drm/i915: Replace global_seqno with a hangcheck heartbeat seqno

To determine whether an engine has 'stuck', 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).

The alternative to using a dedicated seqno on every request is to issue
a heartbeat request and query its progress through the system. Sadly
this requires us to reduce struct_mutex so that we can issue requests
without requiring that bkl.

v2: And without the extra CS_STALL for the hangcheck seqno -- we don't
need strict serialisation with what comes later, we just need to be sure
we don't write the hangcheck seqno before our batch is flushed.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190226094922.31617-1-chris@chris-wilson.co.uk

1 files changed, 18 insertions, 1 deletions

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 5d45ad4ecca9..2869aaa9d225 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;
 };
@@ -726,6 +728,8 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_GEM_HWS_INDEX_ADDR		(I915_GEM_HWS_INDEX * sizeof(u32))
 #define I915_GEM_HWS_PREEMPT		0x32
 #define I915_GEM_HWS_PREEMPT_ADDR	(I915_GEM_HWS_PREEMPT * sizeof(u32))
+#define I915_GEM_HWS_HANGCHECK		0x34
+#define I915_GEM_HWS_HANGCHECK_ADDR	(I915_GEM_HWS_HANGCHECK * sizeof(u32))
 #define I915_GEM_HWS_SEQNO		0x40
 #define I915_GEM_HWS_SEQNO_ADDR		(I915_GEM_HWS_SEQNO * sizeof(u32))
 #define I915_GEM_HWS_SCRATCH		0x80
@@ -1086,4 +1090,17 @@ 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)
+{
+	return engine->hangcheck.next_seqno =
+		next_pseudo_random32(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_ */