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

Pull main drm updates from Dave Airlie:
 "This is the main merge window request for the drm.

  It's big, but jam packed will lots of features and of course 0
  regressions.  (okay maybe there'll be one).

  Highlights:

   - new KMS drivers for server GPU chipsets: ast, mgag200 and cirrus
     (qemu only).  These drivers use the generic modesetting drivers.

   - initial prime/dma-buf support for i915, nouveau, radeon, udl and
     exynos

   - switcheroo audio support: so GPUs with HDMI can turn off the sound
     driver without crashing stuff.

   - There are some patches drifting outside drivers/gpu into x86 and
     EFI for better handling of multiple video adapters in Apple Macs,
     they've got correct acks except one trivial fixup.

   - Core:
	edid parser has better DMT and reduced blanking support,
	crtc properties,
	plane properties,

   - Drivers:
	exynos: add 2D core accel support, prime support, hdmi features
	intel: more Haswell support, initial Valleyview support, more
	    hdmi infoframe fixes, update MAINTAINERS for Daniel, lots of
	    cleanups and fixes
	radeon: more HDMI audio support, improved GPU lockup recovery
	    support, remove nested mutexes, less memory copying on PCIE, fix
	    bus master enable race (kexec), improved fence handling
	gma500: cleanups, 1080p support, acpi fixes
	nouveau: better nva3 memory reclocking, kepler accel (needs
	    external firmware rip), async buffer moves on nv84+ hw.

  I've some more dma-buf patches that rely on the dma-buf merge for vmap
  stuff, and I've a few fixes building up, but I'd decided I'd better
  get rid of the main pull sooner rather than later, so the audio guys
  are also unblocked."

Fix up trivial conflict due to some duplicated changes in
drivers/gpu/drm/i915/intel_ringbuffer.c

* 'drm-core-next' of git://people.freedesktop.org/~airlied/linux: (605 commits)
  drm/nouveau/nvd9: Fix GPIO initialisation sequence.
  drm/nouveau: Unregister switcheroo client on exit
  drm/nouveau: Check dsm on switcheroo unregister
  drm/nouveau: fix a minor annoyance in an output string
  drm/nouveau: turn a BUG into a WARN
  drm/nv50: decode PGRAPH DATA_ERROR = 0x24
  drm/nouveau/disp: fix dithering not being enabled on some eDP macbooks
  drm/nvd9/copy: initialise copy engine, seems to work like nvc0
  drm/nvc0/ttm: use copy engines for async buffer moves
  drm/nva3/ttm: use copy engine for async buffer moves
  drm/nv98/ttm: add in a (disabled) crypto engine buffer copy method
  drm/nv84/ttm: use crypto engine for async buffer copies
  drm/nouveau/ttm: untangle code to support accelerated buffer moves
  drm/nouveau/fbcon: use fence for sync, rather than notifier
  drm/nv98/crypt: non-stub implementation of the engine hooks
  drm/nouveau/fifo: turn all fifo modules into engine modules
  drm/nv50/graph: remove ability to do interrupt-driven context switching
  drm/nv50: remove manual context unload on context destruction
  drm/nv50: remove execution engine context saves on suspend
  drm/nv50/fifo: use hardware channel kickoff functionality
  ...

1 files changed, 334 insertions, 391 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 62892a826ed..b59b6d5b758 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -53,9 +53,35 @@ static inline int ring_space(struct intel_ring_buffer *ring)
 }
 
 static int
-render_ring_flush(struct intel_ring_buffer *ring,
-		  u32	invalidate_domains,
-		  u32	flush_domains)
+gen2_render_ring_flush(struct intel_ring_buffer *ring,
+		       u32	invalidate_domains,
+		       u32	flush_domains)
+{
+	u32 cmd;
+	int ret;
+
+	cmd = MI_FLUSH;
+	if (((invalidate_domains|flush_domains) & I915_GEM_DOMAIN_RENDER) == 0)
+		cmd |= MI_NO_WRITE_FLUSH;
+
+	if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
+		cmd |= MI_READ_FLUSH;
+
+	ret = intel_ring_begin(ring, 2);
+	if (ret)
+		return ret;
+
+	intel_ring_emit(ring, cmd);
+	intel_ring_emit(ring, MI_NOOP);
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
+static int
+gen4_render_ring_flush(struct intel_ring_buffer *ring,
+		       u32	invalidate_domains,
+		       u32	flush_domains)
 {
 	struct drm_device *dev = ring->dev;
 	u32 cmd;
@@ -90,17 +116,8 @@ render_ring_flush(struct intel_ring_buffer *ring,
 	 */
 
 	cmd = MI_FLUSH | MI_NO_WRITE_FLUSH;
-	if ((invalidate_domains|flush_domains) &
-	    I915_GEM_DOMAIN_RENDER)
+	if ((invalidate_domains|flush_domains) & I915_GEM_DOMAIN_RENDER)
 		cmd &= ~MI_NO_WRITE_FLUSH;
-	if (INTEL_INFO(dev)->gen < 4) {
-		/*
-		 * On the 965, the sampler cache always gets flushed
-		 * and this bit is reserved.
-		 */
-		if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
-			cmd |= MI_READ_FLUSH;
-	}
 	if (invalidate_domains & I915_GEM_DOMAIN_INSTRUCTION)
 		cmd |= MI_EXE_FLUSH;
 
@@ -290,9 +307,9 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
-	if ((I915_READ_CTL(ring) & RING_VALID) == 0 ||
-	    I915_READ_START(ring) != obj->gtt_offset ||
-	    (I915_READ_HEAD(ring) & HEAD_ADDR) != 0) {
+	if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 &&
+		     I915_READ_START(ring) == obj->gtt_offset &&
+		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
 				"ctl %08x head %08x tail %08x start %08x\n",
 				ring->name,
@@ -384,12 +401,11 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 	int ret = init_ring_common(ring);
 
 	if (INTEL_INFO(dev)->gen > 3) {
-		int mode = VS_TIMER_DISPATCH << 16 | VS_TIMER_DISPATCH;
-		I915_WRITE(MI_MODE, mode);
+		I915_WRITE(MI_MODE, _MASKED_BIT_ENABLE(VS_TIMER_DISPATCH));
 		if (IS_GEN7(dev))
 			I915_WRITE(GFX_MODE_GEN7,
-				   GFX_MODE_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
-				   GFX_MODE_ENABLE(GFX_REPLAY_MODE));
+				   _MASKED_BIT_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) |
+				   _MASKED_BIT_ENABLE(GFX_REPLAY_MODE));
 	}
 
 	if (INTEL_INFO(dev)->gen >= 5) {
@@ -398,7 +414,6 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 			return ret;
 	}
 
-
 	if (IS_GEN6(dev)) {
 		/* From the Sandybridge PRM, volume 1 part 3, page 24:
 		 * "If this bit is set, STCunit will have LRA as replacement
@@ -406,13 +421,11 @@ static int init_render_ring(struct intel_ring_buffer *ring)
 		 *  policy is not supported."
 		 */
 		I915_WRITE(CACHE_MODE_0,
-			   CM0_STC_EVICT_DISABLE_LRA_SNB << CM0_MASK_SHIFT);
+			   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
 	}
 
-	if (INTEL_INFO(dev)->gen >= 6) {
-		I915_WRITE(INSTPM,
-			   INSTPM_FORCE_ORDERING << 16 | INSTPM_FORCE_ORDERING);
-	}
+	if (INTEL_INFO(dev)->gen >= 6)
+		I915_WRITE(INSTPM, _MASKED_BIT_ENABLE(INSTPM_FORCE_ORDERING));
 
 	return ret;
 }
@@ -483,21 +496,30 @@ gen6_add_request(struct intel_ring_buffer *ring,
  * @seqno - seqno which the waiter will block on
  */
 static int
-intel_ring_sync(struct intel_ring_buffer *waiter,
-		struct intel_ring_buffer *signaller,
-		int ring,
-		u32 seqno)
+gen6_ring_sync(struct intel_ring_buffer *waiter,
+	       struct intel_ring_buffer *signaller,
+	       u32 seqno)
 {
 	int ret;
 	u32 dw1 = MI_SEMAPHORE_MBOX |
 		  MI_SEMAPHORE_COMPARE |
 		  MI_SEMAPHORE_REGISTER;
 
+	/* Throughout all of the GEM code, seqno passed implies our current
+	 * seqno is >= the last seqno executed. However for hardware the
+	 * comparison is strictly greater than.
+	 */
+	seqno -= 1;
+
+	WARN_ON(signaller->semaphore_register[waiter->id] ==
+		MI_SEMAPHORE_SYNC_INVALID);
+
 	ret = intel_ring_begin(waiter, 4);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(waiter, dw1 | signaller->semaphore_register[ring]);
+	intel_ring_emit(waiter,
+			dw1 | signaller->semaphore_register[waiter->id]);
 	intel_ring_emit(waiter, seqno);
 	intel_ring_emit(waiter, 0);
 	intel_ring_emit(waiter, MI_NOOP);
@@ -506,47 +528,6 @@ intel_ring_sync(struct intel_ring_buffer *waiter,
 	return 0;
 }
 
-/* VCS->RCS (RVSYNC) or BCS->RCS (RBSYNC) */
-int
-render_ring_sync_to(struct intel_ring_buffer *waiter,
-		    struct intel_ring_buffer *signaller,
-		    u32 seqno)
-{
-	WARN_ON(signaller->semaphore_register[RCS] == MI_SEMAPHORE_SYNC_INVALID);
-	return intel_ring_sync(waiter,
-			       signaller,
-			       RCS,
-			       seqno);
-}
-
-/* RCS->VCS (VRSYNC) or BCS->VCS (VBSYNC) */
-int
-gen6_bsd_ring_sync_to(struct intel_ring_buffer *waiter,
-		      struct intel_ring_buffer *signaller,
-		      u32 seqno)
-{
-	WARN_ON(signaller->semaphore_register[VCS] == MI_SEMAPHORE_SYNC_INVALID);
-	return intel_ring_sync(waiter,
-			       signaller,
-			       VCS,
-			       seqno);
-}
-
-/* RCS->BCS (BRSYNC) or VCS->BCS (BVSYNC) */
-int
-gen6_blt_ring_sync_to(struct intel_ring_buffer *waiter,
-		      struct intel_ring_buffer *signaller,
-		      u32 seqno)
-{
-	WARN_ON(signaller->semaphore_register[BCS] == MI_SEMAPHORE_SYNC_INVALID);
-	return intel_ring_sync(waiter,
-			       signaller,
-			       BCS,
-			       seqno);
-}
-
-
-
 #define PIPE_CONTROL_FLUSH(ring__, addr__)					\
 do {									\
 	intel_ring_emit(ring__, GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE |		\
@@ -608,27 +589,6 @@ pc_render_add_request(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static int
-render_ring_add_request(struct intel_ring_buffer *ring,
-			u32 *result)
-{
-	u32 seqno = i915_gem_next_request_seqno(ring);
-	int ret;
-
-	ret = intel_ring_begin(ring, 4);
-	if (ret)
-		return ret;
-
-	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
-	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
-	intel_ring_emit(ring, seqno);
-	intel_ring_emit(ring, MI_USER_INTERRUPT);
-	intel_ring_advance(ring);
-
-	*result = seqno;
-	return 0;
-}
-
 static u32
 gen6_ring_get_seqno(struct intel_ring_buffer *ring)
 {
@@ -655,76 +615,115 @@ pc_render_get_seqno(struct intel_ring_buffer *ring)
 	return pc->cpu_page[0];
 }
 
-static void
-ironlake_enable_irq(drm_i915_private_t *dev_priv, u32 mask)
+static bool
+gen5_ring_get_irq(struct intel_ring_buffer *ring)
 {
-	dev_priv->gt_irq_mask &= ~mask;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-	POSTING_READ(GTIMR);
+	struct drm_device *dev = ring->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	if (!dev->irq_enabled)
+		return false;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (ring->irq_refcount++ == 0) {
+		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
+		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+		POSTING_READ(GTIMR);
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	return true;
 }
 
 static void
-ironlake_disable_irq(drm_i915_private_t *dev_priv, u32 mask)
+gen5_ring_put_irq(struct intel_ring_buffer *ring)
 {
-	dev_priv->gt_irq_mask |= mask;
-	I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
-	POSTING_READ(GTIMR);
+	struct drm_device *dev = ring->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (--ring->irq_refcount == 0) {
+		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
+		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+		POSTING_READ(GTIMR);
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
-static void
-i915_enable_irq(drm_i915_private_t *dev_priv, u32 mask)
+static bool
+i9xx_ring_get_irq(struct intel_ring_buffer *ring)
 {
-	dev_priv->irq_mask &= ~mask;
-	I915_WRITE(IMR, dev_priv->irq_mask);
-	POSTING_READ(IMR);
+	struct drm_device *dev = ring->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	if (!dev->irq_enabled)
+		return false;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (ring->irq_refcount++ == 0) {
+		dev_priv->irq_mask &= ~ring->irq_enable_mask;
+		I915_WRITE(IMR, dev_priv->irq_mask);
+		POSTING_READ(IMR);
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
+
+	return true;
 }
 
 static void
-i915_disable_irq(drm_i915_private_t *dev_priv, u32 mask)
+i9xx_ring_put_irq(struct intel_ring_buffer *ring)
 {
-	dev_priv->irq_mask |= mask;
-	I915_WRITE(IMR, dev_priv->irq_mask);
-	POSTING_READ(IMR);
+	struct drm_device *dev = ring->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
+	if (--ring->irq_refcount == 0) {
+		dev_priv->irq_mask |= ring->irq_enable_mask;
+		I915_WRITE(IMR, dev_priv->irq_mask);
+		POSTING_READ(IMR);
+	}
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
 static bool
-render_ring_get_irq(struct intel_ring_buffer *ring)
+i8xx_ring_get_irq(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
 
 	if (!dev->irq_enabled)
 		return false;
 
-	spin_lock(&ring->irq_lock);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		if (HAS_PCH_SPLIT(dev))
-			ironlake_enable_irq(dev_priv,
-					    GT_PIPE_NOTIFY | GT_USER_INTERRUPT);
-		else
-			i915_enable_irq(dev_priv, I915_USER_INTERRUPT);
+		dev_priv->irq_mask &= ~ring->irq_enable_mask;
+		I915_WRITE16(IMR, dev_priv->irq_mask);
+		POSTING_READ16(IMR);
 	}
-	spin_unlock(&ring->irq_lock);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
 }
 
 static void
-render_ring_put_irq(struct intel_ring_buffer *ring)
+i8xx_ring_put_irq(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
 
-	spin_lock(&ring->irq_lock);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		if (HAS_PCH_SPLIT(dev))
-			ironlake_disable_irq(dev_priv,
-					     GT_USER_INTERRUPT |
-					     GT_PIPE_NOTIFY);
-		else
-			i915_disable_irq(dev_priv, I915_USER_INTERRUPT);
+		dev_priv->irq_mask |= ring->irq_enable_mask;
+		I915_WRITE16(IMR, dev_priv->irq_mask);
+		POSTING_READ16(IMR);
 	}
-	spin_unlock(&ring->irq_lock);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 }
 
 void intel_ring_setup_status_page(struct intel_ring_buffer *ring)
@@ -776,7 +775,7 @@ bsd_ring_flush(struct intel_ring_buffer *ring,
 }
 
 static int
-ring_add_request(struct intel_ring_buffer *ring,
+i9xx_add_request(struct intel_ring_buffer *ring,
 		 u32 *result)
 {
 	u32 seqno;
@@ -799,10 +798,11 @@ ring_add_request(struct intel_ring_buffer *ring,
 }
 
 static bool
-gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
+gen6_ring_get_irq(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
 
 	if (!dev->irq_enabled)
 	       return false;
@@ -812,120 +812,87 @@ gen6_ring_get_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
 	 * blt/bsd rings on ivb. */
 	gen6_gt_force_wake_get(dev_priv);
 
-	spin_lock(&ring->irq_lock);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (ring->irq_refcount++ == 0) {
-		ring->irq_mask &= ~rflag;
-		I915_WRITE_IMR(ring, ring->irq_mask);
-		ironlake_enable_irq(dev_priv, gflag);
+		I915_WRITE_IMR(ring, ~ring->irq_enable_mask);
+		dev_priv->gt_irq_mask &= ~ring->irq_enable_mask;
+		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+		POSTING_READ(GTIMR);
 	}
-	spin_unlock(&ring->irq_lock);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	return true;
 }
 
 static void
-gen6_ring_put_irq(struct intel_ring_buffer *ring, u32 gflag, u32 rflag)
+gen6_ring_put_irq(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	unsigned long flags;
 
-	spin_lock(&ring->irq_lock);
+	spin_lock_irqsave(&dev_priv->irq_lock, flags);
 	if (--ring->irq_refcount == 0) {
-		ring->irq_mask |= rflag;
-		I915_WRITE_IMR(ring, ring->irq_mask);
-		ironlake_disable_irq(dev_priv, gflag);
+		I915_WRITE_IMR(ring, ~0);
+		dev_priv->gt_irq_mask |= ring->irq_enable_mask;
+		I915_WRITE(GTIMR, dev_priv->gt_irq_mask);
+		POSTING_READ(GTIMR);
 	}
-	spin_unlock(&ring->irq_lock);
+	spin_unlock_irqrestore(&dev_priv->irq_lock, flags);
 
 	gen6_gt_force_wake_put(dev_priv);
 }
 
-static bool
-bsd_ring_get_irq(struct intel_ring_buffer *ring)
+static int
+i965_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
 {
-	struct drm_device *dev = ring->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
-
-	if (!dev->irq_enabled)
-		return false;
+	int ret;
 
-	spin_lock(&ring->irq_lock);
-	if (ring->irq_refcount++ == 0) {
-		if (IS_G4X(dev))
-			i915_enable_irq(dev_priv, I915_BSD_USER_INTERRUPT);
-		else
-			ironlake_enable_irq(dev_priv, GT_BSD_USER_INTERRUPT);
-	}
-	spin_unlock(&ring->irq_lock);
+	ret = intel_ring_begin(ring, 2);
+	if (ret)
+		return ret;
 
-	return true;
-}
-static void
-bsd_ring_put_irq(struct intel_ring_buffer *ring)
-{
-	struct drm_device *dev = ring->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
+	intel_ring_emit(ring,
+			MI_BATCH_BUFFER_START |
+			MI_BATCH_GTT |
+			MI_BATCH_NON_SECURE_I965);
+	intel_ring_emit(ring, offset);
+	intel_ring_advance(ring);
 
-	spin_lock(&ring->irq_lock);
-	if (--ring->irq_refcount == 0) {
-		if (IS_G4X(dev))
-			i915_disable_irq(dev_priv, I915_BSD_USER_INTERRUPT);
-		else
-			ironlake_disable_irq(dev_priv, GT_BSD_USER_INTERRUPT);
-	}
-	spin_unlock(&ring->irq_lock);
+	return 0;
 }
 
 static int
-ring_dispatch_execbuffer(struct intel_ring_buffer *ring, u32 offset, u32 length)
+i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
+				u32 offset, u32 len)
 {
 	int ret;
 
-	ret = intel_ring_begin(ring, 2);
+	ret = intel_ring_begin(ring, 4);
 	if (ret)
 		return ret;
 
-	intel_ring_emit(ring,
-			MI_BATCH_BUFFER_START | (2 << 6) |
-			MI_BATCH_NON_SECURE_I965);
-	intel_ring_emit(ring, offset);
+	intel_ring_emit(ring, MI_BATCH_BUFFER);
+	intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
+	intel_ring_emit(ring, offset + len - 8);
+	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
 	return 0;
 }
 
 static int
-render_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
+i915_dispatch_execbuffer(struct intel_ring_buffer *ring,
 				u32 offset, u32 len)
 {
-	struct drm_device *dev = ring->dev;
 	int ret;
 
-	if (IS_I830(dev) || IS_845G(dev)) {
-		ret = intel_ring_begin(ring, 4);
-		if (ret)
-			return ret;
-
-		intel_ring_emit(ring, MI_BATCH_BUFFER);
-		intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
-		intel_ring_emit(ring, offset + len - 8);
-		intel_ring_emit(ring, 0);
-	} else {
-		ret = intel_ring_begin(ring, 2);
-		if (ret)
-			return ret;
+	ret = intel_ring_begin(ring, 2);
+	if (ret)
+		return ret;
 
-		if (INTEL_INFO(dev)->gen >= 4) {
-			intel_ring_emit(ring,
-					MI_BATCH_BUFFER_START | (2 << 6) |
-					MI_BATCH_NON_SECURE_I965);
-			intel_ring_emit(ring, offset);
-		} else {
-			intel_ring_emit(ring,
-					MI_BATCH_BUFFER_START | (2 << 6));
-			intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
-		}
-	}
+	intel_ring_emit(ring, MI_BATCH_BUFFER_START | MI_BATCH_GTT);
+	intel_ring_emit(ring, offset | MI_BATCH_NON_SECURE);
 	intel_ring_advance(ring);
 
 	return 0;
@@ -933,7 +900,6 @@ render_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 
 static void cleanup_status_page(struct intel_ring_buffer *ring)
 {
-	drm_i915_private_t *dev_priv = ring->dev->dev_private;
 	struct drm_i915_gem_object *obj;
 
 	obj = ring->status_page.obj;
@@ -944,14 +910,11 @@ static void cleanup_status_page(struct intel_ring_buffer *ring)
 	i915_gem_object_unpin(obj);
 	drm_gem_object_unreference(&obj->base);
 	ring->status_page.obj = NULL;
-
-	memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
 }
 
 static int init_status_page(struct intel_ring_buffer *ring)
 {
 	struct drm_device *dev = ring->dev;
-	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	int ret;
 
@@ -972,7 +935,6 @@ static int init_status_page(struct intel_ring_buffer *ring)
 	ring->status_page.gfx_addr = obj->gtt_offset;
 	ring->status_page.page_addr = kmap(obj->pages[0]);
 	if (ring->status_page.page_addr == NULL) {
-		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
 		goto err_unpin;
 	}
 	ring->status_page.obj = obj;
@@ -992,8 +954,8 @@ err:
 	return ret;
 }
 
-int intel_init_ring_buffer(struct drm_device *dev,
-			   struct intel_ring_buffer *ring)
+static int intel_init_ring_buffer(struct drm_device *dev,
+				  struct intel_ring_buffer *ring)
 {
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -1002,10 +964,9 @@ int intel_init_ring_buffer(struct drm_device *dev,
 	INIT_LIST_HEAD(&ring->active_list);
 	INIT_LIST_HEAD(&ring->request_list);
 	INIT_LIST_HEAD(&ring->gpu_write_list);
+	ring->size = 32 * PAGE_SIZE;
 
 	init_waitqueue_head(&ring->irq_queue);
-	spin_lock_init(&ring->irq_lock);
-	ring->irq_mask = ~0;
 
 	if (I915_NEED_GFX_HWS(dev)) {
 		ret = init_status_page(ring);
@@ -1026,20 +987,14 @@ int intel_init_ring_buffer(struct drm_device *dev,
 	if (ret)
 		goto err_unref;
 
-	ring->map.size = ring->size;
-	ring->map.offset = dev->agp->base + obj->gtt_offset;
-	ring->map.type = 0;
-	ring->map.flags = 0;
-	ring->map.mtrr = 0;
-
-	drm_core_ioremap_wc(&ring->map, dev);
-	if (ring->map.handle == NULL) {
+	ring->virtual_start = ioremap_wc(dev->agp->base + obj->gtt_offset,
+					 ring->size);
+	if (ring->virtual_start == NULL) {
 		DRM_ERROR("Failed to map ringbuffer.\n");
 		ret = -EINVAL;
 		goto err_unpin;
 	}
 
-	ring->virtual_start = ring->map.handle;
 	ret = ring->init(ring);
 	if (ret)
 		goto err_unmap;
@@ -1055,7 +1010,7 @@ int intel_init_ring_buffer(struct drm_device *dev,
 	return 0;
 
 err_unmap:
-	drm_core_ioremapfree(&ring->map, dev);
+	iounmap(ring->virtual_start);
 err_unpin:
 	i915_gem_object_unpin(obj);
 err_unref:
@@ -1083,7 +1038,7 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
 
 	I915_WRITE_CTL(ring, 0);
 
-	drm_core_ioremapfree(&ring->map, ring->dev);
+	iounmap(ring->virtual_start);
 
 	i915_gem_object_unpin(ring->obj);
 	drm_gem_object_unreference(&ring->obj->base);
@@ -1097,7 +1052,7 @@ void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring)
 
 static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
 {
-	unsigned int *virt;
+	uint32_t __iomem *virt;
 	int rem = ring->size - ring->tail;
 
 	if (ring->space < rem) {
@@ -1106,12 +1061,10 @@ static int intel_wrap_ring_buffer(struct intel_ring_buffer *ring)
 			return ret;
 	}
 
-	virt = (unsigned int *)(ring->virtual_start + ring->tail);
-	rem /= 8;
-	while (rem--) {
-		*virt++ = MI_NOOP;
-		*virt++ = MI_NOOP;
-	}
+	virt = ring->virtual_start + ring->tail;
+	rem /= 4;
+	while (rem--)
+		iowrite32(MI_NOOP, virt++);
 
 	ring->tail = 0;
 	ring->space = ring_space(ring);
@@ -1132,9 +1085,11 @@ static int intel_ring_wait_seqno(struct intel_ring_buffer *ring, u32 seqno)
 	was_interruptible = dev_priv->mm.interruptible;
 	dev_priv->mm.interruptible = false;
 
-	ret = i915_wait_request(ring, seqno, true);
+	ret = i915_wait_request(ring, seqno);
 
 	dev_priv->mm.interruptible = was_interruptible;
+	if (!ret)
+		i915_gem_retire_requests_ring(ring);
 
 	return ret;
 }
@@ -1208,15 +1163,12 @@ int intel_wait_ring_buffer(struct intel_ring_buffer *ring, int n)
 		return ret;
 
 	trace_i915_ring_wait_begin(ring);
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		/* With GEM the hangcheck timer should kick us out of the loop,
-		 * leaving it early runs the risk of corrupting GEM state (due
-		 * to running on almost untested codepaths). But on resume
-		 * timers don't work yet, so prevent a complete hang in that
-		 * case by choosing an insanely large timeout. */
-		end = jiffies + 60 * HZ;
-	else
-		end = jiffies + 3 * HZ;
+	/* With GEM the hangcheck timer should kick us out of the loop,
+	 * leaving it early runs the risk of corrupting GEM state (due
+	 * to running on almost untested codepaths). But on resume
+	 * timers don't work yet, so prevent a complete hang in that
+	 * case by choosing an insanely large timeout. */
+	end = jiffies + 60 * HZ;
 
 	do {
 		ring->head = I915_READ_HEAD(ring);
@@ -1268,48 +1220,14 @@ int intel_ring_begin(struct intel_ring_buffer *ring,
 
 void intel_ring_advance(struct intel_ring_buffer *ring)
 {
+	struct drm_i915_private *dev_priv = ring->dev->dev_private;
+
 	ring->tail &= ring->size - 1;
+	if (dev_priv->stop_rings & intel_ring_flag(ring))
+		return;
 	ring->write_tail(ring, ring->tail);
 }
 
-static const struct intel_ring_buffer render_ring = {
-	.name			= "render ring",
-	.id			= RCS,
-	.mmio_base		= RENDER_RING_BASE,
-	.size			= 32 * PAGE_SIZE,
-	.init			= init_render_ring,
-	.write_tail		= ring_write_tail,
-	.flush			= render_ring_flush,
-	.add_request		= render_ring_add_request,
-	.get_seqno		= ring_get_seqno,
-	.irq_get		= render_ring_get_irq,
-	.irq_put		= render_ring_put_irq,
-	.dispatch_execbuffer	= render_ring_dispatch_execbuffer,
-	.cleanup		= render_ring_cleanup,
-	.sync_to		= render_ring_sync_to,
-	.semaphore_register	= {MI_SEMAPHORE_SYNC_INVALID,
-				   MI_SEMAPHORE_SYNC_RV,
-				   MI_SEMAPHORE_SYNC_RB},
-	.signal_mbox		= {GEN6_VRSYNC, GEN6_BRSYNC},
-};
-
-/* ring buffer for bit-stream decoder */
-
-static const struct intel_ring_buffer bsd_ring = {
-	.name                   = "bsd ring",
-	.id			= VCS,
-	.mmio_base		= BSD_RING_BASE,
-	.size			= 32 * PAGE_SIZE,
-	.init			= init_ring_common,
-	.write_tail		= ring_write_tail,
-	.flush			= bsd_ring_flush,
-	.add_request		= ring_add_request,
-	.get_seqno		= ring_get_seqno,
-	.irq_get		= bsd_ring_get_irq,
-	.irq_put		= bsd_ring_put_irq,
-	.dispatch_execbuffer	= ring_dispatch_execbuffer,
-};
-
 
 static void gen6_bsd_ring_write_tail(struct intel_ring_buffer *ring,
 				     u32 value)
@@ -1372,77 +1290,8 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static bool
-gen6_render_ring_get_irq(struct intel_ring_buffer *ring)
-{
-	return gen6_ring_get_irq(ring,
-				 GT_USER_INTERRUPT,
-				 GEN6_RENDER_USER_INTERRUPT);
-}
-
-static void
-gen6_render_ring_put_irq(struct intel_ring_buffer *ring)
-{
-	return gen6_ring_put_irq(ring,
-				 GT_USER_INTERRUPT,
-				 GEN6_RENDER_USER_INTERRUPT);
-}
-
-static bool
-gen6_bsd_ring_get_irq(struct intel_ring_buffer *ring)
-{
-	return gen6_ring_get_irq(ring,
-				 GT_GEN6_BSD_USER_INTERRUPT,
-				 GEN6_BSD_USER_INTERRUPT);
-}
-
-static void
-gen6_bsd_ring_put_irq(struct intel_ring_buffer *ring)
-{
-	return gen6_ring_put_irq(ring,
-				 GT_GEN6_BSD_USER_INTERRUPT,
-				 GEN6_BSD_USER_INTERRUPT);
-}
-
-/* ring buffer for Video Codec for Gen6+ */
-static const struct intel_ring_buffer gen6_bsd_ring = {
-	.name			= "gen6 bsd ring",
-	.id			= VCS,
-	.mmio_base		= GEN6_BSD_RING_BASE,
-	.size			= 32 * PAGE_SIZE,
-	.init			= init_ring_common,
-	.write_tail		= gen6_bsd_ring_write_tail,
-	.flush			= gen6_ring_flush,
-	.add_request		= gen6_add_request,
-	.get_seqno		= gen6_ring_get_seqno,
-	.irq_get		= gen6_bsd_ring_get_irq,
-	.irq_put		= gen6_bsd_ring_put_irq,
-	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
-	.sync_to		= gen6_bsd_ring_sync_to,
-	.semaphore_register	= {MI_SEMAPHORE_SYNC_VR,
-				   MI_SEMAPHORE_SYNC_INVALID,
-				   MI_SEMAPHORE_SYNC_VB},
-	.signal_mbox		= {GEN6_RVSYNC, GEN6_BVSYNC},
-};
-
 /* Blitter support (SandyBridge+) */
 
-static bool
-blt_ring_get_irq(struct intel_ring_buffer *ring)
-{
-	return gen6_ring_get_irq(ring,
-				 GT_BLT_USER_INTERRUPT,
-				 GEN6_BLITTER_USER_INTERRUPT);
-}
-
-static void
-blt_ring_put_irq(struct intel_ring_buffer *ring)
-{
-	gen6_ring_put_irq(ring,
-			  GT_BLT_USER_INTERRUPT,
-			  GEN6_BLITTER_USER_INTERRUPT);
-}
-
 static int blt_ring_flush(struct intel_ring_buffer *ring,
 			  u32 invalidate, u32 flush)
 {
@@ -1464,42 +1313,63 @@ static int blt_ring_flush(struct intel_ring_buffer *ring,
 	return 0;
 }
 
-static const struct intel_ring_buffer gen6_blt_ring = {
-	.name			= "blt ring",
-	.id			= BCS,
-	.mmio_base		= BLT_RING_BASE,
-	.size			= 32 * PAGE_SIZE,
-	.init			= init_ring_common,
-	.write_tail		= ring_write_tail,
-	.flush			= blt_ring_flush,
-	.add_request		= gen6_add_request,
-	.get_seqno		= gen6_ring_get_seqno,
-	.irq_get		= blt_ring_get_irq,
-	.irq_put		= blt_ring_put_irq,
-	.dispatch_execbuffer	= gen6_ring_dispatch_execbuffer,
-	.sync_to		= gen6_blt_ring_sync_to,
-	.semaphore_register	= {MI_SEMAPHORE_SYNC_BR,
-				   MI_SEMAPHORE_SYNC_BV,
-				   MI_SEMAPHORE_SYNC_INVALID},
-	.signal_mbox		= {GEN6_RBSYNC, GEN6_VBSYNC},
-};
-
 int intel_init_render_ring_buffer(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 
-	*ring = render_ring;
+	ring->name = "render ring";
+	ring->id = RCS;
+	ring->mmio_base = RENDER_RING_BASE;
+
 	if (INTEL_INFO(dev)->gen >= 6) {
 		ring->add_request = gen6_add_request;
 		ring->flush = gen6_render_ring_flush;
-		ring->irq_get = gen6_render_ring_get_irq;
-		ring->irq_put = gen6_render_ring_put_irq;
+		ring->irq_get = gen6_ring_get_irq;
+		ring->irq_put = gen6_ring_put_irq;
+		ring->irq_enable_mask = GT_USER_INTERRUPT;
 		ring->get_seqno = gen6_ring_get_seqno;
+		ring->sync_to = gen6_ring_sync;
+		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_RV;
+		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_RB;
+		ring->signal_mbox[0] = GEN6_VRSYNC;
+		ring->signal_mbox[1] = GEN6_BRSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
+		ring->flush = gen4_render_ring_flush;
 		ring->get_seqno = pc_render_get_seqno;
+		ring->irq_get = gen5_ring_get_irq;
+		ring->irq_put = gen5_ring_put_irq;
+		ring->irq_enable_mask = GT_USER_INTERRUPT | GT_PIPE_NOTIFY;
+	} else {
+		ring->add_request = i9xx_add_request;
+		if (INTEL_INFO(dev)->gen < 4)
+			ring->flush = gen2_render_ring_flush;
+		else
+			ring->flush = gen4_render_ring_flush;
+		ring->get_seqno = ring_get_seqno;
+		if (IS_GEN2(dev)) {
+			ring->irq_get = i8xx_ring_get_irq;
+			ring->irq_put = i8xx_ring_put_irq;
+		} else {
+			ring->irq_get = i9xx_ring_get_irq;
+			ring->irq_put = i9xx_ring_put_irq;
+		}
+		ring->irq_enable_mask = I915_USER_INTERRUPT;
 	}
+	ring->write_tail = ring_write_tail;
+	if (INTEL_INFO(dev)->gen >= 6)
+		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
+	else if (INTEL_INFO(dev)->gen >= 4)
+		ring->dispatch_execbuffer = i965_dispatch_execbuffer;
+	else if (IS_I830(dev) || IS_845G(dev))
+		ring->dispatch_execbuffer = i830_dispatch_execbuffer;
+	else
+		ring->dispatch_execbuffer = i915_dispatch_execbuffer;
+	ring->init = init_render_ring;
+	ring->cleanup = render_ring_cleanup;
+
 
 	if (!I915_NEED_GFX_HWS(dev)) {
 		ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
@@ -1514,15 +1384,41 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
 
-	*ring = render_ring;
+	ring->name = "render ring";
+	ring->id = RCS;
+	ring->mmio_base = RENDER_RING_BASE;
+
 	if (INTEL_INFO(dev)->gen >= 6) {
-		ring->add_request = gen6_add_request;
-		ring->irq_get = gen6_render_ring_get_irq;
-		ring->irq_put = gen6_render_ring_put_irq;
-	} else if (IS_GEN5(dev)) {
-		ring->add_request = pc_render_add_request;
-		ring->get_seqno = pc_render_get_seqno;
+		/* non-kms not supported on gen6+ */
+		return -ENODEV;
+	}
+
+	/* Note: gem is not supported on gen5/ilk without kms (the corresponding
+	 * gem_init ioctl returns with -ENODEV). Hence we do not need to set up
+	 * the special gen5 functions. */
+	ring->add_request = i9xx_add_request;
+	if (INTEL_INFO(dev)->gen < 4)
+		ring->flush = gen2_render_ring_flush;
+	else
+		ring->flush = gen4_render_ring_flush;
+	ring->get_seqno = ring_get_seqno;
+	if (IS_GEN2(dev)) {
+		ring->irq_get = i8xx_ring_get_irq;
+		ring->irq_put = i8xx_ring_put_irq;
+	} else {
+		ring->irq_get = i9xx_ring_get_irq;
+		ring->irq_put = i9xx_ring_put_irq;
 	}
+	ring->irq_enable_mask = I915_USER_INTERRUPT;
+	ring->write_tail = ring_write_tail;
+	if (INTEL_INFO(dev)->gen >= 4)
+		ring->dispatch_execbuffer = i965_dispatch_execbuffer;
+	else if (IS_I830(dev) || IS_845G(dev))
+		ring->dispatch_execbuffer = i830_dispatch_execbuffer;
+	else
+		ring->dispatch_execbuffer = i915_dispatch_execbuffer;
+	ring->init = init_render_ring;
+	ring->cleanup = render_ring_cleanup;
 
 	if (!I915_NEED_GFX_HWS(dev))
 		ring->status_page.page_addr = dev_priv->status_page_dmah->vaddr;
@@ -1537,20 +1433,13 @@ int intel_render_ring_init_dri(struct drm_device *dev, u64 start, u32 size)
 	if (IS_I830(ring->dev))
 		ring->effective_size -= 128;
 
-	ring->map.offset = start;
-	ring->map.size = size;
-	ring->map.type = 0;
-	ring->map.flags = 0;
-	ring->map.mtrr = 0;
-
-	drm_core_ioremap_wc(&ring->map, dev);
-	if (ring->map.handle == NULL) {
+	ring->virtual_start = ioremap_wc(start, size);
+	if (ring->virtual_start == NULL) {
 		DRM_ERROR("can not ioremap virtual address for"
 			  " ring buffer\n");
 		return -ENOMEM;
 	}
 
-	ring->virtual_start = (void __force __iomem *)ring->map.handle;
 	return 0;
 }
 
@@ -1559,10 +1448,46 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring = &dev_priv->ring[VCS];
 
-	if (IS_GEN6(dev) || IS_GEN7(dev))
-		*ring = gen6_bsd_ring;
-	else
-		*ring = bsd_ring;
+	ring->name = "bsd ring";
+	ring->id = VCS;
+
+	ring->write_tail = ring_write_tail;
+	if (IS_GEN6(dev) || IS_GEN7(dev)) {
+		ring->mmio_base = GEN6_BSD_RING_BASE;
+		/* gen6 bsd needs a special wa for tail updates */
+		if (IS_GEN6(dev))
+			ring->write_tail = gen6_bsd_ring_write_tail;
+		ring->flush = gen6_ring_flush;
+		ring->add_request = gen6_add_request;
+		ring->get_seqno = gen6_ring_get_seqno;
+		ring->irq_enable_mask = GEN6_BSD_USER_INTERRUPT;
+		ring->irq_get = gen6_ring_get_irq;
+		ring->irq_put = gen6_ring_put_irq;
+		ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
+		ring->sync_to = gen6_ring_sync;
+		ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_VR;
+		ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_INVALID;
+		ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_VB;
+		ring->signal_mbox[0] = GEN6_RVSYNC;
+		ring->signal_mbox[1] = GEN6_BVSYNC;
+	} else {
+		ring->mmio_base = BSD_RING_BASE;
+		ring->flush = bsd_ring_flush;
+		ring->add_request = i9xx_add_request;
+		ring->get_seqno = ring_get_seqno;
+		if (IS_GEN5(dev)) {
+			ring->irq_enable_mask = GT_BSD_USER_INTERRUPT;
+			ring->irq_get = gen5_ring_get_irq;
+			ring->irq_put = gen5_ring_put_irq;
+		} else {
+			ring->irq_enable_mask = I915_BSD_USER_INTERRUPT;
+			ring->irq_get = i9xx_ring_get_irq;
+			ring->irq_put = i9xx_ring_put_irq;
+		}
+		ring->dispatch_execbuffer = i965_dispatch_execbuffer;
+	}
+	ring->init = init_ring_common;
+
 
 	return intel_init_ring_buffer(dev, ring);
 }
@@ -1572,7 +1497,25 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring = &dev_priv->ring[BCS];
 
-	*ring = gen6_blt_ring;
+	ring->name = "blitter ring";
+	ring->id = BCS;
+
+	ring->mmio_base = BLT_RING_BASE;
+	ring->write_tail = ring_write_tail;
+	ring->flush = blt_ring_flush;
+	ring->add_request = gen6_add_request;
+	ring->get_seqno = gen6_ring_get_seqno;
+	ring->irq_enable_mask = GEN6_BLITTER_USER_INTERRUPT;
+	ring->irq_get = gen6_ring_get_irq;
+	ring->irq_put = gen6_ring_put_irq;
+	ring->dispatch_execbuffer = gen6_ring_dispatch_execbuffer;
+	ring->sync_to = gen6_ring_sync;
+	ring->semaphore_register[0] = MI_SEMAPHORE_SYNC_BR;
+	ring->semaphore_register[1] = MI_SEMAPHORE_SYNC_BV;
+	ring->semaphore_register[2] = MI_SEMAPHORE_SYNC_INVALID;
+	ring->signal_mbox[0] = GEN6_RBSYNC;
+	ring->signal_mbox[1] = GEN6_VBSYNC;
+	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
 }