releases/6.8.7/drm-amdgpu-reset-dgpu-if-suspend-got-aborted.patch

From 8b2be55f4d6c1099d7f629b0ed7535a5be788c83 Mon Sep 17 00:00:00 2001
From: Lijo Lazar <lijo.lazar@amd.com>
Date: Wed, 14 Feb 2024 17:55:54 +0530
Subject: drm/amdgpu: Reset dGPU if suspend got aborted

From: Lijo Lazar <lijo.lazar@amd.com>

commit 8b2be55f4d6c1099d7f629b0ed7535a5be788c83 upstream.

For SOC21 ASICs, there is an issue in re-enabling PM features if a
suspend got aborted. In such cases, reset the device during resume
phase. This is a workaround till a proper solution is finalized.

Signed-off-by: Lijo Lazar <lijo.lazar@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/gpu/drm/amd/amdgpu/soc21.c |   25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -832,10 +832,35 @@ static int soc21_common_suspend(void *ha
 	return soc21_common_hw_fini(adev);
 }
 
+static bool soc21_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.
+	 */
+	if (!(adev->flags & AMD_IS_APU) && adev->in_s3 &&
+	    !adev->suspend_complete) {
+		sol_reg1 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+		msleep(100);
+		sol_reg2 = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_81);
+
+		return (sol_reg1 != sol_reg2);
+	}
+
+	return false;
+}
+
 static int soc21_common_resume(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	if (soc21_need_reset_on_resume(adev)) {
+		dev_info(adev->dev, "S3 suspend aborted, resetting...");
+		soc21_asic_reset(adev);
+	}
+
 	return soc21_common_hw_init(adev);
 }