All of lore.kernel.org
 help / color / mirror / Atom feed
From: SRINIVASAN SHANMUGAM <srinivasan.shanmugam@amd.com>
To: "Marek Olšák" <maraeo@gmail.com>
Cc: "Christian König" <christian.koenig@amd.com>,
	"Alex Deucher" <alexander.deucher@amd.com>,
	amd-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/amdgpu/gfx10: Enable cleaner shader for GFX10.1.1/10.1.2 GPUs
Date: Fri, 24 Jan 2025 23:00:06 +0530	[thread overview]
Message-ID: <91fb8f7c-f252-40fa-85ca-e77c04a6fd31@amd.com> (raw)
In-Reply-To: <CAAxE2A4UjeVL1DBYer-Mgn8ufmcmSkBPU1JyZcW_5ghcHD-q3w@mail.gmail.com>

[-- Attachment #1: Type: text/plain, Size: 2094 bytes --]


On 1/24/2025 10:01 PM, Marek Olšák wrote:
> Does this commit really enable it though? Or is it just for sysfs?
>
Yes it enables cleaner shader support not only sysfs.

Best regards,
Srini

> Marek
>
> On Fri, Jan 24, 2025 at 1:42 AM Srinivasan Shanmugam 
> <srinivasan.shanmugam@amd.com> wrote:
>
>     Enable the cleaner shader for GFX10.1.1/10.1.2 GPUs to provide data
>     isolation between GPU workloads. The cleaner shader is responsible for
>     clearing the Local Data Store (LDS), Vector General Purpose Registers
>     (VGPRs), and Scalar General Purpose Registers (SGPRs), which helps
>     prevent data leakage and ensures accurate computation results.
>
>     This update extends cleaner shader support to GFX10.1.1/10.1.2 GPUs,
>     previously available for GFX10.1.10. It enhances security by clearing
>     GPU memory between processes and maintains a consistent GPU state
>     across
>     KGD and KFD workloads.
>
>     Cc: Christian König <christian.koenig@amd.com>
>     Cc: Alex Deucher <alexander.deucher@amd.com>
>     Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
>     ---
>      drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 2 ++
>      1 file changed, 2 insertions(+)
>
>     diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
>     b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
>     index 1878c83ff7e3..938f7d60a0ee 100644
>     --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
>     +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
>     @@ -4795,6 +4795,8 @@ static int gfx_v10_0_sw_init(struct
>     amdgpu_ip_block *ip_block)
>             }
>             switch (amdgpu_ip_version(adev, GC_HWIP, 0)) {
>             case IP_VERSION(10, 1, 10):
>     +       case IP_VERSION(10, 1, 1):
>     +       case IP_VERSION(10, 1, 2):
>                     adev->gfx.cleaner_shader_ptr =
>     gfx_10_1_10_cleaner_shader_hex;
>                     adev->gfx.cleaner_shader_size =
>     sizeof(gfx_10_1_10_cleaner_shader_hex);
>                     if (adev->gfx.me_fw_version >= 101 &&
>     -- 
>     2.34.1
>

[-- Attachment #2: Type: text/html, Size: 4110 bytes --]

  reply	other threads:[~2025-01-24 17:30 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-01-24  6:34 [PATCH] drm/amdgpu/gfx10: Enable cleaner shader for GFX10.1.1/10.1.2 GPUs Srinivasan Shanmugam
2025-01-24 15:25 ` Alex Deucher
2025-01-24 16:31 ` Marek Olšák
2025-01-24 17:30   ` SRINIVASAN SHANMUGAM [this message]
2025-01-24 17:39     ` Alex Deucher
2025-01-24 21:33       ` Marek Olšák
2025-01-24 21:41         ` Alex Deucher

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=91fb8f7c-f252-40fa-85ca-e77c04a6fd31@amd.com \
    --to=srinivasan.shanmugam@amd.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.com \
    --cc=maraeo@gmail.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.