All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paul Menzel <pmenzel@molgen.mpg.de>
To: Lang Yu <Lang.Yu@amd.com>
Cc: "Eric Huang" <jinhuieric.huang@amd.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	"Felix Kühling" <Felix.Kuehling@amd.com>,
	"Huang Rui" <ray.huang@amd.com>,
	amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdkfd: only allow heavy-weight TLB flush on some ASICs for SVM too
Date: Fri, 15 Apr 2022 07:14:05 +0200	[thread overview]
Message-ID: <aac8e868-3a1d-7eca-8c85-65d8972add40@molgen.mpg.de> (raw)
In-Reply-To: <Yljkf/yGk8YFEV9R@lang-desktop>

Dear Lang,


Am 15.04.22 um 05:20 schrieb Lang Yu:
> On 04/14/ , Paul Menzel wrote:

>> Am 14.04.22 um 10:19 schrieb Lang Yu:
>>> The idea is from commit a50fe7078035 ("drm/amdkfd: Only apply heavy-weight
>>> TLB flush on Aldebaran") and commit f61c40c0757a ("drm/amdkfd: enable
>>> heavy-weight TLB flush on Arcturus"). Otherwise, we will run into problems
>>> on some ASICs when running SVM applications.
>>
>> Please list the ASICs, you know of having problems, and even add how to
>> reproduce this.
> 
> Actually, this is ported from previous commits. You can find more details
> from the commits I mentioned. At the moment the ASICs except Aldebaran
> and Arcturus probably have the problem.

I think, it’s always good to make it as easy as possible for reviewers 
and, later, people reading a commit, and include the necessary 
information directly in the commit message. It’d be great if you amended 
the commit message.

> And running a SVM application could reproduce the issue.

Thanks. How will it fail though?

(Also, a small implementation note would be nice to have. Maybe: Move 
the helper function into the header `kfd_priv.h`, and use in 
`svm_range_unmap_from_gpus()`.)


Kind regards,

Paul


>>> Signed-off-by: Lang Yu <Lang.Yu@amd.com>
>>> ---
>>>    drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 8 --------
>>>    drivers/gpu/drm/amd/amdkfd/kfd_priv.h    | 8 ++++++++
>>>    drivers/gpu/drm/amd/amdkfd/kfd_svm.c     | 4 +++-
>>>    3 files changed, 11 insertions(+), 9 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> index 91f82a9ccdaf..459f59e3d0ed 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
>>> @@ -1128,14 +1128,6 @@ static int kfd_ioctl_free_memory_of_gpu(struct file *filep,
>>>    	return ret;
>>>    }
>>> -static bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
>>> -{
>>> -	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
>>> -		(KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) &&
>>> -		dev->adev->sdma.instance[0].fw_version >= 18) ||
>>> -		KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
>>> -}
>>> -
>>>    static int kfd_ioctl_map_memory_to_gpu(struct file *filep,
>>>    					struct kfd_process *p, void *data)
>>>    {
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> index 8a43def1f638..aff6f598ff2c 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>>> @@ -1328,6 +1328,14 @@ void kfd_signal_poison_consumed_event(struct kfd_dev *dev, u32 pasid);
>>>    void kfd_flush_tlb(struct kfd_process_device *pdd, enum TLB_FLUSH_TYPE type);
>>> +static inline bool kfd_flush_tlb_after_unmap(struct kfd_dev *dev)
>>> +{
>>> +	return KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 2) ||
>>> +	       (KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 1) &&
>>> +	       dev->adev->sdma.instance[0].fw_version >= 18) ||
>>> +	       KFD_GC_VERSION(dev) == IP_VERSION(9, 4, 0);
>>> +}
>>> +
>>>    bool kfd_is_locked(void);
>>>    /* Compute profile */
>>> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> index 459fa07a3bcc..5afe216cf099 100644
>>> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
>>> @@ -1229,7 +1229,9 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
>>>    			if (r)
>>>    				break;
>>>    		}
>>> -		kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
>>> +
>>> +		if (kfd_flush_tlb_after_unmap(pdd->dev))
>>> +			kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
>>>    	}
>>>    	return r;

  reply	other threads:[~2022-04-15  5:14 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-14  8:19 [PATCH] drm/amdkfd: only allow heavy-weight TLB flush on some ASICs for SVM too Lang Yu
2022-04-14 13:44 ` Eric Huang
2022-04-15  2:38   ` Lang Yu
2022-04-14 15:15 ` Felix Kuehling
2022-04-15  2:47   ` Lang Yu
2022-04-15  5:07     ` Felix Kuehling
2022-04-14 17:46 ` Paul Menzel
2022-04-15  3:20   ` Lang Yu
2022-04-15  5:14     ` Paul Menzel [this message]
2022-04-15  6:37       ` Lang Yu

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=aac8e868-3a1d-7eca-8c85-65d8972add40@molgen.mpg.de \
    --to=pmenzel@molgen.mpg.de \
    --cc=Felix.Kuehling@amd.com \
    --cc=Lang.Yu@amd.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=jinhuieric.huang@amd.com \
    --cc=ray.huang@amd.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.