diff options
| author | Rob Clark <robdclark@chromium.org> | 2022-03-03 16:52:17 -0800 |
|---|---|---|
| committer | Rob Clark <robdclark@chromium.org> | 2022-03-04 11:59:31 -0800 |
| commit | 5f9ffe89803387078c3b253970795fa7ed447f18 (patch) | |
| tree | 299f41e772b7f30b5b3ace8293ee8e5fa25edaf7 /drivers/gpu/drm/msm/adreno | |
| parent | 90f45c42d7d7b0ec0fd797485c07fc421c474e12 (diff) | |
| download | linux-5f9ffe89803387078c3b253970795fa7ed447f18.tar.bz2 | |
drm/msm/a6xx: Zap counters across context switch
Any app controlled perfcntr collection (GL_AMD_performance_monitor, etc)
does not require counters to maintain state across context switches. So
clear them if systemwide profiling is not active.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Link: https://lore.kernel.org/r/20220304005317.776110-5-robdclark@gmail.com
Diffstat (limited to 'drivers/gpu/drm/msm/adreno')
| -rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 29 |
1 files changed, 29 insertions, 0 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 237c2e7a7baa..02b47977b5c3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -101,6 +101,7 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter, static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, struct msm_ringbuffer *ring, struct msm_file_private *ctx) { + bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1; phys_addr_t ttbr; u32 asid; u64 memptr = rbmemptr(ring, ttbr0); @@ -111,6 +112,15 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid)) return; + if (!sysprof) { + /* Turn off protected mode to write to special registers */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 0); + + OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } + /* Execute the table update */ OUT_PKT7(ring, CP_SMMU_TABLE_UPDATE, 4); OUT_RING(ring, CP_SMMU_TABLE_UPDATE_0_TTBR0_LO(lower_32_bits(ttbr))); @@ -137,6 +147,25 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_PKT7(ring, CP_EVENT_WRITE, 1); OUT_RING(ring, 0x31); + + if (!sysprof) { + /* + * Wait for SRAM clear after the pgtable update, so the + * two can happen in parallel: + */ + OUT_PKT7(ring, CP_WAIT_REG_MEM, 6); + OUT_RING(ring, CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ)); + OUT_RING(ring, CP_WAIT_REG_MEM_1_POLL_ADDR_LO( + REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); + OUT_RING(ring, CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0)); + OUT_RING(ring, CP_WAIT_REG_MEM_3_REF(0x1)); + OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1)); + OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0)); + + /* Re-enable protected mode: */ + OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); + OUT_RING(ring, 1); + } } static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) |