We cannot call kthread_park() from softirq context, so let's avoid it
entirely during the reset. We wanted to suspend the signaler so that it
would not mark a request as complete at the same time as we marked it as
being in error. Instead of parking the signaling, stop the engine from
advancing so that the GPU doesn't emit the breadcrumb for our chosen
"guilty" request.
Signed-off-by: Chris Wilson <ch...@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuopp...@linux.intel.com>
Cc: Michał Winiarski <michal.winiar...@intel.com>
CC: Michel Thierry <michel.thie...@intel.com>
Cc: Jeff McGee <jeff.mc...@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursu...@intel.com>
---
drivers/gpu/drm/i915/i915_gem.c | 14 --------------
drivers/gpu/drm/i915/intel_lrc.c | 21 +++++++++++++++++++++
drivers/gpu/drm/i915/intel_ringbuffer.c | 18 ++++++++++++++++++
3 files changed, 39 insertions(+), 14 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index abf661d40641..b0fe452ce17c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3015,18 +3015,6 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs
*engine)
*/
intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
- /*
- * Prevent the signaler thread from updating the request
- * state (by calling dma_fence_signal) as we are processing
- * the reset. The write from the GPU of the seqno is
- * asynchronous and the signaler thread may see a different
- * value to us and declare the request complete, even though
- * the reset routine have picked that request as the active
- * (incomplete) request. This conflict is not handled
- * gracefully!
- */
- kthread_park(engine->breadcrumbs.signaler);
-
request = engine->reset.prepare(engine);
if (request && request->fence.error == -EIO)
request = ERR_PTR(-EIO); /* Previous reset failed! */
@@ -3229,8 +3217,6 @@ void i915_gem_reset_finish_engine(struct intel_engine_cs
*engine)
{
engine->reset.finish(engine);
- kthread_unpark(engine->breadcrumbs.signaler);
-
intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index cae10ebf9432..16e4f3f6bbbf 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1839,6 +1839,21 @@ static int gen9_init_render_ring(struct intel_engine_cs
*engine)
return 0;
}
+static void set_stop_engine(struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *dev_priv = engine->i915;
+ const u32 base = engine->mmio_base;
+ const i915_reg_t mode = RING_MI_MODE(base);
+
+ GEM_TRACE("%s\n", engine->name);
+ I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+ if (__intel_wait_for_register_fw(dev_priv,
+ mode, MODE_IDLE, MODE_IDLE,
+ 1000, 0,
+ NULL))
+ GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+}
+
static struct i915_request *
execlists_reset_prepare(struct intel_engine_cs *engine)
{
@@ -1878,6 +1893,12 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
if (request) {
unsigned long flags;
+ /*
+ * Prevent the breadcrumb from advancing before we decide
+ * which request is currently active.
+ */
+ set_stop_engine(engine);
+
spin_lock_irqsave(&engine->timeline.lock, flags);
list_for_each_entry_from_reverse(request,
&engine->timeline.requests,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c
b/drivers/gpu/drm/i915/intel_ringbuffer.c
index af5a178366ed..bb88a92fcc1e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -531,8 +531,26 @@ static int init_ring_common(struct intel_engine_cs *engine)
return ret;
}
+static void set_stop_engine(struct intel_engine_cs *engine)
+{
+ struct drm_i915_private *dev_priv = engine->i915;
+ const u32 base = engine->mmio_base;
+ const i915_reg_t mode = RING_MI_MODE(base);
+
+ I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+ if (__intel_wait_for_register_fw(dev_priv,
+ mode, MODE_IDLE, MODE_IDLE,
+ 1000, 0,
+ NULL))
+ DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
+ engine->name);
+}
