From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752966Ab2KPQg0 (ORCPT ); Fri, 16 Nov 2012 11:36:26 -0500 Received: from out03.mta.xmission.com ([166.70.13.233]:33279 "EHLO out03.mta.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752429Ab2KPQgW (ORCPT ); Fri, 16 Nov 2012 11:36:22 -0500 From: "Eric W. Biederman" To: Linux Containers Cc: , Oleg Nesterov , Serge Hallyn , Gao feng , Andrew Morton , "Eric W. Biederman" Date: Fri, 16 Nov 2012 08:35:42 -0800 Message-Id: <1353083750-3621-3-git-send-email-ebiederm@xmission.com> X-Mailer: git-send-email 1.7.5.4 In-Reply-To: <1353083750-3621-1-git-send-email-ebiederm@xmission.com> References: <8739097bkk.fsf@xmission.com> <1353083750-3621-1-git-send-email-ebiederm@xmission.com> X-XM-AID: U2FsdGVkX1/se1HyNLDhP//bYxWMVVvEMb8rbUO9Oo0= X-SA-Exim-Connect-IP: 98.207.153.68 X-SA-Exim-Mail-From: ebiederm@xmission.com X-Spam-Report: * -1.0 ALL_TRUSTED Passed through trusted hosts only via SMTP * 1.5 XMNoVowels Alpha-numberic number with no vowels * 0.1 XMSubLong Long Subject * 0.0 T_TM2_M_HEADER_IN_MSG BODY: T_TM2_M_HEADER_IN_MSG * -3.0 BAYES_00 BODY: Bayes spam probability is 0 to 1% * [score: 0.0032] * -0.0 DCC_CHECK_NEGATIVE Not listed in DCC * [sa07 1397; Body=1 Fuz1=1 Fuz2=1] * 0.0 T_TooManySym_01 4+ unique symbols in subject * 0.0 T_XMDrugObfuBody_08 obfuscated drug references X-Spam-DCC: XMission; sa07 1397; Body=1 Fuz1=1 Fuz2=1 X-Spam-Combo: ;Linux Containers X-Spam-Relay-Country: Subject: [PATCH 03/11] pidns: Capture the user namespace and filter ns_last_pid X-SA-Exim-Version: 4.2.1 (built Sun, 08 Jan 2012 03:05:19 +0000) X-SA-Exim-Scanned: Yes (on in02.mta.xmission.com) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: "Eric W. Biederman" - Capture the the user namespace that creates the pid namespace - Use that user namespace to test if it is ok to write to /proc/sys/kernel/ns_last_pid. Acked-by: Serge Hallyn Signed-off-by: "Eric W. Biederman" --- include/linux/pid_namespace.h | 8 +++++--- kernel/nsproxy.c | 2 +- kernel/pid.c | 1 + kernel/pid_namespace.c | 16 +++++++++++----- 4 files changed, 18 insertions(+), 9 deletions(-) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 65e3e87..c89c9cf 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -31,6 +31,7 @@ struct pid_namespace { #ifdef CONFIG_BSD_PROCESS_ACCT struct bsd_acct_struct *bacct; #endif + struct user_namespace *user_ns; kgid_t pid_gid; int hide_pid; int reboot; /* group exit code if this pidns was rebooted */ @@ -46,7 +47,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } -extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns); +extern struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *ns); extern void zap_pid_ns_processes(struct pid_namespace *pid_ns); extern int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd); extern void put_pid_ns(struct pid_namespace *ns); @@ -59,8 +61,8 @@ static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) return ns; } -static inline struct pid_namespace * -copy_pid_ns(unsigned long flags, struct pid_namespace *ns) +static inline struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *ns) { if (flags & CLONE_NEWPID) ns = ERR_PTR(-EINVAL); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index b576f7f..5fe88e1 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -84,7 +84,7 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_ipc; } - new_nsp->pid_ns = copy_pid_ns(flags, task_active_pid_ns(tsk)); + new_nsp->pid_ns = copy_pid_ns(flags, task_cred_xxx(tsk, user_ns), task_active_pid_ns(tsk)); if (IS_ERR(new_nsp->pid_ns)) { err = PTR_ERR(new_nsp->pid_ns); goto out_pid; diff --git a/kernel/pid.c b/kernel/pid.c index aebd4f5..2a624f1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -78,6 +78,7 @@ struct pid_namespace init_pid_ns = { .last_pid = 0, .level = 0, .child_reaper = &init_task, + .user_ns = &init_user_ns, }; EXPORT_SYMBOL_GPL(init_pid_ns); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 7b07cc0..7580aa0 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -74,7 +75,8 @@ err_alloc: /* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ #define MAX_PID_NS_LEVEL 32 -static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns) +static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns, + struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; @@ -102,6 +104,7 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p kref_init(&ns->kref); ns->level = level; ns->parent = get_pid_ns(parent_pid_ns); + ns->user_ns = get_user_ns(user_ns); set_bit(0, ns->pidmap[0].page); atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1); @@ -117,6 +120,7 @@ static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_p out_put_parent_pid_ns: put_pid_ns(parent_pid_ns); + put_user_ns(user_ns); out_free_map: kfree(ns->pidmap[0].page); out_free: @@ -134,13 +138,14 @@ static void destroy_pid_namespace(struct pid_namespace *ns) kmem_cache_free(pid_ns_cachep, ns); } -struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns) +struct pid_namespace *copy_pid_ns(unsigned long flags, + struct user_namespace *user_ns, struct pid_namespace *old_ns) { if (!(flags & CLONE_NEWPID)) return get_pid_ns(old_ns); if (flags & (CLONE_THREAD|CLONE_PARENT)) return ERR_PTR(-EINVAL); - return create_pid_namespace(old_ns); + return create_pid_namespace(user_ns, old_ns); } static void free_pid_ns(struct kref *kref) @@ -239,9 +244,10 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) static int pid_ns_ctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct pid_namespace *pid_ns = task_active_pid_ns(current); struct ctl_table tmp = *table; - if (write && !capable(CAP_SYS_ADMIN)) + if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* @@ -250,7 +256,7 @@ static int pid_ns_ctl_handler(struct ctl_table *table, int write, * it should synchronize its usage with external means. */ - tmp.data = ¤t->nsproxy->pid_ns->last_pid; + tmp.data = &pid_ns->last_pid; return proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); } -- 1.7.5.4