Relax the rw_verify_area() error checking.

In particular, allow over-large read- or write-requests to be downgraded
to a more reasonable range, rather than considering them outright errors.

We want to protect lower layers from (the sadly all too common) overflow
conditions, but prefer to do so by chopping the requests up, rather than
just refusing them outright.

Cc: Peter Anvin <hpa@zytor.com>
Cc: Ulrich Drepper <drepper@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Al Viro <viro@ftp.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 26 insertions, 10 deletions

diff --git a/fs/compat.c b/fs/compat.c
index 818634120b69..55ac0324aaf1 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1170,7 +1170,7 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
 	}
 
 	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret)
+	if (ret < 0)
 		goto out;
 
 	fnv = NULL;
diff --git a/fs/read_write.c b/fs/read_write.c
index a091ee4f430d..df3468a22fea 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -14,6 +14,7 @@
 #include <linux/security.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/pagemap.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -182,22 +183,33 @@ 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;
 	loff_t pos;
 
-	if (unlikely(count > INT_MAX))
+	if (unlikely((ssize_t) count < 0))
 		goto Einval;
 	pos = *ppos;
 	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
 		goto Einval;
 
 	inode = file->f_dentry->d_inode;
-	if (inode->i_flock && MANDATORY_LOCK(inode))
-		return locks_mandatory_area(read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE, inode, file, pos, count);
-	return 0;
+	if (inode->i_flock && MANDATORY_LOCK(inode)) {
+		int retval = locks_mandatory_area(
+			read_write == READ ? FLOCK_VERIFY_READ : FLOCK_VERIFY_WRITE,
+			inode, file, pos, count);
+		if (retval < 0)
+			return retval;
+	}
+	return count > MAX_RW_COUNT ? MAX_RW_COUNT : count;
 
 Einval:
 	return -EINVAL;
@@ -244,7 +256,8 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 		return -EFAULT;
 
 	ret = rw_verify_area(READ, file, pos, count);
-	if (!ret) {
+	if (ret >= 0) {
+		count = ret;
 		ret = security_file_permission (file, MAY_READ);
 		if (!ret) {
 			if (file->f_op->read)
@@ -295,7 +308,8 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 		return -EFAULT;
 
 	ret = rw_verify_area(WRITE, file, pos, count);
-	if (!ret) {
+	if (ret >= 0) {
+		count = ret;
 		ret = security_file_permission (file, MAY_WRITE);
 		if (!ret) {
 			if (file->f_op->write)
@@ -497,7 +511,7 @@ static ssize_t do_readv_writev(int type, struct file *file,
 	}
 
 	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret)
+	if (ret < 0)
 		goto out;
 	ret = security_file_permission(file, type == READ ? MAY_READ : MAY_WRITE);
 	if (ret)
@@ -653,8 +667,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		if (!(in_file->f_mode & FMODE_PREAD))
 			goto fput_in;
 	retval = rw_verify_area(READ, in_file, ppos, count);
-	if (retval)
+	if (retval < 0)
 		goto fput_in;
+	count = retval;
 
 	retval = security_file_permission (in_file, MAY_READ);
 	if (retval)
@@ -674,8 +689,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		goto fput_out;
 	out_inode = out_file->f_dentry->d_inode;
 	retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
-	if (retval)
+	if (retval < 0)
 		goto fput_out;
+	count = retval;
 
 	retval = security_file_permission (out_file, MAY_WRITE);
 	if (retval)