[PATCH 17/20] drm/i915: Watchdog timeout: DRM kernel interface to set the timeout
Michel Thierry
michel.thierry at intel.com
Thu Apr 6 16:43:04 UTC 2017
Final enablement patch for GPU hang detection using watchdog timeout.
Using the gem_context_setparam ioctl, users can specify the desired
timeout value in microseconds, and the driver will do the conversion to
'timestamps'.
The recommended default watchdog threshold for video engines is 60000 us,
since this has been _empirically determined_ to be a good compromise for
low-latency requirements and low rate of false positives. The default
register value is ~106000us and the theoretical max value (all 1s) is
353 seconds.
Note, UABI engine ids and i915 engine ids are different, and this patch
uses the i915 ones. Some kind of mapping table [1] is required if we
decide to use the UABI engine ids.
[1] http://patchwork.freedesktop.org/patch/msgid/20170329135831.30254-2-chris@chris-wilson.co.uk
v2: Fixed get api to return values in microseconds. Threshold updated to
be per context engine. Check for u32 overflow. Capture ctx threshold
value in error state.
v3: Add a way to get array size, short-cut to disable all thresholds,
return EFAULT / EINVAL as needed. Move the capture of the threshold
value in the error state into a new patch.
Signed-off-by: Tomas Elf <tomas.elf at intel.com>
Signed-off-by: Arun Siluvery <arun.siluvery at linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
drivers/gpu/drm/i915/i915_gem_context.c | 100 ++++++++++++++++++++++++++++++++
drivers/gpu/drm/i915/i915_gem_context.h | 20 +++++++
drivers/gpu/drm/i915/intel_lrc.c | 2 +-
include/uapi/drm/i915_drm.h | 1 +
4 files changed, 122 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index edbed85a1c88..7d244907cbce 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -422,6 +422,100 @@ i915_gem_context_create_gvt(struct drm_device *dev)
return ctx;
}
+/* Return the timer count threshold in microseconds. */
+int i915_gem_context_get_watchdog(struct i915_gem_context *ctx,
+ struct drm_i915_gem_context_param *args)
+{
+ struct drm_i915_private *dev_priv = ctx->i915;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ u32 threshold_in_us[I915_NUM_ENGINES];
+
+ if (args->size == 0)
+ goto out;
+
+ if (args->size < sizeof(threshold_in_us))
+ return -EFAULT;
+
+ if (!dev_priv->engine[VCS]->emit_start_watchdog)
+ return -ENODEV;
+
+ for_each_engine(engine, dev_priv, id) {
+ struct intel_context *ce = &ctx->engine[id];
+
+ threshold_in_us[id] = watchdog_to_us(ce->watchdog_threshold);
+ }
+
+ mutex_unlock(&dev_priv->drm.struct_mutex);
+ if (__copy_to_user(u64_to_user_ptr(args->value),
+ &threshold_in_us,
+ sizeof(threshold_in_us))) {
+ mutex_lock(&dev_priv->drm.struct_mutex);
+ return -EFAULT;
+ }
+ mutex_lock(&dev_priv->drm.struct_mutex);
+
+out:
+ args->size = sizeof(threshold_in_us);
+
+ return 0;
+}
+
+/*
+ * Based on time out value in microseconds (us) calculate
+ * timer count thresholds needed based on core frequency.
+ * Watchdog can be disabled by setting it to 0.
+ */
+int i915_gem_context_set_watchdog(struct i915_gem_context *ctx,
+ struct drm_i915_gem_context_param *args)
+{
+ struct drm_i915_private *dev_priv = ctx->i915;
+ struct intel_engine_cs *engine;
+ enum intel_engine_id id;
+ u32 threshold[I915_NUM_ENGINES];
+
+ memset(&threshold, 0, sizeof(threshold));
+
+ /* shortcut to disable in all engines */
+ if (args->size == 0)
+ goto set_watchdog;
+
+ if (args->size < sizeof(threshold))
+ return -EFAULT;
+
+ if (!dev_priv->engine[VCS]->emit_start_watchdog)
+ return -ENODEV;
+
+ mutex_unlock(&dev_priv->drm.struct_mutex);
+ if (copy_from_user(&threshold,
+ u64_to_user_ptr(args->value),
+ sizeof(threshold))) {
+ mutex_lock(&dev_priv->drm.struct_mutex);
+ return -EFAULT;
+ }
+ mutex_lock(&dev_priv->drm.struct_mutex);
+
+ /* not supported in blitter engine */
+ if (threshold[BCS] != 0)
+ return -EINVAL;
+
+ for_each_engine(engine, dev_priv, id) {
+ threshold[id] = watchdog_to_clock_counts(threshold[id]);
+
+ if (threshold[id] == -EINVAL)
+ return -EINVAL;
+ }
+
+set_watchdog:
+ for_each_engine(engine, dev_priv, id) {
+ struct intel_context *ce = &ctx->engine[id];
+
+ ce->watchdog_threshold = threshold[id];
+ }
+
+ return 0;
+}
+
int i915_gem_context_init(struct drm_i915_private *dev_priv)
{
struct i915_gem_context *ctx;
@@ -1061,6 +1155,9 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
case I915_CONTEXT_PARAM_BANNABLE:
args->value = i915_gem_context_is_bannable(ctx);
break;
+ case I915_CONTEXT_PARAM_WATCHDOG:
+ ret = i915_gem_context_get_watchdog(ctx, args);
+ break;
default:
ret = -EINVAL;
break;
@@ -1118,6 +1215,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
else
i915_gem_context_clear_bannable(ctx);
break;
+ case I915_CONTEXT_PARAM_WATCHDOG:
+ ret = i915_gem_context_set_watchdog(ctx, args);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 88700bdbb4e1..1c3cfa7dab4a 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -250,6 +250,26 @@ static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx)
return !ctx->file_priv;
}
+/*
+ * Timestamp timer resolution = 0.080 uSec,
+ * or 12500000 counts per second, or ~12 counts per microsecond.
+ */
+#define TIMESTAMP_CNTS_PER_USEC 12
+static inline u32 watchdog_to_us(u32 value_in_clock_counts)
+{
+ return value_in_clock_counts / TIMESTAMP_CNTS_PER_USEC;
+}
+
+static inline u32 watchdog_to_clock_counts(u64 value_in_us)
+{
+ u64 threshold = value_in_us * TIMESTAMP_CNTS_PER_USEC;
+
+ if (overflows_type(threshold, u32))
+ return -EINVAL;
+
+ return threshold;
+}
+
/* i915_gem_context.c */
int __must_check i915_gem_context_init(struct drm_i915_private *dev_priv);
void i915_gem_context_lost(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 6c7d5c0d0022..5e5bbcb2d1b4 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1478,7 +1478,7 @@ static int gen8_emit_flush_render(struct drm_i915_gem_request *request,
return 0;
}
-#define GEN8_WATCHDOG_1000US 0x2ee0 //XXX: Temp, replace with helper function
+#define GEN8_WATCHDOG_1000US watchdog_to_clock_counts(1000)
static void gen8_watchdog_irq_handler(unsigned long data)
{
struct intel_engine_cs *engine = (struct intel_engine_cs *)data;
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index f083931a7809..448c9c0faa69 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1293,6 +1293,7 @@ struct drm_i915_gem_context_param {
#define I915_CONTEXT_PARAM_GTT_SIZE 0x3
#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4
#define I915_CONTEXT_PARAM_BANNABLE 0x5
+#define I915_CONTEXT_PARAM_WATCHDOG 0x6
__u64 value;
};
--
2.11.0
More information about the Intel-gfx-trybot
mailing list