diff options
| -rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_context.h | 18 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_context_types.h | 1 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 3 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 34 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/i915_perf_types.h | 8 | ||||
| -rw-r--r-- | include/uapi/drm/i915_drm.h | 11 |
6 files changed, 72 insertions, 3 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h index 9234586830d1..cfe80590f0ed 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h @@ -114,6 +114,24 @@ i915_gem_context_clear_user_engines(struct i915_gem_context *ctx) clear_bit(CONTEXT_USER_ENGINES, &ctx->flags); } +static inline bool +i915_gem_context_nopreempt(const struct i915_gem_context *ctx) +{ + return test_bit(CONTEXT_NOPREEMPT, &ctx->flags); +} + +static inline void +i915_gem_context_set_nopreempt(struct i915_gem_context *ctx) +{ + set_bit(CONTEXT_NOPREEMPT, &ctx->flags); +} + +static inline void +i915_gem_context_clear_nopreempt(struct i915_gem_context *ctx) +{ + clear_bit(CONTEXT_NOPREEMPT, &ctx->flags); +} + static inline bool i915_gem_context_is_kernel(struct i915_gem_context *ctx) { return !ctx->file_priv; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index ab8e1367dfc8..fe97b8ba4fda 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -146,6 +146,7 @@ struct i915_gem_context { #define CONTEXT_CLOSED 1 #define CONTEXT_FORCE_SINGLE_SUBMISSION 2 #define CONTEXT_USER_ENGINES 3 +#define CONTEXT_NOPREEMPT 4 struct mutex mutex; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 580c15e74a0a..98cd92320afb 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2079,6 +2079,9 @@ static int eb_submit(struct i915_execbuffer *eb) if (err) return err; + if (i915_gem_context_nopreempt(eb->gem_context)) + eb->request->flags |= I915_REQUEST_NOPREEMPT; + return 0; } diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 372c91f6a28e..54ec1c4190ac 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -344,6 +344,8 @@ static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = { * struct perf_open_properties - for validated properties given to open a stream * @sample_flags: `DRM_I915_PERF_PROP_SAMPLE_*` properties are tracked as flags * @single_context: Whether a single or all gpu contexts should be monitored + * @hold_preemption: Whether the preemption is disabled for the filtered + * context * @ctx_handle: A gem ctx handle for use with @single_context * @metrics_set: An ID for an OA unit metric set advertised via sysfs * @oa_format: An OA unit HW report format @@ -359,6 +361,7 @@ struct perf_open_properties { u32 sample_flags; u64 single_context:1; + u64 hold_preemption:1; u64 ctx_handle; /* OA sampling state */ @@ -2514,6 +2517,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, if (WARN_ON(stream->oa_buffer.format_size == 0)) return -EINVAL; + stream->hold_preemption = props->hold_preemption; + stream->oa_buffer.format = perf->oa_formats[props->oa_format].format; @@ -2834,6 +2839,9 @@ static void i915_perf_enable_locked(struct i915_perf_stream *stream) if (stream->ops->enable) stream->ops->enable(stream); + + if (stream->hold_preemption) + i915_gem_context_set_nopreempt(stream->ctx); } /** @@ -2858,6 +2866,9 @@ static void i915_perf_disable_locked(struct i915_perf_stream *stream) /* Allow stream->ops->disable() to refer to this */ stream->enabled = false; + if (stream->hold_preemption) + i915_gem_context_clear_nopreempt(stream->ctx); + if (stream->ops->disable) stream->ops->disable(stream); } @@ -3067,6 +3078,15 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, } } + if (props->hold_preemption) { + if (!props->single_context) { + DRM_DEBUG("preemption disable with no context\n"); + ret = -EINVAL; + goto err; + } + privileged_op = true; + } + /* * On Haswell the OA unit supports clock gating off for a specific * context and in this mode there's no visibility of metrics for the @@ -3081,7 +3101,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to * enable the OA unit by default. */ - if (IS_HASWELL(perf->i915) && specific_ctx) + if (IS_HASWELL(perf->i915) && specific_ctx && !props->hold_preemption) privileged_op = false; /* Similar to perf's kernel.perf_paranoid_cpu sysctl option @@ -3091,7 +3111,7 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf, */ if (privileged_op && i915_perf_stream_paranoid && !capable(CAP_SYS_ADMIN)) { - DRM_DEBUG("Insufficient privileges to open system-wide i915 perf stream\n"); + DRM_DEBUG("Insufficient privileges to open i915 perf stream\n"); ret = -EACCES; goto err_ctx; } @@ -3293,6 +3313,9 @@ static int read_properties_unlocked(struct i915_perf *perf, props->oa_periodic = true; props->oa_period_exponent = value; break; + case DRM_I915_PERF_PROP_HOLD_PREEMPTION: + props->hold_preemption = !!value; + break; case DRM_I915_PERF_PROP_MAX: MISSING_CASE(id); return -EINVAL; @@ -4066,8 +4089,13 @@ int i915_perf_ioctl_version(void) * * 2: Added runtime modification of OA config. * I915_PERF_IOCTL_CONFIG + * + * 3: Add DRM_I915_PERF_PROP_HOLD_PREEMPTION parameter to hold + * preemption on a particular context so that performance data is + * accessible from a delta of MI_RPC reports without looking at the + * OA buffer. */ - return 2; + return 3; } #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index d35a3c1946c3..a1f733fc905a 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -171,6 +171,14 @@ struct i915_perf_stream { bool enabled; /** + * @hold_preemption: Whether preemption is put on hold for command + * submissions done on the @ctx. This is useful for some drivers that + * cannot easily post process the OA buffer context to subtract delta + * of performance counters not associated with @ctx. + */ + bool hold_preemption; + + /** * @ops: The callbacks providing the implementation of this specific * type of configured stream. */ diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index b008ce8b4e6f..63d40cba97e0 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1890,6 +1890,17 @@ enum drm_i915_perf_property_id { */ DRM_I915_PERF_PROP_OA_EXPONENT, + /** + * Specifying this property is only valid when specify a context to + * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property + * will hold preemption of the particular context we want to gather + * performance data about. The execbuf2 submissions must include a + * drm_i915_gem_execbuffer_ext_perf parameter for this to apply. + * + * This property is available in perf revision 3. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; |