#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"
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);
}
* 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 {
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;
}
/**
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;
}
/**
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;
}
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;
}
/* 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 */
/* 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
*/
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)
/* 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;
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;
}
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 */
continue;
}
- list_move_tail(&mem->validate_list.head,
+ list_move_tail(&mem->validate_list,
&process_info->userptr_valid_list);
}
*/
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);
/* 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;
*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;
}
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;
}
#include <linux/types.h>
#include <linux/sched/task.h>
#include <drm/ttm/ttm_tt.h>
+#include <drm/drm_exec.h>
+
#include "amdgpu_sync.h"
#include "amdgpu_object.h"
#include "amdgpu_vm.h"
struct svm_range *prange;
bool intr;
DECLARE_BITMAP(bitmap, MAX_GPU_INSTANCE);
- struct ttm_validate_buffer tv[MAX_GPU_INSTANCE];
- struct list_head validate_list;
- struct ww_acquire_ctx ticket;
+ struct drm_exec exec;
};
-static int svm_range_reserve_bos(struct svm_validate_context *ctx)
+static int svm_range_reserve_bos(struct svm_validate_context *ctx, bool intr)
{
struct kfd_process_device *pdd;
struct amdgpu_vm *vm;
uint32_t gpuidx;
int r;
- INIT_LIST_HEAD(&ctx->validate_list);
- for_each_set_bit(gpuidx, ctx->bitmap, MAX_GPU_INSTANCE) {
- pdd = kfd_process_device_from_gpuidx(ctx->process, gpuidx);
- if (!pdd) {
- pr_debug("failed to find device idx %d\n", gpuidx);
- return -EINVAL;
- }
- vm = drm_priv_to_vm(pdd->drm_priv);
-
- ctx->tv[gpuidx].bo = &vm->root.bo->tbo;
- ctx->tv[gpuidx].num_shared = 4;
- list_add(&ctx->tv[gpuidx].head, &ctx->validate_list);
- }
+ drm_exec_init(&ctx->exec, intr ? DRM_EXEC_INTERRUPTIBLE_WAIT: 0);
+ drm_exec_until_all_locked(&ctx->exec) {
+ for_each_set_bit(gpuidx, ctx->bitmap, MAX_GPU_INSTANCE) {
+ pdd = kfd_process_device_from_gpuidx(ctx->process, gpuidx);
+ if (!pdd) {
+ pr_debug("failed to find device idx %d\n", gpuidx);
+ r = -EINVAL;
+ goto unreserve_out;
+ }
+ vm = drm_priv_to_vm(pdd->drm_priv);
- r = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->validate_list,
- ctx->intr, NULL);
- if (r) {
- pr_debug("failed %d to reserve bo\n", r);
- return r;
+ r = amdgpu_vm_lock_pd(vm, &ctx->exec, 2);
+ drm_exec_retry_on_contention(&ctx->exec);
+ if (unlikely(r)) {
+ pr_debug("failed %d to reserve bo\n", r);
+ goto unreserve_out;
+ }
+ }
}
for_each_set_bit(gpuidx, ctx->bitmap, MAX_GPU_INSTANCE) {
return 0;
unreserve_out:
- ttm_eu_backoff_reservation(&ctx->ticket, &ctx->validate_list);
+ drm_exec_fini(&ctx->exec);
return r;
}
static void svm_range_unreserve_bos(struct svm_validate_context *ctx)
{
- ttm_eu_backoff_reservation(&ctx->ticket, &ctx->validate_list);
+ drm_exec_fini(&ctx->exec);
}
static void *kfd_svm_page_owner(struct kfd_process *p, int32_t gpuidx)
goto free_ctx;
}
- svm_range_reserve_bos(ctx);
+ svm_range_reserve_bos(ctx, intr);
p = container_of(prange->svms, struct kfd_process, svms);
owner = kfd_svm_page_owner(p, find_first_bit(ctx->bitmap,
projects / linux-2.6-microblaze.git / commitdiff