Messages in this thread Patch in this message | | | Date | Mon, 6 Apr 2009 21:54:54 +0100 (BST) | From | Hugh Dickins <> | Subject | [PATCH 1/3] shmem: fix division by zero |
| |
From: Yuri Tikhonov <yur@emcraft.com>
Fix a division by zero which we have in shmem_truncate_range() and shmem_unuse_inode() when using big PAGE_SIZE values (e.g. 256kB on ppc44x).
With 256kB PAGE_SIZE, the ENTRIES_PER_PAGEPAGE constant becomes too large (0x1.0000.0000) on a 32-bit kernel, so this patch just changes its type from 'unsigned long' to 'unsigned long long'.
Hugh: reverted its unsigned long longs in shmem_truncate_range() and shmem_getpage(): the pagecache index cannot be more than an unsigned long, so the divisions by zero occurred in unreached code. It's a pity we need any ULL arithmetic here, but I found no pretty way to avoid it.
Signed-off-by: Yuri Tikhonov <yur@emcraft.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> ---
mm/shmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
--- 2.6.29-git13/mm/shmem.c 2009-04-06 11:48:55.000000000 +0100 +++ 2.6.29-git13+/mm/shmem.c 2009-04-06 15:33:09.000000000 +0100 @@ -66,7 +66,7 @@ static struct vfsmount *shm_mnt; #include <asm/pgtable.h> #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long)) -#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) +#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE) #define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512) #define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
| |