Merge tag 'x86-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Ingo Molnar:

 - Add comments about the magic behind the shadow STI
   before MWAIT in __sti_mwait().

 - Fix possible unintended timer delays caused by a race
   in mwait_idle_with_hints().

* tag 'x86-core-2024-01-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Fix CPUIDLE_FLAG_IRQ_ENABLE leaking timer reprogram
  x86: Add a comment about the "magic" behind shadow sti before mwait

2 files changed, 25 insertions, 14 deletions

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 778df05f85391..920426d691ce7 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -87,6 +87,15 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
 }
 
+/*
+ * Re-enable interrupts right upon calling mwait in such a way that
+ * no interrupt can fire _before_ the execution of mwait, ie: no
+ * instruction must be placed between "sti" and "mwait".
+ *
+ * This is necessary because if an interrupt queues a timer before
+ * executing mwait, it would otherwise go unnoticed and the next tick
+ * would not be reprogrammed accordingly before mwait ever wakes up.
+ */
 static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
 	mds_idle_clear_cpu_buffers();
@@ -115,8 +124,15 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
 		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
-		if (!need_resched())
-			__mwait(eax, ecx);
+
+		if (!need_resched()) {
+			if (ecx & 1) {
+				__mwait(eax, ecx);
+			} else {
+				__sti_mwait(eax, ecx);
+				raw_local_irq_disable();
+			}
+		}
 	}
 	current_clr_polling();
 }
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index dcda0afecfc5f..3e01a6b23e75f 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -131,11 +131,12 @@ static unsigned int mwait_substates __initdata;
 #define MWAIT2flg(eax) ((eax & 0xFF) << 24)
 
 static __always_inline int __intel_idle(struct cpuidle_device *dev,
-					struct cpuidle_driver *drv, int index)
+					struct cpuidle_driver *drv,
+					int index, bool irqoff)
 {
 	struct cpuidle_state *state = &drv->states[index];
 	unsigned long eax = flg2MWAIT(state->flags);
-	unsigned long ecx = 1; /* break on interrupt flag */
+	unsigned long ecx = 1*irqoff; /* break on interrupt flag */
 
 	mwait_idle_with_hints(eax, ecx);
 
@@ -159,19 +160,13 @@ static __always_inline int __intel_idle(struct cpuidle_device *dev,
 static __cpuidle int intel_idle(struct cpuidle_device *dev,
 				struct cpuidle_driver *drv, int index)
 {
-	return __intel_idle(dev, drv, index);
+	return __intel_idle(dev, drv, index, true);
 }
 
 static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
 				    struct cpuidle_driver *drv, int index)
 {
-	int ret;
-
-	raw_local_irq_enable();
-	ret = __intel_idle(dev, drv, index);
-	raw_local_irq_disable();
-
-	return ret;
+	return __intel_idle(dev, drv, index, false);
 }
 
 static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
@@ -184,7 +179,7 @@ static __cpuidle int intel_idle_ibrs(struct cpuidle_device *dev,
 	if (smt_active)
 		__update_spec_ctrl(0);
 
-	ret = __intel_idle(dev, drv, index);
+	ret = __intel_idle(dev, drv, index, true);
 
 	if (smt_active)
 		__update_spec_ctrl(spec_ctrl);
@@ -196,7 +191,7 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
 				       struct cpuidle_driver *drv, int index)
 {
 	fpu_idle_fpregs();
-	return __intel_idle(dev, drv, index);
+	return __intel_idle(dev, drv, index, true);
 }
 
 /**