cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic

This allows moving the leave_mm() call into generic code before
rcu_idle_enter(). Gets rid of more trace_*_rcuidle() users.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Marco Elver <elver@google.com>
Link: https://lkml.kernel.org/r/20200821085348.369441600@infradead.org

6 files changed, 19 insertions, 33 deletions

diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 0a301ad0b02f..9257667d13c5 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -59,5 +59,6 @@ typedef struct {
 	}
 
 void leave_mm(int cpu);
+#define leave_mm leave_mm
 
 #endif /* _ASM_X86_MMU_H */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 1a3569b43aa5..0951b47e64c1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -555,21 +555,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 		load_new_mm_cr3(next->pgd, new_asid, true);
 
-		/*
-		 * NB: This gets called via leave_mm() in the idle path
-		 * where RCU functions differently.  Tracing normally
-		 * uses RCU, so we need to use the _rcuidle variant.
-		 *
-		 * (There is no good reason for this.  The idle code should
-		 *  be rearranged to call this before rcu_idle_enter().)
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	} else {
 		/* The new ASID is already up to date. */
 		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		/* See above wrt _rcuidle. */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
 	/* Make sure we write CR3 before loaded_mm. */
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 9bcda4153d3b..04becd70cc41 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/suspend.h>
 #include <linux/tick.h>
+#include <linux/mmu_context.h>
 #include <trace/events/power.h>
 
 #include "cpuidle.h"
@@ -228,6 +229,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		broadcast = false;
 	}
 
+	if (target_state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
+		leave_mm(dev->cpu);
+
 	/* Take note of the planned idle state. */
 	sched_idle_set_state(target_state);
 
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 8e0fb1a5bdbd..9a810e4a7946 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -90,14 +90,6 @@ static unsigned int mwait_substates __initdata;
 #define CPUIDLE_FLAG_ALWAYS_ENABLE	BIT(15)
 
 /*
- * Set this flag for states where the HW flushes the TLB for us
- * and so we don't need cross-calls to keep it consistent.
- * If this flag is set, SW flushes the TLB, so even if the
- * HW doesn't do the flushing, this flag is safe to use.
- */
-#define CPUIDLE_FLAG_TLB_FLUSHED	BIT(16)
-
-/*
  * MWAIT takes an 8-bit "hint" in EAX "suggesting"
  * the C-state (top nibble) and sub-state (bottom nibble)
  * 0x00 means "MWAIT(C1)", 0x10 means "MWAIT(C2)" etc.
@@ -131,14 +123,6 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	unsigned long eax = flg2MWAIT(state->flags);
 	unsigned long ecx = 1; /* break on interrupt flag */
 	bool tick;
-	int cpu = smp_processor_id();
-
-	/*
-	 * leave_mm() to avoid costly and often unnecessary wakeups
-	 * for flushing the user TLB's associated with the active mm.
-	 */
-	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
-		leave_mm(cpu);
 
 	if (!static_cpu_has(X86_FEATURE_ARAT)) {
 		/*
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index b65909ae4e20..75895e6363b8 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -75,12 +75,13 @@ struct cpuidle_state {
 };
 
 /* Idle State Flags */
-#define CPUIDLE_FLAG_NONE       (0x00)
-#define CPUIDLE_FLAG_POLLING	BIT(0) /* polling state */
-#define CPUIDLE_FLAG_COUPLED	BIT(1) /* state applies to multiple cpus */
-#define CPUIDLE_FLAG_TIMER_STOP BIT(2) /* timer is stopped on this state */
-#define CPUIDLE_FLAG_UNUSABLE	BIT(3) /* avoid using this state */
-#define CPUIDLE_FLAG_OFF	BIT(4) /* disable this state by default */
+#define CPUIDLE_FLAG_NONE       	(0x00)
+#define CPUIDLE_FLAG_POLLING		BIT(0) /* polling state */
+#define CPUIDLE_FLAG_COUPLED		BIT(1) /* state applies to multiple cpus */
+#define CPUIDLE_FLAG_TIMER_STOP 	BIT(2) /* timer is stopped on this state */
+#define CPUIDLE_FLAG_UNUSABLE		BIT(3) /* avoid using this state */
+#define CPUIDLE_FLAG_OFF		BIT(4) /* disable this state by default */
+#define CPUIDLE_FLAG_TLB_FLUSHED	BIT(5) /* idle-state flushes TLBs */
 
 struct cpuidle_device_kobj;
 struct cpuidle_state_kobj;
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index c51a84132d7c..03dee12d2b61 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -3,10 +3,15 @@
 #define _LINUX_MMU_CONTEXT_H
 
 #include <asm/mmu_context.h>
+#include <asm/mmu.h>
 
 /* Architectures that care about IRQ state in switch_mm can override this. */
 #ifndef switch_mm_irqs_off
 # define switch_mm_irqs_off switch_mm
 #endif
 
+#ifndef leave_mm
+static inline void leave_mm(int cpu) { }
+#endif
+
 #endif