[PATCH] drm/amdgpu: support new mode-1 reset interface

Tao Zhou tao.zhou1 at amd.com
Tue Nov 16 07:23:37 UTC 2021


If gpu reset is triggered by ras fatal error, tell it to smu in mode-1
reset message.

Signed-off-by: Tao Zhou <tao.zhou1 at amd.com>
---
 .../gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c    | 21 ++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index 35145db6eedf..6f3d064a8232 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1426,16 +1426,31 @@ int smu_v13_0_set_azalia_d3_pme(struct smu_context *smu)
 
 int smu_v13_0_mode1_reset(struct smu_context *smu)
 {
-	u32 smu_version;
+	u32 smu_version, fatal_err, param;
 	int ret = 0;
+	struct amdgpu_device *adev = smu->adev;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
+	fatal_err = 0;
+	param = SMU_RESET_MODE_1;
+
 	/*
 	* PM FW support SMU_MSG_GfxDeviceDriverReset from 68.07
 	*/
 	smu_cmn_get_smc_version(smu, NULL, &smu_version);
 	if (smu_version < 0x00440700)
 		ret = smu_cmn_send_smc_msg(smu, SMU_MSG_Mode1Reset, NULL);
-	else
-		ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, SMU_RESET_MODE_1, NULL);
+	else {
+		/* fatal error triggered by ras, PMFW supports the flag
+		   from 68.44.0 */
+		if ((smu_version >= 0x00442c00) && ras &&
+		    atomic_read(&ras->in_recovery))
+			fatal_err = 1;
+
+		param |= (fatal_err << 16);
+		ret = smu_cmn_send_smc_msg_with_param(smu,
+					SMU_MSG_GfxDeviceDriverReset, param, NULL);
+	}
 
 	if (!ret)
 		msleep(SMU13_MODE1_RESET_WAIT_TIME_IN_MS);
-- 
2.17.1



More information about the amd-gfx mailing list