Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux

Pull drm fixes from Dave Airlie:
 "Radeon and amdkfd fixes.

  Radeon ones mostly for oops in some test/benchmark functions since
  fencing changes, and one regression fix for old GPUs,

  There is one cirrus regression fix, the 32bpp broke userspace, so this
  hides it behind a module option for the few users who care.

  I'm off for a few days, so this is probably the final pull I have, if
  I see fixes from Intel I'll forward the pull as I should have email"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/cirrus: Limit modes depending on bpp option
  drm/radeon: fix the crash in test functions
  drm/radeon: fix the crash in benchmark functions
  drm/radeon: properly set vm fragment size for TN/RL
  drm/radeon: don't init gpuvm if accel is disabled (v3)
  drm/radeon: fix PLLs on RS880 and older v2
  drm/amdkfd: Don't create BUG due to incorrect user parameter
  drm/amdkfd: max num of queues can't be 0
  drm/amdkfd: Fix bug in accounting of queues

13 files changed, 54 insertions, 27 deletions

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 0d8694f015c1..0fd592799d58 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -822,7 +822,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	 * Unconditionally decrement this counter, regardless of the queue's
 	 * type.
 	 */
-	dqm->total_queue_count++;
+	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 	mutex_unlock(&dqm->lock);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index a8be6df85347..1c385c23dd0b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -95,10 +95,10 @@ static int __init kfd_module_init(void)
 	}
 
 	/* Verify module parameters */
-	if ((max_num_of_queues_per_device < 0) ||
+	if ((max_num_of_queues_per_device < 1) ||
 		(max_num_of_queues_per_device >
 			KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
-		pr_err("kfd: max_num_of_queues_per_device must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
+		pr_err("kfd: max_num_of_queues_per_device must be between 1 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
 		return -1;
 	}
 
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 f37cf5efe642..2fda1927bff7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -315,7 +315,11 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	BUG_ON(!pqm);
 
 	pqn = get_queue_by_qid(pqm, qid);
-	BUG_ON(!pqn);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for update operation\n",
+				qid);
+		return -EFAULT;
+	}
 
 	pqn->q->properties.queue_address = p->queue_address;
 	pqn->q->properties.queue_size = p->queue_size;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index c2a1cba1e984..b9140032962d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -16,9 +16,12 @@
 #include "cirrus_drv.h"
 
 int cirrus_modeset = -1;
+int cirrus_bpp = 24;
 
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, cirrus_modeset, int, 0400);
+MODULE_PARM_DESC(bpp, "Max bits-per-pixel (default:24)");
+module_param_named(bpp, cirrus_bpp, int, 0400);
 
 /*
  * This is the generic driver code. This binds the driver to the drm core,
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 693a4565c4ff..705061537a27 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -262,4 +262,7 @@ static inline void cirrus_bo_unreserve(struct cirrus_bo *bo)
 
 int cirrus_bo_push_sysram(struct cirrus_bo *bo);
 int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr);
+
+extern int cirrus_bpp;
+
 #endif				/* __CIRRUS_DRV_H__ */
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 4c2d68e9102d..e4b976658087 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -320,6 +320,8 @@ bool cirrus_check_framebuffer(struct cirrus_device *cdev, int width, int height,
 	const int max_pitch = 0x1FF << 3; /* (4096 - 1) & ~111b bytes */
 	const int max_size = cdev->mc.vram_size;
 
+	if (bpp > cirrus_bpp)
+		return false;
 	if (bpp > 32)
 		return false;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 99d4a74ffeaf..61385f2298bf 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -501,8 +501,13 @@ static int cirrus_vga_get_modes(struct drm_connector *connector)
 	int count;
 
 	/* Just add a static list of modes */
-	count = drm_add_modes_noedid(connector, 1280, 1024);
-	drm_set_preferred_mode(connector, 1024, 768);
+	if (cirrus_bpp <= 24) {
+		count = drm_add_modes_noedid(connector, 1280, 1024);
+		drm_set_preferred_mode(connector, 1024, 768);
+	} else {
+		count = drm_add_modes_noedid(connector, 800, 600);
+		drm_set_preferred_mode(connector, 800, 600);
+	}
 	return count;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 9e7f23dd14bd..87d5fb21cb61 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -34,7 +34,8 @@
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
-				    int flag, int n)
+				    int flag, int n,
+				    struct reservation_object *resv)
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
@@ -47,12 +48,12 @@ static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 		case RADEON_BENCHMARK_COPY_DMA:
 			fence = radeon_copy_dma(rdev, saddr, daddr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						resv);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
 			fence = radeon_copy_blit(rdev, saddr, daddr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 resv);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
@@ -120,7 +121,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 
 	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_DMA, n);
+						RADEON_BENCHMARK_COPY_DMA, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
@@ -130,7 +132,8 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 
 	if (rdev->asic->copy.blit) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_BLIT, n);
+						RADEON_BENCHMARK_COPY_BLIT, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 102116902a07..913fafa597ad 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -960,6 +960,9 @@ void radeon_compute_pll_avivo(struct radeon_pll *pll,
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV &&
 	    pll->flags & RADEON_PLL_USE_REF_DIV)
 		ref_div_max = pll->reference_div;
+	else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP)
+		/* fix for problems on RS880 */
+		ref_div_max = min(pll->max_ref_div, 7u);
 	else
 		ref_div_max = pll->max_ref_div;
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index d0b4f7d1140d..ac3c1310b953 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -146,7 +146,8 @@ int radeon_gem_object_open(struct drm_gem_object *obj, struct drm_file *file_pri
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return 0;
 	}
 
@@ -176,7 +177,8 @@ void radeon_gem_object_close(struct drm_gem_object *obj,
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 3cf9c1fa6475..686411e4e4f6 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -605,14 +605,14 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 			return -ENOMEM;
 		}
 
-		vm = &fpriv->vm;
-		r = radeon_vm_init(rdev, vm);
-		if (r) {
-			kfree(fpriv);
-			return r;
-		}
-
 		if (rdev->accel_working) {
+			vm = &fpriv->vm;
+			r = radeon_vm_init(rdev, vm);
+			if (r) {
+				kfree(fpriv);
+				return r;
+			}
+
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
 				radeon_vm_fini(rdev, vm);
@@ -668,9 +668,9 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
+			radeon_vm_fini(rdev, vm);
 		}
 
-		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 07b506b41008..791818165c76 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -119,11 +119,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
 			r = PTR_ERR(fence);
@@ -170,11 +170,11 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
 			r = PTR_ERR(fence);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 06d2246d07f1..2a5a4a9e772d 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -743,9 +743,11 @@ static void radeon_vm_frag_ptes(struct radeon_device *rdev,
 	 */
 
 	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
-	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+	uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ?
 			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
-	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+	uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80;
 
 	uint64_t frag_start = ALIGN(pe_start, frag_align);
 	uint64_t frag_end = pe_end & ~(frag_align - 1);