From: Alex Deucher <alexander.deucher@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: Alex Deucher <alexander.deucher@amd.com>,
Horace Chen <horace.chen@amd.com>,
Hawking Zhang <Hawking.Zhang@amd.com>
Subject: [PATCH 03/19] drm/amdgpu: add a compute pipe reset for RS64
Date: Tue, 30 Aug 2022 14:39:56 -0400 [thread overview]
Message-ID: <20220830184012.1825313-3-alexander.deucher@amd.com> (raw)
In-Reply-To: <20220830184012.1825313-1-alexander.deucher@amd.com>
From: Horace Chen <horace.chen@amd.com>
[Why]
Under SR-IOV, we are not sure whether pipe status is
good or not when doing initialization. The compute engine
maybe fail to bringup if pipe status is bad.
[How]
Do an RS64 pipe reset for MEC before we do initialization.
Also apply to bare-metal.
Signed-off-by: Horace Chen <horace.chen@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index f2d126b110e8..fa718318568e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -2725,6 +2725,21 @@ static void gfx_v11_0_config_gfx_rs64(struct amdgpu_device *adev)
mec_hdr->ucode_start_addr_hi >> 2);
}
soc21_grbm_select(adev, 0, 0, 0, 0);
+
+ /* reset mec pipe */
+ tmp = RREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE0_RESET, 1);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE1_RESET, 1);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE2_RESET, 1);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE3_RESET, 1);
+ WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, tmp);
+
+ /* clear mec pipe reset */
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE0_RESET, 0);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE1_RESET, 0);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE2_RESET, 0);
+ tmp = REG_SET_FIELD(tmp, CP_MEC_RS64_CNTL, MEC_PIPE3_RESET, 0);
+ WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, tmp);
}
static int gfx_v11_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev)
--
2.37.1
next prev parent reply other threads:[~2022-08-30 18:41 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-08-30 18:39 [PATCH 01/19] drm/amdgpu: add CHIP_IP_DISCOVERY support for virtualization Alex Deucher
2022-08-30 18:39 ` [PATCH 02/19] drm/amdgpu: add sriov nbio callback structure Alex Deucher
2022-08-30 18:39 ` Alex Deucher [this message]
2022-08-30 18:39 ` [PATCH 04/19] drm/amdgpu: enable WPTR_POLL_ENABLE for sriov on sdma_v6_0 Alex Deucher
2022-08-30 18:39 ` [PATCH 05/19] drm/amdgpu: refine virtualization psp fw skip check Alex Deucher
2022-08-30 18:39 ` [PATCH 06/19] drm/amdgpu: sriov remove vcn_4_0 and jpeg_4_0 Alex Deucher
2022-08-30 18:40 ` [PATCH 07/19] drm/amdgpu: Support PSP 13.0.10 on SR-IOV Alex Deucher
2022-08-30 18:40 ` [PATCH 08/19] drm/amdgpu: Use PSP program IH_RB_CNTL registers under SRIOV Alex Deucher
2022-08-30 18:40 ` [PATCH 09/19] drm/amdgpu: Skip the program of MMMC_VM_AGP_* in SRIOV on MMHUB v3_0_0 Alex Deucher
2022-08-30 18:40 ` [PATCH 10/19] drm/amdgpu: skip "Issue additional private vm invalidation to MMHUB" on SRIOV Alex Deucher
2022-08-30 18:40 ` [PATCH 11/19] drm/amdgpu: Skip the VRAM base offset " Alex Deucher
2022-08-30 18:40 ` [PATCH 12/19] drm/amdgpu: Skip program SDMA0_SEM_WAIT_FAIL_TIMER_CNTL under SRIOV VF Alex Deucher
2022-08-30 18:40 ` [PATCH 13/19] drm/amdgpu: Use RLCG to program GRBM_GFX_CNTL during full access time Alex Deucher
2022-08-30 18:40 ` [PATCH 14/19] drm/admgpu: Skip CG/PG on SOC21 under SRIOV VF Alex Deucher
2022-08-30 18:40 ` [PATCH 15/19] drm/amd: Skip smu_v13 register irq on " Alex Deucher
2022-08-30 18:40 ` [PATCH 16/19] drm/amdgpu/vcn: Disable CG/PG for SRIOV Alex Deucher
2022-08-30 18:40 ` [PATCH 17/19] drm/amdgpu/vcn: Add vcn/vcn1 in white list to load its firmware under sriov Alex Deucher
2022-08-30 18:40 ` [PATCH 18/19] drm/amdgpu/vcn: Add sriov VCN v4_0 unified queue support Alex Deucher
2022-08-30 18:40 ` [PATCH 19/19] drm/amdgpu/vcn: Add MMSCH v4_0 support for sriov Alex Deucher
2022-08-31 8:05 ` [PATCH 01/19] drm/amdgpu: add CHIP_IP_DISCOVERY support for virtualization 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=20220830184012.1825313-3-alexander.deucher@amd.com \
--to=alexander.deucher@amd.com \
--cc=Hawking.Zhang@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=horace.chen@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