Commit c8d4c18b authored by Christian König's avatar Christian König

dma-buf/drivers: make reserving a shared slot mandatory v4

Audit all the users of dma_resv_add_excl_fence() and make sure they
reserve a shared slot also when only trying to add an exclusive fence.

This is the next step towards handling the exclusive fence like a
shared one.

v2: fix missed case in amdgpu
v3: and two more radeon, rename function
v4: add one more case to TTM, fix i915 after rebase
Signed-off-by: default avatarChristian König <christian.koenig@amd.com>
Reviewed-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20220406075132.3263-2-christian.koenig@amd.com
parent 20b734c1
......@@ -152,7 +152,7 @@ static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj)
}
/**
* dma_resv_reserve_shared - Reserve space to add shared fences to
* dma_resv_reserve_fences - Reserve space to add shared fences to
* a dma_resv.
* @obj: reservation object
* @num_fences: number of fences we want to add
......@@ -167,7 +167,7 @@ static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj)
* RETURNS
* Zero for success, or -errno
*/
int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences)
int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences)
{
struct dma_resv_list *old, *new;
unsigned int i, j, k, max;
......@@ -230,7 +230,7 @@ int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences)
return 0;
}
EXPORT_SYMBOL(dma_resv_reserve_shared);
EXPORT_SYMBOL(dma_resv_reserve_fences);
#ifdef CONFIG_DEBUG_MUTEXES
/**
......@@ -238,7 +238,7 @@ EXPORT_SYMBOL(dma_resv_reserve_shared);
* @obj: the dma_resv object to reset
*
* Reset the number of pre-reserved shared slots to test that drivers do
* correct slot allocation using dma_resv_reserve_shared(). See also
* correct slot allocation using dma_resv_reserve_fences(). See also
* &dma_resv_list.shared_max.
*/
void dma_resv_reset_shared_max(struct dma_resv *obj)
......@@ -260,7 +260,7 @@ EXPORT_SYMBOL(dma_resv_reset_shared_max);
* @fence: the shared fence to add
*
* Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and
* dma_resv_reserve_shared() has been called.
* dma_resv_reserve_fences() has been called.
*
* See also &dma_resv.fence for a discussion of the semantics.
*/
......
......@@ -75,17 +75,16 @@ static int test_signaling(void *arg, bool shared)
goto err_free;
}
if (shared) {
r = dma_resv_reserve_shared(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
goto err_unlock;
}
r = dma_resv_reserve_fences(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
goto err_unlock;
}
if (shared)
dma_resv_add_shared_fence(&resv, f);
} else {
else
dma_resv_add_excl_fence(&resv, f);
}
if (dma_resv_test_signaled(&resv, shared)) {
pr_err("Resv unexpectedly signaled\n");
......@@ -134,17 +133,16 @@ static int test_for_each(void *arg, bool shared)
goto err_free;
}
if (shared) {
r = dma_resv_reserve_shared(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
goto err_unlock;
}
r = dma_resv_reserve_fences(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
goto err_unlock;
}
if (shared)
dma_resv_add_shared_fence(&resv, f);
} else {
else
dma_resv_add_excl_fence(&resv, f);
}
r = -ENOENT;
dma_resv_for_each_fence(&cursor, &resv, shared, fence) {
......@@ -206,18 +204,17 @@ static int test_for_each_unlocked(void *arg, bool shared)
goto err_free;
}
if (shared) {
r = dma_resv_reserve_shared(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
dma_resv_unlock(&resv);
goto err_free;
}
r = dma_resv_reserve_fences(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
dma_resv_unlock(&resv);
goto err_free;
}
if (shared)
dma_resv_add_shared_fence(&resv, f);
} else {
else
dma_resv_add_excl_fence(&resv, f);
}
dma_resv_unlock(&resv);
r = -ENOENT;
......@@ -290,18 +287,17 @@ static int test_get_fences(void *arg, bool shared)
goto err_resv;
}
if (shared) {
r = dma_resv_reserve_shared(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
dma_resv_unlock(&resv);
goto err_resv;
}
r = dma_resv_reserve_fences(&resv, 1);
if (r) {
pr_err("Resv shared slot allocation failed\n");
dma_resv_unlock(&resv);
goto err_resv;
}
if (shared)
dma_resv_add_shared_fence(&resv, f);
} else {
else
dma_resv_add_excl_fence(&resv, f);
}
dma_resv_unlock(&resv);
r = dma_resv_get_fences(&resv, shared, &i, &fences);
......
......@@ -1233,7 +1233,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info,
AMDGPU_FENCE_OWNER_KFD, false);
if (ret)
goto wait_pd_fail;
ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1);
ret = dma_resv_reserve_fences(vm->root.bo->tbo.base.resv, 1);
if (ret)
goto reserve_shared_fail;
amdgpu_bo_fence(vm->root.bo,
......@@ -2571,7 +2571,7 @@ int amdgpu_amdkfd_add_gws_to_process(void *info, void *gws, struct kgd_mem **mem
* Add process eviction fence to bo so they can
* evict each other.
*/
ret = dma_resv_reserve_shared(gws_bo->tbo.base.resv, 1);
ret = dma_resv_reserve_fences(gws_bo->tbo.base.resv, 1);
if (ret)
goto reserve_shared_fail;
amdgpu_bo_fence(gws_bo, &process_info->eviction_fence->base, true);
......
......@@ -1388,6 +1388,14 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
bool shared)
{
struct dma_resv *resv = bo->tbo.base.resv;
int r;
r = dma_resv_reserve_fences(resv, 1);
if (r) {
/* As last resort on OOM we block for the fence */
dma_fence_wait(fence, false);
return;
}
if (shared)
dma_resv_add_shared_fence(resv, fence);
......
......@@ -2926,7 +2926,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm)
if (r)
goto error_free_root;
r = dma_resv_reserve_shared(root_bo->tbo.base.resv, 1);
r = dma_resv_reserve_fences(root_bo->tbo.base.resv, 1);
if (r)
goto error_unreserve;
......@@ -3369,7 +3369,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid,
value = 0;
}
r = dma_resv_reserve_shared(root->tbo.base.resv, 1);
r = dma_resv_reserve_fences(root->tbo.base.resv, 1);
if (r) {
pr_debug("failed %d to reserve fence slot\n", r);
goto error_unlock;
......
......@@ -548,7 +548,7 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange,
goto reserve_bo_failed;
}
r = dma_resv_reserve_shared(bo->tbo.base.resv, 1);
r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (r) {
pr_debug("failed %d to reserve bo\n", r);
amdgpu_bo_unreserve(bo);
......
......@@ -179,11 +179,9 @@ static int submit_fence_sync(struct etnaviv_gem_submit *submit)
struct etnaviv_gem_submit_bo *bo = &submit->bos[i];
struct dma_resv *robj = bo->obj->base.resv;
if (!(bo->flags & ETNA_SUBMIT_BO_WRITE)) {
ret = dma_resv_reserve_shared(robj, 1);
if (ret)
return ret;
}
ret = dma_resv_reserve_fences(robj, 1);
if (ret)
return ret;
if (submit->flags & ETNA_SUBMIT_NO_IMPLICIT)
continue;
......
......@@ -108,7 +108,8 @@ bool i915_gem_clflush_object(struct drm_i915_gem_object *obj,
trace_i915_gem_object_clflush(obj);
clflush = NULL;
if (!(flags & I915_CLFLUSH_SYNC))
if (!(flags & I915_CLFLUSH_SYNC) &&
dma_resv_reserve_fences(obj->base.resv, 1) == 0)
clflush = clflush_work_create(obj);
if (clflush) {
i915_sw_fence_await_reservation(&clflush->base.chain,
......
......@@ -998,11 +998,9 @@ static int eb_validate_vmas(struct i915_execbuffer *eb)
}
}
if (!(ev->flags & EXEC_OBJECT_WRITE)) {
err = dma_resv_reserve_shared(vma->obj->base.resv, 1);
if (err)
return err;
}
err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
if (err)
return err;
GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
eb_vma_misplaced(&eb->exec[i], vma, ev->flags));
......@@ -2303,7 +2301,7 @@ static int eb_parse(struct i915_execbuffer *eb)
if (IS_ERR(batch))
return PTR_ERR(batch);
err = dma_resv_reserve_shared(shadow->obj->base.resv, 1);
err = dma_resv_reserve_fences(shadow->obj->base.resv, 1);
if (err)
return err;
......
......@@ -611,7 +611,11 @@ int i915_gem_obj_copy_ttm(struct drm_i915_gem_object *dst,
assert_object_held(src);
i915_deps_init(&deps, GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN);
ret = dma_resv_reserve_shared(src_bo->base.resv, 1);
ret = dma_resv_reserve_fences(src_bo->base.resv, 1);
if (ret)
return ret;
ret = dma_resv_reserve_fences(dst_bo->base.resv, 1);
if (ret)
return ret;
......
......@@ -216,7 +216,10 @@ static int __igt_lmem_pages_migrate(struct intel_gt *gt,
i915_gem_object_is_lmem(obj),
0xdeadbeaf, &rq);
if (rq) {
dma_resv_add_excl_fence(obj->base.resv, &rq->fence);
err = dma_resv_reserve_fences(obj->base.resv, 1);
if (!err)
dma_resv_add_excl_fence(obj->base.resv,
&rq->fence);
i915_gem_object_set_moving_fence(obj, &rq->fence);
i915_request_put(rq);
}
......
......@@ -1819,6 +1819,12 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
intel_frontbuffer_put(front);
}
if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
if (unlikely(err))
return err;
}
if (fence) {
dma_resv_add_excl_fence(vma->obj->base.resv, fence);
obj->write_domain = I915_GEM_DOMAIN_RENDER;
......@@ -1826,7 +1832,7 @@ int _i915_vma_move_to_active(struct i915_vma *vma,
}
} else {
if (!(flags & __EXEC_OBJECT_NO_RESERVE)) {
err = dma_resv_reserve_shared(vma->obj->base.resv, 1);
err = dma_resv_reserve_fences(vma->obj->base.resv, 1);
if (unlikely(err))
return err;
}
......@@ -2044,7 +2050,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm)
if (!obj->mm.rsgt)
return -EBUSY;
err = dma_resv_reserve_shared(obj->base.resv, 1);
err = dma_resv_reserve_fences(obj->base.resv, 1);
if (err)
return -EBUSY;
......
......@@ -1043,6 +1043,13 @@ static int igt_lmem_write_cpu(void *arg)
}
i915_gem_object_lock(obj, NULL);
err = dma_resv_reserve_fences(obj->base.resv, 1);
if (err) {
i915_gem_object_unlock(obj);
goto out_put;
}
/* Put the pages into a known state -- from the gpu for added fun */
intel_engine_pm_get(engine);
err = intel_context_migrate_clear(engine->gt->migrate.context, NULL,
......
......@@ -257,13 +257,11 @@ int lima_gem_get_info(struct drm_file *file, u32 handle, u32 *va, u64 *offset)
static int lima_gem_sync_bo(struct lima_sched_task *task, struct lima_bo *bo,
bool write, bool explicit)
{
int err = 0;
int err;
if (!write) {
err = dma_resv_reserve_shared(lima_bo_resv(bo), 1);
if (err)
return err;
}
err = dma_resv_reserve_fences(lima_bo_resv(bo), 1);
if (err)
return err;
/* explicit sync use user passed dep fence */
if (explicit)
......
......@@ -320,16 +320,14 @@ static int submit_fence_sync(struct msm_gem_submit *submit, bool no_implicit)
struct drm_gem_object *obj = &submit->bos[i].obj->base;
bool write = submit->bos[i].flags & MSM_SUBMIT_BO_WRITE;
if (!write) {
/* NOTE: _reserve_shared() must happen before
* _add_shared_fence(), which makes this a slightly
* strange place to call it. OTOH this is a
* convenient can-fail point to hook it in.
*/
ret = dma_resv_reserve_shared(obj->resv, 1);
if (ret)
return ret;
}
/* NOTE: _reserve_shared() must happen before
* _add_shared_fence(), which makes this a slightly
* strange place to call it. OTOH this is a
* convenient can-fail point to hook it in.
*/
ret = dma_resv_reserve_fences(obj->resv, 1);
if (ret)
return ret;
/* exclusive fences must be ordered */
if (no_implicit && !write)
......
......@@ -346,11 +346,9 @@ nouveau_fence_sync(struct nouveau_bo *nvbo, struct nouveau_channel *chan,
struct dma_resv *resv = nvbo->bo.base.resv;
int i, ret;
if (!exclusive) {
ret = dma_resv_reserve_shared(resv, 1);
if (ret)
return ret;
}
ret = dma_resv_reserve_fences(resv, 1);
if (ret)
return ret;
/* Waiting for the exclusive fence first causes performance regressions
* under some circumstances. So manually wait for the shared ones first.
......
......@@ -247,6 +247,10 @@ static int panfrost_acquire_object_fences(struct drm_gem_object **bos,
int i, ret;
for (i = 0; i < bo_count; i++) {
ret = dma_resv_reserve_fences(bos[i]->resv, 1);
if (ret)
return ret;
/* panfrost always uses write mode in its current uapi */
ret = drm_sched_job_add_implicit_dependencies(job, bos[i],
true);
......
......@@ -200,7 +200,7 @@ static int qxl_release_validate_bo(struct qxl_bo *bo)
return ret;
}
ret = dma_resv_reserve_shared(bo->tbo.base.resv, 1);
ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (ret)
return ret;
......
......@@ -535,6 +535,10 @@ static int radeon_bo_vm_update_pte(struct radeon_cs_parser *p,
return r;
radeon_sync_fence(&p->ib.sync, bo_va->last_pt_update);
r = dma_resv_reserve_fences(bo->tbo.base.resv, 1);
if (r)
return r;
}
return radeon_vm_clear_invalids(rdev, vm);
......
......@@ -782,6 +782,14 @@ void radeon_bo_fence(struct radeon_bo *bo, struct radeon_fence *fence,
bool shared)
{
struct dma_resv *resv = bo->tbo.base.resv;
int r;
r = dma_resv_reserve_fences(resv, 1);
if (r) {
/* As last resort on OOM we block for the fence */
dma_fence_wait(&fence->base, false);
return;
}
if (shared)
dma_resv_add_shared_fence(resv, &fence->base);
......
......@@ -831,7 +831,7 @@ static int radeon_vm_update_ptes(struct radeon_device *rdev,
int r;
radeon_sync_resv(rdev, &ib->sync, pt->tbo.base.resv, true);
r = dma_resv_reserve_shared(pt->tbo.base.resv, 1);
r = dma_resv_reserve_fences(pt->tbo.base.resv, 1);
if (r)
return r;
......
......@@ -151,6 +151,10 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
}
}
ret = dma_resv_reserve_fences(bo->base.resv, 1);
if (ret)
goto out_err;
ret = bdev->funcs->move(bo, evict, ctx, mem, hop);
if (ret) {
if (ret == -EMULTIHOP)
......@@ -735,7 +739,7 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
dma_resv_add_shared_fence(bo->base.resv, fence);
ret = dma_resv_reserve_shared(bo->base.resv, 1);
ret = dma_resv_reserve_fences(bo->base.resv, 1);
if (unlikely(ret)) {
dma_fence_put(fence);
return ret;
......@@ -794,7 +798,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
bool type_found = false;
int i, ret;
ret = dma_resv_reserve_shared(bo->base.resv, 1);
ret = dma_resv_reserve_fences(bo->base.resv, 1);
if (unlikely(ret))
return ret;
......
......@@ -221,9 +221,6 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
fbo->base = *bo;
ttm_bo_get(bo);
fbo->bo = bo;
/**
* Fix up members that we shouldn't copy directly:
* TODO: Explicit member copy would probably be better here.
......@@ -250,6 +247,15 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
ret = dma_resv_trylock(&fbo->base.base._resv);
WARN_ON(!ret);
ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1);
if (ret) {
kfree(fbo);
return ret;
}
ttm_bo_get(bo);
fbo->bo = bo;
ttm_bo_move_to_lru_tail_unlocked(&fbo->base);
*new_obj = &fbo->base;
......
......@@ -90,6 +90,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
list_for_each_entry(entry, list, head) {
struct ttm_buffer_object *bo = entry->bo;
unsigned int num_fences;
ret = ttm_bo_reserve(bo, intr, (ticket == NULL), ticket);
if (ret == -EALREADY && dups) {
......@@ -100,12 +101,10 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
continue;
}
num_fences = min(entry->num_shared, 1u);
if (!ret) {
if (!entry->num_shared)
continue;
ret = dma_resv_reserve_shared(bo->base.resv,
entry->num_shared);
ret = dma_resv_reserve_fences(bo->base.resv,
num_fences);
if (!ret)
continue;
}
......@@ -120,9 +119,9 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
ret = ttm_bo_reserve_slowpath(bo, intr, ticket);
}
if (!ret && entry->num_shared)
ret = dma_resv_reserve_shared(bo->base.resv,
entry->num_shared);
if (!ret)
ret = dma_resv_reserve_fences(bo->base.resv,
num_fences);
if (unlikely(ret != 0)) {
if (ticket) {
......
......@@ -259,16 +259,21 @@ v3d_lock_bo_reservations(struct v3d_job *job,
return ret;
for (i = 0; i < job->bo_count; i++) {
ret = dma_resv_reserve_fences(job->bo[i]->resv, 1);
if (ret)
goto fail;
ret = drm_sched_job_add_implicit_dependencies(&job->base,
job->bo[i], true);
if (ret) {
drm_gem_unlock_reservations(job->bo, job->bo_count,
acquire_ctx);
return ret;
}
if (ret)
goto fail;
}
return 0;
fail:
drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
return ret;
}
/**
......
......@@ -644,7 +644,7 @@ vc4_lock_bo_reservations(struct drm_device *dev,
for (i = 0; i < exec->bo_count; i++) {
bo = &exec->bo[i]->base;
ret = dma_resv_reserve_shared(bo->resv, 1);
ret = dma_resv_reserve_fences(bo->resv, 1);
if (ret) {
vc4_unlock_bo_reservations(dev, exec, acquire_ctx);
return ret;
......
......@@ -157,12 +157,14 @@ int vgem_fence_attach_ioctl(struct drm_device *dev,
}
/* Expose the fence via the dma-buf */
ret = 0;
dma_resv_lock(resv, NULL);
if (arg->flags & VGEM_FENCE_WRITE)
dma_resv_add_excl_fence(resv, fence);
else if ((ret = dma_resv_reserve_shared(resv, 1)) == 0)
dma_resv_add_shared_fence(resv, fence);
ret = dma_resv_reserve_fences(resv, 1);
if (!ret) {
if (arg->flags & VGEM_FENCE_WRITE)
dma_resv_add_excl_fence(resv, fence);
else
dma_resv_add_shared_fence(resv, fence);
}
dma_resv_unlock(resv);
/* Record the fence in our idr for later signaling */
......
......@@ -214,6 +214,7 @@ void virtio_gpu_array_add_obj(struct virtio_gpu_object_array *objs,
int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs)
{
unsigned int i;
int ret;
if (objs->nents == 1) {
......@@ -222,6 +223,14 @@ int virtio_gpu_array_lock_resv(struct virtio_gpu_object_array *objs)
ret = drm_gem_lock_reservations(objs->objs, objs->nents,
&objs->ticket);
}
if (ret)
return ret;
for (i = 0; i < objs->nents; ++i) {
ret = dma_resv_reserve_fences(objs->objs[i]->resv, 1);
if (ret)
return ret;
}
return ret;
}
......
......@@ -747,16 +747,22 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
struct vmw_fence_obj *fence)
{
struct ttm_device *bdev = bo->bdev;
struct vmw_private *dev_priv =
container_of(bdev, struct vmw_private, bdev);
int ret;
if (fence == NULL) {
if (fence == NULL)
vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
else
dma_fence_get(&fence->base);
ret = dma_resv_reserve_fences(bo->base.resv, 1);
if (!ret)
dma_resv_add_excl_fence(bo->base.resv, &fence->base);
dma_fence_put(&fence->base);
} else
dma_resv_add_excl_fence(bo->base.resv, &fence->base);
else
/* Last resort fallback when we are OOM */
dma_fence_wait(&fence->base, false);
dma_fence_put(&fence->base);
}
......
......@@ -117,7 +117,7 @@ struct dma_resv {
* A new fence is added by calling dma_resv_add_shared_fence(). Since
* this often needs to be done past the point of no return in command
* submission it cannot fail, and therefore sufficient slots need to be
* reserved by calling dma_resv_reserve_shared().
* reserved by calling dma_resv_reserve_fences().
*
* Note that actual semantics of what an exclusive or shared fence mean
* is defined by the user, for reservation objects shared across drivers
......@@ -413,7 +413,7 @@ static inline void dma_resv_unlock(struct dma_resv *obj)
void dma_resv_init(struct dma_resv *obj);
void dma_resv_fini(struct dma_resv *obj);
int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences);
int dma_resv_reserve_fences(struct dma_resv *obj, unsigned int num_fences);
void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence);
void dma_resv_replace_fences(struct dma_resv *obj, uint64_t context,
struct dma_fence *fence);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment