From: "Sundararaju, Sathishkumar" <sasundar@amd.com>
To: Lijo Lazar <lijo.lazar@amd.com>, amd-gfx@lists.freedesktop.org
Cc: Hawking.Zhang@amd.com, Alexander.Deucher@amd.com,
leo.liu@amd.com, jane.jian@amd.com,
sathishkumar.sundararaju@amd.com
Subject: Re: [PATCH v2] drm/amdgpu: Normalize reg offsets on JPEG v4.0.3
Date: Wed, 28 Aug 2024 19:07:05 +0530 [thread overview]
Message-ID: <6c60f44d-dc8f-4c70-a4ff-1d0d0517fc24@amd.com> (raw)
In-Reply-To: <20240828061133.1880057-1-lijo.lazar@amd.com>
On 8/28/2024 11:41 AM, Lijo Lazar wrote:
> On VFs and SOCs with GC 9.4.4, VCN RRMT is disabled.
> Only local register offsets should be used on JPEG v4.0.3 as they cannot
> handle remote access to other AIDs. Since only local offsets are used,
> the special write to MCM_ADDR register is no longer needed.
>
> Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
please move sign-off below v2 commit description and with that
Reviewed-by: Sathishkumar S <sathishkumar.sundararaju@amd.com>
Thanks,
Sathish
> ---
> v2: Restrict the change to GC 9.4.4 on PFs.
>
> drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 36 ++++++++++--------------
> 1 file changed, 15 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
> index 6ae5a784e187..a4ebceaaa09c 100644
> --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
> +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
> @@ -59,6 +59,12 @@ static int amdgpu_ih_srcid_jpeg[] = {
> VCN_4_0__SRCID__JPEG7_DECODE
> };
>
> +static inline bool jpeg_v4_0_3_normalizn_reqd(struct amdgpu_device *adev)
> +{
> + return amdgpu_sriov_vf(adev) ||
> + (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 4));
> +}
> +
> /**
> * jpeg_v4_0_3_early_init - set function pointers
> *
> @@ -734,32 +740,20 @@ void jpeg_v4_0_3_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
> 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
> amdgpu_ring_write(ring, 0);
>
> - if (ring->adev->jpeg.inst[ring->me].aid_id) {
> - amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_MCM_ADDR_INTERNAL_OFFSET,
> - 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE0));
> - amdgpu_ring_write(ring, 0x4);
> - } else {
> - amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
> - amdgpu_ring_write(ring, 0);
> - }
> + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
> + amdgpu_ring_write(ring, 0);
>
> amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
> 0, 0, PACKETJ_TYPE0));
> amdgpu_ring_write(ring, 0x3fbc);
>
> - if (ring->adev->jpeg.inst[ring->me].aid_id) {
> - amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_EXTERNAL_MCM_ADDR_INTERNAL_OFFSET,
> - 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE0));
> - amdgpu_ring_write(ring, 0x0);
> - } else {
> - amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
> - amdgpu_ring_write(ring, 0);
> - }
> -
> amdgpu_ring_write(ring, PACKETJ(JRBC_DEC_EXTERNAL_REG_WRITE_ADDR,
> 0, 0, PACKETJ_TYPE0));
> amdgpu_ring_write(ring, 0x1);
>
> + amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
> + amdgpu_ring_write(ring, 0);
> +
> amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
> amdgpu_ring_write(ring, 0);
> }
> @@ -834,8 +828,8 @@ void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
> {
> uint32_t reg_offset;
>
> - /* For VF, only local offsets should be used */
> - if (amdgpu_sriov_vf(ring->adev))
> + /* Use normalized offsets if required */
> + if (jpeg_v4_0_3_normalizn_reqd(ring->adev))
> reg = NORMALIZE_JPEG_REG_OFFSET(reg);
>
> reg_offset = (reg << 2);
> @@ -881,8 +875,8 @@ void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint
> {
> uint32_t reg_offset;
>
> - /* For VF, only local offsets should be used */
> - if (amdgpu_sriov_vf(ring->adev))
> + /* Use normalized offsets if required */
> + if (jpeg_v4_0_3_normalizn_reqd(ring->adev))
> reg = NORMALIZE_JPEG_REG_OFFSET(reg);
>
> reg_offset = (reg << 2);
prev parent reply other threads:[~2024-08-28 13:37 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-08-28 6:11 [PATCH v2] drm/amdgpu: Normalize reg offsets on JPEG v4.0.3 Lijo Lazar
2024-08-28 13:37 ` Sundararaju, Sathishkumar [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=6c60f44d-dc8f-4c70-a4ff-1d0d0517fc24@amd.com \
--to=sasundar@amd.com \
--cc=Alexander.Deucher@amd.com \
--cc=Hawking.Zhang@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=jane.jian@amd.com \
--cc=leo.liu@amd.com \
--cc=lijo.lazar@amd.com \
--cc=sathishkumar.sundararaju@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