From aff079bdce65f6d085e4b0091fdf87fffa95b0d9 Mon Sep 17 00:00:00 2001 From: Jakob Linke Date: Wed, 17 Jun 2026 08:24:15 +0200 Subject: drm/amdgpu/soc24: reset dGPU if suspend got aborted For SOC24 ASICs (RDNA4 / Navi 4x dGPUs) re-enabling PM features fails if an S3 suspend got aborted, the same issue already handled for SOC21 and SOC15: commit df3c7dc5c58b ("drm/amdgpu: Reset dGPU if suspend got aborted") commit 38e8ca3e4b6d ("amdgpu/soc15: enable asic reset for dGPU in case of suspend abort") The aborted resume fails with: amdgpu: SMU: No response msg_reg: 6 resp_reg: 0 amdgpu: Failed to enable requested dpm features! amdgpu: resume of IP block failed -62 Apply the same workaround for soc24: detect the aborted-suspend state at resume via the sign-of-life register and reset the device before re-init. This is a workaround till a proper solution is finalized. Fixes: 98b912c50e44 ("drm/amdgpu: Add soc24 common ip block (v2)") Signed-off-by: Jakob Linke Signed-off-by: Alex Deucher (cherry picked from commit fed5bdbfe1d4a19a26c70f7fc58017dc88be1c18) Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/soc24.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/soc24.c b/drivers/gpu/drm/amd/amdgpu/soc24.c index 265db9331d0b..9dce30d2bb8d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc24.c +++ b/drivers/gpu/drm/amd/amdgpu/soc24.c @@ -496,8 +496,36 @@ static int soc24_common_suspend(struct amdgpu_ip_block *ip_block) return soc24_common_hw_fini(ip_block); } +static bool soc24_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg1, sol_reg2; + + /* Will reset for the following suspend abort cases. + * 1) Only reset dGPU side. + * 2) S3 suspend got aborted and TOS is active. + * As for dGPU suspend abort cases the SOL value + * will be kept as zero at this resume point. + */ + if (!(adev->flags & AMD_IS_APU) && adev->in_s3) { + sol_reg1 = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_81); + msleep(100); + sol_reg2 = RREG32_SOC15(MP0, 0, regMPASP_SMN_C2PMSG_81); + + return (sol_reg1 != sol_reg2); + } + + return false; +} + static int soc24_common_resume(struct amdgpu_ip_block *ip_block) { + struct amdgpu_device *adev = ip_block->adev; + + if (soc24_need_reset_on_resume(adev)) { + dev_info(adev->dev, "S3 suspend aborted, resetting..."); + soc24_asic_reset(adev); + } + return soc24_common_hw_init(ip_block); } -- cgit v1.2.3