systemd/0051-pid1-skip-cleanup-if-root-is-not-tmpfs-ramfs.patch

From 7b6a09c47f1fee035c4b42840fabf65edce12aa8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Zbigniew=20J=C4=99drzejewski-Szmek?= <zbyszek@in.waw.pl>
Date: Mon, 7 Nov 2022 12:40:20 +0100
Subject: [PATCH] pid1: skip cleanup if root is not tmpfs/ramfs

in_initrd() was really doing two things: checking if we're in the initrd, and
also verifying that the initrd is set up correctly. But this second check is
complicated, in particular it would return false for overlayfs, even with an
upper tmpfs layer. It also doesn't support the use case of having an initial
initrd with tmpfs, and then transitioning into an intermediate initrd that is
e.g. a DDI, i.e. a filesystem possibly with verity arranged as a disk image.

We don't need to check if we're in initrd in every program. Instead, concerns
are separated:
- in_initrd() just does a simple check for /etc/initrd-release.
- When doing cleanup, pid1 checks if it's on a tmpfs before starting to wipe
  the old root. The only case where we want to remove the old root is when
  we're on a plain tempory filesystem. With an overlay, we'd be creating
  whiteout files, which is not very useful. (*)

This should resolve https://bugzilla.redhat.com/show_bug.cgi?id=2137631
which is caused by systemd refusing to treat the system as an initrd because
overlayfs is used.

(*) I think the idea of keeping the initrd fs around for shutdown is outdated.
We should just have a completely separate exitrd that is unpacked when we want
to shut down. This way, we don't waste memory at runtime, and we also don't
transition to a potentially older version of systemd. But we don't have support
for this yet.

This replaces 0fef5b0f0bd9ded1ae7bcb3e4e4b2893e36c51a6.

(cherry picked from commit a940f507fbe1c81d6787dc0b7ce232c39818eec9)

Related: #2138081
---
 src/basic/util.c         | 19 ++++++++-----------
 src/shared/switch-root.c | 22 ++++++++++++----------
 2 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/src/basic/util.c b/src/basic/util.c
index 981f917fab..e6aaa2dc9b 100644
--- a/src/basic/util.c
+++ b/src/basic/util.c
@@ -56,14 +56,8 @@ bool in_initrd(void) {
         if (saved_in_initrd >= 0)
                 return saved_in_initrd;
 
-        /* We make two checks here:
-         *
-         * 1. the flag file /etc/initrd-release must exist
-         * 2. the root file system must be a memory file system
-         *
-         * The second check is extra paranoia, since misdetecting an
-         * initrd can have bad consequences due the initrd
-         * emptying when transititioning to the main systemd.
+        /* If /etc/initrd-release exists, we're in an initrd.
+         * This can be overridden by setting SYSTEMD_IN_INITRD=0|1.
          */
 
         r = getenv_bool_secure("SYSTEMD_IN_INITRD");
@@ -72,9 +66,12 @@ bool in_initrd(void) {
 
         if (r >= 0)
                 saved_in_initrd = r > 0;
-        else
-                saved_in_initrd = access("/etc/initrd-release", F_OK) >= 0 &&
-                                  path_is_temporary_fs("/") > 0;
+        else {
+                r = access("/etc/initrd-release", F_OK);
+                if (r < 0 && errno != ENOENT)
+                        log_debug_errno(r, "Failed to check if /etc/initrd-release exists, assuming it does not: %m");
+                saved_in_initrd = r >= 0;
+        }
 
         return saved_in_initrd;
 }
diff --git a/src/shared/switch-root.c b/src/shared/switch-root.c
index 1a444841fa..4cad3551a6 100644
--- a/src/shared/switch-root.c
+++ b/src/shared/switch-root.c
@@ -32,7 +32,6 @@ int switch_root(const char *new_root,
 
         _cleanup_free_ char *resolved_old_root_after = NULL;
         _cleanup_close_ int old_root_fd = -1;
-        bool old_root_remove;
         int r;
 
         assert(new_root);
@@ -42,12 +41,16 @@ int switch_root(const char *new_root,
                 return 0;
 
         /* Check if we shall remove the contents of the old root */
-        old_root_remove = in_initrd();
-        if (old_root_remove) {
-                old_root_fd = open("/", O_RDONLY|O_NONBLOCK|O_CLOEXEC|O_NOCTTY|O_DIRECTORY);
-                if (old_root_fd < 0)
-                        return log_error_errno(errno, "Failed to open root directory: %m");
-        }
+        old_root_fd = open("/", O_RDONLY | O_CLOEXEC | O_DIRECTORY);
+        if (old_root_fd < 0)
+                return log_error_errno(errno, "Failed to open root directory: %m");
+        r = fd_is_temporary_fs(old_root_fd);
+        if (r < 0)
+                return log_error_errno(r, "Failed to stat root directory: %m");
+        if (r > 0)
+                log_debug("Root directory is on tmpfs, will do cleanup later.");
+        else
+                old_root_fd = safe_close(old_root_fd);
 
         /* Determine where we shall place the old root after the transition */
         r = chase_symlinks(old_root_after, new_root, CHASE_PREFIX_ROOT|CHASE_NONEXISTENT, &resolved_old_root_after, NULL);
@@ -117,9 +120,8 @@ int switch_root(const char *new_root,
                 struct stat rb;
 
                 if (fstat(old_root_fd, &rb) < 0)
-                        log_warning_errno(errno, "Failed to stat old root directory, leaving: %m");
-                else
-                        (void) rm_rf_children(TAKE_FD(old_root_fd), 0, &rb); /* takes possession of the dir fd, even on failure */
+                        return log_error_errno(errno, "Failed to stat old root directory: %m");
+                (void) rm_rf_children(TAKE_FD(old_root_fd), 0, &rb); /* takes possession of the dir fd, even on failure */
         }
 
         return 0;