On Tue, Sep 17, 2024 at 01:14:17PM +0200, Antonino Maniscalco wrote:
> Use the postamble to reset perf counters when switching between rings,
> except when sysprof is enabled, analogously to how they are reset
> between submissions when switching pagetables.
>
> Signed-off-by: Antonino Maniscalco <antomani103@xxxxxxxxx>
Reviewed-by: Akhil P Oommen <quic_akhilpo@xxxxxxxxxxx>
-Akhil
> ---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 12 +++++++
> drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 6 ++++
> drivers/gpu/drm/msm/adreno/a6xx_preempt.c | 57 +++++++++++++++++++++++++++++++
> drivers/gpu/drm/msm/adreno/adreno_gpu.h | 7 ++--
> 4 files changed, 80 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index 355a3e210335..736f475d696f 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -358,6 +358,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> static void a6xx_emit_set_pseudo_reg(struct msm_ringbuffer *ring,
> struct a6xx_gpu *a6xx_gpu, struct msm_gpu_submitqueue *queue)
> {
> + u64 preempt_postamble;
> +
> OUT_PKT7(ring, CP_SET_PSEUDO_REG, 12);
>
> OUT_RING(ring, SMMU_INFO);
> @@ -381,6 +383,16 @@ static void a6xx_emit_set_pseudo_reg(struct msm_ringbuffer *ring,
> /* seems OK to set to 0 to disable it */
> OUT_RING(ring, 0);
> OUT_RING(ring, 0);
> +
> + /* Emit postamble to clear perfcounters */
> + preempt_postamble = a6xx_gpu->preempt_postamble_iova;
> +
> + OUT_PKT7(ring, CP_SET_AMBLE, 3);
> + OUT_RING(ring, lower_32_bits(preempt_postamble));
> + OUT_RING(ring, upper_32_bits(preempt_postamble));
> + OUT_RING(ring, CP_SET_AMBLE_2_DWORDS(
> + a6xx_gpu->preempt_postamble_len) |
> + CP_SET_AMBLE_2_TYPE(KMD_AMBLE_TYPE));
> }
>
> static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> index 7fc994121676..ae13892c87e3 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> @@ -71,6 +71,12 @@ struct a6xx_gpu {
> bool uses_gmem;
> bool skip_save_restore;
>
> + struct drm_gem_object *preempt_postamble_bo;
> + void *preempt_postamble_ptr;
> + uint64_t preempt_postamble_iova;
> + uint64_t preempt_postamble_len;
> + bool postamble_enabled;
> +
> struct a6xx_gmu gmu;
>
> struct drm_gem_object *shadow_bo;
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c
> index aa4bad394f9e..77c4d5e91854 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c
> @@ -97,6 +97,43 @@ static void a6xx_preempt_timer(struct timer_list *t)
> kthread_queue_work(gpu->worker, &gpu->recover_work);
> }
>
> +static void preempt_prepare_postamble(struct a6xx_gpu *a6xx_gpu)
> +{
> + u32 *postamble = a6xx_gpu->preempt_postamble_ptr;
> + u32 count = 0;
> +
> + postamble[count++] = PKT7(CP_REG_RMW, 3);
> + postamble[count++] = REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD;
> + postamble[count++] = 0;
> + postamble[count++] = 1;
> +
> + postamble[count++] = PKT7(CP_WAIT_REG_MEM, 6);
> + postamble[count++] = CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ);
> + postamble[count++] = CP_WAIT_REG_MEM_1_POLL_ADDR_LO(
> + REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS);
> + postamble[count++] = CP_WAIT_REG_MEM_2_POLL_ADDR_HI(0);
> + postamble[count++] = CP_WAIT_REG_MEM_3_REF(0x1);
> + postamble[count++] = CP_WAIT_REG_MEM_4_MASK(0x1);
> + postamble[count++] = CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0);
> +
> + a6xx_gpu->preempt_postamble_len = count;
> +
> + a6xx_gpu->postamble_enabled = true;
> +}
> +
> +static void preempt_disable_postamble(struct a6xx_gpu *a6xx_gpu)
> +{
> + u32 *postamble = a6xx_gpu->preempt_postamble_ptr;
> +
> + /*
> + * Disable the postamble by replacing the first packet header with a NOP
> + * that covers the whole buffer.
> + */
> + *postamble = PKT7(CP_NOP, (a6xx_gpu->preempt_postamble_len - 1));
> +
> + a6xx_gpu->postamble_enabled = false;
> +}
> +
> void a6xx_preempt_irq(struct msm_gpu *gpu)
> {
> uint32_t status;
> @@ -187,6 +224,7 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu)
> unsigned long flags;
> struct msm_ringbuffer *ring;
> unsigned int cntl;
> + bool sysprof;
>
> if (gpu->nr_rings == 1)
> return;
> @@ -272,6 +310,15 @@ void a6xx_preempt_trigger(struct msm_gpu *gpu)
> /* Start a timer to catch a stuck preemption */
> mod_timer(&a6xx_gpu->preempt_timer, jiffies + msecs_to_jiffies(10000));
>
> + /* Enable or disable postamble as needed */
> + sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1;
> +
> + if (!sysprof && !a6xx_gpu->postamble_enabled)
> + preempt_prepare_postamble(a6xx_gpu);
> +
> + if (sysprof && a6xx_gpu->postamble_enabled)
> + preempt_disable_postamble(a6xx_gpu);
> +
> /* Set the preemption state to triggered */
> set_preempt_state(a6xx_gpu, PREEMPT_TRIGGERED);
>
> @@ -359,6 +406,16 @@ void a6xx_preempt_init(struct msm_gpu *gpu)
> a6xx_gpu->uses_gmem = 1;
> a6xx_gpu->skip_save_restore = 1;
>
> + a6xx_gpu->preempt_postamble_ptr = msm_gem_kernel_new(gpu->dev,
> + PAGE_SIZE, MSM_BO_WC | MSM_BO_MAP_PRIV,
> + gpu->aspace, &a6xx_gpu->preempt_postamble_bo,
> + &a6xx_gpu->preempt_postamble_iova);
> +
> + preempt_prepare_postamble(a6xx_gpu);
> +
> + if (IS_ERR(a6xx_gpu->preempt_postamble_ptr))
> + goto fail;
> +
> timer_setup(&a6xx_gpu->preempt_timer, a6xx_preempt_timer, 0);
>
> return;
> diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> index 6b1888280a83..87098567483b 100644
> --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
> @@ -610,12 +610,15 @@ OUT_PKT4(struct msm_ringbuffer *ring, uint16_t regindx, uint16_t cnt)
> OUT_RING(ring, PKT4(regindx, cnt));
> }
>
> +#define PKT7(opcode, cnt) \
> + (CP_TYPE7_PKT | (cnt << 0) | (PM4_PARITY(cnt) << 15) | \
> + ((opcode & 0x7F) << 16) | (PM4_PARITY(opcode) << 23))
> +
> static inline void
> OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt)
> {
> adreno_wait_ring(ring, cnt + 1);
> - OUT_RING(ring, CP_TYPE7_PKT | (cnt << 0) | (PM4_PARITY(cnt) << 15) |
> - ((opcode & 0x7F) << 16) | (PM4_PARITY(opcode) << 23));
> + OUT_RING(ring, PKT7(opcode, cnt));
> }
>
> struct msm_gpu *a2xx_gpu_init(struct drm_device *dev);
>
> --
> 2.46.0
>
