From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 19/31] drm/i915/gt: Track timeline GGTT offset separately from subpage offset
Date: Mon, 8 Feb 2021 10:52:24 +0000 [thread overview]
Message-ID: <20210208105236.28498-19-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20210208105236.28498-1-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 +-
.../drm/i915/gt/intel_execlists_submission.c | 2 +-
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 ++++++++--------
drivers/gpu/drm/i915/i915_scheduler.c | 2 +-
9 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 d8763146e054..187f1dad1054 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_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index b7d28d09c9c1..86093d0b56ed 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3554,7 +3554,7 @@ 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));
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;
}
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 7483aeb66ea9..ad4e15c9b8f9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -1727,7 +1727,7 @@ void i915_sched_show(struct drm_printer *m,
drm_printf(m, "\tring->space: 0x%08x\n",
rq->ring->space);
drm_printf(m, "\tring->hwsp: 0x%08x\n",
- i915_request_active_timeline(rq)->hwsp_offset);
+ i915_request_active_timeline(rq)->ggtt_offset);
print_request_ring(m, rq);
--
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:[~2021-02-08 10:52 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-08 10:52 [Intel-gfx] [PATCH 01/31] drm/i915/gt: Ratelimit heartbeat completion probing Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 02/31] drm/i915: Move context revocation to scheduler Chris Wilson
2021-02-08 11:18 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 03/31] drm/i915: Introduce the scheduling mode Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 04/31] drm/i915: Move timeslicing flag to scheduler Chris Wilson
2021-02-08 11:43 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 05/31] drm/i915/gt: Declare when we enabled timeslicing Chris Wilson
2021-02-08 11:44 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 06/31] drm/i915: Move busywaiting control to the scheduler Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 07/31] drm/i915: Move preempt-reset flag " Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 08/31] drm/i915: Fix the iterative dfs for defering requests Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 09/31] drm/i915: Replace priolist rbtree with a skiplist Chris Wilson
2021-02-08 12:29 ` Tvrtko Ursulin
2021-02-08 12:46 ` Chris Wilson
2021-02-08 15:10 ` Tvrtko Ursulin
2021-02-08 15:23 ` Tvrtko Ursulin
2021-02-08 16:19 ` Chris Wilson
2021-02-09 16:11 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 10/31] drm/i915: Fair low-latency scheduling Chris Wilson
2021-02-08 14:56 ` Tvrtko Ursulin
2021-02-08 15:29 ` Chris Wilson
2021-02-08 16:03 ` Tvrtko Ursulin
2021-02-08 16:11 ` Chris Wilson
2021-02-09 9:37 ` Tvrtko Ursulin
2021-02-09 10:31 ` Chris Wilson
2021-02-09 10:40 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 11/31] drm/i915/gt: Specify a deadline for the heartbeat Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 12/31] drm/i915: Extend the priority boosting for the display with a deadline Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 13/31] drm/i915/gt: Support virtual engine queues Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 14/31] drm/i915: Move saturated workload detection back to the context Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 15/31] drm/i915: Bump default timeslicing quantum to 5ms Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 16/31] drm/i915/gt: Delay taking irqoff for execlists submission Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 17/31] drm/i915/gt: Convert the legacy ring submission to use the scheduling interface Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 18/31] drm/i915/gt: Wrap intel_timeline.has_initial_breadcrumb Chris Wilson
2021-02-08 10:52 ` Chris Wilson [this message]
2021-02-08 10:52 ` [Intel-gfx] [PATCH 20/31] drm/i915/gt: Add timeline "mode" Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 21/31] drm/i915/gt: Use indices for writing into relative timelines Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 22/31] drm/i915/selftests: Exercise relative timeline modes Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 23/31] drm/i915/gt: Use ppHWSP for unshared non-semaphore related timelines Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 24/31] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq" Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 25/31] drm/i915/gt: Support creation of 'internal' rings Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 26/31] drm/i915/gt: Use client timeline address for seqno writes Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 27/31] drm/i915/gt: Infrastructure for ring scheduling Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 28/31] drm/i915/gt: Implement ring scheduler for gen4-7 Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 29/31] drm/i915/gt: Enable ring scheduling for gen5-7 Chris Wilson
2021-02-08 10:52 ` [Intel-gfx] [PATCH 30/31] drm/i915: Support secure dispatch on gen6/gen7 Chris Wilson
2021-02-08 20:55 ` Dave Airlie
2021-02-08 22:49 ` Chris Wilson
2021-02-09 11:02 ` Tvrtko Ursulin
2021-02-08 10:52 ` [Intel-gfx] [PATCH 31/31] drm/i915/gt: Limit C-states while waiting for requests Chris Wilson
2021-02-08 15:43 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/31] drm/i915/gt: Ratelimit heartbeat completion probing Patchwork
2021-02-08 15:45 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-02-08 16:13 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-02-09 17:52 ` [Intel-gfx] [PATCH 01/31] " Mika Kuoppala
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=20210208105236.28498-19-chris@chris-wilson.co.uk \
--to=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.org \
/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).