Now that we have split out the seqno-barrier from the
engine->get_seqno() callback itself, we can move the users of the
seqno-barrier to the required callsites simplifying the common code and
making the required workaround handling much more explicit.
Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
---
drivers/gpu/drm/i915/i915_debugfs.c | 2 +-
drivers/gpu/drm/i915/i915_drv.h | 17 ++++++++---------
drivers/gpu/drm/i915/i915_gem.c | 24 ++++++++++++++++--------
drivers/gpu/drm/i915/intel_display.c | 2 +-
drivers/gpu/drm/i915/intel_pm.c | 4 ++--
5 files changed, 28 insertions(+), 21 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c
b/drivers/gpu/drm/i915/i915_debugfs.c
index 02a923feeb7d..a4287d729fd9 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -632,7 +632,7 @@ static int i915_gem_pageflip_info(struct seq_file *m, void
*data)
i915_gem_request_get_seqno(work->flip_queued_req),
dev_priv->next_seqno,
engine->get_seqno(engine),
-
i915_gem_request_completed(work->flip_queued_req, true));
+
i915_gem_request_completed(work->flip_queued_req));
} else
seq_printf(m, "Flip not associated with any
ring\n");
seq_printf(m, "Flip queued on frame %d, (was ready on
frame %d), now %d\n",
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7b329464e8eb..6e24b404542d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3142,20 +3142,14 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2)
return (int32_t)(seq1 - seq2) >= 0;
}
-static inline bool i915_gem_request_started(struct drm_i915_gem_request *req,
- bool lazy_coherency)
+static inline bool i915_gem_request_started(struct drm_i915_gem_request *req)
{
- if (!lazy_coherency && req->engine->irq_seqno_barrier)
- req->engine->irq_seqno_barrier(req->engine);
return i915_seqno_passed(req->engine->get_seqno(req->engine),
req->previous_seqno);
}
-static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
- bool lazy_coherency)
+static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req)
{
- if (!lazy_coherency && req->engine->irq_seqno_barrier)
- req->engine->irq_seqno_barrier(req->engine);
return i915_seqno_passed(req->engine->get_seqno(req->engine),
req->seqno);
}
@@ -3823,6 +3817,8 @@ static inline void i915_trace_irq_get(struct
intel_engine_cs *engine,
static inline bool __i915_request_irq_complete(struct drm_i915_gem_request
*req)
{
+ struct intel_engine_cs *engine = req->engine;
+
/* Ensure our read of the seqno is coherent so that we
* do not "miss an interrupt" (i.e. if this is the last
* request and the seqno write from the GPU is not visible
@@ -3834,7 +3830,10 @@ static inline bool __i915_request_irq_complete(struct
drm_i915_gem_request *req)
* but it is easier and safer to do it every time the waiter
* is woken.
*/
- if (i915_gem_request_completed(req, false))
+ if (engine->irq_seqno_barrier)
+ engine->irq_seqno_barrier(engine);
+
+ if (i915_gem_request_completed(req))
return true;
/* We need to check whether any gpu reset happened in between
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9348b5d7de0e..16ef7682ed0c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1171,12 +1171,12 @@ static bool __i915_spin_request(struct
drm_i915_gem_request *req, int state)
*/
/* Only spin if we know the GPU is processing this request */
- if (!i915_gem_request_started(req, true))
+ if (!i915_gem_request_started(req))
return false;
timeout = local_clock_us(&cpu) + 5;
do {
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(req))
return true;
if (signal_pending_state(state, current))
@@ -1223,7 +1223,7 @@ int __i915_wait_request(struct drm_i915_gem_request *req,
if (list_empty(&req->list))
return 0;
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(req))
return 0;
timeout_remain = MAX_SCHEDULE_TIMEOUT;
@@ -2776,8 +2776,16 @@ i915_gem_find_active_request(struct intel_engine_cs
*engine)
{
struct drm_i915_gem_request *request;
+ /* We are called by the error capture and reset at a random
+ * point in time. In particular, note that neither is crucially
+ * ordered with an interrupt. After a hang, the GPU is dead and we
+ * assume that no more writes can happen (we waited long enough for
+ * all writes that were in transaction to be flushed) - adding an
+ * extra delay for a recent interrupt is pointless. Hence, we do
+ * not need an engine->irq_seqno_barrier() before the seqno reads.
+ */
list_for_each_entry(request, &engine->request_list, list) {
- if (i915_gem_request_completed(request, false))
+ if (i915_gem_request_completed(request))
continue;
return request;
@@ -2908,7 +2916,7 @@ i915_gem_retire_requests_ring(struct intel_engine_cs
*engine)
struct drm_i915_gem_request,
list);
- if (!i915_gem_request_completed(request, true))
+ if (!i915_gem_request_completed(request))
break;
i915_gem_request_retire(request);
@@ -2932,7 +2940,7 @@ i915_gem_retire_requests_ring(struct intel_engine_cs
*engine)
}
if (unlikely(engine->trace_irq_req &&
- i915_gem_request_completed(engine->trace_irq_req, true))) {
+ i915_gem_request_completed(engine->trace_irq_req))) {
engine->irq_put(engine);
i915_gem_request_assign(&engine->trace_irq_req, NULL);
}
@@ -3029,7 +3037,7 @@ i915_gem_object_flush_active(struct drm_i915_gem_object
*obj)
if (req == NULL)
continue;
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(req))
i915_gem_object_retire__read(obj, i);
}
@@ -3135,7 +3143,7 @@ __i915_gem_object_sync(struct drm_i915_gem_object *obj,
if (to == from)
return 0;
- if (i915_gem_request_completed(from_req, true))
+ if (i915_gem_request_completed(from_req))
return 0;
if (!i915_semaphore_is_enabled(to_i915(obj->base.dev))) {
diff --git a/drivers/gpu/drm/i915/intel_display.c
b/drivers/gpu/drm/i915/intel_display.c
index 94d28c795e22..4f90920b10a7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11449,7 +11449,7 @@ static bool __intel_pageflip_stall_check(struct
drm_device *dev,
if (work->flip_ready_vblank == 0) {
if (work->flip_queued_req &&
- !i915_gem_request_completed(work->flip_queued_req, true))
+ !i915_gem_request_completed(work->flip_queued_req))
return false;
work->flip_ready_vblank = drm_crtc_vblank_count(crtc);
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index adb64638f595..abb6ab84ad3c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7531,7 +7531,7 @@ static void __intel_rps_boost_work(struct work_struct
*work)
struct request_boost *boost = container_of(work, struct request_boost,
work);
struct drm_i915_gem_request *req = boost->req;
- if (!i915_gem_request_completed(req, true))
+ if (!i915_gem_request_completed(req))
gen6_rps_boost(req->i915, NULL, req->emitted_jiffies);
i915_gem_request_unreference(req);
@@ -7545,7 +7545,7 @@ void intel_queue_rps_boost_for_request(struct
drm_i915_gem_request *req)
if (req == NULL || INTEL_GEN(req->i915) < 6)
return;
- if (i915_gem_request_completed(req, true))
+ if (i915_gem_request_completed(req))
return;
boost = kmalloc(sizeof(*boost), GFP_ATOMIC);
--
2.8.1
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
