Define the interface without modifying the allocation algorithm in any way.
v2: rebase on top of fence new uint64 patch v3: add ring to debugfs output
Signed-off-by: Jerome Glisse jglisse@redhat.com Signed-off-by: Christian König deathsimple@vodafone.de --- drivers/gpu/drm/radeon/radeon.h | 1 + drivers/gpu/drm/radeon/radeon_gart.c | 6 +- drivers/gpu/drm/radeon/radeon_object.h | 5 +- drivers/gpu/drm/radeon/radeon_ring.c | 8 ++-- drivers/gpu/drm/radeon/radeon_sa.c | 60 ++++++++++++++++++++++++---- drivers/gpu/drm/radeon/radeon_semaphore.c | 2 +- 6 files changed, 63 insertions(+), 19 deletions(-)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index 9374ab1..ada70d1 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -398,6 +398,7 @@ struct radeon_sa_bo { struct radeon_sa_manager *manager; unsigned soffset; unsigned eoffset; + struct radeon_fence *fence; };
/* diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index c5789ef..53dba8e 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -326,7 +326,7 @@ static void radeon_vm_unbind_locked(struct radeon_device *rdev, rdev->vm_manager.use_bitmap &= ~(1 << vm->id); list_del_init(&vm->list); vm->id = -1; - radeon_sa_bo_free(rdev, &vm->sa_bo); + radeon_sa_bo_free(rdev, &vm->sa_bo, NULL); vm->pt = NULL;
list_for_each_entry(bo_va, &vm->va, vm_list) { @@ -395,7 +395,7 @@ int radeon_vm_bind(struct radeon_device *rdev, struct radeon_vm *vm) retry: r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, &vm->sa_bo, RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8), - RADEON_GPU_PAGE_SIZE); + RADEON_GPU_PAGE_SIZE, false); if (r) { if (list_empty(&rdev->vm_manager.lru_vm)) { return r; @@ -426,7 +426,7 @@ retry_id: /* do hw bind */ r = rdev->vm_manager.funcs->bind(rdev, vm, id); if (r) { - radeon_sa_bo_free(rdev, &vm->sa_bo); + radeon_sa_bo_free(rdev, &vm->sa_bo, NULL); return r; } rdev->vm_manager.use_bitmap |= 1 << id; diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h index 4fc7f07..befec7d 100644 --- a/drivers/gpu/drm/radeon/radeon_object.h +++ b/drivers/gpu/drm/radeon/radeon_object.h @@ -169,9 +169,10 @@ extern int radeon_sa_bo_manager_suspend(struct radeon_device *rdev, extern int radeon_sa_bo_new(struct radeon_device *rdev, struct radeon_sa_manager *sa_manager, struct radeon_sa_bo **sa_bo, - unsigned size, unsigned align); + unsigned size, unsigned align, bool block); extern void radeon_sa_bo_free(struct radeon_device *rdev, - struct radeon_sa_bo **sa_bo); + struct radeon_sa_bo **sa_bo, + struct radeon_fence *fence); #if defined(CONFIG_DEBUG_FS) extern void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager, struct seq_file *m); diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c index 45adb37..1748d93 100644 --- a/drivers/gpu/drm/radeon/radeon_ring.c +++ b/drivers/gpu/drm/radeon/radeon_ring.c @@ -85,7 +85,7 @@ bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib) if (ib->fence && ib->fence->seq < RADEON_FENCE_NOTEMITED_SEQ) { if (radeon_fence_signaled(ib->fence)) { radeon_fence_unref(&ib->fence); - radeon_sa_bo_free(rdev, &ib->sa_bo); + radeon_sa_bo_free(rdev, &ib->sa_bo, NULL); done = true; } } @@ -124,7 +124,7 @@ retry: if (rdev->ib_pool.ibs[idx].fence == NULL) { r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager, &rdev->ib_pool.ibs[idx].sa_bo, - size, 256); + size, 256, false); if (!r) { *ib = &rdev->ib_pool.ibs[idx]; (*ib)->ptr = radeon_sa_bo_cpu_addr((*ib)->sa_bo); @@ -173,7 +173,7 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib) } radeon_mutex_lock(&rdev->ib_pool.mutex); if (tmp->fence && tmp->fence->seq == RADEON_FENCE_NOTEMITED_SEQ) { - radeon_sa_bo_free(rdev, &tmp->sa_bo); + radeon_sa_bo_free(rdev, &tmp->sa_bo, NULL); radeon_fence_unref(&tmp->fence); } radeon_mutex_unlock(&rdev->ib_pool.mutex); @@ -247,7 +247,7 @@ void radeon_ib_pool_fini(struct radeon_device *rdev) radeon_mutex_lock(&rdev->ib_pool.mutex); if (rdev->ib_pool.ready) { for (i = 0; i < RADEON_IB_POOL_SIZE; i++) { - radeon_sa_bo_free(rdev, &rdev->ib_pool.ibs[i].sa_bo); + radeon_sa_bo_free(rdev, &rdev->ib_pool.ibs[i].sa_bo, NULL); radeon_fence_unref(&rdev->ib_pool.ibs[i].fence); } radeon_sa_bo_manager_fini(rdev, &rdev->ib_pool.sa_manager); diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c index 625f2d4..90ee8ad 100644 --- a/drivers/gpu/drm/radeon/radeon_sa.c +++ b/drivers/gpu/drm/radeon/radeon_sa.c @@ -129,20 +129,32 @@ int radeon_sa_bo_manager_suspend(struct radeon_device *rdev, * * Alignment can't be bigger than page size */ + +static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo) +{ + list_del(&sa_bo->list); + radeon_fence_unref(&sa_bo->fence); + kfree(sa_bo); +} + int radeon_sa_bo_new(struct radeon_device *rdev, struct radeon_sa_manager *sa_manager, struct radeon_sa_bo **sa_bo, - unsigned size, unsigned align) + unsigned size, unsigned align, bool block) { - struct radeon_sa_bo *tmp; + struct radeon_fence *fence = NULL; + struct radeon_sa_bo *tmp, *next; struct list_head *head; unsigned offset = 0, wasted = 0; + int r;
BUG_ON(align > RADEON_GPU_PAGE_SIZE); BUG_ON(size > sa_manager->size);
*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
+retry: + spin_lock(&sa_manager->lock);
/* no one ? */ @@ -153,7 +165,17 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
/* look for a hole big enough */ offset = 0; - list_for_each_entry(tmp, &sa_manager->sa_bo, list) { + list_for_each_entry_safe(tmp, next, &sa_manager->sa_bo, list) { + /* try to free this object */ + if (tmp->fence) { + if (radeon_fence_signaled(tmp->fence)) { + radeon_sa_bo_remove_locked(tmp); + continue; + } else { + fence = tmp->fence; + } + } + /* room before this object ? */ if (offset < tmp->soffset && (tmp->soffset - offset) >= size) { head = tmp->list.prev; @@ -178,6 +200,13 @@ int radeon_sa_bo_new(struct radeon_device *rdev, if ((sa_manager->size - offset) < size) { /* failed to find somethings big enough */ spin_unlock(&sa_manager->lock); + if (block && fence) { + r = radeon_fence_wait(fence, false); + if (r) + return r; + + goto retry; + } kfree(*sa_bo); *sa_bo = NULL; return -ENOMEM; @@ -192,15 +221,22 @@ out: return 0; }
-void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo) +void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo, + struct radeon_fence *fence) { + struct radeon_sa_manager *sa_manager; + if (!sa_bo || !*sa_bo) return;
- spin_lock(&(*sa_bo)->manager->lock); - list_del_init(&(*sa_bo)->list); - spin_unlock(&(*sa_bo)->manager->lock); - kfree(*sa_bo); + sa_manager = (*sa_bo)->manager; + spin_lock(&sa_manager->lock); + if (fence && fence->seq && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) { + (*sa_bo)->fence = radeon_fence_ref(fence); + } else { + radeon_sa_bo_remove_locked(*sa_bo); + } + spin_unlock(&sa_manager->lock); *sa_bo = NULL; }
@@ -212,8 +248,14 @@ void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager,
spin_lock(&sa_manager->lock); list_for_each_entry(i, &sa_manager->sa_bo, list) { - seq_printf(m, "[%08x %08x] size %4d [%p]\n", + seq_printf(m, "[%08x %08x] size %4d (%p)", i->soffset, i->eoffset, i->eoffset - i->soffset, i); + if (i->fence) { + seq_printf(m, " protected by %Ld (%p) on ring %d\n", + i->fence->seq, i->fence, i->fence->ring); + } else { + seq_printf(m, "\n"); + } } spin_unlock(&sa_manager->lock); } diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c index d518d32..dbde874 100644 --- a/drivers/gpu/drm/radeon/radeon_semaphore.c +++ b/drivers/gpu/drm/radeon/radeon_semaphore.c @@ -72,7 +72,7 @@ static int radeon_semaphore_add_bo(struct radeon_device *rdev) static void radeon_semaphore_del_bo_locked(struct radeon_device *rdev, struct radeon_semaphore_bo *bo) { - radeon_sa_bo_free(rdev, &bo->ib->sa_bo); + radeon_sa_bo_free(rdev, &bo->ib->sa_bo, NULL); radeon_fence_unref(&bo->ib->fence); list_del(&bo->list); kfree(bo);