[SRU][J/I][PATCH 1/1] UBUNTU: SAUCE: overlayfs: fix incorrect mnt_id of files opened from map_files

[Andrea Righi]

From: Alexander Mikhalitsyn <alexander at mihalicyn.com>

BugLink: https://bugs.launchpad.net/bugs/1967924
BugLink: https://bugs.launchpad.net/bugs/1857257

The hack was introduced in ("UBUNTU: SAUCE: overlayfs: allow with
shiftfs as underlay") and it broke checkpoint/restore of docker
contains:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1857257

The following script can be used to trigger the issue:
  #!/bin/bash

  cat > test.py << EOF
  import sys

  f = open("/proc/self/maps")

  for l in f.readlines():
    if "python" not in l:
      continue
    print(l)
    s = l.split()
    start, end = s[0].split("-")
    fname = s[-1]
    print(start, end, fname)
    break
  else:
    sys.exit(1)

  test_file1 = open(fname)
  test_file2 = open("/proc/self/map_files/%s-%s" % (start, end))

  fdinfo1 = open("/proc/self/fdinfo/%d" % test_file1.fileno()).read()
  fdinfo2 = open("/proc/self/fdinfo/%d" % test_file2.fileno()).read()

  if fdinfo1 != fdinfo2:
    print("FAIL")
    print(test_file1)
    print(fdinfo1)
    print(test_file2)
    print(fdinfo2)
    sys.exit(1)
  print("PASS")
  EOF
  sudo docker run -it --privileged --rm -v `pwd`:/mnt python python /mnt/test.py

Thanks to Andrei Vagin for the reproducer and investigation of this problem.

Cc: Andrei Vagin <avagin at gmail.com>
Cc: Adrian Reber <areber at redhat.com>
Cc: Christian Brauner <christian.brauner at ubuntu.com>
Cc: Stefan Bader <stefan.bader at canonical.com>
Cc: Kleber Sacilotto de Souza <kleber.souza at canonical.com>
Cc: Krzysztof Kozlowski <krzysztof.kozlowski at canonical.com>

Fixes: d24b8a5 ("UBUNTU: SAUCE: overlayfs: allow with shiftfs as underlay")
Signed-off-by: Alexander Mikhalitsyn <alexander at mihalicyn.com>
Acked-by: Seth Forshee <seth.forshee at canonical.com>
Acked-by: Stefan Bader <stefan.bader at canonical.com>
Acked-by: Krzysztof Kozlowski <krzysztof.kozlowski at canonical.com>
Signed-off-by: Kelsey Skunberg <kelsey.skunberg at canonical.com>
[small refactoring to add the dependency of AUFS for vma->vm_prfile]
Signed-off-by: Andrea Righi <andrea.righi at canonical.com>
---
 fs/overlayfs/file.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index d0c96ca0202e..362dd17b8a00 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -490,6 +490,41 @@ static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 	return ret;
 }
 
+#if IS_ENABLED(CONFIG_AUFS_FS)
+/*
+ * In map_files_get_link() (fs/proc/base.c)
+ * we need to determine correct path from overlayfs.
+ * But real_mount(realfile->f_path.mnt) may be not
+ * equal to real_mount(file->f_path.mnt). In such case
+ * fdinfo of the same file which was opened from
+ * /proc/<pid>/map_files/... and "usual" path
+ * will show different mnt_id.
+ *
+ * We solve issue like in aufs by using additional
+ * field on struct vm_area_struct called "vm_prfile"
+ * which is used only for fdinfo/"printing" needs.
+ *
+ * See also mm/prfile.c
+ */
+static void ovl_vm_prfile_set(struct vm_area_struct *vma,
+			      struct file *file)
+{
+	get_file(file);
+	vma->vm_prfile = file;
+#ifndef CONFIG_MMU
+	get_file(file);
+	vma->vm_region->vm_prfile = file;
+#endif
+	/* Drop reference count from previous vm_file value */
+	fput(file);
+}
+#else /* !CONFIG_AUFS_FS */
+static void ovl_vm_prfile_set(struct vm_area_struct *vma,
+			      struct file *file)
+{
+}
+#endif/* CONFIG_AUFS_FS */
+
 static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct file *realfile = file->private_data;
@@ -507,6 +542,10 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
 	old_cred = ovl_override_creds(file_inode(file)->i_sb);
 	ret = call_mmap(vma->vm_file, vma);
 	revert_creds(old_cred);
+
+	if (!ret)
+		ovl_vm_prfile_set(vma, file);
+
 	ovl_file_accessed(file);
 
 	return ret;
-- 
2.34.1