WebSVN – Kolibri OS – Diff – /drivers/video/drm/i915/intel_ringbuffer.h

 #ifndef _INTEL_RINGBUFFER_H_
 #define _INTEL_RINGBUFFER_H_
+#include
+#define I915_CMD_HASH_ORDER 9
 /*
  * Gen2 BSpec "1. Programming Environment" / 1.4.4.6 "Ring Buffer Use"
  * Gen3 BSpec "vol1c Memory Interface Functions" / 2.3.4.5 "Ring Buffer Use"
  * Gen4+ BSpec "vol1c Memory Interface and Command Stream" / 5.3.4.5 "Ring Buffer Use"
 #define I915_WRITE_CTL(ring, val) I915_WRITE(RING_CTL((ring)->mmio_base), val)
 #define I915_READ_IMR(ring) I915_READ(RING_IMR((ring)->mmio_base))
+#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
+#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; \
-#define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
+	} while(0)
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
+	HANGCHECK_WAIT,
-	HANGCHECK_WAIT,
+	HANGCHECK_ACTIVE,
-	HANGCHECK_ACTIVE,
+	HANGCHECK_ACTIVE_LOOP,
 	HANGCHECK_KICK,
+	HANGCHECK_HUNG,
+};
 	HANGCHECK_HUNG,
+#define HANGCHECK_SCORE_RING_HUNG 31
-};
 struct intel_ring_hangcheck {
-struct intel_ring_hangcheck {
-	bool deadlock;
+	u64 acthd;
-	u32 seqno;
+	u64 max_acthd;
+	u32 seqno;
-	u32 acthd;
+	int score;
-	int score;
+	enum intel_ring_hangcheck_action action;
-	enum intel_ring_hangcheck_action action;
-};
-struct  intel_ring_buffer {
-	const char	*name;
-	enum intel_ring_id {
-		RCS = 0x0,
-		VCS,
-		BCS,
-		VECS,
-	} id;
-#define I915_NUM_RINGS 4
+	int deadlock;
+};
 	u32		mmio_base;
-	void		__iomem *virtual_start;
+struct intel_ringbuffer {
-	struct		drm_device *dev;
+	struct drm_i915_gem_object *obj;
-	struct		drm_i915_gem_object *obj;
+	void		__iomem *virtual_start;
-	u32		head;
-	u32		tail;
+	u32		head;
-	int		space;
+	u32		tail;
-	int		size;
+	int		space;
-	int		effective_size;
+	int		size;
-	struct intel_hw_status_page status_page;
+	int		effective_size;
 	/** We track the position of the requests in the ring buffer, and
 	 * when each is retired we increment last_retired_head as the GPU
 	 * must have finished processing the request and so we know we
+	 * can advance the ringbuffer up to that position.
+	 *
+	 * last_retired_head is set to -1 after the value is consumed so
+	 * we can detect new retirements.
+	 */
+	u32		last_retired_head;
+};
+struct  intel_engine_cs {
+	const char	*name;
+	enum intel_ring_id {
+		RCS = 0x0,
+		VCS,
+		BCS,
+		VECS,
+		VCS2
+	} id;
+#define I915_NUM_RINGS 5
-	 * can advance the ringbuffer up to that position.
+#define LAST_USER_RING (VECS + 1)
 	u32		mmio_base;
-	 * last_retired_head is set to -1 after the value is consumed so
+	struct		drm_device *dev;
-	 * we can detect new retirements.
-	 */
+	struct intel_ringbuffer *buffer;
-	u32		last_retired_head;
+	struct intel_hw_status_page status_page;
-	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
-	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
+	unsigned irq_refcount; /* protected by dev_priv->irq_lock */
-	u32		trace_irq_seqno;
+	u32		irq_enable_mask;	/* bitmask to enable ring interrupt */
-	u32		sync_seqno[I915_NUM_RINGS-1];
+	u32		trace_irq_seqno;
-	bool __must_check (*irq_get)(struct intel_ring_buffer *ring);
+	bool __must_check (*irq_get)(struct intel_engine_cs *ring);
-	void		(*irq_put)(struct intel_ring_buffer *ring);
+	void		(*irq_put)(struct intel_engine_cs *ring);
-	int		(*init)(struct intel_ring_buffer *ring);
+	int		(*init)(struct intel_engine_cs *ring);
-	void		(*write_tail)(struct intel_ring_buffer *ring,
+	void		(*write_tail)(struct intel_engine_cs *ring,
 				      u32 value);
-	int __must_check (*flush)(struct intel_ring_buffer *ring,
+	int __must_check (*flush)(struct intel_engine_cs *ring,
 				  u32	invalidate_domains,
 				  u32	flush_domains);
-	int		(*add_request)(struct intel_ring_buffer *ring);
+	int		(*add_request)(struct intel_engine_cs *ring);
 	/* Some chipsets are not quite as coherent as advertised and need
 	 * an expensive kick to force a true read of the up-to-date seqno.
 	 * However, the up-to-date seqno is not always required and the last
 	 * seen value is good enough. Note that the seqno will always be
 	 * monotonic, even if not coherent.
 	 */
-	u32		(*get_seqno)(struct intel_ring_buffer *ring,
+	u32		(*get_seqno)(struct intel_engine_cs *ring,
-				     bool lazy_coherency);
-	void		(*set_seqno)(struct intel_ring_buffer *ring,
-				     u32 seqno);
+				     bool lazy_coherency);
+	void		(*set_seqno)(struct intel_engine_cs *ring,
+				     u32 seqno);
+	int		(*dispatch_execbuffer)(struct intel_engine_cs *ring,
+					       u64 offset, u32 length,
+					       unsigned flags);
+#define I915_DISPATCH_SECURE 0x1
+#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) |
+	 *	|-------------------------------------------------------------------
 	int		(*dispatch_execbuffer)(struct intel_ring_buffer *ring,
-					       u32 offset, u32 length,
+	 * Generalization:
-					       unsigned flags);
+	 *  g(x, y) := (y->id * NUM_RINGS * seqno_size) + (seqno_size * x->id)
-#define I915_DISPATCH_SECURE 0x1
+	 *  ie. transpose of f(x, y)
+	 */
+	struct {
+		u32	sync_seqno[I915_NUM_RINGS-1];
+		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];
-#define I915_DISPATCH_PINNED 0x2
+		};
 	void		(*cleanup)(struct intel_ring_buffer *ring);
-	int		(*sync_to)(struct intel_ring_buffer *ring,
+		/* AKA wait() */
-				   struct intel_ring_buffer *to,
+		int	(*sync_to)(struct intel_engine_cs *ring,
 	bool gpu_caches_dirty;
 	bool fbc_dirty;
-	wait_queue_head_t irq_queue;
-	/**
-	 * Do an explicit TLB flush before MI_SET_CONTEXT
-	 */
+	wait_queue_head_t irq_queue;
-	bool itlb_before_ctx_switch;
-	struct i915_hw_context *default_context;
+	struct intel_context *default_context;
-	struct i915_hw_context *last_context;
+	struct intel_context *last_context;
 	struct intel_ring_hangcheck hangcheck;
 	struct {
+		struct drm_i915_gem_object *obj;
+		u32 gtt_offset;
+		volatile u32 *cpu_page;
+	} scratch;
+	bool needs_cmd_parser;
+	/*
+	 * Table of commands the command parser needs to know about
+	 * for this ring.
+	 */
+	DECLARE_HASHTABLE(cmd_hash, I915_CMD_HASH_ORDER);
+	/*
+	 * Table of registers allowed in commands that read/write registers.
+	 */
+	const u32 *reg_table;
+	int reg_count;
+	/*
+	 * Table of registers allowed in commands that read/write registers, but
+	 * only from the DRM master.
+	 */
+	const u32 *master_reg_table;
+	int master_reg_count;
+	/*
+	 * Returns the bitmask for the length field of the specified command.
+	 * Return 0 for an unrecognized/invalid command.
+	 *
+	 * If the command parser finds an entry for a command in the ring's
+	 * cmd_tables, it gets the command's length based on the table entry.
+	 * If not, it calls this function to determine the per-ring length field
-		struct drm_i915_gem_object *obj;
+	 * encoding for the command (i.e. certain opcode ranges use certain bits
-		u32 gtt_offset;
+	 * to encode the command length in the header).
-		volatile u32 *cpu_page;
+	 */
-	} scratch;
+	u32 (*get_cmd_length_mask)(u32 cmd_header);
 };
 static inline bool
-intel_ring_initialized(struct intel_ring_buffer *ring)
+intel_ring_initialized(struct intel_engine_cs *ring)
+{
-	return ring->obj != NULL;
+	return ring->buffer && ring->buffer->obj;
+}
 static inline unsigned
-intel_ring_flag(struct intel_ring_buffer *ring)
+intel_ring_flag(struct intel_engine_cs *ring)
+{
 	return 1 << ring->id;
+}
 static inline u32
-intel_ring_sync_index(struct intel_ring_buffer *ring,
+intel_ring_sync_index(struct intel_engine_cs *ring,
+		      struct intel_engine_cs *other)
+{
-		      struct intel_ring_buffer *other)
+	int idx;
-	int idx;
+	/*
 	 * rcs -> 0 = vcs, 1 = bcs, 2 = vecs, 3 = vcs2;
-	/*
+	 * vcs -> 0 = bcs, 1 = vecs, 2 = vcs2, 3 = rcs;
-	 * cs -> 0 = vcs, 1 = bcs
+	 * bcs -> 0 = vecs, 1 = vcs2. 2 = rcs, 3 = vcs;
-	 * vcs -> 0 = bcs, 1 = cs,
+	 * vecs -> 0 = vcs2, 1 = rcs, 2 = vcs, 3 = bcs;
-	 * bcs -> 0 = cs, 1 = vcs.
+	 * vcs2 -> 0 = rcs, 1 = vcs, 2 = bcs, 3 = vecs;
 	 */
 	idx = (other - ring) - 1;
 	if (idx < 0)
 		idx += I915_NUM_RINGS;
 	return idx;
 }
 static inline u32
-intel_read_status_page(struct intel_ring_buffer *ring,
+intel_read_status_page(struct intel_engine_cs *ring,
 		       int reg)
  */
 #define I915_GEM_HWS_INDEX		0x20
 #define I915_GEM_HWS_SCRATCH_INDEX	0x30
 #define I915_GEM_HWS_SCRATCH_ADDR (I915_GEM_HWS_SCRATCH_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
+void intel_stop_ring_buffer(struct intel_engine_cs *ring);
-void intel_cleanup_ring_buffer(struct intel_ring_buffer *ring);
+void intel_cleanup_ring_buffer(struct intel_engine_cs *ring);
+int __must_check intel_ring_begin(struct intel_engine_cs *ring, int n);
-int __must_check intel_ring_begin(struct intel_ring_buffer *ring, int n);
+int __must_check intel_ring_cacheline_align(struct intel_engine_cs *ring);
-static inline void intel_ring_emit(struct intel_ring_buffer *ring,
+static inline void intel_ring_emit(struct intel_engine_cs *ring,
+				   u32 data)
-				   u32 data)
+{
-{
+	struct intel_ringbuffer *ringbuf = ring->buffer;
-	iowrite32(data, ring->virtual_start + ring->tail);
+	iowrite32(data, ringbuf->virtual_start + ringbuf->tail);
-	ring->tail += 4;
+	ringbuf->tail += 4;
+}
+static inline void intel_ring_advance(struct intel_engine_cs *ring)
-static inline void intel_ring_advance(struct intel_ring_buffer *ring)
+{
 	struct intel_ringbuffer *ringbuf = ring->buffer;
-	ring->tail &= ring->size - 1;
+	ringbuf->tail &= ringbuf->size - 1;
 }
-void __intel_ring_advance(struct intel_ring_buffer *ring);
+void __intel_ring_advance(struct intel_engine_cs *ring);
-int __must_check intel_ring_idle(struct intel_ring_buffer *ring);
+int __must_check intel_ring_idle(struct intel_engine_cs *ring);
-void intel_ring_init_seqno(struct intel_ring_buffer *ring, u32 seqno);
+void intel_ring_init_seqno(struct intel_engine_cs *ring, u32 seqno);
-int intel_ring_flush_all_caches(struct intel_ring_buffer *ring);
+int intel_ring_flush_all_caches(struct intel_engine_cs *ring);
+int intel_ring_invalidate_all_caches(struct intel_engine_cs *ring);
 int intel_ring_invalidate_all_caches(struct intel_ring_buffer *ring);
 int intel_init_render_ring_buffer(struct drm_device *dev);
-int intel_init_render_ring_buffer(struct drm_device *dev);
+int intel_init_bsd_ring_buffer(struct drm_device *dev);
-int intel_init_bsd_ring_buffer(struct drm_device *dev);
+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);
-u32 intel_ring_get_active_head(struct intel_ring_buffer *ring);
+u64 intel_ring_get_active_head(struct intel_engine_cs *ring);
-void intel_ring_setup_status_page(struct intel_ring_buffer *ring);
+void intel_ring_setup_status_page(struct intel_engine_cs *ring);
-static inline u32 intel_ring_get_tail(struct intel_ring_buffer *ring)
+static inline u32 intel_ring_get_tail(struct intel_ringbuffer *ringbuf)
+{
-	return ring->tail;
+	return ringbuf->tail;
 }
-static inline u32 intel_ring_get_seqno(struct intel_ring_buffer *ring)
+static inline u32 intel_ring_get_seqno(struct intel_engine_cs *ring)
+{
 	BUG_ON(ring->outstanding_lazy_seqno == 0);

Subversion Repositories Kolibri OS

(root)/drivers/video/drm/i915/intel_ringbuffer.h – Rev 4560 → 5060