From: KAMEZAWA Hiroyuki 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//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. Changelog: v5->v6 - use FMODE_NEG_OFFSET (suggested by Al) - rebased onto 2.6.33-rc1 Changelog: v4->v5 - clean up patches dor /dev/mem. - rebased onto 2.6.32-rc1 Changelog: v3->v4 - make changes in mem.c aligned. - change __negative_fpos_check() to return int. - fixed bug in "pos" check. - added comments. Changelog: v2->v3 - fixed bug in rw_verify_area (it cannot be compiled) CC: Al Viro CC: Heiko Carstens Signed-off-by: Wu Fengguang Signed-off-by: KAMEZAWA Hiroyuki --- 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(-) --- linux.orig/fs/read_write.c 2010-01-14 21:28:00.000000000 +0800 +++ linux/fs/read_write.c 2010-01-14 21:30:41.000000000 +0800 @@ -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( --- linux.orig/include/linux/fs.h 2010-01-14 21:28:00.000000000 +0800 +++ linux/include/linux/fs.h 2010-01-14 21:32:24.000000000 +0800 @@ -93,6 +93,9 @@ 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) + /* * The below are the various read and write types that we support. Some of * them include behavioral modifiers that send information down to the --- linux.orig/drivers/char/mem.c 2010-01-14 21:28:00.000000000 +0800 +++ linux/drivers/char/mem.c 2010-01-14 21:33:20.000000000 +0800 @@ -861,6 +861,10 @@ 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); --- linux.orig/fs/proc/base.c 2010-01-14 21:28:00.000000000 +0800 +++ linux/fs/proc/base.c 2010-01-14 21:37:08.000000000 +0800 @@ -861,6 +861,8 @@ 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; } -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/