readv/writev: do the same MAX_RW_COUNT truncation that read/write does

[pandora-kernel.git] / fs / read_write.c

diff --git a/fs/read_write.c b/fs/read_write.c
index e757ef2..431a0ed 100644 (file)
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -31,6 +31,20 @@ const struct file_operations generic_ro_fops = {
 
 EXPORT_SYMBOL(generic_ro_fops);
 
+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_UNSIGNED_OFFSET)
+               return 0;
+       return -EINVAL;
+}
+
 /**
  * generic_file_llseek_unlocked - lockless generic llseek implementation
  * @file:      file structure to seek on
@@ -62,7 +76,9 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
                break;
        }
 
-       if (offset < 0 || offset > inode->i_sb->s_maxbytes)
+       if (offset < 0 && __negative_fpos_check(file, offset, 0))
+               return -EINVAL;
+       if (offset > inode->i_sb->s_maxbytes)
                return -EINVAL;
 
        /* Special lock needed here? */
@@ -137,7 +153,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
                        offset += file->f_pos;
        }
        retval = -EINVAL;
-       if (offset >= 0) {
+       if (offset >= 0 || !__negative_fpos_check(file, offset, 0)) {
                if (offset != file->f_pos) {
                        file->f_pos = offset;
                        file->f_version = 0;
@@ -221,13 +237,12 @@ bad:
 }
 #endif
 
+
 /*
  * rw_verify_area doesn't like huge counts. We limit
  * them to something that fits in "int" so that others
  * won't have to do range checks all the time.
  */
-#define MAX_RW_COUNT (INT_MAX & PAGE_CACHE_MASK)
-
 int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count)
 {
        struct inode *inode;
@@ -238,8 +253,11 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
        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(
@@ -564,65 +582,71 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
                              unsigned long nr_segs, unsigned long fast_segs,
                              struct iovec *fast_pointer,
                              struct iovec **ret_pointer)
-  {
+{
        unsigned long seg;
-       ssize_t ret;
+       ssize_t ret;
        struct iovec *iov = fast_pointer;
 
-       /*
-        * SuS says "The readv() function *may* fail if the iovcnt argument
-        * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-        * traditionally returned zero for zero segments, so...
-        */
+       /*
+        * SuS says "The readv() function *may* fail if the iovcnt argument
+        * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+        * traditionally returned zero for zero segments, so...
+        */
        if (nr_segs == 0) {
                ret = 0;
-               goto out;
+               goto out;
        }
 
-       /*
-        * First get the "struct iovec" from user memory and
-        * verify all the pointers
-        */
+       /*
+        * First get the "struct iovec" from user memory and
+        * verify all the pointers
+        */
        if (nr_segs > UIO_MAXIOV) {
                ret = -EINVAL;
-               goto out;
+               goto out;
        }
        if (nr_segs > fast_segs) {
-               iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
+               iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
                if (iov == NULL) {
                        ret = -ENOMEM;
-                       goto out;
+                       goto out;
                }
-       }
+       }
        if (copy_from_user(iov, uvector, nr_segs*sizeof(*uvector))) {
                ret = -EFAULT;
-               goto out;
+               goto out;
        }
 
-       /*
+       /*
         * According to the Single Unix Specification we should return EINVAL
         * if an element length is < 0 when cast to ssize_t or if the
         * total length would overflow the ssize_t return value of the
         * system call.
-        */
+        *
+        * Linux caps all read/write calls to MAX_RW_COUNT, and avoids the
+        * overflow case.
+        */
        ret = 0;
-       for (seg = 0; seg < nr_segs; seg++) {
-               void __user *buf = iov[seg].iov_base;
-               ssize_t len = (ssize_t)iov[seg].iov_len;
+       for (seg = 0; seg < nr_segs; seg++) {
+               void __user *buf = iov[seg].iov_base;
+               ssize_t len = (ssize_t)iov[seg].iov_len;
 
                /* see if we we're about to use an invalid len or if
                 * it's about to overflow ssize_t */
-               if (len < 0 || (ret + len < ret)) {
+               if (len < 0) {
                        ret = -EINVAL;
-                       goto out;
+                       goto out;
                }
                if (unlikely(!access_ok(vrfy_dir(type), buf, len))) {
                        ret = -EFAULT;
-                       goto out;
+                       goto out;
+               }
+               if (len > MAX_RW_COUNT - ret) {
+                       len = MAX_RW_COUNT - ret;
+                       iov[seg].iov_len = len;
                }
-
                ret += len;
-       }
+       }
 out:
        *ret_pointer = iov;
        return ret;