diff --git a/arch/ia64/include/asm/acpi.h b/arch/ia64/include/asm/acpi.h
index c86a947f5368633b86d1a8e5dc7ddd1803982c64..a3d0211970e95e5152edbaeeecd8ab3a42041ac6 100644
--- a/arch/ia64/include/asm/acpi.h
+++ b/arch/ia64/include/asm/acpi.h
@@ -112,6 +112,8 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
 	buf[2] |= ACPI_PDC_EST_CAPABILITY_SMP;
 }
 
+#define acpi_unlazy_tlb(x)
+
 #ifdef CONFIG_ACPI_NUMA
 extern cpumask_t early_cpu_possible_map;
 #define for_each_possible_early_cpu(cpu)  \
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 72d867f6b518e4db5a79a10c924f858a3edb0af8..8d0ec9df1cbeb53894f47454cd1391b297e6086c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -150,6 +150,8 @@ static inline void disable_acpi(void) { }
 extern int x86_acpi_numa_init(void);
 #endif /* CONFIG_ACPI_NUMA */
 
+#define acpi_unlazy_tlb(x)	leave_mm(x)
+
 #ifdef CONFIG_ACPI_APEI
 static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 {
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0f3d0cea4d00ca253ee5b46ed78158d460797a56..3118392cdf756bfc913d7a4137d5f7e0d46b046d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -85,6 +85,7 @@ void leave_mm(int cpu)
 
 	switch_mm(NULL, &init_mm, NULL);
 }
+EXPORT_SYMBOL_GPL(leave_mm);
 
 void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	       struct task_struct *tsk)
@@ -195,12 +196,22 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
 			write_cr3(build_cr3(next, new_asid));
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
-					TLB_FLUSH_ALL);
+
+			/*
+			 * 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);
 		} else {
 			/* The new ASID is already up to date. */
 			write_cr3(build_cr3_noflush(next, new_asid));
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
+
+			/* See above wrt _rcuidle. */
+			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 		}
 
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 2736e25e9dc6458d736383ed0bc60761e7eb4a5f..d50a7b6ccddd99785dc7c6b1e0f368144c597d0e 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -710,6 +710,8 @@ static DEFINE_RAW_SPINLOCK(c3_lock);
 static void acpi_idle_enter_bm(struct acpi_processor *pr,
 			       struct acpi_processor_cx *cx, bool timer_bc)
 {
+	acpi_unlazy_tlb(smp_processor_id());
+
 	/*
 	 * Must be done before busmaster disable as we might need to
 	 * access HPET !
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 5dc7ea4b6bc4cc207cffd8d8efbaed776179c9d9..f0b06b14e782b5b926b5ba7876d827551ce4cfa9 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -913,15 +913,16 @@ static __cpuidle int intel_idle(struct cpuidle_device *dev,
 	struct cpuidle_state *state = &drv->states[index];
 	unsigned long eax = flg2MWAIT(state->flags);
 	unsigned int cstate;
+	int cpu = smp_processor_id();
 
 	cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
 
 	/*
-	 * NB: if CPUIDLE_FLAG_TLB_FLUSHED is set, this idle transition
-	 * will probably flush the TLB.  It's not guaranteed to flush
-	 * the TLB, though, so it's not clear that we can do anything
-	 * useful with this knowledge.
+	 * 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 (!(lapic_timer_reliable_states & (1 << (cstate))))
 		tick_broadcast_enter();