drm/i915: Remove HW semaphores for gen7 inter-engine synchronisation

The writing is on the wall for the existence of a single execution queue
along each engine, and as a consequence we will not be able to track
dependencies along the HW queue itself, i.e. we will not be able to use
HW semaphores on gen7 as they use a global set of registers (and unlike
gen8+ we can not effectively target memory to keep per-context seqno and
dependencies).

On the positive side, when we implement request reordering for gen7 we
also can not presume a simple execution queue and would also require
removing the current semaphore generation code. So this bring us another
step closer to request reordering for ringbuffer submission!

The negative side is that using interrupts to drive inter-engine
synchronisation is much slower (4us -> 15us to do a nop on each of the 3
engines on ivb). This is much better than it was at the time of introducing
the HW semaphores and equally important userspace weaned itself off
intermixing dependent BLT/RENDER operations (the prime culprit was glyph
rendering in UXA). So while we regress the microbenchmarks, it should not
impact the user.

References: https://bugs.freedesktop.org/show_bug.cgi?id=108888
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20181228140736.32606-2-chris@chris-wilson.co.uk

1 files changed, 1 insertions, 55 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6b41b9ce5f5b..c927bdfb1ed0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -510,60 +510,6 @@ struct intel_engine_cs {
 	void		(*irq_seqno_barrier)(struct intel_engine_cs *engine);
 	void		(*cleanup)(struct intel_engine_cs *engine);
 
-	/* 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 {
-#define GEN6_SEMAPHORE_LAST	VECS_HW
-#define GEN6_NUM_SEMAPHORES	(GEN6_SEMAPHORE_LAST + 1)
-#define GEN6_SEMAPHORES_MASK	GENMASK(GEN6_SEMAPHORE_LAST, 0)
-		struct {
-			/* our mbox written by others */
-			u32		wait[GEN6_NUM_SEMAPHORES];
-			/* mboxes this ring signals to */
-			i915_reg_t	signal[GEN6_NUM_SEMAPHORES];
-		} mbox;
-
-		/* AKA wait() */
-		int	(*sync_to)(struct i915_request *rq,
-				   struct i915_request *signal);
-		u32	*(*signal)(struct i915_request *rq, u32 *cs);
-	} semaphore;
-
 	struct intel_engine_execlists execlists;
 
 	/* Contexts are pinned whilst they are active on the GPU. The last
@@ -889,7 +835,7 @@ intel_ring_set_tail(struct intel_ring *ring, unsigned int tail)
 	return tail;
 }
 
-void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno);
+void intel_engine_write_global_seqno(struct intel_engine_cs *engine, u32 seqno);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);