hugetlbfs: add O_TMPFILE support

With hugetlbfs, a common pattern for mapping anonymous huge pages is to
create a temporary file first.  Currently libraries like libhugetlbfs
and seastar create these with a standard mkstemp+unlink trick, but it
would be more robust to be able to simply pass the O_TMPFILE flag to
open().  O_TMPFILE is already supported by several file systems like
ext4 and xfs.  The implementation simply uses the existi= ng d_tmpfile
utility function to instantiate the dcache entry for the file.

Tested manually by successfully creating a temporary file by opening it
with (O_TMPFILE|O_RDWR) on mounted hugetlbfs and successfully mapping 2M
huge pages with it.  Without the patch, trying to open a file with
O_TMPFILE results in -ENOSUP.

Link: http://lkml.kernel.org/r/bc9383eff6e1374d79f3a92257ae829ba1e6ae60.1573285189.git.p.sarna@tlen.pl
Signed-off-by: Piotr Sarna <p.sarna@tlen.pl>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cacf99922cc5077bbbbe65756478b07f83fdd40..c978061c3893e38f0dc9bdd71ba611cdd1806400 100644 (file)
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -815,8 +815,11 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 /*
  * File creation. Allocate an inode, and we're done..
  */
-static int hugetlbfs_mknod(struct inode *dir,
-                       struct dentry *dentry, umode_t mode, dev_t dev)
+static int do_hugetlbfs_mknod(struct inode *dir,
+                       struct dentry *dentry,
+                       umode_t mode,
+                       dev_t dev,
+                       bool tmpfile)
 {
        struct inode *inode;
        int error = -ENOSPC;
@@ -824,13 +827,23 @@ static int hugetlbfs_mknod(struct inode *dir,
        inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
        if (inode) {
                dir->i_ctime = dir->i_mtime = current_time(dir);
-               d_instantiate(dentry, inode);
-               dget(dentry);   /* Extra count - pin the dentry in core */
+               if (tmpfile) {
+                       d_tmpfile(dentry, inode);
+               } else {
+                       d_instantiate(dentry, inode);
+                       dget(dentry);/* Extra count - pin the dentry in core */
+               }
                error = 0;
        }
        return error;
 }
 
+static int hugetlbfs_mknod(struct inode *dir,
+                       struct dentry *dentry, umode_t mode, dev_t dev)
+{
+       return do_hugetlbfs_mknod(dir, dentry, mode, dev, false);
+}
+
 static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
        int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
@@ -844,6 +857,12 @@ static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mo
        return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
 }
 
+static int hugetlbfs_tmpfile(struct inode *dir,
+                       struct dentry *dentry, umode_t mode)
+{
+       return do_hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0, true);
+}
+
 static int hugetlbfs_symlink(struct inode *dir,
                        struct dentry *dentry, const char *symname)
 {
@@ -1102,6 +1121,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations = {
        .mknod          = hugetlbfs_mknod,
        .rename         = simple_rename,
        .setattr        = hugetlbfs_setattr,
+       .tmpfile        = hugetlbfs_tmpfile,
 };
 
 static const struct inode_operations hugetlbfs_inode_operations = {