Normally resources are evicted on dGPUs at suspend or hibernate and on APUs at hibernate. These steps are unnecessary when using the S4 callbacks to put the system into S5. Cc: AceLan Kao <acelan.kao@xxxxxxxxxxxxx> Cc: Kai-Heng Feng <kaihengf@xxxxxxxxxx> Cc: Mark Pearson <mpearson-lenovo@xxxxxxxxx> Cc: Denis Benato <benato.denis96@xxxxxxxxx> Cc: Merthan Karakaş <m3rthn.k@xxxxxxxxx> Tested-by: Eric Naim <dnaim@xxxxxxxxxxx> Acked-by: Alex Deucher <alexander.deucher@xxxxxxx> Signed-off-by: Mario Limonciello (AMD) <superm1@xxxxxxxxxx> --- v5: * No changes v4: * Add A-b tag for Alex * https://lore.kernel.org/linux-pci/20250616175019.3471583-1-superm1@xxxxxxxxxx/ --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f9b4c4321f67c..4e4b7a63cc61e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5017,6 +5017,10 @@ static int amdgpu_device_evict_resources(struct amdgpu_device *adev) if (!adev->in_s4 && (adev->flags & AMD_IS_APU)) return 0; + /* No need to evict when going to S5 through S4 callbacks */ + if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF) + return 0; + ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM); if (ret) { dev_warn(adev->dev, "evicting device resources failed\n"); -- 2.43.0
