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 31/41] drm/i915/gt: Use indices for writing into relative timelines
Date: Mon, 25 Jan 2021 14:01:26 +0000 [thread overview]
Message-ID: <20210125140136.10494-31-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210125140136.10494-1-chris@chris-wilson.co.uk>
Relative timelines are relative to either the global or per-process
HWSP, and so we can replace the absolute addressing with store-index
variants for position invariance.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/i915/gt/gen8_engine_cs.c | 98 +++++++++++++++++-------
drivers/gpu/drm/i915/gt/intel_timeline.h | 12 +++
2 files changed, 82 insertions(+), 28 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
index 80784c5e43e3..8b3a96b1afe0 100644
--- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c
@@ -518,7 +518,19 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs)
static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs)
{
- return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0);
+ struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+ unsigned int flags = MI_FLUSH_DW_OP_STOREDW;
+ u32 offset = hwsp_offset(rq);
+
+ if (intel_timeline_is_relative(tl)) {
+ offset = offset_in_page(offset);
+ flags |= MI_FLUSH_DW_STORE_INDEX;
+ }
+ GEM_BUG_ON(offset & 7);
+ if (!intel_timeline_in_context(tl))
+ offset |= MI_FLUSH_DW_USE_GTT;
+
+ return __gen8_emit_flush_dw(cs, rq->fence.seqno, offset, flags);
}
u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
@@ -528,6 +540,18 @@ u32 *gen8_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
{
+ struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+ unsigned int flags = PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL;
+ u32 offset = hwsp_offset(rq);
+
+ if (intel_timeline_is_relative(tl)) {
+ offset = offset_in_page(offset);
+ flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+ }
+ GEM_BUG_ON(offset & 7);
+ if (!intel_timeline_in_context(tl))
+ flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
cs = gen8_emit_pipe_control(cs,
PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
PIPE_CONTROL_DEPTH_CACHE_FLUSH |
@@ -535,26 +559,33 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
0);
/* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */
- cs = gen8_emit_ggtt_write_rcs(cs,
- rq->fence.seqno,
- hwsp_offset(rq),
- PIPE_CONTROL_FLUSH_ENABLE |
- PIPE_CONTROL_CS_STALL);
+ cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
return gen8_emit_fini_breadcrumb_tail(rq, cs);
}
u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
{
- cs = gen8_emit_ggtt_write_rcs(cs,
- rq->fence.seqno,
- hwsp_offset(rq),
- PIPE_CONTROL_CS_STALL |
- PIPE_CONTROL_TILE_CACHE_FLUSH |
- PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
- PIPE_CONTROL_DEPTH_CACHE_FLUSH |
- PIPE_CONTROL_DC_FLUSH_ENABLE |
- PIPE_CONTROL_FLUSH_ENABLE);
+ struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+ u32 offset = hwsp_offset(rq);
+ unsigned int flags;
+
+ flags = (PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_TILE_CACHE_FLUSH |
+ PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+ PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+ PIPE_CONTROL_DC_FLUSH_ENABLE |
+ PIPE_CONTROL_FLUSH_ENABLE);
+
+ if (intel_timeline_is_relative(tl)) {
+ offset = offset_in_page(offset);
+ flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+ }
+ GEM_BUG_ON(offset & 7);
+ if (!intel_timeline_in_context(tl))
+ flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+ cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset, 0, flags);
return gen8_emit_fini_breadcrumb_tail(rq, cs);
}
@@ -617,19 +648,30 @@ u32 *gen12_emit_fini_breadcrumb_xcs(struct i915_request *rq, u32 *cs)
u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs)
{
- cs = gen12_emit_ggtt_write_rcs(cs,
- rq->fence.seqno,
- hwsp_offset(rq),
- PIPE_CONTROL0_HDC_PIPELINE_FLUSH,
- PIPE_CONTROL_CS_STALL |
- PIPE_CONTROL_TILE_CACHE_FLUSH |
- PIPE_CONTROL_FLUSH_L3 |
- PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
- PIPE_CONTROL_DEPTH_CACHE_FLUSH |
- /* Wa_1409600907:tgl */
- PIPE_CONTROL_DEPTH_STALL |
- PIPE_CONTROL_DC_FLUSH_ENABLE |
- PIPE_CONTROL_FLUSH_ENABLE);
+ struct intel_timeline *tl = rcu_dereference_protected(rq->timeline, 1);
+ u32 offset = hwsp_offset(rq);
+ unsigned int flags;
+
+ flags = (PIPE_CONTROL_CS_STALL |
+ PIPE_CONTROL_TILE_CACHE_FLUSH |
+ PIPE_CONTROL_FLUSH_L3 |
+ PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+ PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+ /* Wa_1409600907:tgl */
+ PIPE_CONTROL_DEPTH_STALL |
+ PIPE_CONTROL_DC_FLUSH_ENABLE |
+ PIPE_CONTROL_FLUSH_ENABLE);
+
+ if (intel_timeline_is_relative(tl)) {
+ offset = offset_in_page(offset);
+ flags |= PIPE_CONTROL_STORE_DATA_INDEX;
+ }
+ GEM_BUG_ON(offset & 7);
+ if (!intel_timeline_in_context(tl))
+ flags |= PIPE_CONTROL_GLOBAL_GTT_IVB;
+
+ cs = __gen8_emit_write_rcs(cs, rq->fence.seqno, offset,
+ PIPE_CONTROL0_HDC_PIPELINE_FLUSH, flags);
return gen12_emit_fini_breadcrumb_tail(rq, cs);
}
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h
index e1d522329757..9859a77a6f54 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.h
@@ -48,6 +48,18 @@ intel_timeline_has_initial_breadcrumb(const struct intel_timeline *tl)
return tl->mode == INTEL_TIMELINE_ABSOLUTE;
}
+static inline bool
+intel_timeline_is_relative(const struct intel_timeline *tl)
+{
+ return tl->mode != INTEL_TIMELINE_ABSOLUTE;
+}
+
+static inline bool
+intel_timeline_in_context(const struct intel_timeline *tl)
+{
+ return tl->mode == INTEL_TIMELINE_RELATIVE_CONTEXT;
+}
+
static inline int __intel_timeline_sync_set(struct intel_timeline *tl,
u64 context, u32 seqno)
{
--
2.20.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev 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 ` [Intel-gfx] [PATCH 29/41] drm/i915/gt: Track timeline GGTT offset separately from subpage offset Chris Wilson
2021-01-25 14:01 ` [Intel-gfx] [PATCH 30/41] drm/i915/gt: Add timeline "mode" Chris Wilson
2021-01-25 14:01 ` Chris Wilson [this message]
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=20210125140136.10494-31-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).