proc: subset=pid: Show /proc/self/net only for CAP_NET_ADMIN

Cache the mounters credentials and allow access to the net directories
contingent of the permissions of the mounter of proc.

Do not show /proc/self/net when proc is mounted with subset=pid option
and the mounter does not have CAP_NET_ADMIN. To avoid inadvertently
allowing access to /proc/<pid>/net, updating mounter credentials is not
supported.

Signed-off-by: Alexey Gladkov <legion@kernel.org>
Link: https://patch.msgid.link/d2466fe9085367f1e24693c437ecb8cff2789660.1777278334.git.legion@kernel.org
Reviewed-by: Aleksa Sarai <aleksa@amutable.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>

diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 184cddeb8215cb6f2a4be568acc3e77eae5c0f28..00cc385bce21214579b073391a08ee0f82d640d1 100644 (file)
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -23,6 +23,7 @@
 #include <linux/uidgid.h>
 #include <net/net_namespace.h>
 #include <linux/seq_file.h>
+#include <linux/security.h>
 
 #include "internal.h"
 
@@ -270,6 +271,7 @@ static struct net *get_proc_task_net(struct inode *dir)
        struct task_struct *task;
        struct nsproxy *ns;
        struct net *net = NULL;
+       struct proc_fs_info *fs_info = proc_sb_info(dir->i_sb);
 
        rcu_read_lock();
        task = pid_task(proc_pid(dir), PIDTYPE_PID);
@@ -282,6 +284,12 @@ static struct net *get_proc_task_net(struct inode *dir)
        }
        rcu_read_unlock();
 
+       if (net && (fs_info->pidonly == PROC_PIDONLY_ON) &&
+           security_capable(fs_info->mounter_cred, net->user_ns, CAP_NET_ADMIN, CAP_OPT_NONE) < 0) {
+               put_net(net);
+               net = NULL;
+       }
+
        return net;
 }
 

diff --git a/fs/proc/root.c b/fs/proc/root.c
index b65053f9f0464af997ab87810b1921384a2d478d..89e5678129e4288a3f942d8eeb10b05cd24a35c7 100644 (file)
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -254,6 +254,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
                return -ENOMEM;
 
        fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+       fs_info->mounter_cred = get_cred(fc->cred);
        proc_apply_options(fs_info, fc, current_user_ns());
 
        /* User space would break if executables or devices appear on proc */
@@ -350,6 +351,7 @@ static void proc_kill_sb(struct super_block *sb)
        kill_anon_super(sb);
        if (fs_info) {
                put_pid_ns(fs_info->pid_ns);
+               put_cred(fs_info->mounter_cred);
                kfree_rcu(fs_info, rcu);
        }
 }

diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index d2860c18dca92fa155d1056240ba45c99e540f5c..47d7deaeed8fffdc7197f007e391d49a5d663d14 100644 (file)
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -67,6 +67,7 @@ enum proc_pidonly {
 struct proc_fs_info {
        struct pid_namespace *pid_ns;
        kgid_t pid_gid;
+       const struct cred *mounter_cred;
        enum proc_hidepid hide_pid;
        enum proc_pidonly pidonly;
        struct rcu_head rcu;