drm/radeon/kms: cleanup benchmark code

factor out repeated code into functions
fix units in which the throughput is reported (megabytes per second
and megabits per second make sense, others are kind of confusing)
make report more amenable to awk and friends (e.g. whitespace is
always the separator, unit is separated from the number, etc)
add #defines for some hard coded constants

besides "beautification" this reorg is done in preparation
for writing more elaborate benchmarks

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

diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 10191d9372d8eb07309cf6c1fd46af0a711d54f1..6951426dbb129adc5e7a9d7abc9c68f9ec6ab1cc 100644 (file)
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -26,21 +26,80 @@
 #include "radeon_reg.h"
 #include "radeon.h"
 
-void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
-                          unsigned sdomain, unsigned ddomain)
+#define RADEON_BENCHMARK_COPY_BLIT 1
+#define RADEON_BENCHMARK_COPY_DMA  0
+
+#define RADEON_BENCHMARK_ITERATIONS 1024
+
+static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
+                                   uint64_t saddr, uint64_t daddr,
+                                   int flag, int n)
+{
+       unsigned long start_jiffies;
+       unsigned long end_jiffies;
+       struct radeon_fence *fence = NULL;
+       int i, r;
+
+       start_jiffies = jiffies;
+       for (i = 0; i < n; i++) {
+               r = radeon_fence_create(rdev, &fence);
+               if (r)
+                       return r;
+
+               switch (flag) {
+               case RADEON_BENCHMARK_COPY_DMA:
+                       r = radeon_copy_dma(rdev, saddr, daddr,
+                                           size / RADEON_GPU_PAGE_SIZE,
+                                           fence);
+                       break;
+               case RADEON_BENCHMARK_COPY_BLIT:
+                       r = radeon_copy_blit(rdev, saddr, daddr,
+                                            size / RADEON_GPU_PAGE_SIZE,
+                                            fence);
+                       break;
+               default:
+                       DRM_ERROR("Unknown copy method\n");
+                       r = -EINVAL;
+               }
+               if (r)
+                       goto exit_do_move;
+               r = radeon_fence_wait(fence, false);
+               if (r)
+                       goto exit_do_move;
+               radeon_fence_unref(&fence);
+       }
+       end_jiffies = jiffies;
+       r = jiffies_to_msecs(end_jiffies - start_jiffies);
+
+exit_do_move:
+       if (fence)
+               radeon_fence_unref(&fence);
+       return r;
+}
+
+
+static void radeon_benchmark_log_results(int n, unsigned size,
+                                        unsigned int time,
+                                        unsigned sdomain, unsigned ddomain,
+                                        char *kind)
+{
+       unsigned int throughput = (n * (size >> 10)) / time;
+       DRM_INFO("radeon: %s %u bo moves of %u kB from"
+                " %d to %d in %u ms, throughput: %u Mb/s or %u MB/s\n",
+                kind, n, size >> 10, sdomain, ddomain, time,
+                throughput * 8, throughput);
+}
+
+static void radeon_benchmark_move(struct radeon_device *rdev, unsigned size,
+                                 unsigned sdomain, unsigned ddomain)
 {
        struct radeon_bo *dobj = NULL;
        struct radeon_bo *sobj = NULL;
-       struct radeon_fence *fence = NULL;
        uint64_t saddr, daddr;
-       unsigned long start_jiffies;
-       unsigned long end_jiffies;
-       unsigned long time;
-       unsigned i, n, size;
-       int r;
+       int r, n;
+       unsigned int time;
 
-       size = bsize;
-       n = 1024;
+       n = RADEON_BENCHMARK_ITERATIONS;
        r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, &sobj);
        if (r) {
                goto out_cleanup;
@@ -68,64 +127,23 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 
        /* r100 doesn't have dma engine so skip the test */
        if (rdev->asic->copy_dma) {
-
-               start_jiffies = jiffies;
-               for (i = 0; i < n; i++) {
-                       r = radeon_fence_create(rdev, &fence);
-                       if (r) {
-                               goto out_cleanup;
-                       }
-
-                       r = radeon_copy_dma(rdev, saddr, daddr,
-                                       size / RADEON_GPU_PAGE_SIZE, fence);
-
-                       if (r) {
-                               goto out_cleanup;
-                       }
-                       r = radeon_fence_wait(fence, false);
-                       if (r) {
-                               goto out_cleanup;
-                       }
-                       radeon_fence_unref(&fence);
-               }
-               end_jiffies = jiffies;
-               time = end_jiffies - start_jiffies;
-               time = jiffies_to_msecs(time);
-               if (time > 0) {
-                       i = ((n * size) >> 10) / time;
-                       printk(KERN_INFO "radeon: dma %u bo moves of %ukb from"
-                                       " %d to %d in %lums (%ukb/ms %ukb/s %uM/s)\n",
-                                       n, size >> 10,
-                                       sdomain, ddomain, time,
-                                       i, i * 1000, (i * 1000) / 1024);
-               }
-       }
-
-       start_jiffies = jiffies;
-       for (i = 0; i < n; i++) {
-               r = radeon_fence_create(rdev, &fence);
-               if (r) {
-                       goto out_cleanup;
-               }
-               r = radeon_copy_blit(rdev, saddr, daddr, size / RADEON_GPU_PAGE_SIZE, fence);
-               if (r) {
+               time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
+                                               RADEON_BENCHMARK_COPY_DMA, n);
+               if (time < 0)
                        goto out_cleanup;
-               }
-               r = radeon_fence_wait(fence, false);
-               if (r) {
-                       goto out_cleanup;
-               }
-               radeon_fence_unref(&fence);
-       }
-       end_jiffies = jiffies;
-       time = end_jiffies - start_jiffies;
-       time = jiffies_to_msecs(time);
-       if (time > 0) {
-               i = ((n * size) >> 10) / time;
-               printk(KERN_INFO "radeon: blit %u bo moves of %ukb from %d to %d"
-                      " in %lums (%ukb/ms %ukb/s %uM/s)\n", n, size >> 10,
-                      sdomain, ddomain, time, i, i * 1000, (i * 1000) / 1024);
+               if (time > 0)
+                       radeon_benchmark_log_results(n, size, time,
+                                                    sdomain, ddomain, "dma");
        }
+
+       time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
+                                       RADEON_BENCHMARK_COPY_BLIT, n);
+       if (time < 0)
+               goto out_cleanup;
+       if (time > 0)
+               radeon_benchmark_log_results(n, size, time,
+                                            sdomain, ddomain, "blit");
+
 out_cleanup:
        if (sobj) {
                r = radeon_bo_reserve(sobj, false);
@@ -143,11 +161,9 @@ out_cleanup:
                }
                radeon_bo_unref(&dobj);
        }
-       if (fence) {
-               radeon_fence_unref(&fence);
-       }
+
        if (r) {
-               printk(KERN_WARNING "Error while benchmarking BO move.\n");
+               DRM_ERROR("Error while benchmarking BO move.\n");
        }
 }