]> git.ipfire.org Git - thirdparty/kernel/stable.git/commitdiff
drm/xe/pm: Disable RPM for SR-IOV VFs
authorSatyanarayana K V P <satyanarayana.k.v.p@intel.com>
Tue, 12 Aug 2025 16:36:13 +0000 (22:06 +0530)
committerRodrigo Vivi <rodrigo.vivi@intel.com>
Sun, 17 Aug 2025 16:40:25 +0000 (12:40 -0400)
VFs without native PCIe Power Management (PM) capabilities inherit their
PF's power state as per PCIe specifications(§5.10.1 PCIe Base Spec 7.0).
Enabling Runtime Power Management (RPM) for these VFs trigger unnecessary
driver suspend/resume operations that ultimately perform no PCI-level power
transition.

Since VFs without PM capabilities cannot independently enter low-power
states, the existing RPM workflow becomes redundant:
1. Driver executes full suspend/resume sequence
2. PCI PM transition step becomes no-op
3. VF power state remains tied to PF's status

Disabling RPM for VFs eliminates this redundant processing while
maintaining proper power management through PF dependency. This
optimization ensures VFs follow their PF's power state without superfluous
runtime handling.

Signed-off-by: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Anshuman Gupta <anshuman.gupta@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Maarten Lankhorst <dev@lankhorst.se>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/20250812163613.9954-1-satyanarayana.k.v.p@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
drivers/gpu/drm/xe/xe_pm.c

index cc489c41ae30774d0f54a8ae3bf88ef9871b9af5..51ed7270994a3fd4f249a4637bbd3b180490642c 100644 (file)
@@ -247,6 +247,10 @@ static void xe_pm_runtime_init(struct xe_device *xe)
 {
        struct device *dev = xe->drm.dev;
 
+       /* Our current VFs do not support RPM. so, disable it */
+       if (IS_SRIOV_VF(xe))
+               return;
+
        /*
         * Disable the system suspend direct complete optimization.
         * We need to ensure that the regular device suspend/resume functions
@@ -371,6 +375,10 @@ static void xe_pm_runtime_fini(struct xe_device *xe)
 {
        struct device *dev = xe->drm.dev;
 
+       /* Our current VFs do not support RPM. so, disable it */
+       if (IS_SRIOV_VF(xe))
+               return;
+
        pm_runtime_get_sync(dev);
        pm_runtime_forbid(dev);
 }