Whilst investigating some mysterious failures with hangcheck not running
during gem_busy/basic-hang-default, the question is why did we decide to
cancel the retire_work (which queues the hangcheck)? That decision is
based around GT activity, so include that information in the debug
report.
v2: Include the GT awake status in the error state
Signed-off-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/i915_debugfs.c | 17 +++++++++++++----
drivers/gpu/drm/i915/i915_drv.h | 1 +
drivers/gpu/drm/i915/i915_gpu_error.c | 3 +++
3 files changed, 17 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 9b697fd03721..ee4bf6f71cab 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1341,14 +1341,17 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
} else
seq_printf(m, "Hangcheck inactive\n");
+ seq_printf(m, "GT active? %s\n", yesno(dev_priv->gt.awake));
+
for_each_engine(engine, dev_priv, id) {
struct intel_breadcrumbs *b = &engine->breadcrumbs;
struct rb_node *rb;
seq_printf(m, "%s:\n", engine->name);
- seq_printf(m, "\tseqno = %x [current %x, last %x]\n",
+ seq_printf(m, "\tseqno = %x [current %x, last %x], inflight %d\n",
engine->hangcheck.seqno, seqno[id],
- intel_engine_last_submit(engine));
+ intel_engine_last_submit(engine),
+ engine->timeline->inflight_seqnos);
seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s\n",
yesno(intel_engine_has_waiter(engine)),
yesno(test_bit(engine->id,
@@ -3240,6 +3243,11 @@ static int i915_engine_info(struct seq_file *m, void *unused)
intel_runtime_pm_get(dev_priv);
+ seq_printf(m, "GT awake? %s\n",
+ yesno(dev_priv->gt.awake));
+ seq_printf(m, "Global active requests: %d\n",
+ dev_priv->gt.active_requests);
+
for_each_engine(engine, dev_priv, id) {
struct intel_breadcrumbs *b = &engine->breadcrumbs;
struct drm_i915_gem_request *rq;
@@ -3247,11 +3255,12 @@ static int i915_engine_info(struct seq_file *m, void *unused)
u64 addr;
seq_printf(m, "%s\n", engine->name);
- seq_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms]\n",
+ seq_printf(m, "\tcurrent seqno %x, last %x, hangcheck %x [%d ms], inflight %d\n",
intel_engine_get_seqno(engine),
intel_engine_last_submit(engine),
engine->hangcheck.seqno,
- jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
+ jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp),
+ engine->timeline->inflight_seqnos);
rcu_read_lock();
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 7a2f2e4468d6..66f19924828a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -936,6 +936,7 @@ struct i915_gpu_state {
char error_msg[128];
bool simulated;
+ bool awake;
int iommu;
u32 reset_count;
u32 suspend_count;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 76855e1d8795..b4ae1464e0ab 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -632,6 +632,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
CSR_VERSION_MINOR(csr->version));
}
+ err_printf(m, "GT awake: %s\n", yesno(error->awake));
err_printf(m, "EIR: 0x%08x\n", error->eir);
err_printf(m, "IER: 0x%08x\n", error->ier);
for (i = 0; i < error->ngtier; i++)
@@ -1653,6 +1654,8 @@ static void i915_error_capture_msg(struct drm_i915_private *dev_priv,
static void i915_capture_gen_state(struct drm_i915_private *dev_priv,
struct i915_gpu_state *error)
{
+ error->awake = dev_priv->gt.awake;
+
error->iommu = -1;
#ifdef CONFIG_INTEL_IOMMU
error->iommu = intel_iommu_gfx_mapped;
--
2.11.0
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
