[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240906200847.ajcrpikzl65fwbjz@hu-akhilpo-hyd.qualcomm.com>
Date: Sat, 7 Sep 2024 01:38:47 +0530
From: Akhil P Oommen <quic_akhilpo@...cinc.com>
To: Antonino Maniscalco <antomani103@...il.com>
CC: Rob Clark <robdclark@...il.com>, Sean Paul <sean@...rly.run>,
"Konrad
Dybcio" <konrad.dybcio@...aro.org>,
Abhinav Kumar
<quic_abhinavk@...cinc.com>,
Dmitry Baryshkov <dmitry.baryshkov@...aro.org>,
Marijn Suijten <marijn.suijten@...ainline.org>,
David Airlie
<airlied@...il.com>, "Daniel Vetter" <daniel@...ll.ch>,
Maarten Lankhorst
<maarten.lankhorst@...ux.intel.com>,
Maxime Ripard <mripard@...nel.org>,
Thomas Zimmermann <tzimmermann@...e.de>,
Jonathan Corbet <corbet@....net>, <linux-arm-msm@...r.kernel.org>,
<dri-devel@...ts.freedesktop.org>, <freedreno@...ts.freedesktop.org>,
<linux-kernel@...r.kernel.org>, <linux-doc@...r.kernel.org>
Subject: Re: [PATCH v3 06/10] drm/msm/A6xx: Use posamble to reset counters on
preemption
On Thu, Sep 05, 2024 at 04:51:24PM +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@...il.com>
> ---
> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 20 ++++++++++++++++++-
> drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 5 +++++
> drivers/gpu/drm/msm/adreno/a6xx_preempt.c | 32 +++++++++++++++++++++++++++++++
> drivers/gpu/drm/msm/adreno/adreno_gpu.h | 7 +++++--
> 4 files changed, 61 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> index ed0b138a2d66..710ec3ce2923 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
> @@ -366,7 +366,8 @@ 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_offset_priv_secure;
> + bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1;
> + u64 preempt_offset_priv_secure, preempt_postamble;
>
> OUT_PKT7(ring, CP_SET_PSEUDO_REG, 15);
>
> @@ -398,6 +399,23 @@ 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);
> +
> + /* if not profiling set postamble to clear perfcounters, else clear it */
> + if (!sysprof && a6xx_gpu->preempt_postamble_len) {
> + 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));
> + } else {
Why do we need this else part?
> + OUT_PKT7(ring, CP_SET_AMBLE, 3);
> + OUT_RING(ring, 0);
> + OUT_RING(ring, 0);
> + OUT_RING(ring, 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 da10060e38dc..b009732c08c5 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> @@ -71,6 +71,11 @@ 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;
> +
> 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 1caff76aca6e..ec44f44d925f 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c
> @@ -346,6 +346,28 @@ static int preempt_init_ring(struct a6xx_gpu *a6xx_gpu,
> return 0;
> }
>
> +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);
Isn't it better to just replace this with NOP packets when sysprof is
enabled, just before triggering preemption? It will help to have an
immediate effect.
-Akhil
> +
> + a6xx_gpu->preempt_postamble_len = count;
> +}
> +
> void a6xx_preempt_fini(struct msm_gpu *gpu)
> {
> struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
> @@ -376,6 +398,16 @@ 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
>
Powered by blists - more mailing lists