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

Pull drm fixes from Dave Airlie:
 "All over the map..

   - nouveau:
     disable MSI, needs more work, will try again next merge window
   - radeon:
      audio + uvd regression fixes, dpm fixes, reset fixes
   - i915:
     the dpms fix might fix your haswell

  And one pain in the ass revert, so we have VGA arbitration that when
  implemented 4-5 years ago really hoped that GPUs could remove
  themselves from arbitration completely once they had a kernel driver.

  It seems Intel hw designers decided that was too nice a facility to
  allow us to have so they removed it when they went on-die (so since
  Ironlake at least).  Now Alex Williamson added support for VGA
  arbitration for newer GPUs however this now exposes itself to
  userspace as requireing arbitration of GPU VGA regions and the X
  server gets involved and disables things that it can't handle when VGA
  access is possibly required around every operation.

  So in order to not break userspace we just reverted things back to the
  old known broken status so maybe we can try and design out way out.

  Ville also had a patch to use stop machine for the two times Intel
  needs to access VGA space, that might be acceptable with some rework,
  but for now myself and Daniel agreed to just go back"

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux: (23 commits)
  Revert "i915: Update VGA arbiter support for newer devices"
  Revert "drm/i915: Delay disabling of VGA memory until vgacon->fbcon handoff is done"
  drm/radeon: re-enable sw ACR support on pre-DCE4
  drm/radeon/dpm: disable bapm on TN asics
  drm/radeon: improve soft reset on CIK
  drm/radeon: improve soft reset on SI
  drm/radeon/dpm: off by one in si_set_mc_special_registers()
  drm/radeon/dpm/btc: off by one in btc_set_mc_special_registers()
  drm/radeon: forever loop on error in radeon_do_test_moves()
  drm/radeon: fix hw contexts for SUMO2 asics
  drm/radeon: fix typo in CP DMA register headers
  drm/radeon/dpm: disable multiple UVD states
  drm/radeon: use hw generated CTS/N values for audio
  drm/radeon: fix N/CTS clock matching for audio
  drm/radeon: use 64-bit math to calculate CTS values for audio (v2)
  drm/edid: catch kmalloc failure in drm_edid_to_speaker_allocation
  Revert "drm/fb-helper: don't sleep for screen unblank when an oops is in progress"
  drm/gma500: fix things after get/put page helpers
  drm/nouveau/mc: disable msi support by default, it's busted in tons of places
  drm/i915: Only apply DPMS to the encoder if enabled
  ...

25 files changed, 74 insertions, 93 deletions

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 1688ff50051..830f7501cb4 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -2925,6 +2925,8 @@ int drm_edid_to_speaker_allocation(struct edid *edid, u8 **sadb)
 			/* Speaker Allocation Data Block */
 			if (dbl == 3) {
 				*sadb = kmalloc(dbl, GFP_KERNEL);
+				if (!*sadb)
+					return -ENOMEM;
 				memcpy(*sadb, &db[1], dbl);
 				count = dbl;
 				break;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index f6f6cc7fc13..3d13ca6e257 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -416,14 +416,6 @@ static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode)
 		return;
 
 	/*
-	 * fbdev->blank can be called from irq context in case of a panic.
-	 * Since we already have our own special panic handler which will
-	 * restore the fbdev console mode completely, just bail out early.
-	 */
-	if (oops_in_progress)
-		return;
-
-	/*
 	 * For each CRTC in this fb, turn the connectors on/off.
 	 */
 	drm_modeset_lock_all(dev);
diff --git a/drivers/gpu/drm/gma500/gtt.c b/drivers/gpu/drm/gma500/gtt.c
index 92babac362e..2db731f0093 100644
--- a/drivers/gpu/drm/gma500/gtt.c
+++ b/drivers/gpu/drm/gma500/gtt.c
@@ -204,6 +204,7 @@ static int psb_gtt_attach_pages(struct gtt_range *gt)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
+	gt->npage = gt->gem.size / PAGE_SIZE;
 	gt->pages = pages;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index c27a21034a5..d5c784d4867 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -1290,12 +1290,9 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 * then we do not take part in VGA arbitration and the
 	 * vga_client_register() fails with -ENODEV.
 	 */
-	if (!HAS_PCH_SPLIT(dev)) {
-		ret = vga_client_register(dev->pdev, dev, NULL,
-					  i915_vga_set_decode);
-		if (ret && ret != -ENODEV)
-			goto out;
-	}
+	ret = vga_client_register(dev->pdev, dev, NULL, i915_vga_set_decode);
+	if (ret && ret != -ENODEV)
+		goto out;
 
 	intel_register_dsm_handler();
 
@@ -1351,12 +1348,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	 */
 	intel_fbdev_initial_config(dev);
 
-	/*
-	 * Must do this after fbcon init so that
-	 * vgacon_save_screen() works during the handover.
-	 */
-	i915_disable_vga_mem(dev);
-
 	/* Only enable hotplug handling once the fbdev is fully set up. */
 	dev_priv->enable_hotplug_processing = true;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c159e1a6810..38f96f65d87 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3881,6 +3881,9 @@
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		0x9030
 #define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
 
+#define HSW_SCRATCH1				0xb038
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+
 #define HSW_FUSE_STRAP		0x42014
 #define  HSW_CDCLK_LIMIT	(1 << 24)
 
@@ -4728,6 +4731,9 @@
 #define GEN7_ROW_CHICKEN2_GT2		0xf4f4
 #define   DOP_CLOCK_GATING_DISABLE	(1<<0)
 
+#define HSW_ROW_CHICKEN3		0xe49c
+#define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
+
 #define G4X_AUD_VID_DID			(dev_priv->info->display_mmio_offset + 0x62020)
 #define INTEL_AUDIO_DEVCL		0x808629FB
 #define INTEL_AUDIO_DEVBLC		0x80862801
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index e5822e79f91..581fb4b2f76 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3941,8 +3941,6 @@ static void intel_connector_check_state(struct intel_connector *connector)
  * consider. */
 void intel_connector_dpms(struct drm_connector *connector, int mode)
 {
-	struct intel_encoder *encoder = intel_attached_encoder(connector);
-
 	/* All the simple cases only support two dpms states. */
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
@@ -3953,10 +3951,8 @@ void intel_connector_dpms(struct drm_connector *connector, int mode)
 	connector->dpms = mode;
 
 	/* Only need to change hw state when actually enabled */
-	if (encoder->base.crtc)
-		intel_encoder_dpms(encoder, mode);
-	else
-		WARN_ON(encoder->connectors_active != false);
+	if (connector->encoder)
+		intel_encoder_dpms(to_intel_encoder(connector->encoder), mode);
 
 	intel_modeset_check_state(connector->dev);
 }
@@ -10049,33 +10045,6 @@ static void i915_disable_vga(struct drm_device *dev)
 	POSTING_READ(vga_reg);
 }
 
-static void i915_enable_vga_mem(struct drm_device *dev)
-{
-	/* Enable VGA memory on Intel HD */
-	if (HAS_PCH_SPLIT(dev)) {
-		vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO);
-		outb(inb(VGA_MSR_READ) | VGA_MSR_MEM_EN, VGA_MSR_WRITE);
-		vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO |
-						   VGA_RSRC_LEGACY_MEM |
-						   VGA_RSRC_NORMAL_IO |
-						   VGA_RSRC_NORMAL_MEM);
-		vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
-	}
-}
-
-void i915_disable_vga_mem(struct drm_device *dev)
-{
-	/* Disable VGA memory on Intel HD */
-	if (HAS_PCH_SPLIT(dev)) {
-		vga_get_uninterruptible(dev->pdev, VGA_RSRC_LEGACY_IO);
-		outb(inb(VGA_MSR_READ) & ~VGA_MSR_MEM_EN, VGA_MSR_WRITE);
-		vga_set_legacy_decoding(dev->pdev, VGA_RSRC_LEGACY_IO |
-						   VGA_RSRC_NORMAL_IO |
-						   VGA_RSRC_NORMAL_MEM);
-		vga_put(dev->pdev, VGA_RSRC_LEGACY_IO);
-	}
-}
-
 void intel_modeset_init_hw(struct drm_device *dev)
 {
 	intel_init_power_well(dev);
@@ -10354,7 +10323,6 @@ void i915_redisable_vga(struct drm_device *dev)
 	if (I915_READ(vga_reg) != VGA_DISP_DISABLE) {
 		DRM_DEBUG_KMS("Something enabled VGA plane, disabling it\n");
 		i915_disable_vga(dev);
-		i915_disable_vga_mem(dev);
 	}
 }
 
@@ -10568,8 +10536,6 @@ void intel_modeset_cleanup(struct drm_device *dev)
 
 	intel_disable_fbc(dev);
 
-	i915_enable_vga_mem(dev);
-
 	intel_disable_gt_powersave(dev);
 
 	ironlake_teardown_rc6(dev);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 79c14e298ba..2c555f91bfa 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1467,7 +1467,7 @@ static void intel_edp_psr_setup(struct intel_dp *intel_dp)
 
 	/* Avoid continuous PSR exit by masking memup and hpd */
 	I915_WRITE(EDP_PSR_DEBUG_CTL, EDP_PSR_DEBUG_MASK_MEMUP |
-		   EDP_PSR_DEBUG_MASK_HPD);
+		   EDP_PSR_DEBUG_MASK_HPD | EDP_PSR_DEBUG_MASK_LPSP);
 
 	intel_dp->psr_setup_done = true;
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 28cae80495e..9b7b68fd5d4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -793,6 +793,5 @@ extern void hsw_pc8_disable_interrupts(struct drm_device *dev);
 extern void hsw_pc8_restore_interrupts(struct drm_device *dev);
 extern void intel_aux_display_runtime_get(struct drm_i915_private *dev_priv);
 extern void intel_aux_display_runtime_put(struct drm_i915_private *dev_priv);
-extern void i915_disable_vga_mem(struct drm_device *dev);
 
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index dd176b7296c..f4c5e95b2d6 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -3864,8 +3864,6 @@ static void valleyview_enable_rps(struct drm_device *dev)
 				      dev_priv->rps.rpe_delay),
 			 dev_priv->rps.rpe_delay);
 
-	INIT_DELAYED_WORK(&dev_priv->rps.vlv_work, vlv_rps_timer_work);
-
 	valleyview_set_rps(dev_priv->dev, dev_priv->rps.rpe_delay);
 
 	gen6_enable_rps_interrupts(dev);
@@ -4955,6 +4953,11 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
 			GEN7_WA_L3_CHICKEN_MODE);
 
+	/* L3 caching of data atomics doesn't work -- disable it. */
+	I915_WRITE(HSW_SCRATCH1, HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE);
+	I915_WRITE(HSW_ROW_CHICKEN3,
+		   _MASKED_BIT_ENABLE(HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE));
+
 	/* This is required by WaCatErrorRejectionIssue:hsw */
 	I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
 			I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
@@ -5681,5 +5684,7 @@ void intel_pm_init(struct drm_device *dev)
 
 	INIT_DELAYED_WORK(&dev_priv->rps.delayed_resume_work,
 			  intel_gen6_powersave_work);
+
+	INIT_DELAYED_WORK(&dev_priv->rps.vlv_work, vlv_rps_timer_work);
 }
 
diff --git a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
index 37712a6df92..e290cfa4ace 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/mc/base.c
@@ -113,7 +113,7 @@ nouveau_mc_create_(struct nouveau_object *parent, struct nouveau_object *engine,
 		pmc->use_msi = false;
 		break;
 	default:
-		pmc->use_msi = nouveau_boolopt(device->cfgopt, "NvMSI", true);
+		pmc->use_msi = nouveau_boolopt(device->cfgopt, "NvMSI", false);
 		if (pmc->use_msi) {
 			pmc->use_msi = pci_enable_msi(device->pdev) == 0;
 			if (pmc->use_msi) {
diff --git a/drivers/gpu/drm/radeon/btc_dpm.c b/drivers/gpu/drm/radeon/btc_dpm.c
index b162e98a295..9b6950d9b3c 100644
--- a/drivers/gpu/drm/radeon/btc_dpm.c
+++ b/drivers/gpu/drm/radeon/btc_dpm.c
@@ -1930,7 +1930,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			tmp = RREG32(MC_PMG_CMD_MRS);
@@ -1945,7 +1945,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		case MC_SEQ_RESERVE_M >> 2:
@@ -1959,7 +1959,7 @@ static int btc_set_mc_special_registers(struct radeon_device *rdev,
 			}
 			j++;
 
-			if (j > SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_EVERGREEN_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index d02fd1c045d..b874ccdf52f 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -77,6 +77,8 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev);
 static void cik_program_aspm(struct radeon_device *rdev);
 static void cik_init_pg(struct radeon_device *rdev);
 static void cik_init_cg(struct radeon_device *rdev);
+static void cik_fini_pg(struct radeon_device *rdev);
+static void cik_fini_cg(struct radeon_device *rdev);
 static void cik_enable_gui_idle_interrupt(struct radeon_device *rdev,
 					  bool enable);
 
@@ -4185,6 +4187,10 @@ static void cik_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable CG/PG */
+	cik_fini_pg(rdev);
+	cik_fini_cg(rdev);
+
 	/* stop the rlc */
 	cik_rlc_stop(rdev);
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 555164e270a..b5c67a99dda 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3131,7 +3131,7 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.sx_max_export_size = 256;
 		rdev->config.evergreen.sx_max_export_pos_size = 64;
 		rdev->config.evergreen.sx_max_export_smx_size = 192;
-		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.max_hw_contexts = 4;
 		rdev->config.evergreen.sq_num_cf_insts = 2;
 
 		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c
index f71ce390aeb..f815c20640b 100644
--- a/drivers/gpu/drm/radeon/evergreen_hdmi.c
+++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c
@@ -288,8 +288,7 @@ void evergreen_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode
 	/* fglrx clears sth in AFMT_AUDIO_PACKET_CONTROL2 here */
 
 	WREG32(HDMI_ACR_PACKET_CONTROL + offset,
-	       HDMI_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI_ACR_SOURCE); /* select SW CTS value */
+	       HDMI_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	evergreen_hdmi_update_ACR(encoder, mode->clock);
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index 8768fd6a1e2..4f6d2962767 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -1501,7 +1501,7 @@
  * 6. COMMAND [29:22] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1516,7 +1516,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index b0fa6002af3..5b729319f27 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -57,15 +57,15 @@ enum r600_hdmi_iec_status_bits {
 static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
     /*	     32kHz	  44.1kHz	48kHz    */
     /* Clock      N     CTS      N     CTS      N     CTS */
-    {  25174,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
+    {  25175,  4576,  28125,  7007,  31250,  6864,  28125 }, /*  25,20/1.001 MHz */
     {  25200,  4096,  25200,  6272,  28000,  6144,  25200 }, /*  25.20       MHz */
     {  27000,  4096,  27000,  6272,  30000,  6144,  27000 }, /*  27.00       MHz */
     {  27027,  4096,  27027,  6272,  30030,  6144,  27027 }, /*  27.00*1.001 MHz */
     {  54000,  4096,  54000,  6272,  60000,  6144,  54000 }, /*  54.00       MHz */
     {  54054,  4096,  54054,  6272,  60060,  6144,  54054 }, /*  54.00*1.001 MHz */
-    {  74175, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
+    {  74176, 11648, 210937, 17836, 234375, 11648, 140625 }, /*  74.25/1.001 MHz */
     {  74250,  4096,  74250,  6272,  82500,  6144,  74250 }, /*  74.25       MHz */
-    { 148351, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
+    { 148352, 11648, 421875,  8918, 234375,  5824, 140625 }, /* 148.50/1.001 MHz */
     { 148500,  4096, 148500,  6272, 165000,  6144, 148500 }, /* 148.50       MHz */
     {      0,  4096,      0,  6272,      0,  6144,      0 }  /* Other */
 };
@@ -75,8 +75,15 @@ static const struct radeon_hdmi_acr r600_hdmi_predefined_acr[] = {
  */
 static void r600_hdmi_calc_cts(uint32_t clock, int *CTS, int N, int freq)
 {
-	if (*CTS == 0)
-		*CTS = clock * N / (128 * freq) * 1000;
+	u64 n;
+	u32 d;
+
+	if (*CTS == 0) {
+		n = (u64)clock * (u64)N * 1000ULL;
+		d = 128 * freq;
+		do_div(n, d);
+		*CTS = n;
+	}
 	DRM_DEBUG("Using ACR timing N=%d CTS=%d for frequency %d\n",
 		  N, *CTS, freq);
 }
@@ -444,8 +451,8 @@ void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mod
 	}
 
 	WREG32(HDMI0_ACR_PACKET_CONTROL + offset,
-	       HDMI0_ACR_AUTO_SEND | /* allow hw to sent ACR packets when required */
-	       HDMI0_ACR_SOURCE); /* select SW CTS value */
+	       HDMI0_ACR_SOURCE | /* select SW CTS value - XXX verify that hw CTS works on all families */
+	       HDMI0_ACR_AUTO_SEND); /* allow hw to sent ACR packets when required */
 
 	WREG32(HDMI0_VBI_PACKET_CONTROL + offset,
 	       HDMI0_NULL_SEND | /* send null packets when required */
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index e673fe26ea8..7b3c7b5932c 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1523,7 +1523,7 @@
  */
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index ac07ad1d4f8..4f6b7fc7ad3 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -945,6 +945,8 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 		if (enable) {
 			mutex_lock(&rdev->pm.mutex);
 			rdev->pm.dpm.uvd_active = true;
+			/* disable this for now */
+#if 0
 			if ((rdev->pm.dpm.sd == 1) && (rdev->pm.dpm.hd == 0))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_SD;
 			else if ((rdev->pm.dpm.sd == 2) && (rdev->pm.dpm.hd == 0))
@@ -954,6 +956,7 @@ void radeon_dpm_enable_uvd(struct radeon_device *rdev, bool enable)
 			else if ((rdev->pm.dpm.sd == 0) && (rdev->pm.dpm.hd == 2))
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD_HD2;
 			else
+#endif
 				dpm_state = POWER_STATE_TYPE_INTERNAL_UVD;
 			rdev->pm.dpm.state = dpm_state;
 			mutex_unlock(&rdev->pm.mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index f4d6bcee900..12e8099a082 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -36,8 +36,8 @@ static void radeon_do_test_moves(struct radeon_device *rdev, int flag)
 	struct radeon_bo *vram_obj = NULL;
 	struct radeon_bo **gtt_obj = NULL;
 	uint64_t gtt_addr, vram_addr;
-	unsigned i, n, size;
-	int r, ring;
+	unsigned n, size;
+	int i, r, ring;
 
 	switch (flag) {
 	case RADEON_TEST_COPY_DMA:
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index a0f11856ddd..4f2e73f7963 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -798,7 +798,8 @@ void radeon_uvd_note_usage(struct radeon_device *rdev)
 		    (rdev->pm.dpm.hd != hd)) {
 			rdev->pm.dpm.sd = sd;
 			rdev->pm.dpm.hd = hd;
-			streams_changed = true;
+			/* disable this for now */
+			/*streams_changed = true;*/
 		}
 	}
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index c354c109496..d4652af425b 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -85,6 +85,9 @@ extern void si_dma_vm_set_page(struct radeon_device *rdev,
 			       uint32_t incr, uint32_t flags);
 static void si_enable_gui_idle_interrupt(struct radeon_device *rdev,
 					 bool enable);
+static void si_fini_pg(struct radeon_device *rdev);
+static void si_fini_cg(struct radeon_device *rdev);
+static void si_rlc_stop(struct radeon_device *rdev);
 
 static const u32 verde_rlc_save_restore_register_list[] =
 {
@@ -3608,6 +3611,13 @@ static void si_gpu_soft_reset(struct radeon_device *rdev, u32 reset_mask)
 	dev_info(rdev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
 		 RREG32(VM_CONTEXT1_PROTECTION_FAULT_STATUS));
 
+	/* disable PG/CG */
+	si_fini_pg(rdev);
+	si_fini_cg(rdev);
+
+	/* stop the rlc */
+	si_rlc_stop(rdev);
+
 	/* Disable CP parsing/prefetching */
 	WREG32(CP_ME_CNTL, CP_ME_HALT | CP_PFP_HALT | CP_CE_HALT);
 
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 9ace28702c7..2332aa1bf93 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -5208,7 +5208,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] |= 0x100;
 			}
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 
 			if (!pi->mem_gddr5) {
@@ -5218,7 +5218,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					table->mc_reg_table_entry[k].mc_data[j] =
 						(table->mc_reg_table_entry[k].mc_data[i] & 0xffff0000) >> 16;
 				j++;
-				if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+				if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 					return -EINVAL;
 			}
 			break;
@@ -5231,7 +5231,7 @@ static int si_set_mc_special_registers(struct radeon_device *rdev,
 					(temp_reg & 0xffff0000) |
 					(table->mc_reg_table_entry[k].mc_data[i] & 0x0000ffff);
 			j++;
-			if (j > SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
+			if (j >= SMC_SISLANDS_MC_REGISTER_ARRAY_SIZE)
 				return -EINVAL;
 			break;
 		default:
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 52d2ab6b67a..7e2e0ea66a0 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -1553,7 +1553,7 @@
  * 6. COMMAND [30:21] | BYTE_COUNT [20:0]
  */
 #              define PACKET3_CP_DMA_DST_SEL(x)    ((x) << 20)
-                /* 0 - SRC_ADDR
+                /* 0 - DST_ADDR
 		 * 1 - GDS
 		 */
 #              define PACKET3_CP_DMA_ENGINE(x)     ((x) << 27)
@@ -1568,7 +1568,7 @@
 #              define PACKET3_CP_DMA_CP_SYNC       (1 << 31)
 /* COMMAND */
 #              define PACKET3_CP_DMA_DIS_WC        (1 << 21)
-#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+#              define PACKET3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 22)
                 /* 0 - none
 		 * 1 - 8 in 16
 		 * 2 - 8 in 32
diff --git a/drivers/gpu/drm/radeon/trinity_dpm.c b/drivers/gpu/drm/radeon/trinity_dpm.c
index 7f998bf1cc9..9364129ba29 100644
--- a/drivers/gpu/drm/radeon/trinity_dpm.c
+++ b/drivers/gpu/drm/radeon/trinity_dpm.c
@@ -1868,7 +1868,7 @@ int trinity_dpm_init(struct radeon_device *rdev)
 	for (i = 0; i < SUMO_MAX_HARDWARE_POWERLEVELS; i++)
 		pi->at[i] = TRINITY_AT_DFLT;
 
-	pi->enable_bapm = true;
+	pi->enable_bapm = false;
 	pi->enable_nbps_policy = true;
 	pi->enable_sclk_ds = true;
 	pi->enable_gfx_power_gating = true;
diff --git a/include/linux/vgaarb.h b/include/linux/vgaarb.h
index 80cf8173a65..2c02f3a8d2b 100644
--- a/include/linux/vgaarb.h
+++ b/include/linux/vgaarb.h
@@ -65,15 +65,8 @@ struct pci_dev;
  *     out of the arbitration process (and can be safe to take
  *     interrupts at any time.
  */
-#if defined(CONFIG_VGA_ARB)
 extern void vga_set_legacy_decoding(struct pci_dev *pdev,
 				    unsigned int decodes);
-#else
-static inline void vga_set_legacy_decoding(struct pci_dev *pdev,
-					   unsigned int decodes)
-{
-}
-#endif
 
 /**
  *     vga_get         - acquire & locks VGA resources