Merge with mainline to remove plat-omap/Kconfig conflict

Conflicts:
	arch/arm/plat-omap/Kconfig

32 files changed, 466 insertions, 288 deletions

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index f665b05592f3..ab6c97330412 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -598,6 +598,50 @@ struct drm_display_mode *drm_mode_std(struct drm_device *dev,
 	return mode;
 }
 
+/*
+ * EDID is delightfully ambiguous about how interlaced modes are to be
+ * encoded.  Our internal representation is of frame height, but some
+ * HDTV detailed timings are encoded as field height.
+ *
+ * The format list here is from CEA, in frame size.  Technically we
+ * should be checking refresh rate too.  Whatever.
+ */
+static void
+drm_mode_do_interlace_quirk(struct drm_display_mode *mode,
+			    struct detailed_pixel_timing *pt)
+{
+	int i;
+	static const struct {
+		int w, h;
+	} cea_interlaced[] = {
+		{ 1920, 1080 },
+		{  720,  480 },
+		{ 1440,  480 },
+		{ 2880,  480 },
+		{  720,  576 },
+		{ 1440,  576 },
+		{ 2880,  576 },
+	};
+	static const int n_sizes =
+		sizeof(cea_interlaced)/sizeof(cea_interlaced[0]);
+
+	if (!(pt->misc & DRM_EDID_PT_INTERLACED))
+		return;
+
+	for (i = 0; i < n_sizes; i++) {
+		if ((mode->hdisplay == cea_interlaced[i].w) &&
+		    (mode->vdisplay == cea_interlaced[i].h / 2)) {
+			mode->vdisplay *= 2;
+			mode->vsync_start *= 2;
+			mode->vsync_end *= 2;
+			mode->vtotal *= 2;
+			mode->vtotal |= 1;
+		}
+	}
+
+	mode->flags |= DRM_MODE_FLAG_INTERLACE;
+}
+
 /**
  * drm_mode_detailed - create a new mode from an EDID detailed timing section
  * @dev: DRM device (needed to create new mode)
@@ -680,8 +724,7 @@ static struct drm_display_mode *drm_mode_detailed(struct drm_device *dev,
 
 	drm_mode_set_name(mode);
 
-	if (pt->misc & DRM_EDID_PT_INTERLACED)
-		mode->flags |= DRM_MODE_FLAG_INTERLACE;
+	drm_mode_do_interlace_quirk(mode, pt);
 
 	if (quirks & EDID_QUIRK_DETAILED_SYNC_PP) {
 		pt->misc |= DRM_EDID_PT_HSYNC_POSITIVE | DRM_EDID_PT_VSYNC_POSITIVE;
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index cdec32977129..2ac074c8f5d2 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -405,7 +405,8 @@ struct drm_mm_node *drm_mm_search_free_in_range(const struct drm_mm *mm,
 				wasted += alignment - tmp;
 		}
 
-		if (entry->size >= size + wasted) {
+		if (entry->size >= size + wasted &&
+		    (entry->start + wasted + size) <= end) {
 			if (!best_match)
 				return entry;
 			if (entry->size < best_size) {
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 79beffcf5936..cf4cb3e9a0c2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -176,6 +176,8 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static int i915_drm_freeze(struct drm_device *dev)
 {
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
 	pci_save_state(dev->pdev);
 
 	/* If KMS is active, we do the leavevt stuff here */
@@ -191,17 +193,12 @@ static int i915_drm_freeze(struct drm_device *dev)
 
 	i915_save_state(dev);
 
-	return 0;
-}
-
-static void i915_drm_suspend(struct drm_device *dev)
-{
-	struct drm_i915_private *dev_priv = dev->dev_private;
-
 	intel_opregion_free(dev, 1);
 
 	/* Modeset on resume, not lid events */
 	dev_priv->modeset_on_lid = 0;
+
+	return 0;
 }
 
 static int i915_suspend(struct drm_device *dev, pm_message_t state)
@@ -221,8 +218,6 @@ static int i915_suspend(struct drm_device *dev, pm_message_t state)
 	if (error)
 		return error;
 
-	i915_drm_suspend(dev);
-
 	if (state.event == PM_EVENT_SUSPEND) {
 		/* Shut down the device */
 		pci_disable_device(dev->pdev);
@@ -237,6 +232,10 @@ static int i915_drm_thaw(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int error = 0;
 
+	i915_restore_state(dev);
+
+	intel_opregion_init(dev, 1);
+
 	/* KMS EnterVT equivalent */
 	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
 		mutex_lock(&dev->struct_mutex);
@@ -263,10 +262,6 @@ static int i915_resume(struct drm_device *dev)
 
 	pci_set_master(dev->pdev);
 
-	i915_restore_state(dev);
-
-	intel_opregion_init(dev, 1);
-
 	return i915_drm_thaw(dev);
 }
 
@@ -423,8 +418,6 @@ static int i915_pm_suspend(struct device *dev)
 	if (error)
 		return error;
 
-	i915_drm_suspend(drm_dev);
-
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, PCI_D3hot);
 
@@ -464,13 +457,8 @@ static int i915_pm_poweroff(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	int error;
-
-	error = i915_drm_freeze(drm_dev);
-	if (!error)
-		i915_drm_suspend(drm_dev);
 
-	return error;
+	return i915_drm_freeze(drm_dev);
 }
 
 const struct dev_pm_ops i915_pm_ops = {
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index b1d0acbae4e4..c2e8a45780d5 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -636,6 +636,13 @@ static const struct dmi_system_id bad_lid_status[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "PC-81005"),
 		},
 	},
+	{
+		.ident = "Clevo M5x0N",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "CLEVO Co."),
+			DMI_MATCH(DMI_BOARD_NAME, "M5x0N"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.c b/drivers/gpu/drm/nouveau/nouveau_bios.c
index 2cd0fad17dac..0e9cd1d49130 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.c
@@ -5861,13 +5861,12 @@ nouveau_bios_run_init_table(struct drm_device *dev, uint16_t table,
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nvbios *bios = &dev_priv->VBIOS;
 	struct init_exec iexec = { true, false };
-	unsigned long flags;
 
-	spin_lock_irqsave(&bios->lock, flags);
+	mutex_lock(&bios->lock);
 	bios->display.output = dcbent;
 	parse_init_table(bios, table, &iexec);
 	bios->display.output = NULL;
-	spin_unlock_irqrestore(&bios->lock, flags);
+	mutex_unlock(&bios->lock);
 }
 
 static bool NVInitVBIOS(struct drm_device *dev)
@@ -5876,7 +5875,7 @@ static bool NVInitVBIOS(struct drm_device *dev)
 	struct nvbios *bios = &dev_priv->VBIOS;
 
 	memset(bios, 0, sizeof(struct nvbios));
-	spin_lock_init(&bios->lock);
+	mutex_init(&bios->lock);
 	bios->dev = dev;
 
 	if (!NVShadowVBIOS(dev, bios->data))
diff --git a/drivers/gpu/drm/nouveau/nouveau_bios.h b/drivers/gpu/drm/nouveau/nouveau_bios.h
index 68446fd4146b..fd94bd6dc264 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bios.h
+++ b/drivers/gpu/drm/nouveau/nouveau_bios.h
@@ -205,7 +205,7 @@ struct nvbios {
 	struct drm_device *dev;
 	struct nouveau_bios_info pub;
 
-	spinlock_t lock;
+	struct mutex lock;
 
 	uint8_t data[NV_PROM_SIZE];
 	unsigned int length;
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 5445cefdd03e..1c15ef37b71c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -583,6 +583,7 @@ struct drm_nouveau_private {
 	uint64_t vm_end;
 	struct nouveau_gpuobj *vm_vram_pt[NV50_VM_VRAM_NR];
 	int vm_vram_pt_nr;
+	uint64_t vram_sys_base;
 
 	/* the mtrr covering the FB */
 	int fb_mtrr;
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 8f3a12f614ed..2dc09dbd817d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -285,53 +285,50 @@ nv50_mem_vm_bind_linear(struct drm_device *dev, uint64_t virt, uint32_t size,
 			uint32_t flags, uint64_t phys)
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
-	struct nouveau_gpuobj **pgt;
-	unsigned psz, pfl, pages;
-
-	if (virt >= dev_priv->vm_gart_base &&
-	    (virt + size) < (dev_priv->vm_gart_base + dev_priv->vm_gart_size)) {
-		psz = 12;
-		pgt = &dev_priv->gart_info.sg_ctxdma;
-		pfl = 0x21;
-		virt -= dev_priv->vm_gart_base;
-	} else
-	if (virt >= dev_priv->vm_vram_base &&
-	    (virt + size) < (dev_priv->vm_vram_base + dev_priv->vm_vram_size)) {
-		psz = 16;
-		pgt = dev_priv->vm_vram_pt;
-		pfl = 0x01;
-		virt -= dev_priv->vm_vram_base;
-	} else {
-		NV_ERROR(dev, "Invalid address: 0x%16llx-0x%16llx\n",
-			 virt, virt + size - 1);
-		return -EINVAL;
-	}
+	struct nouveau_gpuobj *pgt;
+	unsigned block;
+	int i;
 
-	pages = size >> psz;
+	virt = ((virt - dev_priv->vm_vram_base) >> 16) << 1;
+	size = (size >> 16) << 1;
+
+	phys |= ((uint64_t)flags << 32);
+	phys |= 1;
+	if (dev_priv->vram_sys_base) {
+		phys += dev_priv->vram_sys_base;
+		phys |= 0x30;
+	}
 
 	dev_priv->engine.instmem.prepare_access(dev, true);
-	if (flags & 0x80000000) {
-		while (pages--) {
-			struct nouveau_gpuobj *pt = pgt[virt >> 29];
-			unsigned pte = ((virt & 0x1fffffffULL) >> psz) << 1;
+	while (size) {
+		unsigned offset_h = upper_32_bits(phys);
+		unsigned offset_l = lower_32_bits(phys);
+		unsigned pte, end;
+
+		for (i = 7; i >= 0; i--) {
+			block = 1 << (i + 1);
+			if (size >= block && !(virt & (block - 1)))
+				break;
+		}
+		offset_l |= (i << 7);
 
-			nv_wo32(dev, pt, pte++, 0x00000000);
-			nv_wo32(dev, pt, pte++, 0x00000000);
+		phys += block << 15;
+		size -= block;
 
-			virt += (1 << psz);
-		}
-	} else {
-		while (pages--) {
-			struct nouveau_gpuobj *pt = pgt[virt >> 29];
-			unsigned pte = ((virt & 0x1fffffffULL) >> psz) << 1;
-			unsigned offset_h = upper_32_bits(phys) & 0xff;
-			unsigned offset_l = lower_32_bits(phys);
+		while (block) {
+			pgt = dev_priv->vm_vram_pt[virt >> 14];
+			pte = virt & 0x3ffe;
 
-			nv_wo32(dev, pt, pte++, offset_l | pfl);
-			nv_wo32(dev, pt, pte++, offset_h | flags);
+			end = pte + block;
+			if (end > 16384)
+				end = 16384;
+			block -= (end - pte);
+			virt  += (end - pte);
 
-			phys += (1 << psz);
-			virt += (1 << psz);
+			while (pte < end) {
+				nv_wo32(dev, pgt, pte++, offset_l);
+				nv_wo32(dev, pgt, pte++, offset_h);
+			}
 		}
 	}
 	dev_priv->engine.instmem.finish_access(dev);
@@ -356,7 +353,41 @@ nv50_mem_vm_bind_linear(struct drm_device *dev, uint64_t virt, uint32_t size,
 void
 nv50_mem_vm_unbind(struct drm_device *dev, uint64_t virt, uint32_t size)
 {
-	nv50_mem_vm_bind_linear(dev, virt, size, 0x80000000, 0);
+	struct drm_nouveau_private *dev_priv = dev->dev_private;
+	struct nouveau_gpuobj *pgt;
+	unsigned pages, pte, end;
+
+	virt -= dev_priv->vm_vram_base;
+	pages = (size >> 16) << 1;
+
+	dev_priv->engine.instmem.prepare_access(dev, true);
+	while (pages) {
+		pgt = dev_priv->vm_vram_pt[virt >> 29];
+		pte = (virt & 0x1ffe0000ULL) >> 15;
+
+		end = pte + pages;
+		if (end > 16384)
+			end = 16384;
+		pages -= (end - pte);
+		virt  += (end - pte) << 15;
+
+		while (pte < end)
+			nv_wo32(dev, pgt, pte++, 0);
+	}
+	dev_priv->engine.instmem.finish_access(dev);
+
+	nv_wr32(dev, 0x100c80, 0x00050001);
+	if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) {
+		NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n");
+		NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80));
+		return;
+	}
+
+	nv_wr32(dev, 0x100c80, 0x00000001);
+	if (!nv_wait(0x100c80, 0x00000001, 0x00000000)) {
+		NV_ERROR(dev, "timeout: (0x100c80 & 1) == 0 (2)\n");
+		NV_ERROR(dev, "0x100c80 = 0x%08x\n", nv_rd32(dev, 0x100c80));
+	}
 }
 
 /*
diff --git a/drivers/gpu/drm/nouveau/nv04_dac.c b/drivers/gpu/drm/nouveau/nv04_dac.c
index d0e038d28948..1d73b15d70da 100644
--- a/drivers/gpu/drm/nouveau/nv04_dac.c
+++ b/drivers/gpu/drm/nouveau/nv04_dac.c
@@ -119,7 +119,7 @@ static enum drm_connector_status nv04_dac_detect(struct drm_encoder *encoder,
 						 struct drm_connector *connector)
 {
 	struct drm_device *dev = encoder->dev;
-	uint8_t saved_seq1, saved_pi, saved_rpc1;
+	uint8_t saved_seq1, saved_pi, saved_rpc1, saved_cr_mode;
 	uint8_t saved_palette0[3], saved_palette_mask;
 	uint32_t saved_rtest_ctrl, saved_rgen_ctrl;
 	int i;
@@ -135,6 +135,9 @@ static enum drm_connector_status nv04_dac_detect(struct drm_encoder *encoder,
 		/* only implemented for head A for now */
 		NVSetOwner(dev, 0);
 
+	saved_cr_mode = NVReadVgaCrtc(dev, 0, NV_CIO_CR_MODE_INDEX);
+	NVWriteVgaCrtc(dev, 0, NV_CIO_CR_MODE_INDEX, saved_cr_mode | 0x80);
+
 	saved_seq1 = NVReadVgaSeq(dev, 0, NV_VIO_SR_CLOCK_INDEX);
 	NVWriteVgaSeq(dev, 0, NV_VIO_SR_CLOCK_INDEX, saved_seq1 & ~0x20);
 
@@ -203,6 +206,7 @@ out:
 	NVWriteVgaCrtc(dev, 0, NV_CIO_CRE_PIXEL_INDEX, saved_pi);
 	NVWriteVgaCrtc(dev, 0, NV_CIO_CRE_RPC1_INDEX, saved_rpc1);
 	NVWriteVgaSeq(dev, 0, NV_VIO_SR_CLOCK_INDEX, saved_seq1);
+	NVWriteVgaCrtc(dev, 0, NV_CIO_CR_MODE_INDEX, saved_cr_mode);
 
 	if (blue == 0x18) {
 		NV_INFO(dev, "Load detected on head A\n");
diff --git a/drivers/gpu/drm/nouveau/nv17_tv.c b/drivers/gpu/drm/nouveau/nv17_tv.c
index 58b917c3341b..21ac6e49b6ee 100644
--- a/drivers/gpu/drm/nouveau/nv17_tv.c
+++ b/drivers/gpu/drm/nouveau/nv17_tv.c
@@ -579,6 +579,8 @@ static void nv17_tv_restore(struct drm_encoder *encoder)
 				nouveau_encoder(encoder)->restore.output);
 
 	nv17_tv_state_load(dev, &to_tv_enc(encoder)->saved_state);
+
+	nouveau_encoder(encoder)->last_dpms = NV_DPMS_CLEARED;
 }
 
 static int nv17_tv_create_resources(struct drm_encoder *encoder,
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index 94400f777e7f..f0dc4e36ef05 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -76,6 +76,11 @@ nv50_instmem_init(struct drm_device *dev)
 	for (i = 0x1700; i <= 0x1710; i += 4)
 		priv->save1700[(i-0x1700)/4] = nv_rd32(dev, i);
 
+	if (dev_priv->chipset == 0xaa || dev_priv->chipset == 0xac)
+		dev_priv->vram_sys_base = nv_rd32(dev, 0x100e10) << 12;
+	else
+		dev_priv->vram_sys_base = 0;
+
 	/* Reserve the last MiB of VRAM, we should probably try to avoid
 	 * setting up the below tables over the top of the VBIOS image at
 	 * some point.
@@ -172,16 +177,28 @@ nv50_instmem_init(struct drm_device *dev)
 	 * We map the entire fake channel into the start of the PRAMIN BAR
 	 */
 	ret = nouveau_gpuobj_new_ref(dev, chan, NULL, 0, pt_size, 0x1000,
-							0, &priv->pramin_pt);
+				     0, &priv->pramin_pt);
 	if (ret)
 		return ret;
 
-	for (i = 0, v = c_offset; i < pt_size; i += 8, v += 0x1000) {
-		if (v < (c_offset + c_size))
-			BAR0_WI32(priv->pramin_pt->gpuobj, i + 0, v | 1);
-		else
-			BAR0_WI32(priv->pramin_pt->gpuobj, i + 0, 0x00000009);
+	v = c_offset | 1;
+	if (dev_priv->vram_sys_base) {
+		v += dev_priv->vram_sys_base;
+		v |= 0x30;
+	}
+
+	i = 0;
+	while (v < dev_priv->vram_sys_base + c_offset + c_size) {
+		BAR0_WI32(priv->pramin_pt->gpuobj, i + 0, v);
+		BAR0_WI32(priv->pramin_pt->gpuobj, i + 4, 0x00000000);
+		v += 0x1000;
+		i += 8;
+	}
+
+	while (i < pt_size) {
+		BAR0_WI32(priv->pramin_pt->gpuobj, i + 0, 0x00000000);
 		BAR0_WI32(priv->pramin_pt->gpuobj, i + 4, 0x00000000);
+		i += 8;
 	}
 
 	BAR0_WI32(chan->vm_pd, 0x00, priv->pramin_pt->instance | 0x63);
@@ -416,7 +433,9 @@ nv50_instmem_bind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj)
 {
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nv50_instmem_priv *priv = dev_priv->engine.instmem.priv;
-	uint32_t pte, pte_end, vram;
+	struct nouveau_gpuobj *pramin_pt = priv->pramin_pt->gpuobj;
+	uint32_t pte, pte_end;
+	uint64_t vram;
 
 	if (!gpuobj->im_backing || !gpuobj->im_pramin || gpuobj->im_bound)
 		return -EINVAL;
@@ -424,20 +443,24 @@ nv50_instmem_bind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj)
 	NV_DEBUG(dev, "st=0x%0llx sz=0x%0llx\n",
 		 gpuobj->im_pramin->start, gpuobj->im_pramin->size);
 
-	pte     = (gpuobj->im_pramin->start >> 12) << 3;
-	pte_end = ((gpuobj->im_pramin->size >> 12) << 3) + pte;
+	pte     = (gpuobj->im_pramin->start >> 12) << 1;
+	pte_end = ((gpuobj->im_pramin->size >> 12) << 1) + pte;
 	vram    = gpuobj->im_backing_start;
 
 	NV_DEBUG(dev, "pramin=0x%llx, pte=%d, pte_end=%d\n",
 		 gpuobj->im_pramin->start, pte, pte_end);
 	NV_DEBUG(dev, "first vram page: 0x%08x\n", gpuobj->im_backing_start);
 
+	vram |= 1;
+	if (dev_priv->vram_sys_base) {
+		vram += dev_priv->vram_sys_base;
+		vram |= 0x30;
+	}
+
 	dev_priv->engine.instmem.prepare_access(dev, true);
 	while (pte < pte_end) {
-		nv_wo32(dev, priv->pramin_pt->gpuobj, (pte + 0)/4, vram | 1);
-		nv_wo32(dev, priv->pramin_pt->gpuobj, (pte + 4)/4, 0x00000000);
-
-		pte += 8;
+		nv_wo32(dev, pramin_pt, pte++, lower_32_bits(vram));
+		nv_wo32(dev, pramin_pt, pte++, upper_32_bits(vram));
 		vram += NV50_INSTMEM_PAGE_SIZE;
 	}
 	dev_priv->engine.instmem.finish_access(dev);
@@ -470,14 +493,13 @@ nv50_instmem_unbind(struct drm_device *dev, struct nouveau_gpuobj *gpuobj)
 	if (gpuobj->im_bound == 0)
 		return -EINVAL;
 
-	pte     = (gpuobj->im_pramin->start >> 12) << 3;
-	pte_end = ((gpuobj->im_pramin->size >> 12) << 3) + pte;
+	pte     = (gpuobj->im_pramin->start >> 12) << 1;
+	pte_end = ((gpuobj->im_pramin->size >> 12) << 1) + pte;
 
 	dev_priv->engine.instmem.prepare_access(dev, true);
 	while (pte < pte_end) {
-		nv_wo32(dev, priv->pramin_pt->gpuobj, (pte + 0)/4, 0x00000009);
-		nv_wo32(dev, priv->pramin_pt->gpuobj, (pte + 4)/4, 0x00000000);
-		pte += 8;
+		nv_wo32(dev, priv->pramin_pt->gpuobj, pte++, 0x00000000);
+		nv_wo32(dev, priv->pramin_pt->gpuobj, pte++, 0x00000000);
 	}
 	dev_priv->engine.instmem.finish_access(dev);
 
diff --git a/drivers/gpu/drm/radeon/atom.c b/drivers/gpu/drm/radeon/atom.c
index e3b44562d265..7f152f66f196 100644
--- a/drivers/gpu/drm/radeon/atom.c
+++ b/drivers/gpu/drm/radeon/atom.c
@@ -24,6 +24,7 @@
 
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <asm/unaligned.h>
 
 #define ATOM_DEBUG
 
@@ -212,7 +213,9 @@ static uint32_t atom_get_src_int(atom_exec_context *ctx, uint8_t attr,
 	case ATOM_ARG_PS:
 		idx = U8(*ptr);
 		(*ptr)++;
-		val = le32_to_cpu(ctx->ps[idx]);
+		/* get_unaligned_le32 avoids unaligned accesses from atombios
+		 * tables, noticed on a DEC Alpha. */
+		val = get_unaligned_le32((u32 *)&ctx->ps[idx]);
 		if (print)
 			DEBUG("PS[0x%02X,0x%04X]", idx, val);
 		break;
@@ -640,7 +643,7 @@ static void atom_op_delay(atom_exec_context *ctx, int *ptr, int arg)
 	uint8_t count = U8((*ptr)++);
 	SDEBUG("   count: %d\n", count);
 	if (arg == ATOM_UNIT_MICROSEC)
-		schedule_timeout_uninterruptible(usecs_to_jiffies(count));
+		udelay(count);
 	else
 		schedule_timeout_uninterruptible(msecs_to_jiffies(count));
 }
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index b32eeea5bb8b..99915a682d59 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -350,7 +350,7 @@ retry:
 	atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 
 	if (args.ucReplyStatus && !args.ucDataOutLen) {
-		if (args.ucReplyStatus == 0x20 && retry_count < 10)
+		if (args.ucReplyStatus == 0x20 && retry_count++ < 10)
 			goto retry;
 		DRM_DEBUG("failed to get auxch %02x%02x %02x %02x 0x%02x %02x after %d retries\n",
 			  req_bytes[1], req_bytes[0], req_bytes[2], req_bytes[3],
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index af1c3ca8a4cb..446b765ac72a 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -543,9 +543,6 @@ int r600_vb_ib_get(struct radeon_device *rdev)
 void r600_vb_ib_put(struct radeon_device *rdev)
 {
 	radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence);
-	mutex_lock(&rdev->ib_pool.mutex);
-	list_add_tail(&rdev->r600_blit.vb_ib->list, &rdev->ib_pool.scheduled_ibs);
-	mutex_unlock(&rdev->ib_pool.mutex);
 	radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
 }
 
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 6d5a711c2e91..75bcf35a0931 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -1428,9 +1428,12 @@ static void r700_gfx_init(struct drm_device *dev,
 
 	gb_tiling_config |= R600_BANK_SWAPS(1);
 
-	backend_map = r700_get_tile_pipe_to_backend_map(dev_priv->r600_max_tile_pipes,
-							dev_priv->r600_max_backends,
-							(0xff << dev_priv->r600_max_backends) & 0xff);
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV740)
+		backend_map = 0x28;
+	else
+		backend_map = r700_get_tile_pipe_to_backend_map(dev_priv->r600_max_tile_pipes,
+								dev_priv->r600_max_backends,
+								(0xff << dev_priv->r600_max_backends) & 0xff);
 	gb_tiling_config |= R600_BACKEND_MAP(backend_map);
 
 	cc_gc_shader_pipe_config =
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index f57480ba1355..c0356bb193e5 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -96,6 +96,7 @@ extern int radeon_audio;
  * symbol;
  */
 #define RADEON_MAX_USEC_TIMEOUT		100000	/* 100 ms */
+/* RADEON_IB_POOL_SIZE must be a power of 2 */
 #define RADEON_IB_POOL_SIZE		16
 #define RADEON_DEBUGFS_MAX_NUM_FILES	32
 #define RADEONFB_CONN_LIMIT		4
@@ -363,11 +364,12 @@ void radeon_irq_kms_sw_irq_put(struct radeon_device *rdev);
  */
 struct radeon_ib {
 	struct list_head	list;
-	unsigned long		idx;
+	unsigned		idx;
 	uint64_t		gpu_addr;
 	struct radeon_fence	*fence;
-	uint32_t	*ptr;
+	uint32_t		*ptr;
 	uint32_t		length_dw;
+	bool			free;
 };
 
 /*
@@ -377,10 +379,9 @@ struct radeon_ib {
 struct radeon_ib_pool {
 	struct mutex		mutex;
 	struct radeon_bo	*robj;
-	struct list_head	scheduled_ibs;
 	struct radeon_ib	ibs[RADEON_IB_POOL_SIZE];
 	bool			ready;
-	DECLARE_BITMAP(alloc_bm, RADEON_IB_POOL_SIZE);
+	unsigned		head_id;
 };
 
 struct radeon_cp {
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index 2dcda6115874..4d8831548a5f 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -206,6 +206,15 @@ static bool radeon_atom_apply_quirks(struct drm_device *dev,
 			*connector_type = DRM_MODE_CONNECTOR_DVID;
 	}
 
+	/* Asrock RS600 board lists the DVI port as HDMI */
+	if ((dev->pdev->device == 0x7941) &&
+	    (dev->pdev->subsystem_vendor == 0x1849) &&
+	    (dev->pdev->subsystem_device == 0x7941)) {
+		if ((*connector_type == DRM_MODE_CONNECTOR_HDMIA) &&
+		    (supported_device == ATOM_DEVICE_DFP3_SUPPORT))
+			*connector_type = DRM_MODE_CONNECTOR_DVID;
+	}
+
 	/* a-bit f-i90hd - ciaranm on #radeonhd - this board has no DVI */
 	if ((dev->pdev->device == 0x7941) &&
 	    (dev->pdev->subsystem_vendor == 0x147b) &&
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index e7b19440102e..22d476160d52 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -1279,47 +1279,47 @@ bool radeon_get_legacy_connector_info_from_table(struct drm_device *dev)
 	rdev->mode_info.connector_table = radeon_connector_table;
 	if (rdev->mode_info.connector_table == CT_NONE) {
 #ifdef CONFIG_PPC_PMAC
-		if (machine_is_compatible("PowerBook3,3")) {
+		if (of_machine_is_compatible("PowerBook3,3")) {
 			/* powerbook with VGA */
 			rdev->mode_info.connector_table = CT_POWERBOOK_VGA;
-		} else if (machine_is_compatible("PowerBook3,4") ||
-			   machine_is_compatible("PowerBook3,5")) {
+		} else if (of_machine_is_compatible("PowerBook3,4") ||
+			   of_machine_is_compatible("PowerBook3,5")) {
 			/* powerbook with internal tmds */
 			rdev->mode_info.connector_table = CT_POWERBOOK_INTERNAL;
-		} else if (machine_is_compatible("PowerBook5,1") ||
-			   machine_is_compatible("PowerBook5,2") ||
-			   machine_is_compatible("PowerBook5,3") ||
-			   machine_is_compatible("PowerBook5,4") ||
-			   machine_is_compatible("PowerBook5,5")) {
+		} else if (of_machine_is_compatible("PowerBook5,1") ||
+			   of_machine_is_compatible("PowerBook5,2") ||
+			   of_machine_is_compatible("PowerBook5,3") ||
+			   of_machine_is_compatible("PowerBook5,4") ||
+			   of_machine_is_compatible("PowerBook5,5")) {
 			/* powerbook with external single link tmds (sil164) */
 			rdev->mode_info.connector_table = CT_POWERBOOK_EXTERNAL;
-		} else if (machine_is_compatible("PowerBook5,6")) {
+		} else if (of_machine_is_compatible("PowerBook5,6")) {
 			/* powerbook with external dual or single link tmds */
 			rdev->mode_info.connector_table = CT_POWERBOOK_EXTERNAL;
-		} else if (machine_is_compatible("PowerBook5,7") ||
-			   machine_is_compatible("PowerBook5,8") ||
-			   machine_is_compatible("PowerBook5,9")) {
+		} else if (of_machine_is_compatible("PowerBook5,7") ||
+			   of_machine_is_compatible("PowerBook5,8") ||
+			   of_machine_is_compatible("PowerBook5,9")) {
 			/* PowerBook6,2 ? */
 			/* powerbook with external dual link tmds (sil1178?) */
 			rdev->mode_info.connector_table = CT_POWERBOOK_EXTERNAL;
-		} else if (machine_is_compatible("PowerBook4,1") ||
-			   machine_is_compatible("PowerBook4,2") ||
-			   machine_is_compatible("PowerBook4,3") ||
-			   machine_is_compatible("PowerBook6,3") ||
-			   machine_is_compatible("PowerBook6,5") ||
-			   machine_is_compatible("PowerBook6,7")) {
+		} else if (of_machine_is_compatible("PowerBook4,1") ||
+			   of_machine_is_compatible("PowerBook4,2") ||
+			   of_machine_is_compatible("PowerBook4,3") ||
+			   of_machine_is_compatible("PowerBook6,3") ||
+			   of_machine_is_compatible("PowerBook6,5") ||
+			   of_machine_is_compatible("PowerBook6,7")) {
 			/* ibook */
 			rdev->mode_info.connector_table = CT_IBOOK;
-		} else if (machine_is_compatible("PowerMac4,4")) {
+		} else if (of_machine_is_compatible("PowerMac4,4")) {
 			/* emac */
 			rdev->mode_info.connector_table = CT_EMAC;
-		} else if (machine_is_compatible("PowerMac10,1")) {
+		} else if (of_machine_is_compatible("PowerMac10,1")) {
 			/* mini with internal tmds */
 			rdev->mode_info.connector_table = CT_MINI_INTERNAL;
-		} else if (machine_is_compatible("PowerMac10,2")) {
+		} else if (of_machine_is_compatible("PowerMac10,2")) {
 			/* mini with external tmds */
 			rdev->mode_info.connector_table = CT_MINI_EXTERNAL;
-		} else if (machine_is_compatible("PowerMac12,1")) {
+		} else if (of_machine_is_compatible("PowerMac12,1")) {
 			/* PowerMac8,1 ? */
 			/* imac g5 isight */
 			rdev->mode_info.connector_table = CT_IMAC_G5_ISIGHT;
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 238188540017..65f81942f399 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -780,7 +780,7 @@ static enum drm_connector_status radeon_dvi_detect(struct drm_connector *connect
 			 * connected and the DVI port disconnected.  If the edid doesn't
 			 * say HDMI, vice versa.
 			 */
-			if (radeon_connector->shared_ddc && connector_status_connected) {
+			if (radeon_connector->shared_ddc && (ret == connector_status_connected)) {
 				struct drm_device *dev = connector->dev;
 				struct drm_connector *list_connector;
 				struct radeon_connector *list_radeon_connector;
@@ -1060,8 +1060,7 @@ radeon_add_atom_connector(struct drm_device *dev,
 			return;
 		}
 		if (radeon_connector->ddc_bus && i2c_bus->valid) {
-			if (memcmp(&radeon_connector->ddc_bus->rec, i2c_bus,
-				    sizeof(struct radeon_i2c_bus_rec)) == 0) {
+			if (radeon_connector->ddc_bus->rec.i2c_id == i2c_bus->i2c_id) {
 				radeon_connector->shared_ddc = true;
 				shared_ddc = true;
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 1190148cf5e6..e9d085021c1f 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -86,7 +86,7 @@ int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 						&p->validated);
 		}
 	}
-	return radeon_bo_list_validate(&p->validated, p->ib->fence);
+	return radeon_bo_list_validate(&p->validated);
 }
 
 int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
@@ -189,12 +189,10 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error)
 {
 	unsigned i;
 
-	if (error && parser->ib) {
-		radeon_bo_list_unvalidate(&parser->validated,
-						parser->ib->fence);
-	} else {
-		radeon_bo_list_unreserve(&parser->validated);
+	if (!error && parser->ib) {
+		radeon_bo_list_fence(&parser->validated, parser->ib->fence);
 	}
+	radeon_bo_list_unreserve(&parser->validated);
 	for (i = 0; i < parser->nrelocs; i++) {
 		if (parser->relocs[i].gobj) {
 			mutex_lock(&parser->rdev->ddev->struct_mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index e13785282a82..c57ad606504d 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -106,9 +106,10 @@
  * 1.29- R500 3D cmd buffer support
  * 1.30- Add support for occlusion queries
  * 1.31- Add support for num Z pipes from GET_PARAM
+ * 1.32- fixes for rv740 setup
  */
 #define DRIVER_MAJOR		1
-#define DRIVER_MINOR		31
+#define DRIVER_MINOR		32
 #define DRIVER_PATCHLEVEL	0
 
 enum radeon_cp_microcode_version {
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index d72a71bff218..f1da370928eb 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -306,11 +306,10 @@ void radeon_bo_list_unreserve(struct list_head *head)
 	}
 }
 
-int radeon_bo_list_validate(struct list_head *head, void *fence)
+int radeon_bo_list_validate(struct list_head *head)
 {
 	struct radeon_bo_list *lobj;
 	struct radeon_bo *bo;
-	struct radeon_fence *old_fence = NULL;
 	int r;
 
 	r = radeon_bo_list_reserve(head);
@@ -334,32 +333,27 @@ int radeon_bo_list_validate(struct list_head *head, void *fence)
 		}
 		lobj->gpu_offset = radeon_bo_gpu_offset(bo);
 		lobj->tiling_flags = bo->tiling_flags;
-		if (fence) {
-			old_fence = (struct radeon_fence *)bo->tbo.sync_obj;
-			bo->tbo.sync_obj = radeon_fence_ref(fence);
-			bo->tbo.sync_obj_arg = NULL;
-		}
-		if (old_fence) {
-			radeon_fence_unref(&old_fence);
-		}
 	}
 	return 0;
 }
 
-void radeon_bo_list_unvalidate(struct list_head *head, void *fence)
+void radeon_bo_list_fence(struct list_head *head, void *fence)
 {
 	struct radeon_bo_list *lobj;
-	struct radeon_fence *old_fence;
-
-	if (fence)
-		list_for_each_entry(lobj, head, list) {
-			old_fence = to_radeon_fence(lobj->bo->tbo.sync_obj);
-			if (old_fence == fence) {
-				lobj->bo->tbo.sync_obj = NULL;
-				radeon_fence_unref(&old_fence);
-			}
+	struct radeon_bo *bo;
+	struct radeon_fence *old_fence = NULL;
+
+	list_for_each_entry(lobj, head, list) {
+		bo = lobj->bo;
+		spin_lock(&bo->tbo.lock);
+		old_fence = (struct radeon_fence *)bo->tbo.sync_obj;
+		bo->tbo.sync_obj = radeon_fence_ref(fence);
+		bo->tbo.sync_obj_arg = NULL;
+		spin_unlock(&bo->tbo.lock);
+		if (old_fence) {
+			radeon_fence_unref(&old_fence);
 		}
-	radeon_bo_list_unreserve(head);
+	}
 }
 
 int radeon_bo_fbdev_mmap(struct radeon_bo *bo,
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index a02f18011ad1..7ab43de1e244 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -156,8 +156,8 @@ extern void radeon_bo_list_add_object(struct radeon_bo_list *lobj,
 				struct list_head *head);
 extern int radeon_bo_list_reserve(struct list_head *head);
 extern void radeon_bo_list_unreserve(struct list_head *head);
-extern int radeon_bo_list_validate(struct list_head *head, void *fence);
-extern void radeon_bo_list_unvalidate(struct list_head *head, void *fence);
+extern int radeon_bo_list_validate(struct list_head *head);
+extern void radeon_bo_list_fence(struct list_head *head, void *fence);
 extern int radeon_bo_fbdev_mmap(struct radeon_bo *bo,
 				struct vm_area_struct *vma);
 extern int radeon_bo_set_tiling_flags(struct radeon_bo *bo,
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 4d12b2d17b4d..6579eb4c1f28 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -41,68 +41,55 @@ int radeon_ib_get(struct radeon_device *rdev, struct radeon_ib **ib)
 {
 	struct radeon_fence *fence;
 	struct radeon_ib *nib;
-	unsigned long i;
-	int r = 0;
+	int r = 0, i, c;
 
 	*ib = NULL;
 	r = radeon_fence_create(rdev, &fence);
 	if (r) {
-		DRM_ERROR("failed to create fence for new IB\n");
+		dev_err(rdev->dev, "failed to create fence for new IB\n");
 		return r;
 	}
 	mutex_lock(&rdev->ib_pool.mutex);
-	i = find_first_zero_bit(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
-	if (i < RADEON_IB_POOL_SIZE) {
-		set_bit(i, rdev->ib_pool.alloc_bm);
-		rdev->ib_pool.ibs[i].length_dw = 0;
-		*ib = &rdev->ib_pool.ibs[i];
-		mutex_unlock(&rdev->ib_pool.mutex);
-		goto out;
+	for (i = rdev->ib_pool.head_id, c = 0, nib = NULL; c < RADEON_IB_POOL_SIZE; c++, i++) {
+		i &= (RADEON_IB_POOL_SIZE - 1);
+		if (rdev->ib_pool.ibs[i].free) {
+			nib = &rdev->ib_pool.ibs[i];
+			break;
+		}
 	}
-	if (list_empty(&rdev->ib_pool.scheduled_ibs)) {
-		/* we go do nothings here */
+	if (nib == NULL) {
+		/* This should never happen, it means we allocated all
+		 * IB and haven't scheduled one yet, return EBUSY to
+		 * userspace hoping that on ioctl recall we get better
+		 * luck
+		 */
+		dev_err(rdev->dev, "no free indirect buffer !\n");
 		mutex_unlock(&rdev->ib_pool.mutex);
-		DRM_ERROR("all IB allocated none scheduled.\n");
-		r = -EINVAL;
-		goto out;
+		radeon_fence_unref(&fence);
+		return -EBUSY;
 	}
-	/* get the first ib on the scheduled list */
-	nib = list_entry(rdev->ib_pool.scheduled_ibs.next,
-			 struct radeon_ib, list);
-	if (nib->fence == NULL) {
-		/* we go do nothings here */
+	rdev->ib_pool.head_id = (nib->idx + 1) & (RADEON_IB_POOL_SIZE - 1);
+	nib->free = false;
+	if (nib->fence) {
 		mutex_unlock(&rdev->ib_pool.mutex);
-		DRM_ERROR("IB %lu scheduled without a fence.\n", nib->idx);
-		r = -EINVAL;
-		goto out;
-	}
-	mutex_unlock(&rdev->ib_pool.mutex);
-
-	r = radeon_fence_wait(nib->fence, false);
-	if (r) {
-		DRM_ERROR("radeon: IB(%lu:0x%016lX:%u)\n", nib->idx,
-			  (unsigned long)nib->gpu_addr, nib->length_dw);
-		DRM_ERROR("radeon: GPU lockup detected, fail to get a IB\n");
-		goto out;
+		r = radeon_fence_wait(nib->fence, false);
+		if (r) {
+			dev_err(rdev->dev, "error waiting fence of IB(%u:0x%016lX:%u)\n",
+				nib->idx, (unsigned long)nib->gpu_addr, nib->length_dw);
+			mutex_lock(&rdev->ib_pool.mutex);
+			nib->free = true;
+			mutex_unlock(&rdev->ib_pool.mutex);
+			radeon_fence_unref(&fence);
+			return r;
+		}
+		mutex_lock(&rdev->ib_pool.mutex);
 	}
 	radeon_fence_unref(&nib->fence);
-
+	nib->fence = fence;
 	nib->length_dw = 0;
-
-	/* scheduled list is accessed here */
-	mutex_lock(&rdev->ib_pool.mutex);
-	list_del(&nib->list);
-	INIT_LIST_HEAD(&nib->list);
 	mutex_unlock(&rdev->ib_pool.mutex);
-
 	*ib = nib;
-out:
-	if (r) {
-		radeon_fence_unref(&fence);
-	} else {
-		(*ib)->fence = fence;
-	}
-	return r;
+	return 0;
 }
 
 void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
@@ -113,19 +100,10 @@ void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
 	if (tmp == NULL) {
 		return;
 	}
-	mutex_lock(&rdev->ib_pool.mutex);
-	if (!list_empty(&tmp->list) && !radeon_fence_signaled(tmp->fence)) {
-		/* IB is scheduled & not signaled don't do anythings */
-		mutex_unlock(&rdev->ib_pool.mutex);
-		return;
-	}
-	list_del(&tmp->list);
-	INIT_LIST_HEAD(&tmp->list);
-	if (tmp->fence)
+	if (!tmp->fence->emited)
 		radeon_fence_unref(&tmp->fence);
-
-	tmp->length_dw = 0;
-	clear_bit(tmp->idx, rdev->ib_pool.alloc_bm);
+	mutex_lock(&rdev->ib_pool.mutex);
+	tmp->free = true;
 	mutex_unlock(&rdev->ib_pool.mutex);
 }
 
@@ -135,7 +113,7 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 
 	if (!ib->length_dw || !rdev->cp.ready) {
 		/* TODO: Nothings in the ib we should report. */
-		DRM_ERROR("radeon: couldn't schedule IB(%lu).\n", ib->idx);
+		DRM_ERROR("radeon: couldn't schedule IB(%u).\n", ib->idx);
 		return -EINVAL;
 	}
 
@@ -148,7 +126,8 @@ int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
 	radeon_ring_ib_execute(rdev, ib);
 	radeon_fence_emit(rdev, ib->fence);
 	mutex_lock(&rdev->ib_pool.mutex);
-	list_add_tail(&ib->list, &rdev->ib_pool.scheduled_ibs);
+	/* once scheduled IB is considered free and protected by the fence */
+	ib->free = true;
 	mutex_unlock(&rdev->ib_pool.mutex);
 	radeon_ring_unlock_commit(rdev);
 	return 0;
@@ -164,7 +143,6 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 	if (rdev->ib_pool.robj)
 		return 0;
 	/* Allocate 1M object buffer */
-	INIT_LIST_HEAD(&rdev->ib_pool.scheduled_ibs);
 	r = radeon_bo_create(rdev, NULL,  RADEON_IB_POOL_SIZE*64*1024,
 				true, RADEON_GEM_DOMAIN_GTT,
 				&rdev->ib_pool.robj);
@@ -195,9 +173,9 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 		rdev->ib_pool.ibs[i].ptr = ptr + offset;
 		rdev->ib_pool.ibs[i].idx = i;
 		rdev->ib_pool.ibs[i].length_dw = 0;
-		INIT_LIST_HEAD(&rdev->ib_pool.ibs[i].list);
+		rdev->ib_pool.ibs[i].free = true;
 	}
-	bitmap_zero(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
+	rdev->ib_pool.head_id = 0;
 	rdev->ib_pool.ready = true;
 	DRM_INFO("radeon: ib pool ready.\n");
 	if (radeon_debugfs_ib_init(rdev)) {
@@ -214,7 +192,6 @@ void radeon_ib_pool_fini(struct radeon_device *rdev)
 		return;
 	}
 	mutex_lock(&rdev->ib_pool.mutex);
-	bitmap_zero(rdev->ib_pool.alloc_bm, RADEON_IB_POOL_SIZE);
 	if (rdev->ib_pool.robj) {
 		r = radeon_bo_reserve(rdev->ib_pool.robj, false);
 		if (likely(r == 0)) {
@@ -363,7 +340,7 @@ static int radeon_debugfs_ib_info(struct seq_file *m, void *data)
 	if (ib == NULL) {
 		return 0;
 	}
-	seq_printf(m, "IB %04lu\n", ib->idx);
+	seq_printf(m, "IB %04u\n", ib->idx);
 	seq_printf(m, "IB fence %p\n", ib->fence);
 	seq_printf(m, "IB size %05u dwords\n", ib->length_dw);
 	for (i = 0; i < ib->length_dw; i++) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 5943d561fd1e..03021674d097 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -549,9 +549,12 @@ static void rv770_gpu_init(struct radeon_device *rdev)
 
 	gb_tiling_config |= BANK_SWAPS(1);
 
-	backend_map = r700_get_tile_pipe_to_backend_map(rdev->config.rv770.max_tile_pipes,
-							rdev->config.rv770.max_backends,
-							(0xff << rdev->config.rv770.max_backends) & 0xff);
+	if (rdev->family == CHIP_RV740)
+		backend_map = 0x28;
+	else
+		backend_map = r700_get_tile_pipe_to_backend_map(rdev->config.rv770.max_tile_pipes,
+								rdev->config.rv770.max_backends,
+								(0xff << rdev->config.rv770.max_backends) & 0xff);
 	gb_tiling_config |= BACKEND_MAP(backend_map);
 
 	cc_gc_shader_pipe_config =
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 1a3e909b7bba..c7320ce4567d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1020,6 +1020,12 @@ static int ttm_bo_mem_compat(struct ttm_placement *placement,
 			     struct ttm_mem_reg *mem)
 {
 	int i;
+	struct drm_mm_node *node = mem->mm_node;
+
+	if (node && placement->lpfn != 0 &&
+	    (node->start < placement->fpfn ||
+	     node->start + node->size > placement->lpfn))
+		return -1;
 
 	for (i = 0; i < placement->num_placement; i++) {
 		if ((placement->placement[i] & mem->placement &
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index e2123af7775a..3d47a2c12322 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -196,14 +196,15 @@ EXPORT_SYMBOL(ttm_tt_populate);
 
 #ifdef CONFIG_X86
 static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_state)
+					  enum ttm_caching_state c_old,
+					  enum ttm_caching_state c_new)
 {
 	int ret = 0;
 
 	if (PageHighMem(p))
 		return 0;
 
-	if (get_page_memtype(p) != -1) {
+	if (c_old != tt_cached) {
 		/* p isn't in the default caching state, set it to
 		 * writeback first to free its current memtype. */
 
@@ -212,16 +213,17 @@ static inline int ttm_tt_set_page_caching(struct page *p,
 			return ret;
 	}
 
-	if (c_state == tt_wc)
+	if (c_new == tt_wc)
 		ret = set_memory_wc((unsigned long) page_address(p), 1);
-	else if (c_state == tt_uncached)
+	else if (c_new == tt_uncached)
 		ret = set_pages_uc(p, 1);
 
 	return ret;
 }
 #else /* CONFIG_X86 */
 static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_state)
+					  enum ttm_caching_state c_old,
+					  enum ttm_caching_state c_new)
 {
 	return 0;
 }
@@ -254,7 +256,9 @@ static int ttm_tt_set_caching(struct ttm_tt *ttm,
 	for (i = 0; i < ttm->num_pages; ++i) {
 		cur_page = ttm->pages[i];
 		if (likely(cur_page != NULL)) {
-			ret = ttm_tt_set_page_caching(cur_page, c_state);
+			ret = ttm_tt_set_page_caching(cur_page,
+						      ttm->caching_state,
+						      c_state);
 			if (unlikely(ret != 0))
 				goto out_err;
 		}
@@ -268,7 +272,7 @@ out_err:
 	for (j = 0; j < i; ++j) {
 		cur_page = ttm->pages[j];
 		if (likely(cur_page != NULL)) {
-			(void)ttm_tt_set_page_caching(cur_page,
+			(void)ttm_tt_set_page_caching(cur_page, c_state,
 						      ttm->caching_state);
 		}
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index a6e8f687fa64..0c9c0811f42d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -348,22 +348,19 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 		 */
 
 		DRM_INFO("It appears like vesafb is loaded. "
-			 "Ignore above error if any. Entering stealth mode.\n");
+			 "Ignore above error if any.\n");
 		ret = pci_request_region(dev->pdev, 2, "vmwgfx stealth probe");
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Failed reserving the SVGA MMIO resource.\n");
 			goto out_no_device;
 		}
-		vmw_kms_init(dev_priv);
-		vmw_overlay_init(dev_priv);
-	} else {
-		ret = vmw_request_device(dev_priv);
-		if (unlikely(ret != 0))
-			goto out_no_device;
-		vmw_kms_init(dev_priv);
-		vmw_overlay_init(dev_priv);
-		vmw_fb_init(dev_priv);
 	}
+	ret = vmw_request_device(dev_priv);
+	if (unlikely(ret != 0))
+		goto out_no_device;
+	vmw_kms_init(dev_priv);
+	vmw_overlay_init(dev_priv);
+	vmw_fb_init(dev_priv);
 
 	dev_priv->pm_nb.notifier_call = vmwgfx_pm_notifier;
 	register_pm_notifier(&dev_priv->pm_nb);
@@ -406,17 +403,15 @@ static int vmw_driver_unload(struct drm_device *dev)
 
 	unregister_pm_notifier(&dev_priv->pm_nb);
 
-	if (!dev_priv->stealth) {
-		vmw_fb_close(dev_priv);
-		vmw_kms_close(dev_priv);
-		vmw_overlay_close(dev_priv);
-		vmw_release_device(dev_priv);
-		pci_release_regions(dev->pdev);
-	} else {
-		vmw_kms_close(dev_priv);
-		vmw_overlay_close(dev_priv);
+	vmw_fb_close(dev_priv);
+	vmw_kms_close(dev_priv);
+	vmw_overlay_close(dev_priv);
+	vmw_release_device(dev_priv);
+	if (dev_priv->stealth)
 		pci_release_region(dev->pdev, 2);
-	}
+	else
+		pci_release_regions(dev->pdev);
+
 	if (dev_priv->capabilities & SVGA_CAP_IRQMASK)
 		drm_irq_uninstall(dev_priv->dev);
 	if (dev->devname == vmw_devname)
@@ -585,11 +580,6 @@ static int vmw_master_set(struct drm_device *dev,
 	int ret = 0;
 
 	DRM_INFO("Master set.\n");
-	if (dev_priv->stealth) {
-		ret = vmw_request_device(dev_priv);
-		if (unlikely(ret != 0))
-			return ret;
-	}
 
 	if (active) {
 		BUG_ON(active != &dev_priv->fbdev_master);
@@ -649,18 +639,11 @@ static void vmw_master_drop(struct drm_device *dev,
 
 	ttm_lock_set_kill(&vmaster->lock, true, SIGTERM);
 
-	if (dev_priv->stealth) {
-		ret = ttm_bo_evict_mm(&dev_priv->bdev, TTM_PL_VRAM);
-		if (unlikely(ret != 0))
-			DRM_ERROR("Unable to clean VRAM on master drop.\n");
-		vmw_release_device(dev_priv);
-	}
 	dev_priv->active_master = &dev_priv->fbdev_master;
 	ttm_lock_set_kill(&dev_priv->fbdev_master.lock, false, SIGTERM);
 	ttm_vt_unlock(&dev_priv->fbdev_master.lock);
 
-	if (!dev_priv->stealth)
-		vmw_fb_on(dev_priv);
+	vmw_fb_on(dev_priv);
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index d69caf92ffe7..0897359b3e4e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -182,25 +182,19 @@ static int vmw_cmd_present_check(struct vmw_private *dev_priv,
 	return vmw_cmd_sid_check(dev_priv, sw_context, &cmd->body.sid);
 }
 
-static int vmw_cmd_dma(struct vmw_private *dev_priv,
-		       struct vmw_sw_context *sw_context,
-		       SVGA3dCmdHeader *header)
+static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
+				   struct vmw_sw_context *sw_context,
+				   SVGAGuestPtr *ptr,
+				   struct vmw_dma_buffer **vmw_bo_p)
 {
-	uint32_t handle;
 	struct vmw_dma_buffer *vmw_bo = NULL;
 	struct ttm_buffer_object *bo;
-	struct vmw_surface *srf = NULL;
-	struct vmw_dma_cmd {
-		SVGA3dCmdHeader header;
-		SVGA3dCmdSurfaceDMA dma;
-	} *cmd;
+	uint32_t handle = ptr->gmrId;
 	struct vmw_relocation *reloc;
-	int ret;
 	uint32_t cur_validate_node;
 	struct ttm_validate_buffer *val_buf;
+	int ret;
 
-	cmd = container_of(header, struct vmw_dma_cmd, header);
-	handle = cmd->dma.guest.ptr.gmrId;
 	ret = vmw_user_dmabuf_lookup(sw_context->tfile, handle, &vmw_bo);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
@@ -209,14 +203,14 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 	bo = &vmw_bo->base;
 
 	if (unlikely(sw_context->cur_reloc >= VMWGFX_MAX_RELOCATIONS)) {
-		DRM_ERROR("Max number of DMA commands per submission"
+		DRM_ERROR("Max number relocations per submission"
 			  " exceeded\n");
 		ret = -EINVAL;
 		goto out_no_reloc;
 	}
 
 	reloc = &sw_context->relocs[sw_context->cur_reloc++];
-	reloc->location = &cmd->dma.guest.ptr;
+	reloc->location = ptr;
 
 	cur_validate_node = vmw_dmabuf_validate_node(bo, sw_context->cur_val_buf);
 	if (unlikely(cur_validate_node >= VMWGFX_MAX_GMRS)) {
@@ -234,7 +228,89 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		list_add_tail(&val_buf->head, &sw_context->validate_nodes);
 		++sw_context->cur_val_buf;
 	}
+	*vmw_bo_p = vmw_bo;
+	return 0;
+
+out_no_reloc:
+	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_p = NULL;
+	return ret;
+}
+
+static int vmw_cmd_end_query(struct vmw_private *dev_priv,
+			     struct vmw_sw_context *sw_context,
+			     SVGA3dCmdHeader *header)
+{
+	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_query_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdEndQuery q;
+	} *cmd;
+	int ret;
+
+	cmd = container_of(header, struct vmw_query_cmd, header);
+	ret = vmw_cmd_cid_check(dev_priv, sw_context, header);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
+				      &cmd->q.guestResult,
+				      &vmw_bo);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_dmabuf_unreference(&vmw_bo);
+	return 0;
+}
 
+static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
+			      struct vmw_sw_context *sw_context,
+			      SVGA3dCmdHeader *header)
+{
+	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_query_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdWaitForQuery q;
+	} *cmd;
+	int ret;
+
+	cmd = container_of(header, struct vmw_query_cmd, header);
+	ret = vmw_cmd_cid_check(dev_priv, sw_context, header);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
+				      &cmd->q.guestResult,
+				      &vmw_bo);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_dmabuf_unreference(&vmw_bo);
+	return 0;
+}
+
+
+static int vmw_cmd_dma(struct vmw_private *dev_priv,
+		       struct vmw_sw_context *sw_context,
+		       SVGA3dCmdHeader *header)
+{
+	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct ttm_buffer_object *bo;
+	struct vmw_surface *srf = NULL;
+	struct vmw_dma_cmd {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdSurfaceDMA dma;
+	} *cmd;
+	int ret;
+
+	cmd = container_of(header, struct vmw_dma_cmd, header);
+	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
+				      &cmd->dma.guest.ptr,
+				      &vmw_bo);
+	if (unlikely(ret != 0))
+		return ret;
+
+	bo = &vmw_bo->base;
 	ret = vmw_user_surface_lookup_handle(dev_priv, sw_context->tfile,
 					     cmd->dma.host.sid, &srf);
 	if (ret) {
@@ -379,8 +455,8 @@ static vmw_cmd_func vmw_cmd_funcs[SVGA_3D_CMD_MAX] = {
 	VMW_CMD_DEF(SVGA_3D_CMD_DRAW_PRIMITIVES, &vmw_cmd_draw),
 	VMW_CMD_DEF(SVGA_3D_CMD_SETSCISSORRECT, &vmw_cmd_cid_check),
 	VMW_CMD_DEF(SVGA_3D_CMD_BEGIN_QUERY, &vmw_cmd_cid_check),
-	VMW_CMD_DEF(SVGA_3D_CMD_END_QUERY, &vmw_cmd_cid_check),
-	VMW_CMD_DEF(SVGA_3D_CMD_WAIT_FOR_QUERY, &vmw_cmd_cid_check),
+	VMW_CMD_DEF(SVGA_3D_CMD_END_QUERY, &vmw_cmd_end_query),
+	VMW_CMD_DEF(SVGA_3D_CMD_WAIT_FOR_QUERY, &vmw_cmd_wait_query),
 	VMW_CMD_DEF(SVGA_3D_CMD_PRESENT_READBACK, &vmw_cmd_ok),
 	VMW_CMD_DEF(SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN,
 		    &vmw_cmd_blt_surf_screen_check)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 4f4f6432be8b..a93367041cdc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -559,6 +559,9 @@ int vmw_fb_init(struct vmw_private *vmw_priv)
 	info->pixmap.scan_align = 1;
 #endif
 
+	info->aperture_base = vmw_priv->vram_start;
+	info->aperture_size = vmw_priv->vram_size;
+
 	/*
 	 * Dirty & Deferred IO
 	 */
diff --git a/drivers/gpu/vga/Kconfig b/drivers/gpu/vga/Kconfig
index 790e675b13eb..0920492cea0a 100644
--- a/drivers/gpu/vga/Kconfig
+++ b/drivers/gpu/vga/Kconfig
@@ -8,3 +8,11 @@ config VGA_ARB
 	  are accessed at same time they need some kind of coordination. Please
 	  see Documentation/vgaarbiter.txt for more details. Select this to
 	  enable VGA arbiter.
+
+config VGA_ARB_MAX_GPUS
+	int "Maximum number of GPUs"
+	default 16
+	depends on VGA_ARB
+	help
+	  Reserves space in the kernel to maintain resource locking for
+	  multiple GPUS.  The overhead for each GPU is very small.
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index 24b56dc54597..8827814d0735 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -688,7 +688,7 @@ EXPORT_SYMBOL(vga_client_register);
  * the arbiter.
  */
 
-#define MAX_USER_CARDS         16
+#define MAX_USER_CARDS         CONFIG_VGA_ARB_MAX_GPUS
 #define PCI_INVALID_CARD       ((struct pci_dev *)-1UL)
 
 /*
@@ -954,6 +954,7 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 		}
 
 	} else if (strncmp(curr_pos, "target ", 7) == 0) {
+		struct pci_bus *pbus;
 		unsigned int domain, bus, devfn;
 		struct vga_device *vgadev;
 
@@ -961,7 +962,7 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 		remaining -= 7;
 		pr_devel("client 0x%p called 'target'\n", priv);
 		/* if target is default */
-		if (!strncmp(kbuf, "default", 7))
+		if (!strncmp(curr_pos, "default", 7))
 			pdev = pci_dev_get(vga_default_device());
 		else {
 			if (!vga_pci_str_to_vars(curr_pos, remaining,
@@ -969,18 +970,31 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 				ret_val = -EPROTO;
 				goto done;
 			}
-
-			pdev = pci_get_bus_and_slot(bus, devfn);
+			pr_devel("vgaarb: %s ==> %x:%x:%x.%x\n", curr_pos,
+				domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+			pbus = pci_find_bus(domain, bus);
+			pr_devel("vgaarb: pbus %p\n", pbus);
+			if (pbus == NULL) {
+				pr_err("vgaarb: invalid PCI domain and/or bus address %x:%x\n",
+					domain, bus);
+				ret_val = -ENODEV;
+				goto done;
+			}
+			pdev = pci_get_slot(pbus, devfn);
+			pr_devel("vgaarb: pdev %p\n", pdev);
 			if (!pdev) {
-				pr_info("vgaarb: invalid PCI address!\n");
+				pr_err("vgaarb: invalid PCI address %x:%x\n",
+					bus, devfn);
 				ret_val = -ENODEV;
 				goto done;
 			}
 		}
 
 		vgadev = vgadev_find(pdev);
+		pr_devel("vgaarb: vgadev %p\n", vgadev);
 		if (vgadev == NULL) {
-			pr_info("vgaarb: this pci device is not a vga device\n");
+			pr_err("vgaarb: this pci device is not a vga device\n");
 			pci_dev_put(pdev);
 			ret_val = -ENODEV;
 			goto done;
@@ -998,7 +1012,8 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 			}
 		}
 		if (i == MAX_USER_CARDS) {
-			pr_err("vgaarb: maximum user cards number reached!\n");
+			pr_err("vgaarb: maximum user cards (%d) number reached!\n",
+				MAX_USER_CARDS);
 			pci_dev_put(pdev);
 			/* XXX: which value to return? */
 			ret_val =  -ENOMEM;