From d84607762889d999f93b89e64e09d2a4dda63bf7 Mon Sep 17 00:00:00 2001
From: Jamie Liu <jamieliu@google.com>
Date: Wed, 13 May 2020 10:51:50 -0700
Subject: Enable overlayfs_stale_read by default for runsc.

Linux 4.18 and later make reads and writes coherent between pre-copy-up and
post-copy-up FDs representing the same file on an overlay filesystem. However,
memory mappings remain incoherent:

- Documentation/filesystems/overlayfs.rst, "Non-standard behavior": "If a file
  residing on a lower layer is opened for read-only and then memory mapped with
  MAP_SHARED, then subsequent changes to the file are not reflected in the
  memory mapping."

- fs/overlay/file.c:ovl_mmap() passes through to the underlying FD without any
  management of coherence in the overlay.

- Experimentally on Linux 5.2:

```
$ cat mmap_cat_page.c
#include <err.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>
#include <sys/mman.h>
#include <unistd.h>

int main(int argc, char **argv) {
  if (argc < 2) {
    errx(1, "syntax: %s [FILE]", argv[0]);
  }
  const int fd = open(argv[1], O_RDONLY);
  if (fd < 0) {
    err(1, "open(%s)", argv[1]);
  }
  const size_t page_size = sysconf(_SC_PAGE_SIZE);
  void* page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0);
  if (page == MAP_FAILED) {
    err(1, "mmap");
  }
  for (;;) {
    write(1, page, strnlen(page, page_size));
    if (getc(stdin) == EOF) {
      break;
    }
  }
  return 0;
}

$ gcc -O2 -o mmap_cat_page mmap_cat_page.c
$ mkdir lowerdir upperdir workdir overlaydir
$ echo old > lowerdir/file
$ sudo mount -t overlay -o "lowerdir=lowerdir,upperdir=upperdir,workdir=workdir" none overlaydir
$ ./mmap_cat_page overlaydir/file
old
^Z
[1]+  Stopped                 ./mmap_cat_page overlaydir/file
$ echo new > overlaydir/file
$ cat overlaydir/file
new
$ fg
./mmap_cat_page overlaydir/file

old
```

Therefore, while the VFS1 gofer client's behavior of reopening read FDs is only
necessary pre-4.18, replacing existing memory mappings (in both sentry and
application address spaces) with mappings of the new FD is required regardless
of kernel version, and this latter behavior is common to both VFS1 and VFS2.
Re-document accordingly, and change the runsc flag to enabled by default.

New test:
- Before this CL: https://source.cloud.google.com/results/invocations/5b222d2c-e918-4bae-afc4-407f5bac509b
- After this CL: https://source.cloud.google.com/results/invocations/f28c747e-d89c-4d8c-a461-602b33e71aab

PiperOrigin-RevId: 311361267
---
 pkg/sentry/fsimpl/gofer/gofer.go | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'pkg/sentry/fsimpl/gofer/gofer.go')

diff --git a/pkg/sentry/fsimpl/gofer/gofer.go b/pkg/sentry/fsimpl/gofer/gofer.go
index 1da8d5d82..353e2cf5b 100644
--- a/pkg/sentry/fsimpl/gofer/gofer.go
+++ b/pkg/sentry/fsimpl/gofer/gofer.go
@@ -143,9 +143,12 @@ type filesystemOptions struct {
 
 	// If overlayfsStaleRead is true, O_RDONLY host FDs provided by the remote
 	// filesystem may not be coherent with writable host FDs opened later, so
-	// mappings of the former must be replaced by mappings of the latter. This
-	// is usually only the case when the remote filesystem is an overlayfs
-	// mount on Linux < 4.19.
+	// all uses of the former must be replaced by uses of the latter. This is
+	// usually only the case when the remote filesystem is a Linux overlayfs
+	// mount. (Prior to Linux 4.18, patch series centered on commit
+	// d1d04ef8572b "ovl: stack file ops", both I/O and memory mappings were
+	// incoherent between pre-copy-up and post-copy-up FDs; after that patch
+	// series, only memory mappings are incoherent.)
 	overlayfsStaleRead bool
 
 	// If regularFilesUseSpecialFileFD is true, application FDs representing
-- 
cgit v1.2.3