We would like to make use of perf in Vulkan. The Vulkan API is much lower level than OpenGL, with applications directly exposed to the concept of command buffers (pretty much equivalent to our batch buffers). In Vulkan, queries are always limited in scope to a command buffer. In OpenGL, the lack of command buffer concept meant that queries' duration could span multiple command buffers.
With that restriction gone in Vulkan, we would like to simplify measuring performance just by measuring the deltas between the counter snapshots written by 2 MI_RECORD_PERF_COUNT commands, rather than the more complex scheme we currently have in the GL driver, using 2 MI_RECORD_PERF_COUNT commands and doing some post processing on the stream of OA reports, coming from the global OA buffer, to remove any unrelated deltas in between the 2 MI_RECORD_PERF_COUNT. Disabling preemption only apply to a single context with which want to query performance counters for and is considered a privileged operation, by default protected by CAP_SYS_ADMIN. It is possible to enable it for a normal user by disabling the paranoid stream setting. v2: Store preemption setting in intel_context (Chris) v3: Use priorities to avoid preemption rather than the HW mechanism v4: Just modify the port priority reporting function Signed-off-by: Lionel Landwerlin <lionel.g.landwer...@intel.com> Reviewed-by: Chris Wilson <ch...@chris-wilson.co.uk> --- .../gpu/drm/i915/gem/i915_gem_execbuffer.c | 8 +++++ drivers/gpu/drm/i915/i915_drv.h | 8 +++++ drivers/gpu/drm/i915/i915_perf.c | 31 +++++++++++++++++-- include/uapi/drm/i915_drm.h | 11 +++++++ 4 files changed, 55 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index bdecd893cd61..5b1349ea135c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2107,6 +2107,14 @@ static int eb_oa_config(struct i915_execbuffer *eb) if (ret) return ret; + /* + * If the perf stream was opened with hold preemption, flag the + * request properly so that the priority of the request is bumped once + * it reaches the execlist ports. + */ + if (eb->i915->perf.exclusive_stream->hold_preemption) + eb->request->flags |= I915_REQUEST_NOPREEMPT; + /* * If the config hasn't changed, skip reconfiguring the HW (this is * subject to a delay we want to avoid has much as possible). diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index c452bf6872e7..ec609c022e5e 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1121,6 +1121,14 @@ 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/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index b9e76378b0c2..1eeabf0bbafc 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -343,6 +343,8 @@ 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 @@ -357,6 +359,7 @@ struct perf_open_properties { u32 sample_flags; u64 single_context:1; + u64 hold_preemption:1; u64 ctx_handle; /* OA sampling state */ @@ -2585,6 +2588,8 @@ 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 = dev_priv->perf.oa_formats[props->oa_format].format; @@ -3111,6 +3116,15 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, } } + 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 @@ -3125,8 +3139,9 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to * enable the OA unit by default. */ - if (IS_HASWELL(dev_priv) && specific_ctx) + if (IS_HASWELL(dev_priv) && specific_ctx && !props->hold_preemption) { privileged_op = false; + } /* Similar to perf's kernel.perf_paranoid_cpu sysctl option * we check a dev.i915.perf_stream_paranoid sysctl option @@ -3135,7 +3150,7 @@ i915_perf_open_ioctl_locked(struct drm_i915_private *dev_priv, */ 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; } @@ -3333,6 +3348,9 @@ static int read_properties_unlocked(struct drm_i915_private *dev_priv, 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; @@ -4100,5 +4118,12 @@ void i915_perf_fini(struct drm_i915_private *dev_priv) */ int i915_perf_ioctl_version(void) { - return 1; + /* 1: initial version + * + * 2: 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; } diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 3166c9ca85f3..5850d68327ec 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1987,6 +1987,17 @@ 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 2. + */ + DRM_I915_PERF_PROP_HOLD_PREEMPTION, + DRM_I915_PERF_PROP_MAX /* non-ABI */ }; -- 2.23.0 _______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx