[PATCH 45/57] drm/i915/gt: Track timeline GGTT offset separately from subpage offset
Chris Wilson
chris at chris-wilson.co.uk
Sun Jan 31 14:08:20 UTC 2021
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 at chris-wilson.co.uk>
Reviewed-by: Matthew Brost <matthew.brost at 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 | 1 -
.../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 +-
10 files changed, 23 insertions(+), 26 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_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 15d4a1973582..922399705634 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1452,7 +1452,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
i915_sched_show(m, intel_engine_get_scheduler(engine),
i915_request_show, 8);
-
drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base);
wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
if (wakeref) {
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index c8ae2f0c52b9..920803445451 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -3598,7 +3598,7 @@ 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 3635dc5aa8c3..ab3ab7a65ce2 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -1666,7 +1666,7 @@ void i915_sched_show(struct drm_printer *m,
if (tl) {
drm_printf(m, "\t\tring->hwsp: 0x%08x\n",
- tl->hwsp_offset);
+ tl->ggtt_offset);
intel_timeline_put(tl);
}
--
2.20.1
More information about the Intel-gfx-trybot
mailing list