Merge back cpuidle material for 5.20.

drivers/cpuidle/governors/haltpoll.c

@@ -19,6 +19,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/kvm_para.h>
+#include <trace/events/power.h>
 
 static unsigned int guest_halt_poll_ns __read_mostly = 200000;
 module_param(guest_halt_poll_ns, uint, 0644);
@@ -90,6 +91,7 @@ static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns)
 		if (val > guest_halt_poll_ns)
 			val = guest_halt_poll_ns;
 
+		trace_guest_halt_poll_ns_grow(val, dev->poll_limit_ns);
 		dev->poll_limit_ns = val;
 	} else if (block_ns > guest_halt_poll_ns &&
 		   guest_halt_poll_allow_shrink) {
@@ -100,6 +102,7 @@ static void adjust_poll_limit(struct cpuidle_device *dev, u64 block_ns)
 			val = 0;
 		else
 			val /= shrink;
+		trace_guest_halt_poll_ns_shrink(val, dev->poll_limit_ns);
 		dev->poll_limit_ns = val;
 	}
 }

drivers/idle/intel_idle.c

@@ -911,16 +911,6 @@ static struct cpuidle_state adl_l_cstates[] __initdata = {
 		.enter = NULL }
 };
 
-/*
- * On Sapphire Rapids Xeon C1 has to be disabled if C1E is enabled, and vice
- * versa. On SPR C1E is enabled only if "C1E promotion" bit is set in
- * MSR_IA32_POWER_CTL. But in this case there effectively no C1, because C1
- * requests are promoted to C1E. If the "C1E promotion" bit is cleared, then
- * both C1 and C1E requests end up with C1, so there is effectively no C1E.
- *
- * By default we enable C1 and disable C1E by marking it with
- * 'CPUIDLE_FLAG_UNUSABLE'.
- */
 static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C1",
@@ -933,8 +923,7 @@ static struct cpuidle_state spr_cstates[] __initdata = {
 	{
 		.name = "C1E",
 		.desc = "MWAIT 0x01",
-		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE |
-					   CPUIDLE_FLAG_UNUSABLE,
+		.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_ALWAYS_ENABLE,
 		.exit_latency = 2,
 		.target_residency = 4,
 		.enter = &intel_idle,
@@ -1756,17 +1745,6 @@ static void __init spr_idle_state_table_update(void)
 {
 	unsigned long long msr;
 
-	/* Check if user prefers C1E over C1. */
-	if ((preferred_states_mask & BIT(2)) &&
-	    !(preferred_states_mask & BIT(1))) {
-		/* Disable C1 and enable C1E. */
-		spr_cstates[0].flags |= CPUIDLE_FLAG_UNUSABLE;
-		spr_cstates[1].flags &= ~CPUIDLE_FLAG_UNUSABLE;
-
-		/* Enable C1E using the "C1E promotion" bit. */
-		c1e_promotion = C1E_PROMOTION_ENABLE;
-	}
-
 	/*
 	 * By default, the C6 state assumes the worst-case scenario of package
 	 * C6. However, if PC6 is disabled, we update the numbers to match

include/trace/events/power.h

@@ -500,6 +500,35 @@ DEFINE_EVENT(dev_pm_qos_request, dev_pm_qos_remove_request,
 
 	TP_ARGS(name, type, new_value)
 );
+
+TRACE_EVENT(guest_halt_poll_ns,
+
+	TP_PROTO(bool grow, unsigned int new, unsigned int old),
+
+	TP_ARGS(grow, new, old),
+
+	TP_STRUCT__entry(
+		__field(bool, grow)
+		__field(unsigned int, new)
+		__field(unsigned int, old)
+	),
+
+	TP_fast_assign(
+		__entry->grow   = grow;
+		__entry->new    = new;
+		__entry->old    = old;
+	),
+
+	TP_printk("halt_poll_ns %u (%s %u)",
+		__entry->new,
+		__entry->grow ? "grow" : "shrink",
+		__entry->old)
+);
+
+#define trace_guest_halt_poll_ns_grow(new, old) \
+	trace_guest_halt_poll_ns(true, new, old)
+#define trace_guest_halt_poll_ns_shrink(new, old) \
+	trace_guest_halt_poll_ns(false, new, old)
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */