[PATCH 107/118] mm: allow arch code to control the user page table ceiling

[Luis Henriques]

3.5.7.12 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Hugh Dickins <hughd at google.com>

commit 6ee8630e02be6dd89926ca0fbc21af68b23dc087 upstream.

On architectures where a pgd entry may be shared between user and kernel
(e.g.  ARM+LPAE), freeing page tables needs a ceiling other than 0.
This patch introduces a generic USER_PGTABLES_CEILING that arch code can
override.  It is the responsibility of the arch code setting the ceiling
to ensure the complete freeing of the page tables (usually in
pgd_free()).

[catalin.marinas at arm.com: commit log; shift_arg_pages(), asm-generic/pgtables.h changes]
Signed-off-by: Hugh Dickins <hughd at google.com>
Signed-off-by: Catalin Marinas <catalin.marinas at arm.com>
Cc: Russell King <linux at arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 fs/exec.c                     |  4 ++--
 include/asm-generic/pgtable.h | 10 ++++++++++
 mm/mmap.c                     |  4 ++--
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 858423a..2013724 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -623,7 +623,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * when the old and new regions overlap clear from new_end.
 		 */
 		free_pgd_range(&tlb, new_end, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	} else {
 		/*
 		 * otherwise, clean from old_start; this is done to not touch
@@ -632,7 +632,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		 * for the others its just a little faster.
 		 */
 		free_pgd_range(&tlb, old_start, old_end, new_end,
-			vma->vm_next ? vma->vm_next->vm_start : 0);
+			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
 	tlb_finish_mmu(&tlb, new_end, old_end);
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index ff4947b..0084135 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -7,6 +7,16 @@
 #include <linux/mm_types.h>
 #include <linux/bug.h>
 
+/*
+ * On almost all architectures and configurations, 0 can be used as the
+ * upper ceiling to free_pgtables(): on many architectures it has the same
+ * effect as using TASK_SIZE.  However, there is one configuration which
+ * must impose a more careful limit, to avoid freeing kernel pgtables.
+ */
+#ifndef USER_PGTABLES_CEILING
+#define USER_PGTABLES_CEILING	0UL
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 extern int ptep_set_access_flags(struct vm_area_struct *vma,
 				 unsigned long address, pte_t *ptep,
diff --git a/mm/mmap.c b/mm/mmap.c
index 5603d88..76b70c9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1913,7 +1913,7 @@ static void unmap_region(struct mm_struct *mm,
 	update_hiwater_rss(mm);
 	unmap_vmas(&tlb, vma, start, end);
 	free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS,
-				 next ? next->vm_start : 0);
+				 next ? next->vm_start : USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, start, end);
 }
 
@@ -2295,7 +2295,7 @@ void exit_mmap(struct mm_struct *mm)
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	unmap_vmas(&tlb, vma, 0, -1);
 
-	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0);
+	free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING);
 	tlb_finish_mmu(&tlb, 0, -1);
 
 	/*
-- 
1.8.1.2