drm/radeon/kms: add more elaborate benchmarks

Lots of new (and hopefully useful) benchmark. Load the driver
with radeon_benchmark=<test_number> and enjoy. Among tests
added are VRAM to VRAM blits and blits with buffer size sweeps.
The latter can be from GTT to VRAM, VRAM to GTT, and VRAM to VRAM
and there are two types of sweeps: powers of two and (probably
more interesting) buffers sizes that correspond to common modes.

Signed-off-by: Ilija Hadzic <ihadzic@research.bell-labs.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

3 files changed, 87 insertions, 8 deletions

diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index a116d42a238a..9f6d206104df 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -843,7 +843,7 @@ struct radeon_pm {
 /*
  * Benchmarking
  */
-void radeon_benchmark(struct radeon_device *rdev);
+void radeon_benchmark(struct radeon_device *rdev, int test_number);
 
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 6951426dbb12..5cafc90de7f8 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -30,6 +30,7 @@
 #define RADEON_BENCHMARK_COPY_DMA  0
 
 #define RADEON_BENCHMARK_ITERATIONS 1024
+#define RADEON_BENCHMARK_COMMON_MODES_N 17
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
@@ -126,7 +127,9 @@ static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
 	}
 
 	/* r100 doesn't have dma engine so skip the test */
-	if (rdev->asic->copy_dma) {
+	/* also, VRAM-to-VRAM test doesn't make much sense for DMA */
+	/* skip it as well if domains are the same */
+	if ((rdev->asic->copy_dma) && (sdomain != ddomain)) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
 						RADEON_BENCHMARK_COPY_DMA, n);
 		if (time < 0)
@@ -167,10 +170,86 @@ out_cleanup:
 	}
 }
 
-void radeon_benchmark(struct radeon_device *rdev)
+void radeon_benchmark(struct radeon_device *rdev, int test_number)
 {
-	radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_GTT,
-			      RADEON_GEM_DOMAIN_VRAM);
-	radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
-			      RADEON_GEM_DOMAIN_GTT);
+	int i;
+	int common_modes[RADEON_BENCHMARK_COMMON_MODES_N] = {
+		640 * 480 * 4,
+		720 * 480 * 4,
+		800 * 600 * 4,
+		848 * 480 * 4,
+		1024 * 768 * 4,
+		1152 * 768 * 4,
+		1280 * 720 * 4,
+		1280 * 800 * 4,
+		1280 * 854 * 4,
+		1280 * 960 * 4,
+		1280 * 1024 * 4,
+		1440 * 900 * 4,
+		1400 * 1050 * 4,
+		1680 * 1050 * 4,
+		1600 * 1200 * 4,
+		1920 * 1080 * 4,
+		1920 * 1200 * 4
+	};
+
+	switch (test_number) {
+	case 1:
+		/* simple test, VRAM to GTT and GTT to VRAM */
+		radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_GTT,
+				      RADEON_GEM_DOMAIN_VRAM);
+		radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
+				      RADEON_GEM_DOMAIN_GTT);
+		break;
+	case 2:
+		/* simple test, VRAM to VRAM */
+		radeon_benchmark_move(rdev, 1024*1024, RADEON_GEM_DOMAIN_VRAM,
+				      RADEON_GEM_DOMAIN_VRAM);
+		break;
+	case 3:
+		/* GTT to VRAM, buffer size sweep, powers of 2 */
+		for (i = 1; i <= 65536; i <<= 1)
+			radeon_benchmark_move(rdev, i*1024,
+					      RADEON_GEM_DOMAIN_GTT,
+					      RADEON_GEM_DOMAIN_VRAM);
+		break;
+	case 4:
+		/* VRAM to GTT, buffer size sweep, powers of 2 */
+		for (i = 1; i <= 65536; i <<= 1)
+			radeon_benchmark_move(rdev, i*1024,
+					      RADEON_GEM_DOMAIN_VRAM,
+					      RADEON_GEM_DOMAIN_GTT);
+		break;
+	case 5:
+		/* VRAM to VRAM, buffer size sweep, powers of 2 */
+		for (i = 1; i <= 65536; i <<= 1)
+			radeon_benchmark_move(rdev, i*1024,
+					      RADEON_GEM_DOMAIN_VRAM,
+					      RADEON_GEM_DOMAIN_VRAM);
+		break;
+	case 6:
+		/* GTT to VRAM, buffer size sweep, common modes */
+		for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+			radeon_benchmark_move(rdev, common_modes[i],
+					      RADEON_GEM_DOMAIN_GTT,
+					      RADEON_GEM_DOMAIN_VRAM);
+		break;
+	case 7:
+		/* VRAM to GTT, buffer size sweep, common modes */
+		for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+			radeon_benchmark_move(rdev, common_modes[i],
+					      RADEON_GEM_DOMAIN_VRAM,
+					      RADEON_GEM_DOMAIN_GTT);
+		break;
+	case 8:
+		/* VRAM to VRAM, buffer size sweep, common modes */
+		for (i = 1; i < RADEON_BENCHMARK_COMMON_MODES_N; i++)
+			radeon_benchmark_move(rdev, common_modes[i],
+					      RADEON_GEM_DOMAIN_VRAM,
+					      RADEON_GEM_DOMAIN_VRAM);
+		break;
+
+	default:
+		DRM_ERROR("Unknown benchmark\n");
+	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index cc695d05bd2b..c33bc914d93d 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -818,7 +818,7 @@ int radeon_device_init(struct radeon_device *rdev,
 		radeon_test_moves(rdev);
 	}
 	if (radeon_benchmarking) {
-		radeon_benchmark(rdev);
+		radeon_benchmark(rdev, radeon_benchmarking);
 	}
 	return 0;
 }