Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Christoph Hellwig <hch@lst.de>
To:     Al Viro <viro@zeniv.linux.org.uk>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Stephen Rothwell <sfr@canb.auug.org.au>
Cc:     Luis Chamberlain <mcgrof@kernel.org>,
        Matthew Wilcox <willy@infradead.org>,
        Kees Cook <keescook@chromium.org>,
        Iurii Zaikin <yzaikin@google.com>,
        linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org
Subject: [PATCH 08/23] fs: don't change the address limit for ->write_iter in __kernel_write
Date:   Tue,  7 Jul 2020 19:47:46 +0200
Message-Id: <20200707174801.4162712-9-hch@lst.de>
In-Reply-To: <20200707174801.4162712-1-hch@lst.de>
References: <20200707174801.4162712-1-hch@lst.de>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

If we write to a file that implements ->write_iter there is no need
to change the address limit if we send a kvec down.  Implement that
case, and prefer it over using plain ->write with a changed address
limit if available.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/read_write.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 96e8e354f99b45..bd46c959799e97 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -489,10 +489,9 @@ 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(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)))
@@ -500,18 +499,29 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
-	old_fs = get_fs();
-	set_fs(KERNEL_DS);
-	p = (__force const char __user *)buf;
 	if (count > MAX_RW_COUNT)
 		count =  MAX_RW_COUNT;
-	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
+	if (file->f_op->write_iter) {
+		struct kvec iov = { .iov_base = (void *)buf, .iov_len = count };
+		struct kiocb kiocb;
+		struct iov_iter iter;
+
+		init_sync_kiocb(&kiocb, file);
+		kiocb.ki_pos = *pos;
+		iov_iter_kvec(&iter, WRITE, &iov, 1, count);
+		ret = file->f_op->write_iter(&kiocb, &iter);
+		if (ret > 0)
+			*pos = kiocb.ki_pos;
+	} else if (file->f_op->write) {
+		mm_segment_t old_fs = get_fs();
+
+		set_fs(KERNEL_DS);
+		ret = file->f_op->write(file, (__force const char __user *)buf,
+				count, pos);
+		set_fs(old_fs);
+	} else {
 		ret = -EINVAL;
-	set_fs(old_fs);
+	}
 	if (ret > 0) {
 		fsnotify_modify(file);
 		add_wchar(current, ret);
-- 
2.26.2