Merge tag 'drm-intel-next-2012-05-06-merged' of git://people.freedesktop.org/~danvet/drm-intel into drm-core-next

Daniel says

Highlights:
- sparse fixes from Ben.
- tons of little cleanups from Chris all over: tiling_changed
 clarification, deferred_free list removal, ...
- fix up irq handler on gen2 & gen3 + related cleanups from Chris
- prep work for wait_rendering_timeout from Ben with some nice
 refactorings
- first set of infoframe fixes from Paulo for doubleclocked CEA modes
- improve pch pll handling from Jesse and Chris
- gpu hangman, this also contains the reset fix for gen4
- rps sanity check from Chris - this papers over issues when the gpu fails
 to clock up on snb/ivb, and it is shockingly easy to hit. The code
 prints a big WARN backtrace and restores the hw to a sane state. The
 real fix is still in the works.

Atm I'm aware of 2 regressions in -next:
- One of the gmbus patches (not gmbus itself) regressed lvds detection on
 a MacbookPro. I've analyzed the bug already and I think I know what's
 going on, patch is awaiting test feedback.
- Just today QA reported that DP on ilk regressed. That bug is fresh of
 the press and still awaiting detailed logfiles and the bisect result.
 The only thing that's clear atm is that -fixes works and -next doesn't.
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index fc6ded8..1ab29a7 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -626,7 +626,7 @@
 	drm_gem_object_reference(obj);
 
 	mutex_lock(&obj->dev->struct_mutex);
-	drm_vm_open_locked(vma);
+	drm_vm_open_locked(obj->dev, vma);
 	mutex_unlock(&obj->dev->struct_mutex);
 }
 EXPORT_SYMBOL(drm_gem_vm_open);
@@ -637,7 +637,7 @@
 	struct drm_device *dev = obj->dev;
 
 	mutex_lock(&dev->struct_mutex);
-	drm_vm_close_locked(vma);
+	drm_vm_close_locked(obj->dev, vma);
 	drm_gem_object_unreference(obj);
 	mutex_unlock(&dev->struct_mutex);
 }
@@ -710,7 +710,7 @@
 	 */
 	drm_gem_object_reference(obj);
 
-	drm_vm_open_locked(vma);
+	drm_vm_open_locked(dev, vma);
 
 out_unlock:
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 1495618..961ee08 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -406,10 +406,9 @@
  * Create a new drm_vma_entry structure as the \p vma private data entry and
  * add it to drm_device::vmalist.
  */
-void drm_vm_open_locked(struct vm_area_struct *vma)
+void drm_vm_open_locked(struct drm_device *dev,
+		struct vm_area_struct *vma)
 {
-	struct drm_file *priv = vma->vm_file->private_data;
-	struct drm_device *dev = priv->minor->dev;
 	struct drm_vma_entry *vma_entry;
 
 	DRM_DEBUG("0x%08lx,0x%08lx\n",
@@ -430,14 +429,13 @@
 	struct drm_device *dev = priv->minor->dev;
 
 	mutex_lock(&dev->struct_mutex);
-	drm_vm_open_locked(vma);
+	drm_vm_open_locked(dev, vma);
 	mutex_unlock(&dev->struct_mutex);
 }
 
-void drm_vm_close_locked(struct vm_area_struct *vma)
+void drm_vm_close_locked(struct drm_device *dev,
+		struct vm_area_struct *vma)
 {
-	struct drm_file *priv = vma->vm_file->private_data;
-	struct drm_device *dev = priv->minor->dev;
 	struct drm_vma_entry *pt, *temp;
 
 	DRM_DEBUG("0x%08lx,0x%08lx\n",
@@ -467,7 +465,7 @@
 	struct drm_device *dev = priv->minor->dev;
 
 	mutex_lock(&dev->struct_mutex);
-	drm_vm_close_locked(vma);
+	drm_vm_close_locked(dev, vma);
 	mutex_unlock(&dev->struct_mutex);
 }
 
@@ -519,7 +517,7 @@
 	vma->vm_flags |= VM_RESERVED;	/* Don't swap */
 	vma->vm_flags |= VM_DONTEXPAND;
 
-	drm_vm_open_locked(vma);
+	drm_vm_open_locked(dev, vma);
 	return 0;
 }
 
@@ -670,7 +668,7 @@
 	vma->vm_flags |= VM_RESERVED;	/* Don't swap */
 	vma->vm_flags |= VM_DONTEXPAND;
 
-	drm_vm_open_locked(vma);
+	drm_vm_open_locked(dev, vma);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/gma500/Makefile b/drivers/gpu/drm/gma500/Makefile
index dd7d6b5..abfa2a93 100644
--- a/drivers/gpu/drm/gma500/Makefile
+++ b/drivers/gpu/drm/gma500/Makefile
@@ -13,7 +13,6 @@
 	  intel_i2c.o \
 	  intel_gmbus.o \
 	  mmu.o \
-	  opregion.o \
 	  power.o \
 	  psb_drv.o \
 	  psb_intel_display.o \
@@ -25,6 +24,8 @@
 	  psb_device.o \
 	  mid_bios.o
 
+gma500_gfx-$(CONFIG_ACPI) +=  opregion.o \
+
 gma500_gfx-$(CONFIG_DRM_GMA3600) +=  cdv_device.o \
 	  cdv_intel_crt.o \
 	  cdv_intel_display.o \
diff --git a/drivers/gpu/drm/gma500/cdv_device.c b/drivers/gpu/drm/gma500/cdv_device.c
index c10f020..8e39330 100644
--- a/drivers/gpu/drm/gma500/cdv_device.c
+++ b/drivers/gpu/drm/gma500/cdv_device.c
@@ -255,7 +255,7 @@
 	struct psb_save_area *regs = &dev_priv->regs;
 	struct drm_connector *connector;
 
-	dev_info(dev->dev, "Saving GPU registers.\n");
+	dev_dbg(dev->dev, "Saving GPU registers.\n");
 
 	pci_read_config_byte(dev->pdev, 0xF4, &regs->cdv.saveLBB);
 
@@ -485,10 +485,68 @@
 	}	
 }
 
+/* Cedarview */
+static const struct psb_offset cdv_regmap[2] = {
+	{
+		.fp0 = FPA0,
+		.fp1 = FPA1,
+		.cntr = DSPACNTR,
+		.conf = PIPEACONF,
+		.src = PIPEASRC,
+		.dpll = DPLL_A,
+		.dpll_md = DPLL_A_MD,
+		.htotal = HTOTAL_A,
+		.hblank = HBLANK_A,
+		.hsync = HSYNC_A,
+		.vtotal = VTOTAL_A,
+		.vblank = VBLANK_A,
+		.vsync = VSYNC_A,
+		.stride = DSPASTRIDE,
+		.size = DSPASIZE,
+		.pos = DSPAPOS,
+		.base = DSPABASE,
+		.surf = DSPASURF,
+		.addr = DSPABASE,
+		.status = PIPEASTAT,
+		.linoff = DSPALINOFF,
+		.tileoff = DSPATILEOFF,
+		.palette = PALETTE_A,
+	},
+	{
+		.fp0 = FPB0,
+		.fp1 = FPB1,
+		.cntr = DSPBCNTR,
+		.conf = PIPEBCONF,
+		.src = PIPEBSRC,
+		.dpll = DPLL_B,
+		.dpll_md = DPLL_B_MD,
+		.htotal = HTOTAL_B,
+		.hblank = HBLANK_B,
+		.hsync = HSYNC_B,
+		.vtotal = VTOTAL_B,
+		.vblank = VBLANK_B,
+		.vsync = VSYNC_B,
+		.stride = DSPBSTRIDE,
+		.size = DSPBSIZE,
+		.pos = DSPBPOS,
+		.base = DSPBBASE,
+		.surf = DSPBSURF,
+		.addr = DSPBBASE,
+		.status = PIPEBSTAT,
+		.linoff = DSPBLINOFF,
+		.tileoff = DSPBTILEOFF,
+		.palette = PALETTE_B,
+	}
+};
+
 static int cdv_chip_setup(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	INIT_WORK(&dev_priv->hotplug_work, cdv_hotplug_work_func);
+
+	if (pci_enable_msi(dev->pdev))
+		dev_warn(dev->dev, "Enabling MSI failed!\n");
+	dev_priv->regmap = cdv_regmap;
 	cdv_get_core_freq(dev);
 	psb_intel_opregion_init(dev);
 	psb_intel_init_bios(dev);
diff --git a/drivers/gpu/drm/gma500/cdv_intel_display.c b/drivers/gpu/drm/gma500/cdv_intel_display.c
index 2fab778..c3e9a0f 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_display.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_display.c
@@ -218,8 +218,7 @@
 cdv_dpll_set_clock_cdv(struct drm_device *dev, struct drm_crtc *crtc,
 			       struct cdv_intel_clock_t *clock, bool is_lvds)
 {
-	struct psb_intel_crtc *psb_crtc =
-				to_psb_intel_crtc(crtc);
+	struct psb_intel_crtc *psb_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_crtc->pipe;
 	u32 m, n_vco, p;
 	int ret = 0;
@@ -503,14 +502,12 @@
 			    int x, int y, struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
-	int dspbase = (pipe == 0 ? DSPABASE : DSPBBASE);
-	int dspsurf = (pipe == 0 ? DSPASURF : DSPBSURF);
-	int dspstride = (pipe == 0) ? DSPASTRIDE : DSPBSTRIDE;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
 	u32 dspcntr;
 	int ret = 0;
 
@@ -532,9 +529,9 @@
 	start = psbfb->gtt->offset;
 	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
 
-	REG_WRITE(dspstride, crtc->fb->pitches[0]);
+	REG_WRITE(map->stride, crtc->fb->pitches[0]);
 
-	dspcntr = REG_READ(dspcntr_reg);
+	dspcntr = REG_READ(map->cntr);
 	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 
 	switch (crtc->fb->bits_per_pixel) {
@@ -556,15 +553,15 @@
 		ret = -EINVAL;
 		goto psb_intel_pipe_set_base_exit;
 	}
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
 	dev_dbg(dev->dev,
 		"Writing base %08lX %08lX %d %d\n", start, offset, x, y);
 
-	REG_WRITE(dspbase, offset);
-	REG_READ(dspbase);
-	REG_WRITE(dspsurf, start);
-	REG_READ(dspsurf);
+	REG_WRITE(map->base, offset);
+	REG_READ(map->base);
+	REG_WRITE(map->surf, start);
+	REG_READ(map->surf);
 
 psb_intel_pipe_cleaner:
 	/* If there was a previous display we can now unpin it */
@@ -721,8 +718,7 @@
 static void cdv_intel_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv =
-				(struct drm_psb_private *)dev->dev_private;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int palreg = PALETTE_A;
 	int i;
@@ -758,7 +754,7 @@
 		gma_power_end(dev);
 	} else {
 		for (i = 0; i < 256; i++) {
-			dev_priv->regs.psb.save_palette_a[i] =
+			dev_priv->regs.pipe[0].palette[i] =
 				  ((psb_intel_crtc->lut_r[i] +
 				  psb_intel_crtc->lut_adj[i]) << 16) |
 				  ((psb_intel_crtc->lut_g[i] +
@@ -779,13 +775,10 @@
 static void cdv_intel_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
-	int dpll_reg = (pipe == 0) ? DPLL_A : DPLL_B;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int dspbase_reg = (pipe == 0) ? DSPABASE : DSPBBASE;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
-	int pipestat_reg = (pipe == 0) ? PIPEASTAT : PIPEBSTAT;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 temp;
 
 	/* XXX: When our outputs are all unaware of DPMS modes other than off
@@ -803,44 +796,44 @@
 		psb_intel_crtc->active = true;
 
 		/* Enable the DPLL */
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) == 0) {
-			REG_WRITE(dpll_reg, temp);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
 		}
 
 		/* Jim Bish - switch plan and pipe per scott */
 		/* Enable the plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp | DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+			REG_WRITE(map->base, REG_READ(map->base));
 		}
 
 		udelay(150);
 
 		/* Enable the pipe */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) == 0)
-			REG_WRITE(pipeconf_reg, temp | PIPEACONF_ENABLE);
+			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
 
-		temp = REG_READ(pipestat_reg);
+		temp = REG_READ(map->status);
 		temp &= ~(0xFFFF);
 		temp |= PIPE_FIFO_UNDERRUN;
-		REG_WRITE(pipestat_reg, temp);
-		REG_READ(pipestat_reg);
+		REG_WRITE(map->status, temp);
+		REG_READ(map->status);
 
 		cdv_intel_update_watermark(dev, crtc);
 		cdv_intel_crtc_load_lut(crtc);
@@ -870,10 +863,10 @@
 		cdv_intel_wait_for_vblank(dev);
 
 		/* Next, disable display pipes */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) != 0) {
-			REG_WRITE(pipeconf_reg, temp & ~PIPEACONF_ENABLE);
-			REG_READ(pipeconf_reg);
+			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
+			REG_READ(map->conf);
 		}
 
 		/* Wait for vblank for the disable to take effect. */
@@ -882,19 +875,19 @@
 		udelay(150);
 
 		/* Disable display plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp & ~DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
-			REG_READ(dspbase_reg);
+			REG_WRITE(map->base, REG_READ(map->base));
+			REG_READ(map->base);
 		}
 
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
-			REG_WRITE(dpll_reg, temp & ~DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 		}
 
 		/* Wait for the clocks to turn off. */
@@ -953,19 +946,7 @@
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
-	int dpll_reg = (pipe == 0) ? DPLL_A : DPLL_B;
-	int dpll_md_reg = (psb_intel_crtc->pipe == 0) ? DPLL_A_MD : DPLL_B_MD;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
-	int htot_reg = (pipe == 0) ? HTOTAL_A : HTOTAL_B;
-	int hblank_reg = (pipe == 0) ? HBLANK_A : HBLANK_B;
-	int hsync_reg = (pipe == 0) ? HSYNC_A : HSYNC_B;
-	int vtot_reg = (pipe == 0) ? VTOTAL_A : VTOTAL_B;
-	int vblank_reg = (pipe == 0) ? VBLANK_A : VBLANK_B;
-	int vsync_reg = (pipe == 0) ? VSYNC_A : VSYNC_B;
-	int dspsize_reg = (pipe == 0) ? DSPASIZE : DSPBSIZE;
-	int dsppos_reg = (pipe == 0) ? DSPAPOS : DSPBPOS;
-	int pipesrc_reg = (pipe == 0) ? PIPEASRC : PIPEBSRC;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk;
 	struct cdv_intel_clock_t clock;
 	u32 dpll = 0, dspcntr, pipeconf;
@@ -1036,7 +1017,7 @@
 	/* dpll |= (2 << 11); */
 
 	/* setup pipeconf */
-	pipeconf = REG_READ(pipeconf_reg);
+	pipeconf = REG_READ(map->conf);
 
 	/* Set up the display plane register */
 	dspcntr = DISPPLANE_GAMMA_ENABLE;
@@ -1049,8 +1030,8 @@
 	dspcntr |= DISPLAY_PLANE_ENABLE;
 	pipeconf |= PIPEACONF_ENABLE;
 
-	REG_WRITE(dpll_reg, dpll | DPLL_VGA_MODE_DIS | DPLL_SYNCLOCK_ENABLE);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->dpll, dpll | DPLL_VGA_MODE_DIS | DPLL_SYNCLOCK_ENABLE);
+	REG_READ(map->dpll);
 
 	cdv_dpll_set_clock_cdv(dev, crtc, &clock, is_lvds);
 
@@ -1094,48 +1075,48 @@
 	DRM_DEBUG_KMS("Mode for pipe %c:\n", pipe == 0 ? 'A' : 'B');
 	drm_mode_debug_printmodeline(mode);
 
-	REG_WRITE(dpll_reg,
-		(REG_READ(dpll_reg) & ~DPLL_LOCK) | DPLL_VCO_ENABLE);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->dpll,
+		(REG_READ(map->dpll) & ~DPLL_LOCK) | DPLL_VCO_ENABLE);
+	REG_READ(map->dpll);
 	/* Wait for the clocks to stabilize. */
 	udelay(150); /* 42 usec w/o calibration, 110 with.  rounded up. */
 
-	if (!(REG_READ(dpll_reg) & DPLL_LOCK)) {
+	if (!(REG_READ(map->dpll) & DPLL_LOCK)) {
 		dev_err(dev->dev, "Failed to get DPLL lock\n");
 		return -EBUSY;
 	}
 
 	{
 		int sdvo_pixel_multiply = adjusted_mode->clock / mode->clock;
-		REG_WRITE(dpll_md_reg, (0 << DPLL_MD_UDI_DIVIDER_SHIFT) | ((sdvo_pixel_multiply - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT));
+		REG_WRITE(map->dpll_md, (0 << DPLL_MD_UDI_DIVIDER_SHIFT) | ((sdvo_pixel_multiply - 1) << DPLL_MD_UDI_MULTIPLIER_SHIFT));
 	}
 
-	REG_WRITE(htot_reg, (adjusted_mode->crtc_hdisplay - 1) |
+	REG_WRITE(map->htotal, (adjusted_mode->crtc_hdisplay - 1) |
 		  ((adjusted_mode->crtc_htotal - 1) << 16));
-	REG_WRITE(hblank_reg, (adjusted_mode->crtc_hblank_start - 1) |
+	REG_WRITE(map->hblank, (adjusted_mode->crtc_hblank_start - 1) |
 		  ((adjusted_mode->crtc_hblank_end - 1) << 16));
-	REG_WRITE(hsync_reg, (adjusted_mode->crtc_hsync_start - 1) |
+	REG_WRITE(map->hsync, (adjusted_mode->crtc_hsync_start - 1) |
 		  ((adjusted_mode->crtc_hsync_end - 1) << 16));
-	REG_WRITE(vtot_reg, (adjusted_mode->crtc_vdisplay - 1) |
+	REG_WRITE(map->vtotal, (adjusted_mode->crtc_vdisplay - 1) |
 		  ((adjusted_mode->crtc_vtotal - 1) << 16));
-	REG_WRITE(vblank_reg, (adjusted_mode->crtc_vblank_start - 1) |
+	REG_WRITE(map->vblank, (adjusted_mode->crtc_vblank_start - 1) |
 		  ((adjusted_mode->crtc_vblank_end - 1) << 16));
-	REG_WRITE(vsync_reg, (adjusted_mode->crtc_vsync_start - 1) |
+	REG_WRITE(map->vsync, (adjusted_mode->crtc_vsync_start - 1) |
 		  ((adjusted_mode->crtc_vsync_end - 1) << 16));
 	/* pipesrc and dspsize control the size that is scaled from,
 	 * which should always be the user's requested size.
 	 */
-	REG_WRITE(dspsize_reg,
+	REG_WRITE(map->size,
 		  ((mode->vdisplay - 1) << 16) | (mode->hdisplay - 1));
-	REG_WRITE(dsppos_reg, 0);
-	REG_WRITE(pipesrc_reg,
+	REG_WRITE(map->pos, 0);
+	REG_WRITE(map->src,
 		  ((mode->hdisplay - 1) << 16) | (mode->vdisplay - 1));
-	REG_WRITE(pipeconf_reg, pipeconf);
-	REG_READ(pipeconf_reg);
+	REG_WRITE(map->conf, pipeconf);
+	REG_READ(map->conf);
 
 	cdv_intel_wait_for_vblank(dev);
 
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
 	/* Flush the plane changes */
 	{
@@ -1156,11 +1137,10 @@
 static void cdv_intel_crtc_save(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_psb_private *dev_priv =
-			(struct drm_psb_private *)dev->dev_private; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	int pipeA = (psb_intel_crtc->pipe == 0);
+	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
 	uint32_t paletteReg;
 	int i;
 
@@ -1169,25 +1149,25 @@
 		return;
 	}
 
-	crtc_state->saveDSPCNTR = REG_READ(pipeA ? DSPACNTR : DSPBCNTR);
-	crtc_state->savePIPECONF = REG_READ(pipeA ? PIPEACONF : PIPEBCONF);
-	crtc_state->savePIPESRC = REG_READ(pipeA ? PIPEASRC : PIPEBSRC);
-	crtc_state->saveFP0 = REG_READ(pipeA ? FPA0 : FPB0);
-	crtc_state->saveFP1 = REG_READ(pipeA ? FPA1 : FPB1);
-	crtc_state->saveDPLL = REG_READ(pipeA ? DPLL_A : DPLL_B);
-	crtc_state->saveHTOTAL = REG_READ(pipeA ? HTOTAL_A : HTOTAL_B);
-	crtc_state->saveHBLANK = REG_READ(pipeA ? HBLANK_A : HBLANK_B);
-	crtc_state->saveHSYNC = REG_READ(pipeA ? HSYNC_A : HSYNC_B);
-	crtc_state->saveVTOTAL = REG_READ(pipeA ? VTOTAL_A : VTOTAL_B);
-	crtc_state->saveVBLANK = REG_READ(pipeA ? VBLANK_A : VBLANK_B);
-	crtc_state->saveVSYNC = REG_READ(pipeA ? VSYNC_A : VSYNC_B);
-	crtc_state->saveDSPSTRIDE = REG_READ(pipeA ? DSPASTRIDE : DSPBSTRIDE);
+	crtc_state->saveDSPCNTR = REG_READ(map->cntr);
+	crtc_state->savePIPECONF = REG_READ(map->conf);
+	crtc_state->savePIPESRC = REG_READ(map->src);
+	crtc_state->saveFP0 = REG_READ(map->fp0);
+	crtc_state->saveFP1 = REG_READ(map->fp1);
+	crtc_state->saveDPLL = REG_READ(map->dpll);
+	crtc_state->saveHTOTAL = REG_READ(map->htotal);
+	crtc_state->saveHBLANK = REG_READ(map->hblank);
+	crtc_state->saveHSYNC = REG_READ(map->hsync);
+	crtc_state->saveVTOTAL = REG_READ(map->vtotal);
+	crtc_state->saveVBLANK = REG_READ(map->vblank);
+	crtc_state->saveVSYNC = REG_READ(map->vsync);
+	crtc_state->saveDSPSTRIDE = REG_READ(map->stride);
 
 	/*NOTE: DSPSIZE DSPPOS only for psb*/
-	crtc_state->saveDSPSIZE = REG_READ(pipeA ? DSPASIZE : DSPBSIZE);
-	crtc_state->saveDSPPOS = REG_READ(pipeA ? DSPAPOS : DSPBPOS);
+	crtc_state->saveDSPSIZE = REG_READ(map->size);
+	crtc_state->saveDSPPOS = REG_READ(map->pos);
 
-	crtc_state->saveDSPBASE = REG_READ(pipeA ? DSPABASE : DSPBBASE);
+	crtc_state->saveDSPBASE = REG_READ(map->base);
 
 	DRM_DEBUG("(%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
 			crtc_state->saveDSPCNTR,
@@ -1208,7 +1188,7 @@
 			crtc_state->saveDSPBASE
 		);
 
-	paletteReg = pipeA ? PALETTE_A : PALETTE_B;
+	paletteReg = map->palette;
 	for (i = 0; i < 256; ++i)
 		crtc_state->savePalette[i] = REG_READ(paletteReg + (i << 2));
 }
@@ -1219,12 +1199,10 @@
 static void cdv_intel_crtc_restore(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_psb_private * dev_priv =
-				(struct drm_psb_private *)dev->dev_private; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc =  to_psb_intel_crtc(crtc);
 	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	/* struct drm_crtc_helper_funcs * crtc_funcs = crtc->helper_private; */
-	int pipeA = (psb_intel_crtc->pipe == 0);
+	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
 	uint32_t paletteReg;
 	int i;
 
@@ -1235,23 +1213,23 @@
 
 	DRM_DEBUG(
 		"current:(%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
-		REG_READ(pipeA ? DSPACNTR : DSPBCNTR),
-		REG_READ(pipeA ? PIPEACONF : PIPEBCONF),
-		REG_READ(pipeA ? PIPEASRC : PIPEBSRC),
-		REG_READ(pipeA ? FPA0 : FPB0),
-		REG_READ(pipeA ? FPA1 : FPB1),
-		REG_READ(pipeA ? DPLL_A : DPLL_B),
-		REG_READ(pipeA ? HTOTAL_A : HTOTAL_B),
-		REG_READ(pipeA ? HBLANK_A : HBLANK_B),
-		REG_READ(pipeA ? HSYNC_A : HSYNC_B),
-		REG_READ(pipeA ? VTOTAL_A : VTOTAL_B),
-		REG_READ(pipeA ? VBLANK_A : VBLANK_B),
-		REG_READ(pipeA ? VSYNC_A : VSYNC_B),
-		REG_READ(pipeA ? DSPASTRIDE : DSPBSTRIDE),
-		REG_READ(pipeA ? DSPASIZE : DSPBSIZE),
-		REG_READ(pipeA ? DSPAPOS : DSPBPOS),
-		REG_READ(pipeA ? DSPABASE : DSPBBASE)
-		);
+		REG_READ(map->cntr),
+		REG_READ(map->conf),
+		REG_READ(map->src),
+		REG_READ(map->fp0),
+		REG_READ(map->fp1),
+		REG_READ(map->dpll),
+		REG_READ(map->htotal),
+		REG_READ(map->hblank),
+		REG_READ(map->hsync),
+		REG_READ(map->vtotal),
+		REG_READ(map->vblank),
+		REG_READ(map->vsync),
+		REG_READ(map->stride),
+		REG_READ(map->size),
+		REG_READ(map->pos),
+		REG_READ(map->base)
+	);
 
 	DRM_DEBUG(
 		"saved: (%x %x %x %x %x %x %x %x %x %x %x %x %x %x %x %x)\n",
@@ -1271,51 +1249,51 @@
 		crtc_state->saveDSPSIZE,
 		crtc_state->saveDSPPOS,
 		crtc_state->saveDSPBASE
-		);
+	);
 
 
 	if (crtc_state->saveDPLL & DPLL_VCO_ENABLE) {
-		REG_WRITE(pipeA ? DPLL_A : DPLL_B,
-			crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
-		REG_READ(pipeA ? DPLL_A : DPLL_B);
+		REG_WRITE(map->dpll,
+				crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
+		REG_READ(map->dpll);
 		DRM_DEBUG("write dpll: %x\n",
-				REG_READ(pipeA ? DPLL_A : DPLL_B));
+				REG_READ(map->dpll));
 		udelay(150);
 	}
 
-	REG_WRITE(pipeA ? FPA0 : FPB0, crtc_state->saveFP0);
-	REG_READ(pipeA ? FPA0 : FPB0);
+	REG_WRITE(map->fp0, crtc_state->saveFP0);
+	REG_READ(map->fp0);
 
-	REG_WRITE(pipeA ? FPA1 : FPB1, crtc_state->saveFP1);
-	REG_READ(pipeA ? FPA1 : FPB1);
+	REG_WRITE(map->fp1, crtc_state->saveFP1);
+	REG_READ(map->fp1);
 
-	REG_WRITE(pipeA ? DPLL_A : DPLL_B, crtc_state->saveDPLL);
-	REG_READ(pipeA ? DPLL_A : DPLL_B);
+	REG_WRITE(map->dpll, crtc_state->saveDPLL);
+	REG_READ(map->dpll);
 	udelay(150);
 
-	REG_WRITE(pipeA ? HTOTAL_A : HTOTAL_B, crtc_state->saveHTOTAL);
-	REG_WRITE(pipeA ? HBLANK_A : HBLANK_B, crtc_state->saveHBLANK);
-	REG_WRITE(pipeA ? HSYNC_A : HSYNC_B, crtc_state->saveHSYNC);
-	REG_WRITE(pipeA ? VTOTAL_A : VTOTAL_B, crtc_state->saveVTOTAL);
-	REG_WRITE(pipeA ? VBLANK_A : VBLANK_B, crtc_state->saveVBLANK);
-	REG_WRITE(pipeA ? VSYNC_A : VSYNC_B, crtc_state->saveVSYNC);
-	REG_WRITE(pipeA ? DSPASTRIDE : DSPBSTRIDE, crtc_state->saveDSPSTRIDE);
+	REG_WRITE(map->htotal, crtc_state->saveHTOTAL);
+	REG_WRITE(map->hblank, crtc_state->saveHBLANK);
+	REG_WRITE(map->hsync, crtc_state->saveHSYNC);
+	REG_WRITE(map->vtotal, crtc_state->saveVTOTAL);
+	REG_WRITE(map->vblank, crtc_state->saveVBLANK);
+	REG_WRITE(map->vsync, crtc_state->saveVSYNC);
+	REG_WRITE(map->stride, crtc_state->saveDSPSTRIDE);
 
-	REG_WRITE(pipeA ? DSPASIZE : DSPBSIZE, crtc_state->saveDSPSIZE);
-	REG_WRITE(pipeA ? DSPAPOS : DSPBPOS, crtc_state->saveDSPPOS);
+	REG_WRITE(map->size, crtc_state->saveDSPSIZE);
+	REG_WRITE(map->pos, crtc_state->saveDSPPOS);
 
-	REG_WRITE(pipeA ? PIPEASRC : PIPEBSRC, crtc_state->savePIPESRC);
-	REG_WRITE(pipeA ? DSPABASE : DSPBBASE, crtc_state->saveDSPBASE);
-	REG_WRITE(pipeA ? PIPEACONF : PIPEBCONF, crtc_state->savePIPECONF);
+	REG_WRITE(map->src, crtc_state->savePIPESRC);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
+	REG_WRITE(map->conf, crtc_state->savePIPECONF);
 
 	cdv_intel_wait_for_vblank(dev);
 
-	REG_WRITE(pipeA ? DSPACNTR : DSPBCNTR, crtc_state->saveDSPCNTR);
-	REG_WRITE(pipeA ? DSPABASE : DSPBBASE, crtc_state->saveDSPBASE);
+	REG_WRITE(map->cntr, crtc_state->saveDSPCNTR);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
 
 	cdv_intel_wait_for_vblank(dev);
 
-	paletteReg = pipeA ? PALETTE_A : PALETTE_B;
+	paletteReg = map->palette;
 	for (i = 0; i < 256; ++i)
 		REG_WRITE(paletteReg + (i << 2), crtc_state->savePalette[i]);
 }
@@ -1490,35 +1468,30 @@
 static int cdv_intel_crtc_clock_get(struct drm_device *dev,
 				struct drm_crtc *crtc)
 {
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 dpll;
 	u32 fp;
 	struct cdv_intel_clock_t clock;
 	bool is_lvds;
-	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
 
 	if (gma_power_begin(dev, false)) {
-		dpll = REG_READ((pipe == 0) ? DPLL_A : DPLL_B);
+		dpll = REG_READ(map->dpll);
 		if ((dpll & DISPLAY_RATE_SELECT_FPA1) == 0)
-			fp = REG_READ((pipe == 0) ? FPA0 : FPB0);
+			fp = REG_READ(map->fp0);
 		else
-			fp = REG_READ((pipe == 0) ? FPA1 : FPB1);
+			fp = REG_READ(map->fp1);
 		is_lvds = (pipe == 1) && (REG_READ(LVDS) & LVDS_PORT_EN);
 		gma_power_end(dev);
 	} else {
-		dpll = (pipe == 0) ?
-			dev_priv->regs.psb.saveDPLL_A :
-			dev_priv->regs.psb.saveDPLL_B;
-
+		dpll = p->dpll;
 		if ((dpll & DISPLAY_RATE_SELECT_FPA1) == 0)
-			fp = (pipe == 0) ?
-				dev_priv->regs.psb.saveFPA0 :
-				dev_priv->regs.psb.saveFPB0;
+			fp = p->fp0;
 		else
-			fp = (pipe == 0) ?
-				dev_priv->regs.psb.saveFPA1 :
-				dev_priv->regs.psb.saveFPB1;
+			fp = p->fp1;
 
 		is_lvds = (pipe == 1) &&
 				(dev_priv->regs.psb.saveLVDS & LVDS_PORT_EN);
@@ -1576,32 +1549,26 @@
 {
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	struct drm_display_mode *mode;
 	int htot;
 	int hsync;
 	int vtot;
 	int vsync;
-	struct drm_psb_private *dev_priv = dev->dev_private;
 
 	if (gma_power_begin(dev, false)) {
-		htot = REG_READ((pipe == 0) ? HTOTAL_A : HTOTAL_B);
-		hsync = REG_READ((pipe == 0) ? HSYNC_A : HSYNC_B);
-		vtot = REG_READ((pipe == 0) ? VTOTAL_A : VTOTAL_B);
-		vsync = REG_READ((pipe == 0) ? VSYNC_A : VSYNC_B);
+		htot = REG_READ(map->htotal);
+		hsync = REG_READ(map->hsync);
+		vtot = REG_READ(map->vtotal);
+		vsync = REG_READ(map->vsync);
 		gma_power_end(dev);
 	} else {
-		htot = (pipe == 0) ?
-			dev_priv->regs.psb.saveHTOTAL_A :
-			dev_priv->regs.psb.saveHTOTAL_B;
-		hsync = (pipe == 0) ?
-			dev_priv->regs.psb.saveHSYNC_A :
-			dev_priv->regs.psb.saveHSYNC_B;
-		vtot = (pipe == 0) ?
-			dev_priv->regs.psb.saveVTOTAL_A :
-			dev_priv->regs.psb.saveVTOTAL_B;
-		vsync = (pipe == 0) ?
-			dev_priv->regs.psb.saveVSYNC_A :
-			dev_priv->regs.psb.saveVSYNC_B;
+		htot = p->htotal;
+		hsync = p->hsync;
+		vtot = p->vtotal;
+		vsync = p->vsync;
 	}
 
 	mode = kzalloc(sizeof(*mode), GFP_KERNEL);
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index f47f883..659ed39 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -476,7 +476,7 @@
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	dev_info(dev->dev, "allocated %dx%d fb\n",
+	dev_dbg(dev->dev, "allocated %dx%d fb\n",
 					psbfb->base.width, psbfb->base.height);
 
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/gma500/gtt.c b/drivers/gpu/drm/gma500/gtt.c
index 4cd33df..04a371a 100644
--- a/drivers/gpu/drm/gma500/gtt.c
+++ b/drivers/gpu/drm/gma500/gtt.c
@@ -416,7 +416,6 @@
 	unsigned long stolen_size, vram_stolen_size;
 	unsigned i, num_pages;
 	unsigned pfn_base;
-	uint32_t dvmt_mode = 0;
 	struct psb_gtt *pg;
 
 	int ret = 0;
@@ -489,13 +488,8 @@
 
 	stolen_size = vram_stolen_size;
 
-	printk(KERN_INFO "Stolen memory information\n");
-	printk(KERN_INFO "       base in RAM: 0x%x\n", dev_priv->stolen_base);
-	printk(KERN_INFO "       size: %luK, calculated by (GTT RAM base) - (Stolen base), seems wrong\n",
-		vram_stolen_size/1024);
-	dvmt_mode = (dev_priv->gmch_ctrl >> 4) & 0x7;
-	printk(KERN_INFO "      the correct size should be: %dM(dvmt mode=%d)\n",
-		(dvmt_mode == 1) ? 1 : (2 << (dvmt_mode - 1)), dvmt_mode);
+	dev_dbg(dev->dev, "Stolen memory base 0x%x, size %luK\n",
+			dev_priv->stolen_base, vram_stolen_size / 1024);
 
 	if (resume && (gtt_pages != pg->gtt_pages) &&
 	    (stolen_size != pg->stolen_size)) {
@@ -532,7 +526,7 @@
 
 	pfn_base = dev_priv->stolen_base >> PAGE_SHIFT;
 	num_pages = vram_stolen_size >> PAGE_SHIFT;
-	printk(KERN_INFO"Set up %d stolen pages starting at 0x%08x, GTT offset %dK\n",
+	dev_dbg(dev->dev, "Set up %d stolen pages starting at 0x%08x, GTT offset %dK\n",
 		num_pages, pfn_base << PAGE_SHIFT, 0);
 	for (i = 0; i < num_pages; ++i) {
 		pte = psb_gtt_mask_pte(pfn_base + i, 0);
diff --git a/drivers/gpu/drm/gma500/mdfld_device.c b/drivers/gpu/drm/gma500/mdfld_device.c
index 717f4db..2d8e741 100644
--- a/drivers/gpu/drm/gma500/mdfld_device.c
+++ b/drivers/gpu/drm/gma500/mdfld_device.c
@@ -163,142 +163,30 @@
  *
  * Notes: FIXME_JLIU7 need to add the support for DPI MIPI & HDMI audio
  */
-static int mdfld_save_display_registers(struct drm_device *dev, int pipe)
+static int mdfld_save_display_registers(struct drm_device *dev, int pipenum)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct medfield_state *regs = &dev_priv->regs.mdfld;
+	struct psb_pipe *pipe = &dev_priv->regs.pipe[pipenum];
+	const struct psb_offset *map = &dev_priv->regmap[pipenum];
 	int i;
+	u32 *mipi_val;
 
 	/* register */
-	u32 dpll_reg = MRST_DPLL_A;
-	u32 fp_reg = MRST_FPA0;
-	u32 pipeconf_reg = PIPEACONF;
-	u32 htot_reg = HTOTAL_A;
-	u32 hblank_reg = HBLANK_A;
-	u32 hsync_reg = HSYNC_A;
-	u32 vtot_reg = VTOTAL_A;
-	u32 vblank_reg = VBLANK_A;
-	u32 vsync_reg = VSYNC_A;
-	u32 pipesrc_reg = PIPEASRC;
-	u32 dspstride_reg = DSPASTRIDE;
-	u32 dsplinoff_reg = DSPALINOFF;
-	u32 dsptileoff_reg = DSPATILEOFF;
-	u32 dspsize_reg = DSPASIZE;
-	u32 dsppos_reg = DSPAPOS;
-	u32 dspsurf_reg = DSPASURF;
 	u32 mipi_reg = MIPI;
-	u32 dspcntr_reg = DSPACNTR;
-	u32 dspstatus_reg = PIPEASTAT;
-	u32 palette_reg = PALETTE_A;
 
-	/* pointer to values */
-	u32 *dpll_val = &regs->saveDPLL_A;
-	u32 *fp_val = &regs->saveFPA0;
-	u32 *pipeconf_val = &regs->savePIPEACONF;
-	u32 *htot_val = &regs->saveHTOTAL_A;
-	u32 *hblank_val = &regs->saveHBLANK_A;
-	u32 *hsync_val = &regs->saveHSYNC_A;
-	u32 *vtot_val = &regs->saveVTOTAL_A;
-	u32 *vblank_val = &regs->saveVBLANK_A;
-	u32 *vsync_val = &regs->saveVSYNC_A;
-	u32 *pipesrc_val = &regs->savePIPEASRC;
-	u32 *dspstride_val = &regs->saveDSPASTRIDE;
-	u32 *dsplinoff_val = &regs->saveDSPALINOFF;
-	u32 *dsptileoff_val = &regs->saveDSPATILEOFF;
-	u32 *dspsize_val = &regs->saveDSPASIZE;
-	u32 *dsppos_val = &regs->saveDSPAPOS;
-	u32 *dspsurf_val = &regs->saveDSPASURF;
-	u32 *mipi_val = &regs->saveMIPI;
-	u32 *dspcntr_val = &regs->saveDSPACNTR;
-	u32 *dspstatus_val = &regs->saveDSPASTATUS;
-	u32 *palette_val = regs->save_palette_a;
-
-	switch (pipe) {
+	switch (pipenum) {
 	case 0:
+		mipi_val = &regs->saveMIPI;
 		break;
 	case 1:
-		/* regester */
-		dpll_reg = MDFLD_DPLL_B;
-		fp_reg = MDFLD_DPLL_DIV0;
-		pipeconf_reg = PIPEBCONF;
-		htot_reg = HTOTAL_B;
-		hblank_reg = HBLANK_B;
-		hsync_reg = HSYNC_B;
-		vtot_reg = VTOTAL_B;
-		vblank_reg = VBLANK_B;
-		vsync_reg = VSYNC_B;
-		pipesrc_reg = PIPEBSRC;
-		dspstride_reg = DSPBSTRIDE;
-		dsplinoff_reg = DSPBLINOFF;
-		dsptileoff_reg = DSPBTILEOFF;
-		dspsize_reg = DSPBSIZE;
-		dsppos_reg = DSPBPOS;
-		dspsurf_reg = DSPBSURF;
-		dspcntr_reg = DSPBCNTR;
-		dspstatus_reg = PIPEBSTAT;
-		palette_reg = PALETTE_B;
-
-		/* values */
-		dpll_val = &regs->saveDPLL_B;
-		fp_val = &regs->saveFPB0;
-		pipeconf_val = &regs->savePIPEBCONF;
-		htot_val = &regs->saveHTOTAL_B;
-		hblank_val = &regs->saveHBLANK_B;
-		hsync_val = &regs->saveHSYNC_B;
-		vtot_val = &regs->saveVTOTAL_B;
-		vblank_val = &regs->saveVBLANK_B;
-		vsync_val = &regs->saveVSYNC_B;
-		pipesrc_val = &regs->savePIPEBSRC;
-		dspstride_val = &regs->saveDSPBSTRIDE;
-		dsplinoff_val = &regs->saveDSPBLINOFF;
-		dsptileoff_val = &regs->saveDSPBTILEOFF;
-		dspsize_val = &regs->saveDSPBSIZE;
-		dsppos_val = &regs->saveDSPBPOS;
-		dspsurf_val = &regs->saveDSPBSURF;
-		dspcntr_val = &regs->saveDSPBCNTR;
-		dspstatus_val = &regs->saveDSPBSTATUS;
-		palette_val = regs->save_palette_b;
+		mipi_val = &regs->saveMIPI;
 		break;
 	case 2:
 		/* register */
-		pipeconf_reg = PIPECCONF;
-		htot_reg = HTOTAL_C;
-		hblank_reg = HBLANK_C;
-		hsync_reg = HSYNC_C;
-		vtot_reg = VTOTAL_C;
-		vblank_reg = VBLANK_C;
-		vsync_reg = VSYNC_C;
-		pipesrc_reg = PIPECSRC;
-		dspstride_reg = DSPCSTRIDE;
-		dsplinoff_reg = DSPCLINOFF;
-		dsptileoff_reg = DSPCTILEOFF;
-		dspsize_reg = DSPCSIZE;
-		dsppos_reg = DSPCPOS;
-		dspsurf_reg = DSPCSURF;
 		mipi_reg = MIPI_C;
-		dspcntr_reg = DSPCCNTR;
-		dspstatus_reg = PIPECSTAT;
-		palette_reg = PALETTE_C;
-
 		/* pointer to values */
-		pipeconf_val = &regs->savePIPECCONF;
-		htot_val = &regs->saveHTOTAL_C;
-		hblank_val = &regs->saveHBLANK_C;
-		hsync_val = &regs->saveHSYNC_C;
-		vtot_val = &regs->saveVTOTAL_C;
-		vblank_val = &regs->saveVBLANK_C;
-		vsync_val = &regs->saveVSYNC_C;
-		pipesrc_val = &regs->savePIPECSRC;
-		dspstride_val = &regs->saveDSPCSTRIDE;
-		dsplinoff_val = &regs->saveDSPCLINOFF;
-		dsptileoff_val = &regs->saveDSPCTILEOFF;
-		dspsize_val = &regs->saveDSPCSIZE;
-		dsppos_val = &regs->saveDSPCPOS;
-		dspsurf_val = &regs->saveDSPCSURF;
 		mipi_val = &regs->saveMIPI_C;
-		dspcntr_val = &regs->saveDSPCCNTR;
-		dspstatus_val = &regs->saveDSPCSTATUS;
-		palette_val = regs->save_palette_c;
 		break;
 	default:
 		DRM_ERROR("%s, invalid pipe number.\n", __func__);
@@ -306,30 +194,30 @@
 	}
 
 	/* Pipe & plane A info */
-	*dpll_val = PSB_RVDC32(dpll_reg);
-	*fp_val = PSB_RVDC32(fp_reg);
-	*pipeconf_val = PSB_RVDC32(pipeconf_reg);
-	*htot_val = PSB_RVDC32(htot_reg);
-	*hblank_val = PSB_RVDC32(hblank_reg);
-	*hsync_val = PSB_RVDC32(hsync_reg);
-	*vtot_val = PSB_RVDC32(vtot_reg);
-	*vblank_val = PSB_RVDC32(vblank_reg);
-	*vsync_val = PSB_RVDC32(vsync_reg);
-	*pipesrc_val = PSB_RVDC32(pipesrc_reg);
-	*dspstride_val = PSB_RVDC32(dspstride_reg);
-	*dsplinoff_val = PSB_RVDC32(dsplinoff_reg);
-	*dsptileoff_val = PSB_RVDC32(dsptileoff_reg);
-	*dspsize_val = PSB_RVDC32(dspsize_reg);
-	*dsppos_val = PSB_RVDC32(dsppos_reg);
-	*dspsurf_val = PSB_RVDC32(dspsurf_reg);
-	*dspcntr_val = PSB_RVDC32(dspcntr_reg);
-	*dspstatus_val = PSB_RVDC32(dspstatus_reg);
+	pipe->dpll = PSB_RVDC32(map->dpll);
+	pipe->fp0 = PSB_RVDC32(map->fp0);
+	pipe->conf = PSB_RVDC32(map->conf);
+	pipe->htotal = PSB_RVDC32(map->htotal);
+	pipe->hblank = PSB_RVDC32(map->hblank);
+	pipe->hsync = PSB_RVDC32(map->hsync);
+	pipe->vtotal = PSB_RVDC32(map->vtotal);
+	pipe->vblank = PSB_RVDC32(map->vblank);
+	pipe->vsync = PSB_RVDC32(map->vsync);
+	pipe->src = PSB_RVDC32(map->src);
+	pipe->stride = PSB_RVDC32(map->stride);
+	pipe->linoff = PSB_RVDC32(map->linoff);
+	pipe->tileoff = PSB_RVDC32(map->tileoff);
+	pipe->size = PSB_RVDC32(map->size);
+	pipe->pos = PSB_RVDC32(map->pos);
+	pipe->surf = PSB_RVDC32(map->surf);
+	pipe->cntr = PSB_RVDC32(map->cntr);
+	pipe->status = PSB_RVDC32(map->status);
 
 	/*save palette (gamma) */
 	for (i = 0; i < 256; i++)
-		palette_val[i] = PSB_RVDC32(palette_reg + (i << 2));
+		pipe->palette[i] = PSB_RVDC32(map->palette + (i << 2));
 
-	if (pipe == 1) {
+	if (pipenum == 1) {
 		regs->savePFIT_CONTROL = PSB_RVDC32(PFIT_CONTROL);
 		regs->savePFIT_PGM_RATIOS = PSB_RVDC32(PFIT_PGM_RATIOS);
 
@@ -349,7 +237,7 @@
  *
  * Notes: FIXME_JLIU7 need to add the support for DPI MIPI & HDMI audio
  */
-static int mdfld_restore_display_registers(struct drm_device *dev, int pipe)
+static int mdfld_restore_display_registers(struct drm_device *dev, int pipenum)
 {
 	/* To get  panel out of ULPS mode. */
 	u32 temp = 0;
@@ -357,142 +245,30 @@
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct mdfld_dsi_config *dsi_config = NULL;
 	struct medfield_state *regs = &dev_priv->regs.mdfld;
-	u32 i = 0;
-	u32 dpll = 0;
+	struct psb_pipe *pipe = &dev_priv->regs.pipe[pipenum];
+	const struct psb_offset *map = &dev_priv->regmap[pipenum];
+	u32 i;
+	u32 dpll;
 	u32 timeout = 0;
 
-	/* regester */
-	u32 dpll_reg = MRST_DPLL_A;
-	u32 fp_reg = MRST_FPA0;
-	u32 pipeconf_reg = PIPEACONF;
-	u32 htot_reg = HTOTAL_A;
-	u32 hblank_reg = HBLANK_A;
-	u32 hsync_reg = HSYNC_A;
-	u32 vtot_reg = VTOTAL_A;
-	u32 vblank_reg = VBLANK_A;
-	u32 vsync_reg = VSYNC_A;
-	u32 pipesrc_reg = PIPEASRC;
-	u32 dspstride_reg = DSPASTRIDE;
-	u32 dsplinoff_reg = DSPALINOFF;
-	u32 dsptileoff_reg = DSPATILEOFF;
-	u32 dspsize_reg = DSPASIZE;
-	u32 dsppos_reg = DSPAPOS;
-	u32 dspsurf_reg = DSPASURF;
-	u32 dspstatus_reg = PIPEASTAT;
+	/* register */
 	u32 mipi_reg = MIPI;
-	u32 dspcntr_reg = DSPACNTR;
-	u32 palette_reg = PALETTE_A;
 
 	/* values */
-	u32 dpll_val = regs->saveDPLL_A & ~DPLL_VCO_ENABLE;
-	u32 fp_val = regs->saveFPA0;
-	u32 pipeconf_val = regs->savePIPEACONF;
-	u32 htot_val = regs->saveHTOTAL_A;
-	u32 hblank_val = regs->saveHBLANK_A;
-	u32 hsync_val = regs->saveHSYNC_A;
-	u32 vtot_val = regs->saveVTOTAL_A;
-	u32 vblank_val = regs->saveVBLANK_A;
-	u32 vsync_val = regs->saveVSYNC_A;
-	u32 pipesrc_val = regs->savePIPEASRC;
-	u32 dspstride_val = regs->saveDSPASTRIDE;
-	u32 dsplinoff_val = regs->saveDSPALINOFF;
-	u32 dsptileoff_val = regs->saveDSPATILEOFF;
-	u32 dspsize_val = regs->saveDSPASIZE;
-	u32 dsppos_val = regs->saveDSPAPOS;
-	u32 dspsurf_val = regs->saveDSPASURF;
-	u32 dspstatus_val = regs->saveDSPASTATUS;
+	u32 dpll_val = pipe->dpll;
 	u32 mipi_val = regs->saveMIPI;
-	u32 dspcntr_val = regs->saveDSPACNTR;
-	u32 *palette_val = regs->save_palette_a;
 
-	switch (pipe) {
+	switch (pipenum) {
 	case 0:
+		dpll_val &= ~DPLL_VCO_ENABLE;
 		dsi_config = dev_priv->dsi_configs[0];
 		break;
 	case 1:
-		/* regester */
-		dpll_reg = MDFLD_DPLL_B;
-		fp_reg = MDFLD_DPLL_DIV0;
-		pipeconf_reg = PIPEBCONF;
-		htot_reg = HTOTAL_B;
-		hblank_reg = HBLANK_B;
-		hsync_reg = HSYNC_B;
-		vtot_reg = VTOTAL_B;
-		vblank_reg = VBLANK_B;
-		vsync_reg = VSYNC_B;
-		pipesrc_reg = PIPEBSRC;
-		dspstride_reg = DSPBSTRIDE;
-		dsplinoff_reg = DSPBLINOFF;
-		dsptileoff_reg = DSPBTILEOFF;
-		dspsize_reg = DSPBSIZE;
-		dsppos_reg = DSPBPOS;
-		dspsurf_reg = DSPBSURF;
-		dspcntr_reg = DSPBCNTR;
-		dspstatus_reg = PIPEBSTAT;
-		palette_reg = PALETTE_B;
-
-		/* values */
-		dpll_val = regs->saveDPLL_B & ~DPLL_VCO_ENABLE;
-		fp_val = regs->saveFPB0;
-		pipeconf_val = regs->savePIPEBCONF;
-		htot_val = regs->saveHTOTAL_B;
-		hblank_val = regs->saveHBLANK_B;
-		hsync_val = regs->saveHSYNC_B;
-		vtot_val = regs->saveVTOTAL_B;
-		vblank_val = regs->saveVBLANK_B;
-		vsync_val = regs->saveVSYNC_B;
-		pipesrc_val = regs->savePIPEBSRC;
-		dspstride_val = regs->saveDSPBSTRIDE;
-		dsplinoff_val = regs->saveDSPBLINOFF;
-		dsptileoff_val = regs->saveDSPBTILEOFF;
-		dspsize_val = regs->saveDSPBSIZE;
-		dsppos_val = regs->saveDSPBPOS;
-		dspsurf_val = regs->saveDSPBSURF;
-		dspcntr_val = regs->saveDSPBCNTR;
-		dspstatus_val = regs->saveDSPBSTATUS;
-		palette_val = regs->save_palette_b;
+		dpll_val &= ~DPLL_VCO_ENABLE;
 		break;
 	case 2:
-		/* regester */
-		pipeconf_reg = PIPECCONF;
-		htot_reg = HTOTAL_C;
-		hblank_reg = HBLANK_C;
-		hsync_reg = HSYNC_C;
-		vtot_reg = VTOTAL_C;
-		vblank_reg = VBLANK_C;
-		vsync_reg = VSYNC_C;
-		pipesrc_reg = PIPECSRC;
-		dspstride_reg = DSPCSTRIDE;
-		dsplinoff_reg = DSPCLINOFF;
-		dsptileoff_reg = DSPCTILEOFF;
-		dspsize_reg = DSPCSIZE;
-		dsppos_reg = DSPCPOS;
-		dspsurf_reg = DSPCSURF;
 		mipi_reg = MIPI_C;
-		dspcntr_reg = DSPCCNTR;
-		dspstatus_reg = PIPECSTAT;
-		palette_reg = PALETTE_C;
-
-		/* values */
-		pipeconf_val = regs->savePIPECCONF;
-		htot_val = regs->saveHTOTAL_C;
-		hblank_val = regs->saveHBLANK_C;
-		hsync_val = regs->saveHSYNC_C;
-		vtot_val = regs->saveVTOTAL_C;
-		vblank_val = regs->saveVBLANK_C;
-		vsync_val = regs->saveVSYNC_C;
-		pipesrc_val = regs->savePIPECSRC;
-		dspstride_val = regs->saveDSPCSTRIDE;
-		dsplinoff_val = regs->saveDSPCLINOFF;
-		dsptileoff_val = regs->saveDSPCTILEOFF;
-		dspsize_val = regs->saveDSPCSIZE;
-		dsppos_val = regs->saveDSPCPOS;
-		dspsurf_val = regs->saveDSPCSURF;
 		mipi_val = regs->saveMIPI_C;
-		dspcntr_val = regs->saveDSPCCNTR;
-		dspstatus_val = regs->saveDSPCSTATUS;
-		palette_val = regs->save_palette_c;
-
 		dsi_config = dev_priv->dsi_configs[1];
 		break;
 	default:
@@ -503,14 +279,14 @@
 	/*make sure VGA plane is off. it initializes to on after reset!*/
 	PSB_WVDC32(0x80000000, VGACNTRL);
 
-	if (pipe == 1) {
-		PSB_WVDC32(dpll_val & ~DPLL_VCO_ENABLE, dpll_reg);
-		PSB_RVDC32(dpll_reg);
+	if (pipenum == 1) {
+		PSB_WVDC32(dpll_val & ~DPLL_VCO_ENABLE, map->dpll);
+		PSB_RVDC32(map->dpll);
 
-		PSB_WVDC32(fp_val, fp_reg);
+		PSB_WVDC32(pipe->fp0, map->fp0);
 	} else {
 
-		dpll = PSB_RVDC32(dpll_reg);
+		dpll = PSB_RVDC32(map->dpll);
 
 		if (!(dpll & DPLL_VCO_ENABLE)) {
 
@@ -518,23 +294,23 @@
 			   before enable the VCO */
 			if (dpll & MDFLD_PWR_GATE_EN) {
 				dpll &= ~MDFLD_PWR_GATE_EN;
-				PSB_WVDC32(dpll, dpll_reg);
+				PSB_WVDC32(dpll, map->dpll);
 				/* FIXME_MDFLD PO - change 500 to 1 after PO */
 				udelay(500);
 			}
 
-			PSB_WVDC32(fp_val, fp_reg);
-			PSB_WVDC32(dpll_val, dpll_reg);
+			PSB_WVDC32(pipe->fp0, map->fp0);
+			PSB_WVDC32(dpll_val, map->dpll);
 			/* FIXME_MDFLD PO - change 500 to 1 after PO */
 			udelay(500);
 
 			dpll_val |= DPLL_VCO_ENABLE;
-			PSB_WVDC32(dpll_val, dpll_reg);
-			PSB_RVDC32(dpll_reg);
+			PSB_WVDC32(dpll_val, map->dpll);
+			PSB_RVDC32(map->dpll);
 
 			/* wait for DSI PLL to lock */
 			while (timeout < 20000 &&
-			  !(PSB_RVDC32(pipeconf_reg) & PIPECONF_DSIPLL_LOCK)) {
+			  !(PSB_RVDC32(map->conf) & PIPECONF_DSIPLL_LOCK)) {
 				udelay(150);
 				timeout++;
 			}
@@ -547,28 +323,28 @@
 		}
 	}
 	/* Restore mode */
-	PSB_WVDC32(htot_val, htot_reg);
-	PSB_WVDC32(hblank_val, hblank_reg);
-	PSB_WVDC32(hsync_val, hsync_reg);
-	PSB_WVDC32(vtot_val, vtot_reg);
-	PSB_WVDC32(vblank_val, vblank_reg);
-	PSB_WVDC32(vsync_val, vsync_reg);
-	PSB_WVDC32(pipesrc_val, pipesrc_reg);
-	PSB_WVDC32(dspstatus_val, dspstatus_reg);
+	PSB_WVDC32(pipe->htotal, map->htotal);
+	PSB_WVDC32(pipe->hblank, map->hblank);
+	PSB_WVDC32(pipe->hsync, map->hsync);
+	PSB_WVDC32(pipe->vtotal, map->vtotal);
+	PSB_WVDC32(pipe->vblank, map->vblank);
+	PSB_WVDC32(pipe->vsync, map->vsync);
+	PSB_WVDC32(pipe->src, map->src);
+	PSB_WVDC32(pipe->status, map->status);
 
 	/*set up the plane*/
-	PSB_WVDC32(dspstride_val, dspstride_reg);
-	PSB_WVDC32(dsplinoff_val, dsplinoff_reg);
-	PSB_WVDC32(dsptileoff_val, dsptileoff_reg);
-	PSB_WVDC32(dspsize_val, dspsize_reg);
-	PSB_WVDC32(dsppos_val, dsppos_reg);
-	PSB_WVDC32(dspsurf_val, dspsurf_reg);
+	PSB_WVDC32(pipe->stride, map->stride);
+	PSB_WVDC32(pipe->linoff, map->linoff);
+	PSB_WVDC32(pipe->tileoff, map->tileoff);
+	PSB_WVDC32(pipe->size, map->size);
+	PSB_WVDC32(pipe->pos, map->pos);
+	PSB_WVDC32(pipe->surf, map->surf);
 
-	if (pipe == 1) {
+	if (pipenum == 1) {
 		/* restore palette (gamma) */
 		/*DRM_UDELAY(50000); */
 		for (i = 0; i < 256; i++)
-			PSB_WVDC32(palette_val[i], palette_reg + (i << 2));
+			PSB_WVDC32(pipe->palette[i], map->palette + (i << 2));
 
 		PSB_WVDC32(regs->savePFIT_CONTROL, PFIT_CONTROL);
 		PSB_WVDC32(regs->savePFIT_PGM_RATIOS, PFIT_PGM_RATIOS);
@@ -578,7 +354,7 @@
 		/*TODO: resume pipe*/
 
 		/*enable the plane*/
-		PSB_WVDC32(dspcntr_val & ~DISPLAY_PLANE_ENABLE, dspcntr_reg);
+		PSB_WVDC32(pipe->cntr & ~DISPLAY_PLANE_ENABLE, map->cntr);
 
 		return 0;
 	}
@@ -588,7 +364,7 @@
 
 	/*setup MIPI adapter + MIPI IP registers*/
 	if (dsi_config)
-		mdfld_dsi_controller_init(dsi_config, pipe);
+		mdfld_dsi_controller_init(dsi_config, pipenum);
 
 	if (in_atomic() || in_interrupt())
 		mdelay(20);
@@ -596,7 +372,7 @@
 		msleep(20);
 
 	/*enable the plane*/
-	PSB_WVDC32(dspcntr_val, dspcntr_reg);
+	PSB_WVDC32(pipe->cntr, map->cntr);
 
 	if (in_atomic() || in_interrupt())
 		mdelay(20);
@@ -625,12 +401,12 @@
 	mdelay(1);
 
 	/*enable the pipe*/
-	PSB_WVDC32(pipeconf_val, pipeconf_reg);
+	PSB_WVDC32(pipe->conf, map->conf);
 
 	/* restore palette (gamma) */
 	/*DRM_UDELAY(50000); */
 	for (i = 0; i < 256; i++)
-		PSB_WVDC32(palette_val[i], palette_reg + (i << 2));
+		PSB_WVDC32(pipe->palette[i], map->palette + (i << 2));
 
 	return 0;
 }
@@ -667,6 +443,87 @@
 	return 0;
 }
 
+/* Medfield  */
+static const struct psb_offset mdfld_regmap[3] = {
+	{
+		.fp0 = MRST_FPA0,
+		.fp1 = MRST_FPA1,
+		.cntr = DSPACNTR,
+		.conf = PIPEACONF,
+		.src = PIPEASRC,
+		.dpll = MRST_DPLL_A,
+		.htotal = HTOTAL_A,
+		.hblank = HBLANK_A,
+		.hsync = HSYNC_A,
+		.vtotal = VTOTAL_A,
+		.vblank = VBLANK_A,
+		.vsync = VSYNC_A,
+		.stride = DSPASTRIDE,
+		.size = DSPASIZE,
+		.pos = DSPAPOS,
+		.surf = DSPASURF,
+		.addr = MRST_DSPABASE,
+		.status = PIPEASTAT,
+		.linoff = DSPALINOFF,
+		.tileoff = DSPATILEOFF,
+		.palette = PALETTE_A,
+	},
+	{
+		.fp0 = MDFLD_DPLL_DIV0,
+		.cntr = DSPBCNTR,
+		.conf = PIPEBCONF,
+		.src = PIPEBSRC,
+		.dpll = MDFLD_DPLL_B,
+		.htotal = HTOTAL_B,
+		.hblank = HBLANK_B,
+		.hsync = HSYNC_B,
+		.vtotal = VTOTAL_B,
+		.vblank = VBLANK_B,
+		.vsync = VSYNC_B,
+		.stride = DSPBSTRIDE,
+		.size = DSPBSIZE,
+		.pos = DSPBPOS,
+		.surf = DSPBSURF,
+		.addr = MRST_DSPBBASE,
+		.status = PIPEBSTAT,
+		.linoff = DSPBLINOFF,
+		.tileoff = DSPBTILEOFF,
+		.palette = PALETTE_B,
+	},
+	{
+		.fp0 = MRST_FPA0,	/* This is what the old code did ?? */
+		.cntr = DSPCCNTR,
+		.conf = PIPECCONF,
+		.src = PIPECSRC,
+		/* No DPLL_C */
+		.dpll = MRST_DPLL_A,
+		.htotal = HTOTAL_C,
+		.hblank = HBLANK_C,
+		.hsync = HSYNC_C,
+		.vtotal = VTOTAL_C,
+		.vblank = VBLANK_C,
+		.vsync = VSYNC_C,
+		.stride = DSPCSTRIDE,
+		.size = DSPBSIZE,
+		.pos = DSPCPOS,
+		.surf = DSPCSURF,
+		.addr = MDFLD_DSPCBASE,
+		.status = PIPECSTAT,
+		.linoff = DSPCLINOFF,
+		.tileoff = DSPCTILEOFF,
+		.palette = PALETTE_C,
+	},
+};
+
+static int mdfld_chip_setup(struct drm_device *dev)
+{
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	if (pci_enable_msi(dev->pdev))
+		dev_warn(dev->dev, "Enabling MSI failed!\n");
+	dev_priv->regmap = mdfld_regmap;
+	return mid_chip_setup(dev);
+}
+
 const struct psb_ops mdfld_chip_ops = {
 	.name = "mdfld",
 	.accel_2d = 0,
@@ -676,7 +533,7 @@
 	.hdmi_mask = (1 << 1),
 	.sgx_offset = MRST_SGX_OFFSET,
 
-	.chip_setup = mid_chip_setup,
+	.chip_setup = mdfld_chip_setup,
 	.crtc_helper = &mdfld_helper_funcs,
 	.crtc_funcs = &psb_intel_crtc_funcs,
 
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
index baa0e14..489ffd2 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_pkg_sender.c
@@ -605,6 +605,8 @@
 	struct mdfld_dsi_config *dsi_config =
 				mdfld_dsi_get_config(dsi_connector);
 	struct drm_device *dev = dsi_config->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 mipi_val = 0;
 
 	if (!dsi_connector) {
@@ -632,21 +634,13 @@
 	pkg_sender->status = MDFLD_DSI_PKG_SENDER_FREE;
 
 	/*init regs*/
-	if (pipe == 0) {
-		pkg_sender->dpll_reg = MRST_DPLL_A;
-		pkg_sender->dspcntr_reg = DSPACNTR;
-		pkg_sender->pipeconf_reg = PIPEACONF;
-		pkg_sender->dsplinoff_reg = DSPALINOFF;
-		pkg_sender->dspsurf_reg = DSPASURF;
-		pkg_sender->pipestat_reg = PIPEASTAT;
-	} else if (pipe == 2) {
-		pkg_sender->dpll_reg = MRST_DPLL_A;
-		pkg_sender->dspcntr_reg = DSPCCNTR;
-		pkg_sender->pipeconf_reg = PIPECCONF;
-		pkg_sender->dsplinoff_reg = DSPCLINOFF;
-		pkg_sender->dspsurf_reg = DSPCSURF;
-		pkg_sender->pipestat_reg = PIPECSTAT;
-	}
+	/* FIXME: should just copy the regmap ptr ? */
+	pkg_sender->dpll_reg = map->dpll;
+	pkg_sender->dspcntr_reg = map->cntr;
+	pkg_sender->pipeconf_reg = map->conf;
+	pkg_sender->dsplinoff_reg = map->linoff;
+	pkg_sender->dspsurf_reg = map->surf;
+	pkg_sender->pipestat_reg = map->status;
 
 	pkg_sender->mipi_intr_stat_reg = MIPI_INTR_STAT_REG(pipe);
 	pkg_sender->mipi_lp_gen_data_reg = MIPI_LP_GEN_DATA_REG(pipe);
diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index a35a292..3f3cd61 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -50,17 +50,14 @@
 
 void mdfldWaitForPipeDisable(struct drm_device *dev, int pipe)
 {
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int count, temp;
-	u32 pipeconf_reg = PIPEACONF;
 
 	switch (pipe) {
 	case 0:
-		break;
 	case 1:
-		pipeconf_reg = PIPEBCONF;
-		break;
 	case 2:
-		pipeconf_reg = PIPECCONF;
 		break;
 	default:
 		DRM_ERROR("Illegal Pipe Number.\n");
@@ -73,7 +70,7 @@
 
 	/* Wait for for the pipe disable to take effect. */
 	for (count = 0; count < COUNT_MAX; count++) {
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_PIPE_STATE) == 0)
 			break;
 	}
@@ -81,17 +78,14 @@
 
 void mdfldWaitForPipeEnable(struct drm_device *dev, int pipe)
 {
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int count, temp;
-	u32 pipeconf_reg = PIPEACONF;
 
 	switch (pipe) {
 	case 0:
-		break;
 	case 1:
-		pipeconf_reg = PIPEBCONF;
-		break;
 	case 2:
-		pipeconf_reg = PIPECCONF;
 		break;
 	default:
 		DRM_ERROR("Illegal Pipe Number.\n");
@@ -104,7 +98,7 @@
 
 	/* Wait for for the pipe enable to take effect. */
 	for (count = 0; count < COUNT_MAX; count++) {
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_PIPE_STATE) == 1)
 			break;
 	}
@@ -189,15 +183,12 @@
 				struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_i915_master_private *master_priv; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
-	int dsplinoff = DSPALINOFF;
-	int dspsurf = DSPASURF;
-	int dspstride = DSPASTRIDE;
-	int dspcntr_reg = DSPACNTR;
 	u32 dspcntr;
 	int ret;
 
@@ -215,23 +206,7 @@
 	if (ret)
 		return ret;
 
-	switch (pipe) {
-	case 0:
-		dsplinoff = DSPALINOFF;
-		break;
-	case 1:
-		dsplinoff = DSPBLINOFF;
-		dspsurf = DSPBSURF;
-		dspstride = DSPBSTRIDE;
-		dspcntr_reg = DSPBCNTR;
-		break;
-	case 2:
-		dsplinoff = DSPCLINOFF;
-		dspsurf = DSPCSURF;
-		dspstride = DSPCSTRIDE;
-		dspcntr_reg = DSPCCNTR;
-		break;
-	default:
+	if (pipe > 2) {
 		DRM_ERROR("Illegal Pipe Number.\n");
 		return -EINVAL;
 	}
@@ -242,8 +217,8 @@
 	start = psbfb->gtt->offset;
 	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
 
-	REG_WRITE(dspstride, crtc->fb->pitches[0]);
-	dspcntr = REG_READ(dspcntr_reg);
+	REG_WRITE(map->stride, crtc->fb->pitches[0]);
+	dspcntr = REG_READ(map->cntr);
 	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 
 	switch (crtc->fb->bits_per_pixel) {
@@ -261,14 +236,14 @@
 		dspcntr |= DISPPLANE_32BPP_NO_ALPHA;
 		break;
 	}
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
 	dev_dbg(dev->dev, "Writing base %08lX %08lX %d %d\n",
 						start, offset, x, y);
-	REG_WRITE(dsplinoff, offset);
-	REG_READ(dsplinoff);
-	REG_WRITE(dspsurf, start);
-	REG_READ(dspsurf);
+	REG_WRITE(map->linoff, offset);
+	REG_READ(map->linoff);
+	REG_WRITE(map->surf, start);
+	REG_READ(map->surf);
 
 	gma_power_end(dev);
 
@@ -281,78 +256,56 @@
  */
 void mdfld_disable_crtc(struct drm_device *dev, int pipe)
 {
-	int dpll_reg = MRST_DPLL_A;
-	int dspcntr_reg = DSPACNTR;
-	int dspbase_reg = MRST_DSPABASE;
-	int pipeconf_reg = PIPEACONF;
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 temp;
 
 	dev_dbg(dev->dev, "pipe = %d\n", pipe);
 
 
-	switch (pipe) {
-	case 0:
-		break;
-	case 1:
-		dpll_reg = MDFLD_DPLL_B;
-		dspcntr_reg = DSPBCNTR;
-		dspbase_reg = DSPBSURF;
-		pipeconf_reg = PIPEBCONF;
-		break;
-	case 2:
-		dpll_reg = MRST_DPLL_A;
-		dspcntr_reg = DSPCCNTR;
-		dspbase_reg = MDFLD_DSPCBASE;
-		pipeconf_reg = PIPECCONF;
-		break;
-	default:
-		DRM_ERROR("Illegal Pipe Number.\n");
-		return;
-	}
-
 	if (pipe != 1)
 		mdfld_dsi_gen_fifo_ready(dev, MIPI_GEN_FIFO_STAT_REG(pipe),
 				HS_CTRL_FIFO_EMPTY | HS_DATA_FIFO_EMPTY);
 
 	/* Disable display plane */
-	temp = REG_READ(dspcntr_reg);
+	temp = REG_READ(map->cntr);
 	if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-		REG_WRITE(dspcntr_reg,
+		REG_WRITE(map->cntr,
 			  temp & ~DISPLAY_PLANE_ENABLE);
 		/* Flush the plane changes */
-		REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
-		REG_READ(dspbase_reg);
+		REG_WRITE(map->base, REG_READ(map->base));
+		REG_READ(map->base);
 	}
 
 	/* FIXME_JLIU7 MDFLD_PO revisit */
 
 	/* Next, disable display pipes */
-	temp = REG_READ(pipeconf_reg);
+	temp = REG_READ(map->conf);
 	if ((temp & PIPEACONF_ENABLE) != 0) {
 		temp &= ~PIPEACONF_ENABLE;
 		temp |= PIPECONF_PLANE_OFF | PIPECONF_CURSOR_OFF;
-		REG_WRITE(pipeconf_reg, temp);
-		REG_READ(pipeconf_reg);
+		REG_WRITE(map->conf, temp);
+		REG_READ(map->conf);
 
 		/* Wait for for the pipe disable to take effect. */
 		mdfldWaitForPipeDisable(dev, pipe);
 	}
 
-	temp = REG_READ(dpll_reg);
+	temp = REG_READ(map->dpll);
 	if (temp & DPLL_VCO_ENABLE) {
 		if ((pipe != 1 &&
 			!((REG_READ(PIPEACONF) | REG_READ(PIPECCONF))
 				& PIPEACONF_ENABLE)) || pipe == 1) {
 			temp &= ~(DPLL_VCO_ENABLE);
-			REG_WRITE(dpll_reg, temp);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to turn off. */
 			/* FIXME_MDFLD PO may need more delay */
 			udelay(500);
 
 			if (!(temp & MDFLD_PWR_GATE_EN)) {
 				/* gating power of DPLL */
-				REG_WRITE(dpll_reg, temp | MDFLD_PWR_GATE_EN);
+				REG_WRITE(map->dpll, temp | MDFLD_PWR_GATE_EN);
 				/* FIXME_MDFLD PO - change 500 to 1 after PO */
 				udelay(5000);
 			}
@@ -373,41 +326,15 @@
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
-	int dpll_reg = MRST_DPLL_A;
-	int dspcntr_reg = DSPACNTR;
-	int dspbase_reg = MRST_DSPABASE;
-	int pipeconf_reg = PIPEACONF;
-	u32 pipestat_reg = PIPEASTAT;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 pipeconf = dev_priv->pipeconf[pipe];
 	u32 temp;
 	int timeout = 0;
 
 	dev_dbg(dev->dev, "mode = %d, pipe = %d\n", mode, pipe);
 
-/* FIXME_JLIU7 MDFLD_PO replaced w/ the following function */
-/* mdfld_dbi_dpms (struct drm_device *dev, int pipe, bool enabled) */
-
-	switch (pipe) {
-	case 0:
-		break;
-	case 1:
-		dpll_reg = DPLL_B;
-		dspcntr_reg = DSPBCNTR;
-		dspbase_reg = MRST_DSPBBASE;
-		pipeconf_reg = PIPEBCONF;
-		dpll_reg = MDFLD_DPLL_B;
-		break;
-	case 2:
-		dpll_reg = MRST_DPLL_A;
-		dspcntr_reg = DSPCCNTR;
-		dspbase_reg = MDFLD_DSPCBASE;
-		pipeconf_reg = PIPECCONF;
-		pipestat_reg = PIPECSTAT;
-		break;
-	default:
-		DRM_ERROR("Illegal Pipe Number.\n");
-		return;
-	}
+	/* Note: Old code uses pipe a stat for pipe b but that appears
+	   to be a bug */
 
 	if (!gma_power_begin(dev, true))
 		return;
@@ -420,25 +347,25 @@
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 		/* Enable the DPLL */
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 
 		if ((temp & DPLL_VCO_ENABLE) == 0) {
 			/* When ungating power of DPLL, needs to wait 0.5us
 			   before enable the VCO */
 			if (temp & MDFLD_PWR_GATE_EN) {
 				temp &= ~MDFLD_PWR_GATE_EN;
-				REG_WRITE(dpll_reg, temp);
+				REG_WRITE(map->dpll, temp);
 				/* FIXME_MDFLD PO - change 500 to 1 after PO */
 				udelay(500);
 			}
 
-			REG_WRITE(dpll_reg, temp);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
 			/* FIXME_MDFLD PO - change 500 to 1 after PO */
 			udelay(500);
 
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 
 			/**
 			 * wait for DSI PLL to lock
@@ -446,25 +373,25 @@
 			 * since both MIPI pipes share the same PLL.
 			 */
 			while ((pipe != 2) && (timeout < 20000) &&
-			  !(REG_READ(pipeconf_reg) & PIPECONF_DSIPLL_LOCK)) {
+			  !(REG_READ(map->conf) & PIPECONF_DSIPLL_LOCK)) {
 				udelay(150);
 				timeout++;
 			}
 		}
 
 		/* Enable the plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				temp | DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+			REG_WRITE(map->base, REG_READ(map->base));
 		}
 
 		/* Enable the pipe */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) == 0) {
-			REG_WRITE(pipeconf_reg, pipeconf);
+			REG_WRITE(map->conf, pipeconf);
 
 			/* Wait for for the pipe enable to take effect. */
 			mdfldWaitForPipeEnable(dev, pipe);
@@ -473,39 +400,39 @@
 		/*workaround for sighting 3741701 Random X blank display*/
 		/*perform w/a in video mode only on pipe A or C*/
 		if (pipe == 0 || pipe == 2) {
-			REG_WRITE(pipestat_reg, REG_READ(pipestat_reg));
+			REG_WRITE(map->status, REG_READ(map->status));
 			msleep(100);
-			if (PIPE_VBLANK_STATUS & REG_READ(pipestat_reg))
+			if (PIPE_VBLANK_STATUS & REG_READ(map->status))
 				dev_dbg(dev->dev, "OK");
 			else {
 				dev_dbg(dev->dev, "STUCK!!!!");
 				/*shutdown controller*/
-				temp = REG_READ(dspcntr_reg);
-				REG_WRITE(dspcntr_reg,
+				temp = REG_READ(map->cntr);
+				REG_WRITE(map->cntr,
 						temp & ~DISPLAY_PLANE_ENABLE);
-				REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+				REG_WRITE(map->base, REG_READ(map->base));
 				/*mdfld_dsi_dpi_shut_down(dev, pipe);*/
 				REG_WRITE(0xb048, 1);
 				msleep(100);
-				temp = REG_READ(pipeconf_reg);
+				temp = REG_READ(map->conf);
 				temp &= ~PIPEACONF_ENABLE;
-				REG_WRITE(pipeconf_reg, temp);
+				REG_WRITE(map->conf, temp);
 				msleep(100); /*wait for pipe disable*/
 				REG_WRITE(MIPI_DEVICE_READY_REG(pipe), 0);
 				msleep(100);
 				REG_WRITE(0xb004, REG_READ(0xb004));
 				/* try to bring the controller back up again*/
 				REG_WRITE(MIPI_DEVICE_READY_REG(pipe), 1);
-				temp = REG_READ(dspcntr_reg);
-				REG_WRITE(dspcntr_reg,
+				temp = REG_READ(map->cntr);
+				REG_WRITE(map->cntr,
 						temp | DISPLAY_PLANE_ENABLE);
-				REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+				REG_WRITE(map->base, REG_READ(map->base));
 				/*mdfld_dsi_dpi_turn_on(dev, pipe);*/
 				REG_WRITE(0xb048, 2);
 				msleep(100);
-				temp = REG_READ(pipeconf_reg);
+				temp = REG_READ(map->conf);
 				temp |= PIPEACONF_ENABLE;
-				REG_WRITE(pipeconf_reg, temp);
+				REG_WRITE(map->conf, temp);
 			}
 		}
 
@@ -529,35 +456,35 @@
 		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
 
 		/* Disable display plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp & ~DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
-			REG_READ(dspbase_reg);
+			REG_WRITE(map->base, REG_READ(map->base));
+			REG_READ(map->base);
 		}
 
 		/* Next, disable display pipes */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) != 0) {
 			temp &= ~PIPEACONF_ENABLE;
 			temp |= PIPECONF_PLANE_OFF | PIPECONF_CURSOR_OFF;
-			REG_WRITE(pipeconf_reg, temp);
-			REG_READ(pipeconf_reg);
+			REG_WRITE(map->conf, temp);
+			REG_READ(map->conf);
 
 			/* Wait for for the pipe disable to take effect. */
 			mdfldWaitForPipeDisable(dev, pipe);
 		}
 
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if (temp & DPLL_VCO_ENABLE) {
 			if ((pipe != 1 && !((REG_READ(PIPEACONF)
 				| REG_READ(PIPECCONF)) & PIPEACONF_ENABLE))
 					|| pipe == 1) {
 				temp &= ~(DPLL_VCO_ENABLE);
-				REG_WRITE(dpll_reg, temp);
-				REG_READ(dpll_reg);
+				REG_WRITE(map->dpll, temp);
+				REG_READ(map->dpll);
 				/* Wait for the clocks to turn off. */
 				/* FIXME_MDFLD PO may need more delay */
 				udelay(500);
@@ -764,21 +691,7 @@
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int pipe = psb_intel_crtc->pipe;
-	int fp_reg = MRST_FPA0;
-	int dpll_reg = MRST_DPLL_A;
-	int dspcntr_reg = DSPACNTR;
-	int pipeconf_reg = PIPEACONF;
-	int htot_reg = HTOTAL_A;
-	int hblank_reg = HBLANK_A;
-	int hsync_reg = HSYNC_A;
-	int vtot_reg = VTOTAL_A;
-	int vblank_reg = VBLANK_A;
-	int vsync_reg = VSYNC_A;
-	int dspsize_reg = DSPASIZE;
-	int dsppos_reg = DSPAPOS;
-	int pipesrc_reg = PIPEASRC;
-	u32 *pipeconf = &dev_priv->pipeconf[pipe];
-	u32 *dspcntr = &dev_priv->dspcntr[pipe];
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk = 0;
 	int clk_n = 0, clk_p2 = 0, clk_byte = 1, clk = 0, m_conv = 0,
 								clk_tmp = 0;
@@ -806,45 +719,6 @@
 	}
 #endif
 
-	switch (pipe) {
-	case 0:
-		break;
-	case 1:
-		fp_reg = FPB0;
-		dpll_reg = DPLL_B;
-		dspcntr_reg = DSPBCNTR;
-		pipeconf_reg = PIPEBCONF;
-		htot_reg = HTOTAL_B;
-		hblank_reg = HBLANK_B;
-		hsync_reg = HSYNC_B;
-		vtot_reg = VTOTAL_B;
-		vblank_reg = VBLANK_B;
-		vsync_reg = VSYNC_B;
-		dspsize_reg = DSPBSIZE;
-		dsppos_reg = DSPBPOS;
-		pipesrc_reg = PIPEBSRC;
-		fp_reg = MDFLD_DPLL_DIV0;
-		dpll_reg = MDFLD_DPLL_B;
-		break;
-	case 2:
-		dpll_reg = MRST_DPLL_A;
-		dspcntr_reg = DSPCCNTR;
-		pipeconf_reg = PIPECCONF;
-		htot_reg = HTOTAL_C;
-		hblank_reg = HBLANK_C;
-		hsync_reg = HSYNC_C;
-		vtot_reg = VTOTAL_C;
-		vblank_reg = VBLANK_C;
-		vsync_reg = VSYNC_C;
-		dspsize_reg = DSPCSIZE;
-		dsppos_reg = DSPCPOS;
-		pipesrc_reg = PIPECSRC;
-		break;
-	default:
-		DRM_ERROR("Illegal Pipe Number.\n");
-		return 0;
-	}
-
 	ret = check_fb(crtc->fb);
 	if (ret)
 		return ret;
@@ -929,21 +803,21 @@
 		 * contained within the displayable area of the screen image
 		 * (frame buffer).
 		 */
-		REG_WRITE(dspsize_reg, ((min(mode->crtc_vdisplay, adjusted_mode->crtc_vdisplay) - 1) << 16)
+		REG_WRITE(map->size, ((min(mode->crtc_vdisplay, adjusted_mode->crtc_vdisplay) - 1) << 16)
 				| (min(mode->crtc_hdisplay, adjusted_mode->crtc_hdisplay) - 1));
 		/* Set the CRTC with encoder mode. */
-		REG_WRITE(pipesrc_reg, ((mode->crtc_hdisplay - 1) << 16)
+		REG_WRITE(map->src, ((mode->crtc_hdisplay - 1) << 16)
 				 | (mode->crtc_vdisplay - 1));
 	} else {
-		REG_WRITE(dspsize_reg,
+		REG_WRITE(map->size,
 				((mode->crtc_vdisplay - 1) << 16) |
 						(mode->crtc_hdisplay - 1));
-		REG_WRITE(pipesrc_reg,
+		REG_WRITE(map->src,
 				((mode->crtc_hdisplay - 1) << 16) |
 						(mode->crtc_vdisplay - 1));
 	}
 
-	REG_WRITE(dsppos_reg, 0);
+	REG_WRITE(map->pos, 0);
 
 	if (psb_intel_encoder)
 		drm_connector_property_get_value(connector,
@@ -961,34 +835,34 @@
 		offsetY = (adjusted_mode->crtc_vdisplay -
 					mode->crtc_vdisplay) / 2;
 
-		REG_WRITE(htot_reg, (mode->crtc_hdisplay - 1) |
+		REG_WRITE(map->htotal, (mode->crtc_hdisplay - 1) |
 			((adjusted_mode->crtc_htotal - 1) << 16));
-		REG_WRITE(vtot_reg, (mode->crtc_vdisplay - 1) |
+		REG_WRITE(map->vtotal, (mode->crtc_vdisplay - 1) |
 			((adjusted_mode->crtc_vtotal - 1) << 16));
-		REG_WRITE(hblank_reg, (adjusted_mode->crtc_hblank_start -
+		REG_WRITE(map->hblank, (adjusted_mode->crtc_hblank_start -
 								offsetX - 1) |
 			((adjusted_mode->crtc_hblank_end - offsetX - 1) << 16));
-		REG_WRITE(hsync_reg, (adjusted_mode->crtc_hsync_start -
+		REG_WRITE(map->hsync, (adjusted_mode->crtc_hsync_start -
 								offsetX - 1) |
 			((adjusted_mode->crtc_hsync_end - offsetX - 1) << 16));
-		REG_WRITE(vblank_reg, (adjusted_mode->crtc_vblank_start -
+		REG_WRITE(map->vblank, (adjusted_mode->crtc_vblank_start -
 								offsetY - 1) |
 			((adjusted_mode->crtc_vblank_end - offsetY - 1) << 16));
-		REG_WRITE(vsync_reg, (adjusted_mode->crtc_vsync_start -
+		REG_WRITE(map->vsync, (adjusted_mode->crtc_vsync_start -
 								offsetY - 1) |
 			((adjusted_mode->crtc_vsync_end - offsetY - 1) << 16));
 	} else {
-		REG_WRITE(htot_reg, (adjusted_mode->crtc_hdisplay - 1) |
+		REG_WRITE(map->htotal, (adjusted_mode->crtc_hdisplay - 1) |
 			((adjusted_mode->crtc_htotal - 1) << 16));
-		REG_WRITE(vtot_reg, (adjusted_mode->crtc_vdisplay - 1) |
+		REG_WRITE(map->vtotal, (adjusted_mode->crtc_vdisplay - 1) |
 			((adjusted_mode->crtc_vtotal - 1) << 16));
-		REG_WRITE(hblank_reg, (adjusted_mode->crtc_hblank_start - 1) |
+		REG_WRITE(map->hblank, (adjusted_mode->crtc_hblank_start - 1) |
 			((adjusted_mode->crtc_hblank_end - 1) << 16));
-		REG_WRITE(hsync_reg, (adjusted_mode->crtc_hsync_start - 1) |
+		REG_WRITE(map->hsync, (adjusted_mode->crtc_hsync_start - 1) |
 			((adjusted_mode->crtc_hsync_end - 1) << 16));
-		REG_WRITE(vblank_reg, (adjusted_mode->crtc_vblank_start - 1) |
+		REG_WRITE(map->vblank, (adjusted_mode->crtc_vblank_start - 1) |
 			((adjusted_mode->crtc_vblank_end - 1) << 16));
-		REG_WRITE(vsync_reg, (adjusted_mode->crtc_vsync_start - 1) |
+		REG_WRITE(map->vsync, (adjusted_mode->crtc_vsync_start - 1) |
 			((adjusted_mode->crtc_vsync_end - 1) << 16));
 	}
 
@@ -1000,12 +874,12 @@
 	}
 
 	/* setup pipeconf */
-	*pipeconf = PIPEACONF_ENABLE; /* FIXME_JLIU7 REG_READ(pipeconf_reg); */
+	dev_priv->pipeconf[pipe] = PIPEACONF_ENABLE; /* FIXME_JLIU7 REG_READ(pipeconf_reg); */
 
 	/* Set up the display plane register */
-	*dspcntr = REG_READ(dspcntr_reg);
-	*dspcntr |= pipe << DISPPLANE_SEL_PIPE_POS;
-	*dspcntr |= DISPLAY_PLANE_ENABLE;
+	dev_priv->dspcntr[pipe] = REG_READ(map->cntr);
+	dev_priv->dspcntr[pipe] |= pipe << DISPPLANE_SEL_PIPE_POS;
+	dev_priv->dspcntr[pipe] |= DISPLAY_PLANE_ENABLE;
 
 	if (is_mipi2)
 		goto mrst_crtc_mode_set_exit;
@@ -1070,21 +944,21 @@
 					clock.p1, m_conv);
 		}
 
-		dpll = REG_READ(dpll_reg);
+		dpll = REG_READ(map->dpll);
 
 		if (dpll & DPLL_VCO_ENABLE) {
 			dpll &= ~DPLL_VCO_ENABLE;
-			REG_WRITE(dpll_reg, dpll);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, dpll);
+			REG_READ(map->dpll);
 
 			/* FIXME jliu7 check the DPLL lock bit PIPEACONF[29] */
 			/* FIXME_MDFLD PO - change 500 to 1 after PO */
 			udelay(500);
 
 			/* reset M1, N1 & P1 */
-			REG_WRITE(fp_reg, 0);
+			REG_WRITE(map->fp0, 0);
 			dpll &= ~MDFLD_P1_MASK;
-			REG_WRITE(dpll_reg, dpll);
+			REG_WRITE(map->dpll, dpll);
 			/* FIXME_MDFLD PO - change 500 to 1 after PO */
 			udelay(500);
 		}
@@ -1093,7 +967,7 @@
 		 * enable the VCO */
 		if (dpll & MDFLD_PWR_GATE_EN) {
 			dpll &= ~MDFLD_PWR_GATE_EN;
-			REG_WRITE(dpll_reg, dpll);
+			REG_WRITE(map->dpll, dpll);
 			/* FIXME_MDFLD PO - change 500 to 1 after PO */
 			udelay(500);
 		}
@@ -1134,18 +1008,18 @@
 		fp = 0x000000c1;
 	}
 
-	REG_WRITE(fp_reg, fp);
-	REG_WRITE(dpll_reg, dpll);
+	REG_WRITE(map->fp0, fp);
+	REG_WRITE(map->dpll, dpll);
 	/* FIXME_MDFLD PO - change 500 to 1 after PO */
 	udelay(500);
 
 	dpll |= DPLL_VCO_ENABLE;
-	REG_WRITE(dpll_reg, dpll);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->dpll, dpll);
+	REG_READ(map->dpll);
 
 	/* wait for DSI PLL to lock */
 	while (timeout < 20000 &&
-			!(REG_READ(pipeconf_reg) & PIPECONF_DSIPLL_LOCK)) {
+			!(REG_READ(map->conf) & PIPECONF_DSIPLL_LOCK)) {
 		udelay(150);
 		timeout++;
 	}
@@ -1155,11 +1029,11 @@
 
 	dev_dbg(dev->dev, "is_mipi = 0x%x\n", is_mipi);
 
-	REG_WRITE(pipeconf_reg, *pipeconf);
-	REG_READ(pipeconf_reg);
+	REG_WRITE(map->conf, dev_priv->pipeconf[pipe]);
+	REG_READ(map->conf);
 
 	/* Wait for for the pipe enable to take effect. */
-	REG_WRITE(dspcntr_reg, *dspcntr);
+	REG_WRITE(map->cntr, dev_priv->dspcntr[pipe]);
 	psb_intel_wait_for_vblank(dev);
 
 mrst_crtc_mode_set_exit:
diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c
index a39b0d0..f821c83 100644
--- a/drivers/gpu/drm/gma500/oaktrail_crtc.c
+++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c
@@ -162,12 +162,10 @@
 static void oaktrail_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
-	int dpll_reg = (pipe == 0) ? MRST_DPLL_A : DPLL_B;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int dspbase_reg = (pipe == 0) ? MRST_DSPABASE : DSPBBASE;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 temp;
 
 	if (!gma_power_begin(dev, true))
@@ -181,32 +179,32 @@
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 		/* Enable the DPLL */
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) == 0) {
-			REG_WRITE(dpll_reg, temp);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
 		}
 		/* Enable the pipe */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) == 0)
-			REG_WRITE(pipeconf_reg, temp | PIPEACONF_ENABLE);
+			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
 		/* Enable the plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp | DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+			REG_WRITE(map->base, REG_READ(map->base));
 		}
 
 		psb_intel_crtc_load_lut(crtc);
@@ -223,28 +221,28 @@
 		/* Disable the VGA plane that we never use */
 		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
 		/* Disable display plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp & ~DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
-			REG_READ(dspbase_reg);
+			REG_WRITE(map->base, REG_READ(map->base));
+			REG_READ(map->base);
 		}
 
 		/* Next, disable display pipes */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) != 0) {
-			REG_WRITE(pipeconf_reg, temp & ~PIPEACONF_ENABLE);
-			REG_READ(pipeconf_reg);
+			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
+			REG_READ(map->conf);
 		}
 		/* Wait for for the pipe disable to take effect. */
 		psb_intel_wait_for_vblank(dev);
 
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
-			REG_WRITE(dpll_reg, temp & ~DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 		}
 
 		/* Wait for the clocks to turn off. */
@@ -292,17 +290,7 @@
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int pipe = psb_intel_crtc->pipe;
-	int fp_reg = (pipe == 0) ? MRST_FPA0 : FPB0;
-	int dpll_reg = (pipe == 0) ? MRST_DPLL_A : DPLL_B;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
-	int htot_reg = (pipe == 0) ? HTOTAL_A : HTOTAL_B;
-	int hblank_reg = (pipe == 0) ? HBLANK_A : HBLANK_B;
-	int hsync_reg = (pipe == 0) ? HSYNC_A : HSYNC_B;
-	int vtot_reg = (pipe == 0) ? VTOTAL_A : VTOTAL_B;
-	int vblank_reg = (pipe == 0) ? VBLANK_A : VBLANK_B;
-	int vsync_reg = (pipe == 0) ? VSYNC_A : VSYNC_B;
-	int pipesrc_reg = (pipe == 0) ? PIPEASRC : PIPEBSRC;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk = 0;
 	struct oaktrail_clock_t clock;
 	u32 dpll = 0, fp = 0, dspcntr, pipeconf;
@@ -350,7 +338,7 @@
 	if (oaktrail_panel_fitter_pipe(dev) == pipe)
 		REG_WRITE(PFIT_CONTROL, 0);
 
-	REG_WRITE(pipesrc_reg,
+	REG_WRITE(map->src,
 		  ((mode->crtc_hdisplay - 1) << 16) |
 		  (mode->crtc_vdisplay - 1));
 
@@ -369,34 +357,34 @@
 		offsetY = (adjusted_mode->crtc_vdisplay -
 			   mode->crtc_vdisplay) / 2;
 
-		REG_WRITE(htot_reg, (mode->crtc_hdisplay - 1) |
+		REG_WRITE(map->htotal, (mode->crtc_hdisplay - 1) |
 			((adjusted_mode->crtc_htotal - 1) << 16));
-		REG_WRITE(vtot_reg, (mode->crtc_vdisplay - 1) |
+		REG_WRITE(map->vtotal, (mode->crtc_vdisplay - 1) |
 			((adjusted_mode->crtc_vtotal - 1) << 16));
-		REG_WRITE(hblank_reg,
+		REG_WRITE(map->hblank,
 			(adjusted_mode->crtc_hblank_start - offsetX - 1) |
 			((adjusted_mode->crtc_hblank_end - offsetX - 1) << 16));
-		REG_WRITE(hsync_reg,
+		REG_WRITE(map->hsync,
 			(adjusted_mode->crtc_hsync_start - offsetX - 1) |
 			((adjusted_mode->crtc_hsync_end - offsetX - 1) << 16));
-		REG_WRITE(vblank_reg,
+		REG_WRITE(map->vblank,
 			(adjusted_mode->crtc_vblank_start - offsetY - 1) |
 			((adjusted_mode->crtc_vblank_end - offsetY - 1) << 16));
-		REG_WRITE(vsync_reg,
+		REG_WRITE(map->vsync,
 			(adjusted_mode->crtc_vsync_start - offsetY - 1) |
 			((adjusted_mode->crtc_vsync_end - offsetY - 1) << 16));
 	} else {
-		REG_WRITE(htot_reg, (adjusted_mode->crtc_hdisplay - 1) |
+		REG_WRITE(map->htotal, (adjusted_mode->crtc_hdisplay - 1) |
 			((adjusted_mode->crtc_htotal - 1) << 16));
-		REG_WRITE(vtot_reg, (adjusted_mode->crtc_vdisplay - 1) |
+		REG_WRITE(map->vtotal, (adjusted_mode->crtc_vdisplay - 1) |
 			((adjusted_mode->crtc_vtotal - 1) << 16));
-		REG_WRITE(hblank_reg, (adjusted_mode->crtc_hblank_start - 1) |
+		REG_WRITE(map->hblank, (adjusted_mode->crtc_hblank_start - 1) |
 			((adjusted_mode->crtc_hblank_end - 1) << 16));
-		REG_WRITE(hsync_reg, (adjusted_mode->crtc_hsync_start - 1) |
+		REG_WRITE(map->hsync, (adjusted_mode->crtc_hsync_start - 1) |
 			((adjusted_mode->crtc_hsync_end - 1) << 16));
-		REG_WRITE(vblank_reg, (adjusted_mode->crtc_vblank_start - 1) |
+		REG_WRITE(map->vblank, (adjusted_mode->crtc_vblank_start - 1) |
 			((adjusted_mode->crtc_vblank_end - 1) << 16));
-		REG_WRITE(vsync_reg, (adjusted_mode->crtc_vsync_start - 1) |
+		REG_WRITE(map->vsync, (adjusted_mode->crtc_vsync_start - 1) |
 			((adjusted_mode->crtc_vsync_end - 1) << 16));
 	}
 
@@ -408,10 +396,10 @@
 	}
 
 	/* setup pipeconf */
-	pipeconf = REG_READ(pipeconf_reg);
+	pipeconf = REG_READ(map->conf);
 
 	/* Set up the display plane register */
-	dspcntr = REG_READ(dspcntr_reg);
+	dspcntr = REG_READ(map->cntr);
 	dspcntr |= DISPPLANE_GAMMA_ENABLE;
 
 	if (pipe == 0)
@@ -467,30 +455,30 @@
 	mrstPrintPll("chosen", &clock);
 
 	if (dpll & DPLL_VCO_ENABLE) {
-		REG_WRITE(fp_reg, fp);
-		REG_WRITE(dpll_reg, dpll & ~DPLL_VCO_ENABLE);
-		REG_READ(dpll_reg);
+		REG_WRITE(map->fp0, fp);
+		REG_WRITE(map->dpll, dpll & ~DPLL_VCO_ENABLE);
+		REG_READ(map->dpll);
 		/* Check the DPLLA lock bit PIPEACONF[29] */
 		udelay(150);
 	}
 
-	REG_WRITE(fp_reg, fp);
-	REG_WRITE(dpll_reg, dpll);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->fp0, fp);
+	REG_WRITE(map->dpll, dpll);
+	REG_READ(map->dpll);
 	/* Wait for the clocks to stabilize. */
 	udelay(150);
 
 	/* write it again -- the BIOS does, after all */
-	REG_WRITE(dpll_reg, dpll);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->dpll, dpll);
+	REG_READ(map->dpll);
 	/* Wait for the clocks to stabilize. */
 	udelay(150);
 
-	REG_WRITE(pipeconf_reg, pipeconf);
-	REG_READ(pipeconf_reg);
+	REG_WRITE(map->conf, pipeconf);
+	REG_READ(map->conf);
 	psb_intel_wait_for_vblank(dev);
 
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 	psb_intel_wait_for_vblank(dev);
 
 oaktrail_crtc_mode_set_exit:
@@ -509,15 +497,13 @@
 			    int x, int y, struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
 
-	int dspbase = (pipe == 0 ? DSPALINOFF : DSPBBASE);
-	int dspsurf = (pipe == 0 ? DSPASURF : DSPBSURF);
-	int dspstride = (pipe == 0) ? DSPASTRIDE : DSPBSTRIDE;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
 	u32 dspcntr;
 	int ret = 0;
 
@@ -533,9 +519,9 @@
 	start = psbfb->gtt->offset;
 	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
 
-	REG_WRITE(dspstride, crtc->fb->pitches[0]);
+	REG_WRITE(map->stride, crtc->fb->pitches[0]);
 
-	dspcntr = REG_READ(dspcntr_reg);
+	dspcntr = REG_READ(map->cntr);
 	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 
 	switch (crtc->fb->bits_per_pixel) {
@@ -557,12 +543,12 @@
 		ret = -EINVAL;
 		goto pipe_set_base_exit;
 	}
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
-	REG_WRITE(dspbase, offset);
-	REG_READ(dspbase);
-	REG_WRITE(dspsurf, start);
-	REG_READ(dspsurf);
+	REG_WRITE(map->base, offset);
+	REG_READ(map->base);
+	REG_WRITE(map->surf, start);
+	REG_READ(map->surf);
 
 pipe_set_base_exit:
 	gma_power_end(dev);
diff --git a/drivers/gpu/drm/gma500/oaktrail_device.c b/drivers/gpu/drm/gma500/oaktrail_device.c
index 0bb74cc..7a8ff8e 100644
--- a/drivers/gpu/drm/gma500/oaktrail_device.c
+++ b/drivers/gpu/drm/gma500/oaktrail_device.c
@@ -187,6 +187,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_save_area *regs = &dev_priv->regs;
+	struct psb_pipe *p = &regs->pipe[0];
 	int i;
 	u32 pp_stat;
 
@@ -201,24 +202,24 @@
 	regs->psb.saveCHICKENBIT = PSB_RVDC32(DSPCHICKENBIT);
 
 	/* Pipe & plane A info */
-	regs->psb.savePIPEACONF = PSB_RVDC32(PIPEACONF);
-	regs->psb.savePIPEASRC = PSB_RVDC32(PIPEASRC);
-	regs->psb.saveFPA0 = PSB_RVDC32(MRST_FPA0);
-	regs->psb.saveFPA1 = PSB_RVDC32(MRST_FPA1);
-	regs->psb.saveDPLL_A = PSB_RVDC32(MRST_DPLL_A);
-	regs->psb.saveHTOTAL_A = PSB_RVDC32(HTOTAL_A);
-	regs->psb.saveHBLANK_A = PSB_RVDC32(HBLANK_A);
-	regs->psb.saveHSYNC_A = PSB_RVDC32(HSYNC_A);
-	regs->psb.saveVTOTAL_A = PSB_RVDC32(VTOTAL_A);
-	regs->psb.saveVBLANK_A = PSB_RVDC32(VBLANK_A);
-	regs->psb.saveVSYNC_A = PSB_RVDC32(VSYNC_A);
+	p->conf = PSB_RVDC32(PIPEACONF);
+	p->src = PSB_RVDC32(PIPEASRC);
+	p->fp0 = PSB_RVDC32(MRST_FPA0);
+	p->fp1 = PSB_RVDC32(MRST_FPA1);
+	p->dpll = PSB_RVDC32(MRST_DPLL_A);
+	p->htotal = PSB_RVDC32(HTOTAL_A);
+	p->hblank = PSB_RVDC32(HBLANK_A);
+	p->hsync = PSB_RVDC32(HSYNC_A);
+	p->vtotal = PSB_RVDC32(VTOTAL_A);
+	p->vblank = PSB_RVDC32(VBLANK_A);
+	p->vsync = PSB_RVDC32(VSYNC_A);
 	regs->psb.saveBCLRPAT_A = PSB_RVDC32(BCLRPAT_A);
-	regs->psb.saveDSPACNTR = PSB_RVDC32(DSPACNTR);
-	regs->psb.saveDSPASTRIDE = PSB_RVDC32(DSPASTRIDE);
-	regs->psb.saveDSPAADDR = PSB_RVDC32(DSPABASE);
-	regs->psb.saveDSPASURF = PSB_RVDC32(DSPASURF);
-	regs->psb.saveDSPALINOFF = PSB_RVDC32(DSPALINOFF);
-	regs->psb.saveDSPATILEOFF = PSB_RVDC32(DSPATILEOFF);
+	p->cntr = PSB_RVDC32(DSPACNTR);
+	p->stride = PSB_RVDC32(DSPASTRIDE);
+	p->addr = PSB_RVDC32(DSPABASE);
+	p->surf = PSB_RVDC32(DSPASURF);
+	p->linoff = PSB_RVDC32(DSPALINOFF);
+	p->tileoff = PSB_RVDC32(DSPATILEOFF);
 
 	/* Save cursor regs */
 	regs->psb.saveDSPACURSOR_CTRL = PSB_RVDC32(CURACNTR);
@@ -227,7 +228,7 @@
 
 	/* Save palette (gamma) */
 	for (i = 0; i < 256; i++)
-		regs->psb.save_palette_a[i] = PSB_RVDC32(PALETTE_A + (i << 2));
+		p->palette[i] = PSB_RVDC32(PALETTE_A + (i << 2));
 
 	if (dev_priv->hdmi_priv)
 		oaktrail_hdmi_save(dev);
@@ -300,6 +301,7 @@
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_save_area *regs = &dev_priv->regs;
+	struct psb_pipe *p = &regs->pipe[0];
 	u32 pp_stat;
 	int i;
 
@@ -317,21 +319,21 @@
 	PSB_WVDC32(0x80000000, VGACNTRL);
 
 	/* set the plls */
-	PSB_WVDC32(regs->psb.saveFPA0, MRST_FPA0);
-	PSB_WVDC32(regs->psb.saveFPA1, MRST_FPA1);
+	PSB_WVDC32(p->fp0, MRST_FPA0);
+	PSB_WVDC32(p->fp1, MRST_FPA1);
 
 	/* Actually enable it */
-	PSB_WVDC32(regs->psb.saveDPLL_A, MRST_DPLL_A);
+	PSB_WVDC32(p->dpll, MRST_DPLL_A);
 	DRM_UDELAY(150);
 
 	/* Restore mode */
-	PSB_WVDC32(regs->psb.saveHTOTAL_A, HTOTAL_A);
-	PSB_WVDC32(regs->psb.saveHBLANK_A, HBLANK_A);
-	PSB_WVDC32(regs->psb.saveHSYNC_A, HSYNC_A);
-	PSB_WVDC32(regs->psb.saveVTOTAL_A, VTOTAL_A);
-	PSB_WVDC32(regs->psb.saveVBLANK_A, VBLANK_A);
-	PSB_WVDC32(regs->psb.saveVSYNC_A, VSYNC_A);
-	PSB_WVDC32(regs->psb.savePIPEASRC, PIPEASRC);
+	PSB_WVDC32(p->htotal, HTOTAL_A);
+	PSB_WVDC32(p->hblank, HBLANK_A);
+	PSB_WVDC32(p->hsync, HSYNC_A);
+	PSB_WVDC32(p->vtotal, VTOTAL_A);
+	PSB_WVDC32(p->vblank, VBLANK_A);
+	PSB_WVDC32(p->vsync, VSYNC_A);
+	PSB_WVDC32(p->src, PIPEASRC);
 	PSB_WVDC32(regs->psb.saveBCLRPAT_A, BCLRPAT_A);
 
 	/* Restore performance mode*/
@@ -339,16 +341,16 @@
 
 	/* Enable the pipe*/
 	if (dev_priv->iLVDS_enable)
-		PSB_WVDC32(regs->psb.savePIPEACONF, PIPEACONF);
+		PSB_WVDC32(p->conf, PIPEACONF);
 
 	/* Set up the plane*/
-	PSB_WVDC32(regs->psb.saveDSPALINOFF, DSPALINOFF);
-	PSB_WVDC32(regs->psb.saveDSPASTRIDE, DSPASTRIDE);
-	PSB_WVDC32(regs->psb.saveDSPATILEOFF, DSPATILEOFF);
+	PSB_WVDC32(p->linoff, DSPALINOFF);
+	PSB_WVDC32(p->stride, DSPASTRIDE);
+	PSB_WVDC32(p->tileoff, DSPATILEOFF);
 
 	/* Enable the plane */
-	PSB_WVDC32(regs->psb.saveDSPACNTR, DSPACNTR);
-	PSB_WVDC32(regs->psb.saveDSPASURF, DSPASURF);
+	PSB_WVDC32(p->cntr, DSPACNTR);
+	PSB_WVDC32(p->surf, DSPASURF);
 
 	/* Enable Cursor A */
 	PSB_WVDC32(regs->psb.saveDSPACURSOR_CTRL, CURACNTR);
@@ -357,7 +359,7 @@
 
 	/* Restore palette (gamma) */
 	for (i = 0; i < 256; i++)
-		PSB_WVDC32(regs->psb.save_palette_a[i], PALETTE_A + (i << 2));
+		PSB_WVDC32(p->palette[i], PALETTE_A + (i << 2));
 
 	if (dev_priv->hdmi_priv)
 		oaktrail_hdmi_restore(dev);
@@ -454,11 +456,65 @@
 	return 0;
 }
 
+/* Oaktrail */
+static const struct psb_offset oaktrail_regmap[2] = {
+	{
+		.fp0 = MRST_FPA0,
+		.fp1 = MRST_FPA1,
+		.cntr = DSPACNTR,
+		.conf = PIPEACONF,
+		.src = PIPEASRC,
+		.dpll = MRST_DPLL_A,
+		.htotal = HTOTAL_A,
+		.hblank = HBLANK_A,
+		.hsync = HSYNC_A,
+		.vtotal = VTOTAL_A,
+		.vblank = VBLANK_A,
+		.vsync = VSYNC_A,
+		.stride = DSPASTRIDE,
+		.size = DSPASIZE,
+		.pos = DSPAPOS,
+		.surf = DSPASURF,
+		.addr = MRST_DSPABASE,
+		.status = PIPEASTAT,
+		.linoff = DSPALINOFF,
+		.tileoff = DSPATILEOFF,
+		.palette = PALETTE_A,
+	},
+	{
+		.fp0 = FPB0,
+		.fp1 = FPB1,
+		.cntr = DSPBCNTR,
+		.conf = PIPEBCONF,
+		.src = PIPEBSRC,
+		.dpll = DPLL_B,
+		.htotal = HTOTAL_B,
+		.hblank = HBLANK_B,
+		.hsync = HSYNC_B,
+		.vtotal = VTOTAL_B,
+		.vblank = VBLANK_B,
+		.vsync = VSYNC_B,
+		.stride = DSPBSTRIDE,
+		.size = DSPBSIZE,
+		.pos = DSPBPOS,
+		.surf = DSPBSURF,
+		.addr = DSPBBASE,
+		.status = PIPEBSTAT,
+		.linoff = DSPBLINOFF,
+		.tileoff = DSPBTILEOFF,
+		.palette = PALETTE_B,
+	},
+};
 
 static int oaktrail_chip_setup(struct drm_device *dev)
 {
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	int ret;
+	
+	if (pci_enable_msi(dev->pdev))
+		dev_warn(dev->dev, "Enabling MSI failed!\n");
+
+	dev_priv->regmap = oaktrail_regmap;
 
 	ret = mid_chip_setup(dev);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 2595660..c10899c9 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -434,6 +434,7 @@
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct oaktrail_hdmi_dev *hdmi_dev = dev_priv->hdmi_priv;
 	struct psb_state *regs = &dev_priv->regs.psb;
+	struct psb_pipe *pipeb = &dev_priv->regs.pipe[1];
 	int i;
 
 	/* dpll */
@@ -444,14 +445,14 @@
 	hdmi_dev->saveDPLL_CLK_ENABLE = PSB_RVDC32(DPLL_CLK_ENABLE);
 
 	/* pipe B */
-	regs->savePIPEBCONF = PSB_RVDC32(PIPEBCONF);
-	regs->savePIPEBSRC  = PSB_RVDC32(PIPEBSRC);
-	regs->saveHTOTAL_B  = PSB_RVDC32(HTOTAL_B);
-	regs->saveHBLANK_B  = PSB_RVDC32(HBLANK_B);
-	regs->saveHSYNC_B   = PSB_RVDC32(HSYNC_B);
-	regs->saveVTOTAL_B  = PSB_RVDC32(VTOTAL_B);
-	regs->saveVBLANK_B  = PSB_RVDC32(VBLANK_B);
-	regs->saveVSYNC_B   = PSB_RVDC32(VSYNC_B);
+	pipeb->conf = PSB_RVDC32(PIPEBCONF);
+	pipeb->src = PSB_RVDC32(PIPEBSRC);
+	pipeb->htotal = PSB_RVDC32(HTOTAL_B);
+	pipeb->hblank = PSB_RVDC32(HBLANK_B);
+	pipeb->hsync = PSB_RVDC32(HSYNC_B);
+	pipeb->vtotal = PSB_RVDC32(VTOTAL_B);
+	pipeb->vblank = PSB_RVDC32(VBLANK_B);
+	pipeb->vsync = PSB_RVDC32(VSYNC_B);
 
 	hdmi_dev->savePCH_PIPEBCONF = PSB_RVDC32(PCH_PIPEBCONF);
 	hdmi_dev->savePCH_PIPEBSRC = PSB_RVDC32(PCH_PIPEBSRC);
@@ -463,12 +464,12 @@
 	hdmi_dev->savePCH_VSYNC_B  = PSB_RVDC32(PCH_VSYNC_B);
 
 	/* plane */
-	regs->saveDSPBCNTR = PSB_RVDC32(DSPBCNTR);
-	regs->saveDSPBSTRIDE = PSB_RVDC32(DSPBSTRIDE);
-	regs->saveDSPBADDR = PSB_RVDC32(DSPBBASE);
-	regs->saveDSPBSURF = PSB_RVDC32(DSPBSURF);
-	regs->saveDSPBLINOFF = PSB_RVDC32(DSPBLINOFF);
-	regs->saveDSPBTILEOFF = PSB_RVDC32(DSPBTILEOFF);
+	pipeb->cntr = PSB_RVDC32(DSPBCNTR);
+	pipeb->stride = PSB_RVDC32(DSPBSTRIDE);
+	pipeb->addr = PSB_RVDC32(DSPBBASE);
+	pipeb->surf = PSB_RVDC32(DSPBSURF);
+	pipeb->linoff = PSB_RVDC32(DSPBLINOFF);
+	pipeb->tileoff = PSB_RVDC32(DSPBTILEOFF);
 
 	/* cursor B */
 	regs->saveDSPBCURSOR_CTRL = PSB_RVDC32(CURBCNTR);
@@ -477,7 +478,7 @@
 
 	/* save palette */
 	for (i = 0; i < 256; i++)
-		regs->save_palette_b[i] = PSB_RVDC32(PALETTE_B + (i << 2));
+		pipeb->palette[i] = PSB_RVDC32(PALETTE_B + (i << 2));
 }
 
 /* restore HDMI register state */
@@ -486,6 +487,7 @@
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct oaktrail_hdmi_dev *hdmi_dev = dev_priv->hdmi_priv;
 	struct psb_state *regs = &dev_priv->regs.psb;
+	struct psb_pipe *pipeb = &dev_priv->regs.pipe[1];
 	int i;
 
 	/* dpll */
@@ -497,13 +499,13 @@
 	DRM_UDELAY(150);
 
 	/* pipe */
-	PSB_WVDC32(regs->savePIPEBSRC, PIPEBSRC);
-	PSB_WVDC32(regs->saveHTOTAL_B, HTOTAL_B);
-	PSB_WVDC32(regs->saveHBLANK_B, HBLANK_B);
-	PSB_WVDC32(regs->saveHSYNC_B,  HSYNC_B);
-	PSB_WVDC32(regs->saveVTOTAL_B, VTOTAL_B);
-	PSB_WVDC32(regs->saveVBLANK_B, VBLANK_B);
-	PSB_WVDC32(regs->saveVSYNC_B,  VSYNC_B);
+	PSB_WVDC32(pipeb->src, PIPEBSRC);
+	PSB_WVDC32(pipeb->htotal, HTOTAL_B);
+	PSB_WVDC32(pipeb->hblank, HBLANK_B);
+	PSB_WVDC32(pipeb->hsync,  HSYNC_B);
+	PSB_WVDC32(pipeb->vtotal, VTOTAL_B);
+	PSB_WVDC32(pipeb->vblank, VBLANK_B);
+	PSB_WVDC32(pipeb->vsync,  VSYNC_B);
 
 	PSB_WVDC32(hdmi_dev->savePCH_PIPEBSRC, PCH_PIPEBSRC);
 	PSB_WVDC32(hdmi_dev->savePCH_HTOTAL_B, PCH_HTOTAL_B);
@@ -513,15 +515,15 @@
 	PSB_WVDC32(hdmi_dev->savePCH_VBLANK_B, PCH_VBLANK_B);
 	PSB_WVDC32(hdmi_dev->savePCH_VSYNC_B,  PCH_VSYNC_B);
 
-	PSB_WVDC32(regs->savePIPEBCONF, PIPEBCONF);
+	PSB_WVDC32(pipeb->conf, PIPEBCONF);
 	PSB_WVDC32(hdmi_dev->savePCH_PIPEBCONF, PCH_PIPEBCONF);
 
 	/* plane */
-	PSB_WVDC32(regs->saveDSPBLINOFF, DSPBLINOFF);
-	PSB_WVDC32(regs->saveDSPBSTRIDE, DSPBSTRIDE);
-	PSB_WVDC32(regs->saveDSPBTILEOFF, DSPBTILEOFF);
-	PSB_WVDC32(regs->saveDSPBCNTR, DSPBCNTR);
-	PSB_WVDC32(regs->saveDSPBSURF, DSPBSURF);
+	PSB_WVDC32(pipeb->linoff, DSPBLINOFF);
+	PSB_WVDC32(pipeb->stride, DSPBSTRIDE);
+	PSB_WVDC32(pipeb->tileoff, DSPBTILEOFF);
+	PSB_WVDC32(pipeb->cntr, DSPBCNTR);
+	PSB_WVDC32(pipeb->surf, DSPBSURF);
 
 	/* cursor B */
 	PSB_WVDC32(regs->saveDSPBCURSOR_CTRL, CURBCNTR);
@@ -530,5 +532,5 @@
 
 	/* restore palette */
 	for (i = 0; i < 256; i++)
-		PSB_WVDC32(regs->save_palette_b[i], PALETTE_B + (i << 2));
+		PSB_WVDC32(pipeb->palette[i], PALETTE_B + (i << 2));
 }
diff --git a/drivers/gpu/drm/gma500/opregion.c b/drivers/gpu/drm/gma500/opregion.c
index 05661bf..aa9e89f 100644
--- a/drivers/gpu/drm/gma500/opregion.c
+++ b/drivers/gpu/drm/gma500/opregion.c
@@ -21,10 +21,8 @@
  * DEALINGS IN THE SOFTWARE.
  *
  */
-#ifdef CONFIG_ACPI
 #include <linux/acpi.h>
 #include <linux/acpi_io.h>
-#endif
 #include "psb_drv.h"
 #include "psb_intel_reg.h"
 
@@ -311,11 +309,7 @@
 		return -ENOTSUPP;
 	}
 	DRM_DEBUG("OpRegion detected at 0x%8x\n", opregion_phy);
-#ifdef CONFIG_ACPI
 	base = acpi_os_ioremap(opregion_phy, 8*1024);
-#else
-	base = ioremap(opregion_phy, 8*1024);
-#endif
 	if (!base)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/gma500/opregion.h b/drivers/gpu/drm/gma500/opregion.h
index a392ea8..72dc6b9 100644
--- a/drivers/gpu/drm/gma500/opregion.h
+++ b/drivers/gpu/drm/gma500/opregion.h
@@ -22,8 +22,28 @@
  *
  */
 
+#if defined(CONFIG_ACPI)
 extern void psb_intel_opregion_asle_intr(struct drm_device *dev);
-extern void psb_intel_opregion_enable_asle(struct drm_device *dev);
 extern void psb_intel_opregion_init(struct drm_device *dev);
 extern void psb_intel_opregion_fini(struct drm_device *dev);
 extern int psb_intel_opregion_setup(struct drm_device *dev);
+
+#else
+
+extern inline void psb_intel_opregion_asle_intr(struct drm_device *dev)
+{
+}
+
+extern inline void psb_intel_opregion_init(struct drm_device *dev)
+{
+}
+
+extern inline void psb_intel_opregion_fini(struct drm_device *dev)
+{
+}
+
+extern inline int psb_intel_opregion_setup(struct drm_device *dev)
+{
+	return 0;
+}
+#endif
diff --git a/drivers/gpu/drm/gma500/psb_device.c b/drivers/gpu/drm/gma500/psb_device.c
index e95cddb..651af67 100644
--- a/drivers/gpu/drm/gma500/psb_device.c
+++ b/drivers/gpu/drm/gma500/psb_device.c
@@ -289,8 +289,62 @@
 	}
 }
 
+/* Poulsbo */
+static const struct psb_offset psb_regmap[2] = {
+	{
+		.fp0 = FPA0,
+		.fp1 = FPA1,
+		.cntr = DSPACNTR,
+		.conf = PIPEACONF,
+		.src = PIPEASRC,
+		.dpll = DPLL_A,
+		.htotal = HTOTAL_A,
+		.hblank = HBLANK_A,
+		.hsync = HSYNC_A,
+		.vtotal = VTOTAL_A,
+		.vblank = VBLANK_A,
+		.vsync = VSYNC_A,
+		.stride = DSPASTRIDE,
+		.size = DSPASIZE,
+		.pos = DSPAPOS,
+		.base = DSPABASE,
+		.surf = DSPASURF,
+		.addr = DSPABASE,
+		.status = PIPEASTAT,
+		.linoff = DSPALINOFF,
+		.tileoff = DSPATILEOFF,
+		.palette = PALETTE_A,
+	},
+	{
+		.fp0 = FPB0,
+		.fp1 = FPB1,
+		.cntr = DSPBCNTR,
+		.conf = PIPEBCONF,
+		.src = PIPEBSRC,
+		.dpll = DPLL_B,
+		.htotal = HTOTAL_B,
+		.hblank = HBLANK_B,
+		.hsync = HSYNC_B,
+		.vtotal = VTOTAL_B,
+		.vblank = VBLANK_B,
+		.vsync = VSYNC_B,
+		.stride = DSPBSTRIDE,
+		.size = DSPBSIZE,
+		.pos = DSPBPOS,
+		.base = DSPBBASE,
+		.surf = DSPBSURF,
+		.addr = DSPBBASE,
+		.status = PIPEBSTAT,
+		.linoff = DSPBLINOFF,
+		.tileoff = DSPBTILEOFF,
+		.palette = PALETTE_B,
+	}
+};
+
 static int psb_chip_setup(struct drm_device *dev)
 {
+	struct drm_psb_private *dev_priv = dev->dev_private;
+	dev_priv->regmap = psb_regmap;
 	psb_get_core_freq(dev);
 	gma_intel_setup_gmbus(dev);
 	psb_intel_opregion_init(dev);
diff --git a/drivers/gpu/drm/gma500/psb_drv.c b/drivers/gpu/drm/gma500/psb_drv.c
index 0e85978..7473d3b 100644
--- a/drivers/gpu/drm/gma500/psb_drv.c
+++ b/drivers/gpu/drm/gma500/psb_drv.c
@@ -79,6 +79,14 @@
 	{ 0x8086, 0x0be5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
 	{ 0x8086, 0x0be6, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
 	{ 0x8086, 0x0be7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0be8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0be9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0bea, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0beb, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0bec, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0bed, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0bee, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
+	{ 0x8086, 0x0bef, PCI_ANY_ID, PCI_ANY_ID, 0, 0, (long) &cdv_chip_ops},
 #endif
 	{ 0, }
 };
@@ -172,24 +180,6 @@
 	dev_priv->gatt_free_offset = pg->mmu_gatt_start +
 	    (stolen_gtt << PAGE_SHIFT) * 1024;
 
-	if (1 || drm_debug) {
-		uint32_t core_id = PSB_RSGX32(PSB_CR_CORE_ID);
-		uint32_t core_rev = PSB_RSGX32(PSB_CR_CORE_REVISION);
-		DRM_INFO("SGX core id = 0x%08x\n", core_id);
-		DRM_INFO("SGX core rev major = 0x%02x, minor = 0x%02x\n",
-			 (core_rev & _PSB_CC_REVISION_MAJOR_MASK) >>
-			 _PSB_CC_REVISION_MAJOR_SHIFT,
-			 (core_rev & _PSB_CC_REVISION_MINOR_MASK) >>
-			 _PSB_CC_REVISION_MINOR_SHIFT);
-		DRM_INFO
-		    ("SGX core rev maintenance = 0x%02x, designer = 0x%02x\n",
-		     (core_rev & _PSB_CC_REVISION_MAINTENANCE_MASK) >>
-		     _PSB_CC_REVISION_MAINTENANCE_SHIFT,
-		     (core_rev & _PSB_CC_REVISION_DESIGNER_MASK) >>
-		     _PSB_CC_REVISION_DESIGNER_SHIFT);
-	}
-
-
 	spin_lock_init(&dev_priv->irqmask_lock);
 	spin_lock_init(&dev_priv->lock_2d);
 
@@ -290,11 +280,6 @@
 
 	pci_set_master(dev->pdev);
 
-	if (!IS_PSB(dev)) {
-		if (pci_enable_msi(dev->pdev))
-			dev_warn(dev->dev, "Enabling MSI failed!\n");
-	}
-
 	dev_priv->num_pipe = dev_priv->ops->pipes;
 
 	resource_start = pci_resource_start(dev->pdev, PSB_MMIO_RESOURCE);
@@ -371,8 +356,8 @@
 	PSB_WVDC32(0x00000000, PSB_INT_ENABLE_R);
 	PSB_WVDC32(0xFFFFFFFF, PSB_INT_MASK_R);
 	spin_unlock_irqrestore(&dev_priv->irqmask_lock, irqflags);
-	if (IS_PSB(dev) && drm_core_check_feature(dev, DRIVER_MODESET))
-		drm_irq_install(dev);
+
+	drm_irq_install(dev);
 
 	dev->vblank_disable_allowed = 1;
 
diff --git a/drivers/gpu/drm/gma500/psb_drv.h b/drivers/gpu/drm/gma500/psb_drv.h
index 270a27b..fd1bc8f 100644
--- a/drivers/gpu/drm/gma500/psb_drv.h
+++ b/drivers/gpu/drm/gma500/psb_drv.h
@@ -281,50 +281,72 @@
 };
 
 /*
+ *	Register offset maps
+ */
+
+struct psb_offset {
+	u32	fp0;
+	u32	fp1;
+	u32	cntr;
+	u32	conf;
+	u32	src;
+	u32	dpll;
+	u32	dpll_md;
+	u32	htotal;
+	u32	hblank;
+	u32	hsync;
+	u32	vtotal;
+	u32	vblank;
+	u32	vsync;
+	u32	stride;
+	u32	size;
+	u32	pos;
+	u32	surf;
+	u32	addr;
+	u32	base;
+	u32	status;
+	u32	linoff;
+	u32	tileoff;
+	u32	palette;
+};
+
+/*
  *	Register save state. This is used to hold the context when the
  *	device is powered off. In the case of Oaktrail this can (but does not
  *	yet) include screen blank. Operations occuring during the save
  *	update the register cache instead.
  */
+
+/*
+ *	Common status for pipes.
+ */
+struct psb_pipe {
+	u32	fp0;
+	u32	fp1;
+	u32	cntr;
+	u32	conf;
+	u32	src;
+	u32	dpll;
+	u32	dpll_md;
+	u32	htotal;
+	u32	hblank;
+	u32	hsync;
+	u32	vtotal;
+	u32	vblank;
+	u32	vsync;
+	u32	stride;
+	u32	size;
+	u32	pos;
+	u32	base;
+	u32	surf;
+	u32	addr;
+	u32	status;
+	u32	linoff;
+	u32	tileoff;
+	u32	palette[256];
+};
+
 struct psb_state {
-	uint32_t saveDSPACNTR;
-	uint32_t saveDSPBCNTR;
-	uint32_t savePIPEACONF;
-	uint32_t savePIPEBCONF;
-	uint32_t savePIPEASRC;
-	uint32_t savePIPEBSRC;
-	uint32_t saveFPA0;
-	uint32_t saveFPA1;
-	uint32_t saveDPLL_A;
-	uint32_t saveDPLL_A_MD;
-	uint32_t saveHTOTAL_A;
-	uint32_t saveHBLANK_A;
-	uint32_t saveHSYNC_A;
-	uint32_t saveVTOTAL_A;
-	uint32_t saveVBLANK_A;
-	uint32_t saveVSYNC_A;
-	uint32_t saveDSPASTRIDE;
-	uint32_t saveDSPASIZE;
-	uint32_t saveDSPAPOS;
-	uint32_t saveDSPABASE;
-	uint32_t saveDSPASURF;
-	uint32_t saveDSPASTATUS;
-	uint32_t saveFPB0;
-	uint32_t saveFPB1;
-	uint32_t saveDPLL_B;
-	uint32_t saveDPLL_B_MD;
-	uint32_t saveHTOTAL_B;
-	uint32_t saveHBLANK_B;
-	uint32_t saveHSYNC_B;
-	uint32_t saveVTOTAL_B;
-	uint32_t saveVBLANK_B;
-	uint32_t saveVSYNC_B;
-	uint32_t saveDSPBSTRIDE;
-	uint32_t saveDSPBSIZE;
-	uint32_t saveDSPBPOS;
-	uint32_t saveDSPBBASE;
-	uint32_t saveDSPBSURF;
-	uint32_t saveDSPBSTATUS;
 	uint32_t saveVCLK_DIVISOR_VGA0;
 	uint32_t saveVCLK_DIVISOR_VGA1;
 	uint32_t saveVCLK_POST_DIV;
@@ -339,14 +361,8 @@
 	uint32_t savePP_CONTROL;
 	uint32_t savePP_CYCLE;
 	uint32_t savePFIT_CONTROL;
-	uint32_t savePaletteA[256];
-	uint32_t savePaletteB[256];
 	uint32_t saveCLOCKGATING;
 	uint32_t saveDSPARB;
-	uint32_t saveDSPATILEOFF;
-	uint32_t saveDSPBTILEOFF;
-	uint32_t saveDSPAADDR;
-	uint32_t saveDSPBADDR;
 	uint32_t savePFIT_AUTO_RATIOS;
 	uint32_t savePFIT_PGM_RATIOS;
 	uint32_t savePP_ON_DELAYS;
@@ -354,8 +370,6 @@
 	uint32_t savePP_DIVISOR;
 	uint32_t saveBCLRPAT_A;
 	uint32_t saveBCLRPAT_B;
-	uint32_t saveDSPALINOFF;
-	uint32_t saveDSPBLINOFF;
 	uint32_t savePERF_MODE;
 	uint32_t saveDSPFW1;
 	uint32_t saveDSPFW2;
@@ -370,8 +384,6 @@
 	uint32_t saveDSPBCURSOR_BASE;
 	uint32_t saveDSPACURSOR_POS;
 	uint32_t saveDSPBCURSOR_POS;
-	uint32_t save_palette_a[256];
-	uint32_t save_palette_b[256];
 	uint32_t saveOV_OVADD;
 	uint32_t saveOV_OGAMC0;
 	uint32_t saveOV_OGAMC1;
@@ -394,64 +406,7 @@
 };
 
 struct medfield_state {
-	uint32_t saveDPLL_A;
-	uint32_t saveFPA0;
-	uint32_t savePIPEACONF;
-	uint32_t saveHTOTAL_A;
-	uint32_t saveHBLANK_A;
-	uint32_t saveHSYNC_A;
-	uint32_t saveVTOTAL_A;
-	uint32_t saveVBLANK_A;
-	uint32_t saveVSYNC_A;
-	uint32_t savePIPEASRC;
-	uint32_t saveDSPASTRIDE;
-	uint32_t saveDSPALINOFF;
-	uint32_t saveDSPATILEOFF;
-	uint32_t saveDSPASIZE;
-	uint32_t saveDSPAPOS;
-	uint32_t saveDSPASURF;
-	uint32_t saveDSPACNTR;
-	uint32_t saveDSPASTATUS;
-	uint32_t save_palette_a[256];
 	uint32_t saveMIPI;
-
-	uint32_t saveDPLL_B;
-	uint32_t saveFPB0;
-	uint32_t savePIPEBCONF;
-	uint32_t saveHTOTAL_B;
-	uint32_t saveHBLANK_B;
-	uint32_t saveHSYNC_B;
-	uint32_t saveVTOTAL_B;
-	uint32_t saveVBLANK_B;
-	uint32_t saveVSYNC_B;
-	uint32_t savePIPEBSRC;
-	uint32_t saveDSPBSTRIDE;
-	uint32_t saveDSPBLINOFF;
-	uint32_t saveDSPBTILEOFF;
-	uint32_t saveDSPBSIZE;
-	uint32_t saveDSPBPOS;
-	uint32_t saveDSPBSURF;
-	uint32_t saveDSPBCNTR;
-	uint32_t saveDSPBSTATUS;
-	uint32_t save_palette_b[256];
-
-	uint32_t savePIPECCONF;
-	uint32_t saveHTOTAL_C;
-	uint32_t saveHBLANK_C;
-	uint32_t saveHSYNC_C;
-	uint32_t saveVTOTAL_C;
-	uint32_t saveVBLANK_C;
-	uint32_t saveVSYNC_C;
-	uint32_t savePIPECSRC;
-	uint32_t saveDSPCSTRIDE;
-	uint32_t saveDSPCLINOFF;
-	uint32_t saveDSPCTILEOFF;
-	uint32_t saveDSPCSIZE;
-	uint32_t saveDSPCPOS;
-	uint32_t saveDSPCSURF;
-	uint32_t saveDSPCCNTR;
-	uint32_t saveDSPCSTATUS;
-	uint32_t save_palette_c[256];
 	uint32_t saveMIPI_C;
 
 	uint32_t savePFIT_CONTROL;
@@ -480,6 +435,7 @@
 };
 
 struct psb_save_area {
+	struct psb_pipe pipe[3];
 	uint32_t saveBSM;
 	uint32_t saveVBT;
 	union {
@@ -498,6 +454,7 @@
 struct drm_psb_private {
 	struct drm_device *dev;
 	const struct psb_ops *ops;
+	const struct psb_offset *regmap;
 	
 	struct child_device_config *child_dev;
 	int child_dev_num;
@@ -808,12 +765,6 @@
 extern u32 psb_get_vblank_counter(struct drm_device *dev, int crtc);
 
 /*
- * intel_opregion.c
- */
-extern int gma_intel_opregion_init(struct drm_device *dev);
-extern int gma_intel_opregion_exit(struct drm_device *dev);
-
-/*
  * framebuffer.c
  */
 extern int psbfb_probed(struct drm_device *dev);
diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c
index 2616558..f3a3160 100644
--- a/drivers/gpu/drm/gma500/psb_intel_display.c
+++ b/drivers/gpu/drm/gma500/psb_intel_display.c
@@ -337,15 +337,12 @@
 			    int x, int y, struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_i915_master_private *master_priv; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_framebuffer *psbfb = to_psb_fb(crtc->fb);
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
-	int dspbase = (pipe == 0 ? DSPABASE : DSPBBASE);
-	int dspsurf = (pipe == 0 ? DSPASURF : DSPBSURF);
-	int dspstride = (pipe == 0) ? DSPASTRIDE : DSPBSTRIDE;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
 	u32 dspcntr;
 	int ret = 0;
 
@@ -367,9 +364,9 @@
 
 	offset = y * crtc->fb->pitches[0] + x * (crtc->fb->bits_per_pixel / 8);
 
-	REG_WRITE(dspstride, crtc->fb->pitches[0]);
+	REG_WRITE(map->stride, crtc->fb->pitches[0]);
 
-	dspcntr = REG_READ(dspcntr_reg);
+	dspcntr = REG_READ(map->cntr);
 	dspcntr &= ~DISPPLANE_PIXFORMAT_MASK;
 
 	switch (crtc->fb->bits_per_pixel) {
@@ -392,18 +389,10 @@
 		psb_gtt_unpin(psbfb->gtt);
 		goto psb_intel_pipe_set_base_exit;
 	}
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
-
-	if (0 /* FIXMEAC - check what PSB needs */) {
-		REG_WRITE(dspbase, offset);
-		REG_READ(dspbase);
-		REG_WRITE(dspsurf, start);
-		REG_READ(dspsurf);
-	} else {
-		REG_WRITE(dspbase, start + offset);
-		REG_READ(dspbase);
-	}
+	REG_WRITE(map->base, start + offset);
+	REG_READ(map->base);
 
 psb_intel_pipe_cleaner:
 	/* If there was a previous display we can now unpin it */
@@ -424,14 +413,10 @@
 static void psb_intel_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_i915_master_private *master_priv; */
-	/* struct drm_i915_private *dev_priv = dev->dev_private; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	int pipe = psb_intel_crtc->pipe;
-	int dpll_reg = (pipe == 0) ? DPLL_A : DPLL_B;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int dspbase_reg = (pipe == 0) ? DSPABASE : DSPBBASE;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 temp;
 
 	/* XXX: When our outputs are all unaware of DPMS modes other than off
@@ -442,34 +427,34 @@
 	case DRM_MODE_DPMS_STANDBY:
 	case DRM_MODE_DPMS_SUSPEND:
 		/* Enable the DPLL */
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) == 0) {
-			REG_WRITE(dpll_reg, temp);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
-			REG_WRITE(dpll_reg, temp | DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp | DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 			/* Wait for the clocks to stabilize. */
 			udelay(150);
 		}
 
 		/* Enable the pipe */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) == 0)
-			REG_WRITE(pipeconf_reg, temp | PIPEACONF_ENABLE);
+			REG_WRITE(map->conf, temp | PIPEACONF_ENABLE);
 
 		/* Enable the plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) == 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp | DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
+			REG_WRITE(map->base, REG_READ(map->base));
 		}
 
 		psb_intel_crtc_load_lut(crtc);
@@ -487,29 +472,29 @@
 		REG_WRITE(VGACNTRL, VGA_DISP_DISABLE);
 
 		/* Disable display plane */
-		temp = REG_READ(dspcntr_reg);
+		temp = REG_READ(map->cntr);
 		if ((temp & DISPLAY_PLANE_ENABLE) != 0) {
-			REG_WRITE(dspcntr_reg,
+			REG_WRITE(map->cntr,
 				  temp & ~DISPLAY_PLANE_ENABLE);
 			/* Flush the plane changes */
-			REG_WRITE(dspbase_reg, REG_READ(dspbase_reg));
-			REG_READ(dspbase_reg);
+			REG_WRITE(map->base, REG_READ(map->base));
+			REG_READ(map->base);
 		}
 
 		/* Next, disable display pipes */
-		temp = REG_READ(pipeconf_reg);
+		temp = REG_READ(map->conf);
 		if ((temp & PIPEACONF_ENABLE) != 0) {
-			REG_WRITE(pipeconf_reg, temp & ~PIPEACONF_ENABLE);
-			REG_READ(pipeconf_reg);
+			REG_WRITE(map->conf, temp & ~PIPEACONF_ENABLE);
+			REG_READ(map->conf);
 		}
 
 		/* Wait for vblank for the disable to take effect. */
 		psb_intel_wait_for_vblank(dev);
 
-		temp = REG_READ(dpll_reg);
+		temp = REG_READ(map->dpll);
 		if ((temp & DPLL_VCO_ENABLE) != 0) {
-			REG_WRITE(dpll_reg, temp & ~DPLL_VCO_ENABLE);
-			REG_READ(dpll_reg);
+			REG_WRITE(map->dpll, temp & ~DPLL_VCO_ENABLE);
+			REG_READ(map->dpll);
 		}
 
 		/* Wait for the clocks to turn off. */
@@ -589,22 +574,11 @@
 			       struct drm_framebuffer *old_fb)
 {
 	struct drm_device *dev = crtc->dev;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct drm_crtc_helper_funcs *crtc_funcs = crtc->helper_private;
 	int pipe = psb_intel_crtc->pipe;
-	int fp_reg = (pipe == 0) ? FPA0 : FPB0;
-	int dpll_reg = (pipe == 0) ? DPLL_A : DPLL_B;
-	int dspcntr_reg = (pipe == 0) ? DSPACNTR : DSPBCNTR;
-	int pipeconf_reg = (pipe == 0) ? PIPEACONF : PIPEBCONF;
-	int htot_reg = (pipe == 0) ? HTOTAL_A : HTOTAL_B;
-	int hblank_reg = (pipe == 0) ? HBLANK_A : HBLANK_B;
-	int hsync_reg = (pipe == 0) ? HSYNC_A : HSYNC_B;
-	int vtot_reg = (pipe == 0) ? VTOTAL_A : VTOTAL_B;
-	int vblank_reg = (pipe == 0) ? VBLANK_A : VBLANK_B;
-	int vsync_reg = (pipe == 0) ? VSYNC_A : VSYNC_B;
-	int dspsize_reg = (pipe == 0) ? DSPASIZE : DSPBSIZE;
-	int dsppos_reg = (pipe == 0) ? DSPAPOS : DSPBPOS;
-	int pipesrc_reg = (pipe == 0) ? PIPEASRC : PIPEBSRC;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	int refclk;
 	struct psb_intel_clock_t clock;
 	u32 dpll = 0, fp = 0, dspcntr, pipeconf;
@@ -690,7 +664,7 @@
 	dpll |= PLL_REF_INPUT_DREFCLK;
 
 	/* setup pipeconf */
-	pipeconf = REG_READ(pipeconf_reg);
+	pipeconf = REG_READ(map->conf);
 
 	/* Set up the display plane register */
 	dspcntr = DISPPLANE_GAMMA_ENABLE;
@@ -712,9 +686,9 @@
 	drm_mode_debug_printmodeline(mode);
 
 	if (dpll & DPLL_VCO_ENABLE) {
-		REG_WRITE(fp_reg, fp);
-		REG_WRITE(dpll_reg, dpll & ~DPLL_VCO_ENABLE);
-		REG_READ(dpll_reg);
+		REG_WRITE(map->fp0, fp);
+		REG_WRITE(map->dpll, dpll & ~DPLL_VCO_ENABLE);
+		REG_READ(map->dpll);
 		udelay(150);
 	}
 
@@ -747,45 +721,45 @@
 		REG_READ(LVDS);
 	}
 
-	REG_WRITE(fp_reg, fp);
-	REG_WRITE(dpll_reg, dpll);
-	REG_READ(dpll_reg);
+	REG_WRITE(map->fp0, fp);
+	REG_WRITE(map->dpll, dpll);
+	REG_READ(map->dpll);
 	/* Wait for the clocks to stabilize. */
 	udelay(150);
 
 	/* write it again -- the BIOS does, after all */
-	REG_WRITE(dpll_reg, dpll);
+	REG_WRITE(map->dpll, dpll);
 
-	REG_READ(dpll_reg);
+	REG_READ(map->dpll);
 	/* Wait for the clocks to stabilize. */
 	udelay(150);
 
-	REG_WRITE(htot_reg, (adjusted_mode->crtc_hdisplay - 1) |
+	REG_WRITE(map->htotal, (adjusted_mode->crtc_hdisplay - 1) |
 		  ((adjusted_mode->crtc_htotal - 1) << 16));
-	REG_WRITE(hblank_reg, (adjusted_mode->crtc_hblank_start - 1) |
+	REG_WRITE(map->hblank, (adjusted_mode->crtc_hblank_start - 1) |
 		  ((adjusted_mode->crtc_hblank_end - 1) << 16));
-	REG_WRITE(hsync_reg, (adjusted_mode->crtc_hsync_start - 1) |
+	REG_WRITE(map->hsync, (adjusted_mode->crtc_hsync_start - 1) |
 		  ((adjusted_mode->crtc_hsync_end - 1) << 16));
-	REG_WRITE(vtot_reg, (adjusted_mode->crtc_vdisplay - 1) |
+	REG_WRITE(map->vtotal, (adjusted_mode->crtc_vdisplay - 1) |
 		  ((adjusted_mode->crtc_vtotal - 1) << 16));
-	REG_WRITE(vblank_reg, (adjusted_mode->crtc_vblank_start - 1) |
+	REG_WRITE(map->vblank, (adjusted_mode->crtc_vblank_start - 1) |
 		  ((adjusted_mode->crtc_vblank_end - 1) << 16));
-	REG_WRITE(vsync_reg, (adjusted_mode->crtc_vsync_start - 1) |
+	REG_WRITE(map->vsync, (adjusted_mode->crtc_vsync_start - 1) |
 		  ((adjusted_mode->crtc_vsync_end - 1) << 16));
 	/* pipesrc and dspsize control the size that is scaled from,
 	 * which should always be the user's requested size.
 	 */
-	REG_WRITE(dspsize_reg,
+	REG_WRITE(map->size,
 		  ((mode->vdisplay - 1) << 16) | (mode->hdisplay - 1));
-	REG_WRITE(dsppos_reg, 0);
-	REG_WRITE(pipesrc_reg,
+	REG_WRITE(map->pos, 0);
+	REG_WRITE(map->src,
 		  ((mode->hdisplay - 1) << 16) | (mode->vdisplay - 1));
-	REG_WRITE(pipeconf_reg, pipeconf);
-	REG_READ(pipeconf_reg);
+	REG_WRITE(map->conf, pipeconf);
+	REG_READ(map->conf);
 
 	psb_intel_wait_for_vblank(dev);
 
-	REG_WRITE(dspcntr_reg, dspcntr);
+	REG_WRITE(map->cntr, dspcntr);
 
 	/* Flush the plane changes */
 	crtc_funcs->mode_set_base(crtc, x, y, old_fb);
@@ -799,10 +773,10 @@
 void psb_intel_crtc_load_lut(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	struct drm_psb_private *dev_priv =
-				(struct drm_psb_private *)dev->dev_private;
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
-	int palreg = PALETTE_A;
+	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
+	int palreg = map->palette;
 	int i;
 
 	/* The clocks have to be on to load the palette. */
@@ -811,12 +785,7 @@
 
 	switch (psb_intel_crtc->pipe) {
 	case 0:
-		break;
 	case 1:
-		palreg = PALETTE_B;
-		break;
-	case 2:
-		palreg = PALETTE_C;
 		break;
 	default:
 		dev_err(dev->dev, "Illegal Pipe Number.\n");
@@ -836,7 +805,7 @@
 		gma_power_end(dev);
 	} else {
 		for (i = 0; i < 256; i++) {
-			dev_priv->regs.psb.save_palette_a[i] =
+			dev_priv->regs.pipe[0].palette[i] =
 				  ((psb_intel_crtc->lut_r[i] +
 				  psb_intel_crtc->lut_adj[i]) << 16) |
 				  ((psb_intel_crtc->lut_g[i] +
@@ -854,11 +823,10 @@
 static void psb_intel_crtc_save(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_psb_private *dev_priv =
-			(struct drm_psb_private *)dev->dev_private; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
 	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	int pipeA = (psb_intel_crtc->pipe == 0);
+	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
 	uint32_t paletteReg;
 	int i;
 
@@ -867,27 +835,27 @@
 		return;
 	}
 
-	crtc_state->saveDSPCNTR = REG_READ(pipeA ? DSPACNTR : DSPBCNTR);
-	crtc_state->savePIPECONF = REG_READ(pipeA ? PIPEACONF : PIPEBCONF);
-	crtc_state->savePIPESRC = REG_READ(pipeA ? PIPEASRC : PIPEBSRC);
-	crtc_state->saveFP0 = REG_READ(pipeA ? FPA0 : FPB0);
-	crtc_state->saveFP1 = REG_READ(pipeA ? FPA1 : FPB1);
-	crtc_state->saveDPLL = REG_READ(pipeA ? DPLL_A : DPLL_B);
-	crtc_state->saveHTOTAL = REG_READ(pipeA ? HTOTAL_A : HTOTAL_B);
-	crtc_state->saveHBLANK = REG_READ(pipeA ? HBLANK_A : HBLANK_B);
-	crtc_state->saveHSYNC = REG_READ(pipeA ? HSYNC_A : HSYNC_B);
-	crtc_state->saveVTOTAL = REG_READ(pipeA ? VTOTAL_A : VTOTAL_B);
-	crtc_state->saveVBLANK = REG_READ(pipeA ? VBLANK_A : VBLANK_B);
-	crtc_state->saveVSYNC = REG_READ(pipeA ? VSYNC_A : VSYNC_B);
-	crtc_state->saveDSPSTRIDE = REG_READ(pipeA ? DSPASTRIDE : DSPBSTRIDE);
+	crtc_state->saveDSPCNTR = REG_READ(map->cntr);
+	crtc_state->savePIPECONF = REG_READ(map->conf);
+	crtc_state->savePIPESRC = REG_READ(map->src);
+	crtc_state->saveFP0 = REG_READ(map->fp0);
+	crtc_state->saveFP1 = REG_READ(map->fp1);
+	crtc_state->saveDPLL = REG_READ(map->dpll);
+	crtc_state->saveHTOTAL = REG_READ(map->htotal);
+	crtc_state->saveHBLANK = REG_READ(map->hblank);
+	crtc_state->saveHSYNC = REG_READ(map->hsync);
+	crtc_state->saveVTOTAL = REG_READ(map->vtotal);
+	crtc_state->saveVBLANK = REG_READ(map->vblank);
+	crtc_state->saveVSYNC = REG_READ(map->vsync);
+	crtc_state->saveDSPSTRIDE = REG_READ(map->stride);
 
 	/*NOTE: DSPSIZE DSPPOS only for psb*/
-	crtc_state->saveDSPSIZE = REG_READ(pipeA ? DSPASIZE : DSPBSIZE);
-	crtc_state->saveDSPPOS = REG_READ(pipeA ? DSPAPOS : DSPBPOS);
+	crtc_state->saveDSPSIZE = REG_READ(map->size);
+	crtc_state->saveDSPPOS = REG_READ(map->pos);
 
-	crtc_state->saveDSPBASE = REG_READ(pipeA ? DSPABASE : DSPBBASE);
+	crtc_state->saveDSPBASE = REG_READ(map->base);
 
-	paletteReg = pipeA ? PALETTE_A : PALETTE_B;
+	paletteReg = map->palette;
 	for (i = 0; i < 256; ++i)
 		crtc_state->savePalette[i] = REG_READ(paletteReg + (i << 2));
 }
@@ -898,12 +866,10 @@
 static void psb_intel_crtc_restore(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
-	/* struct drm_psb_private * dev_priv =
-				(struct drm_psb_private *)dev->dev_private; */
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct psb_intel_crtc *psb_intel_crtc =  to_psb_intel_crtc(crtc);
 	struct psb_intel_crtc_state *crtc_state = psb_intel_crtc->crtc_state;
-	/* struct drm_crtc_helper_funcs * crtc_funcs = crtc->helper_private; */
-	int pipeA = (psb_intel_crtc->pipe == 0);
+	const struct psb_offset *map = &dev_priv->regmap[psb_intel_crtc->pipe];
 	uint32_t paletteReg;
 	int i;
 
@@ -913,45 +879,45 @@
 	}
 
 	if (crtc_state->saveDPLL & DPLL_VCO_ENABLE) {
-		REG_WRITE(pipeA ? DPLL_A : DPLL_B,
+		REG_WRITE(map->dpll,
 			crtc_state->saveDPLL & ~DPLL_VCO_ENABLE);
-		REG_READ(pipeA ? DPLL_A : DPLL_B);
+		REG_READ(map->dpll);
 		udelay(150);
 	}
 
-	REG_WRITE(pipeA ? FPA0 : FPB0, crtc_state->saveFP0);
-	REG_READ(pipeA ? FPA0 : FPB0);
+	REG_WRITE(map->fp0, crtc_state->saveFP0);
+	REG_READ(map->fp0);
 
-	REG_WRITE(pipeA ? FPA1 : FPB1, crtc_state->saveFP1);
-	REG_READ(pipeA ? FPA1 : FPB1);
+	REG_WRITE(map->fp1, crtc_state->saveFP1);
+	REG_READ(map->fp1);
 
-	REG_WRITE(pipeA ? DPLL_A : DPLL_B, crtc_state->saveDPLL);
-	REG_READ(pipeA ? DPLL_A : DPLL_B);
+	REG_WRITE(map->dpll, crtc_state->saveDPLL);
+	REG_READ(map->dpll);
 	udelay(150);
 
-	REG_WRITE(pipeA ? HTOTAL_A : HTOTAL_B, crtc_state->saveHTOTAL);
-	REG_WRITE(pipeA ? HBLANK_A : HBLANK_B, crtc_state->saveHBLANK);
-	REG_WRITE(pipeA ? HSYNC_A : HSYNC_B, crtc_state->saveHSYNC);
-	REG_WRITE(pipeA ? VTOTAL_A : VTOTAL_B, crtc_state->saveVTOTAL);
-	REG_WRITE(pipeA ? VBLANK_A : VBLANK_B, crtc_state->saveVBLANK);
-	REG_WRITE(pipeA ? VSYNC_A : VSYNC_B, crtc_state->saveVSYNC);
-	REG_WRITE(pipeA ? DSPASTRIDE : DSPBSTRIDE, crtc_state->saveDSPSTRIDE);
+	REG_WRITE(map->htotal, crtc_state->saveHTOTAL);
+	REG_WRITE(map->hblank, crtc_state->saveHBLANK);
+	REG_WRITE(map->hsync, crtc_state->saveHSYNC);
+	REG_WRITE(map->vtotal, crtc_state->saveVTOTAL);
+	REG_WRITE(map->vblank, crtc_state->saveVBLANK);
+	REG_WRITE(map->vsync, crtc_state->saveVSYNC);
+	REG_WRITE(map->stride, crtc_state->saveDSPSTRIDE);
 
-	REG_WRITE(pipeA ? DSPASIZE : DSPBSIZE, crtc_state->saveDSPSIZE);
-	REG_WRITE(pipeA ? DSPAPOS : DSPBPOS, crtc_state->saveDSPPOS);
+	REG_WRITE(map->size, crtc_state->saveDSPSIZE);
+	REG_WRITE(map->pos, crtc_state->saveDSPPOS);
 
-	REG_WRITE(pipeA ? PIPEASRC : PIPEBSRC, crtc_state->savePIPESRC);
-	REG_WRITE(pipeA ? DSPABASE : DSPBBASE, crtc_state->saveDSPBASE);
-	REG_WRITE(pipeA ? PIPEACONF : PIPEBCONF, crtc_state->savePIPECONF);
+	REG_WRITE(map->src, crtc_state->savePIPESRC);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
+	REG_WRITE(map->conf, crtc_state->savePIPECONF);
 
 	psb_intel_wait_for_vblank(dev);
 
-	REG_WRITE(pipeA ? DSPACNTR : DSPBCNTR, crtc_state->saveDSPCNTR);
-	REG_WRITE(pipeA ? DSPABASE : DSPBBASE, crtc_state->saveDSPBASE);
+	REG_WRITE(map->cntr, crtc_state->saveDSPCNTR);
+	REG_WRITE(map->base, crtc_state->saveDSPBASE);
 
 	psb_intel_wait_for_vblank(dev);
 
-	paletteReg = pipeA ? PALETTE_A : PALETTE_B;
+	paletteReg = map->palette;
 	for (i = 0; i < 256; ++i)
 		REG_WRITE(paletteReg + (i << 2), crtc_state->savePalette[i]);
 }
@@ -1115,34 +1081,30 @@
 				struct drm_crtc *crtc)
 {
 	struct psb_intel_crtc *psb_intel_crtc = to_psb_intel_crtc(crtc);
+	struct drm_psb_private *dev_priv = dev->dev_private;
 	int pipe = psb_intel_crtc->pipe;
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	u32 dpll;
 	u32 fp;
 	struct psb_intel_clock_t clock;
 	bool is_lvds;
-	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
 
 	if (gma_power_begin(dev, false)) {
-		dpll = REG_READ((pipe == 0) ? DPLL_A : DPLL_B);
+		dpll = REG_READ(map->dpll);
 		if ((dpll & DISPLAY_RATE_SELECT_FPA1) == 0)
-			fp = REG_READ((pipe == 0) ? FPA0 : FPB0);
+			fp = REG_READ(map->fp0);
 		else
-			fp = REG_READ((pipe == 0) ? FPA1 : FPB1);
+			fp = REG_READ(map->fp1);
 		is_lvds = (pipe == 1) && (REG_READ(LVDS) & LVDS_PORT_EN);
 		gma_power_end(dev);
 	} else {
-		dpll = (pipe == 0) ?
-			dev_priv->regs.psb.saveDPLL_A :
-			dev_priv->regs.psb.saveDPLL_B;
+		dpll = p->dpll;
 
 		if ((dpll & DISPLAY_RATE_SELECT_FPA1) == 0)
-			fp = (pipe == 0) ?
-				dev_priv->regs.psb.saveFPA0 :
-				dev_priv->regs.psb.saveFPB0;
+			fp = p->fp0;
 		else
-			fp = (pipe == 0) ?
-				dev_priv->regs.psb.saveFPA1 :
-				dev_priv->regs.psb.saveFPB1;
+		        fp = p->fp1;
 
 		is_lvds = (pipe == 1) && (dev_priv->regs.psb.saveLVDS &
 								LVDS_PORT_EN);
@@ -1202,26 +1164,20 @@
 	int vtot;
 	int vsync;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct psb_pipe *p = &dev_priv->regs.pipe[pipe];
+	const struct psb_offset *map = &dev_priv->regmap[pipe];
 
 	if (gma_power_begin(dev, false)) {
-		htot = REG_READ((pipe == 0) ? HTOTAL_A : HTOTAL_B);
-		hsync = REG_READ((pipe == 0) ? HSYNC_A : HSYNC_B);
-		vtot = REG_READ((pipe == 0) ? VTOTAL_A : VTOTAL_B);
-		vsync = REG_READ((pipe == 0) ? VSYNC_A : VSYNC_B);
+		htot = REG_READ(map->htotal);
+		hsync = REG_READ(map->hsync);
+		vtot = REG_READ(map->vtotal);
+		vsync = REG_READ(map->vsync);
 		gma_power_end(dev);
 	} else {
-		htot = (pipe == 0) ?
-			dev_priv->regs.psb.saveHTOTAL_A :
-			dev_priv->regs.psb.saveHTOTAL_B;
-		hsync = (pipe == 0) ?
-			dev_priv->regs.psb.saveHSYNC_A :
-			dev_priv->regs.psb.saveHSYNC_B;
-		vtot = (pipe == 0) ?
-			dev_priv->regs.psb.saveVTOTAL_A :
-			dev_priv->regs.psb.saveVTOTAL_B;
-		vsync = (pipe == 0) ?
-			dev_priv->regs.psb.saveVSYNC_A :
-			dev_priv->regs.psb.saveVSYNC_B;
+		htot = p->htotal;
+		hsync = p->hsync;
+		vtot = p->vtotal;
+		vsync = p->vsync;
 	}
 
 	mode = kzalloc(sizeof(*mode), GFP_KERNEL);
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 958b4e2..d39b15b 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -2038,8 +2038,7 @@
 	struct drm_device *dev = connector->base.base.dev;
 
 	intel_attach_force_audio_property(&connector->base.base);
-	if (INTEL_INFO(dev)->gen >= 4 && IS_MOBILE(dev))
-		intel_attach_broadcast_rgb_property(&connector->base.base);
+	intel_attach_broadcast_rgb_property(&connector->base.base);
 	*/
 }
 
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index ecc29bc..7e7ac3d 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -3550,7 +3550,6 @@
 	evergreen_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index 222acd2..30f0480 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -637,7 +637,6 @@
 	if (rdev->r600_blit.shader_obj)
 		goto done;
 
-	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
 	if (rdev->family < CHIP_CAYMAN)
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 70089d3..4e7dd2b 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -1057,7 +1057,7 @@
 	uint32_t header, h_idx, reg, wait_reg_mem_info;
 	volatile uint32_t *ib;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 
 	/* parse the WAIT_REG_MEM */
 	r = evergreen_cs_packet_parse(p, &wait_reg_mem, p->idx);
@@ -1215,7 +1215,7 @@
 		if (!(evergreen_reg_safe_bm[i] & m))
 			return 0;
 	}
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	switch (reg) {
 	/* force following reg to 0 in an attempt to disable out buffer
 	 * which will need us to better understand how it works to perform
@@ -1896,7 +1896,7 @@
 	u32 idx_value;
 
 	track = (struct evergreen_cs_track *)p->track;
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	idx = pkt->idx + 1;
 	idx_value = radeon_get_ib_value(p, idx);
 
@@ -2610,8 +2610,8 @@
 		}
 	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
 #if 0
-	for (r = 0; r < p->ib->length_dw; r++) {
-		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib->ptr[r]);
+	for (r = 0; r < p->ib.length_dw; r++) {
+		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib.ptr[r]);
 		mdelay(1);
 	}
 #endif
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 9cd2657..107b217 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1744,7 +1744,6 @@
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ad6ceb7..0874a6d 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -139,9 +139,9 @@
 		}
 
 		tmp |= tile_flags;
-		p->ib->ptr[idx] = (value & 0x3fc00000) | tmp;
+		p->ib.ptr[idx] = (value & 0x3fc00000) | tmp;
 	} else
-		p->ib->ptr[idx] = (value & 0xffc00000) | tmp;
+		p->ib.ptr[idx] = (value & 0xffc00000) | tmp;
 	return 0;
 }
 
@@ -156,7 +156,7 @@
 	volatile uint32_t *ib;
 	u32 idx_value;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	track = (struct r100_cs_track *)p->track;
 	c = radeon_get_ib_value(p, idx++) & 0x1F;
 	if (c > 16) {
@@ -1275,7 +1275,7 @@
 	unsigned i;
 	unsigned idx;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	idx = pkt->idx;
 	for (i = 0; i <= (pkt->count + 1); i++, idx++) {
 		DRM_INFO("ib[%d]=0x%08X\n", idx, ib[idx]);
@@ -1354,7 +1354,7 @@
 	uint32_t header, h_idx, reg;
 	volatile uint32_t *ib;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 
 	/* parse the wait until */
 	r = r100_cs_packet_parse(p, &waitreloc, p->idx);
@@ -1533,7 +1533,7 @@
 	u32 tile_flags = 0;
 	u32 idx_value;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	track = (struct r100_cs_track *)p->track;
 
 	idx_value = radeon_get_ib_value(p, idx);
@@ -1889,7 +1889,7 @@
 	volatile uint32_t *ib;
 	int r;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	idx = pkt->idx + 1;
 	track = (struct r100_cs_track *)p->track;
 	switch (pkt->opcode) {
@@ -3684,7 +3684,7 @@
 
 int r100_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	struct radeon_ib *ib;
+	struct radeon_ib ib;
 	uint32_t scratch;
 	uint32_t tmp = 0;
 	unsigned i;
@@ -3700,22 +3700,22 @@
 	if (r) {
 		return r;
 	}
-	ib->ptr[0] = PACKET0(scratch, 0);
-	ib->ptr[1] = 0xDEADBEEF;
-	ib->ptr[2] = PACKET2(0);
-	ib->ptr[3] = PACKET2(0);
-	ib->ptr[4] = PACKET2(0);
-	ib->ptr[5] = PACKET2(0);
-	ib->ptr[6] = PACKET2(0);
-	ib->ptr[7] = PACKET2(0);
-	ib->length_dw = 8;
-	r = radeon_ib_schedule(rdev, ib);
+	ib.ptr[0] = PACKET0(scratch, 0);
+	ib.ptr[1] = 0xDEADBEEF;
+	ib.ptr[2] = PACKET2(0);
+	ib.ptr[3] = PACKET2(0);
+	ib.ptr[4] = PACKET2(0);
+	ib.ptr[5] = PACKET2(0);
+	ib.ptr[6] = PACKET2(0);
+	ib.ptr[7] = PACKET2(0);
+	ib.length_dw = 8;
+	r = radeon_ib_schedule(rdev, &ib);
 	if (r) {
 		radeon_scratch_free(rdev, scratch);
 		radeon_ib_free(rdev, &ib);
 		return r;
 	}
-	r = radeon_fence_wait(ib->fence, false);
+	r = radeon_fence_wait(ib.fence, false);
 	if (r) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index a59cc47..a26144d 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -154,7 +154,7 @@
 	u32 tile_flags = 0;
 	u32 idx_value;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	track = (struct r100_cs_track *)p->track;
 	idx_value = radeon_get_ib_value(p, idx);
 	switch (reg) {
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 6419a59..97722a3 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -604,7 +604,7 @@
 	int r;
 	u32 idx_value;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	track = (struct r100_cs_track *)p->track;
 	idx_value = radeon_get_ib_value(p, idx);
 
@@ -1146,7 +1146,7 @@
 	unsigned idx;
 	int r;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	idx = pkt->idx + 1;
 	track = (struct r100_cs_track *)p->track;
 	switch(pkt->opcode) {
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index d02f13f..4c0d8c9 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2363,20 +2363,15 @@
 		   unsigned num_gpu_pages,
 		   struct radeon_fence *fence)
 {
+	struct radeon_sa_bo *vb = NULL;
 	int r;
 
-	mutex_lock(&rdev->r600_blit.mutex);
-	rdev->r600_blit.vb_ib = NULL;
-	r = r600_blit_prepare_copy(rdev, num_gpu_pages);
+	r = r600_blit_prepare_copy(rdev, num_gpu_pages, &vb);
 	if (r) {
-		if (rdev->r600_blit.vb_ib)
-			radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-		mutex_unlock(&rdev->r600_blit.mutex);
 		return r;
 	}
-	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages);
-	r600_blit_done_copy(rdev, fence);
-	mutex_unlock(&rdev->r600_blit.mutex);
+	r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages, vb);
+	r600_blit_done_copy(rdev, fence, vb);
 	return 0;
 }
 
@@ -2658,7 +2653,6 @@
 	r600_vram_scratch_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
@@ -2687,7 +2681,7 @@
 
 int r600_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	struct radeon_ib *ib;
+	struct radeon_ib ib;
 	uint32_t scratch;
 	uint32_t tmp = 0;
 	unsigned i;
@@ -2705,18 +2699,18 @@
 		DRM_ERROR("radeon: failed to get ib (%d).\n", r);
 		return r;
 	}
-	ib->ptr[0] = PACKET3(PACKET3_SET_CONFIG_REG, 1);
-	ib->ptr[1] = ((scratch - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
-	ib->ptr[2] = 0xDEADBEEF;
-	ib->length_dw = 3;
-	r = radeon_ib_schedule(rdev, ib);
+	ib.ptr[0] = PACKET3(PACKET3_SET_CONFIG_REG, 1);
+	ib.ptr[1] = ((scratch - PACKET3_SET_CONFIG_REG_OFFSET) >> 2);
+	ib.ptr[2] = 0xDEADBEEF;
+	ib.length_dw = 3;
+	r = radeon_ib_schedule(rdev, &ib);
 	if (r) {
 		radeon_scratch_free(rdev, scratch);
 		radeon_ib_free(rdev, &ib);
 		DRM_ERROR("radeon: failed to schedule ib (%d).\n", r);
 		return r;
 	}
-	r = radeon_fence_wait(ib->fence, false);
+	r = radeon_fence_wait(ib.fence, false);
 	if (r) {
 		DRM_ERROR("radeon: fence wait failed (%d).\n", r);
 		return r;
@@ -2728,7 +2722,7 @@
 		DRM_UDELAY(1);
 	}
 	if (i < rdev->usec_timeout) {
-		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib->fence->ring, i);
+		DRM_INFO("ib test on ring %d succeeded in %u usecs\n", ib.fence->ring, i);
 	} else {
 		DRM_ERROR("radeon: ib test failed (scratch(0x%04X)=0x%08X)\n",
 			  scratch, tmp);
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index db38f58..ef20822 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -513,7 +513,6 @@
 	rdev->r600_blit.primitives.set_default_state = set_default_state;
 
 	rdev->r600_blit.ring_size_common = 40; /* shaders + def state */
-	rdev->r600_blit.ring_size_common += 16; /* fence emit for VB IB */
 	rdev->r600_blit.ring_size_common += 5; /* done copy */
 	rdev->r600_blit.ring_size_common += 16; /* fence emit for done copy */
 
@@ -528,7 +527,6 @@
 	if (rdev->r600_blit.shader_obj)
 		goto done;
 
-	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
 	if (rdev->family >= CHIP_RV770)
@@ -621,27 +619,6 @@
 	radeon_bo_unref(&rdev->r600_blit.shader_obj);
 }
 
-static int r600_vb_ib_get(struct radeon_device *rdev, unsigned size)
-{
-	int r;
-	r = radeon_ib_get(rdev, RADEON_RING_TYPE_GFX_INDEX,
-			  &rdev->r600_blit.vb_ib, size);
-	if (r) {
-		DRM_ERROR("failed to get IB for vertex buffer\n");
-		return r;
-	}
-
-	rdev->r600_blit.vb_total = size;
-	rdev->r600_blit.vb_used = 0;
-	return 0;
-}
-
-static void r600_vb_ib_put(struct radeon_device *rdev)
-{
-	radeon_fence_emit(rdev, rdev->r600_blit.vb_ib->fence);
-	radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
-}
-
 static unsigned r600_blit_create_rect(unsigned num_gpu_pages,
 				      int *width, int *height, int max_dim)
 {
@@ -688,7 +665,8 @@
 }
 
 
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages)
+int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
+			   struct radeon_sa_bo **vb)
 {
 	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
@@ -705,46 +683,54 @@
 	}
 
 	/* 48 bytes for vertex per loop */
-	r = r600_vb_ib_get(rdev, (num_loops*48)+256);
-	if (r)
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, vb,
+			     (num_loops*48)+256, 256, true);
+	if (r) {
 		return r;
+	}
 
 	/* calculate number of loops correctly */
 	ring_size = num_loops * dwords_per_loop;
 	ring_size += rdev->r600_blit.ring_size_common;
 	r = radeon_ring_lock(rdev, ring, ring_size);
-	if (r)
+	if (r) {
+		radeon_sa_bo_free(rdev, vb, NULL);
 		return r;
+	}
 
 	rdev->r600_blit.primitives.set_default_state(rdev);
 	rdev->r600_blit.primitives.set_shaders(rdev);
 	return 0;
 }
 
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence)
+void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence,
+			 struct radeon_sa_bo *vb)
 {
+	struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 	int r;
 
-	if (rdev->r600_blit.vb_ib)
-		r600_vb_ib_put(rdev);
+	r = radeon_fence_emit(rdev, fence);
+	if (r) {
+		radeon_ring_unlock_undo(rdev, ring);
+		return;
+	}
 
-	if (fence)
-		r = radeon_fence_emit(rdev, fence);
-
-	radeon_ring_unlock_commit(rdev, &rdev->ring[RADEON_RING_TYPE_GFX_INDEX]);
+	radeon_ring_unlock_commit(rdev, ring);
+	radeon_sa_bo_free(rdev, &vb, fence);
 }
 
 void r600_kms_blit_copy(struct radeon_device *rdev,
 			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages)
+			unsigned num_gpu_pages,
+			struct radeon_sa_bo *vb)
 {
 	u64 vb_gpu_addr;
-	u32 *vb;
+	u32 *vb_cpu_addr;
 
-	DRM_DEBUG("emitting copy %16llx %16llx %d %d\n",
-		  src_gpu_addr, dst_gpu_addr,
-		  num_gpu_pages, rdev->r600_blit.vb_used);
-	vb = (u32 *)(rdev->r600_blit.vb_ib->ptr + rdev->r600_blit.vb_used);
+	DRM_DEBUG("emitting copy %16llx %16llx %d\n",
+		  src_gpu_addr, dst_gpu_addr, num_gpu_pages);
+	vb_cpu_addr = (u32 *)radeon_sa_bo_cpu_addr(vb);
+	vb_gpu_addr = radeon_sa_bo_gpu_addr(vb);
 
 	while (num_gpu_pages) {
 		int w, h;
@@ -756,39 +742,34 @@
 		size_in_bytes = pages_per_loop * RADEON_GPU_PAGE_SIZE;
 		DRM_DEBUG("rectangle w=%d h=%d\n", w, h);
 
-		if ((rdev->r600_blit.vb_used + 48) > rdev->r600_blit.vb_total) {
-			WARN_ON(1);
-		}
+		vb_cpu_addr[0] = 0;
+		vb_cpu_addr[1] = 0;
+		vb_cpu_addr[2] = 0;
+		vb_cpu_addr[3] = 0;
 
-		vb[0] = 0;
-		vb[1] = 0;
-		vb[2] = 0;
-		vb[3] = 0;
+		vb_cpu_addr[4] = 0;
+		vb_cpu_addr[5] = i2f(h);
+		vb_cpu_addr[6] = 0;
+		vb_cpu_addr[7] = i2f(h);
 
-		vb[4] = 0;
-		vb[5] = i2f(h);
-		vb[6] = 0;
-		vb[7] = i2f(h);
-
-		vb[8] = i2f(w);
-		vb[9] = i2f(h);
-		vb[10] = i2f(w);
-		vb[11] = i2f(h);
+		vb_cpu_addr[8] = i2f(w);
+		vb_cpu_addr[9] = i2f(h);
+		vb_cpu_addr[10] = i2f(w);
+		vb_cpu_addr[11] = i2f(h);
 
 		rdev->r600_blit.primitives.set_tex_resource(rdev, FMT_8_8_8_8,
 							    w, h, w, src_gpu_addr, size_in_bytes);
 		rdev->r600_blit.primitives.set_render_target(rdev, COLOR_8_8_8_8,
 							     w, h, dst_gpu_addr);
 		rdev->r600_blit.primitives.set_scissors(rdev, 0, 0, w, h);
-		vb_gpu_addr = rdev->r600_blit.vb_ib->gpu_addr + rdev->r600_blit.vb_used;
 		rdev->r600_blit.primitives.set_vtx_resource(rdev, vb_gpu_addr);
 		rdev->r600_blit.primitives.draw_auto(rdev);
 		rdev->r600_blit.primitives.cp_set_surface_sync(rdev,
 				    PACKET3_CB_ACTION_ENA | PACKET3_CB0_DEST_BASE_ENA,
 				    size_in_bytes, dst_gpu_addr);
 
-		vb += 12;
-		rdev->r600_blit.vb_used += 4*12;
+		vb_cpu_addr += 12;
+		vb_gpu_addr += 4*12;
 		src_gpu_addr += size_in_bytes;
 		dst_gpu_addr += size_in_bytes;
 		num_gpu_pages -= pages_per_loop;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index b8e12af..0133f5f 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -345,7 +345,7 @@
 	u32 height, height_align, pitch, pitch_align, depth_align;
 	u64 base_offset, base_align;
 	struct array_mode_checker array_check;
-	volatile u32 *ib = p->ib->ptr;
+	volatile u32 *ib = p->ib.ptr;
 	unsigned array_mode;
 	u32 format;
 
@@ -471,7 +471,7 @@
 	u64 base_offset, base_align;
 	struct array_mode_checker array_check;
 	int array_mode;
-	volatile u32 *ib = p->ib->ptr;
+	volatile u32 *ib = p->ib.ptr;
 
 
 	if (track->db_bo == NULL) {
@@ -961,7 +961,7 @@
 	uint32_t header, h_idx, reg, wait_reg_mem_info;
 	volatile uint32_t *ib;
 
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 
 	/* parse the WAIT_REG_MEM */
 	r = r600_cs_packet_parse(p, &wait_reg_mem, p->idx);
@@ -1110,7 +1110,7 @@
 	m = 1 << ((reg >> 2) & 31);
 	if (!(r600_reg_safe_bm[i] & m))
 		return 0;
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	switch (reg) {
 	/* force following reg to 0 in an attempt to disable out buffer
 	 * which will need us to better understand how it works to perform
@@ -1714,7 +1714,7 @@
 	u32 idx_value;
 
 	track = (struct r600_cs_track *)p->track;
-	ib = p->ib->ptr;
+	ib = p->ib.ptr;
 	idx = pkt->idx + 1;
 	idx_value = radeon_get_ib_value(p, idx);
 
@@ -2249,8 +2249,8 @@
 		}
 	} while (p->idx < p->chunks[p->chunk_ib_idx].length_dw);
 #if 0
-	for (r = 0; r < p->ib->length_dw; r++) {
-		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib->ptr[r]);
+	for (r = 0; r < p->ib.length_dw; r++) {
+		printk(KERN_INFO "%05d  0x%08X\n", r, p->ib.ptr[r]);
 		mdelay(1);
 	}
 #endif
@@ -2298,7 +2298,6 @@
 {
 	struct radeon_cs_parser parser;
 	struct radeon_cs_chunk *ib_chunk;
-	struct radeon_ib fake_ib;
 	struct r600_cs_track *track;
 	int r;
 
@@ -2314,9 +2313,8 @@
 	parser.dev = &dev->pdev->dev;
 	parser.rdev = NULL;
 	parser.family = family;
-	parser.ib = &fake_ib;
 	parser.track = track;
-	fake_ib.ptr = ib;
+	parser.ib.ptr = ib;
 	r = radeon_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
@@ -2333,8 +2331,8 @@
 	 * input memory (cached) and write to the IB (which can be
 	 * uncached). */
 	ib_chunk = &parser.chunks[parser.chunk_ib_idx];
-	parser.ib->length_dw = ib_chunk->length_dw;
-	*l = parser.ib->length_dw;
+	parser.ib.length_dw = ib_chunk->length_dw;
+	*l = parser.ib.length_dw;
 	r = r600_cs_parse(&parser);
 	if (r) {
 		DRM_ERROR("Invalid command stream !\n");
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 82ffa6a..60233d7 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -100,28 +100,32 @@
  * Copy from radeon_drv.h so we don't have to include both and have conflicting
  * symbol;
  */
-#define RADEON_MAX_USEC_TIMEOUT		100000	/* 100 ms */
-#define RADEON_FENCE_JIFFIES_TIMEOUT	(HZ / 2)
+#define RADEON_MAX_USEC_TIMEOUT			100000	/* 100 ms */
+#define RADEON_FENCE_JIFFIES_TIMEOUT		(HZ / 2)
 /* RADEON_IB_POOL_SIZE must be a power of 2 */
-#define RADEON_IB_POOL_SIZE		16
-#define RADEON_DEBUGFS_MAX_COMPONENTS	32
-#define RADEONFB_CONN_LIMIT		4
-#define RADEON_BIOS_NUM_SCRATCH		8
+#define RADEON_IB_POOL_SIZE			16
+#define RADEON_DEBUGFS_MAX_COMPONENTS		32
+#define RADEONFB_CONN_LIMIT			4
+#define RADEON_BIOS_NUM_SCRATCH			8
 
 /* max number of rings */
-#define RADEON_NUM_RINGS 3
+#define RADEON_NUM_RINGS			3
+
+/* fence seq are set to this number when signaled */
+#define RADEON_FENCE_SIGNALED_SEQ		0LL
+#define RADEON_FENCE_NOTEMITED_SEQ		(~0LL)
 
 /* internal ring indices */
 /* r1xx+ has gfx CP ring */
-#define RADEON_RING_TYPE_GFX_INDEX  0
+#define RADEON_RING_TYPE_GFX_INDEX		0
 
 /* cayman has 2 compute CP rings */
-#define CAYMAN_RING_TYPE_CP1_INDEX 1
-#define CAYMAN_RING_TYPE_CP2_INDEX 2
+#define CAYMAN_RING_TYPE_CP1_INDEX		1
+#define CAYMAN_RING_TYPE_CP2_INDEX		2
 
 /* hardcode those limit for now */
-#define RADEON_VA_RESERVED_SIZE		(8 << 20)
-#define RADEON_IB_VM_MAX_SIZE		(64 << 10)
+#define RADEON_VA_RESERVED_SIZE			(8 << 20)
+#define RADEON_IB_VM_MAX_SIZE			(64 << 10)
 
 /*
  * Errata workarounds.
@@ -254,26 +258,20 @@
 	uint32_t			scratch_reg;
 	uint64_t			gpu_addr;
 	volatile uint32_t		*cpu_addr;
-	atomic_t			seq;
-	uint32_t			last_seq;
+	/* seq is protected by ring emission lock */
+	uint64_t			seq;
+	atomic64_t			last_seq;
 	unsigned long			last_activity;
-	wait_queue_head_t		queue;
-	struct list_head		emitted;
-	struct list_head		signaled;
 	bool				initialized;
 };
 
 struct radeon_fence {
 	struct radeon_device		*rdev;
 	struct kref			kref;
-	struct list_head		list;
 	/* protected by radeon_fence.lock */
-	uint32_t			seq;
-	bool				emitted;
-	bool				signaled;
+	uint64_t			seq;
 	/* RB, DMA, etc. */
-	int				ring;
-	struct radeon_semaphore		*semaphore;
+	unsigned			ring;
 };
 
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring);
@@ -284,11 +282,14 @@
 void radeon_fence_process(struct radeon_device *rdev, int ring);
 bool radeon_fence_signaled(struct radeon_fence *fence);
 int radeon_fence_wait(struct radeon_fence *fence, bool interruptible);
-int radeon_fence_wait_next(struct radeon_device *rdev, int ring);
-int radeon_fence_wait_empty(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring);
+int radeon_fence_wait_any(struct radeon_device *rdev,
+			  struct radeon_fence **fences,
+			  bool intr);
 struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence);
 void radeon_fence_unref(struct radeon_fence **fence);
-int radeon_fence_count_emitted(struct radeon_device *rdev, int ring);
+unsigned radeon_fence_count_emitted(struct radeon_device *rdev, int ring);
 
 /*
  * Tiling registers
@@ -381,8 +382,11 @@
  * alignment).
  */
 struct radeon_sa_manager {
+	spinlock_t		lock;
 	struct radeon_bo	*bo;
-	struct list_head	sa_bo;
+	struct list_head	*hole;
+	struct list_head	flist[RADEON_NUM_RINGS];
+	struct list_head	olist;
 	unsigned		size;
 	uint64_t		gpu_addr;
 	void			*cpu_ptr;
@@ -393,10 +397,12 @@
 
 /* sub-allocation buffer */
 struct radeon_sa_bo {
-	struct list_head		list;
+	struct list_head		olist;
+	struct list_head		flist;
 	struct radeon_sa_manager	*manager;
-	unsigned			offset;
-	unsigned			size;
+	unsigned			soffset;
+	unsigned			eoffset;
+	struct radeon_fence		*fence;
 };
 
 /*
@@ -427,34 +433,13 @@
 /*
  * Semaphores.
  */
-struct radeon_ring;
-
-#define	RADEON_SEMAPHORE_BO_SIZE	256
-
-struct radeon_semaphore_driver {
-	rwlock_t			lock;
-	struct list_head		bo;
-};
-
-struct radeon_semaphore_bo;
-
 /* everything here is constant */
 struct radeon_semaphore {
-	struct list_head		list;
+	struct radeon_sa_bo		*sa_bo;
+	signed				waiters;
 	uint64_t			gpu_addr;
-	uint32_t			*cpu_ptr;
-	struct radeon_semaphore_bo	*bo;
 };
 
-struct radeon_semaphore_bo {
-	struct list_head		list;
-	struct radeon_ib		*ib;
-	struct list_head		free;
-	struct radeon_semaphore		semaphores[RADEON_SEMAPHORE_BO_SIZE/8];
-	unsigned			nused;
-};
-
-void radeon_semaphore_driver_fini(struct radeon_device *rdev);
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore);
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
@@ -466,7 +451,8 @@
 				bool sync_to[RADEON_NUM_RINGS],
 				int dst_ring);
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore);
+			   struct radeon_semaphore *semaphore,
+			   struct radeon_fence *fence);
 
 /*
  * GART structures, functions & helpers
@@ -637,26 +623,14 @@
  */
 
 struct radeon_ib {
-	struct radeon_sa_bo	sa_bo;
-	unsigned		idx;
-	uint32_t		length_dw;
-	uint64_t		gpu_addr;
-	uint32_t		*ptr;
-	struct radeon_fence	*fence;
-	unsigned		vm_id;
-	bool			is_const_ib;
-};
-
-/*
- * locking -
- * mutex protects scheduled_ibs, ready, alloc_bm
- */
-struct radeon_ib_pool {
-	struct radeon_mutex		mutex;
-	struct radeon_sa_manager	sa_manager;
-	struct radeon_ib		ibs[RADEON_IB_POOL_SIZE];
-	bool				ready;
-	unsigned			head_id;
+	struct radeon_sa_bo		*sa_bo;
+	uint32_t			length_dw;
+	uint64_t			gpu_addr;
+	uint32_t			*ptr;
+	struct radeon_fence		*fence;
+	unsigned			vm_id;
+	bool				is_const_ib;
+	struct radeon_semaphore		*semaphore;
 };
 
 struct radeon_ring {
@@ -676,7 +650,6 @@
 	uint64_t		gpu_addr;
 	uint32_t		align_mask;
 	uint32_t		ptr_mask;
-	struct mutex		mutex;
 	bool			ready;
 	u32			ptr_reg_shift;
 	u32			ptr_reg_mask;
@@ -693,7 +666,7 @@
 	unsigned			last_pfn;
 	u64				pt_gpu_addr;
 	u64				*pt;
-	struct radeon_sa_bo		sa_bo;
+	struct radeon_sa_bo		*sa_bo;
 	struct mutex			mutex;
 	/* last fence for cs using this vm */
 	struct radeon_fence		*fence;
@@ -770,7 +743,6 @@
 };
 
 struct r600_blit {
-	struct mutex		mutex;
 	struct radeon_bo	*shader_obj;
 	struct r600_blit_cp_primitives primitives;
 	int max_dim;
@@ -780,8 +752,6 @@
 	u32 vs_offset, ps_offset;
 	u32 state_offset;
 	u32 state_len;
-	u32 vb_used, vb_total;
-	struct radeon_ib *vb_ib;
 };
 
 void r600_blit_suspend(struct radeon_device *rdev);
@@ -799,9 +769,8 @@
 };
 
 int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib **ib, unsigned size);
-void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib);
-bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib);
+		  struct radeon_ib *ib, unsigned size);
+void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib);
 int radeon_ib_pool_init(struct radeon_device *rdev);
 void radeon_ib_pool_fini(struct radeon_device *rdev);
@@ -815,6 +784,7 @@
 int radeon_ring_lock(struct radeon_device *rdev, struct radeon_ring *cp, unsigned ndw);
 void radeon_ring_commit(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *cp);
+void radeon_ring_undo(struct radeon_ring *ring);
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *cp);
 int radeon_ring_test(struct radeon_device *rdev, struct radeon_ring *cp);
 void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring);
@@ -868,8 +838,8 @@
 	int			chunk_relocs_idx;
 	int			chunk_flags_idx;
 	int			chunk_const_ib_idx;
-	struct radeon_ib	*ib;
-	struct radeon_ib	*const_ib;
+	struct radeon_ib	ib;
+	struct radeon_ib	const_ib;
 	void			*track;
 	unsigned		family;
 	int			parser_error;
@@ -1531,11 +1501,12 @@
 	struct radeon_mode_info		mode_info;
 	struct radeon_scratch		scratch;
 	struct radeon_mman		mman;
-	rwlock_t			fence_lock;
 	struct radeon_fence_driver	fence_drv[RADEON_NUM_RINGS];
-	struct radeon_semaphore_driver	semaphore_drv;
+	wait_queue_head_t		fence_queue;
+	struct mutex			ring_lock;
 	struct radeon_ring		ring[RADEON_NUM_RINGS];
-	struct radeon_ib_pool		ib_pool;
+	bool				ib_pool_ready;
+	struct radeon_sa_manager	ring_tmp_bo;
 	struct radeon_irq		irq;
 	struct radeon_asic		*asic;
 	struct radeon_gem		gem;
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 78309318..05a4e15 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -368,11 +368,14 @@
 int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
 void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
 /* r600 blit */
-int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages);
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
+int r600_blit_prepare_copy(struct radeon_device *rdev, unsigned num_gpu_pages,
+			   struct radeon_sa_bo **vb);
+void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence,
+			 struct radeon_sa_bo *vb);
 void r600_kms_blit_copy(struct radeon_device *rdev,
 			u64 src_gpu_addr, u64 dst_gpu_addr,
-			unsigned num_gpu_pages);
+			unsigned num_gpu_pages,
+			struct radeon_sa_bo *vb);
 int r600_mc_wait_for_idle(struct radeon_device *rdev);
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index c66beb1..c7d64a7 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -122,15 +122,15 @@
 	int i, r;
 
 	for (i = 0; i < p->nrelocs; i++) {
+		struct radeon_fence *fence;
+
 		if (!p->relocs[i].robj || !p->relocs[i].robj->tbo.sync_obj)
 			continue;
 
-		if (!(p->relocs[i].flags & RADEON_RELOC_DONT_SYNC)) {
-			struct radeon_fence *fence = p->relocs[i].robj->tbo.sync_obj;
-			if (fence->ring != p->ring && !radeon_fence_signaled(fence)) {
-				sync_to_ring[fence->ring] = true;
-				need_sync = true;
-			}
+		fence = p->relocs[i].robj->tbo.sync_obj;
+		if (fence->ring != p->ring && !radeon_fence_signaled(fence)) {
+			sync_to_ring[fence->ring] = true;
+			need_sync = true;
 		}
 	}
 
@@ -138,12 +138,12 @@
 		return 0;
 	}
 
-	r = radeon_semaphore_create(p->rdev, &p->ib->fence->semaphore);
+	r = radeon_semaphore_create(p->rdev, &p->ib.semaphore);
 	if (r) {
 		return r;
 	}
 
-	return radeon_semaphore_sync_rings(p->rdev, p->ib->fence->semaphore,
+	return radeon_semaphore_sync_rings(p->rdev, p->ib.semaphore,
 					   sync_to_ring, p->ring);
 }
 
@@ -161,8 +161,10 @@
 	/* get chunks */
 	INIT_LIST_HEAD(&p->validated);
 	p->idx = 0;
-	p->ib = NULL;
-	p->const_ib = NULL;
+	p->ib.sa_bo = NULL;
+	p->ib.semaphore = NULL;
+	p->const_ib.sa_bo = NULL;
+	p->const_ib.semaphore = NULL;
 	p->chunk_ib_idx = -1;
 	p->chunk_relocs_idx = -1;
 	p->chunk_flags_idx = -1;
@@ -301,10 +303,9 @@
 {
 	unsigned i;
 
-
-	if (!error && parser->ib)
+	if (!error)
 		ttm_eu_fence_buffer_objects(&parser->validated,
-					    parser->ib->fence);
+					    parser->ib.fence);
 	else
 		ttm_eu_backoff_reservation(&parser->validated);
 
@@ -327,9 +328,7 @@
 	kfree(parser->chunks);
 	kfree(parser->chunks_array);
 	radeon_ib_free(parser->rdev, &parser->ib);
-	if (parser->const_ib) {
-		radeon_ib_free(parser->rdev, &parser->const_ib);
-	}
+	radeon_ib_free(parser->rdev, &parser->const_ib);
 }
 
 static int radeon_cs_ib_chunk(struct radeon_device *rdev,
@@ -355,7 +354,7 @@
 		DRM_ERROR("Failed to get ib !\n");
 		return r;
 	}
-	parser->ib->length_dw = ib_chunk->length_dw;
+	parser->ib.length_dw = ib_chunk->length_dw;
 	r = radeon_cs_parse(rdev, parser->ring, parser);
 	if (r || parser->parser_error) {
 		DRM_ERROR("Invalid command stream !\n");
@@ -370,8 +369,8 @@
 	if (r) {
 		DRM_ERROR("Failed to synchronize rings !\n");
 	}
-	parser->ib->vm_id = 0;
-	r = radeon_ib_schedule(rdev, parser->ib);
+	parser->ib.vm_id = 0;
+	r = radeon_ib_schedule(rdev, &parser->ib);
 	if (r) {
 		DRM_ERROR("Failed to schedule IB !\n");
 	}
@@ -422,14 +421,14 @@
 			DRM_ERROR("Failed to get const ib !\n");
 			return r;
 		}
-		parser->const_ib->is_const_ib = true;
-		parser->const_ib->length_dw = ib_chunk->length_dw;
+		parser->const_ib.is_const_ib = true;
+		parser->const_ib.length_dw = ib_chunk->length_dw;
 		/* Copy the packet into the IB */
-		if (DRM_COPY_FROM_USER(parser->const_ib->ptr, ib_chunk->user_ptr,
+		if (DRM_COPY_FROM_USER(parser->const_ib.ptr, ib_chunk->user_ptr,
 				       ib_chunk->length_dw * 4)) {
 			return -EFAULT;
 		}
-		r = radeon_ring_ib_parse(rdev, parser->ring, parser->const_ib);
+		r = radeon_ring_ib_parse(rdev, parser->ring, &parser->const_ib);
 		if (r) {
 			return r;
 		}
@@ -446,13 +445,13 @@
 		DRM_ERROR("Failed to get ib !\n");
 		return r;
 	}
-	parser->ib->length_dw = ib_chunk->length_dw;
+	parser->ib.length_dw = ib_chunk->length_dw;
 	/* Copy the packet into the IB */
-	if (DRM_COPY_FROM_USER(parser->ib->ptr, ib_chunk->user_ptr,
+	if (DRM_COPY_FROM_USER(parser->ib.ptr, ib_chunk->user_ptr,
 			       ib_chunk->length_dw * 4)) {
 		return -EFAULT;
 	}
-	r = radeon_ring_ib_parse(rdev, parser->ring, parser->ib);
+	r = radeon_ring_ib_parse(rdev, parser->ring, &parser->ib);
 	if (r) {
 		return r;
 	}
@@ -473,29 +472,29 @@
 
 	if ((rdev->family >= CHIP_TAHITI) &&
 	    (parser->chunk_const_ib_idx != -1)) {
-		parser->const_ib->vm_id = vm->id;
+		parser->const_ib.vm_id = vm->id;
 		/* ib pool is bind at 0 in virtual address space to gpu_addr is the
 		 * offset inside the pool bo
 		 */
-		parser->const_ib->gpu_addr = parser->const_ib->sa_bo.offset;
-		r = radeon_ib_schedule(rdev, parser->const_ib);
+		parser->const_ib.gpu_addr = parser->const_ib.sa_bo->soffset;
+		r = radeon_ib_schedule(rdev, &parser->const_ib);
 		if (r)
 			goto out;
 	}
 
-	parser->ib->vm_id = vm->id;
+	parser->ib.vm_id = vm->id;
 	/* ib pool is bind at 0 in virtual address space to gpu_addr is the
 	 * offset inside the pool bo
 	 */
-	parser->ib->gpu_addr = parser->ib->sa_bo.offset;
-	parser->ib->is_const_ib = false;
-	r = radeon_ib_schedule(rdev, parser->ib);
+	parser->ib.gpu_addr = parser->ib.sa_bo->soffset;
+	parser->ib.is_const_ib = false;
+	r = radeon_ib_schedule(rdev, &parser->ib);
 out:
 	if (!r) {
 		if (vm->fence) {
 			radeon_fence_unref(&vm->fence);
 		}
-		vm->fence = radeon_fence_ref(parser->ib->fence);
+		vm->fence = radeon_fence_ref(parser->ib.fence);
 	}
 	mutex_unlock(&fpriv->vm.mutex);
 	return r;
@@ -573,7 +572,7 @@
 				size = PAGE_SIZE;
 		}
 		
-		if (DRM_COPY_FROM_USER(p->ib->ptr + (i * (PAGE_SIZE/4)),
+		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
 				       ibc->user_ptr + (i * PAGE_SIZE),
 				       size))
 			return -EFAULT;
@@ -590,7 +589,7 @@
 	bool copy1 = (p->rdev->flags & RADEON_IS_AGP) ? false : true;
 
 	for (i = ibc->last_copied_page + 1; i < pg_idx; i++) {
-		if (DRM_COPY_FROM_USER(p->ib->ptr + (i * (PAGE_SIZE/4)),
+		if (DRM_COPY_FROM_USER(p->ib.ptr + (i * (PAGE_SIZE/4)),
 				       ibc->user_ptr + (i * PAGE_SIZE),
 				       PAGE_SIZE)) {
 			p->parser_error = -EFAULT;
@@ -606,7 +605,7 @@
 
 	new_page = ibc->kpage_idx[0] < ibc->kpage_idx[1] ? 0 : 1;
 	if (copy1)
-		ibc->kpage[new_page] = p->ib->ptr + (pg_idx * (PAGE_SIZE / 4));
+		ibc->kpage[new_page] = p->ib.ptr + (pg_idx * (PAGE_SIZE / 4));
 
 	if (DRM_COPY_FROM_USER(ibc->kpage[new_page],
 			       ibc->user_ptr + (pg_idx * PAGE_SIZE),
@@ -617,7 +616,7 @@
 
 	/* copy to IB for non single case */
 	if (!copy1)
-		memcpy((void *)(p->ib->ptr+(pg_idx*(PAGE_SIZE/4))), ibc->kpage[new_page], size);
+		memcpy((void *)(p->ib.ptr+(pg_idx*(PAGE_SIZE/4))), ibc->kpage[new_page], size);
 
 	ibc->last_copied_page = pg_idx;
 	ibc->kpage_idx[new_page] = pg_idx;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index ff28210..e1bc7e9 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -225,9 +225,9 @@
 	/* disable event_write fences */
 	rdev->wb.use_event = false;
 	/* disabled via module param */
-	if (radeon_no_wb == 1)
+	if (radeon_no_wb == 1) {
 		rdev->wb.enabled = false;
-	else {
+	} else {
 		if (rdev->flags & RADEON_IS_AGP) {
 			/* often unreliable on AGP */
 			rdev->wb.enabled = false;
@@ -237,8 +237,9 @@
 		} else {
 			rdev->wb.enabled = true;
 			/* event_write fences are only available on r600+ */
-			if (rdev->family >= CHIP_R600)
+			if (rdev->family >= CHIP_R600) {
 				rdev->wb.use_event = true;
+			}
 		}
 	}
 	/* always use writeback/events on NI, APUs */
@@ -723,21 +724,16 @@
 	/* mutex initialization are all done here so we
 	 * can recall function without having locking issues */
 	radeon_mutex_init(&rdev->cs_mutex);
-	radeon_mutex_init(&rdev->ib_pool.mutex);
-	for (i = 0; i < RADEON_NUM_RINGS; ++i)
-		mutex_init(&rdev->ring[i].mutex);
+	mutex_init(&rdev->ring_lock);
 	mutex_init(&rdev->dc_hw_i2c_mutex);
 	if (rdev->family >= CHIP_R600)
 		spin_lock_init(&rdev->ih.lock);
 	mutex_init(&rdev->gem.mutex);
 	mutex_init(&rdev->pm.mutex);
 	mutex_init(&rdev->vram_mutex);
-	rwlock_init(&rdev->fence_lock);
-	rwlock_init(&rdev->semaphore_drv.lock);
 	INIT_LIST_HEAD(&rdev->gem.objects);
 	init_waitqueue_head(&rdev->irq.vblank_queue);
 	init_waitqueue_head(&rdev->irq.idle_queue);
-	INIT_LIST_HEAD(&rdev->semaphore_drv.bo);
 	/* initialize vm here */
 	rdev->vm_manager.use_bitmap = 1;
 	rdev->vm_manager.max_pfn = 1 << 20;
@@ -913,9 +909,12 @@
 	}
 	/* evict vram memory */
 	radeon_bo_evict_vram(rdev);
+
+	mutex_lock(&rdev->ring_lock);
 	/* wait for gpu to finish processing current batch */
 	for (i = 0; i < RADEON_NUM_RINGS; i++)
-		radeon_fence_wait_empty(rdev, i);
+		radeon_fence_wait_empty_locked(rdev, i);
+	mutex_unlock(&rdev->ring_lock);
 
 	radeon_save_bios_scratch_regs(rdev);
 
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 5bb78bf..11f5f40 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -63,75 +63,82 @@
 
 int radeon_fence_emit(struct radeon_device *rdev, struct radeon_fence *fence)
 {
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
-	if (fence->emitted) {
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+	/* we are protected by the ring emission mutex */
+	if (fence->seq && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {
 		return 0;
 	}
-	fence->seq = atomic_add_return(1, &rdev->fence_drv[fence->ring].seq);
+	fence->seq = ++rdev->fence_drv[fence->ring].seq;
 	radeon_fence_ring_emit(rdev, fence->ring, fence);
 	trace_radeon_fence_emit(rdev->ddev, fence->seq);
-	fence->emitted = true;
-	/* are we the first fence on a previusly idle ring? */
-	if (list_empty(&rdev->fence_drv[fence->ring].emitted)) {
-		rdev->fence_drv[fence->ring].last_activity = jiffies;
-	}
-	list_move_tail(&fence->list, &rdev->fence_drv[fence->ring].emitted);
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 	return 0;
 }
 
-static bool radeon_fence_poll_locked(struct radeon_device *rdev, int ring)
+void radeon_fence_process(struct radeon_device *rdev, int ring)
 {
-	struct radeon_fence *fence;
-	struct list_head *i, *n;
-	uint32_t seq;
+	uint64_t seq, last_seq;
+	unsigned count_loop = 0;
 	bool wake = false;
 
-	seq = radeon_fence_read(rdev, ring);
-	if (seq == rdev->fence_drv[ring].last_seq)
-		return false;
+	/* Note there is a scenario here for an infinite loop but it's
+	 * very unlikely to happen. For it to happen, the current polling
+	 * process need to be interrupted by another process and another
+	 * process needs to update the last_seq btw the atomic read and
+	 * xchg of the current process.
+	 *
+	 * More over for this to go in infinite loop there need to be
+	 * continuously new fence signaled ie radeon_fence_read needs
+	 * to return a different value each time for both the currently
+	 * polling process and the other process that xchg the last_seq
+	 * btw atomic read and xchg of the current process. And the
+	 * value the other process set as last seq must be higher than
+	 * the seq value we just read. Which means that current process
+	 * need to be interrupted after radeon_fence_read and before
+	 * atomic xchg.
+	 *
+	 * To be even more safe we count the number of time we loop and
+	 * we bail after 10 loop just accepting the fact that we might
+	 * have temporarly set the last_seq not to the true real last
+	 * seq but to an older one.
+	 */
+	last_seq = atomic64_read(&rdev->fence_drv[ring].last_seq);
+	do {
+		seq = radeon_fence_read(rdev, ring);
+		seq |= last_seq & 0xffffffff00000000LL;
+		if (seq < last_seq) {
+			seq += 0x100000000LL;
+		}
 
-	rdev->fence_drv[ring].last_seq = seq;
-	rdev->fence_drv[ring].last_activity = jiffies;
-
-	n = NULL;
-	list_for_each(i, &rdev->fence_drv[ring].emitted) {
-		fence = list_entry(i, struct radeon_fence, list);
-		if (fence->seq == seq) {
-			n = i;
+		if (seq == last_seq) {
 			break;
 		}
-	}
-	/* all fence previous to this one are considered as signaled */
-	if (n) {
-		i = n;
-		do {
-			n = i->prev;
-			list_move_tail(i, &rdev->fence_drv[ring].signaled);
-			fence = list_entry(i, struct radeon_fence, list);
-			fence->signaled = true;
-			i = n;
-		} while (i != &rdev->fence_drv[ring].emitted);
+		/* If we loop over we don't want to return without
+		 * checking if a fence is signaled as it means that the
+		 * seq we just read is different from the previous on.
+		 */
 		wake = true;
+		last_seq = seq;
+		if ((count_loop++) > 10) {
+			/* We looped over too many time leave with the
+			 * fact that we might have set an older fence
+			 * seq then the current real last seq as signaled
+			 * by the hw.
+			 */
+			break;
+		}
+	} while (atomic64_xchg(&rdev->fence_drv[ring].last_seq, seq) > seq);
+
+	if (wake) {
+		rdev->fence_drv[ring].last_activity = jiffies;
+		wake_up_all(&rdev->fence_queue);
 	}
-	return wake;
 }
 
 static void radeon_fence_destroy(struct kref *kref)
 {
-	unsigned long irq_flags;
-        struct radeon_fence *fence;
+	struct radeon_fence *fence;
 
 	fence = container_of(kref, struct radeon_fence, kref);
-	write_lock_irqsave(&fence->rdev->fence_lock, irq_flags);
-	list_del(&fence->list);
-	fence->emitted = false;
-	write_unlock_irqrestore(&fence->rdev->fence_lock, irq_flags);
-	if (fence->semaphore)
-		radeon_semaphore_free(fence->rdev, fence->semaphore);
+	fence->seq = RADEON_FENCE_NOTEMITED_SEQ;
 	kfree(fence);
 }
 
@@ -145,83 +152,84 @@
 	}
 	kref_init(&((*fence)->kref));
 	(*fence)->rdev = rdev;
-	(*fence)->emitted = false;
-	(*fence)->signaled = false;
-	(*fence)->seq = 0;
+	(*fence)->seq = RADEON_FENCE_NOTEMITED_SEQ;
 	(*fence)->ring = ring;
-	(*fence)->semaphore = NULL;
-	INIT_LIST_HEAD(&(*fence)->list);
 	return 0;
 }
 
+static bool radeon_fence_seq_signaled(struct radeon_device *rdev,
+				      u64 seq, unsigned ring)
+{
+	if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) {
+		return true;
+	}
+	/* poll new last sequence at least once */
+	radeon_fence_process(rdev, ring);
+	if (atomic64_read(&rdev->fence_drv[ring].last_seq) >= seq) {
+		return true;
+	}
+	return false;
+}
+
 bool radeon_fence_signaled(struct radeon_fence *fence)
 {
-	unsigned long irq_flags;
-	bool signaled = false;
-
-	if (!fence)
+	if (!fence) {
 		return true;
-
-	write_lock_irqsave(&fence->rdev->fence_lock, irq_flags);
-	signaled = fence->signaled;
-	/* if we are shuting down report all fence as signaled */
-	if (fence->rdev->shutdown) {
-		signaled = true;
 	}
-	if (!fence->emitted) {
+	if (fence->seq == RADEON_FENCE_NOTEMITED_SEQ) {
 		WARN(1, "Querying an unemitted fence : %p !\n", fence);
-		signaled = true;
+		return true;
 	}
-	if (!signaled) {
-		radeon_fence_poll_locked(fence->rdev, fence->ring);
-		signaled = fence->signaled;
+	if (fence->seq == RADEON_FENCE_SIGNALED_SEQ) {
+		return true;
 	}
-	write_unlock_irqrestore(&fence->rdev->fence_lock, irq_flags);
-	return signaled;
+	if (radeon_fence_seq_signaled(fence->rdev, fence->seq, fence->ring)) {
+		fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+		return true;
+	}
+	return false;
 }
 
-int radeon_fence_wait(struct radeon_fence *fence, bool intr)
+static int radeon_fence_wait_seq(struct radeon_device *rdev, u64 target_seq,
+				 unsigned ring, bool intr, bool lock_ring)
 {
-	struct radeon_device *rdev;
-	unsigned long irq_flags, timeout;
-	u32 seq;
-	int i, r;
+	unsigned long timeout, last_activity;
+	uint64_t seq;
+	unsigned i;
 	bool signaled;
+	int r;
 
-	if (fence == NULL) {
-		WARN(1, "Querying an invalid fence : %p !\n", fence);
-		return -EINVAL;
-	}
+	while (target_seq > atomic64_read(&rdev->fence_drv[ring].last_seq)) {
+		if (!rdev->ring[ring].ready) {
+			return -EBUSY;
+		}
 
-	rdev = fence->rdev;
-	signaled = radeon_fence_signaled(fence);
-	while (!signaled) {
-		read_lock_irqsave(&rdev->fence_lock, irq_flags);
 		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
-		if (time_after(rdev->fence_drv[fence->ring].last_activity, timeout)) {
+		if (time_after(rdev->fence_drv[ring].last_activity, timeout)) {
 			/* the normal case, timeout is somewhere before last_activity */
-			timeout = rdev->fence_drv[fence->ring].last_activity - timeout;
+			timeout = rdev->fence_drv[ring].last_activity - timeout;
 		} else {
 			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
-			 * anyway we will just wait for the minimum amount and then check for a lockup */
+			 * anyway we will just wait for the minimum amount and then check for a lockup
+			 */
 			timeout = 1;
 		}
-		/* save current sequence value used to check for GPU lockups */
-		seq = rdev->fence_drv[fence->ring].last_seq;
-		read_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+		seq = atomic64_read(&rdev->fence_drv[ring].last_seq);
+		/* Save current last activity valuee, used to check for GPU lockups */
+		last_activity = rdev->fence_drv[ring].last_activity;
 
 		trace_radeon_fence_wait_begin(rdev->ddev, seq);
-		radeon_irq_kms_sw_irq_get(rdev, fence->ring);
+		radeon_irq_kms_sw_irq_get(rdev, ring);
 		if (intr) {
-			r = wait_event_interruptible_timeout(
-				rdev->fence_drv[fence->ring].queue,
-				(signaled = radeon_fence_signaled(fence)), timeout);
-		} else {
-			r = wait_event_timeout(
-				rdev->fence_drv[fence->ring].queue,
-				(signaled = radeon_fence_signaled(fence)), timeout);
+			r = wait_event_interruptible_timeout(rdev->fence_queue,
+				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
+				timeout);
+                } else {
+			r = wait_event_timeout(rdev->fence_queue,
+				(signaled = radeon_fence_seq_signaled(rdev, target_seq, ring)),
+				timeout);
 		}
-		radeon_irq_kms_sw_irq_put(rdev, fence->ring);
+		radeon_irq_kms_sw_irq_put(rdev, ring);
 		if (unlikely(r < 0)) {
 			return r;
 		}
@@ -234,81 +242,246 @@
 				continue;
 			}
 
-			write_lock_irqsave(&rdev->fence_lock, irq_flags);
 			/* check if sequence value has changed since last_activity */
-			if (seq != rdev->fence_drv[fence->ring].last_seq) {
-				write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+			if (seq != atomic64_read(&rdev->fence_drv[ring].last_seq)) {
 				continue;
 			}
 
-			/* change sequence value on all rings, so nobody else things there is a lockup */
-			for (i = 0; i < RADEON_NUM_RINGS; ++i)
-				rdev->fence_drv[i].last_seq -= 0x10000;
+			if (lock_ring) {
+				mutex_lock(&rdev->ring_lock);
+			}
 
-			rdev->fence_drv[fence->ring].last_activity = jiffies;
-			write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+			/* test if somebody else has already decided that this is a lockup */
+			if (last_activity != rdev->fence_drv[ring].last_activity) {
+				if (lock_ring) {
+					mutex_unlock(&rdev->ring_lock);
+				}
+				continue;
+			}
 
-			if (radeon_ring_is_lockup(rdev, fence->ring, &rdev->ring[fence->ring])) {
-
+			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
 				/* good news we believe it's a lockup */
-				printk(KERN_WARNING "GPU lockup (waiting for 0x%08X last fence id 0x%08X)\n",
-				     fence->seq, seq);
+				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx last fence id 0x%016llx)\n",
+					 target_seq, seq);
+
+				/* change last activity so nobody else think there is a lockup */
+				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+					rdev->fence_drv[i].last_activity = jiffies;
+				}
 
 				/* mark the ring as not ready any more */
-				rdev->ring[fence->ring].ready = false;
+				rdev->ring[ring].ready = false;
+				if (lock_ring) {
+					mutex_unlock(&rdev->ring_lock);
+				}
 				return -EDEADLK;
 			}
+
+			if (lock_ring) {
+				mutex_unlock(&rdev->ring_lock);
+			}
 		}
 	}
 	return 0;
 }
 
-int radeon_fence_wait_next(struct radeon_device *rdev, int ring)
+int radeon_fence_wait(struct radeon_fence *fence, bool intr)
 {
-	unsigned long irq_flags;
-	struct radeon_fence *fence;
 	int r;
 
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
-	if (!rdev->ring[ring].ready) {
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		return -EBUSY;
+	if (fence == NULL) {
+		WARN(1, "Querying an invalid fence : %p !\n", fence);
+		return -EINVAL;
 	}
-	if (list_empty(&rdev->fence_drv[ring].emitted)) {
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		return -ENOENT;
+
+	r = radeon_fence_wait_seq(fence->rdev, fence->seq,
+				  fence->ring, intr, true);
+	if (r) {
+		return r;
 	}
-	fence = list_entry(rdev->fence_drv[ring].emitted.next,
-			   struct radeon_fence, list);
-	radeon_fence_ref(fence);
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-	r = radeon_fence_wait(fence, false);
-	radeon_fence_unref(&fence);
-	return r;
+	fence->seq = RADEON_FENCE_SIGNALED_SEQ;
+	return 0;
 }
 
-int radeon_fence_wait_empty(struct radeon_device *rdev, int ring)
+bool radeon_fence_any_seq_signaled(struct radeon_device *rdev, u64 *seq)
 {
-	unsigned long irq_flags;
-	struct radeon_fence *fence;
+	unsigned i;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (seq[i] && radeon_fence_seq_signaled(rdev, seq[i], i)) {
+			return true;
+		}
+	}
+	return false;
+}
+
+static int radeon_fence_wait_any_seq(struct radeon_device *rdev,
+				     u64 *target_seq, bool intr)
+{
+	unsigned long timeout, last_activity, tmp;
+	unsigned i, ring = RADEON_NUM_RINGS;
+	bool signaled;
 	int r;
 
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
-	if (!rdev->ring[ring].ready) {
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		return -EBUSY;
+	for (i = 0, last_activity = 0; i < RADEON_NUM_RINGS; ++i) {
+		if (!target_seq[i]) {
+			continue;
+		}
+
+		/* use the most recent one as indicator */
+		if (time_after(rdev->fence_drv[i].last_activity, last_activity)) {
+			last_activity = rdev->fence_drv[i].last_activity;
+		}
+
+		/* For lockup detection just pick the lowest ring we are
+		 * actively waiting for
+		 */
+		if (i < ring) {
+			ring = i;
+		}
 	}
-	if (list_empty(&rdev->fence_drv[ring].emitted)) {
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
+
+	/* nothing to wait for ? */
+	if (ring == RADEON_NUM_RINGS) {
 		return 0;
 	}
-	fence = list_entry(rdev->fence_drv[ring].emitted.prev,
-			   struct radeon_fence, list);
-	radeon_fence_ref(fence);
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-	r = radeon_fence_wait(fence, false);
-	radeon_fence_unref(&fence);
-	return r;
+
+	while (!radeon_fence_any_seq_signaled(rdev, target_seq)) {
+		timeout = jiffies - RADEON_FENCE_JIFFIES_TIMEOUT;
+		if (time_after(last_activity, timeout)) {
+			/* the normal case, timeout is somewhere before last_activity */
+			timeout = last_activity - timeout;
+		} else {
+			/* either jiffies wrapped around, or no fence was signaled in the last 500ms
+			 * anyway we will just wait for the minimum amount and then check for a lockup
+			 */
+			timeout = 1;
+		}
+
+		trace_radeon_fence_wait_begin(rdev->ddev, target_seq[ring]);
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (target_seq[i]) {
+				radeon_irq_kms_sw_irq_get(rdev, i);
+			}
+		}
+		if (intr) {
+			r = wait_event_interruptible_timeout(rdev->fence_queue,
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
+				timeout);
+		} else {
+			r = wait_event_timeout(rdev->fence_queue,
+				(signaled = radeon_fence_any_seq_signaled(rdev, target_seq)),
+				timeout);
+		}
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			if (target_seq[i]) {
+				radeon_irq_kms_sw_irq_put(rdev, i);
+			}
+		}
+		if (unlikely(r < 0)) {
+			return r;
+		}
+		trace_radeon_fence_wait_end(rdev->ddev, target_seq[ring]);
+
+		if (unlikely(!signaled)) {
+			/* we were interrupted for some reason and fence
+			 * isn't signaled yet, resume waiting */
+			if (r) {
+				continue;
+			}
+
+			mutex_lock(&rdev->ring_lock);
+			for (i = 0, tmp = 0; i < RADEON_NUM_RINGS; ++i) {
+				if (time_after(rdev->fence_drv[i].last_activity, tmp)) {
+					tmp = rdev->fence_drv[i].last_activity;
+				}
+			}
+			/* test if somebody else has already decided that this is a lockup */
+			if (last_activity != tmp) {
+				last_activity = tmp;
+				mutex_unlock(&rdev->ring_lock);
+				continue;
+			}
+
+			if (radeon_ring_is_lockup(rdev, ring, &rdev->ring[ring])) {
+				/* good news we believe it's a lockup */
+				dev_warn(rdev->dev, "GPU lockup (waiting for 0x%016llx)\n",
+					 target_seq[ring]);
+
+				/* change last activity so nobody else think there is a lockup */
+				for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+					rdev->fence_drv[i].last_activity = jiffies;
+				}
+
+				/* mark the ring as not ready any more */
+				rdev->ring[ring].ready = false;
+				mutex_unlock(&rdev->ring_lock);
+				return -EDEADLK;
+			}
+			mutex_unlock(&rdev->ring_lock);
+		}
+	}
+	return 0;
+}
+
+int radeon_fence_wait_any(struct radeon_device *rdev,
+			  struct radeon_fence **fences,
+			  bool intr)
+{
+	uint64_t seq[RADEON_NUM_RINGS];
+	unsigned i;
+	int r;
+
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		seq[i] = 0;
+
+		if (!fences[i]) {
+			continue;
+		}
+
+		if (fences[i]->seq == RADEON_FENCE_SIGNALED_SEQ) {
+			/* something was allready signaled */
+			return 0;
+		}
+
+		if (fences[i]->seq < RADEON_FENCE_NOTEMITED_SEQ) {
+			seq[i] = fences[i]->seq;
+		}
+	}
+
+	r = radeon_fence_wait_any_seq(rdev, seq, intr);
+	if (r) {
+		return r;
+	}
+	return 0;
+}
+
+int radeon_fence_wait_next_locked(struct radeon_device *rdev, int ring)
+{
+	uint64_t seq;
+
+	/* We are not protected by ring lock when reading current seq but
+	 * it's ok as worst case is we return to early while we could have
+	 * wait.
+	 */
+	seq = atomic64_read(&rdev->fence_drv[ring].last_seq) + 1ULL;
+	if (seq >= rdev->fence_drv[ring].seq) {
+		/* nothing to wait for, last_seq is
+		   already the last emited fence */
+		return -ENOENT;
+	}
+	return radeon_fence_wait_seq(rdev, seq, ring, false, false);
+}
+
+int radeon_fence_wait_empty_locked(struct radeon_device *rdev, int ring)
+{
+	/* We are not protected by ring lock when reading current seq
+	 * but it's ok as wait empty is call from place where no more
+	 * activity can be scheduled so there won't be concurrent access
+	 * to seq value.
+	 */
+	return radeon_fence_wait_seq(rdev, rdev->fence_drv[ring].seq,
+				     ring, false, false);
 }
 
 struct radeon_fence *radeon_fence_ref(struct radeon_fence *fence)
@@ -327,49 +500,27 @@
 	}
 }
 
-void radeon_fence_process(struct radeon_device *rdev, int ring)
+unsigned radeon_fence_count_emitted(struct radeon_device *rdev, int ring)
 {
-	unsigned long irq_flags;
-	bool wake;
+	uint64_t emitted;
 
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
-	wake = radeon_fence_poll_locked(rdev, ring);
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-	if (wake) {
-		wake_up_all(&rdev->fence_drv[ring].queue);
+	/* We are not protected by ring lock when reading the last sequence
+	 * but it's ok to report slightly wrong fence count here.
+	 */
+	radeon_fence_process(rdev, ring);
+	emitted = rdev->fence_drv[ring].seq - atomic64_read(&rdev->fence_drv[ring].last_seq);
+	/* to avoid 32bits warp around */
+	if (emitted > 0x10000000) {
+		emitted = 0x10000000;
 	}
-}
-
-int radeon_fence_count_emitted(struct radeon_device *rdev, int ring)
-{
-	unsigned long irq_flags;
-	int not_processed = 0;
-
-	read_lock_irqsave(&rdev->fence_lock, irq_flags);
-	if (!rdev->fence_drv[ring].initialized) {
-		read_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-		return 0;
-	}
-
-	if (!list_empty(&rdev->fence_drv[ring].emitted)) {
-		struct list_head *ptr;
-		list_for_each(ptr, &rdev->fence_drv[ring].emitted) {
-			/* count up to 3, that's enought info */
-			if (++not_processed >= 3)
-				break;
-		}
-	}
-	read_unlock_irqrestore(&rdev->fence_lock, irq_flags);
-	return not_processed;
+	return (unsigned)emitted;
 }
 
 int radeon_fence_driver_start_ring(struct radeon_device *rdev, int ring)
 {
-	unsigned long irq_flags;
 	uint64_t index;
 	int r;
 
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
 	radeon_scratch_free(rdev, rdev->fence_drv[ring].scratch_reg);
 	if (rdev->wb.use_event) {
 		rdev->fence_drv[ring].scratch_reg = 0;
@@ -378,7 +529,6 @@
 		r = radeon_scratch_get(rdev, &rdev->fence_drv[ring].scratch_reg);
 		if (r) {
 			dev_err(rdev->dev, "fence failed to get scratch register\n");
-			write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 			return r;
 		}
 		index = RADEON_WB_SCRATCH_OFFSET +
@@ -387,11 +537,10 @@
 	}
 	rdev->fence_drv[ring].cpu_addr = &rdev->wb.wb[index/4];
 	rdev->fence_drv[ring].gpu_addr = rdev->wb.gpu_addr + index;
-	radeon_fence_write(rdev, atomic_read(&rdev->fence_drv[ring].seq), ring);
+	radeon_fence_write(rdev, rdev->fence_drv[ring].seq, ring);
 	rdev->fence_drv[ring].initialized = true;
-	DRM_INFO("fence driver on ring %d use gpu addr 0x%08Lx and cpu addr 0x%p\n",
+	dev_info(rdev->dev, "fence driver on ring %d use gpu addr 0x%016llx and cpu addr 0x%p\n",
 		 ring, rdev->fence_drv[ring].gpu_addr, rdev->fence_drv[ring].cpu_addr);
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 	return 0;
 }
 
@@ -400,23 +549,20 @@
 	rdev->fence_drv[ring].scratch_reg = -1;
 	rdev->fence_drv[ring].cpu_addr = NULL;
 	rdev->fence_drv[ring].gpu_addr = 0;
-	atomic_set(&rdev->fence_drv[ring].seq, 0);
-	INIT_LIST_HEAD(&rdev->fence_drv[ring].emitted);
-	INIT_LIST_HEAD(&rdev->fence_drv[ring].signaled);
-	init_waitqueue_head(&rdev->fence_drv[ring].queue);
+	rdev->fence_drv[ring].seq = 0;
+	atomic64_set(&rdev->fence_drv[ring].last_seq, 0);
+	rdev->fence_drv[ring].last_activity = jiffies;
 	rdev->fence_drv[ring].initialized = false;
 }
 
 int radeon_fence_driver_init(struct radeon_device *rdev)
 {
-	unsigned long irq_flags;
 	int ring;
 
-	write_lock_irqsave(&rdev->fence_lock, irq_flags);
+	init_waitqueue_head(&rdev->fence_queue);
 	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
 		radeon_fence_driver_init_ring(rdev, ring);
 	}
-	write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 	if (radeon_debugfs_fence_init(rdev)) {
 		dev_err(rdev->dev, "fence debugfs file creation failed\n");
 	}
@@ -425,19 +571,18 @@
 
 void radeon_fence_driver_fini(struct radeon_device *rdev)
 {
-	unsigned long irq_flags;
 	int ring;
 
+	mutex_lock(&rdev->ring_lock);
 	for (ring = 0; ring < RADEON_NUM_RINGS; ring++) {
 		if (!rdev->fence_drv[ring].initialized)
 			continue;
-		radeon_fence_wait_empty(rdev, ring);
-		wake_up_all(&rdev->fence_drv[ring].queue);
-		write_lock_irqsave(&rdev->fence_lock, irq_flags);
+		radeon_fence_wait_empty_locked(rdev, ring);
+		wake_up_all(&rdev->fence_queue);
 		radeon_scratch_free(rdev, rdev->fence_drv[ring].scratch_reg);
-		write_unlock_irqrestore(&rdev->fence_lock, irq_flags);
 		rdev->fence_drv[ring].initialized = false;
 	}
+	mutex_unlock(&rdev->ring_lock);
 }
 
 
@@ -450,7 +595,6 @@
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_fence *fence;
 	int i;
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
@@ -458,14 +602,10 @@
 			continue;
 
 		seq_printf(m, "--- ring %d ---\n", i);
-		seq_printf(m, "Last signaled fence 0x%08X\n",
-			   radeon_fence_read(rdev, i));
-		if (!list_empty(&rdev->fence_drv[i].emitted)) {
-			fence = list_entry(rdev->fence_drv[i].emitted.prev,
-					   struct radeon_fence, list);
-			seq_printf(m, "Last emitted fence %p with 0x%08X\n",
-				   fence,  fence->seq);
-		}
+		seq_printf(m, "Last signaled fence 0x%016llx\n",
+			   (unsigned long long)atomic64_read(&rdev->fence_drv[i].last_seq));
+		seq_printf(m, "Last emitted  0x%016llx\n",
+			   rdev->fence_drv[i].seq);
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index c58a036..8e9ef34 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -326,7 +326,7 @@
 	rdev->vm_manager.use_bitmap &= ~(1 << vm->id);
 	list_del_init(&vm->list);
 	vm->id = -1;
-	radeon_sa_bo_free(rdev, &vm->sa_bo);
+	radeon_sa_bo_free(rdev, &vm->sa_bo, NULL);
 	vm->pt = NULL;
 
 	list_for_each_entry(bo_va, &vm->va, vm_list) {
@@ -395,7 +395,7 @@
 retry:
 	r = radeon_sa_bo_new(rdev, &rdev->vm_manager.sa_manager, &vm->sa_bo,
 			     RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8),
-			     RADEON_GPU_PAGE_SIZE);
+			     RADEON_GPU_PAGE_SIZE, false);
 	if (r) {
 		if (list_empty(&rdev->vm_manager.lru_vm)) {
 			return r;
@@ -404,10 +404,8 @@
 		radeon_vm_unbind(rdev, vm_evict);
 		goto retry;
 	}
-	vm->pt = rdev->vm_manager.sa_manager.cpu_ptr;
-	vm->pt += (vm->sa_bo.offset >> 3);
-	vm->pt_gpu_addr = rdev->vm_manager.sa_manager.gpu_addr;
-	vm->pt_gpu_addr += vm->sa_bo.offset;
+	vm->pt = radeon_sa_bo_cpu_addr(vm->sa_bo);
+	vm->pt_gpu_addr = radeon_sa_bo_gpu_addr(vm->sa_bo);
 	memset(vm->pt, 0, RADEON_GPU_PAGE_ALIGN(vm->last_pfn * 8));
 
 retry_id:
@@ -428,14 +426,14 @@
 	/* do hw bind */
 	r = rdev->vm_manager.funcs->bind(rdev, vm, id);
 	if (r) {
-		radeon_sa_bo_free(rdev, &vm->sa_bo);
+		radeon_sa_bo_free(rdev, &vm->sa_bo, NULL);
 		return r;
 	}
 	rdev->vm_manager.use_bitmap |= 1 << id;
 	vm->id = id;
 	list_add_tail(&vm->list, &rdev->vm_manager.lru_vm);
-	return radeon_vm_bo_update_pte(rdev, vm, rdev->ib_pool.sa_manager.bo,
-				       &rdev->ib_pool.sa_manager.bo->tbo.mem);
+	return radeon_vm_bo_update_pte(rdev, vm, rdev->ring_tmp_bo.bo,
+				       &rdev->ring_tmp_bo.bo->tbo.mem);
 }
 
 /* object have to be reserved */
@@ -633,7 +631,7 @@
 	/* map the ib pool buffer at 0 in virtual address space, set
 	 * read only
 	 */
-	r = radeon_vm_bo_add(rdev, vm, rdev->ib_pool.sa_manager.bo, 0,
+	r = radeon_vm_bo_add(rdev, vm, rdev->ring_tmp_bo.bo, 0,
 			     RADEON_VM_PAGE_READABLE | RADEON_VM_PAGE_SNOOPED);
 	return r;
 }
@@ -650,12 +648,12 @@
 	radeon_mutex_unlock(&rdev->cs_mutex);
 
 	/* remove all bo */
-	r = radeon_bo_reserve(rdev->ib_pool.sa_manager.bo, false);
+	r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 	if (!r) {
-		bo_va = radeon_bo_va(rdev->ib_pool.sa_manager.bo, vm);
+		bo_va = radeon_bo_va(rdev->ring_tmp_bo.bo, vm);
 		list_del_init(&bo_va->bo_list);
 		list_del_init(&bo_va->vm_list);
-		radeon_bo_unreserve(rdev->ib_pool.sa_manager.bo);
+		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 		kfree(bo_va);
 	}
 	if (!list_empty(&vm->va)) {
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index f9104be..befec7d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -146,6 +146,17 @@
 /*
  * sub allocation
  */
+
+static inline uint64_t radeon_sa_bo_gpu_addr(struct radeon_sa_bo *sa_bo)
+{
+	return sa_bo->manager->gpu_addr + sa_bo->soffset;
+}
+
+static inline void * radeon_sa_bo_cpu_addr(struct radeon_sa_bo *sa_bo)
+{
+	return sa_bo->manager->cpu_ptr + sa_bo->soffset;
+}
+
 extern int radeon_sa_bo_manager_init(struct radeon_device *rdev,
 				     struct radeon_sa_manager *sa_manager,
 				     unsigned size, u32 domain);
@@ -157,9 +168,15 @@
 					struct radeon_sa_manager *sa_manager);
 extern int radeon_sa_bo_new(struct radeon_device *rdev,
 			    struct radeon_sa_manager *sa_manager,
-			    struct radeon_sa_bo *sa_bo,
-			    unsigned size, unsigned align);
+			    struct radeon_sa_bo **sa_bo,
+			    unsigned size, unsigned align, bool block);
 extern void radeon_sa_bo_free(struct radeon_device *rdev,
-			      struct radeon_sa_bo *sa_bo);
+			      struct radeon_sa_bo **sa_bo,
+			      struct radeon_fence *fence);
+#if defined(CONFIG_DEBUG_FS)
+extern void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager,
+					 struct seq_file *m);
+#endif
+
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index caa55d6..0882554 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -252,10 +252,7 @@
 
 	mutex_lock(&rdev->ddev->struct_mutex);
 	mutex_lock(&rdev->vram_mutex);
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (rdev->ring[i].ring_obj)
-			mutex_lock(&rdev->ring[i].mutex);
-	}
+	mutex_lock(&rdev->ring_lock);
 
 	/* gui idle int has issues on older chips it seems */
 	if (rdev->family >= CHIP_R600) {
@@ -273,13 +270,7 @@
 	} else {
 		struct radeon_ring *ring = &rdev->ring[RADEON_RING_TYPE_GFX_INDEX];
 		if (ring->ready) {
-			struct radeon_fence *fence;
-			radeon_ring_alloc(rdev, ring, 64);
-			radeon_fence_create(rdev, &fence, radeon_ring_index(rdev, ring));
-			radeon_fence_emit(rdev, fence);
-			radeon_ring_commit(rdev, ring);
-			radeon_fence_wait(fence, false);
-			radeon_fence_unref(&fence);
+			radeon_fence_wait_empty_locked(rdev, RADEON_RING_TYPE_GFX_INDEX);
 		}
 	}
 	radeon_unmap_vram_bos(rdev);
@@ -311,10 +302,7 @@
 
 	rdev->pm.dynpm_planned_action = DYNPM_ACTION_NONE;
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		if (rdev->ring[i].ring_obj)
-			mutex_unlock(&rdev->ring[i].mutex);
-	}
+	mutex_unlock(&rdev->ring_lock);
 	mutex_unlock(&rdev->vram_mutex);
 	mutex_unlock(&rdev->ddev->struct_mutex);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 2eb4c6e..a5dee76 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -24,6 +24,7 @@
  * Authors: Dave Airlie
  *          Alex Deucher
  *          Jerome Glisse
+ *          Christian König
  */
 #include <linux/seq_file.h>
 #include <linux/slab.h>
@@ -33,8 +34,10 @@
 #include "radeon.h"
 #include "atom.h"
 
-int radeon_debugfs_ib_init(struct radeon_device *rdev);
-int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
+/*
+ * IB.
+ */
+int radeon_debugfs_sa_init(struct radeon_device *rdev);
 
 u32 radeon_get_ib_value(struct radeon_cs_parser *p, int idx)
 {
@@ -61,123 +64,37 @@
 	return idx_value;
 }
 
-void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
-{
-#if DRM_DEBUG_CODE
-	if (ring->count_dw <= 0) {
-		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
-	}
-#endif
-	ring->ring[ring->wptr++] = v;
-	ring->wptr &= ring->ptr_mask;
-	ring->count_dw--;
-	ring->ring_free_dw--;
-}
-
-/*
- * IB.
- */
-bool radeon_ib_try_free(struct radeon_device *rdev, struct radeon_ib *ib)
-{
-	bool done = false;
-
-	/* only free ib which have been emited */
-	if (ib->fence && ib->fence->emitted) {
-		if (radeon_fence_signaled(ib->fence)) {
-			radeon_fence_unref(&ib->fence);
-			radeon_sa_bo_free(rdev, &ib->sa_bo);
-			done = true;
-		}
-	}
-	return done;
-}
-
 int radeon_ib_get(struct radeon_device *rdev, int ring,
-		  struct radeon_ib **ib, unsigned size)
+		  struct radeon_ib *ib, unsigned size)
 {
-	struct radeon_fence *fence;
-	unsigned cretry = 0;
-	int r = 0, i, idx;
+	int r;
 
-	*ib = NULL;
-	/* align size on 256 bytes */
-	size = ALIGN(size, 256);
-
-	r = radeon_fence_create(rdev, &fence, ring);
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo, &ib->sa_bo, size, 256, true);
 	if (r) {
-		dev_err(rdev->dev, "failed to create fence for new IB\n");
+		dev_err(rdev->dev, "failed to get a new IB (%d)\n", r);
+		return r;
+	}
+	r = radeon_fence_create(rdev, &ib->fence, ring);
+	if (r) {
+		dev_err(rdev->dev, "failed to create fence for new IB (%d)\n", r);
+		radeon_sa_bo_free(rdev, &ib->sa_bo, NULL);
 		return r;
 	}
 
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	idx = rdev->ib_pool.head_id;
-retry:
-	if (cretry > 5) {
-		dev_err(rdev->dev, "failed to get an ib after 5 retry\n");
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_fence_unref(&fence);
-		return -ENOMEM;
-	}
-	cretry++;
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		radeon_ib_try_free(rdev, &rdev->ib_pool.ibs[idx]);
-		if (rdev->ib_pool.ibs[idx].fence == NULL) {
-			r = radeon_sa_bo_new(rdev, &rdev->ib_pool.sa_manager,
-					     &rdev->ib_pool.ibs[idx].sa_bo,
-					     size, 256);
-			if (!r) {
-				*ib = &rdev->ib_pool.ibs[idx];
-				(*ib)->ptr = rdev->ib_pool.sa_manager.cpu_ptr;
-				(*ib)->ptr += ((*ib)->sa_bo.offset >> 2);
-				(*ib)->gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
-				(*ib)->gpu_addr += (*ib)->sa_bo.offset;
-				(*ib)->fence = fence;
-				(*ib)->vm_id = 0;
-				(*ib)->is_const_ib = false;
-				/* ib are most likely to be allocated in a ring fashion
-				 * thus rdev->ib_pool.head_id should be the id of the
-				 * oldest ib
-				 */
-				rdev->ib_pool.head_id = (1 + idx);
-				rdev->ib_pool.head_id &= (RADEON_IB_POOL_SIZE - 1);
-				radeon_mutex_unlock(&rdev->ib_pool.mutex);
-				return 0;
-			}
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
-	}
-	/* this should be rare event, ie all ib scheduled none signaled yet.
-	 */
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		if (rdev->ib_pool.ibs[idx].fence && rdev->ib_pool.ibs[idx].fence->emitted) {
-			r = radeon_fence_wait(rdev->ib_pool.ibs[idx].fence, false);
-			if (!r) {
-				goto retry;
-			}
-			/* an error happened */
-			break;
-		}
-		idx = (idx + 1) & (RADEON_IB_POOL_SIZE - 1);
-	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
-	radeon_fence_unref(&fence);
-	return r;
+	ib->ptr = radeon_sa_bo_cpu_addr(ib->sa_bo);
+	ib->gpu_addr = radeon_sa_bo_gpu_addr(ib->sa_bo);
+	ib->vm_id = 0;
+	ib->is_const_ib = false;
+	ib->semaphore = NULL;
+
+	return 0;
 }
 
-void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib **ib)
+void radeon_ib_free(struct radeon_device *rdev, struct radeon_ib *ib)
 {
-	struct radeon_ib *tmp = *ib;
-
-	*ib = NULL;
-	if (tmp == NULL) {
-		return;
-	}
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (tmp->fence && !tmp->fence->emitted) {
-		radeon_sa_bo_free(rdev, &tmp->sa_bo);
-		radeon_fence_unref(&tmp->fence);
-	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
+	radeon_semaphore_free(rdev, ib->semaphore, ib->fence);
+	radeon_sa_bo_free(rdev, &ib->sa_bo, ib->fence);
+	radeon_fence_unref(&ib->fence);
 }
 
 int radeon_ib_schedule(struct radeon_device *rdev, struct radeon_ib *ib)
@@ -187,14 +104,14 @@
 
 	if (!ib->length_dw || !ring->ready) {
 		/* TODO: Nothings in the ib we should report. */
-		DRM_ERROR("radeon: couldn't schedule IB(%u).\n", ib->idx);
+		dev_err(rdev->dev, "couldn't schedule ib\n");
 		return -EINVAL;
 	}
 
 	/* 64 dwords should be enough for fence too */
 	r = radeon_ring_lock(rdev, ring, 64);
 	if (r) {
-		DRM_ERROR("radeon: scheduling IB failed (%d).\n", r);
+		dev_err(rdev->dev, "scheduling IB failed (%d).\n", r);
 		return r;
 	}
 	radeon_ring_ib_execute(rdev, ib->fence->ring, ib);
@@ -205,66 +122,40 @@
 
 int radeon_ib_pool_init(struct radeon_device *rdev)
 {
-	struct radeon_sa_manager tmp;
-	int i, r;
+	int r;
 
-	r = radeon_sa_bo_manager_init(rdev, &tmp,
+	if (rdev->ib_pool_ready) {
+		return 0;
+	}
+	r = radeon_sa_bo_manager_init(rdev, &rdev->ring_tmp_bo,
 				      RADEON_IB_POOL_SIZE*64*1024,
 				      RADEON_GEM_DOMAIN_GTT);
 	if (r) {
 		return r;
 	}
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		radeon_mutex_unlock(&rdev->ib_pool.mutex);
-		radeon_sa_bo_manager_fini(rdev, &tmp);
-		return 0;
+	rdev->ib_pool_ready = true;
+	if (radeon_debugfs_sa_init(rdev)) {
+		dev_err(rdev->dev, "failed to register debugfs file for SA\n");
 	}
-
-	rdev->ib_pool.sa_manager = tmp;
-	INIT_LIST_HEAD(&rdev->ib_pool.sa_manager.sa_bo);
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		rdev->ib_pool.ibs[i].fence = NULL;
-		rdev->ib_pool.ibs[i].idx = i;
-		rdev->ib_pool.ibs[i].length_dw = 0;
-		INIT_LIST_HEAD(&rdev->ib_pool.ibs[i].sa_bo.list);
-	}
-	rdev->ib_pool.head_id = 0;
-	rdev->ib_pool.ready = true;
-	DRM_INFO("radeon: ib pool ready.\n");
-
-	if (radeon_debugfs_ib_init(rdev)) {
-		DRM_ERROR("Failed to register debugfs file for IB !\n");
-	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 	return 0;
 }
 
 void radeon_ib_pool_fini(struct radeon_device *rdev)
 {
-	unsigned i;
-
-	radeon_mutex_lock(&rdev->ib_pool.mutex);
-	if (rdev->ib_pool.ready) {
-		for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-			radeon_sa_bo_free(rdev, &rdev->ib_pool.ibs[i].sa_bo);
-			radeon_fence_unref(&rdev->ib_pool.ibs[i].fence);
-		}
-		radeon_sa_bo_manager_fini(rdev, &rdev->ib_pool.sa_manager);
-		rdev->ib_pool.ready = false;
+	if (rdev->ib_pool_ready) {
+		radeon_sa_bo_manager_fini(rdev, &rdev->ring_tmp_bo);
+		rdev->ib_pool_ready = false;
 	}
-	radeon_mutex_unlock(&rdev->ib_pool.mutex);
 }
 
 int radeon_ib_pool_start(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_start(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_start(rdev, &rdev->ring_tmp_bo);
 }
 
 int radeon_ib_pool_suspend(struct radeon_device *rdev)
 {
-	return radeon_sa_bo_manager_suspend(rdev, &rdev->ib_pool.sa_manager);
+	return radeon_sa_bo_manager_suspend(rdev, &rdev->ring_tmp_bo);
 }
 
 int radeon_ib_ring_tests(struct radeon_device *rdev)
@@ -300,6 +191,21 @@
 /*
  * Ring.
  */
+int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring);
+
+void radeon_ring_write(struct radeon_ring *ring, uint32_t v)
+{
+#if DRM_DEBUG_CODE
+	if (ring->count_dw <= 0) {
+		DRM_ERROR("radeon: writting more dword to ring than expected !\n");
+	}
+#endif
+	ring->ring[ring->wptr++] = v;
+	ring->wptr &= ring->ptr_mask;
+	ring->count_dw--;
+	ring->ring_free_dw--;
+}
+
 int radeon_ring_index(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	/* r1xx-r5xx only has CP ring */
@@ -346,9 +252,7 @@
 		if (ndw < ring->ring_free_dw) {
 			break;
 		}
-		mutex_unlock(&ring->mutex);
-		r = radeon_fence_wait_next(rdev, radeon_ring_index(rdev, ring));
-		mutex_lock(&ring->mutex);
+		r = radeon_fence_wait_next_locked(rdev, radeon_ring_index(rdev, ring));
 		if (r)
 			return r;
 	}
@@ -361,10 +265,10 @@
 {
 	int r;
 
-	mutex_lock(&ring->mutex);
+	mutex_lock(&rdev->ring_lock);
 	r = radeon_ring_alloc(rdev, ring, ndw);
 	if (r) {
-		mutex_unlock(&ring->mutex);
+		mutex_unlock(&rdev->ring_lock);
 		return r;
 	}
 	return 0;
@@ -389,20 +293,24 @@
 void radeon_ring_unlock_commit(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	radeon_ring_commit(rdev, ring);
-	mutex_unlock(&ring->mutex);
+	mutex_unlock(&rdev->ring_lock);
+}
+
+void radeon_ring_undo(struct radeon_ring *ring)
+{
+	ring->wptr = ring->wptr_old;
 }
 
 void radeon_ring_unlock_undo(struct radeon_device *rdev, struct radeon_ring *ring)
 {
-	ring->wptr = ring->wptr_old;
-	mutex_unlock(&ring->mutex);
+	radeon_ring_undo(ring);
+	mutex_unlock(&rdev->ring_lock);
 }
 
 void radeon_ring_force_activity(struct radeon_device *rdev, struct radeon_ring *ring)
 {
 	int r;
 
-	mutex_lock(&ring->mutex);
 	radeon_ring_free_size(rdev, ring);
 	if (ring->rptr == ring->wptr) {
 		r = radeon_ring_alloc(rdev, ring, 1);
@@ -411,7 +319,6 @@
 			radeon_ring_commit(rdev, ring);
 		}
 	}
-	mutex_unlock(&ring->mutex);
 }
 
 void radeon_ring_lockup_update(struct radeon_ring *ring)
@@ -520,11 +427,12 @@
 	int r;
 	struct radeon_bo *ring_obj;
 
-	mutex_lock(&ring->mutex);
+	mutex_lock(&rdev->ring_lock);
 	ring_obj = ring->ring_obj;
+	ring->ready = false;
 	ring->ring = NULL;
 	ring->ring_obj = NULL;
-	mutex_unlock(&ring->mutex);
+	mutex_unlock(&rdev->ring_lock);
 
 	if (ring_obj) {
 		r = radeon_bo_reserve(ring_obj, false);
@@ -577,29 +485,22 @@
 	{"radeon_ring_cp2", radeon_debugfs_ring_info, 0, &cayman_ring_type_cp2_index},
 };
 
-static int radeon_debugfs_ib_info(struct seq_file *m, void *data)
+static int radeon_debugfs_sa_info(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct radeon_ib *ib = &rdev->ib_pool.ibs[*((unsigned*)node->info_ent->data)];
-	unsigned i;
 
-	if (ib == NULL) {
-		return 0;
-	}
-	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++) {
-		seq_printf(m, "[%05u]=0x%08X\n", i, ib->ptr[i]);
-	}
+	radeon_sa_bo_dump_debug_info(&rdev->ring_tmp_bo, m);
+
 	return 0;
+
 }
 
-static struct drm_info_list radeon_debugfs_ib_list[RADEON_IB_POOL_SIZE];
-static char radeon_debugfs_ib_names[RADEON_IB_POOL_SIZE][32];
-static unsigned radeon_debugfs_ib_idx[RADEON_IB_POOL_SIZE];
+static struct drm_info_list radeon_debugfs_sa_list[] = {
+        {"radeon_sa_info", &radeon_debugfs_sa_info, 0, NULL},
+};
+
 #endif
 
 int radeon_debugfs_ring_init(struct radeon_device *rdev, struct radeon_ring *ring)
@@ -622,21 +523,10 @@
 	return 0;
 }
 
-int radeon_debugfs_ib_init(struct radeon_device *rdev)
+int radeon_debugfs_sa_init(struct radeon_device *rdev)
 {
 #if defined(CONFIG_DEBUG_FS)
-	unsigned i;
-
-	for (i = 0; i < RADEON_IB_POOL_SIZE; i++) {
-		sprintf(radeon_debugfs_ib_names[i], "radeon_ib_%04u", i);
-		radeon_debugfs_ib_idx[i] = i;
-		radeon_debugfs_ib_list[i].name = radeon_debugfs_ib_names[i];
-		radeon_debugfs_ib_list[i].show = &radeon_debugfs_ib_info;
-		radeon_debugfs_ib_list[i].driver_features = 0;
-		radeon_debugfs_ib_list[i].data = &radeon_debugfs_ib_idx[i];
-	}
-	return radeon_debugfs_add_files(rdev, radeon_debugfs_ib_list,
-					RADEON_IB_POOL_SIZE);
+	return radeon_debugfs_add_files(rdev, radeon_debugfs_sa_list, 1);
 #else
 	return 0;
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_sa.c b/drivers/gpu/drm/radeon/radeon_sa.c
index 8fbfe69..c3ac7f4 100644
--- a/drivers/gpu/drm/radeon/radeon_sa.c
+++ b/drivers/gpu/drm/radeon/radeon_sa.c
@@ -27,20 +27,42 @@
  * Authors:
  *    Jerome Glisse <glisse@freedesktop.org>
  */
+/* Algorithm:
+ *
+ * We store the last allocated bo in "hole", we always try to allocate
+ * after the last allocated bo. Principle is that in a linear GPU ring
+ * progression was is after last is the oldest bo we allocated and thus
+ * the first one that should no longer be in use by the GPU.
+ *
+ * If it's not the case we skip over the bo after last to the closest
+ * done bo if such one exist. If none exist and we are not asked to
+ * block we report failure to allocate.
+ *
+ * If we are asked to block we wait on all the oldest fence of all
+ * rings. We just wait for any of those fence to complete.
+ */
 #include "drmP.h"
 #include "drm.h"
 #include "radeon.h"
 
+static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo);
+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)
 {
-	int r;
+	int i, r;
 
+	spin_lock_init(&sa_manager->lock);
 	sa_manager->bo = NULL;
 	sa_manager->size = size;
 	sa_manager->domain = domain;
-	INIT_LIST_HEAD(&sa_manager->sa_bo);
+	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,
 			     RADEON_GEM_DOMAIN_CPU, &sa_manager->bo);
@@ -57,11 +79,15 @@
 {
 	struct radeon_sa_bo *sa_bo, *tmp;
 
-	if (!list_empty(&sa_manager->sa_bo)) {
-		dev_err(rdev->dev, "sa_manager is not empty, clearing anyway\n");
+	if (!list_empty(&sa_manager->olist)) {
+		sa_manager->hole = &sa_manager->olist,
+		radeon_sa_bo_try_free(sa_manager);
+		if (!list_empty(&sa_manager->olist)) {
+			dev_err(rdev->dev, "sa_manager is not empty, clearing anyway\n");
+		}
 	}
-	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->sa_bo, list) {
-		list_del_init(&sa_bo->list);
+	list_for_each_entry_safe(sa_bo, tmp, &sa_manager->olist, olist) {
+		radeon_sa_bo_remove_locked(sa_bo);
 	}
 	radeon_bo_unref(&sa_manager->bo);
 	sa_manager->size = 0;
@@ -113,77 +139,248 @@
 	return r;
 }
 
-/*
- * Principe is simple, we keep a list of sub allocation in offset
- * order (first entry has offset == 0, last entry has the highest
- * offset).
- *
- * When allocating new object we first check if there is room at
- * the end total_size - (last_object_offset + last_object_size) >=
- * alloc_size. If so we allocate new object there.
- *
- * When there is not enough room at the end, we start waiting for
- * each sub object until we reach object_offset+object_size >=
- * alloc_size, this object then become the sub object we return.
- *
- * Alignment can't be bigger than page size
- */
+static void radeon_sa_bo_remove_locked(struct radeon_sa_bo *sa_bo)
+{
+	struct radeon_sa_manager *sa_manager = sa_bo->manager;
+	if (sa_manager->hole == &sa_bo->olist) {
+		sa_manager->hole = sa_bo->olist.prev;
+	}
+	list_del_init(&sa_bo->olist);
+	list_del_init(&sa_bo->flist);
+	radeon_fence_unref(&sa_bo->fence);
+	kfree(sa_bo);
+}
+
+static void radeon_sa_bo_try_free(struct radeon_sa_manager *sa_manager)
+{
+	struct radeon_sa_bo *sa_bo, *tmp;
+
+	if (sa_manager->hole->next == &sa_manager->olist)
+		return;
+
+	sa_bo = list_entry(sa_manager->hole->next, struct radeon_sa_bo, olist);
+	list_for_each_entry_safe_from(sa_bo, tmp, &sa_manager->olist, olist) {
+		if (sa_bo->fence == NULL || !radeon_fence_signaled(sa_bo->fence)) {
+			return;
+		}
+		radeon_sa_bo_remove_locked(sa_bo);
+	}
+}
+
+static inline unsigned radeon_sa_bo_hole_soffset(struct radeon_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole != &sa_manager->olist) {
+		return list_entry(hole, struct radeon_sa_bo, olist)->eoffset;
+	}
+	return 0;
+}
+
+static inline unsigned radeon_sa_bo_hole_eoffset(struct radeon_sa_manager *sa_manager)
+{
+	struct list_head *hole = sa_manager->hole;
+
+	if (hole->next != &sa_manager->olist) {
+		return list_entry(hole->next, struct radeon_sa_bo, olist)->soffset;
+	}
+	return sa_manager->size;
+}
+
+static bool radeon_sa_bo_try_alloc(struct radeon_sa_manager *sa_manager,
+				   struct radeon_sa_bo *sa_bo,
+				   unsigned size, unsigned align)
+{
+	unsigned soffset, eoffset, wasted;
+
+	soffset = radeon_sa_bo_hole_soffset(sa_manager);
+	eoffset = radeon_sa_bo_hole_eoffset(sa_manager);
+	wasted = (align - (soffset % align)) % align;
+
+	if ((eoffset - soffset) >= (size + wasted)) {
+		soffset += wasted;
+
+		sa_bo->manager = sa_manager;
+		sa_bo->soffset = soffset;
+		sa_bo->eoffset = soffset + size;
+		list_add(&sa_bo->olist, sa_manager->hole);
+		INIT_LIST_HEAD(&sa_bo->flist);
+		sa_manager->hole = &sa_bo->olist;
+		return true;
+	}
+	return false;
+}
+
+static bool radeon_sa_bo_next_hole(struct radeon_sa_manager *sa_manager,
+				   struct radeon_fence **fences,
+				   unsigned *tries)
+{
+	struct radeon_sa_bo *best_bo = NULL;
+	unsigned i, soffset, best, tmp;
+
+	/* if hole points to the end of the buffer */
+	if (sa_manager->hole->next == &sa_manager->olist) {
+		/* try again with its beginning */
+		sa_manager->hole = &sa_manager->olist;
+		return true;
+	}
+
+	soffset = radeon_sa_bo_hole_soffset(sa_manager);
+	/* to handle wrap around we add sa_manager->size */
+	best = sa_manager->size * 2;
+	/* go over all fence list and try to find the closest sa_bo
+	 * of the current last
+	 */
+	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+		struct radeon_sa_bo *sa_bo;
+
+		if (list_empty(&sa_manager->flist[i])) {
+			continue;
+		}
+
+		sa_bo = list_first_entry(&sa_manager->flist[i],
+					 struct radeon_sa_bo, flist);
+
+		if (!radeon_fence_signaled(sa_bo->fence)) {
+			fences[i] = sa_bo->fence;
+			continue;
+		}
+
+		/* limit the number of tries each ring gets */
+		if (tries[i] > 2) {
+			continue;
+		}
+
+		tmp = sa_bo->soffset;
+		if (tmp < soffset) {
+			/* wrap around, pretend it's after */
+			tmp += sa_manager->size;
+		}
+		tmp -= soffset;
+		if (tmp < best) {
+			/* this sa bo is the closest one */
+			best = tmp;
+			best_bo = sa_bo;
+		}
+	}
+
+	if (best_bo) {
+		++tries[best_bo->fence->ring];
+		sa_manager->hole = best_bo->olist.prev;
+
+		/* we knew that this one is signaled,
+		   so it's save to remote it */
+		radeon_sa_bo_remove_locked(best_bo);
+		return true;
+	}
+	return false;
+}
+
 int radeon_sa_bo_new(struct radeon_device *rdev,
 		     struct radeon_sa_manager *sa_manager,
-		     struct radeon_sa_bo *sa_bo,
-		     unsigned size, unsigned align)
+		     struct radeon_sa_bo **sa_bo,
+		     unsigned size, unsigned align, bool block)
 {
-	struct radeon_sa_bo *tmp;
-	struct list_head *head;
-	unsigned offset = 0, wasted = 0;
+	struct radeon_fence *fences[RADEON_NUM_RINGS];
+	unsigned tries[RADEON_NUM_RINGS];
+	int i, r = -ENOMEM;
 
 	BUG_ON(align > RADEON_GPU_PAGE_SIZE);
 	BUG_ON(size > sa_manager->size);
 
-	/* no one ? */
-	head = sa_manager->sa_bo.prev;
-	if (list_empty(&sa_manager->sa_bo)) {
-		goto out;
-	}
-
-	/* look for a hole big enough */
-	offset = 0;
-	list_for_each_entry(tmp, &sa_manager->sa_bo, list) {
-		/* room before this object ? */
-		if (offset < tmp->offset && (tmp->offset - offset) >= size) {
-			head = tmp->list.prev;
-			goto out;
-		}
-		offset = tmp->offset + tmp->size;
-		wasted = offset % align;
-		if (wasted) {
-			wasted = align - wasted;
-		}
-		offset += wasted;
-	}
-	/* room at the end ? */
-	head = sa_manager->sa_bo.prev;
-	tmp = list_entry(head, struct radeon_sa_bo, list);
-	offset = tmp->offset + tmp->size;
-	wasted = offset % align;
-	if (wasted) {
-		wasted = align - wasted;
-	}
-	offset += wasted;
-	if ((sa_manager->size - offset) < size) {
-		/* failed to find somethings big enough */
+	*sa_bo = kmalloc(sizeof(struct radeon_sa_bo), GFP_KERNEL);
+	if ((*sa_bo) == NULL) {
 		return -ENOMEM;
 	}
+	(*sa_bo)->manager = sa_manager;
+	(*sa_bo)->fence = NULL;
+	INIT_LIST_HEAD(&(*sa_bo)->olist);
+	INIT_LIST_HEAD(&(*sa_bo)->flist);
 
-out:
-	sa_bo->manager = sa_manager;
-	sa_bo->offset = offset;
-	sa_bo->size = size;
-	list_add(&sa_bo->list, head);
-	return 0;
+	spin_lock(&sa_manager->lock);
+	do {
+		for (i = 0; i < RADEON_NUM_RINGS; ++i) {
+			fences[i] = NULL;
+			tries[i] = 0;
+		}
+
+		do {
+			radeon_sa_bo_try_free(sa_manager);
+
+			if (radeon_sa_bo_try_alloc(sa_manager, *sa_bo,
+						   size, align)) {
+				spin_unlock(&sa_manager->lock);
+				return 0;
+			}
+
+			/* see if we can skip over some allocations */
+		} while (radeon_sa_bo_next_hole(sa_manager, fences, tries));
+
+		if (block) {
+			spin_unlock(&sa_manager->lock);
+			r = radeon_fence_wait_any(rdev, fences, false);
+			spin_lock(&sa_manager->lock);
+			if (r) {
+				/* if we have nothing to wait for we
+				   are practically out of memory */
+				if (r == -ENOENT) {
+					r = -ENOMEM;
+				}
+				goto out_err;
+			}
+		}
+	} while (block);
+
+out_err:
+	spin_unlock(&sa_manager->lock);
+	kfree(*sa_bo);
+	*sa_bo = NULL;
+	return r;
 }
 
-void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo *sa_bo)
+void radeon_sa_bo_free(struct radeon_device *rdev, struct radeon_sa_bo **sa_bo,
+		       struct radeon_fence *fence)
 {
-	list_del_init(&sa_bo->list);
+	struct radeon_sa_manager *sa_manager;
+
+	if (sa_bo == NULL || *sa_bo == NULL) {
+		return;
+	}
+
+	sa_manager = (*sa_bo)->manager;
+	spin_lock(&sa_manager->lock);
+	if (fence && fence->seq && fence->seq < RADEON_FENCE_NOTEMITED_SEQ) {
+		(*sa_bo)->fence = radeon_fence_ref(fence);
+		list_add_tail(&(*sa_bo)->flist,
+			      &sa_manager->flist[fence->ring]);
+	} else {
+		radeon_sa_bo_remove_locked(*sa_bo);
+	}
+	spin_unlock(&sa_manager->lock);
+	*sa_bo = NULL;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+void radeon_sa_bo_dump_debug_info(struct radeon_sa_manager *sa_manager,
+				  struct seq_file *m)
+{
+	struct radeon_sa_bo *i;
+
+	spin_lock(&sa_manager->lock);
+	list_for_each_entry(i, &sa_manager->olist, olist) {
+		if (&i->olist == sa_manager->hole) {
+			seq_printf(m, ">");
+		} else {
+			seq_printf(m, " ");
+		}
+		seq_printf(m, "[0x%08x 0x%08x] size %8d",
+			   i->soffset, i->eoffset, i->eoffset - i->soffset);
+		if (i->fence) {
+			seq_printf(m, " protected by 0x%016llx on ring %d",
+				   i->fence->seq, i->fence->ring);
+		}
+		seq_printf(m, "\n");
+	}
+	spin_unlock(&sa_manager->lock);
+}
+#endif
diff --git a/drivers/gpu/drm/radeon/radeon_semaphore.c b/drivers/gpu/drm/radeon/radeon_semaphore.c
index 930a08a..e2ace5d 100644
--- a/drivers/gpu/drm/radeon/radeon_semaphore.c
+++ b/drivers/gpu/drm/radeon/radeon_semaphore.c
@@ -31,121 +31,40 @@
 #include "drm.h"
 #include "radeon.h"
 
-static int radeon_semaphore_add_bo(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	uint64_t gpu_addr;
-	uint32_t *cpu_ptr;
-	int r, i;
-
-
-	bo = kmalloc(sizeof(struct radeon_semaphore_bo), GFP_KERNEL);
-	if (bo == NULL) {
-		return -ENOMEM;
-	}
-	INIT_LIST_HEAD(&bo->free);
-	INIT_LIST_HEAD(&bo->list);
-	bo->nused = 0;
-
-	r = radeon_ib_get(rdev, 0, &bo->ib, RADEON_SEMAPHORE_BO_SIZE);
-	if (r) {
-		dev_err(rdev->dev, "failed to get a bo after 5 retry\n");
-		kfree(bo);
-		return r;
-	}
-	gpu_addr = rdev->ib_pool.sa_manager.gpu_addr;
-	gpu_addr += bo->ib->sa_bo.offset;
-	cpu_ptr = rdev->ib_pool.sa_manager.cpu_ptr;
-	cpu_ptr += (bo->ib->sa_bo.offset >> 2);
-	for (i = 0; i < (RADEON_SEMAPHORE_BO_SIZE/8); i++) {
-		bo->semaphores[i].gpu_addr = gpu_addr;
-		bo->semaphores[i].cpu_ptr = cpu_ptr;
-		bo->semaphores[i].bo = bo;
-		list_add_tail(&bo->semaphores[i].list, &bo->free);
-		gpu_addr += 8;
-		cpu_ptr += 2;
-	}
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_add_tail(&bo->list, &rdev->semaphore_drv.bo);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-	return 0;
-}
-
-static void radeon_semaphore_del_bo_locked(struct radeon_device *rdev,
-					   struct radeon_semaphore_bo *bo)
-{
-	radeon_sa_bo_free(rdev, &bo->ib->sa_bo);
-	radeon_fence_unref(&bo->ib->fence);
-	list_del(&bo->list);
-	kfree(bo);
-}
-
-void radeon_semaphore_shrink_locked(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-
-	if (list_empty(&rdev->semaphore_drv.bo)) {
-		return;
-	}
-	/* only shrink if first bo has free semaphore */
-	bo = list_first_entry(&rdev->semaphore_drv.bo, struct radeon_semaphore_bo, list);
-	if (list_empty(&bo->free)) {
-		return;
-	}
-	list_for_each_entry_safe_continue(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (bo->nused)
-			continue;
-		radeon_semaphore_del_bo_locked(rdev, bo);
-	}
-}
 
 int radeon_semaphore_create(struct radeon_device *rdev,
 			    struct radeon_semaphore **semaphore)
 {
-	struct radeon_semaphore_bo *bo;
-	unsigned long irq_flags;
-	bool do_retry = true;
 	int r;
 
-retry:
-	*semaphore = NULL;
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	list_for_each_entry(bo, &rdev->semaphore_drv.bo, list) {
-		if (list_empty(&bo->free))
-			continue;
-		*semaphore = list_first_entry(&bo->free, struct radeon_semaphore, list);
-		(*semaphore)->cpu_ptr[0] = 0;
-		(*semaphore)->cpu_ptr[1] = 0;
-		list_del(&(*semaphore)->list);
-		bo->nused++;
-		break;
-	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-
+	*semaphore = kmalloc(sizeof(struct radeon_semaphore), GFP_KERNEL);
 	if (*semaphore == NULL) {
-		if (do_retry) {
-			do_retry = false;
-			r = radeon_semaphore_add_bo(rdev);
-			if (r)
-				return r;
-			goto retry;
-		}
 		return -ENOMEM;
 	}
-
+	r = radeon_sa_bo_new(rdev, &rdev->ring_tmp_bo,
+			     &(*semaphore)->sa_bo, 8, 8, true);
+	if (r) {
+		kfree(*semaphore);
+		*semaphore = NULL;
+		return r;
+	}
+	(*semaphore)->waiters = 0;
+	(*semaphore)->gpu_addr = radeon_sa_bo_gpu_addr((*semaphore)->sa_bo);
+	*((uint64_t*)radeon_sa_bo_cpu_addr((*semaphore)->sa_bo)) = 0;
 	return 0;
 }
 
 void radeon_semaphore_emit_signal(struct radeon_device *rdev, int ring,
 			          struct radeon_semaphore *semaphore)
 {
+	--semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, false);
 }
 
 void radeon_semaphore_emit_wait(struct radeon_device *rdev, int ring,
 			        struct radeon_semaphore *semaphore)
 {
+	++semaphore->waiters;
 	radeon_semaphore_ring_emit(rdev, ring, &rdev->ring[ring], semaphore, true);
 }
 
@@ -154,13 +73,17 @@
 				bool sync_to[RADEON_NUM_RINGS],
 				int dst_ring)
 {
-	int i, r;
+	int i = 0, r;
+
+	mutex_lock(&rdev->ring_lock);
+	r = radeon_ring_alloc(rdev, &rdev->ring[dst_ring], RADEON_NUM_RINGS * 8);
+	if (r) {
+		goto error;
+	}
 
 	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		unsigned num_ops = i == dst_ring ? RADEON_NUM_RINGS : 1;
-
-		/* don't lock unused rings */
-		if (!sync_to[i] && i != dst_ring)
+		/* no need to sync to our own or unused rings */
+		if (!sync_to[i] || i == dst_ring)
 			continue;
 
 		/* prevent GPU deadlocks */
@@ -170,28 +93,19 @@
 			goto error;
 		}
 
-                r = radeon_ring_lock(rdev, &rdev->ring[i], num_ops * 8);
-                if (r)
+		r = radeon_ring_alloc(rdev, &rdev->ring[i], 8);
+		if (r) {
 			goto error;
-	}
-
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-		/* no need to sync to our own or unused rings */
-		if (!sync_to[i] || i == dst_ring)
-                        continue;
+		}
 
 		radeon_semaphore_emit_signal(rdev, i, semaphore);
 		radeon_semaphore_emit_wait(rdev, dst_ring, semaphore);
+
+		radeon_ring_commit(rdev, &rdev->ring[i]);
 	}
 
-	for (i = 0; i < RADEON_NUM_RINGS; ++i) {
-
-		/* don't unlock unused rings */
-		if (!sync_to[i] && i != dst_ring)
-			continue;
-
-		radeon_ring_unlock_commit(rdev, &rdev->ring[i]);
-	}
+	radeon_ring_commit(rdev, &rdev->ring[dst_ring]);
+	mutex_unlock(&rdev->ring_lock);
 
 	return 0;
 
@@ -199,36 +113,25 @@
 	/* unlock all locks taken so far */
 	for (--i; i >= 0; --i) {
 		if (sync_to[i] || i == dst_ring) {
-			radeon_ring_unlock_undo(rdev, &rdev->ring[i]);
+			radeon_ring_undo(&rdev->ring[i]);
 		}
 	}
+	radeon_ring_undo(&rdev->ring[dst_ring]);
+	mutex_unlock(&rdev->ring_lock);
 	return r;
 }
 
 void radeon_semaphore_free(struct radeon_device *rdev,
-			   struct radeon_semaphore *semaphore)
+			   struct radeon_semaphore *semaphore,
+			   struct radeon_fence *fence)
 {
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	semaphore->bo->nused--;
-	list_add_tail(&semaphore->list, &semaphore->bo->free);
-	radeon_semaphore_shrink_locked(rdev);
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
-}
-
-void radeon_semaphore_driver_fini(struct radeon_device *rdev)
-{
-	struct radeon_semaphore_bo *bo, *n;
-	unsigned long irq_flags;
-
-	write_lock_irqsave(&rdev->semaphore_drv.lock, irq_flags);
-	/* we force to free everything */
-	list_for_each_entry_safe(bo, n, &rdev->semaphore_drv.bo, list) {
-		if (!list_empty(&bo->free)) {
-			dev_err(rdev->dev, "still in use semaphore\n");
-		}
-		radeon_semaphore_del_bo_locked(rdev, bo);
+	if (semaphore == NULL) {
+		return;
 	}
-	write_unlock_irqrestore(&rdev->semaphore_drv.lock, irq_flags);
+	if (semaphore->waiters > 0) {
+		dev_err(rdev->dev, "semaphore %p has more waiters than signalers,"
+			" hardware lockup imminent!\n", semaphore);
+	}
+	radeon_sa_bo_free(rdev, &semaphore->sa_bo, fence);
+	kfree(semaphore);
 }
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index dc5dcf4..b057387 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -317,7 +317,7 @@
 
 out_cleanup:
 	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore);
+		radeon_semaphore_free(rdev, semaphore, NULL);
 
 	if (fence1)
 		radeon_fence_unref(&fence1);
@@ -437,7 +437,7 @@
 
 out_cleanup:
 	if (semaphore)
-		radeon_semaphore_free(rdev, semaphore);
+		radeon_semaphore_free(rdev, semaphore, NULL);
 
 	if (fenceA)
 		radeon_fence_unref(&fenceA);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 5e3d54d..0f6aee8 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -223,6 +223,7 @@
 	struct radeon_device *rdev;
 	uint64_t old_start, new_start;
 	struct radeon_fence *fence, *old_fence;
+	struct radeon_semaphore *sem = NULL;
 	int r;
 
 	rdev = radeon_get_rdev(bo->bdev);
@@ -272,15 +273,16 @@
 		bool sync_to_ring[RADEON_NUM_RINGS] = { };
 		sync_to_ring[old_fence->ring] = true;
 
-		r = radeon_semaphore_create(rdev, &fence->semaphore);
+		r = radeon_semaphore_create(rdev, &sem);
 		if (r) {
 			radeon_fence_unref(&fence);
 			return r;
 		}
 
-		r = radeon_semaphore_sync_rings(rdev, fence->semaphore,
+		r = radeon_semaphore_sync_rings(rdev, sem,
 						sync_to_ring, fence->ring);
 		if (r) {
+			radeon_semaphore_free(rdev, sem, NULL);
 			radeon_fence_unref(&fence);
 			return r;
 		}
@@ -292,6 +294,7 @@
 	/* FIXME: handle copy error */
 	r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
 				      evict, no_wait_reserve, no_wait_gpu, new_mem);
+	radeon_semaphore_free(rdev, sem, fence);
 	radeon_fence_unref(&fence);
 	return r;
 }
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index a8b0016..40f82e2 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -1278,7 +1278,6 @@
 	rv770_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_agp_fini(rdev);
 	radeon_bo_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 779f0b6..be3b9fd 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -4109,7 +4109,6 @@
 	si_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
-	radeon_semaphore_driver_fini(rdev);
 	radeon_fence_driver_fini(rdev);
 	radeon_bo_fini(rdev);
 	radeon_atombios_fini(rdev);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 10a5f37..efd1249 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1309,8 +1309,8 @@
 				/* Mapping support (drm_vm.h) */
 extern int drm_mmap(struct file *filp, struct vm_area_struct *vma);
 extern int drm_mmap_locked(struct file *filp, struct vm_area_struct *vma);
-extern void drm_vm_open_locked(struct vm_area_struct *vma);
-extern void drm_vm_close_locked(struct vm_area_struct *vma);
+extern void drm_vm_open_locked(struct drm_device *dev, struct vm_area_struct *vma);
+extern void drm_vm_close_locked(struct drm_device *dev, struct vm_area_struct *vma);
 extern unsigned int drm_poll(struct file *filp, struct poll_table_struct *wait);
 
 				/* Memory management support (drm_memory.h) */
diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h
index 7c491b4..5805686 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -926,7 +926,6 @@
 };
 
 /* drm_radeon_cs_reloc.flags */
-#define RADEON_RELOC_DONT_SYNC		0x01
 
 struct drm_radeon_cs_reloc {
 	uint32_t		handle;