From b75efe88b20c2be28b67e2821a794cc183e32374 Mon Sep 17 00:00:00 2001 From: Evan Quan Date: Thu, 4 May 2023 17:09:39 +0800 Subject: drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation An intentional delay is added on soft ctf triggered. Then there will be a double check for the GPU temperature before taking further action. This can avoid unintended shutdown due to temperature momentary fluctuation. Signed-off-by: Evan Quan Reviewed-by: Lijo Lazar Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'drivers/gpu/drm/amd/pm/swsmu/smu11') diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index e1ef88ee1ed3..aa4a5498a12f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1412,13 +1412,8 @@ static int smu_v11_0_irq_process(struct amdgpu_device *adev, if (client_id == SOC15_IH_CLIENTID_THM) { switch (src_id) { case THM_11_0__SRCID__THM_DIG_THERM_L2H: - dev_emerg(adev->dev, "ERROR: GPU over temperature range(SW CTF) detected!\n"); - /* - * SW CTF just occurred. - * Try to do a graceful shutdown to prevent further damage. - */ - dev_emerg(adev->dev, "ERROR: System is going to shutdown due to GPU SW CTF!\n"); - orderly_poweroff(true); + schedule_delayed_work(&smu->swctf_delayed_work, + msecs_to_jiffies(AMDGPU_SWCTF_EXTRA_DELAY)); break; case THM_11_0__SRCID__THM_DIG_THERM_H2L: dev_emerg(adev->dev, "ERROR: GPU under temperature range detected\n"); -- cgit