drm/radeon: simplify semaphore handling v2

Directly use the suballocator to get small chunks of memory.
It's equally fast and doesn't crash when we encounter a GPU reset.

v2: rebased on new SA interface.
Signed-off-by: Christian König <deathsimple@vodafone.de>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/evergreen.c

@@ -3550,7 +3550,6 @@ void evergreen_fini(struct radeon_device *rdev)
 	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);

drivers/gpu/drm/radeon/ni.c

@@ -1744,7 +1744,6 @@ void cayman_fini(struct radeon_device *rdev)
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);

drivers/gpu/drm/radeon/r600.c

@@ -2658,7 +2658,6 @@ void r600_fini(struct radeon_device *rdev)
 	r600_vram_scratch_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);

drivers/gpu/drm/radeon/radeon.h

@@ -434,34 +434,13 @@ int radeon_mode_dumb_destroy(struct drm_file *file_priv,
 /*
  * Semaphores.
  */
-struct radeon_ring;
-
-#define	RADEON_SEMAPHORE_BO_SIZE	256
-
-struct radeon_semaphore_driver {
-	rwlock_t			lock;
-	struct list_head		bo;
-};
-
-struct radeon_semaphore_bo;
-
 /* everything here is constant */
 struct radeon_semaphore {
-	struct list_head		list;
+	struct radeon_sa_bo		*sa_bo;
+	signed				waiters;
 	uint64_t			gpu_addr;
-	uint32_t			*cpu_ptr;
-	struct radeon_semaphore_bo	*bo;
 };
 
-struct radeon_semaphore_bo {
-	struct list_head		list;
-	struct radeon_ib		*ib;
-	struct list_head		free;
-	struct radeon_semaphore		semaphores[RADEON_SEMAPHORE_BO_SIZE/8];
-	unsigned			nused;
-};
-
-void radeon_semaphore_driver_fini(struct radeon_device *rdev);
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore);
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
@@ -473,7 +452,8 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 				bool sync_to[RADEON_NUM_RINGS],
 				int dst_ring);
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore);
+			   struct radeon_semaphore *semaphore,
+			   struct radeon_fence *fence);
 
 /*
  * GART structures, functions & helpers
@@ -1540,7 +1520,6 @@ struct radeon_device {
 	struct radeon_mman		mman;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
 	wait_queue_head_t		fence_queue;
-	struct radeon_semaphore_driver	semaphore_drv;
 	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
 	struct radeon_ib_pool		ib_pool;

drivers/gpu/drm/radeon/radeon_device.c

@@ -732,11 +732,9 @@ int radeon_device_init(struct radeon_device *rdev,
 	mutex_init(&rdev->gem.mutex);
 	mutex_init(&rdev->pm.mutex);
 	mutex_init(&rdev->vram_mutex);
-	rwlock_init(&rdev->semaphore_drv.lock);
 	INIT_LIST_HEAD(&rdev->gem.objects);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
 	init_waitqueue_head(&rdev->irq.idle_queue);
-	INIT_LIST_HEAD(&rdev->semaphore_drv.bo);
 	/* initialize vm here */
 	rdev->vm_manager.use_bitmap = 1;
 	rdev->vm_manager.max_pfn = 1 << 20;

drivers/gpu/drm/radeon/radeon_fence.c

@@ -140,7 +140,7 @@ static void radeon_fence_destroy(struct kref *kref)
 	fence = container_of(kref, struct radeon_fence, kref);
 	fence->seq = RADEON_FENCE_NOTEMITED_SEQ;
 	if (fence->semaphore)
-		radeon_semaphore_free(fence->rdev, fence->semaphore);
+		radeon_semaphore_free(fence->rdev, fence->semaphore, NULL);
 	kfree(fence);
 }
 

drivers/gpu/drm/radeon/radeon_semaphore.c

@@ -31,118 +31,40 @@
 #include "drm.h"
 #include "radeon.h"
 
-static int radeon_semaphore_add_bo(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	uint64_t gpu_addr;
-	uint32_t *cpu_ptr;
-	int r, i;
-
-	bo = kmalloc(sizeof(struct radeon_semaphore_bo), GFP_KERNEL);
-	if (bo == NULL) {
-		return -ENOMEM;
-	}
-	INIT_LIST_HEAD(&bo->free);
-	INIT_LIST_HEAD(&bo->list);
-	bo->nused = 0;
-
-	r = radeon_ib_get(rdev, 0, &bo->ib, RADEON_SEMAPHORE_BO_SIZE);
-	if (r) {
-		dev_err(rdev->dev, "failed to get a bo after 5 retry\n");
-		kfree(bo);
-		return r;
-	}
-	gpu_addr = radeon_sa_bo_gpu_addr(bo->ib->sa_bo);
-	cpu_ptr = radeon_sa_bo_cpu_addr(bo->ib->sa_bo);
-	for (i = 0; i < (RADEON_SEMAPHORE_BO_SIZE/8); i++) {
-		bo->semaphores[i].gpu_addr = gpu_addr;
-		bo->semaphores[i].cpu_ptr = cpu_ptr;
-		bo->semaphores[i].bo = bo;
-		list_add_tail(&bo->semaphores[i].list, &bo->free);
-		gpu_addr += 8;
-		cpu_ptr += 2;
-	}
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_add_tail(&bo->list, &rdev->semaphore_drv.bo);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-	return 0;
-}
-
-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, NULL);
-	radeon_fence_unref(&bo->ib->fence);
-	list_del(&bo->list);
-	kfree(bo);
-}
-
-void radeon_semaphore_shrink_locked(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-
-	if (list_empty(&rdev->semaphore_drv.bo)) {
-		return;
-	}
-	/* only shrink if first bo has free semaphore */
-	bo = list_first_entry(&rdev->semaphore_drv.bo, struct radeon_semaphore_bo, list);
-	if (list_empty(&bo->free)) {
-		return;
-	}
-	list_for_each_entry_safe_continue(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (bo->nused)
-			continue;
-		radeon_semaphore_del_bo_locked(rdev, bo);
-	}
-}
 
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore)
 {
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	bool do_retry = true;
 	int r;
 
-retry:
-	*semaphore = NULL;
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_for_each_entry(bo, &rdev->semaphore_drv.bo, list) {
-		if (list_empty(&bo->free))
-			continue;
-		*semaphore = list_first_entry(&bo->free, struct radeon_semaphore, list);
-		(*semaphore)->cpu_ptr[0] = 0;
-		(*semaphore)->cpu_ptr[1] = 0;
-		list_del(&(*semaphore)->list);
-		bo->nused++;
-		break;
-	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-
+	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
 	if (*semaphore == NULL) {
-		if (do_retry) {
-			do_retry = false;
-			r = radeon_semaphore_add_bo(rdev);
-			if (r)
-				return r;
-			goto retry;
-		}
 		return -ENOMEM;
 	}
-
+	r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
+			     &(*semaphore)->sa_bo, 8, 8, true);
+	if (r) {
+		kfree(*semaphore);
+		*semaphore = NULL;
+		return r;
+	}
+	(*semaphore)->waiters = 0;
+	(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
+	*((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
 	return 0;
 }
 
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 			          struct radeon_semaphore *semaphore)
 {
+	--semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, false);
 }
 
 void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 			        struct radeon_semaphore *semaphore)
 {
+	++semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
 }
 
@@ -200,29 +122,16 @@ int radeon_semaphore_sync_rings(struct radeon_device *rdev,
 }
 
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore)
+			   struct radeon_semaphore *semaphore,
+			   struct radeon_fence *fence)
 {
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	semaphore->bo->nused--;
-	list_add_tail(&semaphore->list, &semaphore->bo->free);
-	radeon_semaphore_shrink_locked(rdev);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-}
-
-void radeon_semaphore_driver_fini(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	/* we force to free everything */
-	list_for_each_entry_safe(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (!list_empty(&bo->free)) {
-			dev_err(rdev->dev, "still in use semaphore\n");
-		}
-		radeon_semaphore_del_bo_locked(rdev, bo);
+	if (semaphore == NULL) {
+		return;
+	}
+	if (semaphore->waiters > 0) {
+		dev_err(rdev->dev, "semaphore %p has more waiters than signalers,"
+			" hardware lockup imminent!\n", semaphore);
 	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
+	radeon_sa_bo_free(rdev, &semaphore->sa_bo, fence);
+	kfree(semaphore);
 }

drivers/gpu/drm/radeon/radeon_test.c

@@ -317,7 +317,7 @@ void radeon_test_ring_sync(struct radeon_device *rdev,
 
 out_cleanup:
 	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore);
+		radeon_semaphore_free(rdev, semaphore, NULL);
 
 	if (fence1)
 		radeon_fence_unref(&fence1);
@@ -437,7 +437,7 @@ void radeon_test_ring_sync2(struct radeon_device *rdev,
 
 out_cleanup:
 	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore);
+		radeon_semaphore_free(rdev, semaphore, NULL);
 
 	if (fenceA)
 		radeon_fence_unref(&fenceA);

drivers/gpu/drm/radeon/rv770.c

@@ -1278,7 +1278,6 @@ void rv770_fini(struct radeon_device *rdev)
 	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);

drivers/gpu/drm/radeon/si.c

@@ -4109,7 +4109,6 @@ void si_fini(struct radeon_device *rdev)
 	si_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);