tt_get_user_pages_done(e->bo->tbo.ttm, + e->range); e->range = NULL; } if (r) { @@ -1338,20 +1311,22 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, } p->fence = dma_fence_get(&leader->base.s_fence->finished); - list_for_each_entry(e, &p->validated, tv.head) { + drm_exec_for_each_locked_object(&p->exec, index, gobj) { + + ttm_bo_move_to_lru_tail_unlocked(&gem_to_amdgpu_bo(gobj)->tbo); /* Everybody except for the gang leader uses READ */ for (i = 0; i < p->gang_size; ++i) { if (p->jobs[i] == leader) continue; - dma_resv_add_fence(e->tv.bo->base.resv, + dma_resv_add_fence(gobj->resv, &p->jobs[i]->base.s_fence->finished, DMA_RESV_USAGE_READ); } - /* The gang leader is remembered as writer */ - e->tv.num_shared = 0; + /* The gang leader as remembered as writer */ + dma_resv_add_fence(gobj->resv, p->fence, DMA_RESV_USAGE_WRITE); } seq = amdgpu_ctx_add_fence(p->ctx, p->entities[p->gang_leader_idx], @@ -1367,7 +1342,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, cs->out.handle = seq; leader->uf_sequence = seq; - amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket); + amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->exec.ticket); for (i = 0; i < p->gang_size; ++i) { amdgpu_job_free_resources(p->jobs[i]); trace_amdgpu_cs_ioctl(p->jobs[i]); @@ -1376,7 +1351,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, } amdgpu_vm_move_to_lru_tail(p->adev, &fpriv->vm); - ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence); mutex_unlock(&p->adev->notifier_lock); mutex_unlock(&p->bo_list->bo_list_mutex); @@ -1389,6 +1363,8 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) unsigned int i; amdgpu_sync_free(&parser->sync); + drm_exec_fini(&parser->exec); + for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); kfree(parser->post_deps[i].chain); @@ -1409,11 +1385,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) if (parser->jobs[i]) amdgpu_job_free(parser->jobs[i]); } - if (parser->uf_entry.tv.bo) { - struct amdgpu_bo *uf = ttm_to_amdgpu_bo(parser->uf_entry.tv.bo); - - amdgpu_bo_unref(&uf); - } + amdgpu_bo_unref(&parser->uf_bo); } int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) @@ -1474,7 +1446,6 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return 0; error_backoff: - ttm_eu_backoff_reservation(&parser.ticket, &parser.validated); mutex_unlock(&parser.bo_list->bo_list_mutex); error_fini: @@ -1809,7 +1780,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser, *map = mapping; /* Double check that the BO is reserved by this CS */ - if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->ticket) + if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket) return -EINVAL; if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h index fb3e3d56d427..39c33ad100cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h @@ -24,6 +24,7 @@ #define __AMDGPU_CS_H__ #include <linux/ww_mutex.h> +#include <drm/drm_exec.h> #include "amdgpu_job.h" #include "amdgpu_bo_list.h" @@ -62,11 +63,9 @@ struct amdgpu_cs_parser { struct amdgpu_job *gang_leader; /* buffer objects */ - struct ww_acquire_ctx ticket; + struct drm_exec exec; struct amdgpu_bo_list *bo_list; struct amdgpu_mn *mn; - struct amdgpu_bo_list_entry vm_pd; - struct list_head validated; struct dma_fence *fence; uint64_t bytes_moved_threshold; uint64_t bytes_moved_vis_threshold; @@ -74,7 +73,7 @@ struct amdgpu_cs_parser { uint64_t bytes_moved_vis; /* user fence */ - struct amdgpu_bo_list_entry uf_entry; + struct amdgpu_bo *uf_bo; unsigned num_post_deps; struct amdgpu_cs_post_dep *post_deps; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c index 23d054526e7c..720011019741 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c @@ -22,6 +22,8 @@ * * Author: Monk.liu@amd.com */ +#include <drm/drm_exec.h> + #include "amdgpu.h" uint64_t amdgpu_csa_vaddr(struct amdgpu_device *adev) @@ -65,31 +67,25 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_bo *bo, struct amdgpu_bo_va **bo_va, uint64_t csa_addr, uint32_t size) { - struct ww_acquire_ctx ticket; - struct list_head list; - struct amdgpu_bo_list_entry pd; - struct ttm_validate_buffer csa_tv; + struct drm_exec exec; int r; - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&csa_tv.head); - csa_tv.bo = &bo->tbo; - csa_tv.num_shared = 1; - - list_add(&csa_tv.head, &list); - amdgpu_vm_get_pd_bo(vm, &list, &pd); - - r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL); - if (r) { - DRM_ERROR("failed to reserve CSA,PD BOs: err=%d\n", r); - return r; + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_until_all_locked(&exec) { + r = amdgpu_vm_lock_pd(vm, &exec, 0); + if (likely(!r)) + r = drm_exec_lock_obj(&exec, &bo->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) { + DRM_ERROR("failed to reserve CSA,PD BOs: err=%d\n", r); + goto error; + } } *bo_va = amdgpu_vm_bo_add(adev, vm, bo); if (!*bo_va) { - ttm_eu_backoff_reservation(&ticket, &list); - DRM_ERROR("failed to create bo_va for static CSA\n"); - return -ENOMEM; + r = -ENOMEM; + goto error; } r = amdgpu_vm_bo_map(adev, *bo_va, csa_addr, 0, size, @@ -99,48 +95,42 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) { DRM_ERROR("failed to do bo_map on static CSA, err=%d\n", r); amdgpu_vm_bo_del(adev, *bo_va); - ttm_eu_backoff_reservation(&ticket, &list); - return r; + goto error; } - ttm_eu_backoff_reservation(&ticket, &list); - return 0; +error: + drm_exec_fini(&exec); + return r; } int amdgpu_unmap_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_bo *bo, struct amdgpu_bo_va *bo_va, uint64_t csa_addr) { - struct ww_acquire_ctx ticket; - struct list_head list; - struct amdgpu_bo_list_entry pd; - struct ttm_validate_buffer csa_tv; + struct drm_exec exec; int r; - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&csa_tv.head); - csa_tv.bo = &bo->tbo; - csa_tv.num_shared = 1; - - list_add(&csa_tv.head, &list); - amdgpu_vm_get_pd_bo(vm, &list, &pd); - - r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL); - if (r) { - DRM_ERROR("failed to reserve CSA,PD BOs: err=%d\n", r); - return r; + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT); + drm_exec_until_all_locked(&exec) { + r = amdgpu_vm_lock_pd(vm, &exec, 0); + if (likely(!r)) + r = drm_exec_lock_obj(&exec, &bo->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) { + DRM_ERROR("failed to reserve CSA,PD BOs: err=%d\n", r); + goto error; + } } r = amdgpu_vm_bo_unmap(adev, bo_va, csa_addr); if (r) { DRM_ERROR("failed to do bo_unmap on static CSA, err=%d\n", r); - ttm_eu_backoff_reservation(&ticket, &list); - return r; + goto error; } amdgpu_vm_bo_del(adev, bo_va); - ttm_eu_backoff_reservation(&ticket, &list); - - return 0; +error: + drm_exec_fini(&exec); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 144fcb326668..d6439d56dcd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2847,10 +2847,7 @@ static const struct drm_driver amdgpu_kms_driver = { .show_fdinfo = amdgpu_show_fdinfo, #endif - .prime_handle_to_fd = drm_gem_prime_handle_to_fd, - .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_import = amdgpu_gem_prime_import, - .gem_prime_mmap = drm_gem_prime_mmap, .name = DRIVER_NAME, .desc = DRIVER_DESC, @@ -2874,10 +2871,7 @@ const struct drm_driver amdgpu_partition_driver = { .fops = &amdgpu_driver_kms_fops, .release = &amdgpu_driver_release_kms, - .prime_handle_to_fd = drm_gem_prime_handle_to_fd, - .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_import = amdgpu_gem_prime_import, - .gem_prime_mmap = drm_gem_prime_mmap, .name = DRIVER_NAME, .desc = DRIVER_DESC, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 992dfd3de49c..693b1fd1191a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -33,6 +33,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> +#include <drm/drm_exec.h> #include <drm/drm_gem_ttm_helper.h> #include <drm/ttm/ttm_tt.h> @@ -197,29 +198,24 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, struct amdgpu_fpriv *fpriv = file_priv->driver_priv; struct amdgpu_vm *vm = &fpriv->vm; - struct amdgpu_bo_list_entry vm_pd; - struct list_head list, duplicates; struct dma_fence *fence = NULL; - struct ttm_validate_buffer tv; - struct ww_acquire_ctx ticket; struct amdgpu_bo_va *bo_va; + struct drm_exec exec; long r; - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&duplicates); - - tv.bo = &bo->tbo; - tv.num_shared = 2; - list_add(&tv.head, &list); - - amdgpu_vm_get_pd_bo(vm, &list, &vm_pd); - - r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates); - if (r) { - dev_err(adev->dev, "leaking bo va because we fail to reserve bo (%ld)\n", - r); - return; + drm_exec_init(&exec, DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_until_all_locked(&exec) { + r = drm_exec_prepare_obj(&exec, &bo->tbo.base, 1); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto out_unlock; + + r = amdgpu_vm_lock_pd(vm, &exec, 0); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto out_unlock; } + bo_va = amdgpu_vm_bo_find(vm, bo); if (!bo_va || --bo_va->ref_count) goto out_unlock; @@ -229,6 +225,9 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, goto out_unlock; r = amdgpu_vm_clear_freed(adev, vm, &fence); + if (unlikely(r < 0)) + dev_err(adev->dev, "failed to clear page " + "tables on GEM object close (%ld)\n", r); if (r || !fence) goto out_unlock; @@ -236,10 +235,9 @@ static void amdgpu_gem_object_close(struct drm_gem_object *obj, dma_fence_put(fence); out_unlock: - if (unlikely(r < 0)) - dev_err(adev->dev, "failed to clear page tables on GEM object close (%ld)\n", - r); - ttm_eu_backoff_reservation(&ticket, &list); + if (r) + dev_err(adev->dev, "leaking bo va (%ld)\n", r); + drm_exec_fini(&exec); } static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) @@ -675,10 +673,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct amdgpu_fpriv *fpriv = filp->driver_priv; struct amdgpu_bo *abo; struct amdgpu_bo_va *bo_va; - struct amdgpu_bo_list_entry vm_pd; - struct ttm_validate_buffer tv; - struct ww_acquire_ctx ticket; - struct list_head list, duplicates; + struct drm_exec exec; uint64_t va_flags; uint64_t vm_size; int r = 0; @@ -728,36 +723,38 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, return -EINVAL; } - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&duplicates); if ((args->operation != AMDGPU_VA_OP_CLEAR) && !(args->flags & AMDGPU_VM_PAGE_PRT)) { gobj = drm_gem_object_lookup(filp, args->handle); if (gobj == NULL) return -ENOENT; abo = gem_to_amdgpu_bo(gobj); - tv.bo = &abo->tbo; - if (abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) - tv.num_shared = 1; - else - tv.num_shared = 0; - list_add(&tv.head, &list); } else { gobj = NULL; abo = NULL; } - amdgpu_vm_get_pd_bo(&fpriv->vm, &list, &vm_pd); + drm_exec_init(&exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_until_all_locked(&exec) { + if (gobj) { + r = drm_exec_lock_obj(&exec, gobj); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto error; + } - r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates); - if (r) - goto error_unref; + r = amdgpu_vm_lock_pd(&fpriv->vm, &exec, 2); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto error; + } if (abo) { bo_va = amdgpu_vm_bo_find(&fpriv->vm, abo); if (!bo_va) { r = -ENOENT; - goto error_backoff; + goto error; } } else if (args->operation != AMDGPU_VA_OP_CLEAR) { bo_va = fpriv->prt_va; @@ -794,10 +791,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va, args->operation); -error_backoff: - ttm_eu_backoff_reservation(&ticket, &list); - -error_unref: +error: + drm_exec_fini(&exec); drm_gem_object_put(gobj); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 72ab6a838bb6..37f15abf7543 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -22,6 +22,7 @@ */ #include <linux/firmware.h> +#include <drm/drm_exec.h> #include "amdgpu_mes.h" #include "amdgpu.h" @@ -1170,34 +1171,31 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev, struct amdgpu_mes_ctx_data *ctx_data) { struct amdgpu_bo_va *bo_va; - struct ww_acquire_ctx ticket; - struct list_head list; - struct amdgpu_bo_list_entry pd; - struct ttm_validate_buffer csa_tv; struct amdgpu_sync sync; + struct drm_exec exec; int r; amdgpu_sync_create(&sync); - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&csa_tv.head); - csa_tv.bo = &ctx_data->meta_data_obj->tbo; - csa_tv.num_shared = 1; - - list_add(&csa_tv.head, &list); - amdgpu_vm_get_pd_bo(vm, &list, &pd); - - r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL); - if (r) { - DRM_ERROR("failed to reserve meta data BO: err=%d\n", r); - return r; + drm_exec_init(&exec, 0); + drm_exec_until_all_locked(&exec) { + r = drm_exec_lock_obj(&exec, + &ctx_data->meta_data_obj->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto error_fini_exec; + + r = amdgpu_vm_lock_pd(vm, &exec, 0); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto error_fini_exec; } bo_va = amdgpu_vm_bo_add(adev, vm, ctx_data->meta_data_obj); if (!bo_va) { - ttm_eu_backoff_reservation(&ticket, &list); DRM_ERROR("failed to create bo_va for meta data BO\n"); - return -ENOMEM; + r = -ENOMEM; + goto error_fini_exec; } r = amdgpu_vm_bo_map(adev, bo_va, ctx_data->meta_data_gpu_addr, 0, @@ -1207,33 +1205,35 @@ int amdgpu_mes_ctx_map_meta_data(struct amdgpu_device *adev, if (r) { DRM_ERROR("failed to do bo_map on meta data, err=%d\n", r); - goto error; + goto error_del_bo_va; } r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) { DRM_ERROR("failed to do vm_bo_update on meta data\n"); - goto error; + goto error_del_bo_va; } amdgpu_sync_fence(&sync, bo_va->last_pt_update); r = amdgpu_vm_update_pdes(adev, vm, false); if (r) { DRM_ERROR("failed to update pdes on meta data\n"); - goto error; + goto error_del_bo_va; } amdgpu_sync_fence(&sync, vm->last_update); amdgpu_sync_wait(&sync, false); - ttm_eu_backoff_reservation(&ticket, &list); + drm_exec_fini(&exec); amdgpu_sync_free(&sync); ctx_data->meta_data_va = bo_va; return 0; -error: +error_del_bo_va: amdgpu_vm_bo_del(adev, bo_va); - ttm_eu_backoff_reservation(&ticket, &list); + +error_fini_exec: + drm_exec_fini(&exec); amdgpu_sync_free(&sync); return r; } @@ -1244,34 +1244,30 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va = ctx_data->meta_data_va; struct amdgpu_bo *bo = ctx_data->meta_data_obj; struct amdgpu_vm *vm = bo_va->base.vm; - struct amdgpu_bo_list_entry vm_pd; - struct list_head list, duplicates; - struct dma_fence *fence = NULL; - struct ttm_validate_buffer tv; - struct ww_acquire_ctx ticket; - long r = 0; - - INIT_LIST_HEAD(&list); - INIT_LIST_HEAD(&duplicates); - - tv.bo = &bo->tbo; - tv.num_shared = 2; - list_add(&tv.head, &list); - - amdgpu_vm_get_pd_bo(vm, &list, &vm_pd); - - r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates); - if (r) { - dev_err(adev->dev, "leaking bo va because " - "we fail to reserve bo (%ld)\n", r); - return r; + struct dma_fence *fence; + struct drm_exec exec; + long r; + + drm_exec_init(&exec, 0); + drm_exec_until_all_locked(&exec) { + r = drm_exec_lock_obj(&exec, + &ctx_data->meta_data_obj->tbo.base); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto out_unlock; + + r = amdgpu_vm_lock_pd(vm, &exec, 0); + drm_exec_retry_on_contention(&exec); + if (unlikely(r)) + goto out_unlock; } amdgpu_vm_bo_del(adev, bo_va); if (!amdgpu_vm_ready(vm)) goto out_unlock; - r = dma_resv_get_singleton(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, &fence); + r = dma_resv_get_singleton(bo->tbo.base.resv, DMA_RESV_USAGE_BOOKKEEP, + &fence); if (r) goto out_unlock; if (fence) { @@ -1290,7 +1286,7 @@ int amdgpu_mes_ctx_unmap_meta_data(struct amdgpu_device *adev, out_unlock: if (unlikely(r < 0)) dev_err(adev->dev, "failed to clear page tables (%ld)\n", r); - ttm_eu_backoff_reservation(&ticket, &list); + drm_exec_fini(&exec); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 74380b21e7a5..f5daadcec865 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -34,6 +34,7 @@ #include <drm/amdgpu_drm.h> #include <drm/drm_drv.h> #include <drm/ttm/ttm_tt.h> +#include <drm/drm_exec.h> #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_amdkfd.h" @@ -339,25 +340,20 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, } /** - * amdgpu_vm_get_pd_bo - add the VM PD to a validation list + * amdgpu_vm_lock_pd - lock PD in drm_exec * * @vm: vm providing the BOs - * @validated: head of validation list - * @entry: entry to add + * @exec: drm execution context + * @num_fences: number of extra fences to reserve * - * Add the page directory to the list of BOs to - * validate for command submission. + * Lock the VM root PD in the DRM execution context. */ -void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, - struct list_head *validated, - struct amdgpu_bo_list_entry *entry) +int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec, + unsigned int num_fences) { - entry->priority = 0; - entry->tv.bo = &vm->root.bo->tbo; - /* Two for VM updates, one for TTM and one for the CS job */ - entry->tv.num_shared = 4; - entry->user_pages = NULL; - list_add(&entry->tv.head, validated); + /* We need at least two fences for the VM PD/PT updates */ + return drm_exec_prepare_obj(exec, &vm->root.bo->tbo.base, + 2 + num_fences); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index bca258c38919..204ab13184ed 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -36,6 +36,8 @@ #include "amdgpu_ring.h" #include "amdgpu_ids.h" +struct drm_exec; + struct amdgpu_bo_va; struct amdgpu_job; struct amdgpu_bo_list_entry; @@ -402,9 +404,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, int32_t xcp int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); -void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, - struct list_head *validated, - struct amdgpu_bo_list_entry *entry); +int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec, + unsigned int num_fences); bool amdgpu_vm_ready(struct amdgpu_vm *vm); uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm); int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, |