From: "Christian König" <ckoenig.leichtzumerken-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: "Zhao, Yong" <Yong.Zhao-5C7GfCeVMHo@public.gmane.org>,
"amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org"
<amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org>
Subject: Re: [PATCH] drm/amdgpu: Add more page fault info printing for GFX10
Date: Mon, 12 Aug 2019 21:12:16 +0200 [thread overview]
Message-ID: <b8fd8285-12f8-373d-022f-e846dbb99efc@gmail.com> (raw)
In-Reply-To: <20190812190536.22744-1-Yong.Zhao-5C7GfCeVMHo@public.gmane.org>
Am 12.08.19 um 21:05 schrieb Zhao, Yong:
> The printing we did for GFX9 was not propogated to GFX10 somehow, so fix
> it now.
>
> Change-Id: Ic0b8381134340b83cd69c3fe186ac7a8a97b1bca
> Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 33 ++++++++++++++++++++++----
> drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 5 +++-
> 2 files changed, 32 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index 4e3ac1084a94..f23be98e9897 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -140,17 +140,40 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
> }
>
> if (printk_ratelimit()) {
> + struct amdgpu_task_info task_info;
> +
> + memset(&task_info, 0, sizeof(struct amdgpu_task_info));
> + amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
> +
> dev_err(adev->dev,
> - "[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
> + "[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u, "
> + "for process:%s pid:%d thread:%s pid:%d)\n",
> entry->vmid_src ? "mmhub" : "gfxhub",
> entry->src_id, entry->ring_id, entry->vmid,
> - entry->pasid);
> - dev_err(adev->dev, " at page 0x%016llx from %d\n",
> + entry->pasid, task_info.process_name, task_info.tgid,
> + task_info.task_name, task_info.pid);
> + dev_err(adev->dev, " in page starting at address 0x%016llx from client %d\n",
> addr, entry->client_id);
> - if (!amdgpu_sriov_vf(adev))
> + if (!amdgpu_sriov_vf(adev)) {
> dev_err(adev->dev,
> - "VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
> + "GCVM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
> status);
> + dev_err(adev->dev, "\t MORE_FAULTS: 0x%lx\n",
> + REG_GET_FIELD(status,
> + GCVM_L2_PROTECTION_FAULT_STATUS, MORE_FAULTS));
> + dev_err(adev->dev, "\t WALKER_ERROR: 0x%lx\n",
> + REG_GET_FIELD(status,
> + GCVM_L2_PROTECTION_FAULT_STATUS, WALKER_ERROR));
> + dev_err(adev->dev, "\t PERMISSION_FAULTS: 0x%lx\n",
> + REG_GET_FIELD(status,
> + GCVM_L2_PROTECTION_FAULT_STATUS, PERMISSION_FAULTS));
> + dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
> + REG_GET_FIELD(status,
> + GCVM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
> + dev_err(adev->dev, "\t RW: 0x%lx\n",
> + REG_GET_FIELD(status,
> + GCVM_L2_PROTECTION_FAULT_STATUS, RW));
> + }
> }
>
> return 0;
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 296e2d982578..34c4c2d08550 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -364,7 +364,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
>
> dev_err(adev->dev,
> "[%s] %s page fault (src_id:%u ring:%u vmid:%u "
> - "pasid:%u, for process %s pid %d thread %s pid %d)\n",
> + "pasid:%u, for process:%s pid:%d thread:%s pid:%d)\n",
I think the text actually looks better without the ":".
> hub_name, retry_fault ? "retry" : "no-retry",
> entry->src_id, entry->ring_id, entry->vmid,
> entry->pasid, task_info.process_name, task_info.tgid,
> @@ -387,6 +387,9 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
> dev_err(adev->dev, "\t MAPPING_ERROR: 0x%lx\n",
> REG_GET_FIELD(status,
> VM_L2_PROTECTION_FAULT_STATUS, MAPPING_ERROR));
> + dev_err(adev->dev, "\t RW: 0x%lx\n",
> + REG_GET_FIELD(status,
> + VM_L2_PROTECTION_FAULT_STATUS, RW));
That should probably be a separate patch since it is fixing gfx9.
Apart from that the patch looks good to me,
Christian.
>
> }
> }
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next prev parent reply other threads:[~2019-08-12 19:12 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-12 19:05 [PATCH] drm/amdgpu: Add more page fault info printing for GFX10 Zhao, Yong
[not found] ` <20190812190536.22744-1-Yong.Zhao-5C7GfCeVMHo@public.gmane.org>
2019-08-12 19:12 ` Christian König [this message]
[not found] ` <b8fd8285-12f8-373d-022f-e846dbb99efc-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2019-08-12 19:20 ` Zhao, Yong
[not found] ` <2da6884f-fcbf-e1ba-9150-28609dd16c2b-5C7GfCeVMHo@public.gmane.org>
2019-08-12 19:29 ` Christian König
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=b8fd8285-12f8-373d-022f-e846dbb99efc@gmail.com \
--to=ckoenig.leichtzumerken-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=Yong.Zhao-5C7GfCeVMHo@public.gmane.org \
--cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
--cc=christian.koenig-5C7GfCeVMHo@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