From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Now, rw_verify_area() checsk f_pos is negative or not. And if negative, returns -EINVAL. But, some special files as /dev/(k)mem and /proc/<pid>/mem etc.. has negative offsets. And we can't do any access via read/write to the file(device). So introduce FMODE_NEG_OFFSET to allow negative file offsets. Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx> Cc: Heiko Carstens <heiko.carstens@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- drivers/char/mem.c | 4 ++++ fs/proc/base.c | 2 ++ fs/read_write.c | 21 +++++++++++++++++++-- include/linux/fs.h | 3 +++ 4 files changed, 28 insertions(+), 2 deletions(-) diff -puN drivers/char/mem.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos drivers/char/mem.c --- a/drivers/char/mem.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos +++ a/drivers/char/mem.c @@ -873,6 +873,10 @@ static int memory_open(struct inode *ino if (dev->dev_info) filp->f_mapping->backing_dev_info = dev->dev_info; + /* Is /dev/mem or /dev/kmem ? */ + if (dev->dev_info == &directly_mappable_cdev_bdi) + filp->f_mode |= FMODE_NEG_OFFSET; + if (dev->fops->open) return dev->fops->open(inode, filp); diff -puN fs/proc/base.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos fs/proc/base.c --- a/fs/proc/base.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos +++ a/fs/proc/base.c @@ -775,6 +775,8 @@ static const struct file_operations proc static int mem_open(struct inode* inode, struct file* file) { file->private_data = (void*)((long)current->self_exec_id); + /* OK to pass negative loff_t, we can catch out-of-range */ + file->f_mode |= FMODE_NEG_OFFSET; return 0; } diff -puN fs/read_write.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos fs/read_write.c --- a/fs/read_write.c~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos +++ a/fs/read_write.c @@ -205,6 +205,20 @@ bad: } #endif +static int +__negative_fpos_check(struct file *file, loff_t pos, size_t count) +{ + /* + * pos or pos+count is negative here, check overflow. + * too big "count" will be caught in rw_verify_area(). + */ + if ((pos < 0) && (pos + count < pos)) + return -EOVERFLOW; + if (file->f_mode & FMODE_NEG_OFFSET) + return 0; + return -EINVAL; +} + /* * rw_verify_area doesn't like huge counts. We limit * them to something that fits in "int" so that others @@ -222,8 +236,11 @@ int rw_verify_area(int read_write, struc if (unlikely((ssize_t) count < 0)) return retval; pos = *ppos; - if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) - return retval; + if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) { + retval = __negative_fpos_check(file, pos, count); + if (retval) + return retval; + } if (unlikely(inode->i_flock && mandatory_lock(inode))) { retval = locks_mandatory_area( diff -puN include/linux/fs.h~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos include/linux/fs.h --- a/include/linux/fs.h~vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos +++ a/include/linux/fs.h @@ -90,6 +90,9 @@ struct inodes_stat_t { /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) +/* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ +#define FMODE_NEG_OFFSET ((__force fmode_t)0x2000) + /* File was opened by fanotify and shouldn't generate fanotify events */ /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x1000000) _ -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html