All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: mika.kuoppala@intel.com
Subject: [PATCH 33/38] drm/i915: Move the global sync optimisation to the timeline
Date: Tue, 20 Sep 2016 09:30:07 +0100	[thread overview]
Message-ID: <20160920083012.2754-34-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20160920083012.2754-1-chris@chris-wilson.co.uk>

Currently we try to reduce the number of synchronisations (now the
number of requests we need to wait upon) by noting that if we have
earlier waited upon a request, all subsequent requests in the timeline
will be after the wait. This only applies to requests in this timeline,
as other timelines will not be ordered by that waiter.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c      |  9 ------
 drivers/gpu/drm/i915/i915_drv.h          |  1 -
 drivers/gpu/drm/i915/i915_gem_request.c  | 18 ++++++++----
 drivers/gpu/drm/i915/i915_gem_timeline.h |  1 +
 drivers/gpu/drm/i915/i915_gpu_error.c    | 48 +++++++++++++++++++-------------
 drivers/gpu/drm/i915/intel_engine_cs.c   |  2 --
 drivers/gpu/drm/i915/intel_ringbuffer.c  |  3 --
 drivers/gpu/drm/i915/intel_ringbuffer.h  | 23 ---------------
 8 files changed, 43 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 79ad67893d41..ca7d2e0da23c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3185,15 +3185,6 @@ static int i915_semaphore_status(struct seq_file *m, void *unused)
 		seq_putc(m, '\n');
 	}
 
-	seq_puts(m, "\nSync seqno:\n");
-	for_each_engine(engine, dev_priv) {
-		for (j = 0; j < num_rings; j++)
-			seq_printf(m, "  0x%08x ",
-				   engine->semaphore.sync_seqno[j]);
-		seq_putc(m, '\n');
-	}
-	seq_putc(m, '\n');
-
 	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ac83f449efa5..6daa4d538f42 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -784,7 +784,6 @@ struct drm_i915_error_state {
 		u32 cpu_ring_tail;
 
 		u32 last_seqno;
-		u32 semaphore_seqno[I915_NUM_ENGINES - 1];
 
 		/* Register state */
 		u32 start;
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index c31cb7c4a61f..3d09301f7b40 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/drivers/gpu/drm/i915/i915_gem_request.c
@@ -238,8 +238,9 @@ static int i915_gem_check_wedge(struct drm_i915_private *dev_priv)
 static int i915_gem_init_global_seqno(struct drm_i915_private *dev_priv,
 				      u32 seqno)
 {
+	struct i915_gem_timeline *timeline;
 	struct intel_engine_cs *engine;
-	int ret;
+	int ret, i;
 
 	/* Carefully retire all requests without writing to the rings */
 	ret = i915_gem_wait_for_idle(dev_priv,
@@ -262,6 +263,14 @@ static int i915_gem_init_global_seqno(struct drm_i915_private *dev_priv,
 	for_each_engine(engine, dev_priv)
 		intel_engine_init_global_seqno(engine, seqno);
 
+	list_for_each_entry(timeline, &dev_priv->gt.timelines, link) {
+		for (i = 0; i < ARRAY_SIZE(timeline->engine); i++) {
+			struct intel_timeline *tl = &timeline->engine[i];
+
+			memset(tl->sync_seqno, 0, sizeof(tl->sync_seqno));
+		}
+	}
+
 	return 0;
 }
 
@@ -456,7 +465,7 @@ static int
 i915_gem_request_await_request(struct drm_i915_gem_request *to,
 			       struct drm_i915_gem_request *from)
 {
-	int idx, ret;
+	int ret;
 
 	GEM_BUG_ON(to == from);
 
@@ -476,8 +485,7 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to,
 		return ret < 0 ? ret : 0;
 	}
 
-	idx = intel_engine_sync_index(from->engine, to->engine);
-	if (from->global_seqno <= from->engine->semaphore.sync_seqno[idx])
+	if (from->global_seqno <= to->timeline->sync_seqno[from->engine->id])
 		return 0;
 
 	trace_i915_gem_ring_sync_to(to, from);
@@ -495,7 +503,7 @@ i915_gem_request_await_request(struct drm_i915_gem_request *to,
 			return ret;
 	}
 
-	from->engine->semaphore.sync_seqno[idx] = from->global_seqno;
+	to->timeline->sync_seqno[from->engine->id] = from->global_seqno;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.h b/drivers/gpu/drm/i915/i915_gem_timeline.h
index be34c2e5ac85..ec2e56352c4b 100644
--- a/drivers/gpu/drm/i915/i915_gem_timeline.h
+++ b/drivers/gpu/drm/i915/i915_gem_timeline.h
@@ -47,6 +47,7 @@ struct intel_timeline {
 	 * struct_mutex.
 	 */
 	struct i915_gem_active last_request;
+	u32 sync_seqno[I915_NUM_ENGINES];
 
 	struct i915_gem_timeline *common;
 };
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index c263f42cca07..4ee31c9a2bd9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -371,17 +371,13 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	if (INTEL_GEN(m->i915) >= 6) {
 		err_printf(m, "  RC PSMI: 0x%08x\n", ee->rc_psmi);
 		err_printf(m, "  FAULT_REG: 0x%08x\n", ee->fault_reg);
-		err_printf(m, "  SYNC_0: 0x%08x [last synced 0x%08x]\n",
-			   ee->semaphore_mboxes[0],
-			   ee->semaphore_seqno[0]);
-		err_printf(m, "  SYNC_1: 0x%08x [last synced 0x%08x]\n",
-			   ee->semaphore_mboxes[1],
-			   ee->semaphore_seqno[1]);
-		if (HAS_VEBOX(m->i915)) {
-			err_printf(m, "  SYNC_2: 0x%08x [last synced 0x%08x]\n",
-				   ee->semaphore_mboxes[2],
-				   ee->semaphore_seqno[2]);
-		}
+		err_printf(m, "  SYNC_0: 0x%08x\n",
+			   ee->semaphore_mboxes[0]);
+		err_printf(m, "  SYNC_1: 0x%08x\n",
+			   ee->semaphore_mboxes[1]);
+		if (HAS_VEBOX(m->i915))
+			err_printf(m, "  SYNC_2: 0x%08x\n",
+				   ee->semaphore_mboxes[2]);
 	}
 	if (USES_PPGTT(m->i915)) {
 		err_printf(m, "  GFX_MODE: 0x%08x\n", ee->vm_info.gfx_mode);
@@ -923,6 +919,26 @@ static void i915_gem_record_fences(struct drm_i915_private *dev_priv,
 	}
 }
 
+static inline u32
+gen8_engine_sync_index(struct intel_engine_cs *engine,
+		       struct intel_engine_cs *other)
+{
+	int idx;
+
+	/*
+	 * 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 - engine) - 1;
+	if (idx < 0)
+		idx += I915_NUM_ENGINES;
+
+	return idx;
+}
 
 static void gen8_record_semaphore_state(struct drm_i915_error_state *error,
 					struct intel_engine_cs *engine,
@@ -946,10 +962,9 @@ static void gen8_record_semaphore_state(struct drm_i915_error_state *error,
 		signal_offset =
 			(GEN8_SIGNAL_OFFSET(engine, id) & (PAGE_SIZE - 1)) / 4;
 		tmp = error->semaphore->pages[0];
-		idx = intel_engine_sync_index(engine, to);
+		idx = gen8_engine_sync_index(engine, to);
 
 		ee->semaphore_mboxes[idx] = tmp[signal_offset];
-		ee->semaphore_seqno[idx] = engine->semaphore.sync_seqno[idx];
 	}
 }
 
@@ -960,14 +975,9 @@ static void gen6_record_semaphore_state(struct intel_engine_cs *engine,
 
 	ee->semaphore_mboxes[0] = I915_READ(RING_SYNC_0(engine->mmio_base));
 	ee->semaphore_mboxes[1] = I915_READ(RING_SYNC_1(engine->mmio_base));
-	ee->semaphore_seqno[0] = engine->semaphore.sync_seqno[0];
-	ee->semaphore_seqno[1] = engine->semaphore.sync_seqno[1];
-
-	if (HAS_VEBOX(dev_priv)) {
+	if (HAS_VEBOX(dev_priv))
 		ee->semaphore_mboxes[2] =
 			I915_READ(RING_SYNC_2(engine->mmio_base));
-		ee->semaphore_seqno[2] = engine->semaphore.sync_seqno[2];
-	}
 }
 
 static void error_record_engine_waiters(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 1e23d171349f..2c8883d0b892 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -191,8 +191,6 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno)
 				       I915_NUM_ENGINES * gen8_semaphore_seqno_size);
 		kunmap(page);
 	}
-	memset(engine->semaphore.sync_seqno, 0,
-	       sizeof(engine->semaphore.sync_seqno));
 
 	intel_write_status_page(engine, I915_GEM_HWS_INDEX, seqno);
 	if (engine->irq_seqno_barrier)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index c2c39dc555ea..2423139faaad 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -2041,9 +2041,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 
 	intel_engine_setup_common(engine);
 
-	memset(engine->semaphore.sync_seqno, 0,
-	       sizeof(engine->semaphore.sync_seqno));
-
 	ret = intel_engine_init_common(engine);
 	if (ret)
 		goto error;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 9185deb9134a..436880149ee0 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -287,8 +287,6 @@ struct intel_engine_cs {
 	 *  ie. transpose of f(x, y)
 	 */
 	struct {
-		u32	sync_seqno[I915_NUM_ENGINES-1];
-
 		union {
 #define GEN6_SEMAPHORE_LAST	VECS_HW
 #define GEN6_NUM_SEMAPHORES	(GEN6_SEMAPHORE_LAST + 1)
@@ -364,27 +362,6 @@ intel_engine_flag(const struct intel_engine_cs *engine)
 	return 1 << engine->id;
 }
 
-static inline u32
-intel_engine_sync_index(struct intel_engine_cs *engine,
-			struct intel_engine_cs *other)
-{
-	int idx;
-
-	/*
-	 * 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 - engine) - 1;
-	if (idx < 0)
-		idx += I915_NUM_ENGINES;
-
-	return idx;
-}
-
 static inline void
 intel_flush_status_page(struct intel_engine_cs *engine, int reg)
 {
-- 
2.9.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2016-09-20  8:30 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-20  8:29 Multiple timelines, take 2 Chris Wilson
2016-09-20  8:29 ` [PATCH 01/38] drm/i915: Allow disabling error capture Chris Wilson
2016-09-21  6:13   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 02/38] drm/i915: Stop the machine whilst capturing the GPU crash dump Chris Wilson
2016-09-26  8:58   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 03/38] drm/i915: Always use the GTT for error capture Chris Wilson
2016-09-21  7:24   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 04/38] drm/i915: Consolidate error object printing Chris Wilson
2016-09-20  8:29 ` [PATCH 05/38] drm/i915: Compress GPU objects in error state Chris Wilson
2016-09-21  7:55   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 06/38] drm/i915: Support asynchronous waits on struct fence from i915_gem_request Chris Wilson
2016-09-21  8:05   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 07/38] drm/i915: Allow i915_sw_fence_await_sw_fence() to allocate Chris Wilson
2016-09-20  8:29 ` [PATCH 08/38] drm/i915: Rearrange i915_wait_request() accounting with callers Chris Wilson
2016-09-21  8:12   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 09/38] drm/i915: Remove unused i915_gem_active_wait() in favour of _unlocked() Chris Wilson
2016-09-20  8:29 ` [PATCH 10/38] drm/i915: Defer active reference until required Chris Wilson
2016-09-21  8:44   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 11/38] drm/i915: Introduce an internal allocator for disposable private objects Chris Wilson
2016-09-21 11:50   ` Joonas Lahtinen
2016-09-27  9:10     ` Chris Wilson
2016-09-20  8:29 ` [PATCH 12/38] drm/i915: Reuse the active golden render state batch Chris Wilson
2016-09-26  7:24   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 13/38] drm/i915: Markup GEM API with lockdep asserts Chris Wilson
2016-09-21 11:56   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 14/38] drm/i915: Use a radixtree for random access to the object's backing storage Chris Wilson
2016-09-20  8:29 ` [PATCH 15/38] drm/i915: Refactor object page API Chris Wilson
2016-09-20  8:29 ` [PATCH 16/38] drm/i915: Pass around sg_table to get_pages/put_pages backend Chris Wilson
2016-09-20 11:24   ` kbuild test robot
2016-09-20  8:29 ` [PATCH 17/38] drm/i915: Move object backing storage manipulation to its own locking Chris Wilson
2016-09-20  8:29 ` [PATCH 18/38] drm/i915/dmabuf: Acquire the backing storage outside of struct_mutex Chris Wilson
2016-09-20  8:29 ` [PATCH 19/38] drm/i915: Implement pread without struct-mutex Chris Wilson
2016-09-20  8:29 ` [PATCH 20/38] drm/i915: Implement pwrite " Chris Wilson
2016-09-20 13:47   ` kbuild test robot
2016-09-20  8:29 ` [PATCH 21/38] drm/i915: Acquire the backing storage outside of struct_mutex in set-domain Chris Wilson
2016-09-20  8:29 ` [PATCH 22/38] drm/i915: Move object release to a freelist + worker Chris Wilson
2016-09-20  8:29 ` [PATCH 23/38] drm/i915: Use lockless object free Chris Wilson
2016-09-20  8:29 ` [PATCH 24/38] drm/i915: Move GEM activity tracking into a common struct reservation_object Chris Wilson
2016-09-26  7:53   ` Joonas Lahtinen
2016-09-20  8:29 ` [PATCH 25/38] drm: Add reference counting to drm_atomic_state Chris Wilson
2016-09-21  7:24   ` Sean Paul
2016-09-20  8:30 ` [PATCH 26/38] drm/i915: Restore nonblocking awaits for modesetting Chris Wilson
2016-09-26  8:11   ` Joonas Lahtinen
2016-09-20  8:30 ` [PATCH 27/38] drm/i915: Combine seqno + tracking into a global timeline struct Chris Wilson
2016-09-20  8:30 ` [PATCH 28/38] drm/i915: Queue the idling context switch after all other timelines Chris Wilson
2016-09-26  8:49   ` Joonas Lahtinen
2016-09-20  8:30 ` [PATCH 29/38] drm/i915: Wait first for submission, before waiting for request completion Chris Wilson
2016-09-20  8:30 ` [PATCH 30/38] drm/i915: Introduce a global_seqno for each request Chris Wilson
2016-09-20  8:30 ` [PATCH 31/38] drm/i915: Record space required for request emission Chris Wilson
2016-09-20  8:30 ` [PATCH 32/38] drm/i915: Defer " Chris Wilson
2016-09-26  8:53   ` Joonas Lahtinen
2016-09-26  9:04     ` Chris Wilson
2016-09-26  9:06       ` Joonas Lahtinen
2016-09-26  9:25         ` Chris Wilson
2016-09-20  8:30 ` Chris Wilson [this message]
2016-09-20  8:30 ` [PATCH 34/38] drm/i915: Create a unique name for the context Chris Wilson
2016-09-20  8:30 ` [PATCH 35/38] drm/i915: Reserve space in the global seqno during request allocation Chris Wilson
2016-09-20 18:49   ` kbuild test robot
2016-09-20 18:49   ` [PATCH] drm/i915: fix semicolon.cocci warnings kbuild test robot
2016-09-20  8:30 ` [PATCH 36/38] drm/i915: Enable multiple timelines Chris Wilson
2016-09-26  8:55   ` Joonas Lahtinen
2016-09-20  8:30 ` [PATCH 37/38] drm/i915: Enable userspace to opt-out of implicit fencing Chris Wilson
2016-09-20  8:30 ` [PATCH 38/38] drm/i915: Support explicit fencing for execbuf Chris Wilson
2016-09-20  9:24 ` ✗ Fi.CI.BAT: failure for series starting with [01/38] drm/i915: Allow disabling error capture Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160920083012.2754-34-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=mika.kuoppala@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.