x86/mm: Reimplement flush_tlb_page() using flush_tlb_mm_range()

flush_tlb_page() was very similar to flush_tlb_mm_range() except that
it had a couple of issues:

 - It was missing an smp_mb() in the case where
   current->active_mm != mm.  (This is a longstanding bug reported by Nadav Amit)

 - It was missing tracepoints and vm counter updates.

The only reason that I can see for keeping it at as a separate
function is that it could avoid a few branches that
flush_tlb_mm_range() needs to decide to flush just one page.  This
hardly seems worthwhile.  If we decide we want to get rid of those
branches again, a better way would be to introduce an
__flush_tlb_mm_range() helper and make both flush_tlb_page() and
flush_tlb_mm_range() use it.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Nadav Amit <namit@vmware.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/3cc3847cf888d8907577569b8bac3f01992ef8f9.1495492063.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/tlbflush.h

@@ -307,11 +307,15 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
 
 extern void flush_tlb_all(void);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned long vmflag);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
+{
+	flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE);
+}
+
 void native_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm,
 				unsigned long start, unsigned long end);

arch/x86/mm/tlb.c

@@ -354,33 +354,6 @@ out:
 	preempt_enable();
 }
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
-{
-	struct mm_struct *mm = vma->vm_mm;
-
-	preempt_disable();
-
-	if (current->active_mm == mm) {
-		if (current->mm) {
-			/*
-			 * Implicit full barrier (INVLPG) that synchronizes
-			 * with switch_mm.
-			 */
-			__flush_tlb_one(start);
-		} else {
-			leave_mm(smp_processor_id());
-
-			/* Synchronize with switch_mm. */
-			smp_mb();
-		}
-	}
-
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, start, start + PAGE_SIZE);
-
-	preempt_enable();
-}
-
 static void do_flush_tlb_all(void *info)
 {
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);