drm/i915: Enable i915 perf stream for Haswell OA unit

Gen graphics hardware can be set up to periodically write snapshots of
performance counters into a circular buffer via its Observation
Architecture and this patch exposes that capability to userspace via the
i915 perf interface.

v2:
   Make sure to initialize ->specific_ctx_id when opening, without
   relying on _pin_notify hook, in case ctx already pinned.
v3:
   Revert back to pinning ctx upfront when opening stream, removing
   need to hook in to pinning and to update OACONTROL on the fly.
Signed-off-by: NRobert Bragg <robert@sixbynine.org>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMatthew Auld <matthew.auld@intel.com>
Reviewed-by: NSourab Gupta <sourab.gupta@intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20161107194957.3385-7-robert@sixbynine.org

drivers/gpu/drm/i915/i915_drv.h

@@ -1797,6 +1797,11 @@ struct intel_wm_config {
 	bool sprites_scaled;
 };
 
+struct i915_oa_format {
+	u32 format;
+	int size;
+};
+
 struct i915_oa_reg {
 	i915_reg_t addr;
 	u32 value;
@@ -1817,11 +1822,6 @@ struct i915_perf_stream_ops {
 	 */
 	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
 	 */
@@ -1831,9 +1831,7 @@ struct i915_perf_stream_ops {
 
 	/* 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).
+	 * wait queue that would be passed to poll_wait().
 	 */
 	int (*wait_unlocked)(struct i915_perf_stream *stream);
 
@@ -1873,11 +1871,28 @@ struct i915_perf_stream {
 	struct list_head link;
 
 	u32 sample_flags;
+	int sample_size;
 
 	struct i915_gem_context *ctx;
 	bool enabled;
 
-	struct i915_perf_stream_ops *ops;
+	const struct i915_perf_stream_ops *ops;
+};
+
+struct i915_oa_ops {
+	void (*init_oa_buffer)(struct drm_i915_private *dev_priv);
+	int (*enable_metric_set)(struct drm_i915_private *dev_priv);
+	void (*disable_metric_set)(struct drm_i915_private *dev_priv);
+	void (*oa_enable)(struct drm_i915_private *dev_priv);
+	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);
+	int (*read)(struct i915_perf_stream *stream,
+		    char __user *buf,
+		    size_t count,
+		    size_t *offset);
+	bool (*oa_buffer_is_empty)(struct drm_i915_private *dev_priv);
 };
 
 struct drm_i915_private {
@@ -2177,16 +2192,47 @@ struct drm_i915_private {
 
 	struct {
 		bool initialized;
+
 		struct mutex lock;
 		struct list_head streams;
 
+		spinlock_t hook_lock;
+
 		struct {
-			u32 metrics_set;
+			struct i915_perf_stream *exclusive_stream;
+
+			u32 specific_ctx_id;
+			struct i915_vma *pinned_rcs_vma;
+
+			struct hrtimer poll_check_timer;
+			wait_queue_head_t poll_wq;
+			bool pollin;
+
+			bool periodic;
+			int period_exponent;
+			int timestamp_frequency;
+
+			int tail_margin;
+
+			int metrics_set;
 
 			const struct i915_oa_reg *mux_regs;
 			int mux_regs_len;
 			const struct i915_oa_reg *b_counter_regs;
 			int b_counter_regs_len;
+
+			struct {
+				struct i915_vma *vma;
+				u8 *vaddr;
+				int format;
+				int format_size;
+			} oa_buffer;
+
+			u32 gen7_latched_oastatus1;
+
+			struct i915_oa_ops ops;
+			const struct i915_oa_format *oa_formats;
+			int n_builtin_sets;
 		} oa;
 	} perf;
 

drivers/gpu/drm/i915/i915_reg.h

@@ -616,6 +616,343 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define HSW_CS_GPR_UDW(n)               _MMIO(0x2600 + (n) * 8 + 4)
 
 #define GEN7_OACONTROL _MMIO(0x2360)
+#define  GEN7_OACONTROL_CTX_MASK	    0xFFFFF000
+#define  GEN7_OACONTROL_TIMER_PERIOD_MASK   0x3F
+#define  GEN7_OACONTROL_TIMER_PERIOD_SHIFT  6
+#define  GEN7_OACONTROL_TIMER_ENABLE	    (1<<5)
+#define  GEN7_OACONTROL_FORMAT_A13	    (0<<2)
+#define  GEN7_OACONTROL_FORMAT_A29	    (1<<2)
+#define  GEN7_OACONTROL_FORMAT_A13_B8_C8    (2<<2)
+#define  GEN7_OACONTROL_FORMAT_A29_B8_C8    (3<<2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8	    (4<<2)
+#define  GEN7_OACONTROL_FORMAT_A45_B8_C8    (5<<2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8_A16    (6<<2)
+#define  GEN7_OACONTROL_FORMAT_C4_B8	    (7<<2)
+#define  GEN7_OACONTROL_FORMAT_SHIFT	    2
+#define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1<<1)
+#define  GEN7_OACONTROL_ENABLE		    (1<<0)
+
+#define GEN8_OACTXID _MMIO(0x2364)
+
+#define GEN8_OACONTROL _MMIO(0x2B00)
+#define  GEN8_OA_REPORT_FORMAT_A12	    (0<<2)
+#define  GEN8_OA_REPORT_FORMAT_A12_B8_C8    (2<<2)
+#define  GEN8_OA_REPORT_FORMAT_A36_B8_C8    (5<<2)
+#define  GEN8_OA_REPORT_FORMAT_C4_B8	    (7<<2)
+#define  GEN8_OA_REPORT_FORMAT_SHIFT	    2
+#define  GEN8_OA_SPECIFIC_CONTEXT_ENABLE    (1<<1)
+#define  GEN8_OA_COUNTER_ENABLE             (1<<0)
+
+#define GEN8_OACTXCONTROL _MMIO(0x2360)
+#define  GEN8_OA_TIMER_PERIOD_MASK	    0x3F
+#define  GEN8_OA_TIMER_PERIOD_SHIFT	    2
+#define  GEN8_OA_TIMER_ENABLE		    (1<<1)
+#define  GEN8_OA_COUNTER_RESUME		    (1<<0)
+
+#define GEN7_OABUFFER _MMIO(0x23B0) /* R/W */
+#define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1<<3)
+#define  GEN7_OABUFFER_EDGE_TRIGGER	    (1<<2)
+#define  GEN7_OABUFFER_STOP_RESUME_ENABLE   (1<<1)
+#define  GEN7_OABUFFER_RESUME		    (1<<0)
+
+#define GEN8_OABUFFER _MMIO(0x2b14)
+
+#define GEN7_OASTATUS1 _MMIO(0x2364)
+#define  GEN7_OASTATUS1_TAIL_MASK	    0xffffffc0
+#define  GEN7_OASTATUS1_COUNTER_OVERFLOW    (1<<2)
+#define  GEN7_OASTATUS1_OABUFFER_OVERFLOW   (1<<1)
+#define  GEN7_OASTATUS1_REPORT_LOST	    (1<<0)
+
+#define GEN7_OASTATUS2 _MMIO(0x2368)
+#define GEN7_OASTATUS2_HEAD_MASK    0xffffffc0
+
+#define GEN8_OASTATUS _MMIO(0x2b08)
+#define  GEN8_OASTATUS_OVERRUN_STATUS	    (1<<3)
+#define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1<<2)
+#define  GEN8_OASTATUS_OABUFFER_OVERFLOW    (1<<1)
+#define  GEN8_OASTATUS_REPORT_LOST	    (1<<0)
+
+#define GEN8_OAHEADPTR _MMIO(0x2B0C)
+#define GEN8_OATAILPTR _MMIO(0x2B10)
+
+#define OABUFFER_SIZE_128K  (0<<3)
+#define OABUFFER_SIZE_256K  (1<<3)
+#define OABUFFER_SIZE_512K  (2<<3)
+#define OABUFFER_SIZE_1M    (3<<3)
+#define OABUFFER_SIZE_2M    (4<<3)
+#define OABUFFER_SIZE_4M    (5<<3)
+#define OABUFFER_SIZE_8M    (6<<3)
+#define OABUFFER_SIZE_16M   (7<<3)
+
+#define OA_MEM_SELECT_GGTT  (1<<0)
+
+#define EU_PERF_CNTL0	    _MMIO(0xe458)
+
+#define GDT_CHICKEN_BITS    _MMIO(0x9840)
+#define GT_NOA_ENABLE	    0x00000080
+
+/*
+ * OA Boolean state
+ */
+
+#define OAREPORTTRIG1 _MMIO(0x2740)
+#define OAREPORTTRIG1_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG2 _MMIO(0x2744)
+#define OAREPORTTRIG2_INVERT_A_0  (1<<0)
+#define OAREPORTTRIG2_INVERT_A_1  (1<<1)
+#define OAREPORTTRIG2_INVERT_A_2  (1<<2)
+#define OAREPORTTRIG2_INVERT_A_3  (1<<3)
+#define OAREPORTTRIG2_INVERT_A_4  (1<<4)
+#define OAREPORTTRIG2_INVERT_A_5  (1<<5)
+#define OAREPORTTRIG2_INVERT_A_6  (1<<6)
+#define OAREPORTTRIG2_INVERT_A_7  (1<<7)
+#define OAREPORTTRIG2_INVERT_A_8  (1<<8)
+#define OAREPORTTRIG2_INVERT_A_9  (1<<9)
+#define OAREPORTTRIG2_INVERT_A_10 (1<<10)
+#define OAREPORTTRIG2_INVERT_A_11 (1<<11)
+#define OAREPORTTRIG2_INVERT_A_12 (1<<12)
+#define OAREPORTTRIG2_INVERT_A_13 (1<<13)
+#define OAREPORTTRIG2_INVERT_A_14 (1<<14)
+#define OAREPORTTRIG2_INVERT_A_15 (1<<15)
+#define OAREPORTTRIG2_INVERT_B_0  (1<<16)
+#define OAREPORTTRIG2_INVERT_B_1  (1<<17)
+#define OAREPORTTRIG2_INVERT_B_2  (1<<18)
+#define OAREPORTTRIG2_INVERT_B_3  (1<<19)
+#define OAREPORTTRIG2_INVERT_C_0  (1<<20)
+#define OAREPORTTRIG2_INVERT_C_1  (1<<21)
+#define OAREPORTTRIG2_INVERT_D_0  (1<<22)
+#define OAREPORTTRIG2_THRESHOLD_ENABLE	    (1<<23)
+#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1<<31)
+
+#define OAREPORTTRIG3 _MMIO(0x2748)
+#define OAREPORTTRIG3_NOA_SELECT_MASK	    0xf
+#define OAREPORTTRIG3_NOA_SELECT_8_SHIFT    0
+#define OAREPORTTRIG3_NOA_SELECT_9_SHIFT    4
+#define OAREPORTTRIG3_NOA_SELECT_10_SHIFT   8
+#define OAREPORTTRIG3_NOA_SELECT_11_SHIFT   12
+#define OAREPORTTRIG3_NOA_SELECT_12_SHIFT   16
+#define OAREPORTTRIG3_NOA_SELECT_13_SHIFT   20
+#define OAREPORTTRIG3_NOA_SELECT_14_SHIFT   24
+#define OAREPORTTRIG3_NOA_SELECT_15_SHIFT   28
+
+#define OAREPORTTRIG4 _MMIO(0x274c)
+#define OAREPORTTRIG4_NOA_SELECT_MASK	    0xf
+#define OAREPORTTRIG4_NOA_SELECT_0_SHIFT    0
+#define OAREPORTTRIG4_NOA_SELECT_1_SHIFT    4
+#define OAREPORTTRIG4_NOA_SELECT_2_SHIFT    8
+#define OAREPORTTRIG4_NOA_SELECT_3_SHIFT    12
+#define OAREPORTTRIG4_NOA_SELECT_4_SHIFT    16
+#define OAREPORTTRIG4_NOA_SELECT_5_SHIFT    20
+#define OAREPORTTRIG4_NOA_SELECT_6_SHIFT    24
+#define OAREPORTTRIG4_NOA_SELECT_7_SHIFT    28
+
+#define OAREPORTTRIG5 _MMIO(0x2750)
+#define OAREPORTTRIG5_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG6 _MMIO(0x2754)
+#define OAREPORTTRIG6_INVERT_A_0  (1<<0)
+#define OAREPORTTRIG6_INVERT_A_1  (1<<1)
+#define OAREPORTTRIG6_INVERT_A_2  (1<<2)
+#define OAREPORTTRIG6_INVERT_A_3  (1<<3)
+#define OAREPORTTRIG6_INVERT_A_4  (1<<4)
+#define OAREPORTTRIG6_INVERT_A_5  (1<<5)
+#define OAREPORTTRIG6_INVERT_A_6  (1<<6)
+#define OAREPORTTRIG6_INVERT_A_7  (1<<7)
+#define OAREPORTTRIG6_INVERT_A_8  (1<<8)
+#define OAREPORTTRIG6_INVERT_A_9  (1<<9)
+#define OAREPORTTRIG6_INVERT_A_10 (1<<10)
+#define OAREPORTTRIG6_INVERT_A_11 (1<<11)
+#define OAREPORTTRIG6_INVERT_A_12 (1<<12)
+#define OAREPORTTRIG6_INVERT_A_13 (1<<13)
+#define OAREPORTTRIG6_INVERT_A_14 (1<<14)
+#define OAREPORTTRIG6_INVERT_A_15 (1<<15)
+#define OAREPORTTRIG6_INVERT_B_0  (1<<16)
+#define OAREPORTTRIG6_INVERT_B_1  (1<<17)
+#define OAREPORTTRIG6_INVERT_B_2  (1<<18)
+#define OAREPORTTRIG6_INVERT_B_3  (1<<19)
+#define OAREPORTTRIG6_INVERT_C_0  (1<<20)
+#define OAREPORTTRIG6_INVERT_C_1  (1<<21)
+#define OAREPORTTRIG6_INVERT_D_0  (1<<22)
+#define OAREPORTTRIG6_THRESHOLD_ENABLE	    (1<<23)
+#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1<<31)
+
+#define OAREPORTTRIG7 _MMIO(0x2758)
+#define OAREPORTTRIG7_NOA_SELECT_MASK	    0xf
+#define OAREPORTTRIG7_NOA_SELECT_8_SHIFT    0
+#define OAREPORTTRIG7_NOA_SELECT_9_SHIFT    4
+#define OAREPORTTRIG7_NOA_SELECT_10_SHIFT   8
+#define OAREPORTTRIG7_NOA_SELECT_11_SHIFT   12
+#define OAREPORTTRIG7_NOA_SELECT_12_SHIFT   16
+#define OAREPORTTRIG7_NOA_SELECT_13_SHIFT   20
+#define OAREPORTTRIG7_NOA_SELECT_14_SHIFT   24
+#define OAREPORTTRIG7_NOA_SELECT_15_SHIFT   28
+
+#define OAREPORTTRIG8 _MMIO(0x275c)
+#define OAREPORTTRIG8_NOA_SELECT_MASK	    0xf
+#define OAREPORTTRIG8_NOA_SELECT_0_SHIFT    0
+#define OAREPORTTRIG8_NOA_SELECT_1_SHIFT    4
+#define OAREPORTTRIG8_NOA_SELECT_2_SHIFT    8
+#define OAREPORTTRIG8_NOA_SELECT_3_SHIFT    12
+#define OAREPORTTRIG8_NOA_SELECT_4_SHIFT    16
+#define OAREPORTTRIG8_NOA_SELECT_5_SHIFT    20
+#define OAREPORTTRIG8_NOA_SELECT_6_SHIFT    24
+#define OAREPORTTRIG8_NOA_SELECT_7_SHIFT    28
+
+#define OASTARTTRIG1 _MMIO(0x2710)
+#define OASTARTTRIG1_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG1_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG2 _MMIO(0x2714)
+#define OASTARTTRIG2_INVERT_A_0 (1<<0)
+#define OASTARTTRIG2_INVERT_A_1 (1<<1)
+#define OASTARTTRIG2_INVERT_A_2 (1<<2)
+#define OASTARTTRIG2_INVERT_A_3 (1<<3)
+#define OASTARTTRIG2_INVERT_A_4 (1<<4)
+#define OASTARTTRIG2_INVERT_A_5 (1<<5)
+#define OASTARTTRIG2_INVERT_A_6 (1<<6)
+#define OASTARTTRIG2_INVERT_A_7 (1<<7)
+#define OASTARTTRIG2_INVERT_A_8 (1<<8)
+#define OASTARTTRIG2_INVERT_A_9 (1<<9)
+#define OASTARTTRIG2_INVERT_A_10 (1<<10)
+#define OASTARTTRIG2_INVERT_A_11 (1<<11)
+#define OASTARTTRIG2_INVERT_A_12 (1<<12)
+#define OASTARTTRIG2_INVERT_A_13 (1<<13)
+#define OASTARTTRIG2_INVERT_A_14 (1<<14)
+#define OASTARTTRIG2_INVERT_A_15 (1<<15)
+#define OASTARTTRIG2_INVERT_B_0 (1<<16)
+#define OASTARTTRIG2_INVERT_B_1 (1<<17)
+#define OASTARTTRIG2_INVERT_B_2 (1<<18)
+#define OASTARTTRIG2_INVERT_B_3 (1<<19)
+#define OASTARTTRIG2_INVERT_C_0 (1<<20)
+#define OASTARTTRIG2_INVERT_C_1 (1<<21)
+#define OASTARTTRIG2_INVERT_D_0 (1<<22)
+#define OASTARTTRIG2_THRESHOLD_ENABLE	    (1<<23)
+#define OASTARTTRIG2_START_TRIG_FLAG_MBZ    (1<<24)
+#define OASTARTTRIG2_EVENT_SELECT_0  (1<<28)
+#define OASTARTTRIG2_EVENT_SELECT_1  (1<<29)
+#define OASTARTTRIG2_EVENT_SELECT_2  (1<<30)
+#define OASTARTTRIG2_EVENT_SELECT_3  (1<<31)
+
+#define OASTARTTRIG3 _MMIO(0x2718)
+#define OASTARTTRIG3_NOA_SELECT_MASK	   0xf
+#define OASTARTTRIG3_NOA_SELECT_8_SHIFT    0
+#define OASTARTTRIG3_NOA_SELECT_9_SHIFT    4
+#define OASTARTTRIG3_NOA_SELECT_10_SHIFT   8
+#define OASTARTTRIG3_NOA_SELECT_11_SHIFT   12
+#define OASTARTTRIG3_NOA_SELECT_12_SHIFT   16
+#define OASTARTTRIG3_NOA_SELECT_13_SHIFT   20
+#define OASTARTTRIG3_NOA_SELECT_14_SHIFT   24
+#define OASTARTTRIG3_NOA_SELECT_15_SHIFT   28
+
+#define OASTARTTRIG4 _MMIO(0x271c)
+#define OASTARTTRIG4_NOA_SELECT_MASK	    0xf
+#define OASTARTTRIG4_NOA_SELECT_0_SHIFT    0
+#define OASTARTTRIG4_NOA_SELECT_1_SHIFT    4
+#define OASTARTTRIG4_NOA_SELECT_2_SHIFT    8
+#define OASTARTTRIG4_NOA_SELECT_3_SHIFT    12
+#define OASTARTTRIG4_NOA_SELECT_4_SHIFT    16
+#define OASTARTTRIG4_NOA_SELECT_5_SHIFT    20
+#define OASTARTTRIG4_NOA_SELECT_6_SHIFT    24
+#define OASTARTTRIG4_NOA_SELECT_7_SHIFT    28
+
+#define OASTARTTRIG5 _MMIO(0x2720)
+#define OASTARTTRIG5_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG5_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG6 _MMIO(0x2724)
+#define OASTARTTRIG6_INVERT_A_0 (1<<0)
+#define OASTARTTRIG6_INVERT_A_1 (1<<1)
+#define OASTARTTRIG6_INVERT_A_2 (1<<2)
+#define OASTARTTRIG6_INVERT_A_3 (1<<3)
+#define OASTARTTRIG6_INVERT_A_4 (1<<4)
+#define OASTARTTRIG6_INVERT_A_5 (1<<5)
+#define OASTARTTRIG6_INVERT_A_6 (1<<6)
+#define OASTARTTRIG6_INVERT_A_7 (1<<7)
+#define OASTARTTRIG6_INVERT_A_8 (1<<8)
+#define OASTARTTRIG6_INVERT_A_9 (1<<9)
+#define OASTARTTRIG6_INVERT_A_10 (1<<10)
+#define OASTARTTRIG6_INVERT_A_11 (1<<11)
+#define OASTARTTRIG6_INVERT_A_12 (1<<12)
+#define OASTARTTRIG6_INVERT_A_13 (1<<13)
+#define OASTARTTRIG6_INVERT_A_14 (1<<14)
+#define OASTARTTRIG6_INVERT_A_15 (1<<15)
+#define OASTARTTRIG6_INVERT_B_0 (1<<16)
+#define OASTARTTRIG6_INVERT_B_1 (1<<17)
+#define OASTARTTRIG6_INVERT_B_2 (1<<18)
+#define OASTARTTRIG6_INVERT_B_3 (1<<19)
+#define OASTARTTRIG6_INVERT_C_0 (1<<20)
+#define OASTARTTRIG6_INVERT_C_1 (1<<21)
+#define OASTARTTRIG6_INVERT_D_0 (1<<22)
+#define OASTARTTRIG6_THRESHOLD_ENABLE	    (1<<23)
+#define OASTARTTRIG6_START_TRIG_FLAG_MBZ    (1<<24)
+#define OASTARTTRIG6_EVENT_SELECT_4  (1<<28)
+#define OASTARTTRIG6_EVENT_SELECT_5  (1<<29)
+#define OASTARTTRIG6_EVENT_SELECT_6  (1<<30)
+#define OASTARTTRIG6_EVENT_SELECT_7  (1<<31)
+
+#define OASTARTTRIG7 _MMIO(0x2728)
+#define OASTARTTRIG7_NOA_SELECT_MASK	   0xf
+#define OASTARTTRIG7_NOA_SELECT_8_SHIFT    0
+#define OASTARTTRIG7_NOA_SELECT_9_SHIFT    4
+#define OASTARTTRIG7_NOA_SELECT_10_SHIFT   8
+#define OASTARTTRIG7_NOA_SELECT_11_SHIFT   12
+#define OASTARTTRIG7_NOA_SELECT_12_SHIFT   16
+#define OASTARTTRIG7_NOA_SELECT_13_SHIFT   20
+#define OASTARTTRIG7_NOA_SELECT_14_SHIFT   24
+#define OASTARTTRIG7_NOA_SELECT_15_SHIFT   28
+
+#define OASTARTTRIG8 _MMIO(0x272c)
+#define OASTARTTRIG8_NOA_SELECT_MASK	   0xf
+#define OASTARTTRIG8_NOA_SELECT_0_SHIFT    0
+#define OASTARTTRIG8_NOA_SELECT_1_SHIFT    4
+#define OASTARTTRIG8_NOA_SELECT_2_SHIFT    8
+#define OASTARTTRIG8_NOA_SELECT_3_SHIFT    12
+#define OASTARTTRIG8_NOA_SELECT_4_SHIFT    16
+#define OASTARTTRIG8_NOA_SELECT_5_SHIFT    20
+#define OASTARTTRIG8_NOA_SELECT_6_SHIFT    24
+#define OASTARTTRIG8_NOA_SELECT_7_SHIFT    28
+
+/* CECX_0 */
+#define OACEC_COMPARE_LESS_OR_EQUAL	6
+#define OACEC_COMPARE_NOT_EQUAL		5
+#define OACEC_COMPARE_LESS_THAN		4
+#define OACEC_COMPARE_GREATER_OR_EQUAL	3
+#define OACEC_COMPARE_EQUAL		2
+#define OACEC_COMPARE_GREATER_THAN	1
+#define OACEC_COMPARE_ANY_EQUAL		0
+
+#define OACEC_COMPARE_VALUE_MASK    0xffff
+#define OACEC_COMPARE_VALUE_SHIFT   3
+
+#define OACEC_SELECT_NOA	(0<<19)
+#define OACEC_SELECT_PREV	(1<<19)
+#define OACEC_SELECT_BOOLEAN	(2<<19)
+
+/* CECX_1 */
+#define OACEC_MASK_MASK		    0xffff
+#define OACEC_CONSIDERATIONS_MASK   0xffff
+#define OACEC_CONSIDERATIONS_SHIFT  16
+
+#define OACEC0_0 _MMIO(0x2770)
+#define OACEC0_1 _MMIO(0x2774)
+#define OACEC1_0 _MMIO(0x2778)
+#define OACEC1_1 _MMIO(0x277c)
+#define OACEC2_0 _MMIO(0x2780)
+#define OACEC2_1 _MMIO(0x2784)
+#define OACEC3_0 _MMIO(0x2788)
+#define OACEC3_1 _MMIO(0x278c)
+#define OACEC4_0 _MMIO(0x2790)
+#define OACEC4_1 _MMIO(0x2794)
+#define OACEC5_0 _MMIO(0x2798)
+#define OACEC5_1 _MMIO(0x279c)
+#define OACEC6_0 _MMIO(0x27a0)
+#define OACEC6_1 _MMIO(0x27a4)
+#define OACEC7_0 _MMIO(0x27a8)
+#define OACEC7_1 _MMIO(0x27ac)
+
 
 #define _GEN7_PIPEA_DE_LOAD_SL	0x70068
 #define _GEN7_PIPEB_DE_LOAD_SL	0x71068
@@ -6914,6 +7251,7 @@ enum {
 # define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
 
 #define GEN6_UCGCTL3				_MMIO(0x9408)
+# define GEN6_OACSUNIT_CLOCK_GATE_DISABLE		(1 << 20)
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
 #define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)

include/uapi/drm/i915_drm.h

@@ -1230,6 +1230,18 @@ struct drm_i915_gem_context_param {
 	__u64 value;
 };
 
+enum drm_i915_oa_format {
+	I915_OA_FORMAT_A13 = 1,
+	I915_OA_FORMAT_A29,
+	I915_OA_FORMAT_A13_B8_C8,
+	I915_OA_FORMAT_B4_C8,
+	I915_OA_FORMAT_A45_B8_C8,
+	I915_OA_FORMAT_B4_C8_A16,
+	I915_OA_FORMAT_C4_B8,
+
+	I915_OA_FORMAT_MAX	    /* non-ABI */
+};
+
 enum drm_i915_perf_property_id {
 	/**
 	 * Open the stream for a specific context handle (as used with
@@ -1238,6 +1250,32 @@ enum drm_i915_perf_property_id {
 	 */
 	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
 
+	/**
+	 * A value of 1 requests the inclusion of raw OA unit reports as
+	 * part of stream samples.
+	 */
+	DRM_I915_PERF_PROP_SAMPLE_OA,
+
+	/**
+	 * The value specifies which set of OA unit metrics should be
+	 * be configured, defining the contents of any OA unit reports.
+	 */
+	DRM_I915_PERF_PROP_OA_METRICS_SET,
+
+	/**
+	 * The value specifies the size and layout of OA unit reports.
+	 */
+	DRM_I915_PERF_PROP_OA_FORMAT,
+
+	/**
+	 * Specifying this property implicitly requests periodic OA unit
+	 * sampling and (at least on Haswell) the sampling frequency is derived
+	 * from this exponent as follows:
+	 *
+	 *   80ns * 2^(period_exponent + 1)
+	 */
+	DRM_I915_PERF_PROP_OA_EXPONENT,
+
 	DRM_I915_PERF_PROP_MAX /* non-ABI */
 };
 
@@ -1257,7 +1295,23 @@ struct drm_i915_perf_open_param {
 	__u64 __user properties_ptr;
 };
 
+/**
+ * Enable data capture for a stream that was either opened in a disabled state
+ * via I915_PERF_FLAG_DISABLED or was later disabled via
+ * I915_PERF_IOCTL_DISABLE.
+ *
+ * It is intended to be cheaper to disable and enable a stream than it may be
+ * to close and re-open a stream with the same configuration.
+ *
+ * It's undefined whether any pending data for the stream will be lost.
+ */
 #define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
+
+/**
+ * Disable data capture for a stream.
+ *
+ * It is an error to try and read a stream that is disabled.
+ */
 #define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
 
 /**
@@ -1281,17 +1335,30 @@ enum drm_i915_perf_record_type {
 	 * 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
+	 * affect on the ordering of data within a sample. The order is
 	 * documented here.
 	 *
 	 * struct {
 	 *     struct drm_i915_perf_record_header header;
 	 *
-	 *     TODO: itemize extensible sample data here
+	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
 	 * };
 	 */
 	DRM_I915_PERF_RECORD_SAMPLE = 1,
 
+	/*
+	 * Indicates that one or more OA reports were not written by the
+	 * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
+	 * command collides with periodic sampling - which would be more likely
+	 * at higher sampling frequencies.
+	 */
+	DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
+
+	/**
+	 * An error occurred that resulted in all pending OA reports being lost.
+	 */
+	DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,
+
 	DRM_I915_PERF_RECORD_MAX /* non-ABI */
 };