diff options
| author | David M Nieto <david.nieto@amd.com> | 2021-05-13 10:45:39 -0700 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2021-05-13 14:09:12 -0400 |
| commit | 5c439c38f5fb8fd16b65af4d5bc4618d1ec9bca3 (patch) | |
| tree | adbd38c6e9577f56fdaf45de009cd8b38b6be38a /drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | |
| parent | a7f0849682b75b6d50f07c70090443eebd90218c (diff) | |
drm/amdgpu: fix fence calculation (v2)
The proper metric for fence utilization over several
contexts is an harmonic mean, but such calculation is
prohibitive in kernel space, so the code approximates it.
Because the approximation diverges when one context has a
very small ratio compared with the other context, this change
filter out ratios smaller that 0.01%
v2: make the fence calculation static and initialize variables
within that function
v3: Fix warnings (Alex)
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: David M Nieto <david.nieto@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210513174539.27409-2-david.nieto@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 19 |
1 files changed, 16 insertions, 3 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 9036c93b4a0c..fc83445fbc40 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -652,12 +652,14 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr) mutex_destroy(&mgr->lock); } -void amdgpu_ctx_fence_time(struct amdgpu_ctx *ctx, struct amdgpu_ctx_entity *centity, - ktime_t *total, ktime_t *max) +static void amdgpu_ctx_fence_time(struct amdgpu_ctx *ctx, + struct amdgpu_ctx_entity *centity, ktime_t *total, ktime_t *max) { ktime_t now, t1; uint32_t i; + *total = *max = 0; + now = ktime_get(); for (i = 0; i < amdgpu_sched_jobs; i++) { struct dma_fence *fence; @@ -703,11 +705,22 @@ ktime_t amdgpu_ctx_mgr_fence_usage(struct amdgpu_ctx_mgr *mgr, uint32_t hwip, idp = &mgr->ctx_handles; mutex_lock(&mgr->lock); idr_for_each_entry(idp, ctx, id) { + ktime_t ttotal, tmax; + if (!ctx->entities[hwip][idx]) continue; centity = ctx->entities[hwip][idx]; - amdgpu_ctx_fence_time(ctx, centity, &total, &max); + amdgpu_ctx_fence_time(ctx, centity, &ttotal, &tmax); + + /* Harmonic mean approximation diverges for very small + * values. If ratio < 0.01% ignore + */ + if (AMDGPU_CTX_FENCE_USAGE_MIN_RATIO(tmax, ttotal)) + continue; + + total = ktime_add(total, ttotal); + max = ktime_after(tmax, max) ? tmax : max; } mutex_unlock(&mgr->lock); |