x86/mm: Stop calling leave_mm() in idle code

Now that lazy TLB suppresses all flush IPIs (as opposed to all but
the first), there's no need to leave_mm() when going idle.

This means we can get rid of the rcuidle hack in
switch_mm_irqs_off() and we can unexport leave_mm().

This also removes acpi_unlazy_tlb() from the x86 and ia64 headers,
since it has no callers any more.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Nadav Amit <nadav.amit@gmail.com>
Reviewed-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/03c699cfd6021e467be650d6b73deaccfe4b4bd7.1498751203.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/ia64/include/asm/acpi.h

@@ -112,8 +112,6 @@ 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)  \

arch/x86/include/asm/acpi.h

@@ -150,8 +150,6 @@ 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)
 {

arch/x86/mm/tlb.c

@@ -50,7 +50,6 @@ 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)
@@ -117,15 +116,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen,
 				       next_tlb_gen);
 			write_cr3(__pa(next->pgd));
-
-			/*
-			 * This gets called via leave_mm() in the idle path
-			 * where RCU functions differently.  Tracing normally
-			 * uses RCU, so we have to call the tracepoint
-			 * specially here.
-			 */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH,
-						TLB_FLUSH_ALL);
+			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
+					TLB_FLUSH_ALL);
 		}
 
 		/*
@@ -167,13 +159,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
 		write_cr3(__pa(next->pgd));
 
-		/*
-		 * This gets called via leave_mm() in the idle path where RCU
-		 * functions differently.  Tracing normally uses RCU, so we
-		 * have to call the tracepoint specially here.
-		 */
-		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH,
-					TLB_FLUSH_ALL);
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 	}
 
 	load_mm_cr4(next);

drivers/acpi/processor_idle.c

@@ -708,8 +708,6 @@ 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 !

drivers/idle/intel_idle.c

@@ -912,16 +912,15 @@ 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;
 
 	/*
-	 * leave_mm() to avoid costly and often unnecessary wakeups
-	 * for flushing the user TLB's associated with the active mm.
+	 * 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.
 	 */
-	if (state->flags & CPUIDLE_FLAG_TLB_FLUSHED)
-		leave_mm(cpu);
 
 	if (!(lapic_timer_reliable_states & (1 << (cstate))))
 		tick_broadcast_enter();