From: Felix Kuehling <felix.kuehling@amd.com>
To: Philip Yang <Philip.Yang@amd.com>, amd-gfx@lists.freedesktop.org
Cc: harish.kasiviswanathan@amd.com, Xiaogang.Chen@amd.com
Subject: Re: [PATCH v2 2/3] drm/amdkfd: svm unmap use page aligned address
Date: Fri, 3 Oct 2025 16:27:04 -0400 [thread overview]
Message-ID: <2ac6c9db-ea01-4598-ba4b-e264d973633a@amd.com> (raw)
In-Reply-To: <20251003181518.24270-2-Philip.Yang@amd.com>
On 2025-10-03 14:15, Philip Yang wrote:
> svm_range_unmap_from_gpus uses page aligned start, end address, the end
> address is inclusive.
>
> Fixes: 38c55f6719f7 ("drm/amdkfd: Handle lack of READ permissions in SVM mapping")
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 7 +++----
> 1 file changed, 3 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index e8a15751c125..0aadd20be56a 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -1723,10 +1723,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
> svm_range_lock(prange);
> if (vma->vm_flags & VM_WRITE)
> pr_debug("VM_WRITE without VM_READ is not supported");
> - s = max(start, prange->start);
> - e = min(end, prange->last);
> - if (e >= s)
> - r = svm_range_unmap_from_gpus(prange, s, e,
> + s = max(addr >> PAGE_SHIFT, prange->start);
> + e = s + npages - 1;
This is confusing. The old code was clamping prange->start/last with
start/end. start/end are based on map_start/map_end. Your updated code
uses npages, which comes from the VMA, which may not start at the same
address as the prange or the map_start. So I think just using npages
here is incorrect.
You also completely removed the condition that s >= e. I think that's
OK, since all callers make sure that map_start/map_end fall inside
prange->start/last.
What are you actually trying to unmap here? Do you want to unmap the
entire prange, the part of prange inside map_start..map_end, or the part
of prange that overlaps with the VMA, or something else?
Regards,
Felix
> + r = svm_range_unmap_from_gpus(prange, s, e,
> KFD_SVM_UNMAP_TRIGGER_UNMAP_FROM_CPU);
> svm_range_unlock(prange);
> /* If unmap returns non-zero, we'll bail on the next for loop
next prev parent reply other threads:[~2025-10-03 20:27 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-03 18:15 [PATCH v2 1/3] drm/amdgpu: svm check hmm range kzalloc return NULL Philip Yang
2025-10-03 18:15 ` [PATCH v2 2/3] drm/amdkfd: svm unmap use page aligned address Philip Yang
2025-10-03 19:11 ` Chen, Xiaogang
2025-10-03 20:27 ` Felix Kuehling [this message]
2025-10-03 21:46 ` Philip Yang
2025-10-03 18:15 ` [PATCH v2 3/3] drm/amdkfd: Don't stuck in svm restore worker Philip Yang
2025-10-03 18:22 ` Chen, Xiaogang
2025-10-03 18:27 ` Philip Yang
2025-10-03 18:34 ` Chen, Xiaogang
2025-10-03 20:46 ` Felix Kuehling
2025-10-03 19:10 ` Chen, Xiaogang
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=2ac6c9db-ea01-4598-ba4b-e264d973633a@amd.com \
--to=felix.kuehling@amd.com \
--cc=Philip.Yang@amd.com \
--cc=Xiaogang.Chen@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=harish.kasiviswanathan@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox