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

Pull drm fixes from Dave Airlie:
 "You'll be terribly disappointed in this, I'm not trying to sneak any
  features in or anything, its mostly radeon and intel fixes, a couple
  of ARM driver fixes"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (34 commits)
  drm/radeon/dpm: add debugfs support for RS780/RS880 (v3)
  drm/radeon/dpm/atom: fix broken gcc harder
  drm/radeon/dpm/atom: restructure logic to work around a compiler bug
  drm/radeon/dpm: fix atom vram table parsing
  drm/radeon: fix an endian bug in atom table parsing
  drm/radeon: add a module parameter to disable aspm
  drm/rcar-du: Use the GEM PRIME helpers
  drm/shmobile: Use the GEM PRIME helpers
  uvesafb: Really allow mtrr being 0, as documented and warn()ed
  radeon kms: do not flush uninitialized hotplug work
  drm/radeon/dpm/sumo: handle boost states properly when forcing a perf level
  drm/radeon: align VM PTBs (Page Table Blocks) to 32K
  drm/radeon: allow selection of alignment in the sub-allocator
  drm/radeon: never unpin UVD bo v3
  drm/radeon: fix UVD fence emit
  drm/radeon: add fault decode function for CIK
  drm/radeon: add fault decode function for SI (v2)
  drm/radeon: add fault decode function for cayman/TN (v2)
  drm/radeon: use radeon device for request firmware
  drm/radeon: add missing ttm_eu_backoff_reservation to radeon_bo_list_validate
  ...

39 files changed, 918 insertions, 277 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 062cbda..f4af1ca 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -123,10 +123,10 @@ module_param_named(preliminary_hw_support, i915_preliminary_hw_support, int, 060
 MODULE_PARM_DESC(preliminary_hw_support,
 		"Enable preliminary hardware support. (default: false)");
 
-int i915_disable_power_well __read_mostly = 0;
+int i915_disable_power_well __read_mostly = 1;
 module_param_named(disable_power_well, i915_disable_power_well, int, 0600);
 MODULE_PARM_DESC(disable_power_well,
-		 "Disable the power well when possible (default: false)");
+		 "Disable the power well when possible (default: true)");
 
 int i915_enable_ips __read_mostly = 1;
 module_param_named(enable_ips, i915_enable_ips, int, 0600);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4200c32..97afd26 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1880,6 +1880,10 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	u32 seqno = intel_ring_get_seqno(ring);
 
 	BUG_ON(ring == NULL);
+	if (obj->ring != ring && obj->last_write_seqno) {
+		/* Keep the seqno relative to the current ring */
+		obj->last_write_seqno = seqno;
+	}
 	obj->ring = ring;
 
 	/* Add a reference if we're newly entering the active list. */
@@ -2653,7 +2657,6 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	int fence_reg;
 	int fence_pitch_shift;
-	uint64_t val;
 
 	if (INTEL_INFO(dev)->gen >= 6) {
 		fence_reg = FENCE_REG_SANDYBRIDGE_0;
@@ -2663,8 +2666,23 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 		fence_pitch_shift = I965_FENCE_PITCH_SHIFT;
 	}
 
+	fence_reg += reg * 8;
+
+	/* To w/a incoherency with non-atomic 64-bit register updates,
+	 * we split the 64-bit update into two 32-bit writes. In order
+	 * for a partial fence not to be evaluated between writes, we
+	 * precede the update with write to turn off the fence register,
+	 * and only enable the fence as the last step.
+	 *
+	 * For extra levels of paranoia, we make sure each step lands
+	 * before applying the next step.
+	 */
+	I915_WRITE(fence_reg, 0);
+	POSTING_READ(fence_reg);
+
 	if (obj) {
 		u32 size = obj->gtt_space->size;
+		uint64_t val;
 
 		val = (uint64_t)((obj->gtt_offset + size - 4096) &
 				 0xfffff000) << 32;
@@ -2673,12 +2691,16 @@ static void i965_write_fence_reg(struct drm_device *dev, int reg,
 		if (obj->tiling_mode == I915_TILING_Y)
 			val |= 1 << I965_FENCE_TILING_Y_SHIFT;
 		val |= I965_FENCE_REG_VALID;
-	} else
-		val = 0;
 
-	fence_reg += reg * 8;
-	I915_WRITE64(fence_reg, val);
-	POSTING_READ(fence_reg);
+		I915_WRITE(fence_reg + 4, val >> 32);
+		POSTING_READ(fence_reg + 4);
+
+		I915_WRITE(fence_reg + 0, val);
+		POSTING_READ(fence_reg);
+	} else {
+		I915_WRITE(fence_reg + 4, 0);
+		POSTING_READ(fence_reg + 4);
+	}
 }
 
 static void i915_write_fence_reg(struct drm_device *dev, int reg,
@@ -2796,56 +2818,17 @@ static inline int fence_number(struct drm_i915_private *dev_priv,
 	return fence - dev_priv->fence_regs;
 }
 
-struct write_fence {
-	struct drm_device *dev;
-	struct drm_i915_gem_object *obj;
-	int fence;
-};
-
-static void i915_gem_write_fence__ipi(void *data)
-{
-	struct write_fence *args = data;
-
-	/* Required for SNB+ with LLC */
-	wbinvd();
-
-	/* Required for VLV */
-	i915_gem_write_fence(args->dev, args->fence, args->obj);
-}
-
 static void i915_gem_object_update_fence(struct drm_i915_gem_object *obj,
 					 struct drm_i915_fence_reg *fence,
 					 bool enable)
 {
 	struct drm_i915_private *dev_priv = obj->base.dev->dev_private;
-	struct write_fence args = {
-		.dev = obj->base.dev,
-		.fence = fence_number(dev_priv, fence),
-		.obj = enable ? obj : NULL,
-	};
-
-	/* In order to fully serialize access to the fenced region and
-	 * the update to the fence register we need to take extreme
-	 * measures on SNB+. In theory, the write to the fence register
-	 * flushes all memory transactions before, and coupled with the
-	 * mb() placed around the register write we serialise all memory
-	 * operations with respect to the changes in the tiler. Yet, on
-	 * SNB+ we need to take a step further and emit an explicit wbinvd()
-	 * on each processor in order to manually flush all memory
-	 * transactions before updating the fence register.
-	 *
-	 * However, Valleyview complicates matter. There the wbinvd is
-	 * insufficient and unlike SNB/IVB requires the serialising
-	 * register write. (Note that that register write by itself is
-	 * conversely not sufficient for SNB+.) To compromise, we do both.
-	 */
-	if (INTEL_INFO(args.dev)->gen >= 6)
-		on_each_cpu(i915_gem_write_fence__ipi, &args, 1);
-	else
-		i915_gem_write_fence(args.dev, args.fence, args.obj);
+	int reg = fence_number(dev_priv, fence);
+
+	i915_gem_write_fence(obj->base.dev, reg, enable ? obj : NULL);
 
 	if (enable) {
-		obj->fence_reg = args.fence;
+		obj->fence_reg = reg;
 		fence->obj = obj;
 		list_move_tail(&fence->lru_list, &dev_priv->mm.fence_list);
 	} else {
@@ -4611,7 +4594,7 @@ i915_gem_inactive_shrink(struct shrinker *shrinker, struct shrink_control *sc)
 	list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_list)
 		if (obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;
-	list_for_each_entry(obj, &dev_priv->mm.inactive_list, global_list)
+	list_for_each_entry(obj, &dev_priv->mm.inactive_list, mm_list)
 		if (obj->pin_count == 0 && obj->pages_pin_count == 0)
 			cnt += obj->base.size >> PAGE_SHIFT;
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index b739712..26e162b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -75,7 +75,12 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp)
 	case DP_LINK_BW_1_62:
 	case DP_LINK_BW_2_7:
 		break;
+	case DP_LINK_BW_5_4: /* 1.2 capable displays may advertise higher bw */
+		max_link_bw = DP_LINK_BW_2_7;
+		break;
 	default:
+		WARN(1, "invalid max DP link bw val %x, using 1.62Gbps\n",
+		     max_link_bw);
 		max_link_bw = DP_LINK_BW_1_62;
 		break;
 	}
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index ccbdd83..d10e673 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5500,9 +5500,38 @@ void intel_gt_init(struct drm_device *dev)
 	if (IS_VALLEYVIEW(dev)) {
 		dev_priv->gt.force_wake_get = vlv_force_wake_get;
 		dev_priv->gt.force_wake_put = vlv_force_wake_put;
-	} else if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
+	} else if (IS_HASWELL(dev)) {
 		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_mt_get;
 		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_mt_put;
+	} else if (IS_IVYBRIDGE(dev)) {
+		u32 ecobus;
+
+		/* IVB configs may use multi-threaded forcewake */
+
+		/* A small trick here - if the bios hasn't configured
+		 * MT forcewake, and if the device is in RC6, then
+		 * force_wake_mt_get will not wake the device and the
+		 * ECOBUS read will return zero. Which will be
+		 * (correctly) interpreted by the test below as MT
+		 * forcewake being disabled.
+		 */
+		mutex_lock(&dev->struct_mutex);
+		__gen6_gt_force_wake_mt_get(dev_priv);
+		ecobus = I915_READ_NOTRACE(ECOBUS);
+		__gen6_gt_force_wake_mt_put(dev_priv);
+		mutex_unlock(&dev->struct_mutex);
+
+		if (ecobus & FORCEWAKE_MT_ENABLE) {
+			dev_priv->gt.force_wake_get =
+						__gen6_gt_force_wake_mt_get;
+			dev_priv->gt.force_wake_put =
+						__gen6_gt_force_wake_mt_put;
+		} else {
+			DRM_INFO("No MT forcewake available on Ivybridge, this can result in issues\n");
+			DRM_INFO("when using vblank-synced partial screen updates.\n");
+			dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
+			dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
+		}
 	} else if (IS_GEN6(dev)) {
 		dev_priv->gt.force_wake_get = __gen6_gt_force_wake_get;
 		dev_priv->gt.force_wake_put = __gen6_gt_force_wake_put;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e51ab55..664118d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -379,6 +379,17 @@ u32 intel_ring_get_active_head(struct intel_ring_buffer *ring)
 	return I915_READ(acthd_reg);
 }
 
+static void ring_setup_phys_status_page(struct intel_ring_buffer *ring)
+{
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+	u32 addr;
+
+	addr = dev_priv->status_page_dmah->busaddr;
+	if (INTEL_INFO(ring->dev)->gen >= 4)
+		addr |= (dev_priv->status_page_dmah->busaddr >> 28) & 0xf0;
+	I915_WRITE(HWS_PGA, addr);
+}
+
 static int init_ring_common(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -390,6 +401,11 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	if (HAS_FORCE_WAKE(dev))
 		gen6_gt_force_wake_get(dev_priv);
 
+	if (I915_NEED_GFX_HWS(dev))
+		intel_ring_setup_status_page(ring);
+	else
+		ring_setup_phys_status_page(ring);
+
 	/* Stop the ring if it's running. */
 	I915_WRITE_CTL(ring, 0);
 	I915_WRITE_HEAD(ring, 0);
@@ -518,9 +534,6 @@ cleanup_pipe_control(struct intel_ring_buffer *ring)
 	struct pipe_control *pc = ring->private;
 	struct drm_i915_gem_object *obj;
 
-	if (!ring->private)
-		return;
-
 	obj = pc->obj;
 
 	kunmap(sg_page(obj->pages->sgl));
@@ -528,7 +541,6 @@ cleanup_pipe_control(struct intel_ring_buffer *ring)
 	drm_gem_object_unreference(&obj->base);
 
 	kfree(pc);
-	ring->private = NULL;
 }
 
 static int init_render_ring(struct intel_ring_buffer *ring)
@@ -601,7 +613,10 @@ static void render_ring_cleanup(struct intel_ring_buffer *ring)
 	if (HAS_BROKEN_CS_TLB(dev))
 		drm_gem_object_unreference(to_gem_object(ring->private));
 
-	cleanup_pipe_control(ring);
+	if (INTEL_INFO(dev)->gen >= 5)
+		cleanup_pipe_control(ring);
+
+	ring->private = NULL;
 }
 
 static void
@@ -1223,7 +1238,6 @@ static int init_status_page(struct intel_ring_buffer *ring)
 	ring->status_page.obj = obj;
 	memset(ring->status_page.page_addr, 0, PAGE_SIZE);
 
-	intel_ring_setup_status_page(ring);
 	DRM_DEBUG_DRIVER("%s hws offset: 0x%08x\n",
 			ring->name, ring->status_page.gfx_addr);
 
@@ -1237,10 +1251,9 @@ err:
 	return ret;
 }
 
-static int init_phys_hws_pga(struct intel_ring_buffer *ring)
+static int init_phys_status_page(struct intel_ring_buffer *ring)
 {
 	struct drm_i915_private *dev_priv = ring->dev->dev_private;
-	u32 addr;
 
 	if (!dev_priv->status_page_dmah) {
 		dev_priv->status_page_dmah =
@@ -1249,11 +1262,6 @@ static int init_phys_hws_pga(struct intel_ring_buffer *ring)
 			return -ENOMEM;
 	}
 
-	addr = dev_priv->status_page_dmah->busaddr;
-	if (INTEL_INFO(ring->dev)->gen >= 4)
-		addr |= (dev_priv->status_page_dmah->busaddr >> 28) & 0xf0;
-	I915_WRITE(HWS_PGA, addr);
-
 	ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
 	memset(ring->status_page.page_addr, 0, PAGE_SIZE);
 
@@ -1281,7 +1289,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 			return ret;
 	} else {
 		BUG_ON(ring->id != RCS);
-		ret = init_phys_hws_pga(ring);
+		ret = init_phys_status_page(ring);
 		if (ret)
 			return ret;
 	}
@@ -1893,7 +1901,7 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	}
 
 	if (!I915_NEED_GFX_HWS(dev)) {
-		ret = init_phys_hws_pga(ring);
+		ret = init_phys_status_page(ring);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index ed1d910..6dacec4 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -22,7 +22,6 @@
  * Authors: Alex Deucher
  */
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include "drmP.h"
@@ -742,7 +741,6 @@ static int ci_mc_load_microcode(struct radeon_device *rdev)
  */
 static int cik_init_microcode(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
 	const char *chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size,
 		mec_req_size, rlc_req_size, mc_req_size,
@@ -752,13 +750,6 @@ static int cik_init_microcode(struct radeon_device *rdev)
 
 	DRM_DEBUG("\n");
 
-	pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
-	err = IS_ERR(pdev);
-	if (err) {
-		printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
-		return -EINVAL;
-	}
-
 	switch (rdev->family) {
 	case CHIP_BONAIRE:
 		chip_name = "BONAIRE";
@@ -794,7 +785,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	DRM_INFO("Loading %s Microcode\n", chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
-	err = request_firmware(&rdev->pfp_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->pfp_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->pfp_fw->size != pfp_req_size) {
@@ -806,7 +797,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
-	err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->me_fw->size != me_req_size) {
@@ -817,7 +808,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
-	err = request_firmware(&rdev->ce_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->ce_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->ce_fw->size != ce_req_size) {
@@ -828,7 +819,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec.bin", chip_name);
-	err = request_firmware(&rdev->mec_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->mec_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->mec_fw->size != mec_req_size) {
@@ -839,7 +830,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
-	err = request_firmware(&rdev->rlc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->rlc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->rlc_fw->size != rlc_req_size) {
@@ -850,7 +841,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
-	err = request_firmware(&rdev->sdma_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->sdma_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->sdma_fw->size != sdma_req_size) {
@@ -863,7 +854,7 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	/* No MC ucode on APUs */
 	if (!(rdev->flags & RADEON_IS_IGP)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
-		err = request_firmware(&rdev->mc_fw, fw_name, &pdev->dev);
+		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 		if (err)
 			goto out;
 		if (rdev->mc_fw->size != mc_req_size) {
@@ -875,8 +866,6 @@ static int cik_init_microcode(struct radeon_device *rdev)
 	}
 
 out:
-	platform_device_unregister(pdev);
-
 	if (err) {
 		if (err != -EINVAL)
 			printk(KERN_ERR
@@ -4453,6 +4442,29 @@ void cik_vm_fini(struct radeon_device *rdev)
 }
 
 /**
+ * cik_vm_decode_fault - print human readable fault info
+ *
+ * @rdev: radeon_device pointer
+ * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value
+ * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value
+ *
+ * Print human readable fault information (CIK).
+ */
+static void cik_vm_decode_fault(struct radeon_device *rdev,
+				u32 status, u32 addr, u32 mc_client)
+{
+	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
+	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
+	char *block = (char *)&mc_client;
+
+	printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+	       protections, vmid, addr,
+	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
+	       block, mc_id);
+}
+
+/**
  * cik_vm_flush - cik vm flush using the CP
  *
  * @rdev: radeon_device pointer
@@ -5507,6 +5519,7 @@ int cik_irq_process(struct radeon_device *rdev)
 	u32 ring_index;
 	bool queue_hotplug = false;
 	bool queue_reset = false;
+	u32 addr, status, mc_client;
 
 	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
@@ -5742,11 +5755,15 @@ restart_ih:
 			break;
 		case 146:
 		case 147:
+			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
+			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
+			mc_client = RREG32(VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT);
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR));
+				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
+				status);
+			cik_vm_decode_fault(rdev, status, addr, mc_client);
 			/* reset addr and status */
 			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
@@ -6961,7 +6978,7 @@ int cik_uvd_resume(struct radeon_device *rdev)
 
 	/* programm the VCPU memory controller bits 0-27 */
 	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd.fw_size + 4) >> 3;
 	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(UVD_VCPU_CACHE_SIZE0, size);
 
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 63514b9..7e9275e 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -136,6 +136,22 @@
 #define VM_INVALIDATE_RESPONSE				0x147c
 
 #define	VM_CONTEXT1_PROTECTION_FAULT_STATUS		0x14DC
+#define		PROTECTIONS_MASK			(0xf << 0)
+#define		PROTECTIONS_SHIFT			0
+		/* bit 0: range
+		 * bit 1: pde0
+		 * bit 2: valid
+		 * bit 3: read
+		 * bit 4: write
+		 */
+#define		MEMORY_CLIENT_ID_MASK			(0xff << 12)
+#define		MEMORY_CLIENT_ID_SHIFT			12
+#define		MEMORY_CLIENT_RW_MASK			(1 << 24)
+#define		MEMORY_CLIENT_RW_SHIFT			24
+#define		FAULT_VMID_MASK				(0xf << 25)
+#define		FAULT_VMID_SHIFT			25
+
+#define	VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT		0x14E4
 
 #define	VM_CONTEXT1_PROTECTION_FAULT_ADDR		0x14FC
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e49059d..038dcac 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -139,6 +139,8 @@ void evergreen_pcie_gen2_enable(struct radeon_device *rdev);
 void evergreen_program_aspm(struct radeon_device *rdev);
 extern void cayman_cp_int_cntl_setup(struct radeon_device *rdev,
 				     int ring, u32 cp_int_cntl);
+extern void cayman_vm_decode_fault(struct radeon_device *rdev,
+				   u32 status, u32 addr);
 
 static const u32 evergreen_golden_registers[] =
 {
@@ -4586,6 +4588,7 @@ int evergreen_irq_process(struct radeon_device *rdev)
 	bool queue_hotplug = false;
 	bool queue_hdmi = false;
 	bool queue_thermal = false;
+	u32 status, addr;
 
 	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
@@ -4872,11 +4875,14 @@ restart_ih:
 			break;
 		case 146:
 		case 147:
+			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
+			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR));
+				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
+				status);
+			cayman_vm_decode_fault(rdev, status, addr);
 			/* reset addr and status */
 			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
@@ -5509,6 +5515,9 @@ void evergreen_program_aspm(struct radeon_device *rdev)
 	 */
 	bool fusion_platform = false;
 
+	if (radeon_aspm == 0)
+		return;
+
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index b9c6f76..b0d3fb3 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -177,6 +177,9 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	uint32_t offset;
 	ssize_t err;
 
+	if (!dig || !dig->afmt)
+		return;
+
 	/* Silent, r600_hdmi_enable will raise WARN for us */
 	if (!dig->afmt->enabled)
 		return;
@@ -280,6 +283,9 @@ void evergreen_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 
+	if (!dig || !dig->afmt)
+		return;
+
 	/* Silent, r600_hdmi_enable will raise WARN for us */
 	if (enable && dig->afmt->enabled)
 		return;
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index f30127c..56bd4f3 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -22,7 +22,6 @@
  * Authors: Alex Deucher
  */
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <drm/drmP.h>
@@ -684,7 +683,6 @@ int ni_mc_load_microcode(struct radeon_device *rdev)
 
 int ni_init_microcode(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
 	const char *chip_name;
 	const char *rlc_chip_name;
 	size_t pfp_req_size, me_req_size, rlc_req_size, mc_req_size;
@@ -694,13 +692,6 @@ int ni_init_microcode(struct radeon_device *rdev)
 
 	DRM_DEBUG("\n");
 
-	pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
-	err = IS_ERR(pdev);
-	if (err) {
-		printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
-		return -EINVAL;
-	}
-
 	switch (rdev->family) {
 	case CHIP_BARTS:
 		chip_name = "BARTS";
@@ -753,7 +744,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 	DRM_INFO("Loading %s Microcode\n", chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
-	err = request_firmware(&rdev->pfp_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->pfp_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->pfp_fw->size != pfp_req_size) {
@@ -765,7 +756,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
-	err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->me_fw->size != me_req_size) {
@@ -776,7 +767,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", rlc_chip_name);
-	err = request_firmware(&rdev->rlc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->rlc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->rlc_fw->size != rlc_req_size) {
@@ -789,7 +780,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 	/* no MC ucode on TN */
 	if (!(rdev->flags & RADEON_IS_IGP)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
-		err = request_firmware(&rdev->mc_fw, fw_name, &pdev->dev);
+		err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 		if (err)
 			goto out;
 		if (rdev->mc_fw->size != mc_req_size) {
@@ -802,7 +793,7 @@ int ni_init_microcode(struct radeon_device *rdev)
 
 	if ((rdev->family >= CHIP_BARTS) && (rdev->family <= CHIP_CAYMAN)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
-		err = request_firmware(&rdev->smc_fw, fw_name, &pdev->dev);
+		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
 		if (err)
 			goto out;
 		if (rdev->smc_fw->size != smc_req_size) {
@@ -814,8 +805,6 @@ int ni_init_microcode(struct radeon_device *rdev)
 	}
 
 out:
-	platform_device_unregister(pdev);
-
 	if (err) {
 		if (err != -EINVAL)
 			printk(KERN_ERR
@@ -2461,6 +2450,167 @@ void cayman_vm_fini(struct radeon_device *rdev)
 {
 }
 
+/**
+ * cayman_vm_decode_fault - print human readable fault info
+ *
+ * @rdev: radeon_device pointer
+ * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value
+ * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value
+ *
+ * Print human readable fault information (cayman/TN).
+ */
+void cayman_vm_decode_fault(struct radeon_device *rdev,
+			    u32 status, u32 addr)
+{
+	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
+	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
+	char *block;
+
+	switch (mc_id) {
+	case 32:
+	case 16:
+	case 96:
+	case 80:
+	case 160:
+	case 144:
+	case 224:
+	case 208:
+		block = "CB";
+		break;
+	case 33:
+	case 17:
+	case 97:
+	case 81:
+	case 161:
+	case 145:
+	case 225:
+	case 209:
+		block = "CB_FMASK";
+		break;
+	case 34:
+	case 18:
+	case 98:
+	case 82:
+	case 162:
+	case 146:
+	case 226:
+	case 210:
+		block = "CB_CMASK";
+		break;
+	case 35:
+	case 19:
+	case 99:
+	case 83:
+	case 163:
+	case 147:
+	case 227:
+	case 211:
+		block = "CB_IMMED";
+		break;
+	case 36:
+	case 20:
+	case 100:
+	case 84:
+	case 164:
+	case 148:
+	case 228:
+	case 212:
+		block = "DB";
+		break;
+	case 37:
+	case 21:
+	case 101:
+	case 85:
+	case 165:
+	case 149:
+	case 229:
+	case 213:
+		block = "DB_HTILE";
+		break;
+	case 38:
+	case 22:
+	case 102:
+	case 86:
+	case 166:
+	case 150:
+	case 230:
+	case 214:
+		block = "SX";
+		break;
+	case 39:
+	case 23:
+	case 103:
+	case 87:
+	case 167:
+	case 151:
+	case 231:
+	case 215:
+		block = "DB_STEN";
+		break;
+	case 40:
+	case 24:
+	case 104:
+	case 88:
+	case 232:
+	case 216:
+	case 168:
+	case 152:
+		block = "TC_TFETCH";
+		break;
+	case 41:
+	case 25:
+	case 105:
+	case 89:
+	case 233:
+	case 217:
+	case 169:
+	case 153:
+		block = "TC_VFETCH";
+		break;
+	case 42:
+	case 26:
+	case 106:
+	case 90:
+	case 234:
+	case 218:
+	case 170:
+	case 154:
+		block = "VC";
+		break;
+	case 112:
+		block = "CP";
+		break;
+	case 113:
+	case 114:
+		block = "SH";
+		break;
+	case 115:
+		block = "VGT";
+		break;
+	case 178:
+		block = "IH";
+		break;
+	case 51:
+		block = "RLC";
+		break;
+	case 55:
+		block = "DMA";
+		break;
+	case 56:
+		block = "HDP";
+		break;
+	default:
+		block = "unknown";
+		break;
+	}
+
+	printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+	       protections, vmid, addr,
+	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
+	       block, mc_id);
+}
+
 #define R600_ENTRY_VALID   (1 << 0)
 #define R600_PTE_SYSTEM    (1 << 1)
 #define R600_PTE_SNOOPED   (1 << 2)
diff --git a/drivers/gpu/drm/radeon/nid.h b/drivers/gpu/drm/radeon/nid.h
index fe24a93..22421bc 100644
--- a/drivers/gpu/drm/radeon/nid.h
+++ b/drivers/gpu/drm/radeon/nid.h
@@ -133,6 +133,22 @@
 #define VM_CONTEXT1_CNTL2				0x1434
 #define VM_INVALIDATE_REQUEST				0x1478
 #define VM_INVALIDATE_RESPONSE				0x147c
+#define	VM_CONTEXT1_PROTECTION_FAULT_ADDR		0x14FC
+#define	VM_CONTEXT1_PROTECTION_FAULT_STATUS		0x14DC
+#define		PROTECTIONS_MASK			(0xf << 0)
+#define		PROTECTIONS_SHIFT			0
+		/* bit 0: range
+		 * bit 2: pde0
+		 * bit 3: valid
+		 * bit 4: read
+		 * bit 5: write
+		 */
+#define		MEMORY_CLIENT_ID_MASK			(0xff << 12)
+#define		MEMORY_CLIENT_ID_SHIFT			12
+#define		MEMORY_CLIENT_RW_MASK			(1 << 24)
+#define		MEMORY_CLIENT_RW_SHIFT			24
+#define		FAULT_VMID_MASK				(0x7 << 25)
+#define		FAULT_VMID_SHIFT			25
 #define VM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR	0x1518
 #define VM_CONTEXT1_PROTECTION_FAULT_DEFAULT_ADDR	0x151c
 #define	VM_CONTEXT0_PAGE_TABLE_BASE_ADDR		0x153C
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index c9affef..75349cd 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -39,7 +39,6 @@
 #include "atom.h"
 
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/module.h>
 
 #include "r100_reg_safe.h"
@@ -989,18 +988,11 @@ void r100_ring_start(struct radeon_device *rdev, struct radeon_ring *ring)
 /* Load the microcode for the CP */
 static int r100_cp_init_microcode(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
 	const char *fw_name = NULL;
 	int err;
 
 	DRM_DEBUG_KMS("\n");
 
-	pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
-	err = IS_ERR(pdev);
-	if (err) {
-		printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
-		return -EINVAL;
-	}
 	if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) ||
 	    (rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) ||
 	    (rdev->family == CHIP_RS200)) {
@@ -1042,8 +1034,7 @@ static int r100_cp_init_microcode(struct radeon_device *rdev)
 		fw_name = FIRMWARE_R520;
 	}
 
-	err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
-	platform_device_unregister(pdev);
+	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
 	if (err) {
 		printk(KERN_ERR "radeon_cp: Failed to load firmware \"%s\"\n",
 		       fw_name);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 2d3655f..393880a 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <linux/seq_file.h>
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/module.h>
 #include <drm/drmP.h>
 #include <drm/radeon_drm.h>
@@ -2144,7 +2143,6 @@ void r600_cp_stop(struct radeon_device *rdev)
 
 int r600_init_microcode(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
 	const char *chip_name;
 	const char *rlc_chip_name;
 	const char *smc_chip_name = "RV770";
@@ -2154,13 +2152,6 @@ int r600_init_microcode(struct radeon_device *rdev)
 
 	DRM_DEBUG("\n");
 
-	pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
-	err = IS_ERR(pdev);
-	if (err) {
-		printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
-		return -EINVAL;
-	}
-
 	switch (rdev->family) {
 	case CHIP_R600:
 		chip_name = "R600";
@@ -2272,7 +2263,7 @@ int r600_init_microcode(struct radeon_device *rdev)
 	DRM_INFO("Loading %s Microcode\n", chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
-	err = request_firmware(&rdev->pfp_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->pfp_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->pfp_fw->size != pfp_req_size) {
@@ -2284,7 +2275,7 @@ int r600_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
-	err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->me_fw->size != me_req_size) {
@@ -2295,7 +2286,7 @@ int r600_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", rlc_chip_name);
-	err = request_firmware(&rdev->rlc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->rlc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->rlc_fw->size != rlc_req_size) {
@@ -2307,7 +2298,7 @@ int r600_init_microcode(struct radeon_device *rdev)
 
 	if ((rdev->family >= CHIP_RV770) && (rdev->family <= CHIP_HEMLOCK)) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", smc_chip_name);
-		err = request_firmware(&rdev->smc_fw, fw_name, &pdev->dev);
+		err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
 		if (err)
 			goto out;
 		if (rdev->smc_fw->size != smc_req_size) {
@@ -2319,8 +2310,6 @@ int r600_init_microcode(struct radeon_device *rdev)
 	}
 
 out:
-	platform_device_unregister(pdev);
-
 	if (err) {
 		if (err != -EINVAL)
 			printk(KERN_ERR
@@ -3019,7 +3008,7 @@ void r600_uvd_fence_emit(struct radeon_device *rdev,
 			 struct radeon_fence *fence)
 {
 	struct radeon_ring *ring = &rdev->ring[fence->ring];
-	uint32_t addr = rdev->fence_drv[fence->ring].gpu_addr;
+	uint64_t addr = rdev->fence_drv[fence->ring].gpu_addr;
 
 	radeon_ring_write(ring, PACKET0(UVD_CONTEXT_ID, 0));
 	radeon_ring_write(ring, fence->seq);
@@ -3145,6 +3134,87 @@ int r600_copy_blit(struct radeon_device *rdev,
 }
 
 /**
+ * r600_copy_cpdma - copy pages using the CP DMA engine
+ *
+ * @rdev: radeon_device pointer
+ * @src_offset: src GPU address
+ * @dst_offset: dst GPU address
+ * @num_gpu_pages: number of GPU pages to xfer
+ * @fence: radeon fence object
+ *
+ * Copy GPU paging using the CP DMA engine (r6xx+).
+ * Used by the radeon ttm implementation to move pages if
+ * registered as the asic copy callback.
+ */
+int r600_copy_cpdma(struct radeon_device *rdev,
+		    uint64_t src_offset, uint64_t dst_offset,
+		    unsigned num_gpu_pages,
+		    struct radeon_fence **fence)
+{
+	struct radeon_semaphore *sem = NULL;
+	int ring_index = rdev->asic->copy.blit_ring_index;
+	struct radeon_ring *ring = &rdev->ring[ring_index];
+	u32 size_in_bytes, cur_size_in_bytes, tmp;
+	int i, num_loops;
+	int r = 0;
+
+	r = radeon_semaphore_create(rdev, &sem);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		return r;
+	}
+
+	size_in_bytes = (num_gpu_pages << RADEON_GPU_PAGE_SHIFT);
+	num_loops = DIV_ROUND_UP(size_in_bytes, 0x1fffff);
+	r = radeon_ring_lock(rdev, ring, num_loops * 6 + 21);
+	if (r) {
+		DRM_ERROR("radeon: moving bo (%d).\n", r);
+		radeon_semaphore_free(rdev, &sem, NULL);
+		return r;
+	}
+
+	if (radeon_fence_need_sync(*fence, ring->idx)) {
+		radeon_semaphore_sync_rings(rdev, sem, (*fence)->ring,
+					    ring->idx);
+		radeon_fence_note_sync(*fence, ring->idx);
+	} else {
+		radeon_semaphore_free(rdev, &sem, NULL);
+	}
+
+	for (i = 0; i < num_loops; i++) {
+		cur_size_in_bytes = size_in_bytes;
+		if (cur_size_in_bytes > 0x1fffff)
+			cur_size_in_bytes = 0x1fffff;
+		size_in_bytes -= cur_size_in_bytes;
+		tmp = upper_32_bits(src_offset) & 0xff;
+		if (size_in_bytes == 0)
+			tmp |= PACKET3_CP_DMA_CP_SYNC;
+		radeon_ring_write(ring, PACKET3(PACKET3_CP_DMA, 4));
+		radeon_ring_write(ring, src_offset & 0xffffffff);
+		radeon_ring_write(ring, tmp);
+		radeon_ring_write(ring, dst_offset & 0xffffffff);
+		radeon_ring_write(ring, upper_32_bits(dst_offset) & 0xff);
+		radeon_ring_write(ring, cur_size_in_bytes);
+		src_offset += cur_size_in_bytes;
+		dst_offset += cur_size_in_bytes;
+	}
+	radeon_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+	radeon_ring_write(ring, (WAIT_UNTIL - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
+	radeon_ring_write(ring, WAIT_CP_DMA_IDLE_bit);
+
+	r = radeon_fence_emit(rdev, fence, ring->idx);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return r;
+	}
+
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_semaphore_free(rdev, &sem, *fence);
+
+	return r;
+}
+
+/**
  * r600_copy_dma - copy pages using the DMA engine
  *
  * @rdev: radeon_device pointer
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index e73b2a7..f48240b 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -266,6 +266,9 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	uint32_t offset;
 	ssize_t err;
 
+	if (!dig || !dig->afmt)
+		return;
+
 	/* Silent, r600_hdmi_enable will raise WARN for us */
 	if (!dig->afmt->enabled)
 		return;
@@ -448,6 +451,9 @@ void r600_hdmi_enable(struct drm_encoder *encoder, bool enable)
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
 	u32 hdmi = HDMI0_ERROR_ACK;
 
+	if (!dig || !dig->afmt)
+		return;
+
 	/* Silent, r600_hdmi_enable will raise WARN for us */
 	if (enable && dig->afmt->enabled)
 		return;
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index f1b3084..8e3fe81 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -602,6 +602,7 @@
 #define		L2_BUSY						(1 << 0)
 
 #define	WAIT_UNTIL					0x8040
+#define         WAIT_CP_DMA_IDLE_bit                            (1 << 8)
 #define         WAIT_2D_IDLE_bit                                (1 << 14)
 #define         WAIT_3D_IDLE_bit                                (1 << 15)
 #define         WAIT_2D_IDLECLEAN_bit                           (1 << 16)
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 9b7025d..2f08219 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -97,6 +97,7 @@ extern int radeon_msi;
 extern int radeon_lockup_timeout;
 extern int radeon_fastfb;
 extern int radeon_dpm;
+extern int radeon_aspm;
 
 /*
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
@@ -455,6 +456,7 @@ struct radeon_sa_manager {
 	uint64_t		gpu_addr;
 	void			*cpu_ptr;
 	uint32_t		domain;
+	uint32_t		align;
 };
 
 struct radeon_sa_bo;
@@ -783,6 +785,11 @@ struct radeon_mec {
 /* number of entries in page table */
 #define RADEON_VM_PTE_COUNT (1 << RADEON_VM_BLOCK_SIZE)
 
+/* PTBs (Page Table Blocks) need to be aligned to 32K */
+#define RADEON_VM_PTB_ALIGN_SIZE   32768
+#define RADEON_VM_PTB_ALIGN_MASK (RADEON_VM_PTB_ALIGN_SIZE - 1)
+#define RADEON_VM_PTB_ALIGN(a) (((a) + RADEON_VM_PTB_ALIGN_MASK) & ~RADEON_VM_PTB_ALIGN_MASK)
+
 struct radeon_vm {
 	struct list_head		list;
 	struct list_head		va;
@@ -1460,6 +1467,8 @@ struct radeon_uvd {
 	struct radeon_bo	*vcpu_bo;
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
+	void			*saved_bo;
+	unsigned		fw_size;
 	atomic_t		handles[RADEON_MAX_UVD_HANDLES];
 	struct drm_file		*filp[RADEON_MAX_UVD_HANDLES];
 	struct delayed_work	idle_work;
@@ -2054,7 +2063,6 @@ struct radeon_device {
 	const struct firmware *rlc_fw;	/* r6/700 RLC firmware */
 	const struct firmware *mc_fw;	/* NI MC firmware */
 	const struct firmware *ce_fw;	/* SI CE firmware */
-	const struct firmware *uvd_fw;	/* UVD firmware */
 	const struct firmware *mec_fw;	/* CIK MEC firmware */
 	const struct firmware *sdma_fw;	/* CIK SDMA firmware */
 	const struct firmware *smc_fw;	/* SMC firmware */
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index 0970774..78bec1a 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -1026,8 +1026,8 @@ static struct radeon_asic r600_asic = {
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.copy = &r600_copy_dma,
-		.copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.copy = &r600_copy_cpdma,
+		.copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 	},
 	.surface = {
 		.set_reg = r600_set_surface_reg,
@@ -1119,8 +1119,8 @@ static struct radeon_asic rv6xx_asic = {
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.copy = &r600_copy_dma,
-		.copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.copy = &r600_copy_cpdma,
+		.copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 	},
 	.surface = {
 		.set_reg = r600_set_surface_reg,
@@ -1229,8 +1229,8 @@ static struct radeon_asic rs780_asic = {
 		.blit_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 		.dma = &r600_copy_dma,
 		.dma_ring_index = R600_RING_TYPE_DMA_INDEX,
-		.copy = &r600_copy_dma,
-		.copy_ring_index = R600_RING_TYPE_DMA_INDEX,
+		.copy = &r600_copy_cpdma,
+		.copy_ring_index = RADEON_RING_TYPE_GFX_INDEX,
 	},
 	.surface = {
 		.set_reg = r600_set_surface_reg,
@@ -1270,6 +1270,7 @@ static struct radeon_asic rs780_asic = {
 		.get_sclk = &rs780_dpm_get_sclk,
 		.get_mclk = &rs780_dpm_get_mclk,
 		.print_power_state = &rs780_dpm_print_power_state,
+		.debugfs_print_current_performance_level = &rs780_dpm_debugfs_print_current_performance_level,
 	},
 	.pflip = {
 		.pre_page_flip = &rs600_pre_page_flip,
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 45d0693..ca18957 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -340,6 +340,9 @@ int r600_uvd_ring_test(struct radeon_device *rdev, struct radeon_ring *ring);
 int r600_copy_blit(struct radeon_device *rdev,
 		   uint64_t src_offset, uint64_t dst_offset,
 		   unsigned num_gpu_pages, struct radeon_fence **fence);
+int r600_copy_cpdma(struct radeon_device *rdev,
+		    uint64_t src_offset, uint64_t dst_offset,
+		    unsigned num_gpu_pages, struct radeon_fence **fence);
 int r600_copy_dma(struct radeon_device *rdev,
 		  uint64_t src_offset, uint64_t dst_offset,
 		  unsigned num_gpu_pages, struct radeon_fence **fence);
@@ -430,6 +433,8 @@ u32 rs780_dpm_get_sclk(struct radeon_device *rdev, bool low);
 u32 rs780_dpm_get_mclk(struct radeon_device *rdev, bool low);
 void rs780_dpm_print_power_state(struct radeon_device *rdev,
 				 struct radeon_ps *ps);
+void rs780_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						       struct seq_file *m);
 
 /* uvd */
 int r600_uvd_init(struct radeon_device *rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index fbdaff5..e3f3e88 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -3513,7 +3513,6 @@ int radeon_atom_get_memory_info(struct radeon_device *rdev,
 	u8 frev, crev, i;
 	u16 data_offset, size;
 	union vram_info *vram_info;
-	u8 *p;
 
 	memset(mem_info, 0, sizeof(struct atom_memory_info));
 
@@ -3529,13 +3528,12 @@ int radeon_atom_get_memory_info(struct radeon_device *rdev,
 				if (module_index < vram_info->v1_3.ucNumOfVRAMModule) {
 					ATOM_VRAM_MODULE_V3 *vram_module =
 						(ATOM_VRAM_MODULE_V3 *)vram_info->v1_3.aVramInfo;
-					p = (u8 *)vram_info->v1_3.aVramInfo;
 
 					for (i = 0; i < module_index; i++) {
-						vram_module = (ATOM_VRAM_MODULE_V3 *)p;
 						if (le16_to_cpu(vram_module->usSize) == 0)
 							return -EINVAL;
-						p += le16_to_cpu(vram_module->usSize);
+						vram_module = (ATOM_VRAM_MODULE_V3 *)
+							((u8 *)vram_module + le16_to_cpu(vram_module->usSize));
 					}
 					mem_info->mem_vendor = vram_module->asMemory.ucMemoryVenderID & 0xf;
 					mem_info->mem_type = vram_module->asMemory.ucMemoryType & 0xf0;
@@ -3547,13 +3545,12 @@ int radeon_atom_get_memory_info(struct radeon_device *rdev,
 				if (module_index < vram_info->v1_4.ucNumOfVRAMModule) {
 					ATOM_VRAM_MODULE_V4 *vram_module =
 						(ATOM_VRAM_MODULE_V4 *)vram_info->v1_4.aVramInfo;
-					p = (u8 *)vram_info->v1_4.aVramInfo;
 
 					for (i = 0; i < module_index; i++) {
-						vram_module = (ATOM_VRAM_MODULE_V4 *)p;
 						if (le16_to_cpu(vram_module->usModuleSize) == 0)
 							return -EINVAL;
-						p += le16_to_cpu(vram_module->usModuleSize);
+						vram_module = (ATOM_VRAM_MODULE_V4 *)
+							((u8 *)vram_module + le16_to_cpu(vram_module->usModuleSize));
 					}
 					mem_info->mem_vendor = vram_module->ucMemoryVenderID & 0xf;
 					mem_info->mem_type = vram_module->ucMemoryType & 0xf0;
@@ -3572,13 +3569,12 @@ int radeon_atom_get_memory_info(struct radeon_device *rdev,
 				if (module_index < vram_info->v2_1.ucNumOfVRAMModule) {
 					ATOM_VRAM_MODULE_V7 *vram_module =
 						(ATOM_VRAM_MODULE_V7 *)vram_info->v2_1.aVramInfo;
-					p = (u8 *)vram_info->v2_1.aVramInfo;
 
 					for (i = 0; i < module_index; i++) {
-						vram_module = (ATOM_VRAM_MODULE_V7 *)p;
 						if (le16_to_cpu(vram_module->usModuleSize) == 0)
 							return -EINVAL;
-						p += le16_to_cpu(vram_module->usModuleSize);
+						vram_module = (ATOM_VRAM_MODULE_V7 *)
+							((u8 *)vram_module + le16_to_cpu(vram_module->usModuleSize));
 					}
 					mem_info->mem_vendor = vram_module->ucMemoryVenderID & 0xf;
 					mem_info->mem_type = vram_module->ucMemoryType & 0xf0;
@@ -3628,21 +3624,19 @@ int radeon_atom_get_mclk_range_table(struct radeon_device *rdev,
 				if (module_index < vram_info->v1_4.ucNumOfVRAMModule) {
 					ATOM_VRAM_MODULE_V4 *vram_module =
 						(ATOM_VRAM_MODULE_V4 *)vram_info->v1_4.aVramInfo;
-					ATOM_MEMORY_TIMING_FORMAT *format;
-					p = (u8 *)vram_info->v1_4.aVramInfo;
 
 					for (i = 0; i < module_index; i++) {
-						vram_module = (ATOM_VRAM_MODULE_V4 *)p;
 						if (le16_to_cpu(vram_module->usModuleSize) == 0)
 							return -EINVAL;
-						p += le16_to_cpu(vram_module->usModuleSize);
+						vram_module = (ATOM_VRAM_MODULE_V4 *)
+							((u8 *)vram_module + le16_to_cpu(vram_module->usModuleSize));
 					}
 					mclk_range_table->num_entries = (u8)
-						((vram_module->usModuleSize - offsetof(ATOM_VRAM_MODULE_V4, asMemTiming)) /
+						((le16_to_cpu(vram_module->usModuleSize) - offsetof(ATOM_VRAM_MODULE_V4, asMemTiming)) /
 						 mem_timing_size);
-					p = (u8 *)vram_module->asMemTiming;
+					p = (u8 *)&vram_module->asMemTiming[0];
 					for (i = 0; i < mclk_range_table->num_entries; i++) {
-						format = (ATOM_MEMORY_TIMING_FORMAT *)p;
+						ATOM_MEMORY_TIMING_FORMAT *format = (ATOM_MEMORY_TIMING_FORMAT *)p;
 						mclk_range_table->mclk[i] = le32_to_cpu(format->ulClkRange);
 						p += mem_timing_size;
 					}
@@ -3705,17 +3699,21 @@ int radeon_atom_init_mc_reg_table(struct radeon_device *rdev,
 						(ATOM_MEMORY_SETTING_DATA_BLOCK *)
 						((u8 *)reg_block + (2 * sizeof(u16)) +
 						 le16_to_cpu(reg_block->usRegIndexTblSize));
+					ATOM_INIT_REG_INDEX_FORMAT *format = &reg_block->asRegIndexBuf[0];
 					num_entries = (u8)((le16_to_cpu(reg_block->usRegIndexTblSize)) /
 							   sizeof(ATOM_INIT_REG_INDEX_FORMAT)) - 1;
 					if (num_entries > VBIOS_MC_REGISTER_ARRAY_SIZE)
 						return -EINVAL;
-					while (!(reg_block->asRegIndexBuf[i].ucPreRegDataLength & ACCESS_PLACEHOLDER) &&
-					      (i < num_entries)) {
+					while (i < num_entries) {
+						if (format->ucPreRegDataLength & ACCESS_PLACEHOLDER)
+							break;
 						reg_table->mc_reg_address[i].s1 =
-							(u16)(le16_to_cpu(reg_block->asRegIndexBuf[i].usRegIndex));
+							(u16)(le16_to_cpu(format->usRegIndex));
 						reg_table->mc_reg_address[i].pre_reg_data =
-							(u8)(reg_block->asRegIndexBuf[i].ucPreRegDataLength);
+							(u8)(format->ucPreRegDataLength);
 						i++;
+						format = (ATOM_INIT_REG_INDEX_FORMAT *)
+							((u8 *)format + sizeof(ATOM_INIT_REG_INDEX_FORMAT));
 					}
 					reg_table->last = i;
 					while ((*(u32 *)reg_data != END_OF_REG_DATA_BLOCK) &&
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index e5419b3..29876b1 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -167,6 +167,7 @@ int radeon_msi = -1;
 int radeon_lockup_timeout = 10000;
 int radeon_fastfb = 0;
 int radeon_dpm = -1;
+int radeon_aspm = -1;
 
 MODULE_PARM_DESC(no_wb, "Disable AGP writeback for scratch registers");
 module_param_named(no_wb, radeon_no_wb, int, 0444);
@@ -225,6 +226,9 @@ module_param_named(fastfb, radeon_fastfb, int, 0444);
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(dpm, radeon_dpm, int, 0444);
 
+MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
+module_param_named(aspm, radeon_aspm, int, 0444);
+
 static struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index ddb8f8e..7ddb0ef 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -782,7 +782,7 @@ int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring)
 
 		} else {
 			/* put fence directly behind firmware */
-			index = ALIGN(rdev->uvd_fw->size, 8);
+			index = ALIGN(rdev->uvd.fw_size, 8);
 			rdev->fence_drv[ring].cpu_addr = rdev->uvd.cpu_addr + index;
 			rdev->fence_drv[ring].gpu_addr = rdev->uvd.gpu_addr + index;
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 43ec4a4..d9d31a3 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -466,7 +466,8 @@ int radeon_vm_manager_init(struct radeon_device *rdev)
 		size += rdev->vm_manager.max_pfn * 8;
 		size *= 2;
 		r = radeon_sa_bo_manager_init(rdev, &rdev->vm_manager.sa_manager,
-					      RADEON_GPU_PAGE_ALIGN(size),
+					      RADEON_VM_PTB_ALIGN(size),
+					      RADEON_VM_PTB_ALIGN_SIZE,
 					      RADEON_GEM_DOMAIN_VRAM);
 		if (r) {
 			dev_err(rdev->dev, "failed to allocate vm bo (%dKB)\n",
@@ -620,10 +621,10 @@ int radeon_vm_alloc_pt(struct radeon_device *rdev, struct radeon_vm *vm)
 	}
 
 retry:
-	pd_size = RADEON_GPU_PAGE_ALIGN(radeon_vm_directory_size(rdev));
+	pd_size = RADEON_VM_PTB_ALIGN(radeon_vm_directory_size(rdev));
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 			     &vm->page_directory, pd_size,
-			     RADEON_GPU_PAGE_SIZE, false);
+			     RADEON_VM_PTB_ALIGN_SIZE, false);
 	if (r == -ENOMEM) {
 		r = radeon_vm_evict(rdev, vm);
 		if (r)
@@ -952,8 +953,8 @@ static int radeon_vm_update_pdes(struct radeon_device *rdev,
 retry:
 		r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager,
 				     &vm->page_tables[pt_idx],
-				     RADEON_VM_PTE_COUNT * 8,
-				     RADEON_GPU_PAGE_SIZE, false);
+				     RADEON_VM_PTB_ALIGN(RADEON_VM_PTE_COUNT * 8),
+				     RADEON_VM_PTB_ALIGN_SIZE, false);
 
 		if (r == -ENOMEM) {
 			r = radeon_vm_evict(rdev, vm);
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index bcdefd1..081886b 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -260,10 +260,6 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 {
 	int r = 0;
 
-	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
-	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
-	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
-
 	spin_lock_init(&rdev->irq.lock);
 	r = drm_vblank_init(rdev->ddev, rdev->num_crtc);
 	if (r) {
@@ -285,6 +281,11 @@ int radeon_irq_kms_init(struct radeon_device *rdev)
 		rdev->irq.installed = false;
 		return r;
 	}
+
+	INIT_WORK(&rdev->hotplug_work, radeon_hotplug_work_func);
+	INIT_WORK(&rdev->audio_work, r600_audio_update_hdmi);
+	INIT_WORK(&rdev->reset_work, radeon_irq_reset_work_func);
+
 	DRM_INFO("radeon: irq initialized.\n");
 	return 0;
 }
@@ -304,8 +305,8 @@ void radeon_irq_kms_fini(struct radeon_device *rdev)
 		rdev->irq.installed = false;
 		if (rdev->msi_enabled)
 			pci_disable_msi(rdev->pdev);
+		flush_work(&rdev->hotplug_work);
 	}
-	flush_work(&rdev->hotplug_work);
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 0219d26..2020bf4 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -377,6 +377,7 @@ int radeon_bo_list_validate(struct ww_acquire_ctx *ticket,
 					domain = lobj->alt_domain;
 					goto retry;
 				}
+				ttm_eu_backoff_reservation(ticket, head);
 				return r;
 			}
 		}
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 91519a5..49c82c4 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -174,7 +174,7 @@ static inline void * radeon_sa_bo_cpu_addr(struct radeon_sa_bo *sa_bo)
 
 extern int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 				     struct radeon_sa_manager *sa_manager,
-				     unsigned size, u32 domain);
+				     unsigned size, u32 align, u32 domain);
 extern void radeon_sa_bo_manager_fini(struct radeon_device *rdev,
 				      struct radeon_sa_manager *sa_manager);
 extern int radeon_sa_bo_manager_start(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 5f1c51a..fb5ea62 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -224,6 +224,7 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	}
 	r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo,
 				      RADEON_IB_POOL_SIZE*64*1024,
+				      RADEON_GPU_PAGE_SIZE,
 				      RADEON_GEM_DOMAIN_GTT);
 	if (r) {
 		return r;
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 0abe5a9..f0bac68 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -49,7 +49,7 @@ static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager);
 
 int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 			      struct radeon_sa_manager *sa_manager,
-			      unsigned size, u32 domain)
+			      unsigned size, u32 align, u32 domain)
 {
 	int i, r;
 
@@ -57,13 +57,14 @@ int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 	sa_manager->bo = NULL;
 	sa_manager->size = size;
 	sa_manager->domain = domain;
+	sa_manager->align = align;
 	sa_manager->hole = &sa_manager->olist;
 	INIT_LIST_HEAD(&sa_manager->olist);
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
 		INIT_LIST_HEAD(&sa_manager->flist[i]);
 	}
 
-	r = radeon_bo_create(rdev, size, RADEON_GPU_PAGE_SIZE, true,
+	r = radeon_bo_create(rdev, size, align, true,
 			     domain, NULL, &sa_manager->bo);
 	if (r) {
 		dev_err(rdev->dev, "(%d) failed to allocate bo for manager\n", r);
@@ -317,7 +318,7 @@ int radeon_sa_bo_new(struct radeon_device *rdev,
 	unsigned tries[RADEON_NUM_RINGS];
 	int i, r;
 
-	BUG_ON(align > RADEON_GPU_PAGE_SIZE);
+	BUG_ON(align > sa_manager->align);
 	BUG_ON(size > sa_manager->size);
 
 	*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 41efcec..414fd14 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -56,20 +56,13 @@ static void radeon_uvd_idle_work_handler(struct work_struct *work);
 
 int radeon_uvd_init(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
+	const struct firmware *fw;
 	unsigned long bo_size;
 	const char *fw_name;
 	int i, r;
 
 	INIT_DELAYED_WORK(&rdev->uvd.idle_work, radeon_uvd_idle_work_handler);
 
-	pdev = platform_device_register_simple("radeon_uvd", 0, NULL, 0);
-	r = IS_ERR(pdev);
-	if (r) {
-		dev_err(rdev->dev, "radeon_uvd: Failed to register firmware\n");
-		return -EINVAL;
-	}
-
 	switch (rdev->family) {
 	case CHIP_RV710:
 	case CHIP_RV730:
@@ -112,17 +105,14 @@ int radeon_uvd_init(struct radeon_device *rdev)
 		return -EINVAL;
 	}
 
-	r = request_firmware(&rdev->uvd_fw, fw_name, &pdev->dev);
+	r = request_firmware(&fw, fw_name, rdev->dev);
 	if (r) {
 		dev_err(rdev->dev, "radeon_uvd: Can't load firmware \"%s\"\n",
 			fw_name);
-		platform_device_unregister(pdev);
 		return r;
 	}
 
-	platform_device_unregister(pdev);
-
-	bo_size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 8) +
+	bo_size = RADEON_GPU_PAGE_ALIGN(fw->size + 8) +
 		  RADEON_UVD_STACK_SIZE + RADEON_UVD_HEAP_SIZE;
 	r = radeon_bo_create(rdev, bo_size, PAGE_SIZE, true,
 			     RADEON_GEM_DOMAIN_VRAM, NULL, &rdev->uvd.vcpu_bo);
@@ -131,16 +121,35 @@ int radeon_uvd_init(struct radeon_device *rdev)
 		return r;
 	}
 
-	r = radeon_uvd_resume(rdev);
-	if (r)
+	r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
+	if (r) {
+		radeon_bo_unref(&rdev->uvd.vcpu_bo);
+		dev_err(rdev->dev, "(%d) failed to reserve UVD bo\n", r);
 		return r;
+	}
 
-	memset(rdev->uvd.cpu_addr, 0, bo_size);
-	memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);
+	r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
+			  &rdev->uvd.gpu_addr);
+	if (r) {
+		radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+		radeon_bo_unref(&rdev->uvd.vcpu_bo);
+		dev_err(rdev->dev, "(%d) UVD bo pin failed\n", r);
+		return r;
+	}
 
-	r = radeon_uvd_suspend(rdev);
-	if (r)
+	r = radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr);
+	if (r) {
+		dev_err(rdev->dev, "(%d) UVD map failed\n", r);
 		return r;
+	}
+
+	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+
+	rdev->uvd.fw_size = fw->size;
+	memset(rdev->uvd.cpu_addr, 0, bo_size);
+	memcpy(rdev->uvd.cpu_addr, fw->data, fw->size);
+
+	release_firmware(fw);
 
 	for (i = 0; i < RADEON_MAX_UVD_HANDLES; ++i) {
 		atomic_set(&rdev->uvd.handles[i], 0);
@@ -152,71 +161,47 @@ int radeon_uvd_init(struct radeon_device *rdev)
 
 void radeon_uvd_fini(struct radeon_device *rdev)
 {
-	radeon_uvd_suspend(rdev);
-	radeon_bo_unref(&rdev->uvd.vcpu_bo);
-}
-
-int radeon_uvd_suspend(struct radeon_device *rdev)
-{
 	int r;
 
 	if (rdev->uvd.vcpu_bo == NULL)
-		return 0;
+		return;
 
 	r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
 	if (!r) {
 		radeon_bo_kunmap(rdev->uvd.vcpu_bo);
 		radeon_bo_unpin(rdev->uvd.vcpu_bo);
-		rdev->uvd.cpu_addr = NULL;
-		if (!radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_CPU, NULL)) {
-			radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr);
-		}
 		radeon_bo_unreserve(rdev->uvd.vcpu_bo);
-
-		if (rdev->uvd.cpu_addr) {
-			radeon_fence_driver_start_ring(rdev, R600_RING_TYPE_UVD_INDEX);
-		} else {
-			rdev->fence_drv[R600_RING_TYPE_UVD_INDEX].cpu_addr = NULL;
-		}
 	}
-	return r;
+
+	radeon_bo_unref(&rdev->uvd.vcpu_bo);
 }
 
-int radeon_uvd_resume(struct radeon_device *rdev)
+int radeon_uvd_suspend(struct radeon_device *rdev)
 {
-	int r;
+	unsigned size;
 
 	if (rdev->uvd.vcpu_bo == NULL)
-		return -EINVAL;
+		return 0;
 
-	r = radeon_bo_reserve(rdev->uvd.vcpu_bo, false);
-	if (r) {
-		radeon_bo_unref(&rdev->uvd.vcpu_bo);
-		dev_err(rdev->dev, "(%d) failed to reserve UVD bo\n", r);
-		return r;
-	}
+	size = radeon_bo_size(rdev->uvd.vcpu_bo);
+	rdev->uvd.saved_bo = kmalloc(size, GFP_KERNEL);
+	memcpy(rdev->uvd.saved_bo, rdev->uvd.cpu_addr, size);
 
-	/* Have been pin in cpu unmap unpin */
-	radeon_bo_kunmap(rdev->uvd.vcpu_bo);
-	radeon_bo_unpin(rdev->uvd.vcpu_bo);
+	return 0;
+}
 
-	r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
-			  &rdev->uvd.gpu_addr);
-	if (r) {
-		radeon_bo_unreserve(rdev->uvd.vcpu_bo);
-		radeon_bo_unref(&rdev->uvd.vcpu_bo);
-		dev_err(rdev->dev, "(%d) UVD bo pin failed\n", r);
-		return r;
-	}
+int radeon_uvd_resume(struct radeon_device *rdev)
+{
+	if (rdev->uvd.vcpu_bo == NULL)
+		return -EINVAL;
 
-	r = radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr);
-	if (r) {
-		dev_err(rdev->dev, "(%d) UVD map failed\n", r);
-		return r;
+	if (rdev->uvd.saved_bo != NULL) {
+		unsigned size = radeon_bo_size(rdev->uvd.vcpu_bo);
+		memcpy(rdev->uvd.cpu_addr, rdev->uvd.saved_bo, size);
+		kfree(rdev->uvd.saved_bo);
+		rdev->uvd.saved_bo = NULL;
 	}
 
-	radeon_bo_unreserve(rdev->uvd.vcpu_bo);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/rs780_dpm.c b/drivers/gpu/drm/radeon/rs780_dpm.c
index bef832a..d1a1ce7 100644
--- a/drivers/gpu/drm/radeon/rs780_dpm.c
+++ b/drivers/gpu/drm/radeon/rs780_dpm.c
@@ -28,6 +28,7 @@
 #include "r600_dpm.h"
 #include "rs780_dpm.h"
 #include "atom.h"
+#include <linux/seq_file.h>
 
 static struct igp_ps *rs780_get_ps(struct radeon_ps *rps)
 {
@@ -961,3 +962,27 @@ u32 rs780_dpm_get_mclk(struct radeon_device *rdev, bool low)
 
 	return pi->bootup_uma_clk;
 }
+
+void rs780_dpm_debugfs_print_current_performance_level(struct radeon_device *rdev,
+						       struct seq_file *m)
+{
+	struct radeon_ps *rps = rdev->pm.dpm.current_ps;
+	struct igp_ps *ps = rs780_get_ps(rps);
+	u32 current_fb_div = RREG32(FVTHROT_STATUS_REG0) & CURRENT_FEEDBACK_DIV_MASK;
+	u32 func_cntl = RREG32(CG_SPLL_FUNC_CNTL);
+	u32 ref_div = ((func_cntl & SPLL_REF_DIV_MASK) >> SPLL_REF_DIV_SHIFT) + 1;
+	u32 post_div = ((func_cntl & SPLL_SW_HILEN_MASK) >> SPLL_SW_HILEN_SHIFT) + 1 +
+		((func_cntl & SPLL_SW_LOLEN_MASK) >> SPLL_SW_LOLEN_SHIFT) + 1;
+	u32 sclk = (rdev->clock.spll.reference_freq * current_fb_div) /
+		(post_div * ref_div);
+
+	seq_printf(m, "uvd    vclk: %d dclk: %d\n", rps->vclk, rps->dclk);
+
+	/* guess based on the current sclk */
+	if (sclk < (ps->sclk_low + 500))
+		seq_printf(m, "power level 0    sclk: %u vddc_index: %d\n",
+			   ps->sclk_low, ps->min_voltage);
+	else
+		seq_printf(m, "power level 1    sclk: %u vddc_index: %d\n",
+			   ps->sclk_high, ps->max_voltage);
+}
diff --git a/drivers/gpu/drm/radeon/rs780d.h b/drivers/gpu/drm/radeon/rs780d.h
index b1142ed..cfbe9a4 100644
--- a/drivers/gpu/drm/radeon/rs780d.h
+++ b/drivers/gpu/drm/radeon/rs780d.h
@@ -28,6 +28,7 @@
 #       define SPLL_SLEEP                                (1 << 1)
 #       define SPLL_REF_DIV(x)                           ((x) << 2)
 #       define SPLL_REF_DIV_MASK                         (7 << 2)
+#       define SPLL_REF_DIV_SHIFT                        2
 #       define SPLL_FB_DIV(x)                            ((x) << 5)
 #       define SPLL_FB_DIV_MASK                          (0xff << 2)
 #       define SPLL_FB_DIV_SHIFT                         2
@@ -36,8 +37,10 @@
 #       define SPLL_PULSENUM_MASK                        (3 << 14)
 #       define SPLL_SW_HILEN(x)                          ((x) << 16)
 #       define SPLL_SW_HILEN_MASK                        (0xf << 16)
+#       define SPLL_SW_HILEN_SHIFT                       16
 #       define SPLL_SW_LOLEN(x)                          ((x) << 20)
 #       define SPLL_SW_LOLEN_MASK                        (0xf << 20)
+#       define SPLL_SW_LOLEN_SHIFT                       20
 #       define SPLL_DIVEN                                (1 << 24)
 #       define SPLL_BYPASS_EN                            (1 << 25)
 #       define SPLL_CHG_STATUS                           (1 << 29)
diff --git a/drivers/gpu/drm/radeon/rv6xx_dpm.c b/drivers/gpu/drm/radeon/rv6xx_dpm.c
index 8303de2..65e33f3 100644
--- a/drivers/gpu/drm/radeon/rv6xx_dpm.c
+++ b/drivers/gpu/drm/radeon/rv6xx_dpm.c
@@ -1763,12 +1763,14 @@ void rv6xx_setup_asic(struct radeon_device *rdev)
 {
 	r600_enable_acpi_pm(rdev);
 
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L0s)
-		rv6xx_enable_l0s(rdev);
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L1)
-		rv6xx_enable_l1(rdev);
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1)
-		rv6xx_enable_pll_sleep_in_l1(rdev);
+	if (radeon_aspm != 0) {
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L0s)
+			rv6xx_enable_l0s(rdev);
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L1)
+			rv6xx_enable_l1(rdev);
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1)
+			rv6xx_enable_pll_sleep_in_l1(rdev);
+	}
 }
 
 void rv6xx_dpm_display_configuration_changed(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 4a62ad2..30ea14e 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -813,7 +813,7 @@ int rv770_uvd_resume(struct radeon_device *rdev)
 
 	/* programm the VCPU memory controller bits 0-27 */
 	addr = rdev->uvd.gpu_addr >> 3;
-	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd_fw->size + 4) >> 3;
+	size = RADEON_GPU_PAGE_ALIGN(rdev->uvd.fw_size + 4) >> 3;
 	WREG32(UVD_VCPU_CACHE_OFFSET0, addr);
 	WREG32(UVD_VCPU_CACHE_SIZE0, size);
 
diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c
index d914e04..2d34792 100644
--- a/drivers/gpu/drm/radeon/rv770_dpm.c
+++ b/drivers/gpu/drm/radeon/rv770_dpm.c
@@ -2099,12 +2099,14 @@ void rv770_dpm_setup_asic(struct radeon_device *rdev)
 
 	rv770_enable_acpi_pm(rdev);
 
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L0s)
-		rv770_enable_l0s(rdev);
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L1)
-		rv770_enable_l1(rdev);
-	if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1)
-		rv770_enable_pll_sleep_in_l1(rdev);
+	if (radeon_aspm != 0) {
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L0s)
+			rv770_enable_l0s(rdev);
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_ASPM_L1)
+			rv770_enable_l1(rdev);
+		if (rdev->pm.dpm.platform_caps & ATOM_PP_PLATFORM_CAP_TURNOFFPLL_ASPML1)
+			rv770_enable_pll_sleep_in_l1(rdev);
+	}
 }
 
 void rv770_dpm_display_configuration_changed(struct radeon_device *rdev)
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 2349067..d325280 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -22,7 +22,6 @@
  * Authors: Alex Deucher
  */
 #include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <drm/drmP.h>
@@ -1541,7 +1540,6 @@ static int si_mc_load_microcode(struct radeon_device *rdev)
 
 static int si_init_microcode(struct radeon_device *rdev)
 {
-	struct platform_device *pdev;
 	const char *chip_name;
 	const char *rlc_chip_name;
 	size_t pfp_req_size, me_req_size, ce_req_size, rlc_req_size, mc_req_size;
@@ -1551,13 +1549,6 @@ static int si_init_microcode(struct radeon_device *rdev)
 
 	DRM_DEBUG("\n");
 
-	pdev = platform_device_register_simple("radeon_cp", 0, NULL, 0);
-	err = IS_ERR(pdev);
-	if (err) {
-		printk(KERN_ERR "radeon_cp: Failed to register firmware\n");
-		return -EINVAL;
-	}
-
 	switch (rdev->family) {
 	case CHIP_TAHITI:
 		chip_name = "TAHITI";
@@ -1615,7 +1606,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	DRM_INFO("Loading %s Microcode\n", chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
-	err = request_firmware(&rdev->pfp_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->pfp_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->pfp_fw->size != pfp_req_size) {
@@ -1627,7 +1618,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
-	err = request_firmware(&rdev->me_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->me_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->me_fw->size != me_req_size) {
@@ -1638,7 +1629,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
-	err = request_firmware(&rdev->ce_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->ce_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->ce_fw->size != ce_req_size) {
@@ -1649,7 +1640,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", rlc_chip_name);
-	err = request_firmware(&rdev->rlc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->rlc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->rlc_fw->size != rlc_req_size) {
@@ -1660,7 +1651,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
-	err = request_firmware(&rdev->mc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->mc_fw->size != mc_req_size) {
@@ -1671,7 +1662,7 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
-	err = request_firmware(&rdev->smc_fw, fw_name, &pdev->dev);
+	err = request_firmware(&rdev->smc_fw, fw_name, rdev->dev);
 	if (err)
 		goto out;
 	if (rdev->smc_fw->size != smc_req_size) {
@@ -1682,8 +1673,6 @@ static int si_init_microcode(struct radeon_device *rdev)
 	}
 
 out:
-	platform_device_unregister(pdev);
-
 	if (err) {
 		if (err != -EINVAL)
 			printk(KERN_ERR
@@ -4401,6 +4390,270 @@ void si_vm_fini(struct radeon_device *rdev)
 }
 
 /**
+ * si_vm_decode_fault - print human readable fault info
+ *
+ * @rdev: radeon_device pointer
+ * @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value
+ * @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value
+ *
+ * Print human readable fault information (SI).
+ */
+static void si_vm_decode_fault(struct radeon_device *rdev,
+			       u32 status, u32 addr)
+{
+	u32 mc_id = (status & MEMORY_CLIENT_ID_MASK) >> MEMORY_CLIENT_ID_SHIFT;
+	u32 vmid = (status & FAULT_VMID_MASK) >> FAULT_VMID_SHIFT;
+	u32 protections = (status & PROTECTIONS_MASK) >> PROTECTIONS_SHIFT;
+	char *block;
+
+	if (rdev->family == CHIP_TAHITI) {
+		switch (mc_id) {
+		case 160:
+		case 144:
+		case 96:
+		case 80:
+		case 224:
+		case 208:
+		case 32:
+		case 16:
+			block = "CB";
+			break;
+		case 161:
+		case 145:
+		case 97:
+		case 81:
+		case 225:
+		case 209:
+		case 33:
+		case 17:
+			block = "CB_FMASK";
+			break;
+		case 162:
+		case 146:
+		case 98:
+		case 82:
+		case 226:
+		case 210:
+		case 34:
+		case 18:
+			block = "CB_CMASK";
+			break;
+		case 163:
+		case 147:
+		case 99:
+		case 83:
+		case 227:
+		case 211:
+		case 35:
+		case 19:
+			block = "CB_IMMED";
+			break;
+		case 164:
+		case 148:
+		case 100:
+		case 84:
+		case 228:
+		case 212:
+		case 36:
+		case 20:
+			block = "DB";
+			break;
+		case 165:
+		case 149:
+		case 101:
+		case 85:
+		case 229:
+		case 213:
+		case 37:
+		case 21:
+			block = "DB_HTILE";
+			break;
+		case 167:
+		case 151:
+		case 103:
+		case 87:
+		case 231:
+		case 215:
+		case 39:
+		case 23:
+			block = "DB_STEN";
+			break;
+		case 72:
+		case 68:
+		case 64:
+		case 8:
+		case 4:
+		case 0:
+		case 136:
+		case 132:
+		case 128:
+		case 200:
+		case 196:
+		case 192:
+			block = "TC";
+			break;
+		case 112:
+		case 48:
+			block = "CP";
+			break;
+		case 49:
+		case 177:
+		case 50:
+		case 178:
+			block = "SH";
+			break;
+		case 53:
+		case 190:
+			block = "VGT";
+			break;
+		case 117:
+			block = "IH";
+			break;
+		case 51:
+		case 115:
+			block = "RLC";
+			break;
+		case 119:
+		case 183:
+			block = "DMA0";
+			break;
+		case 61:
+			block = "DMA1";
+			break;
+		case 248:
+		case 120:
+			block = "HDP";
+			break;
+		default:
+			block = "unknown";
+			break;
+		}
+	} else {
+		switch (mc_id) {
+		case 32:
+		case 16:
+		case 96:
+		case 80:
+		case 160:
+		case 144:
+		case 224:
+		case 208:
+			block = "CB";
+			break;
+		case 33:
+		case 17:
+		case 97:
+		case 81:
+		case 161:
+		case 145:
+		case 225:
+		case 209:
+			block = "CB_FMASK";
+			break;
+		case 34:
+		case 18:
+		case 98:
+		case 82:
+		case 162:
+		case 146:
+		case 226:
+		case 210:
+			block = "CB_CMASK";
+			break;
+		case 35:
+		case 19:
+		case 99:
+		case 83:
+		case 163:
+		case 147:
+		case 227:
+		case 211:
+			block = "CB_IMMED";
+			break;
+		case 36:
+		case 20:
+		case 100:
+		case 84:
+		case 164:
+		case 148:
+		case 228:
+		case 212:
+			block = "DB";
+			break;
+		case 37:
+		case 21:
+		case 101:
+		case 85:
+		case 165:
+		case 149:
+		case 229:
+		case 213:
+			block = "DB_HTILE";
+			break;
+		case 39:
+		case 23:
+		case 103:
+		case 87:
+		case 167:
+		case 151:
+		case 231:
+		case 215:
+			block = "DB_STEN";
+			break;
+		case 72:
+		case 68:
+		case 8:
+		case 4:
+		case 136:
+		case 132:
+		case 200:
+		case 196:
+			block = "TC";
+			break;
+		case 112:
+		case 48:
+			block = "CP";
+			break;
+		case 49:
+		case 177:
+		case 50:
+		case 178:
+			block = "SH";
+			break;
+		case 53:
+			block = "VGT";
+			break;
+		case 117:
+			block = "IH";
+			break;
+		case 51:
+		case 115:
+			block = "RLC";
+			break;
+		case 119:
+		case 183:
+			block = "DMA0";
+			break;
+		case 61:
+			block = "DMA1";
+			break;
+		case 248:
+		case 120:
+			block = "HDP";
+			break;
+		default:
+			block = "unknown";
+			break;
+		}
+	}
+
+	printk("VM fault (0x%02x, vmid %d) at page %u, %s from %s (%d)\n",
+	       protections, vmid, addr,
+	       (status & MEMORY_CLIENT_RW_MASK) ? "write" : "read",
+	       block, mc_id);
+}
+
+/**
  * si_vm_set_page - update the page tables using the CP
  *
  * @rdev: radeon_device pointer
@@ -5766,6 +6019,7 @@ int si_irq_process(struct radeon_device *rdev)
 	u32 ring_index;
 	bool queue_hotplug = false;
 	bool queue_thermal = false;
+	u32 status, addr;
 
 	if (!rdev->ih.enabled || rdev->shutdown)
 		return IRQ_NONE;
@@ -6001,11 +6255,14 @@ restart_ih:
 			break;
 		case 146:
 		case 147:
+			addr = RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR);
+			status = RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS);
 			dev_err(rdev->dev, "GPU fault detected: %d 0x%08x\n", src_id, src_data);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_ADDR));
+				addr);
 			dev_err(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
-				RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
+				status);
+			si_vm_decode_fault(rdev, status, addr);
 			/* reset addr and status */
 			WREG32_P(VM_CONTEXT1_CNTL2, 1, ~1);
 			break;
@@ -6796,6 +7053,9 @@ static void si_program_aspm(struct radeon_device *rdev)
 	bool disable_l0s = false, disable_l1 = false, disable_plloff_in_l1 = false;
 	bool disable_clkreq = false;
 
+	if (radeon_aspm == 0)
+		return;
+
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 12a20eb..2c8da27 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -367,6 +367,20 @@
 
 #define	VM_CONTEXT1_PROTECTION_FAULT_ADDR		0x14FC
 #define	VM_CONTEXT1_PROTECTION_FAULT_STATUS		0x14DC
+#define		PROTECTIONS_MASK			(0xf << 0)
+#define		PROTECTIONS_SHIFT			0
+		/* bit 0: range
+		 * bit 1: pde0
+		 * bit 2: valid
+		 * bit 3: read
+		 * bit 4: write
+		 */
+#define		MEMORY_CLIENT_ID_MASK			(0xff << 12)
+#define		MEMORY_CLIENT_ID_SHIFT			12
+#define		MEMORY_CLIENT_RW_MASK			(1 << 24)
+#define		MEMORY_CLIENT_RW_SHIFT			24
+#define		FAULT_VMID_MASK				(0xf << 25)
+#define		FAULT_VMID_SHIFT			25
 
 #define VM_INVALIDATE_REQUEST				0x1478
 #define VM_INVALIDATE_RESPONSE				0x147c
diff --git a/drivers/gpu/drm/radeon/sumo_dpm.c b/drivers/gpu/drm/radeon/sumo_dpm.c
index 11b6b99..c0a8503 100644
--- a/drivers/gpu/drm/radeon/sumo_dpm.c
+++ b/drivers/gpu/drm/radeon/sumo_dpm.c
@@ -1732,7 +1732,13 @@ int sumo_dpm_init(struct radeon_device *rdev)
 	pi->enable_sclk_ds = true;
 	pi->enable_dynamic_m3_arbiter = false;
 	pi->enable_dynamic_patch_ps = true;
-	pi->enable_gfx_power_gating = true;
+	/* Some PALM chips don't seem to properly ungate gfx when UVD is in use;
+	 * for now just disable gfx PG.
+	 */
+	if (rdev->family == CHIP_PALM)
+		pi->enable_gfx_power_gating = false;
+	else
+		pi->enable_gfx_power_gating = true;
 	pi->enable_gfx_clock_gating = true;
 	pi->enable_mg_clock_gating = true;
 	pi->enable_auto_thermal_throttling = true;
@@ -1845,6 +1851,8 @@ int sumo_dpm_force_performance_level(struct radeon_device *rdev,
 		return 0;
 
 	if (level == RADEON_DPM_FORCED_LEVEL_HIGH) {
+		if (pi->enable_boost)
+			sumo_enable_boost(rdev, rps, false);
 		sumo_power_level_enable(rdev, ps->num_levels - 1, true);
 		sumo_set_forced_level(rdev, ps->num_levels - 1);
 		sumo_set_forced_mode_enabled(rdev);
@@ -1855,6 +1863,8 @@ int sumo_dpm_force_performance_level(struct radeon_device *rdev,
 		sumo_set_forced_mode_enabled(rdev);
 		sumo_set_forced_mode(rdev, false);
 	} else if (level == RADEON_DPM_FORCED_LEVEL_LOW) {
+		if (pi->enable_boost)
+			sumo_enable_boost(rdev, rps, false);
 		sumo_power_level_enable(rdev, 0, true);
 		sumo_set_forced_level(rdev, 0);
 		sumo_set_forced_mode_enabled(rdev);
@@ -1868,6 +1878,8 @@ int sumo_dpm_force_performance_level(struct radeon_device *rdev,
 		for (i = 0; i < ps->num_levels; i++) {
 			sumo_power_level_enable(rdev, i, true);
 		}
+		if (pi->enable_boost)
+			sumo_enable_boost(rdev, rps, true);
 	}
 
 	rdev->pm.dpm.forced_level = level;
diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
index ff82877..dc0fe09 100644
--- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c
+++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c
@@ -249,8 +249,13 @@ static struct drm_driver rcar_du_driver = {
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
-	.gem_prime_import	= drm_gem_cma_dmabuf_import,
-	.gem_prime_export	= drm_gem_cma_dmabuf_export,
+	.gem_prime_import	= drm_gem_prime_import,
+	.gem_prime_export	= drm_gem_prime_export,
+	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
+	.gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table,
+	.gem_prime_vmap		= drm_gem_cma_prime_vmap,
+	.gem_prime_vunmap	= drm_gem_cma_prime_vunmap,
+	.gem_prime_mmap		= drm_gem_cma_prime_mmap,
 	.dumb_create		= rcar_du_dumb_create,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
 	.dumb_destroy		= drm_gem_cma_dumb_destroy,
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_drv.c b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
index edc1018..5f83f9a 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_drv.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_drv.c
@@ -276,8 +276,13 @@ static struct drm_driver shmob_drm_driver = {
 	.gem_vm_ops		= &drm_gem_cma_vm_ops,
 	.prime_handle_to_fd	= drm_gem_prime_handle_to_fd,
 	.prime_fd_to_handle	= drm_gem_prime_fd_to_handle,
-	.gem_prime_import	= drm_gem_cma_dmabuf_import,
-	.gem_prime_export	= drm_gem_cma_dmabuf_export,
+	.gem_prime_import	= drm_gem_prime_import,
+	.gem_prime_export	= drm_gem_prime_export,
+	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
+	.gem_prime_import_sg_table = drm_gem_cma_prime_import_sg_table,
+	.gem_prime_vmap		= drm_gem_cma_prime_vmap,
+	.gem_prime_vunmap	= drm_gem_cma_prime_vunmap,
+	.gem_prime_mmap		= drm_gem_cma_prime_mmap,
 	.dumb_create		= drm_gem_cma_dumb_create,
 	.dumb_map_offset	= drm_gem_cma_dumb_map_offset,
 	.dumb_destroy		= drm_gem_cma_dumb_destroy,
diff --git a/drivers/video/uvesafb.c b/drivers/video/uvesafb.c
index b963ea1..7aec6f3 100644
--- a/drivers/video/uvesafb.c
+++ b/drivers/video/uvesafb.c
@@ -1891,7 +1891,7 @@ static int uvesafb_setup(char *options)
 		}
 	}
 
-	if (mtrr != 3 && mtrr != 1)
+	if (mtrr != 3 && mtrr != 0)
 		pr_warn("uvesafb: mtrr should be set to 0 or 3; %d is unsupported", mtrr);
 
 	return 0;