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

Pull drm updates from Dave Airlie:
 "Here's the main drm pull request for 4.7, it's been a busy one, and
  I've been a bit more distracted in real life this merge window.  Lots
  more ARM drivers, not sure if it'll ever end.  I think I've at least
  one more coming the next merge window.

  But changes are all over the place, support for AMD Polaris GPUs is in
  here, some missing GM108 support for nouveau (found in some Lenovos),
  a bunch of MST and skylake fixes.

  I've also noticed a few fixes from Arnd in my inbox, that I'll try and
  get in asap, but I didn't think they should hold this up.

  New drivers:
   - Hisilicon kirin display driver
   - Mediatek MT8173 display driver
   - ARC PGU - bitstreamer on Synopsys ARC SDP boards
   - Allwinner A13 initial RGB output driver
   - Analogix driver for DisplayPort IP found in exynos and rockchip

  DRM Core:
   - UAPI headers fixes and C++ safety
   - DRM connector reference counting
   - DisplayID mode parsing for Dell 5K monitors
   - Removal of struct_mutex from drivers
   - Connector registration cleanups
   - MST robustness fixes
   - MAINTAINERS updates
   - Lockless GEM object freeing
   - Generic fbdev deferred IO support

  panel:
   - Support for a bunch of new panels

  i915:
   - VBT refactoring
   - PLL computation cleanups
   - DSI support for BXT
   - Color manager support
   - More atomic patches
   - GEM improvements
   - GuC fw loading fixes
   - DP detection fixes
   - SKL GPU hang fixes
   - Lots of BXT fixes

  radeon/amdgpu:
   - Initial Polaris support
   - GPUVM/Scheduler/Clock/Power improvements
   - ASYNC pageflip support
   - New mesa feature support

  nouveau:
   - GM108 support
   - Power sensor support improvements
   - GR init + ucode fixes.
   - Use GPU provided topology information

  vmwgfx:
   - Add host messaging support

  gma500:
   - Some cleanups and fixes

  atmel:
   - Bridge support
   - Async atomic commit support

  fsl-dcu:
   - Timing controller for LCD support
   - Pixel clock polarity support

  rcar-du:
   - Misc fixes

  exynos:
   - Pipeline clock support
   - Exynoss4533 SoC support
   - HW trigger mode support
   - export HDMI_PHY clock
   - DECON5433 fixes
   - Use generic prime functions
   - use DMA mapping APIs

  rockchip:
   - Lots of little fixes

  vc4:
   - Render node support
   - Gamma ramp support
   - DPI output support

  msm:
   - Mostly cleanups and fixes
   - Conversion to generic struct fence

  etnaviv:
   - Fix for prime buffer handling
   - Allow hangcheck to be coalesced with other wakeups

  tegra:
   - Gamme table size fix"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (1050 commits)
  drm/edid: add displayid detailed 1 timings to the modelist. (v1.1)
  drm/edid: move displayid validation to it's own function.
  drm/displayid: Iterate over all DisplayID blocks
  drm/edid: move displayid tiled block parsing into separate function.
  drm: Nuke ->vblank_disable_allowed
  drm/vmwgfx: Report vmwgfx version to vmware.log
  drm/vmwgfx: Add VMWare host messaging capability
  drm/vmwgfx: Kill some lockdep warnings
  drm/nouveau/gr/gf100-: fix race condition in fecs/gpccs ucode
  drm/nouveau/core: recognise GM108 chipsets
  drm/nouveau/gr/gm107-: fix touching non-existent ppcs in attrib cb setup
  drm/nouveau/gr/gk104-: share implementation of ppc exception init
  drm/nouveau/gr/gk104-: move rop_active_fbps init to nonctx
  drm/nouveau/bios/pll: check BIT table version before trying to parse it
  drm/nouveau/bios/pll: prevent oops when limits table can't be parsed
  drm/nouveau/volt/gk104: round up in gk104_volt_set
  drm/nouveau/fb/gm200: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gk20a,gm20b: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gf100-: allocate mmu debug buffers
  drm/nouveau/fb: allow chipset-specific actions for oneinit()
  ...

1 files changed, 61 insertions, 67 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 566b0ae10ce0..2ade194bbea9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -52,34 +52,32 @@ struct  intel_hw_status_page {
 /* 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_semaphore_seqno_size sizeof(uint64_t)
+#define GEN8_SEMAPHORE_OFFSET(__from, __to)			     \
+	(((__from) * I915_NUM_ENGINES  + (__to)) * gen8_semaphore_seqno_size)
 #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)))
-
+	 GEN8_SEMAPHORE_OFFSET((__ring)->id, (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))
+	 GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
 
-#define GEN8_RING_SEMAPHORE_INIT do { \
+#define GEN8_RING_SEMAPHORE_INIT(e) 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; \
+	(e)->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET((e), RCS); \
+	(e)->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET((e), VCS); \
+	(e)->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET((e), BCS); \
+	(e)->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET((e), VECS); \
+	(e)->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET((e), VCS2); \
+	(e)->semaphore.signal_ggtt[(e)->id] = MI_SEMAPHORE_SYNC_INVALID; \
 	} while(0)
 
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
 	HANGCHECK_WAIT,
 	HANGCHECK_ACTIVE,
-	HANGCHECK_ACTIVE_LOOP,
 	HANGCHECK_KICK,
 	HANGCHECK_HUNG,
 };
@@ -88,8 +86,8 @@ enum intel_ring_hangcheck_action {
 
 struct intel_ring_hangcheck {
 	u64 acthd;
-	u64 max_acthd;
 	u32 seqno;
+	unsigned user_interrupts;
 	int score;
 	enum intel_ring_hangcheck_action action;
 	int deadlock;
@@ -101,7 +99,7 @@ struct intel_ringbuffer {
 	void __iomem *virtual_start;
 	struct i915_vma *vma;
 
-	struct intel_engine_cs *ring;
+	struct intel_engine_cs *engine;
 	struct list_head link;
 
 	u32 head;
@@ -125,7 +123,7 @@ struct intel_ringbuffer {
 };
 
 struct	intel_context;
-struct drm_i915_reg_descriptor;
+struct drm_i915_reg_table;
 
 /*
  * we use a single page to load ctx workarounds so all of these
@@ -148,14 +146,14 @@ struct  i915_ctx_workarounds {
 
 struct  intel_engine_cs {
 	const char	*name;
-	enum intel_ring_id {
+	enum intel_engine_id {
 		RCS = 0,
 		BCS,
 		VCS,
 		VCS2,	/* Keep instances of the same type engine together. */
 		VECS
 	} id;
-#define I915_NUM_RINGS 5
+#define I915_NUM_ENGINES 5
 #define _VCS(n) (VCS + (n))
 	unsigned int exec_id;
 	unsigned int guc_id;
@@ -196,8 +194,8 @@ struct  intel_engine_cs {
 	 * seen value is good enough. Note that the seqno will always be
 	 * monotonic, even if not coherent.
 	 */
-	u32		(*get_seqno)(struct intel_engine_cs *ring,
-				     bool lazy_coherency);
+	void		(*irq_seqno_barrier)(struct intel_engine_cs *ring);
+	u32		(*get_seqno)(struct intel_engine_cs *ring);
 	void		(*set_seqno)(struct intel_engine_cs *ring,
 				     u32 seqno);
 	int		(*dispatch_execbuffer)(struct drm_i915_gem_request *req,
@@ -246,16 +244,16 @@ struct  intel_engine_cs {
 	 *  ie. transpose of f(x, y)
 	 */
 	struct {
-		u32	sync_seqno[I915_NUM_RINGS-1];
+		u32	sync_seqno[I915_NUM_ENGINES-1];
 
 		union {
 			struct {
 				/* our mbox written by others */
-				u32		wait[I915_NUM_RINGS];
+				u32		wait[I915_NUM_ENGINES];
 				/* mboxes this ring signals to */
-				i915_reg_t	signal[I915_NUM_RINGS];
+				i915_reg_t	signal[I915_NUM_ENGINES];
 			} mbox;
-			u64		signal_ggtt[I915_NUM_RINGS];
+			u64		signal_ggtt[I915_NUM_ENGINES];
 		};
 
 		/* AKA wait() */
@@ -268,10 +266,13 @@ struct  intel_engine_cs {
 	} semaphore;
 
 	/* Execlists */
-	spinlock_t execlist_lock;
+	struct tasklet_struct irq_tasklet;
+	spinlock_t execlist_lock; /* used inside tasklet, use spin_lock_bh */
 	struct list_head execlist_queue;
 	struct list_head execlist_retired_req_list;
-	u8 next_context_status_buffer;
+	unsigned int fw_domains;
+	unsigned int next_context_status_buffer;
+	unsigned int idle_lite_restore_wa;
 	bool disable_lite_restore_wa;
 	u32 ctx_desc_template;
 	u32             irq_keep_mask; /* bitmask for interrupts that should not be masked */
@@ -306,6 +307,7 @@ struct  intel_engine_cs {
 	 * inspecting request list.
 	 */
 	u32 last_submitted_seqno;
+	unsigned user_interrupts;
 
 	bool gpu_caches_dirty;
 
@@ -332,15 +334,8 @@ struct  intel_engine_cs {
 	/*
 	 * Table of registers allowed in commands that read/write registers.
 	 */
-	const struct drm_i915_reg_descriptor *reg_table;
-	int reg_count;
-
-	/*
-	 * Table of registers allowed in commands that read/write registers, but
-	 * only from the DRM master.
-	 */
-	const struct drm_i915_reg_descriptor *master_reg_table;
-	int master_reg_count;
+	const struct drm_i915_reg_table *reg_tables;
+	int reg_table_count;
 
 	/*
 	 * Returns the bitmask for the length field of the specified command.
@@ -356,19 +351,19 @@ struct  intel_engine_cs {
 };
 
 static inline bool
-intel_ring_initialized(struct intel_engine_cs *ring)
+intel_engine_initialized(struct intel_engine_cs *engine)
 {
-	return ring->dev != NULL;
+	return engine->dev != NULL;
 }
 
 static inline unsigned
-intel_ring_flag(struct intel_engine_cs *ring)
+intel_engine_flag(struct intel_engine_cs *engine)
 {
-	return 1 << ring->id;
+	return 1 << engine->id;
 }
 
 static inline u32
-intel_ring_sync_index(struct intel_engine_cs *ring,
+intel_ring_sync_index(struct intel_engine_cs *engine,
 		      struct intel_engine_cs *other)
 {
 	int idx;
@@ -381,34 +376,33 @@ intel_ring_sync_index(struct intel_engine_cs *ring,
 	 * vcs2 -> 0 = rcs, 1 = vcs, 2 = bcs, 3 = vecs;
 	 */
 
-	idx = (other - ring) - 1;
+	idx = (other - engine) - 1;
 	if (idx < 0)
-		idx += I915_NUM_RINGS;
+		idx += I915_NUM_ENGINES;
 
 	return idx;
 }
 
 static inline void
-intel_flush_status_page(struct intel_engine_cs *ring, int reg)
+intel_flush_status_page(struct intel_engine_cs *engine, int reg)
 {
-	drm_clflush_virt_range(&ring->status_page.page_addr[reg],
-			       sizeof(uint32_t));
+	mb();
+	clflush(&engine->status_page.page_addr[reg]);
+	mb();
 }
 
 static inline u32
-intel_read_status_page(struct intel_engine_cs *ring,
-		       int reg)
+intel_read_status_page(struct intel_engine_cs *engine, int reg)
 {
 	/* Ensure that the compiler doesn't optimize away the load. */
-	barrier();
-	return ring->status_page.page_addr[reg];
+	return READ_ONCE(engine->status_page.page_addr[reg]);
 }
 
 static inline void
-intel_write_status_page(struct intel_engine_cs *ring,
+intel_write_status_page(struct intel_engine_cs *engine,
 			int reg, u32 value)
 {
-	ring->status_page.page_addr[reg] = value;
+	engine->status_page.page_addr[reg] = value;
 }
 
 /*
@@ -439,42 +433,42 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 void intel_unpin_ringbuffer_obj(struct intel_ringbuffer *ringbuf);
 void intel_ringbuffer_free(struct intel_ringbuffer *ring);
 
-void intel_stop_ring_buffer(struct intel_engine_cs *ring);
-void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
+void intel_stop_engine(struct intel_engine_cs *engine);
+void intel_cleanup_engine(struct intel_engine_cs *engine);
 
 int intel_ring_alloc_request_extras(struct drm_i915_gem_request *request);
 
 int __must_check intel_ring_begin(struct drm_i915_gem_request *req, int n);
 int __must_check intel_ring_cacheline_align(struct drm_i915_gem_request *req);
-static inline void intel_ring_emit(struct intel_engine_cs *ring,
+static inline void intel_ring_emit(struct intel_engine_cs *engine,
 				   u32 data)
 {
-	struct intel_ringbuffer *ringbuf = ring->buffer;
+	struct intel_ringbuffer *ringbuf = engine->buffer;
 	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
 	ringbuf->tail += 4;
 }
-static inline void intel_ring_emit_reg(struct intel_engine_cs *ring,
+static inline void intel_ring_emit_reg(struct intel_engine_cs *engine,
 				       i915_reg_t reg)
 {
-	intel_ring_emit(ring, i915_mmio_reg_offset(reg));
+	intel_ring_emit(engine, i915_mmio_reg_offset(reg));
 }
-static inline void intel_ring_advance(struct intel_engine_cs *ring)
+static inline void intel_ring_advance(struct intel_engine_cs *engine)
 {
-	struct intel_ringbuffer *ringbuf = ring->buffer;
+	struct intel_ringbuffer *ringbuf = engine->buffer;
 	ringbuf->tail &= ringbuf->size - 1;
 }
 int __intel_ring_space(int head, int tail, int size);
 void intel_ring_update_space(struct intel_ringbuffer *ringbuf);
 int intel_ring_space(struct intel_ringbuffer *ringbuf);
-bool intel_ring_stopped(struct intel_engine_cs *ring);
+bool intel_engine_stopped(struct intel_engine_cs *engine);
 
-int __must_check intel_ring_idle(struct intel_engine_cs *ring);
-void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
+int __must_check intel_engine_idle(struct intel_engine_cs *engine);
+void intel_ring_init_seqno(struct intel_engine_cs *engine, u32 seqno);
 int intel_ring_flush_all_caches(struct drm_i915_gem_request *req);
 int intel_ring_invalidate_all_caches(struct drm_i915_gem_request *req);
 
-void intel_fini_pipe_control(struct intel_engine_cs *ring);
-int intel_init_pipe_control(struct intel_engine_cs *ring);
+void intel_fini_pipe_control(struct intel_engine_cs *engine);
+int intel_init_pipe_control(struct intel_engine_cs *engine);
 
 int intel_init_render_ring_buffer(struct drm_device *dev);
 int intel_init_bsd_ring_buffer(struct drm_device *dev);
@@ -482,9 +476,9 @@ int intel_init_bsd2_ring_buffer(struct drm_device *dev);
 int intel_init_blt_ring_buffer(struct drm_device *dev);
 int intel_init_vebox_ring_buffer(struct drm_device *dev);
 
-u64 intel_ring_get_active_head(struct intel_engine_cs *ring);
+u64 intel_ring_get_active_head(struct intel_engine_cs *engine);
 
-int init_workarounds_ring(struct intel_engine_cs *ring);
+int init_workarounds_ring(struct intel_engine_cs *engine);
 
 static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
 {