drm/i915: Suspend submission tasklets around wedging

After staring hard at sequences like

[   28.199013]  systemd-1       2..s. 26062228us : execlists_submission_tasklet: rcs0 cs-irq head=0 [0?], tail=1 [1?]
[   28.199095]  systemd-1       2..s. 26062229us : execlists_submission_tasklet: rcs0 csb[1]: status=0x00000018:0x00000000, active=0x1
[   28.199177]  systemd-1       2..s. 26062230us : execlists_submission_tasklet: rcs0 out[0]: ctx=0.1, seqno=3, prio=-1024
[   28.199258]  systemd-1       2..s. 26062231us : execlists_submission_tasklet: rcs0 completed ctx=0
[   28.199340]  gem_eio-829     1..s1 26066853us : execlists_submission_tasklet: rcs0 in[0]:  ctx=1.1, seqno=1, prio=0
[   28.199421]   <idle>-0       2..s. 26066863us : execlists_submission_tasklet: rcs0 cs-irq head=1 [1?], tail=2 [2?]
[   28.199503]   <idle>-0       2..s. 26066865us : execlists_submission_tasklet: rcs0 csb[2]: status=0x00000001:0x00000000, active=0x1
[   28.199585]  gem_eio-829     1..s1 26067077us : execlists_submission_tasklet: rcs0 in[1]:  ctx=3.1, seqno=2, prio=0
[   28.199667]  gem_eio-829     1..s1 26067078us : execlists_submission_tasklet: rcs0 in[0]:  ctx=1.2, seqno=1, prio=0
[   28.199749]   <idle>-0       2..s. 26067084us : execlists_submission_tasklet: rcs0 cs-irq head=2 [2?], tail=3 [3?]
[   28.199830]   <idle>-0       2..s. 26067085us : execlists_submission_tasklet: rcs0 csb[3]: status=0x00008002:0x00000001, active=0x1
[   28.199912]   <idle>-0       2..s. 26067086us : execlists_submission_tasklet: rcs0 out[0]: ctx=1.2, seqno=1, prio=0
[   28.199994]  gem_eio-829     2..s. 28246084us : execlists_submission_tasklet: rcs0 cs-irq head=3 [3?], tail=4 [4?]
[   28.200096]  gem_eio-829     2..s. 28246088us : execlists_submission_tasklet: rcs0 csb[4]: status=0x00000014:0x00000001, active=0x5
[   28.200178]  gem_eio-829     2..s. 28246089us : execlists_submission_tasklet: rcs0 out[0]: ctx=0.0, seqno=0, prio=0
[   28.200260]  gem_eio-829     2..s. 28246127us : execlists_submission_tasklet: execlists_submission_tasklet:886 GEM_BUG_ON(buf[2 * head + 1] != port->context_id)

the conclusion is that the only place where the ports are reset to zero,
is from engine->cancel_requests called during i915_gem_set_wedged().

The race is horrible as it results from calling set-wedged on active HW
(the GPU reset failed) and as such we need to be careful as the HW state
changes beneath us. Fortunately, it's the same scary conditions as
affect normal reset, so we can reuse the same machinery to disable state
tracking as we clobber it.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104945
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Fixes: af7a8ffad9c5 ("drm/i915: Use rcu instead of stop_machine in set_wedged")
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180302113324.23189-2-chris@chris-wilson.co.uk
(cherry picked from commit 963ddd63c314e9b5d9cd999873d473a93aed5380)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index dd89abd..66ee9d8 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3205,8 +3205,10 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
         * rolling the global seqno forward (since this would complete requests
         * for which we haven't set the fence error to EIO yet).
         */
-       for_each_engine(engine, i915, id)
+       for_each_engine(engine, i915, id) {
+               i915_gem_reset_prepare_engine(engine);
                engine->submit_request = nop_submit_request;
+       }
 
        /*
         * Make sure no one is running the old callback before we proceed with
@@ -3244,6 +3246,8 @@ void i915_gem_set_wedged(struct drm_i915_private *i915)
                intel_engine_init_global_seqno(engine,
                                               intel_engine_last_submit(engine));
                spin_unlock_irqrestore(&engine->timeline->lock, flags);
+
+               i915_gem_reset_finish_engine(engine);
        }
 
        set_bit(I915_WEDGED, &i915->gpu_error.flags);

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7ece2f0..e0fca03 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -719,6 +719,8 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
        struct rb_node *rb;
        unsigned long flags;
 
+       GEM_TRACE("%s\n", engine->name);
+
        spin_lock_irqsave(&engine->timeline->lock, flags);
 
        /* Cancel the requests on the HW and clear the ELSP tracker. */
@@ -765,6 +767,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
         */
        clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 
+       /* Mark all CS interrupts as complete */
+       execlists->active = 0;
+
        spin_unlock_irqrestore(&engine->timeline->lock, flags);
 }