From 7b0f9123badc793d3d76a451ba0f8199fdb136d7 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Wed, 21 Jul 2021 14:50:55 -0700
Subject: drm/i915/guc: Ensure request ordering via completion fences
Git-commit: 38d5ec43063c5908d1cda4e7eb24330405ccdb6f
Patch-mainline: v5.15-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225
If two requests are on the same ring, they are explicitly ordered by the
HW. So, a submission fence is sufficient to ensure ordering when using
the new GuC submission interface. Conversely, if two requests share a
timeline and are on the same physical engine but different context this
doesn't ensure ordering on the new GuC submission interface. So, a
completion fence needs to be used to ensure ordering.
v2:
(Daniele)
- Don't delete spin lock
v3:
(Daniele)
- Delete forward dec
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210721215101.139794-13-matthew.brost@intel.com
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/i915/i915_request.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index d35d7c96839d..6594cb2f8ebd 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -432,6 +432,7 @@ void i915_request_retire_upto(struct i915_request *rq)
do {
tmp = list_first_entry(&tl->requests, typeof(*tmp), link);
+ GEM_BUG_ON(!i915_request_completed(tmp));
} while (i915_request_retire(tmp) && tmp != rq);
}
@@ -1463,7 +1464,8 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
return ret;
}
- if (is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask)))
+ if (!intel_engine_uses_guc(to->engine) &&
+ is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask)))
ret = await_request_submit(to, from);
else
ret = emit_semaphore_wait(to, from, I915_FENCE_GFP);
@@ -1622,6 +1624,8 @@ __i915_request_add_to_timeline(struct i915_request *rq)
prev = to_request(__i915_active_fence_set(&timeline->last_request,
&rq->fence));
if (prev && !__i915_request_is_complete(prev)) {
+ bool uses_guc = intel_engine_uses_guc(rq->engine);
+
/*
* The requests are supposed to be kept in order. However,
* we need to be wary in case the timeline->last_request
@@ -1632,7 +1636,9 @@ __i915_request_add_to_timeline(struct i915_request *rq)
i915_seqno_passed(prev->fence.seqno,
rq->fence.seqno));
- if (is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask))
+ if ((!uses_guc &&
+ is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) ||
+ (uses_guc && prev->context == rq->context))
i915_sw_fence_await_sw_fence(&rq->submit,
&prev->submit,
&rq->submitq);
--
2.38.1