1 files changed, 106 insertions, 74 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 0074afa7ecb3..328ce8cf9a85 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -227,12 +227,6 @@ loff_t noop_llseek(struct file *file, loff_t offset, int whence)
 }
 EXPORT_SYMBOL(noop_llseek);
 
-loff_t no_llseek(struct file *file, loff_t offset, int whence)
-{
-	return -ESPIPE;
-}
-EXPORT_SYMBOL(no_llseek);
-
 loff_t default_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(file);
@@ -290,14 +284,9 @@ EXPORT_SYMBOL(default_llseek);
 
 loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
 {
-	loff_t (*fn)(struct file *, loff_t, int);
-
-	fn = no_llseek;
-	if (file->f_mode & FMODE_LSEEK) {
-		if (file->f_op->llseek)
-			fn = file->f_op->llseek;
-	}
-	return fn(file, offset, whence);
+	if (!(file->f_mode & FMODE_LSEEK))
+		return -ESPIPE;
+	return file->f_op->llseek(file, offset, whence);
 }
 EXPORT_SYMBOL(vfs_llseek);
 
@@ -385,17 +374,17 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 	return security_file_permission(file,
 				read_write == READ ? MAY_READ : MAY_WRITE);
 }
+EXPORT_SYMBOL(rw_verify_area);
 
 static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {
-	struct iovec iov = { .iov_base = buf, .iov_len = len };
 	struct kiocb kiocb;
 	struct iov_iter iter;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = (ppos ? *ppos : 0);
-	iov_iter_init(&iter, READ, &iov, 1, len);
+	iov_iter_ubuf(&iter, READ, buf, len);
 
 	ret = call_read_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
@@ -491,14 +480,13 @@ ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
 
 static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos)
 {
-	struct iovec iov = { .iov_base = (void __user *)buf, .iov_len = len };
 	struct kiocb kiocb;
 	struct iov_iter iter;
 	ssize_t ret;
 
 	init_sync_kiocb(&kiocb, filp);
 	kiocb.ki_pos = (ppos ? *ppos : 0);
-	iov_iter_init(&iter, WRITE, &iov, 1, len);
+	iov_iter_ubuf(&iter, WRITE, (void __user *)buf, len);
 
 	ret = call_write_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
@@ -508,14 +496,9 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 }
 
 /* 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)
+ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos)
 {
-	struct kvec iov = {
-		.iov_base	= (void *)buf,
-		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
-	};
 	struct kiocb kiocb;
-	struct iov_iter iter;
 	ssize_t ret;
 
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE)))
@@ -531,8 +514,7 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 
 	init_sync_kiocb(&kiocb, file);
 	kiocb.ki_pos = pos ? *pos : 0;
-	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
-	ret = file->f_op->write_iter(&kiocb, &iter);
+	ret = file->f_op->write_iter(&kiocb, from);
 	if (ret > 0) {
 		if (pos)
 			*pos = kiocb.ki_pos;
@@ -542,6 +524,18 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	inc_syscw(current);
 	return ret;
 }
+
+/* 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)
+{
+	struct kvec iov = {
+		.iov_base	= (void *)buf,
+		.iov_len	= min_t(size_t, count, MAX_RW_COUNT),
+	};
+	struct iov_iter iter;
+	iov_iter_kvec(&iter, WRITE, &iov, 1, iov.iov_len);
+	return __kernel_write_iter(file, &iter, pos);
+}
 /*
  * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()",
  * but autofs is one of the few internal kernel users that actually
@@ -681,6 +675,14 @@ SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf,
 	return ksys_pread64(fd, buf, count, pos);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64)
+COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf,
+		       size_t, count, compat_arg_u64_dual(pos))
+{
+	return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos));
+}
+#endif
+
 ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf,
 		      size_t count, loff_t pos)
 {
@@ -707,6 +709,14 @@ SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf,
 	return ksys_pwrite64(fd, buf, count, pos);
 }
 
+#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64)
+COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf,
+		       size_t, count, compat_arg_u64_dual(pos))
+{
+	return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos));
+}
+#endif
+
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 		loff_t *ppos, int type, rwf_t flags)
 {
@@ -1246,6 +1256,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 					  count, fl);
 		file_end_write(out.file);
 	} else {
+		if (out.file->f_flags & O_NONBLOCK)
+			fl |= SPLICE_F_NONBLOCK;
+
 		retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
 	}
 
@@ -1380,28 +1393,6 @@ ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
 }
 EXPORT_SYMBOL(generic_copy_file_range);
 
-static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  size_t len, unsigned int flags)
-{
-	/*
-	 * Although we now allow filesystems to handle cross sb copy, passing
-	 * a file of the wrong filesystem type to filesystem driver can result
-	 * in an attempt to dereference the wrong type of ->private_data, so
-	 * avoid doing that until we really have a good reason.  NFS defines
-	 * several different file_system_type structures, but they all end up
-	 * using the same ->copy_file_range() function pointer.
-	 */
-	if (file_out->f_op->copy_file_range &&
-	    file_out->f_op->copy_file_range == file_in->f_op->copy_file_range)
-		return file_out->f_op->copy_file_range(file_in, pos_in,
-						       file_out, pos_out,
-						       len, flags);
-
-	return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
-				       flags);
-}
-
 /*
  * Performs necessary checks before doing a file copy
  *
@@ -1423,6 +1414,24 @@ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
 	if (ret)
 		return ret;
 
+	/*
+	 * We allow some filesystems to handle cross sb copy, but passing
+	 * a file of the wrong filesystem type to filesystem driver can result
+	 * in an attempt to dereference the wrong type of ->private_data, so
+	 * avoid doing that until we really have a good reason.
+	 *
+	 * nfs and cifs define several different file_system_type structures
+	 * and several different sets of file_operations, but they all end up
+	 * using the same ->copy_file_range() function pointer.
+	 */
+	if (file_out->f_op->copy_file_range) {
+		if (file_in->f_op->copy_file_range !=
+		    file_out->f_op->copy_file_range)
+			return -EXDEV;
+	} else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) {
+		return -EXDEV;
+	}
+
 	/* Don't touch certain kinds of inodes */
 	if (IS_IMMUTABLE(inode_out))
 		return -EPERM;
@@ -1488,26 +1497,41 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	file_start_write(file_out);
 
 	/*
-	 * Try cloning first, this is supported by more file systems, and
-	 * more efficient if both clone and copy are supported (e.g. NFS).
+	 * Cloning is supported by more file systems, so we implement copy on
+	 * same sb using clone, but for filesystems where both clone and copy
+	 * are supported (e.g. nfs,cifs), we only call the copy method.
 	 */
+	if (file_out->f_op->copy_file_range) {
+		ret = file_out->f_op->copy_file_range(file_in, pos_in,
+						      file_out, pos_out,
+						      len, flags);
+		goto done;
+	}
+
 	if (file_in->f_op->remap_file_range &&
 	    file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
-		loff_t cloned;
-
-		cloned = file_in->f_op->remap_file_range(file_in, pos_in,
+		ret = file_in->f_op->remap_file_range(file_in, pos_in,
 				file_out, pos_out,
 				min_t(loff_t, MAX_RW_COUNT, len),
 				REMAP_FILE_CAN_SHORTEN);
-		if (cloned > 0) {
-			ret = cloned;
+		if (ret > 0)
 			goto done;
-		}
 	}
 
-	ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len,
-				flags);
-	WARN_ON_ONCE(ret == -EOPNOTSUPP);
+	/*
+	 * We can get here for same sb copy of filesystems that do not implement
+	 * ->copy_file_range() in case filesystem does not support clone or in
+	 * case filesystem supports clone but rejected the clone request (e.g.
+	 * because it was not block aligned).
+	 *
+	 * In both cases, fall back to kernel copy so we are able to maintain a
+	 * consistent story about which filesystems support copy_file_range()
+	 * and which filesystems do not, that will allow userspace tools to
+	 * make consistent desicions w.r.t using copy_file_range().
+	 */
+	ret = generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
+				      flags);
+
 done:
 	if (ret > 0) {
 		fsnotify_access(file_in);
@@ -1617,35 +1641,43 @@ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
 	return 0;
 }
 
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+/* Like generic_write_checks(), but takes size of write instead of iter. */
+int generic_write_checks_count(struct kiocb *iocb, loff_t *count)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
 
 	if (IS_SWAPFILE(inode))
 		return -ETXTBSY;
 
-	if (!iov_iter_count(from))
+	if (!*count)
 		return 0;
 
-	/* FIXME: this is for backwards compatibility with 2.4 */
 	if (iocb->ki_flags & IOCB_APPEND)
 		iocb->ki_pos = i_size_read(inode);
 
-	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+	if ((iocb->ki_flags & IOCB_NOWAIT) &&
+	    !((iocb->ki_flags & IOCB_DIRECT) ||
+	      (file->f_mode & FMODE_BUF_WASYNC)))
 		return -EINVAL;
 
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
+}
+EXPORT_SYMBOL(generic_write_checks_count);
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns appropriate error code that caller should return or
+ * zero in case that write should be allowed.
+ */
+ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	loff_t count = iov_iter_count(from);
+	int ret;
+
+	ret = generic_write_checks_count(iocb, &count);
 	if (ret)
 		return ret;