From 6a9e2fb1bab53b54d02714a2ee3c6612d19629ce Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 6 Jun 2025 11:45:07 +0200 Subject: nsfs: move root inode number to uapi Userspace relies on the root inode numbers to identify the initial namespaces. That's already a hard dependency. So we cannot change that anymore. Move the initial inode numbers to a public header. Link: https://github.com/systemd/systemd/commit/d293fade24b34ccc2f5716b0ff5513e9533cf0c4 Link: https://lore.kernel.org/20250606-work-nsfs-v1-1-b8749c9a8844@kernel.org Signed-off-by: Christian Brauner --- include/linux/proc_ns.h | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 5ea470eb4d76..e77a37b23ca7 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -6,6 +6,7 @@ #define _LINUX_PROC_NS_H #include +#include struct pid_namespace; struct nsset; @@ -40,12 +41,12 @@ extern const struct proc_ns_operations timens_for_children_operations; */ enum { PROC_ROOT_INO = 1, - PROC_IPC_INIT_INO = 0xEFFFFFFFU, - PROC_UTS_INIT_INO = 0xEFFFFFFEU, - PROC_USER_INIT_INO = 0xEFFFFFFDU, - PROC_PID_INIT_INO = 0xEFFFFFFCU, - PROC_CGROUP_INIT_INO = 0xEFFFFFFBU, - PROC_TIME_INIT_INO = 0xEFFFFFFAU, + PROC_IPC_INIT_INO = IPC_NS_INIT_INO, + PROC_UTS_INIT_INO = UTS_NS_INIT_INO, + PROC_USER_INIT_INO = USER_NS_INIT_INO, + PROC_PID_INIT_INO = PID_NS_INIT_INO, + PROC_CGROUP_INIT_INO = CGROUP_NS_INIT_INO, + PROC_TIME_INIT_INO = TIME_NS_INIT_INO, }; #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 9b0240b3ccc325c7a96cf362877180bc9e10d546 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 6 Jun 2025 11:45:08 +0200 Subject: netns: use stable inode number for initial mount ns Apart from the network and mount namespace all other namespaces expose a stable inode number and userspace has been relying on that for a very long time now. It's very much heavily used API. Align the network namespace and use a stable inode number from the reserved procfs inode number space so this is consistent across all namespaces. Link: https://lore.kernel.org/20250606-work-nsfs-v1-2-b8749c9a8844@kernel.org Reviewed-by: Jakub Kicinski Signed-off-by: Christian Brauner --- include/linux/proc_ns.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index e77a37b23ca7..3ff0bd381704 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -47,6 +47,7 @@ enum { PROC_PID_INIT_INO = PID_NS_INIT_INO, PROC_CGROUP_INIT_INO = CGROUP_NS_INIT_INO, PROC_TIME_INIT_INO = TIME_NS_INIT_INO, + PROC_NET_INIT_INO = NET_NS_INIT_INO, }; #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 7f4f229195b73606ded77e56943f463b78adf635 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 6 Jun 2025 11:45:09 +0200 Subject: mntns: use stable inode number for initial mount ns Apart from the network and mount namespace all other namespaces expose a stable inode number and userspace has been relying on that for a very long time now. It's very much heavily used API. Align the mount namespace and use a stable inode number from the reserved procfs inode number space so this is consistent across all namespaces. Link: https://lore.kernel.org/20250606-work-nsfs-v1-3-b8749c9a8844@kernel.org Signed-off-by: Christian Brauner --- include/linux/proc_ns.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 3ff0bd381704..6258455e49a4 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -48,6 +48,7 @@ enum { PROC_CGROUP_INIT_INO = CGROUP_NS_INIT_INO, PROC_TIME_INIT_INO = TIME_NS_INIT_INO, PROC_NET_INIT_INO = NET_NS_INIT_INO, + PROC_MNT_INIT_INO = MNT_NS_INIT_INO, }; #ifdef CONFIG_PROC_FS -- cgit v1.2.3 From 76fdb7eb4e1c91086ce9c3db6972c2ed48c96afb Mon Sep 17 00:00:00 2001 From: Aleksa Sarai Date: Tue, 8 Jul 2025 23:21:51 +1000 Subject: uapi: export PROCFS_ROOT_INO The root inode of /proc having a fixed inode number has been part of the core kernel ABI since its inception, and recently some userspace programs (mainly container runtimes) have started to explicitly depend on this behaviour. The main reason this is useful to userspace is that by checking that a suspect /proc handle has fstype PROC_SUPER_MAGIC and is PROCFS_ROOT_INO, they can then use openat2(RESOLVE_{NO_{XDEV,MAGICLINK},BENEATH}) to ensure that there isn't a bind-mount that replaces some procfs file with a different one. This kind of attack has lead to security issues in container runtimes in the past (such as CVE-2019-19921) and libraries like libpathrs[1] use this feature of procfs to provide safe procfs handling functions. There was also some trailing whitespace in the "struct proc_dir_entry" initialiser, so fix that up as well. [1]: https://github.com/openSUSE/libpathrs Signed-off-by: Aleksa Sarai Link: https://lore.kernel.org/20250708-uapi-procfs-root-ino-v1-1-6ae61e97c79b@cyphar.com Signed-off-by: Christian Brauner --- include/linux/proc_ns.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h index 6258455e49a4..4b20375f3783 100644 --- a/include/linux/proc_ns.h +++ b/include/linux/proc_ns.h @@ -40,7 +40,6 @@ extern const struct proc_ns_operations timens_for_children_operations; * We always define these enumerators */ enum { - PROC_ROOT_INO = 1, PROC_IPC_INIT_INO = IPC_NS_INIT_INO, PROC_UTS_INIT_INO = UTS_NS_INIT_INO, PROC_USER_INIT_INO = USER_NS_INIT_INO, -- cgit v1.2.3