From: Lennart Poettering <lennart@poettering.net>
Date: Thu, 3 May 2018 14:10:35 +0000 (+0200)
Subject: mount-setup: add a comment that the character/block device nodes are "optional" ... 
X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~ianmdlvl/git?a=commitdiff_plain;h=1791a21ab8c2809115c095f96b300195262f7a9e;p=elogind.git

mount-setup: add a comment that the character/block device nodes are "optional" (#8893)

if we lack privs to create device nodes that's fine, and creating
/run/systemd/inaccessible/chr or /run/systemd/inaccessible/blk won't
work then. Document this in longer comments.

Fixes: #4484
---

diff --git a/src/basic/mount-util.c b/src/basic/mount-util.c
index 1736cf19b..9d1f34e08 100644
--- a/src/basic/mount-util.c
+++ b/src/basic/mount-util.c
@@ -702,24 +702,33 @@ int repeat_unmount(const char *path, int flags) {
 #endif // 0
 
 const char* mode_to_inaccessible_node(mode_t mode) {
-        /* This function maps a node type to the correspondent inaccessible node type.
-         * Character and block inaccessible devices may not be created (because major=0 and minor=0),
-         * in such case we map character and block devices to the inaccessible node type socket. */
+        /* This function maps a node type to a corresponding inaccessible file node. These nodes are created during
+         * early boot by PID 1. In some cases we lacked the privs to create the character and block devices (maybe
+         * because we run in an userns environment, or miss CAP_SYS_MKNOD, or run with a devices policy that excludes
+         * device nodes with major and minor of 0), but that's fine, in that case we use an AF_UNIX file node instead,
+         * which is not the same, but close enough for most uses. And most importantly, the kernel allows bind mounts
+         * from socket nodes to any non-directory file nodes, and that's the most important thing that matters. */
+
         switch(mode & S_IFMT) {
                 case S_IFREG:
                         return "/run/systemd/inaccessible/reg";
+
                 case S_IFDIR:
                         return "/run/systemd/inaccessible/dir";
+
                 case S_IFCHR:
                         if (access("/run/systemd/inaccessible/chr", F_OK) == 0)
                                 return "/run/systemd/inaccessible/chr";
                         return "/run/systemd/inaccessible/sock";
+
                 case S_IFBLK:
                         if (access("/run/systemd/inaccessible/blk", F_OK) == 0)
                                 return "/run/systemd/inaccessible/blk";
                         return "/run/systemd/inaccessible/sock";
+
                 case S_IFIFO:
                         return "/run/systemd/inaccessible/fifo";
+
                 case S_IFSOCK:
                         return "/run/systemd/inaccessible/sock";
         }
diff --git a/src/core/mount-setup.c b/src/core/mount-setup.c
index eda2328f0..d98507db1 100644
--- a/src/core/mount-setup.c
+++ b/src/core/mount-setup.c
@@ -477,14 +477,20 @@ int mount_setup(bool loaded_policy) {
         (void) mkdir_label("/run/systemd/system", 0755);
 #endif // 0
 
-        /* Set up inaccessible items */
+        /* Set up inaccessible (and empty) file nodes of all types */
         (void) mkdir_label("/run/systemd/inaccessible", 0000);
         (void) mknod("/run/systemd/inaccessible/reg", S_IFREG | 0000, 0);
         (void) mkdir_label("/run/systemd/inaccessible/dir", 0000);
-        (void) mknod("/run/systemd/inaccessible/chr", S_IFCHR | 0000, makedev(0, 0));
-        (void) mknod("/run/systemd/inaccessible/blk", S_IFBLK | 0000, makedev(0, 0));
         (void) mkfifo("/run/systemd/inaccessible/fifo", 0000);
         (void) mknod("/run/systemd/inaccessible/sock", S_IFSOCK | 0000, 0);
 
+        /* The following two are likely to fail if we lack the privs for it (for example in an userns environment, if
+         * CAP_SYS_MKNOD is missing, or if a device node policy prohibit major/minor of 0 device nodes to be
+         * created). But that's entirely fine. Consumers of these files should carry fallback to use a different node
+         * then, for example /run/systemd/inaccessible/sock, which is close enough in behaviour and semantics for most
+         * uses. */
+        (void) mknod("/run/systemd/inaccessible/chr", S_IFCHR | 0000, makedev(0, 0));
+        (void) mknod("/run/systemd/inaccessible/blk", S_IFBLK | 0000, makedev(0, 0));
+
         return 0;
 }