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

Pull DRM updates from Dave Airlie:
 "Like all good pull reqs this ends with a revert, so it must mean we
  tested it,

[ Ed. That's _one_ way of looking at it ]

  This pull is missing nouveau, Ben has been stuck trying to track down
  a very longstanding bug that revealed itself due to some other
  changes.  I've asked him to send you a direct pull request for nouveau
  once he cleans things up.  I'm away until Monday so don't want to
  delay things, you can make a decision on that when he sends it, I have
  my phone so I can ack things just not really merge much.

  It has one trivial conflict with your tree in armada_drv.c, and also
  the pull request contains some component changes that are already in
  your tree, the base tree from Russell went via Greg's tree already,
  but some stuff still shows up in here that doesn't when I merge my
  tree into yours.

  Otherwise all pretty standard graphics fare, one new driver and
  changes all over the place.

  New drivers:
   - sti kms driver for STMicroelectronics chipsets stih416 and stih407.

  core:
   - lots of cleanups to the drm core
   - DP MST helper code merged
   - universal cursor planes.
   - render nodes enabled by default

  panel:
   - better panel interfaces
   - new panel support
   - non-continuous cock advertising ability

  ttm:
   - shrinker fixes

  i915:
   - hopefully ditched UMS support
   - runtime pm fixes
   - psr tracking and locking - now enabled by default
   - userptr fixes
   - backlight brightness fixes
   - MST support merged
   - runtime PM for dpms
   - primary planes locking fixes
   - gen8 hw semaphore support
   - fbc fixes
   - runtime PM on SOix sleep state hw.
   - mmio base page flipping
   - lots of vlv/chv fixes.
   - universal cursor planes

  radeon:
   - Hawaii fixes
   - display scalar support for non-fixed mode displays
   - new firmware format support
   - dpm on more asics by default
   - GPUVM improvements
   - uncached and wc GTT buffers
   - BOs > visible VRAM

  exynos:
   - i80 interface support
   - module auto-loading
   - ipp driver consolidated.

  armada:
   - irq handling in crtc layer only
   - crtc renumbering
   - add component support
   - DT interaction changes.

  tegra:
   - load as module fixes
   - eDP bpp and sync polarity fixed
   - DSI non-continuous clock mode support
   - better support for importing buffers from nouveau

  msm:
   - mdp5/adq8084 v1.3 hw enablement
   - devicetree clk changse
   - ifc6410 board working

  tda998x:
   - component support
   - DT documentation update

  vmwgfx:
   - fix compat shader namespace"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (551 commits)
  Revert "drm: drop redundant drm_file->is_master"
  drm/panel: simple: Use devm_gpiod_get_optional()
  drm/dsi: Replace upcasting macro by function
  drm/panel: ld9040: Replace upcasting macro by function
  drm/exynos: dp: Modify driver to support drm_panel
  drm/exynos: Move DP setup into commit()
  drm/panel: simple: Add AUO B133HTN01 panel support
  drm/panel: simple: Support delays in panel functions
  drm/panel: simple: Add proper definition for prepare and unprepare
  drm/panel: s6e8aa0: Add proper definition for prepare and unprepare
  drm/panel: ld9040: Add proper definition for prepare and unprepare
  drm/tegra: Add support for panel prepare and unprepare routines
  drm/exynos: dsi: Add support for panel prepare and unprepare routines
  drm/exynos: dpi: Add support for panel prepare and unprepare routines
  drm/panel: simple: Add dummy prepare and unprepare routines
  drm/panel: s6e8aa0: Add dummy prepare and unprepare routines
  drm/panel: ld9040: Add dummy prepare and unprepare routines
  drm/panel: Provide convenience wrapper for .get_modes()
  drm/panel: add .prepare() and .unprepare() functions
  drm/panel: simple: Remove simple-panel compatible
  ...

1 files changed, 79 insertions, 11 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e72017bdcd7..ed5941078f9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -40,6 +40,32 @@ struct  intel_hw_status_page {
 #define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base))
 #define I915_WRITE_MODE(ring, val) I915_WRITE(RING_MI_MODE((ring)->mmio_base), val)
 
+/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
+ * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
+ */
+#define i915_semaphore_seqno_size sizeof(uint64_t)
+#define GEN8_SIGNAL_OFFSET(__ring, to)			     \
+	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
+	((__ring)->id * I915_NUM_RINGS * i915_semaphore_seqno_size) +	\
+	(i915_semaphore_seqno_size * (to)))
+
+#define GEN8_WAIT_OFFSET(__ring, from)			     \
+	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
+	((from) * I915_NUM_RINGS * i915_semaphore_seqno_size) + \
+	(i915_semaphore_seqno_size * (__ring)->id))
+
+#define GEN8_RING_SEMAPHORE_INIT do { \
+	if (!dev_priv->semaphore_obj) { \
+		break; \
+	} \
+	ring->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET(ring, RCS); \
+	ring->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET(ring, VCS); \
+	ring->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET(ring, BCS); \
+	ring->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET(ring, VECS); \
+	ring->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET(ring, VCS2); \
+	ring->semaphore.signal_ggtt[ring->id] = MI_SEMAPHORE_SYNC_INVALID; \
+	} while(0)
+
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
 	HANGCHECK_WAIT,
@@ -127,15 +153,55 @@ struct  intel_engine_cs {
 #define I915_DISPATCH_PINNED 0x2
 	void		(*cleanup)(struct intel_engine_cs *ring);
 
+	/* GEN8 signal/wait table - never trust comments!
+	 *	  signal to	signal to    signal to   signal to      signal to
+	 *	    RCS		   VCS          BCS        VECS		 VCS2
+	 *      --------------------------------------------------------------------
+	 *  RCS | NOP (0x00) | VCS (0x08) | BCS (0x10) | VECS (0x18) | VCS2 (0x20) |
+	 *	|-------------------------------------------------------------------
+	 *  VCS | RCS (0x28) | NOP (0x30) | BCS (0x38) | VECS (0x40) | VCS2 (0x48) |
+	 *	|-------------------------------------------------------------------
+	 *  BCS | RCS (0x50) | VCS (0x58) | NOP (0x60) | VECS (0x68) | VCS2 (0x70) |
+	 *	|-------------------------------------------------------------------
+	 * VECS | RCS (0x78) | VCS (0x80) | BCS (0x88) |  NOP (0x90) | VCS2 (0x98) |
+	 *	|-------------------------------------------------------------------
+	 * VCS2 | RCS (0xa0) | VCS (0xa8) | BCS (0xb0) | VECS (0xb8) | NOP  (0xc0) |
+	 *	|-------------------------------------------------------------------
+	 *
+	 * Generalization:
+	 *  f(x, y) := (x->id * NUM_RINGS * seqno_size) + (seqno_size * y->id)
+	 *  ie. transpose of g(x, y)
+	 *
+	 *	 sync from	sync from    sync from    sync from	sync from
+	 *	    RCS		   VCS          BCS        VECS		 VCS2
+	 *      --------------------------------------------------------------------
+	 *  RCS | NOP (0x00) | VCS (0x28) | BCS (0x50) | VECS (0x78) | VCS2 (0xa0) |
+	 *	|-------------------------------------------------------------------
+	 *  VCS | RCS (0x08) | NOP (0x30) | BCS (0x58) | VECS (0x80) | VCS2 (0xa8) |
+	 *	|-------------------------------------------------------------------
+	 *  BCS | RCS (0x10) | VCS (0x38) | NOP (0x60) | VECS (0x88) | VCS2 (0xb0) |
+	 *	|-------------------------------------------------------------------
+	 * VECS | RCS (0x18) | VCS (0x40) | BCS (0x68) |  NOP (0x90) | VCS2 (0xb8) |
+	 *	|-------------------------------------------------------------------
+	 * VCS2 | RCS (0x20) | VCS (0x48) | BCS (0x70) | VECS (0x98) |  NOP (0xc0) |
+	 *	|-------------------------------------------------------------------
+	 *
+	 * Generalization:
+	 *  g(x, y) := (y->id * NUM_RINGS * seqno_size) + (seqno_size * x->id)
+	 *  ie. transpose of f(x, y)
+	 */
 	struct {
 		u32	sync_seqno[I915_NUM_RINGS-1];
 
-		struct {
-			/* our mbox written by others */
-			u32		wait[I915_NUM_RINGS];
-			/* mboxes this ring signals to */
-			u32		signal[I915_NUM_RINGS];
-		} mbox;
+		union {
+			struct {
+				/* our mbox written by others */
+				u32		wait[I915_NUM_RINGS];
+				/* mboxes this ring signals to */
+				u32		signal[I915_NUM_RINGS];
+			} mbox;
+			u64		signal_ggtt[I915_NUM_RINGS];
+		};
 
 		/* AKA wait() */
 		int	(*sync_to)(struct intel_engine_cs *ring,
@@ -238,9 +304,11 @@ intel_ring_sync_index(struct intel_engine_cs *ring,
 	int idx;
 
 	/*
-	 * cs -> 0 = vcs, 1 = bcs
-	 * vcs -> 0 = bcs, 1 = cs,
-	 * bcs -> 0 = cs, 1 = vcs.
+	 * rcs -> 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
+	 * vcs -> 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
+	 * bcs -> 0 = vecs, 1 = vcs2. 2 = rcs, 3 = vcs;
+	 * vecs -> 0 = vcs2, 1 = rcs, 2 = vcs, 3 = bcs;
+	 * vcs2 -> 0 = rcs, 1 = vcs, 2 = bcs, 3 = vecs;
 	 */
 
 	idx = (other - ring) - 1;
@@ -318,9 +386,9 @@ int intel_init_vebox_ring_buffer(struct drm_device *dev);
 u64 intel_ring_get_active_head(struct intel_engine_cs *ring);
 void intel_ring_setup_status_page(struct intel_engine_cs *ring);
 
-static inline u32 intel_ring_get_tail(struct intel_engine_cs *ring)
+static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
 {
-	return ring->buffer->tail;
+	return ringbuf->tail;
 }
 
 static inline u32 intel_ring_get_seqno(struct intel_engine_cs *ring)