mm: close race between do_fault_around() and fault_around_bytes_set()

Things can go wrong if fault_around_bytes will be changed under
do_fault_around(): between fault_around_mask() and fault_around_pages().

Let's read fault_around_bytes only once during do_fault_around() and
calculate mask based on the reading.

Note: fault_around_bytes can only be updated via debug interface.  Also
I've tried but was not able to trigger a bad behaviour without the
patch.  So I would not consider this patch as urgent.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index 4d0a543..dc47261 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2768,16 +2768,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 
 static unsigned long fault_around_bytes = rounddown_pow_of_two(65536);
 
-static inline unsigned long fault_around_pages(void)
-{
-       return fault_around_bytes >> PAGE_SHIFT;
-}
-
-static inline unsigned long fault_around_mask(void)
-{
-       return ~(fault_around_bytes - 1) & PAGE_MASK;
-}
-
 #ifdef CONFIG_DEBUG_FS
 static int fault_around_bytes_get(void *data, u64 *val)
 {
@@ -2842,12 +2832,15 @@ late_initcall(fault_around_debugfs);
 static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
                pte_t *pte, pgoff_t pgoff, unsigned int flags)
 {
-       unsigned long start_addr;
+       unsigned long start_addr, nr_pages, mask;
        pgoff_t max_pgoff;
        struct vm_fault vmf;
        int off;
 
-       start_addr = max(address & fault_around_mask(), vma->vm_start);
+       nr_pages = ACCESS_ONCE(fault_around_bytes) >> PAGE_SHIFT;
+       mask = ~(nr_pages * PAGE_SIZE - 1) & PAGE_MASK;
+
+       start_addr = max(address & mask, vma->vm_start);
        off = ((address - start_addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
        pte -= off;
        pgoff -= off;
@@ -2859,7 +2852,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
        max_pgoff = pgoff - ((start_addr >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +
                PTRS_PER_PTE - 1;
        max_pgoff = min3(max_pgoff, vma_pages(vma) + vma->vm_pgoff - 1,
-                       pgoff + fault_around_pages() - 1);
+                       pgoff + nr_pages - 1);
 
        /* Check if it makes any sense to call ->map_pages */
        while (!pte_none(*pte)) {
@@ -2894,7 +2887,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         * something).
         */
        if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) &&
-           fault_around_pages() > 1) {
+           fault_around_bytes >> PAGE_SHIFT > 1) {
                pte = pte_offset_map_lock(mm, pmd, address, &ptl);
                do_fault_around(vma, address, pte, pgoff, flags);
                if (!pte_same(*pte, orig_pte))