On 2022-06-13 11:20, Graham Sider
wrote:
Starting with GFX11, MES requires wptr BOs to be GTT allocated/mapped to GART for usermode queues in order to support oversubscription. In the case that work is submitted to an unmapped queue, MES must have a GART wptr address to determine whether the queue should be mapped. This change is accompanied with changes in MES and is applicable for MES_VERSION >= 3. v2: - Update MES_VERSION check from 2 to 3. v3: - Use amdgpu_vm_bo_lookup_mapping for wptr_bo mapping lookup - Move wptr_bo refcount increment to amdgpu_amdkfd_map_gtt_bo_to_gart - Remove list_del_init from amdgpu_amdkfd_map_gtt_bo_to_gart - Cleanup/fix create_queue wptr_bo error handling
Two nit-pick below, with those fixed, this patch is
Reviewed-by: Philip Yang<Philip.Yang@xxxxxxx>
pinned bo should keep in validate_list as PDB/PTB may move and update, please remove list_del_init here.Signed-off-by: Graham Sider <Graham.Sider@xxxxxxx> --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 49 +++++++++++++++++++ drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 37 +++++++++++++- .../drm/amd/amdkfd/kfd_device_queue_manager.c | 9 +++- .../gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 2 + drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 3 ++ .../amd/amdkfd/kfd_process_queue_manager.c | 17 +++++-- 7 files changed, 110 insertions(+), 8 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 429b16ba10bf..dba26d1e3be9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -301,6 +301,7 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct amdgpu_device *adev, struct kgd_mem *mem, void **kptr, uint64_t *size); void amdgpu_amdkfd_gpuvm_unmap_gtt_bo_from_kernel(struct amdgpu_device *adev, struct kgd_mem *mem); +int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo); int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info, struct dma_fence **ef); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index efab923056f4..888d08128a94 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2030,6 +2030,55 @@ int amdgpu_amdkfd_gpuvm_sync_memory( return ret; } +/** + * amdgpu_amdkfd_map_gtt_bo_to_gart - Map BO to GART and increment reference count + * @adev: Device to which allocated BO belongs + * @bo: Buffer object to be mapped + * + * Before return, bo reference count is incremented. To release the reference and unpin/ + * unmap the BO, call amdgpu_amdkfd_free_gtt_mem. + */ +int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_bo *bo) +{ + int ret; + + ret = amdgpu_bo_reserve(bo, true); + if (ret) { + pr_err("Failed to reserve bo. ret %d\n", ret); + goto err_reserve_bo_failed; + } + + ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); + if (ret) { + pr_err("Failed to pin bo. ret %d\n", ret); + goto err_pin_bo_failed; + } + + ret = amdgpu_ttm_alloc_gart(&bo->tbo); + if (ret) { + pr_err("Failed to bind bo to GART. ret %d\n", ret); + goto err_map_bo_gart_failed; + } + + amdgpu_amdkfd_remove_eviction_fence( + bo, bo->kfd_bo->process_info->eviction_fence); + list_del_init(&bo->kfd_bo->validate_list.head);
+
+ amdgpu_bo_unreserve(bo);
+
+ bo = amdgpu_bo_ref(bo);
+
+ return 0;
+
+err_map_bo_gart_failed:
+ amdgpu_bo_unpin(bo);
+err_pin_bo_failed:
+ amdgpu_bo_unreserve(bo);
+err_reserve_bo_failed:
+
+ return ret;
+}
+
int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct amdgpu_device *adev,
struct kgd_mem *mem, void **kptr, uint64_t *size)
{
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index e9766e165c38..1789ed8b79f5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -289,6 +289,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
struct kfd_process_device *pdd;
struct queue_properties q_properties;
uint32_t doorbell_offset_in_process = 0;
+ struct amdgpu_bo *wptr_bo = NULL;
memset(&q_properties, 0, sizeof(struct queue_properties));
@@ -316,12 +317,41 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
goto err_bind_process;
}
+ /* Starting with GFX11, wptr BOs must be mapped to GART for MES to determine work
+ * on unmapped queues for usermode queue oversubscription (no aggregated doorbell)
+ */
+ if (dev->shared_resources.enable_mes && (dev->adev->mes.sched_version & 0xff) >= 3) {
Should we check ip version for GFX11 only? Because GFX10 set
enable_mes, and may set adev->mes.sched_version later as well.
Regards,
Philip
+ struct amdgpu_bo_va_mapping *wptr_mapping;
+ struct amdgpu_vm *wptr_vm;
+
+ wptr_vm = drm_priv_to_vm(pdd->drm_priv);
+ err = amdgpu_bo_reserve(wptr_vm->root.bo, false);
+ if (err)
+ goto err_wptr_map_gart;
+
+ wptr_mapping = amdgpu_vm_bo_lookup_mapping(
+ wptr_vm, args->write_pointer_address >> PAGE_SHIFT);
+ amdgpu_bo_unreserve(wptr_vm->root.bo);
+ if (!wptr_mapping) {
+ pr_err("Failed to lookup wptr bo\n");
+ err = -EINVAL;
+ goto err_wptr_map_gart;
+ }
+
+ wptr_bo = wptr_mapping->bo_va->base.bo;
+ err = amdgpu_amdkfd_map_gtt_bo_to_gart(dev->adev, wptr_bo);
+ if (err) {
+ pr_err("Failed to map wptr bo to GART\n");
+ goto err_wptr_map_gart;
+ }
+ }
+
pr_debug("Creating queue for PASID 0x%x on gpu 0x%x\n",
p->pasid,
dev->id);
- err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, NULL, NULL, NULL,
- &doorbell_offset_in_process);
+ err = pqm_create_queue(&p->pqm, dev, filep, &q_properties, &queue_id, wptr_bo,
+ NULL, NULL, NULL, &doorbell_offset_in_process);
if (err != 0)
goto err_create_queue;
@@ -354,6 +384,9 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
return 0;
err_create_queue:
+ if (wptr_bo)
+ amdgpu_amdkfd_free_gtt_mem(dev->adev, wptr_bo);
+err_wptr_map_gart:
err_bind_process:
err_pdd:
mutex_unlock(&p->mutex);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index b39d89c52887..d8de2fbdfc7d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -208,6 +208,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
struct kfd_process_device *pdd = qpd_to_pdd(qpd);
struct mes_add_queue_input queue_input;
int r, queue_type;
+ uint64_t wptr_addr_off;
if (dqm->is_hws_hang)
return -EIO;
@@ -227,7 +228,13 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
AMDGPU_MES_PRIORITY_LEVEL_NORMAL;
queue_input.doorbell_offset = q->properties.doorbell_off;
queue_input.mqd_addr = q->gart_mqd_addr;
- queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
+
+ if (q->wptr_bo) {
+ wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+ queue_input.wptr_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
+ } else
+ queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
+
queue_input.paging = false;
queue_input.tba_addr = qpd->tba_addr;
queue_input.tma_addr = qpd->tma_addr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index f1654b4da856..35e74bdd81da 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -377,6 +377,8 @@ static void update_mqd_sdma(struct mqd_manager *mm, void *mqd,
m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8);
m->sdmax_rlcx_rb_rptr_addr_lo = lower_32_bits((uint64_t)q->read_ptr);
m->sdmax_rlcx_rb_rptr_addr_hi = upper_32_bits((uint64_t)q->read_ptr);
+ m->sdmax_rlcx_rb_wptr_poll_addr_lo = lower_32_bits((uint64_t)q->write_ptr);
+ m->sdmax_rlcx_rb_wptr_poll_addr_hi = upper_32_bits((uint64_t)q->write_ptr);
m->sdmax_rlcx_doorbell_offset =
q->doorbell_off << SDMA0_QUEUE0_DOORBELL_OFFSET__OFFSET__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index a5d3963537d7..dcddee0d6f06 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -639,6 +639,8 @@ struct queue {
void *gang_ctx_bo;
uint64_t gang_ctx_gpu_addr;
void *gang_ctx_cpu_ptr;
+
+ struct amdgpu_bo *wptr_bo;
};
enum KFD_MQD_TYPE {
@@ -1404,6 +1406,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
struct file *f,
struct queue_properties *properties,
unsigned int *qid,
+ struct amdgpu_bo *wptr_bo,
const struct kfd_criu_queue_priv_data *q_data,
const void *restore_mqd,
const void *restore_ctl_stack,
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 f99e09dc43ea..3a17c1ebc527 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -190,7 +190,8 @@ void pqm_uninit(struct process_queue_manager *pqm)
static int init_user_queue(struct process_queue_manager *pqm,
struct kfd_dev *dev, struct queue **q,
struct queue_properties *q_properties,
- struct file *f, unsigned int qid)
+ struct file *f, struct amdgpu_bo *wptr_bo,
+ unsigned int qid)
{
int retval;
@@ -221,6 +222,7 @@ static int init_user_queue(struct process_queue_manager *pqm,
goto cleanup;
}
memset((*q)->gang_ctx_cpu_ptr, 0, AMDGPU_MES_GANG_CTX_SIZE);
+ (*q)->wptr_bo = wptr_bo;
}
pr_debug("PQM After init queue");
@@ -237,6 +239,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
struct file *f,
struct queue_properties *properties,
unsigned int *qid,
+ struct amdgpu_bo *wptr_bo,
const struct kfd_criu_queue_priv_data *q_data,
const void *restore_mqd,
const void *restore_ctl_stack,
@@ -299,7 +302,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
* allocate_sdma_queue() in create_queue() has the
* corresponding check logic.
*/
- retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
+ retval = init_user_queue(pqm, dev, &q, properties, f, wptr_bo, *qid);
if (retval != 0)
goto err_create_queue;
pqn->q = q;
@@ -320,7 +323,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
goto err_create_queue;
}
- retval = init_user_queue(pqm, dev, &q, properties, f, *qid);
+ retval = init_user_queue(pqm, dev, &q, properties, f, wptr_bo, *qid);
if (retval != 0)
goto err_create_queue;
pqn->q = q;
@@ -457,9 +460,13 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
pdd->qpd.num_gws = 0;
}
- if (dev->shared_resources.enable_mes)
+ if (dev->shared_resources.enable_mes) {
amdgpu_amdkfd_free_gtt_mem(dev->adev,
pqn->q->gang_ctx_bo);
+ if (pqn->q->wptr_bo)
+ amdgpu_amdkfd_free_gtt_mem(dev->adev, pqn->q->wptr_bo);
+
+ }
uninit_queue(pqn->q);
}
@@ -900,7 +907,7 @@ int kfd_criu_restore_queue(struct kfd_process *p,
print_queue_properties(&qp);
- ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, q_data, mqd, ctl_stack,
+ ret = pqm_create_queue(&p->pqm, pdd->dev, NULL, &qp, &queue_id, NULL, q_data, mqd, ctl_stack,
NULL);
if (ret) {
pr_err("Failed to create new queue err:%d\n", ret);
