Merge tag 'cleanup-kernel_read_write' of git://git.infradead.org/users/hch/misc

Pull in-kernel read and write op cleanups from Christoph Hellwig:
 "Cleanup in-kernel read and write operations

  Reshuffle the (__)kernel_read and (__)kernel_write helpers, and ensure
  all users of in-kernel file I/O use them if they don't use iov_iter
  based methods already.

  The new WARN_ONs in combination with syzcaller already found a missing
  input validation in 9p. The fix should be on your way through the
  maintainer ASAP".

[ This is prep-work for the real changes coming 5.9 ]

* tag 'cleanup-kernel_read_write' of git://git.infradead.org/users/hch/misc:
  fs: remove __vfs_read
  fs: implement kernel_read using __kernel_read
  integrity/ima: switch to using __kernel_read
  fs: add a __kernel_read helper
  fs: remove __vfs_write
  fs: implement kernel_write using __kernel_write
  fs: check FMODE_WRITE in __kernel_write
  fs: unexport __kernel_write
  bpfilter: switch to kernel_write
  autofs: switch to kernel_write
  cachefiles: switch to kernel_write

Author: torvalds

fs/autofs/waitq.c

@@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi,
 
 	mutex_lock(&sbi->pipe_mutex);
 	while (bytes) {
-		wr = __kernel_write(file, data, bytes, &file->f_pos);
+		wr = kernel_write(file, data, bytes, &file->f_pos);
 		if (wr <= 0)
 			break;
 		data += wr;

fs/cachefiles/rdwr.c

@@ -937,7 +937,7 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
 	}
 
 	data = kmap(page);
-	ret = __kernel_write(file, data, len, &pos);
+	ret = kernel_write(file, data, len, &pos);
 	kunmap(page);
 	fput(file);
 	if (ret != len)

fs/read_write.c

@@ -419,28 +419,42 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	return ret;
 }
 
-ssize_t __vfs_read(struct file *file, char __user *buf, size_t count,
-		   loff_t *pos)
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
+	mm_segment_t old_fs = get_fs();
+	ssize_t ret;
+
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ)))
+		return -EINVAL;
+	if (!(file->f_mode & FMODE_CAN_READ))
+		return -EINVAL;
+
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	set_fs(KERNEL_DS);
 	if (file->f_op->read)
-		return file->f_op->read(file, buf, count, pos);
+		ret = file->f_op->read(file, (void __user *)buf, count, pos);
 	else if (file->f_op->read_iter)
-		return new_sync_read(file, buf, count, pos);
+		ret = new_sync_read(file, (void __user *)buf, count, pos);
 	else
-		return -EINVAL;
+		ret = -EINVAL;
+	set_fs(old_fs);
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
+	return ret;
 }
 
 ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t result;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	result = vfs_read(file, (void __user *)buf, count, pos);
-	set_fs(old_fs);
-	return result;
+	ret = rw_verify_area(READ, file, pos, count);
+	if (ret)
+		return ret;
+	return __kernel_read(file, buf, count, pos);
 }
 EXPORT_SYMBOL(kernel_read);
 
@@ -456,17 +470,22 @@ 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 (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		ret = __vfs_read(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_access(file);
-			add_rchar(current, ret);
-		}
-		inc_syscr(current);
-	}
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
 
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, pos);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_access(file);
+		add_rchar(current, ret);
+	}
+	inc_syscr(current);
 	return ret;
 }
 
@@ -488,23 +507,15 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	return ret;
 }
 
-static ssize_t __vfs_write(struct file *file, const char __user *p,
-			   size_t count, loff_t *pos)
-{
-	if (file->f_op->write)
-		return file->f_op->write(file, p, count, pos);
-	else if (file->f_op->write_iter)
-		return new_sync_write(file, p, count, pos);
-	else
-		return -EINVAL;
-}
-
+/* caller is responsible for file_start_write/file_end_write */
 ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos)
 {
 	mm_segment_t old_fs;
 	const char __user *p;
 	ssize_t ret;
 
+	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
+		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
@@ -513,7 +524,12 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	p = (__force const char __user *)buf;
 	if (count > MAX_RW_COUNT)
 		count =  MAX_RW_COUNT;
-	ret = __vfs_write(file, p, count, pos);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, p, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, p, count, pos);
+	else
+		ret = -EINVAL;
 	set_fs(old_fs);
 	if (ret > 0) {
 		fsnotify_modify(file);
@@ -522,21 +538,20 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	inc_syscw(current);
 	return ret;
 }
-EXPORT_SYMBOL(__kernel_write);
 
 ssize_t kernel_write(struct file *file, const void *buf, size_t count,
 			    loff_t *pos)
 {
-	mm_segment_t old_fs;
-	ssize_t res;
+	ssize_t ret;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	/* The cast to a user pointer is valid due to the set_fs() */
-	res = vfs_write(file, (__force const char __user *)buf, count, pos);
-	set_fs(old_fs);
+	ret = rw_verify_area(WRITE, file, pos, count);
+	if (ret)
+		return ret;
 
-	return res;
+	file_start_write(file);
+	ret =  __kernel_write(file, buf, count, pos);
+	file_end_write(file);
+	return ret;
 }
 EXPORT_SYMBOL(kernel_write);
 
@@ -552,19 +567,23 @@ 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 (count > MAX_RW_COUNT)
-			count =  MAX_RW_COUNT;
-		file_start_write(file);
-		ret = __vfs_write(file, buf, count, pos);
-		if (ret > 0) {
-			fsnotify_modify(file);
-			add_wchar(current, ret);
-		}
-		inc_syscw(current);
-		file_end_write(file);
+	if (ret)
+		return ret;
+	if (count > MAX_RW_COUNT)
+		count =  MAX_RW_COUNT;
+	file_start_write(file);
+	if (file->f_op->write)
+		ret = file->f_op->write(file, buf, count, pos);
+	else if (file->f_op->write_iter)
+		ret = new_sync_write(file, buf, count, pos);
+	else
+		ret = -EINVAL;
+	if (ret > 0) {
+		fsnotify_modify(file);
+		add_wchar(current, ret);
 	}
-
+	inc_syscw(current);
+	file_end_write(file);
 	return ret;
 }
 

include/linux/fs.h

@@ -1918,7 +1918,6 @@ ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
 			      struct iovec *fast_pointer,
 			      struct iovec **ret_pointer);
 
-extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
@@ -3034,6 +3033,7 @@ extern int kernel_read_file_from_path_initns(const char *, void **, loff_t *, lo
 extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t,
 				    enum kernel_read_file_id);
 extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
+ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
 extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
 extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
 extern struct file * open_exec(const char *);

net/bpfilter/bpfilter_kern.c

@@ -50,7 +50,7 @@ static int __bpfilter_process_sockopt(struct sock *sk, int optname,
 	req.len = optlen;
 	if (!bpfilter_ops.info.pid)
 		goto out;
-	n = __kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req),
+	n = kernel_write(bpfilter_ops.info.pipe_to_umh, &req, sizeof(req),
 			   &pos);
 	if (n != sizeof(req)) {
 		pr_err("write fail %zd\n", n);

security/integrity/iint.c

@@ -188,19 +188,7 @@ DEFINE_LSM(integrity) = {
 int integrity_kernel_read(struct file *file, loff_t offset,
 			  void *addr, unsigned long count)
 {
-	mm_segment_t old_fs;
-	char __user *buf = (char __user *)addr;
-	ssize_t ret;
-
-	if (!(file->f_mode & FMODE_READ))
-		return -EBADF;
-
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = __vfs_read(file, buf, count, &offset);
-	set_fs(old_fs);
-
-	return ret;
+	return __kernel_read(file, addr, count, &offset);
 }
 
 /*