From 770d1a4502dd214c75b1418b49c0f51fdbb2ad8e Mon Sep 17 00:00:00 2001 From: Stefano Brivio Date: Sun, 21 May 2023 15:03:31 +0200 Subject: isolation: Initially Keep CAP_SETFCAP if running as UID 0 in non-init If pasta spawns a child process while running as UID 0, which is only allowed from a non-init namespace, we need to keep CAP_SETFCAP before pasta_start_ns() is called: otherwise, starting from Linux 5.12, we won't be able to update /proc/self/uid_map with the intended mapping (from 0 to 0). See user_namespaces(7). Signed-off-by: Stefano Brivio Reviewed-by: David Gibson --- isolation.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'isolation.c') diff --git a/isolation.c b/isolation.c index 5f89047..19932bf 100644 --- a/isolation.c +++ b/isolation.c @@ -177,6 +177,8 @@ static void clamp_caps(void) */ void isolate_initial(void) { + uint64_t keep; + /* We want to keep CAP_NET_BIND_SERVICE in the initial * namespace if we have it, so that we can forward low ports * into the guest/namespace @@ -193,9 +195,18 @@ void isolate_initial(void) * further capabilites in isolate_user() and * isolate_prefork(). */ - drop_caps_ep_except(BIT(CAP_NET_BIND_SERVICE) | - BIT(CAP_SETUID) | BIT(CAP_SETGID) | - BIT(CAP_SYS_ADMIN) | BIT(CAP_NET_ADMIN)); + keep = BIT(CAP_NET_BIND_SERVICE) | BIT(CAP_SETUID) | BIT(CAP_SETGID) | + BIT(CAP_SYS_ADMIN) | BIT(CAP_NET_ADMIN); + + /* Since Linux 5.12, if we want to update /proc/self/uid_map to create + * a mapping from UID 0, which only happens with pasta spawning a child + * from a non-init user namespace (pasta can't run as root), we need to + * retain CAP_SETFCAP too. + */ + if (!ns_is_init() && !geteuid()) + keep |= BIT(CAP_SETFCAP); + + drop_caps_ep_except(keep); } /** -- cgit v1.2.3