[Intel-gfx] [PATCH i-g-t v5 02/11] tests/perf: add per context filtering test for gen8+

2017-08-31 Thread Lionel Landwerlin 
From: Robert Bragg 

Signed-off-by: Robert Bragg 
Signed-off-by: Lionel Landwerlin 
---
 tests/perf.c | 777 ---
 1 file changed, 745 insertions(+), 32 deletions(-)

diff --git a/tests/perf.c b/tests/perf.c
index f89a235e..8644e252 100644
--- a/tests/perf.c
+++ b/tests/perf.c
@@ -48,7 +48,9 @@ IGT_TEST_DESCRIPTION("Test the i915 perf metrics streaming 
interface");
 #define OAREPORT_REASON_MASK   0x3f
 #define OAREPORT_REASON_SHIFT  19
 #define OAREPORT_REASON_TIMER  (1<<0)
+#define OAREPORT_REASON_INTERNAL   (3<<1)
 #define OAREPORT_REASON_CTX_SWITCH (1<<3)
+#define OAREPORT_REASON_GO (1<<4)
 #define OAREPORT_REASON_CLK_RATIO  (1<<5)
 
 #define GFX_OP_PIPE_CONTROL ((3 << 29) | (3 << 27) | (2 << 24))
@@ -574,6 +576,22 @@ oa_exponent_to_ns(int exponent)
return 10ULL * (2ULL << exponent) / timestamp_frequency;
 }
 
+static bool
+oa_report_ctx_is_valid(uint32_t *report)
+{
+   if (IS_HASWELL(devid)) {
+   return false; /* TODO */
+   } else if (IS_GEN8(devid)) {
+   return report[0] & (1ul << 25);
+   } else if (IS_GEN9(devid)) {
+   return report[0] & (1ul << 16);
+   }
+
+   /* Need to update this function for newer Gen. */
+   igt_assert(!"reached");
+}
+
+
 static void
 hsw_sanity_check_render_basic_reports(uint32_t *oa_report0, uint32_t 
*oa_report1,
  enum drm_i915_oa_format fmt)
@@ -678,6 +696,100 @@ gen8_40bit_a_delta(uint64_t value0, uint64_t value1)
return value1 - value0;
 }
 
+static void
+accumulate_uint32(size_t offset,
+ uint32_t *report0,
+  uint32_t *report1,
+  uint64_t *delta)
+{
+   uint32_t value0 = *(uint32_t *)(((uint8_t *)report0) + offset);
+   uint32_t value1 = *(uint32_t *)(((uint8_t *)report1) + offset);
+
+   *delta += (uint32_t)(value1 - value0);
+}
+
+static void
+accumulate_uint40(int a_index,
+  uint32_t *report0,
+  uint32_t *report1,
+ enum drm_i915_oa_format format,
+  uint64_t *delta)
+{
+   uint64_t value0 = gen8_read_40bit_a_counter(report0, format, a_index),
+value1 = gen8_read_40bit_a_counter(report1, format, a_index);
+
+   *delta += gen8_40bit_a_delta(value0, value1);
+}
+
+static void
+accumulate_reports(struct accumulator *accumulator,
+  uint32_t *start,
+  uint32_t *end)
+{
+   enum drm_i915_oa_format format = accumulator->format;
+   uint64_t *deltas = accumulator->deltas;
+   int idx = 0;
+
+   if (intel_gen(devid) >= 8) {
+   /* timestamp */
+   accumulate_uint32(4, start, end, deltas + idx++);
+
+   /* clock cycles */
+   accumulate_uint32(12, start, end, deltas + idx++);
+   } else {
+   /* timestamp */
+   accumulate_uint32(4, start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a40; i++)
+   accumulate_uint40(i, start, end, format, deltas + idx++);
+
+   for (int i = 0; i < oa_formats[format].n_a; i++) {
+   accumulate_uint32(oa_formats[format].a_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_b; i++) {
+   accumulate_uint32(oa_formats[format].b_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_c; i++) {
+   accumulate_uint32(oa_formats[format].c_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+}
+
+static void
+accumulator_print(struct accumulator *accumulator, const char *title)
+{
+   enum drm_i915_oa_format format = accumulator->format;
+   uint64_t *deltas = accumulator->deltas;
+   int idx = 0;
+
+   igt_debug("%s:\n", title);
+   if (intel_gen(devid) >= 8) {
+   igt_debug("\ttime delta = %lu\n", deltas[idx++]);
+   igt_debug("\tclock cycle delta = %lu\n", deltas[idx++]);
+
+   for (int i = 0; i < oa_formats[format].n_a40; i++)
+   igt_debug("\tA%u = %lu\n", i, deltas[idx++]);
+   } else {
+   igt_debug("\ttime delta = %lu\n", deltas[idx++]);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a; i++) {
+   int a_id = oa_formats[format].first_a + i;
+   igt_debug("\tA%u = %lu\n", a_id, deltas[idx++]);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a; i++)
+   igt_debug("\tB%u = %lu\n", i, deltas[idx++]);
+
+   for (int i = 0; i < oa_formats[format].n_c; i++)
+   igt_debug("\tC%u = %lu\n", i, deltas[idx++]);
+}
+
 /* The TestOa metric set is designed so */
 static void
 gen8_sanity_check_test_

Re: [Intel-gfx] [PATCH i-g-t v5 02/11] tests/perf: add per context filtering test for gen8+

2017-10-04 Thread Lionel Landwerlin 

Hey Matt,

Any feedback on this patch?

On 31/08/17 11:35, Lionel Landwerlin wrote:

From: Robert Bragg 

Signed-off-by: Robert Bragg 
Signed-off-by: Lionel Landwerlin 
---
  tests/perf.c | 777 ---
  1 file changed, 745 insertions(+), 32 deletions(-)

diff --git a/tests/perf.c b/tests/perf.c
index f89a235e..8644e252 100644
--- a/tests/perf.c
+++ b/tests/perf.c
@@ -48,7 +48,9 @@ IGT_TEST_DESCRIPTION("Test the i915 perf metrics streaming 
interface");
  #define OAREPORT_REASON_MASK   0x3f
  #define OAREPORT_REASON_SHIFT  19
  #define OAREPORT_REASON_TIMER  (1<<0)
+#define OAREPORT_REASON_INTERNAL   (3<<1)
  #define OAREPORT_REASON_CTX_SWITCH (1<<3)
+#define OAREPORT_REASON_GO (1<<4)
  #define OAREPORT_REASON_CLK_RATIO  (1<<5)
  
  #define GFX_OP_PIPE_CONTROL ((3 << 29) | (3 << 27) | (2 << 24))

@@ -574,6 +576,22 @@ oa_exponent_to_ns(int exponent)
 return 10ULL * (2ULL << exponent) / timestamp_frequency;
  }
  
+static bool

+oa_report_ctx_is_valid(uint32_t *report)
+{
+   if (IS_HASWELL(devid)) {
+   return false; /* TODO */
+   } else if (IS_GEN8(devid)) {
+   return report[0] & (1ul << 25);
+   } else if (IS_GEN9(devid)) {
+   return report[0] & (1ul << 16);
+   }
+
+   /* Need to update this function for newer Gen. */
+   igt_assert(!"reached");
+}
+
+
  static void
  hsw_sanity_check_render_basic_reports(uint32_t *oa_report0, uint32_t 
*oa_report1,
  enum drm_i915_oa_format fmt)
@@ -678,6 +696,100 @@ gen8_40bit_a_delta(uint64_t value0, uint64_t value1)
return value1 - value0;
  }
  
+static void

+accumulate_uint32(size_t offset,
+ uint32_t *report0,
+  uint32_t *report1,
+  uint64_t *delta)
+{
+   uint32_t value0 = *(uint32_t *)(((uint8_t *)report0) + offset);
+   uint32_t value1 = *(uint32_t *)(((uint8_t *)report1) + offset);
+
+   *delta += (uint32_t)(value1 - value0);
+}
+
+static void
+accumulate_uint40(int a_index,
+  uint32_t *report0,
+  uint32_t *report1,
+ enum drm_i915_oa_format format,
+  uint64_t *delta)
+{
+   uint64_t value0 = gen8_read_40bit_a_counter(report0, format, a_index),
+value1 = gen8_read_40bit_a_counter(report1, format, a_index);
+
+   *delta += gen8_40bit_a_delta(value0, value1);
+}
+
+static void
+accumulate_reports(struct accumulator *accumulator,
+  uint32_t *start,
+  uint32_t *end)
+{
+   enum drm_i915_oa_format format = accumulator->format;
+   uint64_t *deltas = accumulator->deltas;
+   int idx = 0;
+
+   if (intel_gen(devid) >= 8) {
+   /* timestamp */
+   accumulate_uint32(4, start, end, deltas + idx++);
+
+   /* clock cycles */
+   accumulate_uint32(12, start, end, deltas + idx++);
+   } else {
+   /* timestamp */
+   accumulate_uint32(4, start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a40; i++)
+   accumulate_uint40(i, start, end, format, deltas + idx++);
+
+   for (int i = 0; i < oa_formats[format].n_a; i++) {
+   accumulate_uint32(oa_formats[format].a_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_b; i++) {
+   accumulate_uint32(oa_formats[format].b_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_c; i++) {
+   accumulate_uint32(oa_formats[format].c_off + 4 * i,
+ start, end, deltas + idx++);
+   }
+}
+
+static void
+accumulator_print(struct accumulator *accumulator, const char *title)
+{
+   enum drm_i915_oa_format format = accumulator->format;
+   uint64_t *deltas = accumulator->deltas;
+   int idx = 0;
+
+   igt_debug("%s:\n", title);
+   if (intel_gen(devid) >= 8) {
+   igt_debug("\ttime delta = %lu\n", deltas[idx++]);
+   igt_debug("\tclock cycle delta = %lu\n", deltas[idx++]);
+
+   for (int i = 0; i < oa_formats[format].n_a40; i++)
+   igt_debug("\tA%u = %lu\n", i, deltas[idx++]);
+   } else {
+   igt_debug("\ttime delta = %lu\n", deltas[idx++]);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a; i++) {
+   int a_id = oa_formats[format].first_a + i;
+   igt_debug("\tA%u = %lu\n", a_id, deltas[idx++]);
+   }
+
+   for (int i = 0; i < oa_formats[format].n_a; i++)
+   igt_debug("\tB%u = %lu\n", i, deltas[idx++]);
+
+   for (int i = 0; i < oa_formats[format].n_c; i++)
+   igt_debug("\tC%u = %lu\n",