linux-arm-msm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jordan Crouse <jordan@cosmicpenguin.net>
To: Rob Clark <robdclark@gmail.com>
Cc: dri-devel@lists.freedesktop.org,
	Rob Clark <robdclark@chromium.org>, Sean Paul <sean@poorly.run>,
	David Airlie <airlied@linux.ie>, Daniel Vetter <daniel@ffwll.ch>,
	Iskren Chernev <iskren.chernev@gmail.com>,
	Akhil P Oommen <akhilpo@codeaurora.org>,
	AngeloGioacchino Del Regno 
	<angelogioacchino.delregno@somainline.org>,
	Konrad Dybcio <konrad.dybcio@somainline.org>,
	"Kristian H. Kristensen" <hoegsberg@google.com>,
	Marijn Suijten <marijn.suijten@somainline.org>,
	Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>,
	Sharat Masetty <smasetty@codeaurora.org>,
	Jonathan Marek <jonathan@marek.ca>,
	Zhenzhong Duan <zhenzhong.duan@gmail.com>,
	Lee Jones <lee.jones@linaro.org>,
	"open list:DRM DRIVER FOR MSM ADRENO GPU" 
	<linux-arm-msm@vger.kernel.org>,
	"open list:DRM DRIVER FOR MSM ADRENO GPU" 
	<freedreno@lists.freedesktop.org>,
	open list <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v4 5/6] drm/msm: Add crashdump support for stalled SMMU
Date: Tue, 8 Jun 2021 09:12:47 -0600	[thread overview]
Message-ID: <20210608151247.u3uxznfoek7trxiv@cosmicpenguin.net> (raw)
In-Reply-To: <20210601224750.513996-7-robdclark@gmail.com>

On Tue, Jun 01, 2021 at 03:47:24PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark@chromium.org>
> 
> For collecting devcoredumps with the SMMU stalled after an iova fault,
> we need to skip the parts of the GPU state which are normally collected
> with the hw crashdumper, since with the SMMU stalled the hw would be
> unable to write out the requested state to memory.

On a5xx and a6xx you can query RBBM_STATUS3 bit 24 to see if the IOMMU is
stalled.  That could be an alternative option to adding the "stalled"
infrastructure across all targets.

Jordan
>
> Signed-off-by: Rob Clark <robdclark@chromium.org>
> ---
>  drivers/gpu/drm/msm/adreno/a2xx_gpu.c       |  2 +-
>  drivers/gpu/drm/msm/adreno/a3xx_gpu.c       |  2 +-
>  drivers/gpu/drm/msm/adreno/a4xx_gpu.c       |  2 +-
>  drivers/gpu/drm/msm/adreno/a5xx_gpu.c       |  5 ++-
>  drivers/gpu/drm/msm/adreno/a6xx_gpu.h       |  2 +-
>  drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 43 ++++++++++++++++-----
>  drivers/gpu/drm/msm/msm_debugfs.c           |  2 +-
>  drivers/gpu/drm/msm/msm_gpu.c               |  7 ++--
>  drivers/gpu/drm/msm/msm_gpu.h               |  2 +-
>  9 files changed, 47 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
> index bdc989183c64..d2c31fae64fd 100644
> --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c
> @@ -434,7 +434,7 @@ static void a2xx_dump(struct msm_gpu *gpu)
>  	adreno_dump(gpu);
>  }
>  
> -static struct msm_gpu_state *a2xx_gpu_state_get(struct msm_gpu *gpu)
> +static struct msm_gpu_state *a2xx_gpu_state_get(struct msm_gpu *gpu, bool stalled)
>  {
>  	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
>  
> diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
> index 4534633fe7cd..b1a6f87d74ef 100644
> --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
> @@ -464,7 +464,7 @@ static void a3xx_dump(struct msm_gpu *gpu)
>  	adreno_dump(gpu);
>  }
>  
> -static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
> +static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu, bool stalled)
>  {
>  	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
>  
> diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
> index 82bebb40234d..22780a594d6f 100644
> --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
> @@ -549,7 +549,7 @@ static const unsigned int a405_registers[] = {
>  	~0 /* sentinel */
>  };
>  
> -static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
> +static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu, bool stalled)
>  {
>  	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
>  
> diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> index a0eef5d9b89b..2e7714b1a17f 100644
> --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
> @@ -1519,7 +1519,7 @@ static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
>  	msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
>  }
>  
> -static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
> +static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu, bool stalled)
>  {
>  	struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state),
>  			GFP_KERNEL);
> @@ -1536,7 +1536,8 @@ static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
>  	a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
>  
>  	/* Get the HLSQ regs with the help of the crashdumper */
> -	a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
> +	if (!stalled)
> +		a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
>  
>  	a5xx_set_hwcg(gpu, true);
>  
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> index ce0610c5256f..e0f06ce4e1a9 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h
> @@ -86,7 +86,7 @@ unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu);
>  void a6xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
>  		struct drm_printer *p);
>  
> -struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu);
> +struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu, bool stalled);
>  int a6xx_gpu_state_put(struct msm_gpu_state *state);
>  
>  #endif /* __A6XX_GPU_H__ */
> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
> index c1699b4f9a89..d0af68a76c4f 100644
> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
> @@ -833,6 +833,21 @@ static void a6xx_get_registers(struct msm_gpu *gpu,
>  				a6xx_state, &a6xx_vbif_reglist,
>  				&a6xx_state->registers[index++]);
>  
> +	if (!dumper) {
> +		/*
> +		 * We can't use the crashdumper when the SMMU is stalled,
> +		 * because the GPU has no memory access until we resume
> +		 * translation (but we don't want to do that until after
> +		 * we have captured as much useful GPU state as possible).
> +		 * So instead collect registers via the CPU:
> +		 */
> +		for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++)
> +			a6xx_get_ahb_gpu_registers(gpu,
> +				a6xx_state, &a6xx_reglist[i],
> +				&a6xx_state->registers[index++]);
> +		return;
> +	}
> +
>  	for (i = 0; i < ARRAY_SIZE(a6xx_reglist); i++)
>  		a6xx_get_crashdumper_registers(gpu,
>  			a6xx_state, &a6xx_reglist[i],
> @@ -903,9 +918,9 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu,
>  	a6xx_state->nr_indexed_regs = count;
>  }
>  
> -struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
> +struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu, bool stalled)
>  {
> -	struct a6xx_crashdumper dumper = { 0 };
> +	struct a6xx_crashdumper _dumper = { 0 }, *dumper = NULL;
>  	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
>  	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
>  	struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state),
> @@ -928,14 +943,24 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
>  	/* Get the banks of indexed registers */
>  	a6xx_get_indexed_registers(gpu, a6xx_state);
>  
> -	/* Try to initialize the crashdumper */
> -	if (!a6xx_crashdumper_init(gpu, &dumper)) {
> -		a6xx_get_registers(gpu, a6xx_state, &dumper);
> -		a6xx_get_shaders(gpu, a6xx_state, &dumper);
> -		a6xx_get_clusters(gpu, a6xx_state, &dumper);
> -		a6xx_get_dbgahb_clusters(gpu, a6xx_state, &dumper);
> +	/*
> +	 * Try to initialize the crashdumper, if we are not dumping state
> +	 * with the SMMU stalled.  The crashdumper needs memory access to
> +	 * write out GPU state, so we need to skip this when the SMMU is
> +	 * stalled in response to an iova fault
> +	 */
> +	if (!stalled && !a6xx_crashdumper_init(gpu, &_dumper)) {
> +		dumper = &_dumper;
> +	}
> +
> +	a6xx_get_registers(gpu, a6xx_state, dumper);
> +
> +	if (dumper) {
> +		a6xx_get_shaders(gpu, a6xx_state, dumper);
> +		a6xx_get_clusters(gpu, a6xx_state, dumper);
> +		a6xx_get_dbgahb_clusters(gpu, a6xx_state, dumper);
>  
> -		msm_gem_kernel_put(dumper.bo, gpu->aspace, true);
> +		msm_gem_kernel_put(dumper->bo, gpu->aspace, true);
>  	}
>  
>  	if (snapshot_debugbus)
> diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
> index 7a2b53d35e6b..90558e826934 100644
> --- a/drivers/gpu/drm/msm/msm_debugfs.c
> +++ b/drivers/gpu/drm/msm/msm_debugfs.c
> @@ -77,7 +77,7 @@ static int msm_gpu_open(struct inode *inode, struct file *file)
>  		goto free_priv;
>  
>  	pm_runtime_get_sync(&gpu->pdev->dev);
> -	show_priv->state = gpu->funcs->gpu_state_get(gpu);
> +	show_priv->state = gpu->funcs->gpu_state_get(gpu, false);
>  	pm_runtime_put_sync(&gpu->pdev->dev);
>  
>  	mutex_unlock(&dev->struct_mutex);
> diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
> index fa7691cb4614..4d280bf446e6 100644
> --- a/drivers/gpu/drm/msm/msm_gpu.c
> +++ b/drivers/gpu/drm/msm/msm_gpu.c
> @@ -381,7 +381,8 @@ static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
>  }
>  
>  static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
> -		struct msm_gem_submit *submit, char *comm, char *cmd)
> +		struct msm_gem_submit *submit, char *comm, char *cmd,
> +		bool stalled)
>  {
>  	struct msm_gpu_state *state;
>  
> @@ -393,7 +394,7 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
>  	if (gpu->crashstate)
>  		return;
>  
> -	state = gpu->funcs->gpu_state_get(gpu);
> +	state = gpu->funcs->gpu_state_get(gpu, stalled);
>  	if (IS_ERR_OR_NULL(state))
>  		return;
>  
> @@ -519,7 +520,7 @@ static void recover_worker(struct kthread_work *work)
>  
>  	/* Record the crash state */
>  	pm_runtime_get_sync(&gpu->pdev->dev);
> -	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
> +	msm_gpu_crashstate_capture(gpu, submit, comm, cmd, false);
>  	pm_runtime_put_sync(&gpu->pdev->dev);
>  
>  	kfree(cmd);
> diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
> index 7a082a12d98f..c15e5fd675d2 100644
> --- a/drivers/gpu/drm/msm/msm_gpu.h
> +++ b/drivers/gpu/drm/msm/msm_gpu.h
> @@ -60,7 +60,7 @@ struct msm_gpu_funcs {
>  	void (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
>  #endif
>  	unsigned long (*gpu_busy)(struct msm_gpu *gpu);
> -	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
> +	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu, bool stalled);
>  	int (*gpu_state_put)(struct msm_gpu_state *state);
>  	unsigned long (*gpu_get_freq)(struct msm_gpu *gpu);
>  	void (*gpu_set_freq)(struct msm_gpu *gpu, struct dev_pm_opp *opp);
> -- 
> 2.31.1
> 

  reply	other threads:[~2021-06-08 15:13 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-01 22:47 [PATCH v4 0/6] iommu/arm-smmu: adreno-smmu page fault handling Rob Clark
2021-06-01 22:47 ` [PATCH] drm/msm/dpu: Delete bonkers code Rob Clark
2021-06-01 22:47 ` [PATCH v4 3/6] drm/msm: Improve the a6xx page fault handler Rob Clark
2021-06-01 22:47 ` [PATCH v4 5/6] drm/msm: Add crashdump support for stalled SMMU Rob Clark
2021-06-08 15:12   ` Jordan Crouse [this message]
2021-06-09 21:46     ` Rob Clark
2021-06-01 22:47 ` [PATCH v4 6/6] drm/msm: devcoredump iommu fault support Rob Clark
2021-06-08 15:20   ` Jordan Crouse
2021-06-09 21:50     ` Rob Clark

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210608151247.u3uxznfoek7trxiv@cosmicpenguin.net \
    --to=jordan@cosmicpenguin.net \
    --cc=airlied@linux.ie \
    --cc=akhilpo@codeaurora.org \
    --cc=angelogioacchino.delregno@somainline.org \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=freedreno@lists.freedesktop.org \
    --cc=hoegsberg@google.com \
    --cc=iskren.chernev@gmail.com \
    --cc=jonathan@marek.ca \
    --cc=konrad.dybcio@somainline.org \
    --cc=lee.jones@linaro.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marijn.suijten@somainline.org \
    --cc=robdclark@chromium.org \
    --cc=robdclark@gmail.com \
    --cc=saiprakash.ranjan@codeaurora.org \
    --cc=sean@poorly.run \
    --cc=smasetty@codeaurora.org \
    --cc=zhenzhong.duan@gmail.com \
    --subject='Re: [PATCH v4 5/6] drm/msm: Add crashdump support for stalled SMMU' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).