drm/i915: Reorder semaphore deadlock check

If a semaphore is waiting on another ring, which in turn happens to be
waiting on the first ring, but that second semaphore has been signalled,
we will be able to kick the second ring and so can treat the first ring
as a valid WAIT and not as HUNG.

v2: Be paranoid and cap the potential recursion depth whilst visiting
the semaphore signallers. (Mika)

References: https://bugs.freedesktop.org/show_bug.cgi?id=54226
References: https://bugs.freedesktop.org/show_bug.cgi?id=75502
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index cf288a95347c02c81d195e86f9e8bd8469660314..69aaa1100986ec6c4a8c76c4b3a6e040e2b0d1e4 100644 (file)
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2847,10 +2847,14 @@ static int semaphore_passed(struct intel_engine_cs *ring)
        struct intel_engine_cs *signaller;
        u32 seqno, ctl;
 
-       ring->hangcheck.deadlock = true;
+       ring->hangcheck.deadlock++;
 
        signaller = semaphore_waits_for(ring, &seqno);
-       if (signaller == NULL || signaller->hangcheck.deadlock)
+       if (signaller == NULL)
+               return -1;
+
+       /* Prevent pathological recursion due to driver bugs */
+       if (signaller->hangcheck.deadlock >= I915_NUM_RINGS)
                return -1;
 
        /* cursory check for an unkickable deadlock */
@@ -2858,7 +2862,13 @@ static int semaphore_passed(struct intel_engine_cs *ring)
        if (ctl & RING_WAIT_SEMAPHORE && semaphore_passed(signaller) < 0)
                return -1;
 
-       return i915_seqno_passed(signaller->get_seqno(signaller, false), seqno);
+       if (i915_seqno_passed(signaller->get_seqno(signaller, false), seqno))
+               return 1;
+
+       if (signaller->hangcheck.deadlock)
+               return -1;
+
+       return 0;
 }
 
 static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
@@ -2867,7 +2877,7 @@ static void semaphore_clear_deadlocks(struct drm_i915_private *dev_priv)
        int i;
 
        for_each_ring(ring, dev_priv, i)
-               ring->hangcheck.deadlock = false;
+               ring->hangcheck.deadlock = 0;
 }
 
 static enum intel_ring_hangcheck_action

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 910c83cf7d441e26d226e4c975ad712949d32f0a..e72017bdcd7f8e7df95a1ab75853d8351b8bbb9d 100644 (file)
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -55,7 +55,7 @@ struct intel_ring_hangcheck {
        u32 seqno;
        int score;
        enum intel_ring_hangcheck_action action;
-       bool deadlock;
+       int deadlock;
 };
 
 struct intel_ringbuffer {