splice: implement default splice_read method

If f_op->splice_read() is not implemented, fall back to a plain read.
Use vfs_readv() to read into previously allocated pages.

This will allow splice and functions using splice, such as the loop
device, to work on all filesystems.  This includes "direct_io" files
in fuse which bypass the page cache.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

1 files changed, 115 insertions, 5 deletions

diff --git a/fs/splice.c b/fs/splice.c
index e405cf552f5c..3bd9cb21b38e 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -507,9 +507,116 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 
         return ret;
 }
-
 EXPORT_SYMBOL(generic_file_splice_read);
 
+static const struct pipe_buf_operations default_pipe_buf_ops = {
+        .can_merge = 0,
+        .map = generic_pipe_buf_map,
+        .unmap = generic_pipe_buf_unmap,
+        .confirm = generic_pipe_buf_confirm,
+        .release = generic_pipe_buf_release,
+        .steal = generic_pipe_buf_steal,
+        .get = generic_pipe_buf_get,
+};
+
+static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
+                            unsigned long vlen, loff_t offset)
+{
+        mm_segment_t old_fs;
+        loff_t pos = offset;
+        ssize_t res;
+
+        old_fs = get_fs();
+        set_fs(get_ds());
+        /* The cast to a user pointer is valid due to the set_fs() */
+        res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+        set_fs(old_fs);
+
+        return res;
+}
+
+ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+                                 struct pipe_inode_info *pipe, size_t len,
+                                 unsigned int flags)
+{
+        unsigned int nr_pages;
+        unsigned int nr_freed;
+        size_t offset;
+        struct page *pages[PIPE_BUFFERS];
+        struct partial_page partial[PIPE_BUFFERS];
+        struct iovec vec[PIPE_BUFFERS];
+        pgoff_t index;
+        ssize_t res;
+        size_t this_len;
+        int error;
+        int i;
+        struct splice_pipe_desc spd = {
+                .pages = pages,
+                .partial = partial,
+                .flags = flags,
+                .ops = &default_pipe_buf_ops,
+                .spd_release = spd_release_page,
+        };
+
+        index = *ppos >> PAGE_CACHE_SHIFT;
+        offset = *ppos & ~PAGE_CACHE_MASK;
+        nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+        for (i = 0; i < nr_pages && i < PIPE_BUFFERS && len; i++) {
+                struct page *page;
+
+                page = alloc_page(GFP_HIGHUSER);
+                error = -ENOMEM;
+                if (!page)
+                        goto err;
+
+                this_len = min_t(size_t, len, PAGE_CACHE_SIZE - offset);
+                vec[i].iov_base = (void __user *) kmap(page);
+                vec[i].iov_len = this_len;
+                pages[i] = page;
+                spd.nr_pages++;
+                len -= this_len;
+                offset = 0;
+        }
+
+        res = kernel_readv(in, vec, spd.nr_pages, *ppos);
+        if (res < 0)
+                goto err;
+
+        error = 0;
+        if (!res)
+                goto err;
+
+        nr_freed = 0;
+        for (i = 0; i < spd.nr_pages; i++) {
+                kunmap(pages[i]);
+                this_len = min_t(size_t, vec[i].iov_len, res);
+                partial[i].offset = 0;
+                partial[i].len = this_len;
+                if (!this_len) {
+                        __free_page(pages[i]);
+                        pages[i] = NULL;
+                        nr_freed++;
+                }
+                res -= this_len;
+        }
+        spd.nr_pages -= nr_freed;
+
+        res = splice_to_pipe(pipe, &spd);
+        if (res > 0)
+                *ppos += res;
+
+        return res;
+
+err:
+        for (i = 0; i < spd.nr_pages; i++) {
+                kunmap(pages[i]);
+                __free_page(pages[i]);
+        }
+        return error;
+}
+EXPORT_SYMBOL(default_file_splice_read);
+
 /*
  * Send 'sd->len' bytes to socket from 'sd->file' at position 'sd->pos'
  * using sendpage(). Return the number of bytes sent.
@@ -933,11 +1040,10 @@ static long do_splice_to(struct file *in, loff_t *ppos,
                          struct pipe_inode_info *pipe, size_t len,
                          unsigned int flags)
 {
+        ssize_t (*splice_read)(struct file *, loff_t *,
+                               struct pipe_inode_info *, size_t, unsigned int);
         int ret;
 
-        if (unlikely(!in->f_op || !in->f_op->splice_read))
-                return -EINVAL;
-
         if (unlikely(!(in->f_mode & FMODE_READ)))
                 return -EBADF;
 
@@ -945,7 +1051,11 @@ static long do_splice_to(struct file *in, loff_t *ppos,
         if (unlikely(ret < 0))
                 return ret;
 
-        return in->f_op->splice_read(in, ppos, pipe, len, flags);
+        splice_read = in->f_op->splice_read;
+        if (!splice_read)
+                splice_read = default_file_splice_read;
+
+        return splice_read(in, ppos, pipe, len, flags);
 }
 
 /**