All of lore.kernel.org
 help / color / mirror / Atom feed
From: Robert Bragg <robert@sixbynine.org>
To: intel-gfx@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@intel.com>,
	Jani Nikula <jani.nikula@linux.intel.com>,
	David Airlie <airlied@linux.ie>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Paul Mackerras <paulus@samba.org>, Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
	linux-api@vger.kernel.org
Subject: [RFC PATCH 08/11] drm/i915: add OA config for 3D render counters
Date: Thu,  7 May 2015 15:15:51 +0100	[thread overview]
Message-ID: <1431008154-6833-9-git-send-email-robert@sixbynine.org> (raw)
In-Reply-To: <1431008154-6833-1-git-send-email-robert@sixbynine.org>

This enables access to some additional counters beyond the aggregating A
counters, adding a '3D' metric set configuration useful while profiling
3D rendering workloads.

Signed-off-by: Robert Bragg <robert@sixbynine.org>
---
 drivers/gpu/drm/i915/i915_drv.h     |   7 +
 drivers/gpu/drm/i915/i915_oa_perf.c | 124 +++++++++++++--
 drivers/gpu/drm/i915/i915_reg.h     | 294 ++++++++++++++++++++++++++++++++----
 include/uapi/drm/i915_drm.h         |   2 +
 4 files changed, 385 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3d8e4ed..1e65dc2 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1564,6 +1564,13 @@ struct i915_virtual_gpu {
 	bool active;
 };
 
+#ifdef CONFIG_PERF_EVENTS
+struct i915_oa_reg {
+	u32 addr;
+	u32 value;
+};
+#endif
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *objects;
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index a1cf55f..d0e144c 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -23,6 +23,80 @@ static int hsw_perf_format_sizes[] = {
 	64   /* C4_B8_HSW */
 };
 
+
+/* A generated mux config to select counters useful for profiling 3D
+ * workloads */
+static struct i915_oa_reg hsw_profile_3d_mux_config[] = {
+
+	{ 0x253A4, 0x01600000 },
+	{ 0x25440, 0x00100000 },
+	{ 0x25128, 0x00000000 },
+	{ 0x2691C, 0x00000800 },
+	{ 0x26AA0, 0x01500000 },
+	{ 0x26B9C, 0x00006000 },
+	{ 0x2791C, 0x00000800 },
+	{ 0x27AA0, 0x01500000 },
+	{ 0x27B9C, 0x00006000 },
+	{ 0x2641C, 0x00000400 },
+	{ 0x25380, 0x00000010 },
+	{ 0x2538C, 0x00000000 },
+	{ 0x25384, 0x0800AAAA },
+	{ 0x25400, 0x00000004 },
+	{ 0x2540C, 0x06029000 },
+	{ 0x25410, 0x00000002 },
+	{ 0x25404, 0x5C30FFFF },
+	{ 0x25100, 0x00000016 },
+	{ 0x25110, 0x00000400 },
+	{ 0x25104, 0x00000000 },
+	{ 0x26804, 0x00001211 },
+	{ 0x26884, 0x00000100 },
+	{ 0x26900, 0x00000002 },
+	{ 0x26908, 0x00700000 },
+	{ 0x26904, 0x00000000 },
+	{ 0x26984, 0x00001022 },
+	{ 0x26A04, 0x00000011 },
+	{ 0x26A80, 0x00000006 },
+	{ 0x26A88, 0x00000C02 },
+	{ 0x26A84, 0x00000000 },
+	{ 0x26B04, 0x00001000 },
+	{ 0x26B80, 0x00000002 },
+	{ 0x26B8C, 0x00000007 },
+	{ 0x26B84, 0x00000000 },
+	{ 0x27804, 0x00004844 },
+	{ 0x27884, 0x00000400 },
+	{ 0x27900, 0x00000002 },
+	{ 0x27908, 0x0E000000 },
+	{ 0x27904, 0x00000000 },
+	{ 0x27984, 0x00004088 },
+	{ 0x27A04, 0x00000044 },
+	{ 0x27A80, 0x00000006 },
+	{ 0x27A88, 0x00018040 },
+	{ 0x27A84, 0x00000000 },
+	{ 0x27B04, 0x00004000 },
+	{ 0x27B80, 0x00000002 },
+	{ 0x27B8C, 0x000000E0 },
+	{ 0x27B84, 0x00000000 },
+	{ 0x26104, 0x00002222 },
+	{ 0x26184, 0x0C006666 },
+	{ 0x26284, 0x04000000 },
+	{ 0x26304, 0x04000000 },
+	{ 0x26400, 0x00000002 },
+	{ 0x26410, 0x000000A0 },
+	{ 0x26404, 0x00000000 },
+	{ 0x25420, 0x04108020 },
+	{ 0x25424, 0x1284A420 },
+	{ 0x2541C, 0x00000000 },
+	{ 0x25428, 0x00042049 },
+};
+
+/* A corresponding B counter configuration for profiling 3D workloads */
+static struct i915_oa_reg hsw_profile_3d_b_counter_config[] = {
+	{ 0x2724, 0x00800000 },
+	{ 0x2720, 0x00000000 },
+	{ 0x2714, 0x00800000 },
+	{ 0x2710, 0x00000000 },
+};
+
 static void forward_one_oa_snapshot_to_event(struct drm_i915_private *dev_priv,
 					     u8 *snapshot,
 					     struct perf_event *event)
@@ -551,6 +625,19 @@ static void update_oacontrol(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN7_OACONTROL, 0);
 }
 
+static void config_oa_regs(struct drm_i915_private *dev_priv,
+			   struct i915_oa_reg *regs,
+			   int n_regs)
+{
+	int i;
+
+	for (i = 0; i < n_regs; i++) {
+		struct i915_oa_reg *reg = regs + i;
+
+		I915_WRITE(reg->addr, reg->value);
+	}
+}
+
 static void i915_oa_event_start(struct perf_event *event, int flags)
 {
 	struct drm_i915_private *dev_priv =
@@ -571,22 +658,31 @@ static void i915_oa_event_start(struct perf_event *event, int flags)
 	WARN_ONCE(I915_READ(GEN6_UCGCTL3) & GEN6_OACSUNIT_CLOCK_GATE_DISABLE,
 		  "disabled OA unit level clock gating will result in incorrect per-context OA counters");
 
-	/* XXX: On Haswell, when threshold disable mode is desired,
-	 * instead of setting the threshold enable to '0', we need to
-	 * program it to '1' and set OASTARTTRIG1 bits 15:0 to 0
-	 * (threshold value of 0)
-	 */
-	I915_WRITE(OASTARTTRIG6, (OASTARTTRIG6_B4_TO_B7_THRESHOLD_ENABLE |
-				  OASTARTTRIG6_B4_CUSTOM_EVENT_ENABLE));
-	I915_WRITE(OASTARTTRIG5, 0); /* threshold value */
+	I915_WRITE(GDT_CHICKEN_BITS, GT_NOA_ENABLE);
 
-	I915_WRITE(OASTARTTRIG2, (OASTARTTRIG2_B0_TO_B3_THRESHOLD_ENABLE |
-				  OASTARTTRIG2_B0_CUSTOM_EVENT_ENABLE));
-	I915_WRITE(OASTARTTRIG1, 0); /* threshold value */
+	if (dev_priv->oa_pmu.metrics_set == I915_OA_METRICS_SET_3D) {
+		config_oa_regs(dev_priv, hsw_profile_3d_mux_config,
+			       ARRAY_SIZE(hsw_profile_3d_mux_config));
+		config_oa_regs(dev_priv, hsw_profile_3d_b_counter_config,
+			       ARRAY_SIZE(hsw_profile_3d_b_counter_config));
+	} else {
+		/* XXX: On Haswell, when threshold disable mode is desired,
+		 * instead of setting the threshold enable to '0', we need to
+		 * program it to '1' and set OASTARTTRIG1 bits 15:0 to 0
+		 * (threshold value of 0)
+		 */
+		I915_WRITE(OASTARTTRIG6, (OASTARTTRIG6_THRESHOLD_ENABLE |
+					  OASTARTTRIG6_EVENT_SELECT_4));
+		I915_WRITE(OASTARTTRIG5, 0); /* threshold value */
 
-	/* Setup B0 as the gpu clock counter... */
-	I915_WRITE(OACEC0_0, OACEC0_0_B0_COMPARE_GREATER_OR_EQUAL); /* to 0 */
-	I915_WRITE(OACEC0_1, 0xfffe); /* Select NOA[0] */
+		I915_WRITE(OASTARTTRIG2, (OASTARTTRIG2_THRESHOLD_ENABLE |
+					  OASTARTTRIG2_EVENT_SELECT_0));
+		I915_WRITE(OASTARTTRIG1, 0); /* threshold value */
+
+		/* Setup B0 as the gpu clock counter... */
+		I915_WRITE(OACEC0_0, OACEC_COMPARE_GREATER_OR_EQUAL); /* to 0 */
+		I915_WRITE(OACEC0_1, 0xfffe); /* Select NOA[0] */
+	}
 
 	spin_lock_irqsave(&dev_priv->oa_pmu.lock, lock_flags);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9e427cc..d94932a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -532,34 +532,6 @@
 #define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1<<1)
 #define  GEN7_OACONTROL_ENABLE		    (1<<0)
 
-#define OASTARTTRIG5 0x02720
-#define  OASTARTTRIG5_THRESHOLD_VALUE_MASK	0xffff
-
-#define OASTARTTRIG6 0x02724
-#define  OASTARTTRIG6_B4_TO_B7_THRESHOLD_ENABLE (1<<23)
-#define  OASTARTTRIG6_B4_CUSTOM_EVENT_ENABLE	(1<<28)
-
-#define OASTARTTRIG1 0x02710
-#define  OASTARTTRIG1_THRESHOLD_VALUE_MASK	0xffff
-
-#define OASTARTTRIG2 0x02714
-#define  OASTARTTRIG2_B0_TO_B3_THRESHOLD_ENABLE (1<<23)
-#define  OASTARTTRIG2_B0_CUSTOM_EVENT_ENABLE	(1<<28)
-
-#define OACEC0_0 0x2770
-#define  OACEC0_0_B0_COMPARE_ANY_EQUAL		0
-#define  OACEC0_0_B0_COMPARE_OR			0
-#define  OACEC0_0_B0_COMPARE_GREATER_THAN	1
-#define  OACEC0_0_B0_COMPARE_EQUAL		2
-#define  OACEC0_0_B0_COMPARE_GREATER_OR_EQUAL	3
-#define  OACEC0_0_B0_COMPARE_LESS_THAN		4
-#define  OACEC0_0_B0_COMPARE_NOT_EQUAL		5
-#define  OACEC0_0_B0_COMPARE_LESS_OR_EQUAL	6
-#define  OACEC0_0_B0_COMPARE_VALUE_MASK		0xffff
-#define  OACEC0_0_B0_COMPARE_VALUE_SHIFT	3
-
-#define OACEC0_1 0x2774
-
 #define GEN7_OABUFFER 0x23B0 /* R/W */
 #define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1<<3)
 #define  GEN7_OABUFFER_EDGE_TRIGGER	    (1<<2)
@@ -584,6 +556,272 @@
 #define GEN7_OASTATUS2_HEAD_MASK    0xffffffc0
 #define GEN7_OASTATUS2_GGTT	    0x1
 
+#define GDT_CHICKEN_BITS    0x9840
+#define GT_NOA_ENABLE	    0x00000080
+
+/*
+ * OA Boolean state
+ */
+
+#define OAREPORTTRIG1 0x2740
+#define OAREPORTTRIG1_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG2 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 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 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 0x2750
+#define OAREPORTTRIG5_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG6 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 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 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 0x2710
+#define OASTARTTRIG1_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG1_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG2 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 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 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 0x2720
+#define OASTARTTRIG5_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG5_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG6 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 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 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 0x2770
+#define OACEC0_1 0x2774
+#define OACEC1_0 0x2778
+#define OACEC1_1 0x277c
+#define OACEC2_0 0x2780
+#define OACEC2_1 0x2784
+#define OACEC3_0 0x2788
+#define OACEC3_1 0x278c
+#define OACEC4_0 0x2790
+#define OACEC4_1 0x2794
+#define OACEC5_0 0x2798
+#define OACEC5_1 0x279c
+#define OACEC6_0 0x27a0
+#define OACEC6_1 0x27a4
+#define OACEC7_0 0x27a8
+#define OACEC7_1 0x27ac
+
+
 #define _GEN7_PIPEA_DE_LOAD_SL	0x70068
 #define _GEN7_PIPEB_DE_LOAD_SL	0x71068
 #define GEN7_PIPE_DE_LOAD_SL(pipe) _PIPE(pipe, \
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index f78f232..7aa1d33 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -71,6 +71,8 @@
 #define I915_OA_FORMAT_B4_C8_A16_HSW	6
 #define I915_OA_FORMAT_C4_B8_HSW	7
 
+#define I915_OA_METRICS_SET_3D		1
+
 #define I915_OA_ATTR_SIZE_VER0		32  /* sizeof first published struct */
 
 typedef struct _drm_i915_oa_attr {
-- 
2.3.2


WARNING: multiple messages have this Message-ID (diff)
From: Robert Bragg <robert@sixbynine.org>
To: intel-gfx@lists.freedesktop.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	David Airlie <airlied@linux.ie>,
	linux-api@vger.kernel.org, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
	Paul Mackerras <paulus@samba.org>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Daniel Vetter <daniel.vetter@intel.com>
Subject: [RFC PATCH 08/11] drm/i915: add OA config for 3D render counters
Date: Thu,  7 May 2015 15:15:51 +0100	[thread overview]
Message-ID: <1431008154-6833-9-git-send-email-robert@sixbynine.org> (raw)
In-Reply-To: <1431008154-6833-1-git-send-email-robert@sixbynine.org>

This enables access to some additional counters beyond the aggregating A
counters, adding a '3D' metric set configuration useful while profiling
3D rendering workloads.

Signed-off-by: Robert Bragg <robert@sixbynine.org>
---
 drivers/gpu/drm/i915/i915_drv.h     |   7 +
 drivers/gpu/drm/i915/i915_oa_perf.c | 124 +++++++++++++--
 drivers/gpu/drm/i915/i915_reg.h     | 294 ++++++++++++++++++++++++++++++++----
 include/uapi/drm/i915_drm.h         |   2 +
 4 files changed, 385 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3d8e4ed..1e65dc2 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1564,6 +1564,13 @@ struct i915_virtual_gpu {
 	bool active;
 };
 
+#ifdef CONFIG_PERF_EVENTS
+struct i915_oa_reg {
+	u32 addr;
+	u32 value;
+};
+#endif
+
 struct drm_i915_private {
 	struct drm_device *dev;
 	struct kmem_cache *objects;
diff --git a/drivers/gpu/drm/i915/i915_oa_perf.c b/drivers/gpu/drm/i915/i915_oa_perf.c
index a1cf55f..d0e144c 100644
--- a/drivers/gpu/drm/i915/i915_oa_perf.c
+++ b/drivers/gpu/drm/i915/i915_oa_perf.c
@@ -23,6 +23,80 @@ static int hsw_perf_format_sizes[] = {
 	64   /* C4_B8_HSW */
 };
 
+
+/* A generated mux config to select counters useful for profiling 3D
+ * workloads */
+static struct i915_oa_reg hsw_profile_3d_mux_config[] = {
+
+	{ 0x253A4, 0x01600000 },
+	{ 0x25440, 0x00100000 },
+	{ 0x25128, 0x00000000 },
+	{ 0x2691C, 0x00000800 },
+	{ 0x26AA0, 0x01500000 },
+	{ 0x26B9C, 0x00006000 },
+	{ 0x2791C, 0x00000800 },
+	{ 0x27AA0, 0x01500000 },
+	{ 0x27B9C, 0x00006000 },
+	{ 0x2641C, 0x00000400 },
+	{ 0x25380, 0x00000010 },
+	{ 0x2538C, 0x00000000 },
+	{ 0x25384, 0x0800AAAA },
+	{ 0x25400, 0x00000004 },
+	{ 0x2540C, 0x06029000 },
+	{ 0x25410, 0x00000002 },
+	{ 0x25404, 0x5C30FFFF },
+	{ 0x25100, 0x00000016 },
+	{ 0x25110, 0x00000400 },
+	{ 0x25104, 0x00000000 },
+	{ 0x26804, 0x00001211 },
+	{ 0x26884, 0x00000100 },
+	{ 0x26900, 0x00000002 },
+	{ 0x26908, 0x00700000 },
+	{ 0x26904, 0x00000000 },
+	{ 0x26984, 0x00001022 },
+	{ 0x26A04, 0x00000011 },
+	{ 0x26A80, 0x00000006 },
+	{ 0x26A88, 0x00000C02 },
+	{ 0x26A84, 0x00000000 },
+	{ 0x26B04, 0x00001000 },
+	{ 0x26B80, 0x00000002 },
+	{ 0x26B8C, 0x00000007 },
+	{ 0x26B84, 0x00000000 },
+	{ 0x27804, 0x00004844 },
+	{ 0x27884, 0x00000400 },
+	{ 0x27900, 0x00000002 },
+	{ 0x27908, 0x0E000000 },
+	{ 0x27904, 0x00000000 },
+	{ 0x27984, 0x00004088 },
+	{ 0x27A04, 0x00000044 },
+	{ 0x27A80, 0x00000006 },
+	{ 0x27A88, 0x00018040 },
+	{ 0x27A84, 0x00000000 },
+	{ 0x27B04, 0x00004000 },
+	{ 0x27B80, 0x00000002 },
+	{ 0x27B8C, 0x000000E0 },
+	{ 0x27B84, 0x00000000 },
+	{ 0x26104, 0x00002222 },
+	{ 0x26184, 0x0C006666 },
+	{ 0x26284, 0x04000000 },
+	{ 0x26304, 0x04000000 },
+	{ 0x26400, 0x00000002 },
+	{ 0x26410, 0x000000A0 },
+	{ 0x26404, 0x00000000 },
+	{ 0x25420, 0x04108020 },
+	{ 0x25424, 0x1284A420 },
+	{ 0x2541C, 0x00000000 },
+	{ 0x25428, 0x00042049 },
+};
+
+/* A corresponding B counter configuration for profiling 3D workloads */
+static struct i915_oa_reg hsw_profile_3d_b_counter_config[] = {
+	{ 0x2724, 0x00800000 },
+	{ 0x2720, 0x00000000 },
+	{ 0x2714, 0x00800000 },
+	{ 0x2710, 0x00000000 },
+};
+
 static void forward_one_oa_snapshot_to_event(struct drm_i915_private *dev_priv,
 					     u8 *snapshot,
 					     struct perf_event *event)
@@ -551,6 +625,19 @@ static void update_oacontrol(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN7_OACONTROL, 0);
 }
 
+static void config_oa_regs(struct drm_i915_private *dev_priv,
+			   struct i915_oa_reg *regs,
+			   int n_regs)
+{
+	int i;
+
+	for (i = 0; i < n_regs; i++) {
+		struct i915_oa_reg *reg = regs + i;
+
+		I915_WRITE(reg->addr, reg->value);
+	}
+}
+
 static void i915_oa_event_start(struct perf_event *event, int flags)
 {
 	struct drm_i915_private *dev_priv =
@@ -571,22 +658,31 @@ static void i915_oa_event_start(struct perf_event *event, int flags)
 	WARN_ONCE(I915_READ(GEN6_UCGCTL3) & GEN6_OACSUNIT_CLOCK_GATE_DISABLE,
 		  "disabled OA unit level clock gating will result in incorrect per-context OA counters");
 
-	/* XXX: On Haswell, when threshold disable mode is desired,
-	 * instead of setting the threshold enable to '0', we need to
-	 * program it to '1' and set OASTARTTRIG1 bits 15:0 to 0
-	 * (threshold value of 0)
-	 */
-	I915_WRITE(OASTARTTRIG6, (OASTARTTRIG6_B4_TO_B7_THRESHOLD_ENABLE |
-				  OASTARTTRIG6_B4_CUSTOM_EVENT_ENABLE));
-	I915_WRITE(OASTARTTRIG5, 0); /* threshold value */
+	I915_WRITE(GDT_CHICKEN_BITS, GT_NOA_ENABLE);
 
-	I915_WRITE(OASTARTTRIG2, (OASTARTTRIG2_B0_TO_B3_THRESHOLD_ENABLE |
-				  OASTARTTRIG2_B0_CUSTOM_EVENT_ENABLE));
-	I915_WRITE(OASTARTTRIG1, 0); /* threshold value */
+	if (dev_priv->oa_pmu.metrics_set == I915_OA_METRICS_SET_3D) {
+		config_oa_regs(dev_priv, hsw_profile_3d_mux_config,
+			       ARRAY_SIZE(hsw_profile_3d_mux_config));
+		config_oa_regs(dev_priv, hsw_profile_3d_b_counter_config,
+			       ARRAY_SIZE(hsw_profile_3d_b_counter_config));
+	} else {
+		/* XXX: On Haswell, when threshold disable mode is desired,
+		 * instead of setting the threshold enable to '0', we need to
+		 * program it to '1' and set OASTARTTRIG1 bits 15:0 to 0
+		 * (threshold value of 0)
+		 */
+		I915_WRITE(OASTARTTRIG6, (OASTARTTRIG6_THRESHOLD_ENABLE |
+					  OASTARTTRIG6_EVENT_SELECT_4));
+		I915_WRITE(OASTARTTRIG5, 0); /* threshold value */
 
-	/* Setup B0 as the gpu clock counter... */
-	I915_WRITE(OACEC0_0, OACEC0_0_B0_COMPARE_GREATER_OR_EQUAL); /* to 0 */
-	I915_WRITE(OACEC0_1, 0xfffe); /* Select NOA[0] */
+		I915_WRITE(OASTARTTRIG2, (OASTARTTRIG2_THRESHOLD_ENABLE |
+					  OASTARTTRIG2_EVENT_SELECT_0));
+		I915_WRITE(OASTARTTRIG1, 0); /* threshold value */
+
+		/* Setup B0 as the gpu clock counter... */
+		I915_WRITE(OACEC0_0, OACEC_COMPARE_GREATER_OR_EQUAL); /* to 0 */
+		I915_WRITE(OACEC0_1, 0xfffe); /* Select NOA[0] */
+	}
 
 	spin_lock_irqsave(&dev_priv->oa_pmu.lock, lock_flags);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9e427cc..d94932a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -532,34 +532,6 @@
 #define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1<<1)
 #define  GEN7_OACONTROL_ENABLE		    (1<<0)
 
-#define OASTARTTRIG5 0x02720
-#define  OASTARTTRIG5_THRESHOLD_VALUE_MASK	0xffff
-
-#define OASTARTTRIG6 0x02724
-#define  OASTARTTRIG6_B4_TO_B7_THRESHOLD_ENABLE (1<<23)
-#define  OASTARTTRIG6_B4_CUSTOM_EVENT_ENABLE	(1<<28)
-
-#define OASTARTTRIG1 0x02710
-#define  OASTARTTRIG1_THRESHOLD_VALUE_MASK	0xffff
-
-#define OASTARTTRIG2 0x02714
-#define  OASTARTTRIG2_B0_TO_B3_THRESHOLD_ENABLE (1<<23)
-#define  OASTARTTRIG2_B0_CUSTOM_EVENT_ENABLE	(1<<28)
-
-#define OACEC0_0 0x2770
-#define  OACEC0_0_B0_COMPARE_ANY_EQUAL		0
-#define  OACEC0_0_B0_COMPARE_OR			0
-#define  OACEC0_0_B0_COMPARE_GREATER_THAN	1
-#define  OACEC0_0_B0_COMPARE_EQUAL		2
-#define  OACEC0_0_B0_COMPARE_GREATER_OR_EQUAL	3
-#define  OACEC0_0_B0_COMPARE_LESS_THAN		4
-#define  OACEC0_0_B0_COMPARE_NOT_EQUAL		5
-#define  OACEC0_0_B0_COMPARE_LESS_OR_EQUAL	6
-#define  OACEC0_0_B0_COMPARE_VALUE_MASK		0xffff
-#define  OACEC0_0_B0_COMPARE_VALUE_SHIFT	3
-
-#define OACEC0_1 0x2774
-
 #define GEN7_OABUFFER 0x23B0 /* R/W */
 #define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1<<3)
 #define  GEN7_OABUFFER_EDGE_TRIGGER	    (1<<2)
@@ -584,6 +556,272 @@
 #define GEN7_OASTATUS2_HEAD_MASK    0xffffffc0
 #define GEN7_OASTATUS2_GGTT	    0x1
 
+#define GDT_CHICKEN_BITS    0x9840
+#define GT_NOA_ENABLE	    0x00000080
+
+/*
+ * OA Boolean state
+ */
+
+#define OAREPORTTRIG1 0x2740
+#define OAREPORTTRIG1_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG2 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 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 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 0x2750
+#define OAREPORTTRIG5_THRESHOLD_MASK 0xffff
+#define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
+
+#define OAREPORTTRIG6 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 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 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 0x2710
+#define OASTARTTRIG1_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG1_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG2 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 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 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 0x2720
+#define OASTARTTRIG5_THRESHOLD_COUNT_MASK_MBZ 0xffff0000
+#define OASTARTTRIG5_THRESHOLD_MASK	      0xffff
+
+#define OASTARTTRIG6 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 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 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 0x2770
+#define OACEC0_1 0x2774
+#define OACEC1_0 0x2778
+#define OACEC1_1 0x277c
+#define OACEC2_0 0x2780
+#define OACEC2_1 0x2784
+#define OACEC3_0 0x2788
+#define OACEC3_1 0x278c
+#define OACEC4_0 0x2790
+#define OACEC4_1 0x2794
+#define OACEC5_0 0x2798
+#define OACEC5_1 0x279c
+#define OACEC6_0 0x27a0
+#define OACEC6_1 0x27a4
+#define OACEC7_0 0x27a8
+#define OACEC7_1 0x27ac
+
+
 #define _GEN7_PIPEA_DE_LOAD_SL	0x70068
 #define _GEN7_PIPEB_DE_LOAD_SL	0x71068
 #define GEN7_PIPE_DE_LOAD_SL(pipe) _PIPE(pipe, \
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index f78f232..7aa1d33 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -71,6 +71,8 @@
 #define I915_OA_FORMAT_B4_C8_A16_HSW	6
 #define I915_OA_FORMAT_C4_B8_HSW	7
 
+#define I915_OA_METRICS_SET_3D		1
+
 #define I915_OA_ATTR_SIZE_VER0		32  /* sizeof first published struct */
 
 typedef struct _drm_i915_oa_attr {
-- 
2.3.2

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

  parent reply	other threads:[~2015-05-07 14:17 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-05-07 14:15 [RFC PATCH 00/11] drm/i915: Expose OA metrics via perf PMU Robert Bragg
2015-05-07 14:15 ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 01/11] perf: export perf_event_overflow Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 02/11] perf: Add PERF_PMU_CAP_IS_DEVICE flag Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 03/11] perf: Add PERF_EVENT_IOC_FLUSH ioctl Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:20   ` [Intel-gfx] " Chris Wilson
2015-05-07 14:20     ` Chris Wilson
2015-05-18 17:25     ` [RFC PATCH v2] " Robert Bragg
2015-05-18 17:25       ` Robert Bragg
2015-05-20 12:12       ` Ingo Molnar
2015-05-20 12:12         ` Ingo Molnar
2015-05-21 17:40         ` [RFC PATCH] perf: enable fsync to flush buffered samples Robert Bragg
2015-05-21 17:40           ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 04/11] perf: Add a PERF_RECORD_DEVICE event type Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 05/11] perf: allow drivers more control over event logging Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 06/11] drm/i915: rename OACONTROL GEN7_OACONTROL Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 07/11] drm/i915: Expose PMU for Observation Architecture Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:36   ` [Intel-gfx] " Chris Wilson
2015-05-07 14:36     ` Chris Wilson
2015-05-18 16:21     ` Robert Bragg
2015-05-07 14:58   ` [Intel-gfx] " Chris Wilson
2015-05-07 14:58     ` Chris Wilson
2015-05-18 16:36     ` Robert Bragg
2015-05-18 16:36       ` Robert Bragg
2015-05-18 17:17       ` [RFC PATCH v2] " Robert Bragg
2015-05-18 17:17         ` Robert Bragg
2015-05-18 17:21       ` [RFC PATCH] squash: be more careful stopping oacontrol updates Robert Bragg
2015-05-18 17:21         ` Robert Bragg
2015-05-07 14:15 ` Robert Bragg [this message]
2015-05-07 14:15   ` [RFC PATCH 08/11] drm/i915: add OA config for 3D render counters Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 09/11] drm/i915: Add dev.i915.oa_event_paranoid sysctl option Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 10/11] drm/i915: report OA buf overrun + report lost status Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-07 14:15 ` [RFC PATCH 11/11] WIP: drm/i915: constrain unit gating while using OA Robert Bragg
2015-05-07 14:15   ` Robert Bragg
2015-05-08 16:21 ` [RFC PATCH 00/11] drm/i915: Expose OA metrics via perf PMU Peter Zijlstra
2015-05-08 16:21   ` Peter Zijlstra
2015-05-18 17:29   ` Robert Bragg
2015-05-18 17:29     ` Robert Bragg
2015-05-08 16:24 ` Peter Zijlstra
2015-05-08 16:24   ` Peter Zijlstra
2015-05-15  1:07   ` Robert Bragg
2015-05-15  1:07     ` Robert Bragg
2015-05-19 14:53     ` Peter Zijlstra
2015-05-19 14:53       ` Peter Zijlstra
2015-05-20 23:17       ` Robert Bragg
2015-05-20 23:17         ` Robert Bragg
2015-05-21  8:24         ` [Intel-gfx] " Daniel Vetter
2015-05-21  8:24           ` Daniel Vetter
2015-05-27 15:39         ` Peter Zijlstra
2015-05-27 15:39           ` Peter Zijlstra
2015-05-27 16:41           ` Ingo Molnar
2015-05-27 16:41             ` Ingo Molnar
2015-06-04 18:53           ` [Intel-gfx] " Robert Bragg
2015-06-04 18:53             ` Robert Bragg

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1431008154-6833-9-git-send-email-robert@sixbynine.org \
    --to=robert@sixbynine.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=airlied@linux.ie \
    --cc=daniel.vetter@intel.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=jani.nikula@linux.intel.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.