Merge branch 'drm-fixes-3.7' of git://people.freedesktop.org/~agd5f/linux into drm-fixes

Alex writes:
"Fixes pull request for radeon.  The main things here are
fixing a ATPX regression from the acpi rework, fixing some
fallout from the async VM work, and fixing some module options
that were broken in certain cases.  Other than that, mainly
just bug fixes."

* 'drm-fixes-3.7' of git://people.freedesktop.org/~agd5f/linux:
  drm/radeon: fix ATPX regression in acpi rework
  drm/radeon: fix ATPX function documentation
  drm/radeon: move the retry to gem_object_create
  drm/radeon: move size limits to gem_object_create.
  drm/radeon: use vzalloc for gart pages
  drm/radeon: fix and simplify pot argument checks v3
  drm/radeon: fix header size estimation in VM code
  drm/radeon: remove set_page check from VM code
  drm/radeon: fix si_set_page v2
  drm/radeon: fix cayman_vm_set_page v2
  drm/radeon: fix PFP sync in vm_flush
  drm/radeon: add error output if VM CS fails on cayman
  drm/radeon: give each backlight a unique id
  drm/radeon: fix sparse warning
  drm/radeon: add some new SI PCI ids

11 files changed, 119 insertions, 110 deletions

diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index 49cbb3795a10..ba498f8e47a2 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -184,6 +184,7 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	struct radeon_backlight_privdata *pdata;
 	struct radeon_encoder_atom_dig *dig;
 	u8 backlight_level;
+	char bl_name[16];
 
 	if (!radeon_encoder->enc_priv)
 		return;
@@ -203,7 +204,9 @@ void radeon_atom_backlight_init(struct radeon_encoder *radeon_encoder,
 	memset(&props, 0, sizeof(props));
 	props.max_brightness = RADEON_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
-	bd = backlight_device_register("radeon_bl", &drm_connector->kdev,
+	snprintf(bl_name, sizeof(bl_name),
+		 "radeon_bl%d", dev->primary->index);
+	bd = backlight_device_register(bl_name, &drm_connector->kdev,
 				       pdata, &radeon_atom_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 573ed1bc6cf7..30271b641913 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -2829,6 +2829,7 @@ static bool evergreen_vm_reg_valid(u32 reg)
 	case CAYMAN_SQ_EX_ALLOC_TABLE_SLOTS:
 		return true;
 	default:
+		DRM_ERROR("Invalid register 0x%x in CS\n", reg);
 		return false;
 	}
 }
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8c74c729586d..81e6a568c29d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1538,26 +1538,31 @@ void cayman_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 {
 	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
 	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	int i;
 
-	radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, 1 + count * 2));
-	radeon_ring_write(ring, pe);
-	radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
-	for (i = 0; i < count; ++i) {
-		uint64_t value = 0;
-		if (flags & RADEON_VM_PAGE_SYSTEM) {
-			value = radeon_vm_map_gart(rdev, addr);
-			value &= 0xFFFFFFFFFFFFF000ULL;
-			addr += incr;
-
-		} else if (flags & RADEON_VM_PAGE_VALID) {
-			value = addr;
-			addr += incr;
-		}
+	while (count) {
+		unsigned ndw = 1 + count * 2;
+		if (ndw > 0x3FFF)
+			ndw = 0x3FFF;
+
+		radeon_ring_write(ring, PACKET3(PACKET3_ME_WRITE, ndw));
+		radeon_ring_write(ring, pe);
+		radeon_ring_write(ring, upper_32_bits(pe) & 0xff);
+		for (; ndw > 1; ndw -= 2, --count, pe += 8) {
+			uint64_t value = 0;
+			if (flags & RADEON_VM_PAGE_SYSTEM) {
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
+				addr += incr;
+
+			} else if (flags & RADEON_VM_PAGE_VALID) {
+				value = addr;
+				addr += incr;
+			}
 
-		value |= r600_flags;
-		radeon_ring_write(ring, value);
-		radeon_ring_write(ring, upper_32_bits(value));
+			value |= r600_flags;
+			radeon_ring_write(ring, value);
+			radeon_ring_write(ring, upper_32_bits(value));
+		}
 	}
 }
 
@@ -1586,4 +1591,8 @@ void cayman_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	/* bits 0-7 are the VM contexts0-7 */
 	radeon_ring_write(ring, PACKET0(VM_INVALIDATE_REQUEST, 0));
 	radeon_ring_write(ring, 1 << vm->id);
+
+	/* sync PFP to ME, otherwise we might get invalid PFP reads */
+	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+	radeon_ring_write(ring, 0x0);
 }
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index 2423d1b5d385..cbef6815907a 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -502,6 +502,7 @@
 #define	PACKET3_MPEG_INDEX				0x3A
 #define	PACKET3_WAIT_REG_MEM				0x3C
 #define	PACKET3_MEM_WRITE				0x3D
+#define	PACKET3_PFP_SYNC_ME				0x42
 #define	PACKET3_SURFACE_SYNC				0x43
 #              define PACKET3_CB0_DEST_BASE_ENA    (1 << 6)
 #              define PACKET3_CB1_DEST_BASE_ENA    (1 << 7)
diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
index 1aa3f910b993..37f6a907aea4 100644
--- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c
+++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c
@@ -87,7 +87,7 @@ static union acpi_object *radeon_atpx_call(acpi_handle handle, int function,
 		atpx_arg_elements[1].integer.value = 0;
 	}
 
-	status = acpi_evaluate_object(handle, "ATPX", &atpx_arg, &buffer);
+	status = acpi_evaluate_object(handle, NULL, &atpx_arg, &buffer);
 
 	/* Fail only if calling the method fails and ATPX is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
@@ -373,11 +373,11 @@ static int radeon_atpx_power_state(enum vga_switcheroo_client_id id,
 }
 
 /**
- * radeon_atpx_pci_probe_handle - look up the ATRM and ATPX handles
+ * radeon_atpx_pci_probe_handle - look up the ATPX handle
  *
  * @pdev: pci device
  *
- * Look up the ATPX and ATRM handles (all asics).
+ * Look up the ATPX handles (all asics).
  * Returns true if the handles are found, false if not.
  */
 static bool radeon_atpx_pci_probe_handle(struct pci_dev *pdev)
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index bd13ca09eb62..e2f5f888c374 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -355,6 +355,8 @@ int radeon_wb_init(struct radeon_device *rdev)
  */
 void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64 base)
 {
+	uint64_t limit = (uint64_t)radeon_vram_limit << 20;
+
 	mc->vram_start = base;
 	if (mc->mc_vram_size > (0xFFFFFFFF - base + 1)) {
 		dev_warn(rdev->dev, "limiting VRAM to PCI aperture size\n");
@@ -368,8 +370,8 @@ void radeon_vram_location(struct radeon_device *rdev, struct radeon_mc *mc, u64
 		mc->mc_vram_size = mc->aper_size;
 	}
 	mc->vram_end = mc->vram_start + mc->mc_vram_size - 1;
-	if (radeon_vram_limit && radeon_vram_limit < mc->real_vram_size)
-		mc->real_vram_size = radeon_vram_limit;
+	if (limit && limit < mc->real_vram_size)
+		mc->real_vram_size = limit;
 	dev_info(rdev->dev, "VRAM: %lluM 0x%016llX - 0x%016llX (%lluM used)\n",
 			mc->mc_vram_size >> 20, mc->vram_start,
 			mc->vram_end, mc->real_vram_size >> 20);
@@ -835,6 +837,19 @@ static unsigned int radeon_vga_set_decode(void *cookie, bool state)
 }
 
 /**
+ * radeon_check_pot_argument - check that argument is a power of two
+ *
+ * @arg: value to check
+ *
+ * Validates that a certain argument is a power of two (all asics).
+ * Returns true if argument is valid.
+ */
+static bool radeon_check_pot_argument(int arg)
+{
+	return (arg & (arg - 1)) == 0;
+}
+
+/**
  * radeon_check_arguments - validate module params
  *
  * @rdev: radeon_device pointer
@@ -845,52 +860,25 @@ static unsigned int radeon_vga_set_decode(void *cookie, bool state)
 static void radeon_check_arguments(struct radeon_device *rdev)
 {
 	/* vramlimit must be a power of two */
-	switch (radeon_vram_limit) {
-	case 0:
-	case 4:
-	case 8:
-	case 16:
-	case 32:
-	case 64:
-	case 128:
-	case 256:
-	case 512:
-	case 1024:
-	case 2048:
-	case 4096:
-		break;
-	default:
+	if (!radeon_check_pot_argument(radeon_vram_limit)) {
 		dev_warn(rdev->dev, "vram limit (%d) must be a power of 2\n",
 				radeon_vram_limit);
 		radeon_vram_limit = 0;
-		break;
 	}
-	radeon_vram_limit = radeon_vram_limit << 20;
+
 	/* gtt size must be power of two and greater or equal to 32M */
-	switch (radeon_gart_size) {
-	case 4:
-	case 8:
-	case 16:
+	if (radeon_gart_size < 32) {
 		dev_warn(rdev->dev, "gart size (%d) too small forcing to 512M\n",
 				radeon_gart_size);
 		radeon_gart_size = 512;
-		break;
-	case 32:
-	case 64:
-	case 128:
-	case 256:
-	case 512:
-	case 1024:
-	case 2048:
-	case 4096:
-		break;
-	default:
+
+	} else if (!radeon_check_pot_argument(radeon_gart_size)) {
 		dev_warn(rdev->dev, "gart size (%d) must be a power of 2\n",
 				radeon_gart_size);
 		radeon_gart_size = 512;
-		break;
 	}
-	rdev->mc.gtt_size = radeon_gart_size * 1024 * 1024;
+	rdev->mc.gtt_size = (uint64_t)radeon_gart_size << 20;
+
 	/* AGP mode can only be -1, 1, 2, 4, 8 */
 	switch (radeon_agpmode) {
 	case -1:
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index a7677dd1ce98..4debd60e5aa6 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -355,14 +355,13 @@ int radeon_gart_init(struct radeon_device *rdev)
 	DRM_INFO("GART: num cpu pages %u, num gpu pages %u\n",
 		 rdev->gart.num_cpu_pages, rdev->gart.num_gpu_pages);
 	/* Allocate pages table */
-	rdev->gart.pages = kzalloc(sizeof(void *) * rdev->gart.num_cpu_pages,
-				   GFP_KERNEL);
+	rdev->gart.pages = vzalloc(sizeof(void *) * rdev->gart.num_cpu_pages);
 	if (rdev->gart.pages == NULL) {
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
 	}
-	rdev->gart.pages_addr = kzalloc(sizeof(dma_addr_t) *
-					rdev->gart.num_cpu_pages, GFP_KERNEL);
+	rdev->gart.pages_addr = vzalloc(sizeof(dma_addr_t) *
+					rdev->gart.num_cpu_pages);
 	if (rdev->gart.pages_addr == NULL) {
 		radeon_gart_fini(rdev);
 		return -ENOMEM;
@@ -388,8 +387,8 @@ void radeon_gart_fini(struct radeon_device *rdev)
 		radeon_gart_unbind(rdev, 0, rdev->gart.num_cpu_pages);
 	}
 	rdev->gart.ready = false;
-	kfree(rdev->gart.pages);
-	kfree(rdev->gart.pages_addr);
+	vfree(rdev->gart.pages);
+	vfree(rdev->gart.pages_addr);
 	rdev->gart.pages = NULL;
 	rdev->gart.pages_addr = NULL;
 
@@ -577,7 +576,7 @@ void radeon_vm_manager_fini(struct radeon_device *rdev)
  *
  * Global and local mutex must be locked!
  */
-int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm)
+static int radeon_vm_evict(struct radeon_device *rdev, struct radeon_vm *vm)
 {
 	struct radeon_vm *vm_evict;
 
@@ -1036,8 +1035,7 @@ static void radeon_vm_update_ptes(struct radeon_device *rdev,
 		pte = radeon_sa_bo_gpu_addr(vm->page_tables[pt_idx]);
 		pte += (addr & mask) * 8;
 
-		if (((last_pte + 8 * count) != pte) ||
-		    ((count + nptes) > 1 << 11)) {
+		if ((last_pte + 8 * count) != pte) {
 
 			if (count) {
 				radeon_asic_vm_set_page(rdev, last_pte,
@@ -1148,17 +1146,17 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 
 	if (RADEON_VM_BLOCK_SIZE > 11)
 		/* reserve space for one header for every 2k dwords */
-		ndw += (nptes >> 11) * 3;
+		ndw += (nptes >> 11) * 4;
 	else
 		/* reserve space for one header for
 		    every (1 << BLOCK_SIZE) entries */
-		ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 3;
+		ndw += (nptes >> RADEON_VM_BLOCK_SIZE) * 4;
 
 	/* reserve space for pte addresses */
 	ndw += nptes * 2;
 
 	/* reserve space for one header for every 2k dwords */
-	ndw += (npdes >> 11) * 3;
+	ndw += (npdes >> 11) * 4;
 
 	/* reserve space for pde addresses */
 	ndw += npdes * 2;
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index f38fbcc46935..fe5c1f6b7957 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -53,6 +53,7 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size,
 				struct drm_gem_object **obj)
 {
 	struct radeon_bo *robj;
+	unsigned long max_size;
 	int r;
 
 	*obj = NULL;
@@ -60,11 +61,26 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size,
 	if (alignment < PAGE_SIZE) {
 		alignment = PAGE_SIZE;
 	}
+
+	/* maximun bo size is the minimun btw visible vram and gtt size */
+	max_size = min(rdev->mc.visible_vram_size, rdev->mc.gtt_size);
+	if (size > max_size) {
+		printk(KERN_WARNING "%s:%d alloc size %dMb bigger than %ldMb limit\n",
+		       __func__, __LINE__, size >> 20, max_size >> 20);
+		return -ENOMEM;
+	}
+
+retry:
 	r = radeon_bo_create(rdev, size, alignment, kernel, initial_domain, NULL, &robj);
 	if (r) {
-		if (r != -ERESTARTSYS)
+		if (r != -ERESTARTSYS) {
+			if (initial_domain == RADEON_GEM_DOMAIN_VRAM) {
+				initial_domain |= RADEON_GEM_DOMAIN_GTT;
+				goto retry;
+			}
 			DRM_ERROR("Failed to allocate GEM object (%d, %d, %u, %d)\n",
 				  size, initial_domain, alignment, r);
+		}
 		return r;
 	}
 	*obj = &robj->gem_base;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
index a13ad9d707cf..0063df9d166d 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_encoders.c
@@ -370,6 +370,7 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 	struct backlight_properties props;
 	struct radeon_backlight_privdata *pdata;
 	uint8_t backlight_level;
+	char bl_name[16];
 
 	if (!radeon_encoder->enc_priv)
 		return;
@@ -389,7 +390,9 @@ void radeon_legacy_backlight_init(struct radeon_encoder *radeon_encoder,
 	memset(&props, 0, sizeof(props));
 	props.max_brightness = RADEON_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
-	bd = backlight_device_register("radeon_bl", &drm_connector->kdev,
+	snprintf(bl_name, sizeof(bl_name),
+		 "radeon_bl%d", dev->primary->index);
+	bd = backlight_device_register(bl_name, &drm_connector->kdev,
 				       pdata, &radeon_backlight_ops, &props);
 	if (IS_ERR(bd)) {
 		DRM_ERROR("Backlight registration failed\n");
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 8b27dd6e3144..b91118ccef86 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -105,7 +105,6 @@ int radeon_bo_create(struct radeon_device *rdev,
 	struct radeon_bo *bo;
 	enum ttm_bo_type type;
 	unsigned long page_align = roundup(byte_align, PAGE_SIZE) >> PAGE_SHIFT;
-	unsigned long max_size = 0;
 	size_t acc_size;
 	int r;
 
@@ -121,18 +120,9 @@ int radeon_bo_create(struct radeon_device *rdev,
 	}
 	*bo_ptr = NULL;
 
-	/* maximun bo size is the minimun btw visible vram and gtt size */
-	max_size = min(rdev->mc.visible_vram_size, rdev->mc.gtt_size);
-	if ((page_align << PAGE_SHIFT) >= max_size) {
-		printk(KERN_WARNING "%s:%d alloc size %ldM bigger than %ldMb limit\n",
-			__func__, __LINE__, page_align  >> (20 - PAGE_SHIFT), max_size >> 20);
-		return -ENOMEM;
-	}
-
 	acc_size = ttm_bo_dma_acc_size(&rdev->mman.bdev, size,
 				       sizeof(struct radeon_bo));
 
-retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
@@ -154,15 +144,6 @@ retry:
 			acc_size, sg, &radeon_ttm_bo_destroy);
 	up_read(&rdev->pm.mclk_lock);
 	if (unlikely(r != 0)) {
-		if (r != -ERESTARTSYS) {
-			if (domain == RADEON_GEM_DOMAIN_VRAM) {
-				domain |= RADEON_GEM_DOMAIN_GTT;
-				goto retry;
-			}
-			dev_err(rdev->dev,
-				"object_init failed for (%lu, 0x%08X)\n",
-				size, domain);
-		}
 		return r;
 	}
 	*bo_ptr = bo;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index df8dd7701643..b0db712060fb 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -2808,26 +2808,31 @@ void si_vm_set_page(struct radeon_device *rdev, uint64_t pe,
 {
 	struct radeon_ring *ring = &rdev->ring[rdev->asic->vm.pt_ring_index];
 	uint32_t r600_flags = cayman_vm_page_flags(rdev, flags);
-	int i;
-	uint64_t value;
 
-	radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 2 + count * 2));
-	radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
-				 WRITE_DATA_DST_SEL(1)));
-	radeon_ring_write(ring, pe);
-	radeon_ring_write(ring, upper_32_bits(pe));
-	for (i = 0; i < count; ++i) {
-		if (flags & RADEON_VM_PAGE_SYSTEM) {
-			value = radeon_vm_map_gart(rdev, addr);
-			value &= 0xFFFFFFFFFFFFF000ULL;
-		} else if (flags & RADEON_VM_PAGE_VALID)
-			value = addr;
-		else
-			value = 0;
-		addr += incr;
-		value |= r600_flags;
-		radeon_ring_write(ring, value);
-		radeon_ring_write(ring, upper_32_bits(value));
+	while (count) {
+		unsigned ndw = 2 + count * 2;
+		if (ndw > 0x3FFE)
+			ndw = 0x3FFE;
+
+		radeon_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, ndw));
+		radeon_ring_write(ring, (WRITE_DATA_ENGINE_SEL(0) |
+					 WRITE_DATA_DST_SEL(1)));
+		radeon_ring_write(ring, pe);
+		radeon_ring_write(ring, upper_32_bits(pe));
+		for (; ndw > 2; ndw -= 2, --count, pe += 8) {
+			uint64_t value;
+			if (flags & RADEON_VM_PAGE_SYSTEM) {
+				value = radeon_vm_map_gart(rdev, addr);
+				value &= 0xFFFFFFFFFFFFF000ULL;
+			} else if (flags & RADEON_VM_PAGE_VALID)
+				value = addr;
+			else
+				value = 0;
+			addr += incr;
+			value |= r600_flags;
+			radeon_ring_write(ring, value);
+			radeon_ring_write(ring, upper_32_bits(value));
+		}
 	}
 }
 
@@ -2868,6 +2873,10 @@ void si_vm_flush(struct radeon_device *rdev, int ridx, struct radeon_vm *vm)
 	radeon_ring_write(ring, VM_INVALIDATE_REQUEST >> 2);
 	radeon_ring_write(ring, 0);
 	radeon_ring_write(ring, 1 << vm->id);
+
+	/* sync PFP to ME, otherwise we might get invalid PFP reads */
+	radeon_ring_write(ring, PACKET3(PACKET3_PFP_SYNC_ME, 0));
+	radeon_ring_write(ring, 0x0);
 }
 
 /*