[PATCH] check_user_page_readable() deadlock fix

Fix bug identifued by Richard Purdie <rpurdie@rpsys.net>.

oprofile calls check_user_page_readable() from interrupt context, so we
deadlock over various VFS locks.

But check_user_page_readable() doesn't imply either a read or a write of the
page's contents.  Change __follow_page() so that check_user_page_readable()
can tell __follow_page() that we're not accessing the page's contents, and use
that info to avoid the troublesome lock-takings.

Also, make follow_page() inline for the single callsite in memory.c to save a
bit of stack space.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/mm/memory.c b/mm/memory.c
index beabdefa6254a521da762d3a7c44274b29553edd..6fe77acbc1cd7c3ae02fe8c732fca66c49e0f1d1 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -776,8 +776,8 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
  * Do a quick page-table lookup for a single page.
  * mm->page_table_lock must be held.
  */
-static struct page *
-__follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
+static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
+                       int read, int write, int accessed)
 {
        pgd_t *pgd;
        pud_t *pud;
@@ -818,9 +818,11 @@ __follow_page(struct mm_struct *mm, unsigned long address, int read, int write)
                pfn = pte_pfn(pte);
                if (pfn_valid(pfn)) {
                        page = pfn_to_page(pfn);
-                       if (write && !pte_dirty(pte) && !PageDirty(page))
-                               set_page_dirty(page);
-                       mark_page_accessed(page);
+                       if (accessed) {
+                               if (write && !pte_dirty(pte) &&!PageDirty(page))
+                                       set_page_dirty(page);
+                               mark_page_accessed(page);
+                       }
                        return page;
                }
        }
@@ -829,16 +831,19 @@ out:
        return NULL;
 }
 
-struct page *
+inline struct page *
 follow_page(struct mm_struct *mm, unsigned long address, int write)
 {
-       return __follow_page(mm, address, /*read*/0, write);
+       return __follow_page(mm, address, 0, write, 1);
 }
 
-int
-check_user_page_readable(struct mm_struct *mm, unsigned long address)
+/*
+ * check_user_page_readable() can be called frm niterrupt context by oprofile,
+ * so we need to avoid taking any non-irq-safe locks
+ */
+int check_user_page_readable(struct mm_struct *mm, unsigned long address)
 {
-       return __follow_page(mm, address, /*read*/1, /*write*/0) != NULL;
+       return __follow_page(mm, address, 1, 0, 0) != NULL;
 }
 EXPORT_SYMBOL(check_user_page_readable);