If we read to a file that implements ->read_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 ->read with a changed address
limit if available.

Signed-off-by: Christoph Hellwig <h...@lst.de>
---
 fs/read_write.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/fs/read_write.c b/fs/read_write.c
index 46ddfce17e839..c93acbd8bf5a3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -421,7 +421,6 @@ static ssize_t new_sync_read(struct file *filp, char __user 
*buf, size_t len, lo
 
 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 (!(file->f_mode & FMODE_CAN_READ))
@@ -429,14 +428,25 @@ ssize_t __kernel_read(struct file *file, void *buf, 
size_t count, loff_t *pos)
 
        if (count > MAX_RW_COUNT)
                count =  MAX_RW_COUNT;
-       set_fs(KERNEL_DS);
-       if (file->f_op->read)
+       if (file->f_op->read_iter) {
+               struct kvec iov = { .iov_base = buf, .iov_len = count };
+               struct kiocb kiocb;
+               struct iov_iter iter;
+
+               init_sync_kiocb(&kiocb, file);
+               kiocb.ki_pos = *pos;
+               iov_iter_kvec(&iter, READ, &iov, 1, count);
+               ret = file->f_op->read_iter(&kiocb, &iter);
+               *pos = kiocb.ki_pos;
+       } else if (file->f_op->read) {
+               mm_segment_t old_fs = get_fs();
+
+               set_fs(KERNEL_DS);
                ret = file->f_op->read(file, (void __user *)buf, count, pos);
-       else if (file->f_op->read_iter)
-               ret = new_sync_read(file, (void __user *)buf, count, pos);
-       else
+               set_fs(old_fs);
+       } else {
                ret = -EINVAL;
-       set_fs(old_fs);
+       }
        if (ret > 0) {
                fsnotify_access(file);
                add_rchar(current, ret);
-- 
2.26.2

Reply via email to