Any architecture that has hardware updated A/D bits that require
synchronization against other processors during PTE operations
can benefit from doing non-atomic PTE updates during address space
destruction.  Originally done on i386, now ported to x86_64.

Doing a read/write pair instead of an xchg() operation saves the
implicit lock, which turns out to be a big win on 32-bit (esp w PAE).

Diffs-against: 2.6.13-rc5-mm1
Signed-off-by: Zachary Amsden <zach@vmware.com>
Index: linux-2.6.13-rc5-mm1/include/asm-x86_64/pgtable.h
===================================================================
--- linux-2.6.13-rc5-mm1.orig/include/asm-x86_64/pgtable.h	2005-08-07 04:56:37.000000000 -0700
+++ linux-2.6.13-rc5-mm1/include/asm-x86_64/pgtable.h	2005-08-07 04:59:18.601856096 -0700
@@ -104,6 +104,19 @@
 ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
 
 #define ptep_get_and_clear(mm,addr,xp)	__pte(xchg(&(xp)->pte, 0))
+
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+{
+	pte_t pte;
+	if (full) {
+		pte = *ptep;
+		*ptep = __pte(0);
+	} else {
+		pte = ptep_get_and_clear(mm, addr, ptep);
+	}
+	return pte;
+}
+
 #define pte_same(a, b)		((a).pte == (b).pte)
 
 #define PMD_SIZE	(1UL << PMD_SHIFT)
@@ -433,6 +446,7 @@
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME
 #include <asm-generic/pgtable.h>