[PATCH] hugepage: Fix hugepage logic in free_pgtables()

free_pgtables() has special logic to call hugetlb_free_pgd_range() instead
of the normal free_pgd_range() on hugepage VMAs.  However, the test it uses
to do so is incorrect: it calls is_hugepage_only_range on a hugepage sized
range at the start of the vma.  is_hugepage_only_range() will return true
if the given range has any intersection with a hugepage address region, and
in this case the given region need not be hugepage aligned.  So, for
example, this test can return true if called on, say, a 4k VMA immediately
preceding a (nicely aligned) hugepage VMA.

At present we get away with this because the powerpc version of
hugetlb_free_pgd_range() is just a call to free_pgd_range().  On ia64 (the
only other arch with a non-trivial is_hugepage_only_range()) we get away
with it for a different reason; the hugepage area is not contiguous with
the rest of the user address space, and VMAs are not permitted in between,
so the test can't return a false positive there.

Nonetheless this should be fixed.  We do that in the patch below by
replacing the is_hugepage_only_range() test with an explicit test of the
VMA using is_vm_hugetlb_page().

This in turn changes behaviour for platforms where is_hugepage_only_range()
returns false always (everything except powerpc and ia64).  We address this
by ensuring that hugetlb_free_pgd_range() is defined to be identical to
free_pgd_range() (instead of a no-op) on everything except ia64.  Even so,
it will prevent some otherwise possible coalescing of calls down to
free_pgd_range().  Since this only happens for hugepage VMAs, removing this
small optimization seems unlikely to cause any trouble.

This patch causes no regressions on the libhugetlbfs testsuite - ppc64
POWER5 (8-way), ppc64 G5 (2-way) and i386 Pentium M (UP).

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Cc: William Lee Irwin III <wli@holomorphy.com>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/asm-ia64/page.h

@@ -57,6 +57,7 @@
 
 # define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
 # define ARCH_HAS_HUGEPAGE_ONLY_RANGE
+# define ARCH_HAS_HUGETLB_FREE_PGD_RANGE
 #endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef __ASSEMBLY__

include/asm-powerpc/pgtable.h

@@ -468,11 +468,6 @@ extern pgd_t swapper_pg_dir[];
 
 extern void paging_init(void);
 
-#ifdef CONFIG_HUGETLB_PAGE
-#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
-	free_pgd_range(tlb, addr, end, floor, ceiling)
-#endif
-
 /*
  * This gets called at the end of handling a page fault, when
  * the kernel has put a new PTE into the page table for the process.

include/linux/hugetlb.h

@@ -43,8 +43,10 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 
 #ifndef ARCH_HAS_HUGEPAGE_ONLY_RANGE
 #define is_hugepage_only_range(mm, addr, len)	0
-#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
+#endif
-						do { } while (0)
+
+#ifndef ARCH_HAS_HUGETLB_FREE_PGD_RANGE
+#define hugetlb_free_pgd_range	free_pgd_range
 #endif
 
 #ifndef ARCH_HAS_PREPARE_HUGEPAGE_RANGE
@@ -93,8 +95,7 @@ static inline unsigned long hugetlb_total_pages(void)
 #define prepare_hugepage_range(addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
-#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
+#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
-						do { } while (0)
 #define hugetlb_fault(mm, vma, addr, write)	({ BUG(); 0; })
 
 #define hugetlb_change_protection(vma, address, end, newprot)

mm/memory.c

@@ -277,7 +277,7 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
 		anon_vma_unlink(vma);
 		unlink_file_vma(vma);
 
-		if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
+		if (is_vm_hugetlb_page(vma)) {
 			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
 				floor, next? next->vm_start: ceiling);
 		} else {
@@ -285,8 +285,7 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
 			 * Optimization: gather nearby vmas into one call down
 			 */
 			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
-			  && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
+			       && !is_vm_hugetlb_page(vma)) {
-							HPAGE_SIZE)) {
 				vma = next;
 				next = vma->vm_next;
 				anon_vma_unlink(vma);