x86/tlb: fall back to flush all when meet a THP large page

We don't need to flush large pages by PAGE_SIZE step, that just waste
time. and actually, large page don't need 'invlpg' optimizing according
to our micro benchmark. So, just flush whole TLB is enough for them.

The following result is tested on a 2CPU * 4cores * 2HT NHM EP machine,
with THP 'always' setting.

Multi-thread testing, '-t' paramter is thread number:
                       without this patch 	with this patch
./mprotect -t 1         14ns                       13ns
./mprotect -t 2         13ns                       13ns
./mprotect -t 4         12ns                       11ns
./mprotect -t 8         14ns                       10ns
./mprotect -t 16        28ns                       28ns
./mprotect -t 32        54ns                       52ns
./mprotect -t 128       200ns                      200ns
Signed-off-by: NAlex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-4-git-send-email-alex.shi@intel.comSigned-off-by: NH. Peter Anvin <hpa@zytor.com>

arch/x86/mm/tlb.c

@@ -318,12 +318,42 @@ void flush_tlb_mm(struct mm_struct *mm)
 
 #define FLUSHALL_BAR	16
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long has_large_page(struct mm_struct *mm,
+				 unsigned long start, unsigned long end)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr = ALIGN(start, HPAGE_SIZE);
+	for (; addr < end; addr += HPAGE_SIZE) {
+		pgd = pgd_offset(mm, addr);
+		if (likely(!pgd_none(*pgd))) {
+			pud = pud_offset(pgd, addr);
+			if (likely(!pud_none(*pud))) {
+				pmd = pmd_offset(pud, addr);
+				if (likely(!pmd_none(*pmd)))
+					if (pmd_large(*pmd))
+						return addr;
+			}
+		}
+	}
+	return 0;
+}
+#else
+static inline unsigned long has_large_page(struct mm_struct *mm,
+				 unsigned long start, unsigned long end)
+{
+	return 0;
+}
+#endif
 void flush_tlb_range(struct vm_area_struct *vma,
 				   unsigned long start, unsigned long end)
 {
 	struct mm_struct *mm;
 
 	if (!cpu_has_invlpg || vma->vm_flags & VM_HUGETLB) {
+flush_all:
 		flush_tlb_mm(vma->vm_mm);
 		return;
 	}
@@ -346,6 +376,10 @@ void flush_tlb_range(struct vm_area_struct *vma,
 			if ((end - start)/PAGE_SIZE > act_entries/FLUSHALL_BAR)
 				local_flush_tlb();
 			else {
+				if (has_large_page(mm, start, end)) {
+					preempt_enable();
+					goto flush_all;
+				}
 				for (addr = start; addr < end;
 						addr += PAGE_SIZE)
 					__flush_tlb_single(addr);