[PATCH 24/38] drm/i915: Replace global_seqno with a hangcheck heartbeat seqno

Chris Wilson chris at chris-wilson.co.uk
Thu Jan 17 19:42:05 UTC 2019


To determine whether an engine has 'struck', we simply check whether or
not is still on the same seqno for several seconds. To keep this simple
mechanism intact over the loss of a global seqno, we can simply add a
new global heartbeat seqno instead. As we cannot know the sequence in
which requests will then be completed, we use a primitive random number
generator instead (with a cycle long enough to not matter over an
interval of a few thousand requests between hangcheck samples).

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  7 ++++---
 drivers/gpu/drm/i915/intel_engine_cs.c  |  5 +++--
 drivers/gpu/drm/i915/intel_hangcheck.c  |  6 +++---
 drivers/gpu/drm/i915/intel_lrc.c        | 19 +++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 28 +++++++++++++++++++------
 drivers/gpu/drm/i915/intel_ringbuffer.h | 19 ++++++++++++++++-
 6 files changed, 67 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c77c909738e9..4f323c3c3bcb 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1297,7 +1297,7 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	with_intel_runtime_pm(dev_priv, wakeref) {
 		for_each_engine(engine, dev_priv, id) {
 			acthd[id] = intel_engine_get_active_head(engine);
-			seqno[id] = intel_engine_get_seqno(engine);
+			seqno[id] = intel_engine_get_hangcheck_seqno(engine);
 		}
 
 		intel_engine_get_instdone(dev_priv->engine[RCS], &instdone);
@@ -1317,8 +1317,9 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 	for_each_engine(engine, dev_priv, id) {
 		seq_printf(m, "%s:\n", engine->name);
 		seq_printf(m, "\tseqno = %x [current %x, last %x], %dms ago\n",
-			   engine->hangcheck.seqno, seqno[id],
-			   intel_engine_last_submit(engine),
+			   engine->hangcheck.last_seqno,
+			   seqno[id],
+			   engine->hangcheck.next_seqno,
 			   jiffies_to_msecs(jiffies -
 					    engine->hangcheck.action_timestamp));
 
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 429f21e16428..81349258c4d6 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1438,10 +1438,11 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	if (i915_terminally_wedged(&engine->i915->gpu_error))
 		drm_printf(m, "*** WEDGED ***\n");
 
-	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
+	drm_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x/%x [%d ms]\n",
 		   intel_engine_get_seqno(engine),
 		   intel_engine_last_submit(engine),
-		   engine->hangcheck.seqno,
+		   engine->hangcheck.last_seqno,
+		   engine->hangcheck.next_seqno,
 		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index e92f48a40a59..2d0ef22518b1 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -133,21 +133,21 @@ static void hangcheck_load_sample(struct intel_engine_cs *engine,
 				  struct hangcheck *hc)
 {
 	hc->acthd = intel_engine_get_active_head(engine);
-	hc->seqno = intel_engine_get_seqno(engine);
+	hc->seqno = intel_engine_get_hangcheck_seqno(engine);
 }
 
 static void hangcheck_store_sample(struct intel_engine_cs *engine,
 				   const struct hangcheck *hc)
 {
 	engine->hangcheck.acthd = hc->acthd;
-	engine->hangcheck.seqno = hc->seqno;
+	engine->hangcheck.last_seqno = hc->seqno;
 }
 
 static enum intel_engine_hangcheck_action
 hangcheck_get_action(struct intel_engine_cs *engine,
 		     const struct hangcheck *hc)
 {
-	if (engine->hangcheck.seqno != hc->seqno)
+	if (engine->hangcheck.last_seqno != hc->seqno)
 		return ENGINE_ACTIVE_SEQNO;
 
 	if (intel_engine_is_idle(engine))
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 87b334a29836..cbdd161889f2 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -177,6 +177,12 @@ static inline u32 intel_hws_seqno_address(struct intel_engine_cs *engine)
 	return i915_ggtt_offset(engine->status_page.vma) + I915_GEM_HWS_INDEX_ADDR;
 }
 
+static inline u32 intel_hws_hangcheck_address(struct intel_engine_cs *engine)
+{
+	return (i915_ggtt_offset(engine->status_page.vma) +
+		I915_GEM_HWS_HANGCHECK_ADDR);
+}
+
 static inline struct i915_priolist *to_priolist(struct rb_node *rb)
 {
 	return rb_entry(rb, struct i915_priolist, node);
@@ -2050,6 +2056,10 @@ static void gen8_emit_breadcrumb(struct i915_request *request, u32 *cs)
 				  request->fence.seqno,
 				  i915_timeline_seqno_address(request->timeline));
 
+	cs = gen8_emit_ggtt_write(cs,
+				  intel_engine_next_hangcheck_seqno(request->engine),
+				  intel_hws_hangcheck_address(request->engine));
+
 	cs = gen8_emit_ggtt_write(cs,
 				  request->global_seqno,
 				  intel_hws_seqno_address(request->engine));
@@ -2062,7 +2072,7 @@ static void gen8_emit_breadcrumb(struct i915_request *request, u32 *cs)
 
 	gen8_emit_wa_tail(request, cs);
 }
-static const int gen8_emit_breadcrumb_sz = 10 + WA_TAIL_DWORDS;
+static const int gen8_emit_breadcrumb_sz = 14 + WA_TAIL_DWORDS;
 
 static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 {
@@ -2075,6 +2085,11 @@ static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 				      PIPE_CONTROL_FLUSH_ENABLE |
 				      PIPE_CONTROL_CS_STALL);
 
+	cs = gen8_emit_ggtt_write_rcs(cs,
+				      intel_engine_next_hangcheck_seqno(request->engine),
+				      intel_hws_hangcheck_address(request->engine),
+				      PIPE_CONTROL_CS_STALL);
+
 	cs = gen8_emit_ggtt_write_rcs(cs,
 				      request->global_seqno,
 				      intel_hws_seqno_address(request->engine),
@@ -2088,7 +2103,7 @@ static void gen8_emit_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 
 	gen8_emit_wa_tail(request, cs);
 }
-static const int gen8_emit_breadcrumb_rcs_sz = 14 + WA_TAIL_DWORDS;
+static const int gen8_emit_breadcrumb_rcs_sz = 20 + WA_TAIL_DWORDS;
 
 static int gen8_init_rcs_context(struct i915_request *rq)
 {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 97732e387821..0bc513c1db33 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -455,17 +455,20 @@ static void gen6_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->fence.seqno;
 
+	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+	*cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
+	*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
 	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->global_seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
-	*cs++ = MI_NOOP;
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
 }
-static const int gen6_xcs_emit_breadcrumb_sz = 8;
+static const int gen6_xcs_emit_breadcrumb_sz = 10;
 
 #define GEN7_XCS_WA 32
 static void gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
@@ -476,6 +479,10 @@ static void gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->fence.seqno;
 
+	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
+	*cs++ = I915_GEM_HWS_HANGCHECK_ADDR | MI_FLUSH_DW_USE_GTT;
+	*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
 	*cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX;
 	*cs++ = I915_GEM_HWS_INDEX_ADDR | MI_FLUSH_DW_USE_GTT;
 	*cs++ = rq->global_seqno;
@@ -491,11 +498,12 @@ static void gen7_xcs_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	*cs++ = 0;
 
 	*cs++ = MI_USER_INTERRUPT;
+	*cs++ = MI_NOOP;
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
 }
-static const int gen7_xcs_emit_breadcrumb_sz = 10 + GEN7_XCS_WA * 3;
+static const int gen7_xcs_emit_breadcrumb_sz = 14 + GEN7_XCS_WA * 3;
 #undef GEN7_XCS_WA
 
 static void set_hwstam(struct intel_engine_cs *engine, u32 mask)
@@ -932,16 +940,21 @@ static void i9xx_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR;
 	*cs++ = rq->fence.seqno;
 
+	*cs++ = MI_STORE_DWORD_INDEX;
+	*cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
+	*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
 	*cs++ = MI_STORE_DWORD_INDEX;
 	*cs++ = I915_GEM_HWS_INDEX_ADDR;
 	*cs++ = rq->global_seqno;
 
 	*cs++ = MI_USER_INTERRUPT;
+	*cs++ = MI_NOOP;
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
 }
-static const int i9xx_emit_breadcrumb_sz = 8;
+static const int i9xx_emit_breadcrumb_sz = 12;
 
 #define GEN5_WA_STORES 8 /* must be at least 1! */
 static void gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
@@ -956,6 +969,10 @@ static void gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	*cs++ = I915_GEM_HWS_SEQNO_ADDR;
 	*cs++ = rq->fence.seqno;
 
+	*cs++ = MI_STORE_DWORD_INDEX;
+	*cs++ = I915_GEM_HWS_HANGCHECK_ADDR;
+	*cs++ = intel_engine_next_hangcheck_seqno(rq->engine);
+
 	BUILD_BUG_ON(GEN5_WA_STORES < 1);
 	for (i = 0; i < GEN5_WA_STORES; i++) {
 		*cs++ = MI_STORE_DWORD_INDEX;
@@ -964,12 +981,11 @@ static void gen5_emit_breadcrumb(struct i915_request *rq, u32 *cs)
 	}
 
 	*cs++ = MI_USER_INTERRUPT;
-	*cs++ = MI_NOOP;
 
 	rq->tail = intel_ring_offset(rq, cs);
 	assert_ring_tail_valid(rq->ring, rq->tail);
 }
-static const int gen5_emit_breadcrumb_sz = GEN5_WA_STORES * 3 + 6;
+static const int gen5_emit_breadcrumb_sz = GEN5_WA_STORES * 3 + 8;
 #undef GEN5_WA_STORES
 
 static void
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index f087efa6a17e..24562a7603ab 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -6,6 +6,7 @@
 
 #include <linux/hashtable.h>
 #include <linux/irq_work.h>
+#include <linux/random.h>
 #include <linux/seqlock.h>
 
 #include "i915_gem_batch_pool.h"
@@ -119,7 +120,8 @@ struct intel_instdone {
 
 struct intel_engine_hangcheck {
 	u64 acthd;
-	u32 seqno;
+	u32 last_seqno;
+	u32 next_seqno;
 	unsigned long action_timestamp;
 	struct intel_instdone instdone;
 };
@@ -705,6 +707,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_GEM_HWS_INDEX_ADDR (I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
 #define I915_GEM_HWS_PREEMPT_INDEX	0x32
 #define I915_GEM_HWS_PREEMPT_ADDR (I915_GEM_HWS_PREEMPT_INDEX << MI_STORE_DWORD_INDEX_SHIFT)
+#define I915_GEM_HWS_HANGCHECK		0x34
+#define I915_GEM_HWS_HANGCHECK_ADDR (I915_GEM_HWS_HANGCHECK << MI_STORE_DWORD_INDEX_SHIFT)
 #define I915_GEM_HWS_SEQNO		0x40
 #define I915_GEM_HWS_SEQNO_ADDR (I915_GEM_HWS_SEQNO << MI_STORE_DWORD_INDEX_SHIFT)
 #define I915_GEM_HWS_SCRATCH_INDEX	0x80
@@ -1056,4 +1060,17 @@ static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
 
 #endif
 
+static inline u32 intel_engine_next_hangcheck_seqno(struct intel_engine_cs *engine)
+{
+	engine->hangcheck.next_seqno =
+		next_pseudo_random32(engine->hangcheck.next_seqno);
+
+	return engine->hangcheck.next_seqno;
+}
+
+static inline u32 intel_engine_get_hangcheck_seqno(struct intel_engine_cs *engine)
+{
+	return intel_read_status_page(engine, I915_GEM_HWS_HANGCHECK);
+}
+
 #endif /* _INTEL_RINGBUFFER_H_ */
-- 
2.20.1



More information about the Intel-gfx-trybot mailing list