AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: "Liu, Shaoyun" <Shaoyun.Liu-5C7GfCeVMHo@public.gmane.org>
To: "Kuehling, Felix" <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>,
	"amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
	<amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Cc: "Yang, Philip" <Philip.Yang-5C7GfCeVMHo@public.gmane.org>
Subject: Re: [PATCH 1/1] drm/amdkfd: Consistently apply noretry setting
Date: Fri, 12 Jul 2019 19:48:15 +0000	[thread overview]
Message-ID: <49eac765-819f-3eaa-9f8c-30c77cd58c97@amd.com> (raw)
In-Reply-To: <20190622001959.32290-1-Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>

Reviewed-by : Shaoyun.liu < Shaoyun.liu@amd.com>

I manually applied the change and  verified on vega10 on visualization  
which we do have  retry vm fault issue . With  this patch , the no-retry 
interrupt delivered as expected and I don't see  the interrupt storm.

Regards

shaoyun.liu


On 2019-06-21 8:19 p.m., Felix Kuehling wrote:
> Apply the same setting to SH_MEM_CONFIG and VM_CONTEXT1_CNTL. This
> makes the noretry param no longer KFD-specific. On GFX10 I'm not
> changing SH_MEM_CONFIG in this commit because GFX10 has different
> retry behaviour in the SQ and I don't have a way to test it at the
> moment.
>
> Suggested-by: Christian König <Christian.Koenig@amd.com>
> CC: Philip Yang <Philip.Yang@amd.com>
> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h              |  1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c          | 16 +++++-----------
>   drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c            |  4 ++++
>   drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c         |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c         |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c          |  3 ++-
>   drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c          |  3 ++-
>   .../drm/amd/amdkfd/kfd_device_queue_manager_v9.c |  2 +-
>   drivers/gpu/drm/amd/amdkfd/kfd_priv.h            |  2 +-
>   9 files changed, 20 insertions(+), 17 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 9b1efdf94bdf..05875279c09e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -164,6 +164,7 @@ extern int amdgpu_async_gfx_ring;
>   extern int amdgpu_mcbp;
>   extern int amdgpu_discovery;
>   extern int amdgpu_mes;
> +extern int amdgpu_noretry;
>   
>   #ifdef CONFIG_DRM_AMDGPU_SI
>   extern int amdgpu_si_support;
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 7cf6ab07b113..0d578d95be93 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -140,6 +140,7 @@ int amdgpu_async_gfx_ring = 1;
>   int amdgpu_mcbp = 0;
>   int amdgpu_discovery = 0;
>   int amdgpu_mes = 0;
> +int amdgpu_noretry;
>   
>   struct amdgpu_mgpu_info mgpu_info = {
>   	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
> @@ -591,6 +592,10 @@ MODULE_PARM_DESC(mes,
>   	"Enable Micro Engine Scheduler (0 = disabled (default), 1 = enabled)");
>   module_param_named(mes, amdgpu_mes, int, 0444);
>   
> +MODULE_PARM_DESC(noretry,
> +	"Disable retry faults (0 = retry enabled (default), 1 = retry disabled)");
> +module_param_named(noretry, amdgpu_noretry, int, 0644);
> +
>   #ifdef CONFIG_HSA_AMD
>   /**
>    * DOC: sched_policy (int)
> @@ -666,17 +671,6 @@ module_param(ignore_crat, int, 0444);
>   MODULE_PARM_DESC(ignore_crat,
>   	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
>   
> -/**
> - * DOC: noretry (int)
> - * This parameter sets sh_mem_config.retry_disable. Default value, 0, enables retry.
> - * Setting 1 disables retry.
> - * Retry is needed for recoverable page faults.
> - */
> -int noretry;
> -module_param(noretry, int, 0644);
> -MODULE_PARM_DESC(noretry,
> -	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
> -
>   /**
>    * DOC: halt_if_hws_hang (int)
>    * Halt if HWS hang is detected. Default value, 0, disables the halt on hang.
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> index e0f3014e76ea..c4e715170bfe 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
> @@ -1938,11 +1938,15 @@ static void gfx_v9_0_constants_init(struct amdgpu_device *adev)
>   		if (i == 0) {
>   			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
>   					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
> +			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
> +					    !!amdgpu_noretry);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_BASES, 0);
>   		} else {
>   			tmp = REG_SET_FIELD(0, SH_MEM_CONFIG, ALIGNMENT_MODE,
>   					    SH_MEM_ALIGNMENT_MODE_UNALIGNED);
> +			tmp = REG_SET_FIELD(tmp, SH_MEM_CONFIG, RETRY_DISABLE,
> +					    !!amdgpu_noretry);
>   			WREG32_SOC15_RLC(GC, 0, mmSH_MEM_CONFIG, tmp);
>   			tmp = REG_SET_FIELD(0, SH_MEM_BASES, PRIVATE_BASE,
>   				(adev->gmc.private_aperture_start >> 48));
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> index 9f0f189fc111..15986748f59f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
> @@ -236,7 +236,8 @@ static void gfxhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
>   				    block_size);
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
> -				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 1);
> +				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> +				    !amdgpu_noretry);
>   		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_CNTL, i, tmp);
>   		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0);
>   		WREG32_SOC15_OFFSET(GC, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0);
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> index b7de60a15623..d605b4963f8a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
> @@ -215,7 +215,8 @@ static void gfxhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
>   				adev->vm_manager.block_size - 9);
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT1_CNTL,
> -				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
> +				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> +				    !amdgpu_noretry);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_CNTL, i, tmp);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0);
>   		WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0);
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> index 05d1d448c8f5..dc5ce03034d3 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
> @@ -265,7 +265,8 @@ static void mmhub_v1_0_setup_vmid_config(struct amdgpu_device *adev)
>   				    block_size);
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, VM_CONTEXT1_CNTL,
> -				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 1);
> +				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> +				    !amdgpu_noretry);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_CNTL, i, tmp);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0);
> diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> index 37a1a318ae63..0f9549f19ade 100644
> --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
> @@ -205,7 +205,8 @@ static void mmhub_v2_0_setup_vmid_config(struct amdgpu_device *adev)
>   				    adev->vm_manager.block_size - 9);
>   		/* Send no-retry XNACK on fault to suppress VM fault storm. */
>   		tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT1_CNTL,
> -				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
> +				    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT,
> +				    !amdgpu_noretry);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_CNTL, i, tmp);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_LO32, i*2, 0);
>   		WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT1_PAGE_TABLE_START_ADDR_HI32, i*2, 0);
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> index e9fe39382371..95a82ac455f2 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
> @@ -61,7 +61,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
>   		qpd->sh_mem_config =
>   				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
>   					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
> -		if (noretry &&
> +		if (amdgpu_noretry &&
>   		    !dqm->dev->device_info->needs_iommu_device)
>   			qpd->sh_mem_config |=
>   				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> index d4bba0124d29..aa7bf20d20f8 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
> @@ -157,7 +157,7 @@ extern int ignore_crat;
>   /*
>    * Set sh_mem_config.retry_disable on Vega10
>    */
> -extern int noretry;
> +extern int amdgpu_noretry;
>   
>   /*
>    * Halt if HWS hang is detected
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

      parent reply	other threads:[~2019-07-12 19:48 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-22  0:20 [PATCH 1/1] drm/amdkfd: Consistently apply noretry setting Kuehling, Felix
     [not found] ` <20190622001959.32290-1-Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
2019-07-02 19:05   ` Kuehling, Felix
     [not found]     ` <953e3a92-2d3b-0275-2a05-253570ab6277-5C7GfCeVMHo@public.gmane.org>
2019-07-03 22:19       ` Yang, Philip
     [not found]         ` <5edef671-8986-e513-f03b-15066b8ab0d6-5C7GfCeVMHo@public.gmane.org>
2019-07-04  7:14           ` Koenig, Christian
2019-07-04 16:02           ` Kuehling, Felix
     [not found]             ` <00e7be6b-4869-ad60-9dc2-88d0ecaf1fc0-5C7GfCeVMHo@public.gmane.org>
2019-07-04 17:16               ` Yang, Philip
     [not found]                 ` <3bf9cf4c-456c-cb22-7b2a-edd5433cae47-5C7GfCeVMHo@public.gmane.org>
2019-07-04 18:00                   ` Kuehling, Felix
2019-07-12 19:48   ` Liu, Shaoyun [this message]

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=49eac765-819f-3eaa-9f8c-30c77cd58c97@amd.com \
    --to=shaoyun.liu-5c7gfcevmho@public.gmane.org \
    --cc=Felix.Kuehling-5C7GfCeVMHo@public.gmane.org \
    --cc=Philip.Yang-5C7GfCeVMHo@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox