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>

7 files changed, 140 insertions, 24 deletions

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 9ca4bb014657..801f4ab83302 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -709,10 +709,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
         if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
                 goto out_putf;
 
-        /* new backing store needs to support loop (eg splice_read) */
-        if (!inode->i_fop->splice_read)
-                goto out_putf;
-
         /* size of the new backing store needs to be the same */
         if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
                 goto out_putf;
@@ -788,12 +784,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
         error = -EINVAL;
         if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
                 const struct address_space_operations *aops = mapping->a_ops;
-                /*
-                 * If we can't read - sorry. If we only can't write - well,
-                 * it's going to be read-only.
-                 */
-                if (!file->f_op->splice_read)
-                        goto out_putf;
+
                 if (aops->write_begin)
                         lo_flags |= LO_FLAGS_USE_AOPS;
                 if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 6a347fbc998a..ffd42815fda1 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -47,6 +47,8 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
                       struct pipe_inode_info *pipe, size_t count,
                       unsigned int flags)
 {
+        ssize_t (*splice_read)(struct file *, loff_t *,
+                               struct pipe_inode_info *, size_t, unsigned int);
         struct coda_file_info *cfi;
         struct file *host_file;
 
@@ -54,10 +56,11 @@ coda_file_splice_read(struct file *coda_file, loff_t *ppos,
         BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
         host_file = cfi->cfi_container;
 
-        if (!host_file->f_op || !host_file->f_op->splice_read)
-                return -EINVAL;
+        splice_read = host_file->f_op->splice_read;
+        if (!splice_read)
+                splice_read = default_file_splice_read;
 
-        return host_file->f_op->splice_read(host_file, ppos, pipe, count,flags);
+        return splice_read(host_file, ppos, pipe, count, flags);
 }
 
 static ssize_t
diff --git a/fs/pipe.c b/fs/pipe.c
index 13414ec45b8d..f7dd21ad85a6 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -302,6 +302,20 @@ int generic_pipe_buf_confirm(struct pipe_inode_info *info,
         return 0;
 }
 
+/**
+ * generic_pipe_buf_release - put a reference to a &struct pipe_buffer
+ * @pipe:       the pipe that the buffer belongs to
+ * @buf:        the buffer to put a reference to
+ *
+ * Description:
+ *      This function releases a reference to @buf.
+ */
+void generic_pipe_buf_release(struct pipe_inode_info *pipe,
+                              struct pipe_buffer *buf)
+{
+        page_cache_release(buf->page);
+}
+
 static const struct pipe_buf_operations anon_pipe_buf_ops = {
         .can_merge = 1,
         .map = generic_pipe_buf_map,
diff --git a/fs/read_write.c b/fs/read_write.c
index 9d1e76bb9ee1..6c8c55dec2bc 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -805,12 +805,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
                 goto out;
         if (!(in_file->f_mode & FMODE_READ))
                 goto fput_in;
-        retval = -EINVAL;
-        in_inode = in_file->f_path.dentry->d_inode;
-        if (!in_inode)
-                goto fput_in;
-        if (!in_file->f_op || !in_file->f_op->splice_read)
-                goto fput_in;
         retval = -ESPIPE;
         if (!ppos)
                 ppos = &in_file->f_pos;
@@ -834,6 +828,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
         retval = -EINVAL;
         if (!out_file->f_op || !out_file->f_op->sendpage)
                 goto fput_out;
+        in_inode = in_file->f_path.dentry->d_inode;
         out_inode = out_file->f_path.dentry->d_inode;
         retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
         if (retval < 0)
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);
 }
 
 /**
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5bed436f4353..d926c2bea166 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2204,6 +2204,8 @@ extern int generic_segment_checks(const struct iovec *iov,
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
                 struct pipe_inode_info *, size_t, unsigned int);
+extern ssize_t default_file_splice_read(struct file *, loff_t *,
+                struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
                 struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index c8f038554e80..b43a9e039059 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -152,5 +152,6 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
 #endif