drm/i915/perf: More documentation hooked to i915.rst
This adds a 'Perf' section to i915.rst with the following sub sections:
- Overview
- Comparison with Core Perf
- i915 Driver Entry Points
- i915 Perf Stream
- i915 Perf Observation Architecture Stream
- All i915 Perf Internals
v2:
section headers in i915.rst (Daniel Vetter)
missing symbol docs + other fixups (Matthew Auld)
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161207214033.3581-1-robert@sixbynine.org
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 288152a..40c55c9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1930,89 +1930,186 @@ struct i915_oa_reg {
struct i915_perf_stream;
+/**
+ * struct i915_perf_stream_ops - the OPs to support a specific stream type
+ */
struct i915_perf_stream_ops {
- /* Enables the collection of HW samples, either in response to
- * I915_PERF_IOCTL_ENABLE or implicitly called when stream is
- * opened without I915_PERF_FLAG_DISABLED.
+ /**
+ * @enable: Enables the collection of HW samples, either in response to
+ * `I915_PERF_IOCTL_ENABLE` or implicitly called when stream is opened
+ * without `I915_PERF_FLAG_DISABLED`.
*/
void (*enable)(struct i915_perf_stream *stream);
- /* Disables the collection of HW samples, either in response to
- * I915_PERF_IOCTL_DISABLE or implicitly called before
- * destroying the stream.
+ /**
+ * @disable: Disables the collection of HW samples, either in response
+ * to `I915_PERF_IOCTL_DISABLE` or implicitly called before destroying
+ * the stream.
*/
void (*disable)(struct i915_perf_stream *stream);
- /* Call poll_wait, passing a wait queue that will be woken
+ /**
+ * @poll_wait: Call poll_wait, passing a wait queue that will be woken
* once there is something ready to read() for the stream
*/
void (*poll_wait)(struct i915_perf_stream *stream,
struct file *file,
poll_table *wait);
- /* For handling a blocking read, wait until there is something
- * to ready to read() for the stream. E.g. wait on the same
+ /**
+ * @wait_unlocked: For handling a blocking read, wait until there is
+ * something to ready to read() for the stream. E.g. wait on the same
* wait queue that would be passed to poll_wait().
*/
int (*wait_unlocked)(struct i915_perf_stream *stream);
- /* read - Copy buffered metrics as records to userspace
- * @buf: the userspace, destination buffer
- * @count: the number of bytes to copy, requested by userspace
- * @offset: zero at the start of the read, updated as the read
- * proceeds, it represents how many bytes have been
- * copied so far and the buffer offset for copying the
- * next record.
+ /**
+ * @read: Copy buffered metrics as records to userspace
+ * **buf**: the userspace, destination buffer
+ * **count**: the number of bytes to copy, requested by userspace
+ * **offset**: zero at the start of the read, updated as the read
+ * proceeds, it represents how many bytes have been copied so far and
+ * the buffer offset for copying the next record.
*
- * Copy as many buffered i915 perf samples and records for
- * this stream to userspace as will fit in the given buffer.
+ * Copy as many buffered i915 perf samples and records for this stream
+ * to userspace as will fit in the given buffer.
*
- * Only write complete records; returning -ENOSPC if there
- * isn't room for a complete record.
+ * Only write complete records; returning -%ENOSPC if there isn't room
+ * for a complete record.
*
- * Return any error condition that results in a short read
- * such as -ENOSPC or -EFAULT, even though these may be
- * squashed before returning to userspace.
+ * Return any error condition that results in a short read such as
+ * -%ENOSPC or -%EFAULT, even though these may be squashed before
+ * returning to userspace.
*/
int (*read)(struct i915_perf_stream *stream,
char __user *buf,
size_t count,
size_t *offset);
- /* Cleanup any stream specific resources.
+ /**
+ * @destroy: Cleanup any stream specific resources.
*
* The stream will always be disabled before this is called.
*/
void (*destroy)(struct i915_perf_stream *stream);
};
+/**
+ * struct i915_perf_stream - state for a single open stream FD
+ */
struct i915_perf_stream {
+ /**
+ * @dev_priv: i915 drm device
+ */
struct drm_i915_private *dev_priv;
+ /**
+ * @link: Links the stream into ``&drm_i915_private->streams``
+ */
struct list_head link;
+ /**
+ * @sample_flags: Flags representing the `DRM_I915_PERF_PROP_SAMPLE_*`
+ * properties given when opening a stream, representing the contents
+ * of a single sample as read() by userspace.
+ */
u32 sample_flags;
+
+ /**
+ * @sample_size: Considering the configured contents of a sample
+ * combined with the required header size, this is the total size
+ * of a single sample record.
+ */
int sample_size;
+ /**
+ * @ctx: %NULL if measuring system-wide across all contexts or a
+ * specific context that is being monitored.
+ */
struct i915_gem_context *ctx;
+
+ /**
+ * @enabled: Whether the stream is currently enabled, considering
+ * whether the stream was opened in a disabled state and based
+ * on `I915_PERF_IOCTL_ENABLE` and `I915_PERF_IOCTL_DISABLE` calls.
+ */
bool enabled;
+ /**
+ * @ops: The callbacks providing the implementation of this specific
+ * type of configured stream.
+ */
const struct i915_perf_stream_ops *ops;
};
+/**
+ * struct i915_oa_ops - Gen specific implementation of an OA unit stream
+ */
struct i915_oa_ops {
+ /**
+ * @init_oa_buffer: Resets the head and tail pointers of the
+ * circular buffer for periodic OA reports.
+ *
+ * Called when first opening a stream for OA metrics, but also may be
+ * called in response to an OA buffer overflow or other error
+ * condition.
+ *
+ * Note it may be necessary to clear the full OA buffer here as part of
+ * maintaining the invariable that new reports must be written to
+ * zeroed memory for us to be able to reliable detect if an expected
+ * report has not yet landed in memory. (At least on Haswell the OA
+ * buffer tail pointer is not synchronized with reports being visible
+ * to the CPU)
+ */
void (*init_oa_buffer)(struct drm_i915_private *dev_priv);
+
+ /**
+ * @enable_metric_set: Applies any MUX configuration to set up the
+ * Boolean and Custom (B/C) counters that are part of the counter
+ * reports being sampled. May apply system constraints such as
+ * disabling EU clock gating as required.
+ */
int (*enable_metric_set)(struct drm_i915_private *dev_priv);
+
+ /**
+ * @disable_metric_set: Remove system constraints associated with using
+ * the OA unit.
+ */
void (*disable_metric_set)(struct drm_i915_private *dev_priv);
+
+ /**
+ * @oa_enable: Enable periodic sampling
+ */
void (*oa_enable)(struct drm_i915_private *dev_priv);
+
+ /**
+ * @oa_disable: Disable periodic sampling
+ */
void (*oa_disable)(struct drm_i915_private *dev_priv);
- void (*update_oacontrol)(struct drm_i915_private *dev_priv);
- void (*update_hw_ctx_id_locked)(struct drm_i915_private *dev_priv,
- u32 ctx_id);
+
+ /**
+ * @read: Copy data from the circular OA buffer into a given userspace
+ * buffer.
+ */
int (*read)(struct i915_perf_stream *stream,
char __user *buf,
size_t count,
size_t *offset);
+
+ /**
+ * @oa_buffer_is_empty: Check if OA buffer empty (false positives OK)
+ *
+ * This is either called via fops or the poll check hrtimer (atomic
+ * ctx) without any locks taken.
+ *
+ * It's safe to read OA config state here unlocked, assuming that this
+ * is only called while the stream is enabled, while the global OA
+ * configuration can't be modified.
+ *
+ * Efficiency is more important than avoiding some false positives
+ * here, which will be handled gracefully - likely resulting in an
+ * %EAGAIN error for userspace.
+ */
bool (*oa_buffer_is_empty)(struct drm_i915_private *dev_priv);
};