@@ -20,6 +20,7 @@
#include <linux/file.h>
#include <linux/mm_inline.h>
#include <linux/blk-cgroup.h>
+#include <linux/fadvise.h>
#include "internal.h"
@@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping,
}
EXPORT_SYMBOL_GPL(page_cache_async_readahead);
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
- pgoff_t index, unsigned long nr)
-{
- if (!mapping || !mapping->a_ops)
- return -EINVAL;
-
- /*
- * Readahead doesn't make sense for DAX inodes, but we don't want it
- * to report a failure either. Instead, we just return success and
- * don't do any work.
- */
- if (dax_mapping(mapping))
- return 0;
-
- return force_page_cache_readahead(mapping, filp, index, nr);
-}
-
ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
{
ssize_t ret;
@@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count)
ret = -EBADF;
f = fdget(fd);
- if (f.file) {
- if (f.file->f_mode & FMODE_READ) {
- struct address_space *mapping = f.file->f_mapping;
- pgoff_t start = offset >> PAGE_SHIFT;
- pgoff_t end = (offset + count - 1) >> PAGE_SHIFT;
- unsigned long len = end - start + 1;
- ret = do_readahead(mapping, f.file, start, len);
- }
- fdput(f);
- }
+ if (!f.file || !(f.file->f_mode & FMODE_READ))
+ goto out;
+
+ /*
+ * The readahead() syscall is intended to run only on files
+ * that can execute readahead. If readahead is not possible
+ * on this file, then we must return -EINVAL.
+ */
+ ret = -EINVAL;
+ if (!f.file->f_mapping || !f.file->f_mapping->a_ops ||
+ !S_ISREG(file_inode(f.file)->i_mode))
+ goto out;
+
+ ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED);
+out:
+ fdput(f);
return ret;
}
The implementation of readahead(2) syscall is identical to that of fadvise64(POSIX_FADV_WILLNEED) with a few exceptions: 1. readahead(2) returns -EINVAL for !mapping->a_ops and fadvise64() ignores the request and returns 0. 2. fadvise64() checks for integer overflow corner case 3. fadvise64() calls the optional filesystem fadvise() file operation Unite the two implementations by calling vfs_fadvise() from readahead(2) syscall. Check the !mapping->a_ops in readahead(2) syscall to preserve documented syscall ABI behaviour. Suggested-by: Miklos Szeredi <mszeredi@redhat.com> Fixes: d1d04ef8572b ("ovl: stack file ops") Signed-off-by: Amir Goldstein <amir73il@gmail.com> --- Miklos, Following v5 addresses some more editorial comment from dchinner. Thanks, Amir. Changes from v4: - fix typos and editing of comments Changes from v3: - fold do_readahead helper and reduce code nesting mm/readahead.c | 45 +++++++++++++++++---------------------------- 1 file changed, 17 insertions(+), 28 deletions(-)