浅析Linux namespace

环境背景

Linux版本：linux-4.10.5
Linux namespace 作用：
Linux Namespace是一种Linux Kernel提供的资源隔离方案，提供Pid，Network，Ipc，Uts，Mount等资源的隔离，每个Namespace下的这些资源对于其他Namespace是不可见的
作用对象：进程

分析

对Linux namespace的分析会结合一些简单的源码做一些分析，代码只关注Linux namespace相关的部分，只是浅析逻辑，不涉及细节分析。有需要深入的可以自行跟踪源码分析。
好了，不多说，进入正文。
Linux namespace是作用于进程的，也就是说每个进程都有属于自己的namespce，所以在进程描述符中，就可以找到namespace的结构体信息。

代码目录：linux-4.10.5\include\linux\sched.h

struct task_struct {
...
/* namespaces */
	struct nsproxy *nsproxy
...
}
# 由于这个结构体的信息比较多，这里只关注namespace相关的信息，所以直接搜索namespace或者nsproxy

这里的nssproxy结构体就是我们要分析的namespace的结构体，所以直接看它里面有什么东西（task_struct这个结构体也很值得大家去深入了解，会对进程有更加深刻的认识）

nsproxy

代码路径：linux-4.10.5\include\linux\nsproxy.h

struct mnt_namespace;
struct uts_namespace;
struct ipc_namespace;
struct pid_namespace;
struct cgroup_namespace;
struct fs_struct;

/*
 * A structure to contain pointers to all per-process
 * namespaces - fs (mount), uts, network, sysvipc, etc.
 *
 * The pid namespace is an exception -- it's accessed using
 * task_active_pid_ns.  The pid namespace here is the
 * namespace that children will use.
 *
 * 'count' is the number of tasks holding a reference.
 * The count for each namespace, then, will be the number
 * of nsproxies pointing to it, not the number of tasks.
 *
 * The nsproxy is shared by tasks which share all namespaces.
 * As soon as a single namespace is cloned or unshared, the
 * nsproxy is copied.
 */
 
struct nsproxy {
	atomic_t count;
	struct uts_namespace *uts_ns;
	struct ipc_namespace *ipc_ns;
	struct mnt_namespace *mnt_ns;
	struct pid_namespace *pid_ns_for_children;
	struct net 	     *net_ns;
	struct cgroup_namespace *cgroup_ns;
};
extern struct nsproxy init_nsproxy;

大家仔细阅读以下上面的注释，就可以知道当一个fork出来的进程，nsproxy的信息也会被复制到新的进程中。

上面的nsproxy有6个主要的结构体，下面展示每个结构体中包含了哪些内容。

uts_namespace

代码路径：include/linux/utsname.h

UTS（UNIX Time-sharing System）namespace提供了主机名和域名的隔离。

struct uts_namespace {
	struct kref kref;
	struct new_utsname name;
	struct user_namespace *user_ns;
	struct ucounts *ucounts;
	struct ns_common ns;
};
extern struct uts_namespace init_uts_ns;

这里又包含了很多个结构体，这里有个user_namespace是需要我们额外关注的（在Linux3.8才开始有）

user_namespace

代码路径：include\linux\user_namespace.h

主要用来隔离安全相关的标识符（idebtifier）和属性（attribute），包括用户ID、用户组ID、root目录、key（密钥）以及特殊权限。

struct user_namespace {
	struct uid_gid_map	uid_map;
	struct uid_gid_map	gid_map;
	struct uid_gid_map	projid_map;
	atomic_t		count;
	struct user_namespace	*parent;
	int			level;
	kuid_t			owner;
	kgid_t			group;
	struct ns_common	ns;
	unsigned long		flags;

	/* Register of per-UID persistent keyrings for this namespace */
#ifdef CONFIG_PERSISTENT_KEYRINGS
	struct key		*persistent_keyring_register;
	struct rw_semaphore	persistent_keyring_register_sem;
#endif
	struct work_struct	work;
#ifdef CONFIG_SYSCTL
	struct ctl_table_set	set;
	struct ctl_table_header *sysctls;
#endif
	struct ucounts		*ucounts;
	int ucount_max[UCOUNT_COUNTS];
};

ipc_namespace

代码路径：include/linux/ipc_namespace.h

进程间通信（Inter-Process Communication，IPC）涉及的IPC资源包括常见的信号量、消息队列、共享内存

struct ipc_namespace {
	atomic_t	count;
	struct ipc_ids	ids[3];

	int		sem_ctls[4];
	int		used_sems;

	unsigned int	msg_ctlmax;
	unsigned int	msg_ctlmnb;
	unsigned int	msg_ctlmni;
	atomic_t	msg_bytes;
	atomic_t	msg_hdrs;

	size_t		shm_ctlmax;
	size_t		shm_ctlall;
	unsigned long	shm_tot;
	int		shm_ctlmni;
	/*
	 * Defines whether IPC_RMID is forced for _all_ shm segments regardless
	 * of shmctl()
	 */
	int		shm_rmid_forced;

	struct notifier_block ipcns_nb;

	/* The kern_mount of the mqueuefs sb.  We take a ref on it */
	struct vfsmount	*mq_mnt;

	/* # queues in this ns, protected by mq_lock */
	unsigned int    mq_queues_count;

	/* next fields are set through sysctl */
	unsigned int    mq_queues_max;   /* initialized to DFLT_QUEUESMAX */
	unsigned int    mq_msg_max;      /* initialized to DFLT_MSGMAX */
	unsigned int    mq_msgsize_max;  /* initialized to DFLT_MSGSIZEMAX */
	unsigned int    mq_msg_default;
	unsigned int    mq_msgsize_default;

	/* user_ns which owns the ipc ns */
	struct user_namespace *user_ns;
	struct ucounts *ucounts;

	struct ns_common ns;
};

mnt_namespace

代码路径：fs/mount.h

通过隔离文件系统挂载点对文件系统做隔离

struct mnt_namespace {
	atomic_t		count;
	struct ns_common	ns;
	struct mount *	root;
	struct list_head	list;
	struct user_namespace	*user_ns;
	struct ucounts		*ucounts;
	u64			seq;	/* Sequence number to prevent loops */
	wait_queue_head_t poll;
	u64 event;
	unsigned int		mounts; /* # of mounts in the namespace */
	unsigned int		pending_mounts;
};

pid_namespace

代码路径：include/linux/pid_namespace.h

在Linux系统中。pid为1的进程是init（或systemd），地位非常特殊。它作为所有系统的父进程，维护一张进程表，不断检查进程的状态，一旦有某个子进程因为父进程错误成为“孤儿”进程，1号进程就会负责回收这个子进程并最终回收资源，结束进程。

struct pid_namespace {
       struct kref kref;
       struct pidmap pidmap[PIDMAP_ENTRIES];
       struct rcu_head rcu;
       int last_pid;
       unsigned int nr_hashed;
       struct task_struct *child_reaper;
       struct kmem_cache *pid_cachep;
       unsigned int level;
       struct pid_namespace *parent;
#ifdef CONFIG_PROC_FS
       struct vfsmount *proc_mnt;
       struct dentry *proc_self;
       struct dentry *proc_thread_self;
#endif
#ifdef CONFIG_BSD_PROCESS_ACCT
       struct fs_pin *bacct;
#endif
       struct user_namespace *user_ns;
       struct work_struct proc_work;
       kgid_t pid_gid;
       int hide_pid;
       int reboot;    /* group exit code if this pidns was rebooted */
       struct ns_common ns;};

net

代码路径：include\net\net_namespace.h

实现网络隔离，使用ip netns可以查看network namespace的详情

struct net {
	atomic_t		passive;	/* To decided when the network
						 * namespace should be freed.
						 */
	atomic_t		count;		/* To decided when the network
						 *  namespace should be shut down.
						 */
	spinlock_t		rules_mod_lock;

	atomic64_t		cookie_gen;

	struct list_head	list;		/* list of network namespaces */
	struct list_head	cleanup_list;	/* namespaces on death row */
	struct list_head	exit_list;	/* Use only net_mutex */

	struct user_namespace   *user_ns;	/* Owning user namespace */
	struct ucounts		*ucounts;
	spinlock_t		nsid_lock;
	struct idr		netns_ids;

	struct ns_common	ns;

	struct proc_dir_entry 	*proc_net;
	struct proc_dir_entry 	*proc_net_stat;

#ifdef CONFIG_SYSCTL
	struct ctl_table_set	sysctls;
#endif

	struct sock 		*rtnl;			/* rtnetlink socket */
	struct sock		*genl_sock;

	struct list_head 	dev_base_head;
	struct hlist_head 	*dev_name_head;
	struct hlist_head	*dev_index_head;
	unsigned int		dev_base_seq;	/* protected by rtnl_mutex */
	int			ifindex;
	unsigned int		dev_unreg_count;

	/* core fib_rules */
	struct list_head	rules_ops;


	struct net_device       *loopback_dev;          /* The loopback */
	struct netns_core	core;
	struct netns_mib	mib;
	struct netns_packet	packet;
	struct netns_unix	unx;
	struct netns_ipv4	ipv4;
#if IS_ENABLED(CONFIG_IPV6)
	struct netns_ipv6	ipv6;
#endif
#if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN)
	struct netns_ieee802154_lowpan	ieee802154_lowpan;
#endif
#if defined(CONFIG_IP_SCTP) || defined(CONFIG_IP_SCTP_MODULE)
	struct netns_sctp	sctp;
#endif
#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
	struct netns_dccp	dccp;
#endif
#ifdef CONFIG_NETFILTER
	struct netns_nf		nf;
	struct netns_xt		xt;
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	struct netns_ct		ct;
#endif
#if defined(CONFIG_NF_TABLES) || defined(CONFIG_NF_TABLES_MODULE)
	struct netns_nftables	nft;
#endif
#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
	struct netns_nf_frag	nf_frag;
#endif
	struct sock		*nfnl;
	struct sock		*nfnl_stash;
#if IS_ENABLED(CONFIG_NETFILTER_NETLINK_ACCT)
	struct list_head        nfnl_acct_list;
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
	struct list_head	nfct_timeout_list;
#endif
#endif
#ifdef CONFIG_WEXT_CORE
	struct sk_buff_head	wext_nlevents;
#endif
	struct net_generic __rcu	*gen;

	/* Note : following structs are cache line aligned */
#ifdef CONFIG_XFRM
	struct netns_xfrm	xfrm;
#endif
#if IS_ENABLED(CONFIG_IP_VS)
	struct netns_ipvs	*ipvs;
#endif
#if IS_ENABLED(CONFIG_MPLS)
	struct netns_mpls	mpls;
#endif
	struct sock		*diag_nlsk;
	atomic_t		fnhe_genid;
};

cgroup_namespace

代码路径：include\linux\cgroup.h

提供cgroup的一些隔离

struct cgroup_namespace {
	atomic_t		count;
	struct ns_common	ns;
	struct user_namespace	*user_ns;
	struct ucounts		*ucounts;
	struct css_set          *root_cset;
};

Linux namespace的几个重要的结构体就是这些，深入研究的需要进入源码。

fork流程分析

下面分析下Linux namespace在整个生成进程中是如何创建的。

Linux使用fork函数来创建一个进程

代码路径：kernel/fork.c

#ifdef __ARCH_WANT_SYS_FORK
SYSCALL_DEFINE0(fork)
{
#ifdef CONFIG_MMU
	return _do_fork(SIGCHLD, 0, 0, NULL, NULL, 0);
#else
	/* can not support in nommu mode */
	return -EINVAL;
#endif
}
#endif

#ifdef __ARCH_WANT_SYS_VFORK
SYSCALL_DEFINE0(vfork)
{
	return _do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, 0,
			0, NULL, NULL, 0);
}
#endif

通过上面的信息可以看到主要是fork和vfork，而且两个都是调用_do_fork。
这里分析的是Linux namespace 所以重点关注namespace相关的，忽略一些代码

long _do_fork(unsigned long clone_flags,
	      unsigned long stack_start,
	      unsigned long stack_size,
	      int __user *parent_tidptr,
	      int __user *child_tidptr,
	      unsigned long tls)
{
	struct task_struct *p;
	int trace = 0;
	long nr;
...

	p = copy_process(clone_flags, stack_start, stack_size,
			 child_tidptr, NULL, trace, tls, NUMA_NO_NODE);
 }
 ...

copy_process是重点，其它可以个人再去分析。

/*
 * This creates a new process as a copy of the old one,
 * but does not actually start it yet.
 *
 * It copies the registers, and all the appropriate
 * parts of the process environment (as per the clone
 * flags). The actual kick-off is left to the caller.
 */
static __latent_entropy struct task_struct *copy_process(
					unsigned long clone_flags,
					unsigned long stack_start,
					unsigned long stack_size,
					int __user *child_tidptr,
					struct pid *pid,
					int trace,
					unsigned long tls,
					int node)
{
    ...
    cgroup_fork(p);
    ....
	if (retval)
		goto bad_fork_cleanup_signal;
	retval = copy_namespaces(clone_flags, p);
    ...
}

上面终于看到我们要分析的Linux namespace的函数了。

代码路径：kernel/nsproxy.c

/*
 * called from clone.  This now handles copy for nsproxy and all
 * namespaces therein.
 */
int copy_namespaces(unsigned long flags, struct task_struct *tsk)
{
	struct nsproxy *old_ns = tsk->nsproxy;
	struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns);
	struct nsproxy *new_ns;

	if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC |
			      CLONE_NEWPID | CLONE_NEWNET |
			      CLONE_NEWCGROUP)))) {
		get_nsproxy(old_ns);
		return 0;
	}

	if (!ns_capable(user_ns, CAP_SYS_ADMIN))
		return -EPERM;

	/*
	 * CLONE_NEWIPC must detach from the undolist: after switching
	 * to a new ipc namespace, the semaphore arrays from the old
	 * namespace are unreachable.  In clone parlance, CLONE_SYSVSEM
	 * means share undolist with parent, so we must forbid using
	 * it along with CLONE_NEWIPC.
	 */
	if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) ==
		(CLONE_NEWIPC | CLONE_SYSVSEM)) 
		return -EINVAL;

	new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs);
	if (IS_ERR(new_ns))
		return  PTR_ERR(new_ns);

	tsk->nsproxy = new_ns;
	return 0;
}

上面主要的重点是create_new_namespaces

/*
 * Create new nsproxy and all of its the associated namespaces.
 * Return the newly created nsproxy.  Do not attach this to the task,
 * leave it to the caller to do proper locking and attach it to task.
 */
static struct nsproxy *create_new_namespaces(unsigned long flags,
	struct task_struct *tsk, struct user_namespace *user_ns,
	struct fs_struct *new_fs)
{
	struct nsproxy *new_nsp;
	int err;

	new_nsp = create_nsproxy();
	if (!new_nsp)
		return ERR_PTR(-ENOMEM);

	new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs);
	if (IS_ERR(new_nsp->mnt_ns)) {
		err = PTR_ERR(new_nsp->mnt_ns);
		goto out_ns;
	}

	new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns);
	if (IS_ERR(new_nsp->uts_ns)) {
		err = PTR_ERR(new_nsp->uts_ns);
		goto out_uts;
	}

	new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns);
	if (IS_ERR(new_nsp->ipc_ns)) {
		err = PTR_ERR(new_nsp->ipc_ns);
		goto out_ipc;
	}

	new_nsp->pid_ns_for_children =
		copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
	if (IS_ERR(new_nsp->pid_ns_for_children)) {
		err = PTR_ERR(new_nsp->pid_ns_for_children);
		goto out_pid;
	}

	new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns,
					    tsk->nsproxy->cgroup_ns);
	if (IS_ERR(new_nsp->cgroup_ns)) {
		err = PTR_ERR(new_nsp->cgroup_ns);
		goto out_cgroup;
	}

	new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns);
	if (IS_ERR(new_nsp->net_ns)) {
		err = PTR_ERR(new_nsp->net_ns);
		goto out_net;
	}

	return new_nsp;

out_net:
	put_cgroup_ns(new_nsp->cgroup_ns);
out_cgroup:
	if (new_nsp->pid_ns_for_children)
		put_pid_ns(new_nsp->pid_ns_for_children);
out_pid:
	if (new_nsp->ipc_ns)
		put_ipc_ns(new_nsp->ipc_ns);
out_ipc:
	if (new_nsp->uts_ns)
		put_uts_ns(new_nsp->uts_ns);
out_uts:
	if (new_nsp->mnt_ns)
		put_mnt_ns(new_nsp->mnt_ns);
out_ns:
	kmem_cache_free(nsproxy_cachep, new_nsp);
	return ERR_PTR(err);
}

上面的代码就能看到熟悉的身影了
总结

• 先调用create_nsproxy 创建一个nsproxy
• copy_mnt_ns 创建一个mnt_namespace
• copy_utsname 创建一个uts_namespace
• copy_ipcs 创建一个ipc_namespace
• copy_pid_ns 创建一个pid_namespace
• copy_cgroup_ns 创建一个cgroup_namespace
• copy_net_ns 创建一个net

这里文章主要是分析个流程，没有对具体的代码进行分析。