@@ -1061,17 +1061,18 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict,
{
struct nouveau_drm *drm = nouveau_bdev(bo->bdev);
struct nouveau_bo *nvbo = nouveau_bo(bo);
+ struct drm_gem_object *obj = &bo->base;
struct ttm_resource *old_reg = bo->resource;
struct nouveau_drm_tile *new_tile = NULL;
int ret = 0;
-
if (new_reg->mem_type == TTM_PL_TT) {
ret = nouveau_ttm_tt_bind(bo->bdev, bo->ttm, new_reg);
if (ret)
return ret;
}
+ drm_gpuvm_bo_gem_evict(obj, evict);
nouveau_bo_move_ntfy(bo, new_reg);
ret = ttm_bo_wait_ctx(bo, ctx);
if (ret)
@@ -1136,6 +1137,7 @@ nouveau_bo_move(struct ttm_buffer_object *bo, bool evict,
out_ntfy:
if (ret) {
nouveau_bo_move_ntfy(bo, bo->resource);
+ drm_gpuvm_bo_gem_evict(obj, !evict);
}
return ret;
}
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: MIT
-#include <drm/drm_exec.h>
-
#include "nouveau_drv.h"
#include "nouveau_gem.h"
#include "nouveau_mem.h"
@@ -86,14 +84,12 @@
*/
static int
-nouveau_exec_job_submit(struct nouveau_job *job)
+nouveau_exec_job_submit(struct nouveau_job *job,
+ struct drm_gpuvm_exec *vme)
{
struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job);
struct nouveau_cli *cli = job->cli;
struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli);
- struct drm_exec *exec = &job->exec;
- struct drm_gem_object *obj;
- unsigned long index;
int ret;
/* Create a new fence, but do not emit yet. */
@@ -102,52 +98,29 @@ nouveau_exec_job_submit(struct nouveau_job *job)
return ret;
nouveau_uvmm_lock(uvmm);
- drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
- DRM_EXEC_IGNORE_DUPLICATES);
- drm_exec_until_all_locked(exec) {
- struct drm_gpuva *va;
-
- drm_gpuvm_for_each_va(va, &uvmm->base) {
- if (unlikely(va == &uvmm->base.kernel_alloc_node))
- continue;
-
- ret = drm_exec_prepare_obj(exec, va->gem.obj, 1);
- drm_exec_retry_on_contention(exec);
- if (ret)
- goto err_uvmm_unlock;
- }
+ ret = drm_gpuvm_exec_lock(vme);
+ if (ret) {
+ nouveau_uvmm_unlock(uvmm);
+ return ret;
}
nouveau_uvmm_unlock(uvmm);
- drm_exec_for_each_locked_object(exec, index, obj) {
- struct nouveau_bo *nvbo = nouveau_gem_object(obj);
-
- ret = nouveau_bo_validate(nvbo, true, false);
- if (ret)
- goto err_exec_fini;
+ ret = drm_gpuvm_exec_validate(vme);
+ if (ret) {
+ drm_gpuvm_exec_unlock(vme);
+ return ret;
}
return 0;
-
-err_uvmm_unlock:
- nouveau_uvmm_unlock(uvmm);
-err_exec_fini:
- drm_exec_fini(exec);
- return ret;
-
}
static void
-nouveau_exec_job_armed_submit(struct nouveau_job *job)
+nouveau_exec_job_armed_submit(struct nouveau_job *job,
+ struct drm_gpuvm_exec *vme)
{
- struct drm_exec *exec = &job->exec;
- struct drm_gem_object *obj;
- unsigned long index;
-
- drm_exec_for_each_locked_object(exec, index, obj)
- dma_resv_add_fence(obj->resv, job->done_fence, job->resv_usage);
-
- drm_exec_fini(exec);
+ drm_gpuvm_exec_resv_add_fence(vme, job->done_fence,
+ job->resv_usage, job->resv_usage);
+ drm_gpuvm_exec_unlock(vme);
}
static struct dma_fence *
@@ -3,16 +3,12 @@
#ifndef __NOUVEAU_EXEC_H__
#define __NOUVEAU_EXEC_H__
-#include <drm/drm_exec.h>
-
#include "nouveau_drv.h"
#include "nouveau_sched.h"
struct nouveau_exec_job_args {
struct drm_file *file_priv;
struct nouveau_sched_entity *sched_entity;
-
- struct drm_exec exec;
struct nouveau_channel *chan;
struct {
@@ -263,6 +263,11 @@ nouveau_job_submit(struct nouveau_job *job)
{
struct nouveau_sched_entity *entity = to_nouveau_sched_entity(job->base.entity);
struct dma_fence *done_fence = NULL;
+ struct drm_gpuvm_exec vm_exec = {
+ .vm = &nouveau_cli_uvmm(job->cli)->base,
+ .flags = DRM_EXEC_IGNORE_DUPLICATES,
+ .num_fences = 1,
+ };
int ret;
ret = nouveau_job_add_deps(job);
@@ -282,7 +287,7 @@ nouveau_job_submit(struct nouveau_job *job)
* successfully.
*/
if (job->ops->submit) {
- ret = job->ops->submit(job);
+ ret = job->ops->submit(job, &vm_exec);
if (ret)
goto err_cleanup;
}
@@ -315,7 +320,7 @@ nouveau_job_submit(struct nouveau_job *job)
set_bit(DRM_SCHED_FENCE_DONT_PIPELINE, &job->done_fence->flags);
if (job->ops->armed_submit)
- job->ops->armed_submit(job);
+ job->ops->armed_submit(job, &vm_exec);
nouveau_job_fence_attach(job);
@@ -5,7 +5,7 @@
#include <linux/types.h>
-#include <drm/drm_exec.h>
+#include <drm/drm_gpuvm.h>
#include <drm/gpu_scheduler.h>
#include "nouveau_drv.h"
@@ -54,7 +54,6 @@ struct nouveau_job {
struct drm_file *file_priv;
struct nouveau_cli *cli;
- struct drm_exec exec;
enum dma_resv_usage resv_usage;
struct dma_fence *done_fence;
@@ -76,8 +75,8 @@ struct nouveau_job {
/* If .submit() returns without any error, it is guaranteed that
* armed_submit() is called.
*/
- int (*submit)(struct nouveau_job *);
- void (*armed_submit)(struct nouveau_job *);
+ int (*submit)(struct nouveau_job *, struct drm_gpuvm_exec *);
+ void (*armed_submit)(struct nouveau_job *, struct drm_gpuvm_exec *);
struct dma_fence *(*run)(struct nouveau_job *);
void (*free)(struct nouveau_job *);
enum drm_gpu_sched_stat (*timeout)(struct nouveau_job *);
@@ -438,8 +438,9 @@ nouveau_uvma_region_complete(struct nouveau_uvma_region *reg)
static void
op_map_prepare_unwind(struct nouveau_uvma *uvma)
{
+ struct drm_gpuva *va = &uvma->va;
nouveau_uvma_gem_put(uvma);
- drm_gpuva_remove(&uvma->va);
+ drm_gpuva_remove(va);
nouveau_uvma_free(uvma);
}
@@ -468,6 +469,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
break;
case DRM_GPUVA_OP_REMAP: {
struct drm_gpuva_op_remap *r = &op->remap;
+ struct drm_gpuva *va = r->unmap->va;
if (r->next)
op_map_prepare_unwind(new->next);
@@ -475,7 +477,7 @@ nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm,
if (r->prev)
op_map_prepare_unwind(new->prev);
- op_unmap_prepare_unwind(r->unmap->va);
+ op_unmap_prepare_unwind(va);
break;
}
case DRM_GPUVA_OP_UNMAP:
@@ -634,6 +636,7 @@ nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm,
goto unwind;
}
}
+
break;
}
case DRM_GPUVA_OP_REMAP: {
@@ -1147,12 +1150,44 @@ bind_link_gpuvas(struct bind_job_op *bop)
}
static int
-nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
+bind_lock_extra(struct drm_gpuvm_exec *vme)
+{
+ struct nouveau_uvmm_bind_job *bind_job = vme->extra.priv;
+ struct drm_exec *exec = &vme->exec;
+ struct bind_job_op *op;
+ int ret;
+
+ list_for_each_op(op, &bind_job->ops) {
+ struct drm_gpuva_op *va_op;
+
+ if (IS_ERR_OR_NULL(op->ops))
+ continue;
+
+ drm_gpuva_for_each_op(va_op, op->ops) {
+ struct drm_gem_object *obj = op_gem_obj(va_op);
+
+ if (unlikely(!obj))
+ continue;
+
+ if (va_op->op != DRM_GPUVA_OP_UNMAP)
+ continue;
+
+ ret = drm_exec_prepare_obj(exec, obj, vme->num_fences);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int
+nouveau_uvmm_bind_job_submit(struct nouveau_job *job,
+ struct drm_gpuvm_exec *vme)
{
struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli);
struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(job);
struct nouveau_sched_entity *entity = job->entity;
- struct drm_exec *exec = &job->exec;
struct bind_job_op *op;
int ret;
@@ -1170,6 +1205,8 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
dma_resv_unlock(obj->resv);
if (IS_ERR(op->vm_bo))
return PTR_ERR(op->vm_bo);
+
+ drm_gpuvm_bo_extobj_add(op->vm_bo);
}
ret = bind_validate_op(job, op);
@@ -1192,6 +1229,7 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
* unwind all GPU VA space changes on failure.
*/
nouveau_uvmm_lock(uvmm);
+
list_for_each_op(op, &bind_job->ops) {
switch (op->op) {
case OP_MAP_SPARSE:
@@ -1303,30 +1341,12 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
}
}
- drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT |
- DRM_EXEC_IGNORE_DUPLICATES);
- drm_exec_until_all_locked(exec) {
- list_for_each_op(op, &bind_job->ops) {
- struct drm_gpuva_op *va_op;
+ vme->extra.fn = bind_lock_extra;
+ vme->extra.priv = bind_job;
- if (IS_ERR_OR_NULL(op->ops))
- continue;
-
- drm_gpuva_for_each_op(va_op, op->ops) {
- struct drm_gem_object *obj = op_gem_obj(va_op);
-
- if (unlikely(!obj))
- continue;
-
- ret = drm_exec_prepare_obj(exec, obj, 1);
- drm_exec_retry_on_contention(exec);
- if (ret) {
- op = list_last_op(&bind_job->ops);
- goto unwind;
- }
- }
- }
- }
+ ret = drm_gpuvm_exec_lock(vme);
+ if (ret)
+ goto unwind_continue;
list_for_each_op(op, &bind_job->ops) {
struct drm_gpuva_op *va_op;
@@ -1426,21 +1446,17 @@ nouveau_uvmm_bind_job_submit(struct nouveau_job *job)
}
nouveau_uvmm_unlock(uvmm);
- drm_exec_fini(exec);
+ drm_gpuvm_exec_unlock(vme);
return ret;
}
static void
-nouveau_uvmm_bind_job_armed_submit(struct nouveau_job *job)
+nouveau_uvmm_bind_job_armed_submit(struct nouveau_job *job,
+ struct drm_gpuvm_exec *vme)
{
- struct drm_exec *exec = &job->exec;
- struct drm_gem_object *obj;
- unsigned long index;
-
- drm_exec_for_each_locked_object(exec, index, obj)
- dma_resv_add_fence(obj->resv, job->done_fence, job->resv_usage);
-
- drm_exec_fini(exec);
+ drm_gpuvm_exec_resv_add_fence(vme, job->done_fence,
+ job->resv_usage, job->resv_usage);
+ drm_gpuvm_exec_unlock(vme);
}
static struct dma_fence *
@@ -1832,6 +1848,18 @@ nouveau_uvmm_bo_unmap_all(struct nouveau_bo *nvbo)
}
}
+static int
+nouveau_uvmm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
+{
+ struct nouveau_bo *nvbo = nouveau_gem_object(vm_bo->obj);
+
+ return nouveau_bo_validate(nvbo, true, false);
+}
+
+static const struct drm_gpuvm_ops gpuvm_ops = {
+ .vm_bo_validate = nouveau_uvmm_bo_validate,
+};
+
int
nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli,
u64 kernel_managed_addr, u64 kernel_managed_size)
@@ -1875,7 +1903,7 @@ nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli,
NOUVEAU_VA_SPACE_START,
NOUVEAU_VA_SPACE_END,
kernel_managed_addr, kernel_managed_size,
- NULL);
+ &gpuvm_ops);
/* GPUVM takes care from here on. */
drm_gem_object_put(r_obj);
GPUVM provides common infrastructure to track external and evicted GEM objects as well as locking and validation helpers. Especially external and evicted object tracking is a huge improvement compared to the current brute force approach of iterating all mappings in order to lock and validate the GPUVM's GEM objects. Hence, make us of it. Signed-off-by: Danilo Krummrich <dakr@redhat.com> --- drivers/gpu/drm/nouveau/nouveau_bo.c | 4 +- drivers/gpu/drm/nouveau/nouveau_exec.c | 57 ++++--------- drivers/gpu/drm/nouveau/nouveau_exec.h | 4 - drivers/gpu/drm/nouveau/nouveau_sched.c | 9 +- drivers/gpu/drm/nouveau/nouveau_sched.h | 7 +- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 104 +++++++++++++++--------- 6 files changed, 94 insertions(+), 91 deletions(-)