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: thomas.hellstrom@intel.com, Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 29/41] drm/i915/gt: Track timeline GGTT offset separately from subpage offset
Date: Mon, 25 Jan 2021 14:01:24 +0000	[thread overview]
Message-ID: <20210125140136.10494-29-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210125140136.10494-1-chris@chris-wilson.co.uk>

Currently we know that the timeline status page is at most a page in
size, and so we can preserve the lower 12bits of the offset when
relocating the status page in the GGTT. If we want to use a larger
object, such as the context state, we may not necessarily use a position
within the first page and so need more than 12b.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/i915/gt/gen6_engine_cs.c       |  4 ++--
 drivers/gpu/drm/i915/gt/gen8_engine_cs.c       |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c      |  4 ++--
 drivers/gpu/drm/i915/gt/intel_timeline.c       | 17 +++++++----------
 drivers/gpu/drm/i915/gt/intel_timeline_types.h |  1 +
 drivers/gpu/drm/i915/gt/selftest_engine_cs.c   |  2 +-
 drivers/gpu/drm/i915/gt/selftest_rc6.c         |  2 +-
 drivers/gpu/drm/i915/gt/selftest_timeline.c    | 16 ++++++++--------
 8 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
index ce38d1bcaba3..2f59dd3bdc18 100644
--- a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c
@@ -161,7 +161,7 @@ u32 *gen6_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_DC_FLUSH_ENABLE |
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->hwsp_offset |
+	*cs++ = i915_request_active_timeline(rq)->ggtt_offset |
 		PIPE_CONTROL_GLOBAL_GTT;
 	*cs++ = rq->fence.seqno;
 
@@ -359,7 +359,7 @@ u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
 		 PIPE_CONTROL_QW_WRITE |
 		 PIPE_CONTROL_GLOBAL_GTT_IVB |
 		 PIPE_CONTROL_CS_STALL);
-	*cs++ = i915_request_active_timeline(rq)->hwsp_offset;
+	*cs++ = i915_request_active_timeline(rq)->ggtt_offset;
 	*cs++ = rq->fence.seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 449633371de6..80784c5e43e3 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -346,7 +346,7 @@ static u32 hwsp_offset(const struct i915_request *rq)
 	if (cl)
 		return cl->ggtt_offset;
 
-	return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset;
+	return rcu_dereference_protected(rq->timeline, 1)->ggtt_offset;
 }
 
 int gen8_emit_init_breadcrumb(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 8372c8bc4ca5..a1cd511223a2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1322,7 +1322,7 @@ static int print_ring(char *buf, int sz, struct i915_request *rq)
 		len = scnprintf(buf, sz,
 				"ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
 				i915_ggtt_offset(rq->ring->vma),
-				tl ? tl->hwsp_offset : 0,
+				tl ? tl->ggtt_offset : 0,
 				hwsp_seqno(rq),
 				DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
 						      1000 * 1000));
@@ -1667,7 +1667,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 
 		if (tl) {
 			drm_printf(m, "\t\tring->hwsp:   0x%08x\n",
-				   tl->hwsp_offset);
+				   tl->ggtt_offset);
 			intel_timeline_put(tl);
 		}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 1505dffbaba9..b684322c879c 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -354,13 +354,11 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww)
 	if (err)
 		return err;
 
-	tl->hwsp_offset =
-		i915_ggtt_offset(tl->hwsp_ggtt) +
-		offset_in_page(tl->hwsp_offset);
+	tl->ggtt_offset = i915_ggtt_offset(tl->hwsp_ggtt) + tl->hwsp_offset;
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
-		 tl->fence_context, tl->hwsp_offset);
+		 tl->fence_context, tl->ggtt_offset);
 
-	cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset);
+	cacheline_acquire(tl->hwsp_cacheline, tl->ggtt_offset);
 	if (atomic_fetch_inc(&tl->pin_count)) {
 		cacheline_release(tl->hwsp_cacheline);
 		__i915_vma_unpin(tl->hwsp_ggtt);
@@ -528,14 +526,13 @@ __intel_timeline_get_seqno(struct intel_timeline *tl,
 
 	vaddr = page_mask_bits(cl->vaddr);
 	tl->hwsp_offset = cacheline * CACHELINE_BYTES;
-	tl->hwsp_seqno =
-		memset(vaddr + tl->hwsp_offset, 0, CACHELINE_BYTES);
+	tl->hwsp_seqno = memset(vaddr + tl->hwsp_offset, 0, CACHELINE_BYTES);
 
-	tl->hwsp_offset += i915_ggtt_offset(vma);
+	tl->ggtt_offset = i915_ggtt_offset(vma) + tl->hwsp_offset;
 	GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n",
-		 tl->fence_context, tl->hwsp_offset);
+		 tl->fence_context, tl->ggtt_offset);
 
-	cacheline_acquire(cl, tl->hwsp_offset);
+	cacheline_acquire(cl, tl->ggtt_offset);
 	tl->hwsp_cacheline = cl;
 
 	*seqno = timeline_advance(tl);
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 9f677c9b7d06..c5995cc290a0 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -47,6 +47,7 @@ struct intel_timeline {
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
 	u32 hwsp_offset;
+	u32 ggtt_offset;
 
 	struct intel_timeline_cacheline *hwsp_cacheline;
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
index 84d883de30ee..e33ec4e3b35d 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c
@@ -53,7 +53,7 @@ static int write_timestamp(struct i915_request *rq, int slot)
 		cmd++;
 	*cs++ = cmd;
 	*cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base));
-	*cs++ = i915_request_timeline(rq)->hwsp_offset + slot * sizeof(u32);
+	*cs++ = i915_request_timeline(rq)->ggtt_offset + slot * sizeof(u32);
 	*cs++ = 0;
 
 	intel_ring_advance(rq, cs);
diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c
index f097e420ac45..285cead849dd 100644
--- a/drivers/gpu/drm/i915/gt/selftest_rc6.c
+++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c
@@ -137,7 +137,7 @@ static const u32 *__live_rc6_ctx(struct intel_context *ce)
 
 	*cs++ = cmd;
 	*cs++ = i915_mmio_reg_offset(GEN8_RC6_CTX_INFO);
-	*cs++ = ce->timeline->hwsp_offset + 8;
+	*cs++ = ce->timeline->ggtt_offset + 8;
 	*cs++ = 0;
 	intel_ring_advance(rq, cs);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index 562a450d2832..6b412228a6fd 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -468,7 +468,7 @@ tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value)
 
 	i915_request_get(rq);
 
-	err = emit_ggtt_store_dw(rq, tl->hwsp_offset, value);
+	err = emit_ggtt_store_dw(rq, tl->ggtt_offset, value);
 	i915_request_add(rq);
 	if (err) {
 		i915_request_put(rq);
@@ -564,7 +564,7 @@ static int live_hwsp_engine(void *arg)
 
 		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
 			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
-				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
+				      n, tl->fence_context, tl->ggtt_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -636,7 +636,7 @@ static int live_hwsp_alternate(void *arg)
 
 		if (!err && READ_ONCE(*tl->hwsp_seqno) != n) {
 			GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x, found 0x%x\n",
-				      n, tl->fence_context, tl->hwsp_offset, *tl->hwsp_seqno);
+				      n, tl->fence_context, tl->ggtt_offset, *tl->hwsp_seqno);
 			GEM_TRACE_DUMP();
 			err = -EINVAL;
 		}
@@ -696,9 +696,9 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 		pr_debug("seqno[0]:%08x, hwsp_offset:%08x\n",
-			 seqno[0], tl->hwsp_offset);
+			 seqno[0], tl->ggtt_offset);
 
-		err = emit_ggtt_store_dw(rq, tl->hwsp_offset, seqno[0]);
+		err = emit_ggtt_store_dw(rq, tl->ggtt_offset, seqno[0]);
 		if (err) {
 			i915_request_add(rq);
 			goto out;
@@ -713,9 +713,9 @@ static int live_hwsp_wrap(void *arg)
 			goto out;
 		}
 		pr_debug("seqno[1]:%08x, hwsp_offset:%08x\n",
-			 seqno[1], tl->hwsp_offset);
+			 seqno[1], tl->ggtt_offset);
 
-		err = emit_ggtt_store_dw(rq, tl->hwsp_offset, seqno[1]);
+		err = emit_ggtt_store_dw(rq, tl->ggtt_offset, seqno[1]);
 		if (err) {
 			i915_request_add(rq);
 			goto out;
@@ -1343,7 +1343,7 @@ static int live_hwsp_recycle(void *arg)
 			if (READ_ONCE(*tl->hwsp_seqno) != count) {
 				GEM_TRACE_ERR("Invalid seqno:%lu stored in timeline %llu @ %x found 0x%x\n",
 					      count, tl->fence_context,
-					      tl->hwsp_offset, *tl->hwsp_seqno);
+					      tl->ggtt_offset, *tl->hwsp_seqno);
 				GEM_TRACE_DUMP();
 				err = -EINVAL;
 			}
-- 
2.20.1

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

  parent reply	other threads:[~2021-01-25 14:02 UTC|newest]

Thread overview: 90+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-25 14:00 [Intel-gfx] [PATCH 01/41] drm/i915/selftests: Check for engine-reset errors in the middle of workarounds Chris Wilson
2021-01-25 14:00 ` [Intel-gfx] [PATCH 02/41] drm/i915/gt: Move the defer_request waiter active assertion Chris Wilson
2021-01-25 14:53   ` Tvrtko Ursulin
2021-01-25 14:00 ` [Intel-gfx] [PATCH 03/41] drm/i915: Replace engine->schedule() with a known request operation Chris Wilson
2021-01-25 15:14   ` Tvrtko Ursulin
2021-01-25 14:00 ` [Intel-gfx] [PATCH 04/41] drm/i915: Teach the i915_dependency to use a double-lock Chris Wilson
2021-01-25 15:34   ` Tvrtko Ursulin
2021-01-25 21:37     ` Chris Wilson
2021-01-26  9:40       ` Tvrtko Ursulin
2021-01-25 14:01 ` [Intel-gfx] [PATCH 05/41] drm/i915: Restructure priority inheritance Chris Wilson
2021-01-26 11:12   ` Tvrtko Ursulin
2021-01-26 11:30     ` Chris Wilson
2021-01-26 11:40       ` Tvrtko Ursulin
2021-01-26 11:55         ` Chris Wilson
2021-01-26 13:15           ` Tvrtko Ursulin
2021-01-26 13:24             ` Chris Wilson
2021-01-26 13:45               ` Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 06/41] drm/i915/selftests: Measure set-priority duration Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 07/41] drm/i915/selftests: Exercise priority inheritance around an engine loop Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 08/41] drm/i915: Improve DFS for priority inheritance Chris Wilson
2021-01-26 16:22   ` Tvrtko Ursulin
2021-01-26 16:26     ` Chris Wilson
2021-01-26 16:42       ` Tvrtko Ursulin
2021-01-26 16:51         ` Tvrtko Ursulin
2021-01-26 16:51         ` Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 09/41] drm/i915/selftests: Exercise relative mmio paths to non-privileged registers Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 10/41] drm/i915/selftests: Exercise cross-process context isolation Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 11/41] drm/i915: Extract request submission from execlists Chris Wilson
2021-01-26 16:28   ` Tvrtko Ursulin
2021-01-25 14:01 ` [Intel-gfx] [PATCH 12/41] drm/i915: Extract request rewinding " Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 13/41] drm/i915: Extract request suspension from the execlists Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 14/41] drm/i915: Extract the ability to defer and rerun a request later Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 15/41] drm/i915: Fix the iterative dfs for defering requests Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 16/41] drm/i915: Move common active lists from engine to i915_scheduler Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 17/41] drm/i915: Move scheduler queue Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 18/41] drm/i915: Move tasklet from execlists to sched Chris Wilson
2021-01-27 14:10   ` Tvrtko Ursulin
2021-01-27 14:24     ` Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 19/41] drm/i915/gt: Show scheduler queues when dumping state Chris Wilson
2021-01-27 14:13   ` Tvrtko Ursulin
2021-01-27 14:35     ` Chris Wilson
2021-01-27 14:50       ` Tvrtko Ursulin
2021-01-27 14:55         ` Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 20/41] drm/i915: Replace priolist rbtree with a skiplist Chris Wilson
2021-01-27 15:10   ` Tvrtko Ursulin
2021-01-27 15:33     ` Chris Wilson
2021-01-27 15:44       ` Chris Wilson
2021-01-27 15:58         ` Tvrtko Ursulin
2021-01-28  9:50           ` Chris Wilson
2021-01-28 15:56   ` Tvrtko Ursulin
2021-01-28 16:26     ` Chris Wilson
2021-01-28 16:42       ` Tvrtko Ursulin
2021-01-28 22:20         ` Chris Wilson
2021-01-28 22:44         ` Chris Wilson
2021-01-29  9:24           ` Tvrtko Ursulin
2021-01-29  9:37       ` Tvrtko Ursulin
2021-01-29 10:26         ` Chris Wilson
2021-01-28 22:56   ` Matthew Brost
2021-01-29 10:30     ` Chris Wilson
2021-01-29 17:01       ` Matthew Brost
2021-01-29 10:22   ` Tvrtko Ursulin
2021-01-25 14:01 ` [Intel-gfx] [PATCH 21/41] drm/i915: Wrap cmpxchg64 with try_cmpxchg64() helper Chris Wilson
2021-01-27 15:28   ` Tvrtko Ursulin
2021-01-25 14:01 ` [Intel-gfx] [PATCH 22/41] drm/i915: Fair low-latency scheduling Chris Wilson
2021-01-28 11:35   ` Tvrtko Ursulin
2021-01-28 12:32     ` Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 23/41] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 24/41] drm/i915: Extend the priority boosting for the display with a deadline Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 25/41] drm/i915/gt: Support virtual engine queues Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 26/41] drm/i915: Move saturated workload detection back to the context Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 27/41] drm/i915: Bump default timeslicing quantum to 5ms Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 28/41] drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb Chris Wilson
2021-01-25 14:01 ` Chris Wilson [this message]
2021-01-25 14:01 ` [Intel-gfx] [PATCH 30/41] drm/i915/gt: Add timeline "mode" Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 31/41] drm/i915/gt: Use indices for writing into relative timelines Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 32/41] drm/i915/selftests: Exercise relative timeline modes Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 33/41] drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 34/41] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq" Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 35/41] drm/i915/gt: Couple tasklet scheduling for all CS interrupts Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 36/41] drm/i915/gt: Support creation of 'internal' rings Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 37/41] drm/i915/gt: Use client timeline address for seqno writes Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 38/41] drm/i915/gt: Infrastructure for ring scheduling Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 39/41] drm/i915/gt: Implement ring scheduler for gen4-7 Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 40/41] drm/i915/gt: Enable ring scheduling for gen5-7 Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 41/41] drm/i915: Support secure dispatch on gen6/gen7 Chris Wilson
2021-01-25 14:40 ` [Intel-gfx] [PATCH 01/41] drm/i915/selftests: Check for engine-reset errors in the middle of workarounds Tvrtko Ursulin
2021-01-25 17:08 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/41] " Patchwork
2021-01-25 17:10 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-01-25 17:38 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-01-25 22:45 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " 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=20210125140136.10494-29-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=thomas.hellstrom@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.