drm/i915: Add i915 perf infrastructure

Adds base i915 perf infrastructure for Gen performance metrics.

This adds a DRM_IOCTL_I915_PERF_OPEN ioctl that takes an array of uint64
properties to configure a stream of metrics and returns a new fd usable
with standard VFS system calls including read() to read typed and sized
records; ioctl() to enable or disable capture and poll() to wait for
data.

A stream is opened something like:

  uint64_t properties[] = {
      /* Single context sampling */
      DRM_I915_PERF_PROP_CTX_HANDLE,        ctx_handle,

      /* Include OA reports in samples */
      DRM_I915_PERF_PROP_SAMPLE_OA,         true,

      /* OA unit configuration */
      DRM_I915_PERF_PROP_OA_METRICS_SET,    metrics_set_id,
      DRM_I915_PERF_PROP_OA_FORMAT,         report_format,
      DRM_I915_PERF_PROP_OA_EXPONENT,       period_exponent,
   };
   struct drm_i915_perf_open_param parm = {
      .flags = I915_PERF_FLAG_FD_CLOEXEC |
               I915_PERF_FLAG_FD_NONBLOCK |
               I915_PERF_FLAG_DISABLED,
      .properties_ptr = (uint64_t)properties,
      .num_properties = sizeof(properties) / 16,
   };
   int fd = drmIoctl(drm_fd, DRM_IOCTL_I915_PERF_OPEN, &param);

Records read all start with a common { type, size } header with
DRM_I915_PERF_RECORD_SAMPLE being of most interest. Sample records
contain an extensible number of fields and it's the
DRM_I915_PERF_PROP_SAMPLE_xyz properties given when opening that
determine what's included in every sample.

No specific streams are supported yet so any attempt to open a stream
will return an error.

v2:
    use i915_gem_context_get() - Chris Wilson
v3:
    update read() interface to avoid passing state struct - Chris Wilson
    fix some rebase fallout, with i915-perf init/deinit
v4:
    s/DRM_IORW/DRM_IOW/ - Emil Velikov
Signed-off-by: Robert Bragg <robert@sixbynine.org>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Sourab Gupta <sourab.gupta@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-2-robert@sixbynine.org

drivers/gpu/drm/i915/Makefile

@@ -117,6 +117,9 @@ i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
 # virtual gpu code
 i915-y += i915_vgpu.o
 
+# perf code
+i915-y += i915_perf.o
+
 ifeq ($(CONFIG_DRM_I915_GVT),y)
 i915-y += intel_gvt.o
 include $(src)/gvt/Makefile

drivers/gpu/drm/i915/i915_drv.c

@@ -848,6 +848,8 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 
 	intel_detect_preproduction_hw(dev_priv);
 
+	i915_perf_init(dev_priv);
+
 	return 0;
 
 err_gvt:
@@ -863,6 +865,7 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
  */
 static void i915_driver_cleanup_early(struct drm_i915_private *dev_priv)
 {
+	i915_perf_fini(dev_priv);
 	i915_gem_load_cleanup(&dev_priv->drm);
 	i915_workqueues_cleanup(dev_priv);
 }
@@ -2565,6 +2568,7 @@ static const struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(I915_GEM_USERPTR, i915_gem_userptr_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_GETPARAM, i915_gem_context_getparam_ioctl, DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(I915_GEM_CONTEXT_SETPARAM, i915_gem_context_setparam_ioctl, DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(I915_PERF_OPEN, i915_perf_open_ioctl, DRM_RENDER_ALLOW),
 };
 
 static struct drm_driver driver = {

drivers/gpu/drm/i915/i915_drv.h

@@ -1797,6 +1797,84 @@ struct intel_wm_config {
 	bool sprites_scaled;
 };
 
+struct i915_perf_stream;
+
+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.
+	 */
+	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.
+	 */
+	void (*disable)(struct i915_perf_stream *stream);
+
+	/* Return: true if any i915 perf records are ready to read()
+	 * for this stream.
+	 */
+	bool (*can_read)(struct i915_perf_stream *stream);
+
+	/* 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 queue that would be passed to poll_wait() until
+	 * ->can_read() returns true (if its safe to call ->can_read()
+	 * without the i915 perf lock held).
+	 */
+	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.
+	 *
+	 * 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.
+	 *
+	 * 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.
+	 *
+	 * The stream will always be disabled before this is called.
+	 */
+	void (*destroy)(struct i915_perf_stream *stream);
+};
+
+struct i915_perf_stream {
+	struct drm_i915_private *dev_priv;
+
+	struct list_head link;
+
+	u32 sample_flags;
+
+	struct i915_gem_context *ctx;
+	bool enabled;
+
+	struct i915_perf_stream_ops *ops;
+};
+
 struct drm_i915_private {
 	struct drm_device drm;
 
@@ -2092,6 +2170,12 @@ struct drm_i915_private {
 
 	struct i915_runtime_pm pm;
 
+	struct {
+		bool initialized;
+		struct mutex lock;
+		struct list_head streams;
+	} perf;
+
 	/* Abstract the submission mechanism (legacy ringbuffer or execlists) away */
 	struct {
 		void (*resume)(struct drm_i915_private *);
@@ -3253,6 +3337,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 int i915_gem_context_reset_stats_ioctl(struct drm_device *dev, void *data,
 				       struct drm_file *file);
 
+int i915_perf_open_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file);
+
 /* i915_gem_evict.c */
 int __must_check i915_gem_evict_something(struct i915_address_space *vm,
 					  u64 min_size, u64 alignment,
@@ -3383,6 +3470,10 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 			    u32 batch_len,
 			    bool is_master);
 
+/* i915_perf.c */
+extern void i915_perf_init(struct drm_i915_private *dev_priv);
+extern void i915_perf_fini(struct drm_i915_private *dev_priv);
+
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_device *dev);
 extern int i915_restore_state(struct drm_device *dev);

include/uapi/drm/i915_drm.h

@@ -258,6 +258,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GEM_USERPTR		0x33
 #define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
 #define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
+#define DRM_I915_PERF_OPEN		0x36
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -311,6 +312,7 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_GEM_USERPTR			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
 #define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
 #define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -1228,6 +1230,71 @@ struct drm_i915_gem_context_param {
 	__u64 value;
 };
 
+enum drm_i915_perf_property_id {
+	/**
+	 * Open the stream for a specific context handle (as used with
+	 * execbuffer2). A stream opened for a specific context this way
+	 * won't typically require root privileges.
+	 */
+	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
+
+	DRM_I915_PERF_PROP_MAX /* non-ABI */
+};
+
+struct drm_i915_perf_open_param {
+	__u32 flags;
+#define I915_PERF_FLAG_FD_CLOEXEC	(1<<0)
+#define I915_PERF_FLAG_FD_NONBLOCK	(1<<1)
+#define I915_PERF_FLAG_DISABLED		(1<<2)
+
+	/** The number of u64 (id, value) pairs */
+	__u32 num_properties;
+
+	/**
+	 * Pointer to array of u64 (id, value) pairs configuring the stream
+	 * to open.
+	 */
+	__u64 __user properties_ptr;
+};
+
+#define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
+#define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
+
+/**
+ * Common to all i915 perf records
+ */
+struct drm_i915_perf_record_header {
+	__u32 type;
+	__u16 pad;
+	__u16 size;
+};
+
+enum drm_i915_perf_record_type {
+
+	/**
+	 * Samples are the work horse record type whose contents are extensible
+	 * and defined when opening an i915 perf stream based on the given
+	 * properties.
+	 *
+	 * Boolean properties following the naming convention
+	 * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
+	 * every sample.
+	 *
+	 * The order of these sample properties given by userspace has no
+	 * affect on the ordering of data within a sample. The order will be
+	 * documented here.
+	 *
+	 * struct {
+	 *     struct drm_i915_perf_record_header header;
+	 *
+	 *     TODO: itemize extensible sample data here
+	 * };
+	 */
+	DRM_I915_PERF_RECORD_SAMPLE = 1,
+
+	DRM_I915_PERF_RECORD_MAX /* non-ABI */
+};
+
 #if defined(__cplusplus)
 }
 #endif