[PATCH] namespaces: add nsproxy

This patch adds a nsproxy structure to the task struct.  Later patches will
move the fs namespace pointer into this structure, and introduce a new utsname
namespace into the nsproxy.

The vserver and openvz functionality, then, would be implemented in large part
by virtualizing/isolating more and more resources into namespaces, each
contained in the nsproxy.

[akpm@osdl.org: build fix]
Signed-off-by: Serge Hallyn <serue@us.ibm.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Andrey Savochkin <saw@sw.ru>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 54 insertions, 0 deletions

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 60aac2cea0cf..8f8bb422a5c7 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -68,6 +68,12 @@
 	.session	= 1,						\
 }
 
+extern struct nsproxy init_nsproxy;
+#define INIT_NSPROXY(nsproxy) {						\
+	.count		= ATOMIC_INIT(1),				\
+	.nslock		= SPIN_LOCK_UNLOCKED,				\
+}
+
 #define INIT_SIGHAND(sighand) {						\
 	.count		= ATOMIC_INIT(1), 				\
 	.action		= { { { .sa_handler = NULL, } }, },		\
@@ -117,6 +123,7 @@ extern struct group_info init_groups;
 	.files		= &init_files,					\
 	.signal		= &init_signals,				\
 	.sighand	= &init_sighand,				\
+	.nsproxy	= &init_nsproxy,				\
 	.pending	= {						\
 		.list = LIST_HEAD_INIT(tsk.pending.list),		\
 		.signal = {{0}}},					\
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
new file mode 100644
index 000000000000..7bdebfaab6a5
--- /dev/null
+++ b/include/linux/nsproxy.h
@@ -0,0 +1,45 @@
+#ifndef _LINUX_NSPROXY_H
+#define _LINUX_NSPROXY_H
+
+#include <linux/spinlock.h>
+#include <linux/sched.h>
+
+/*
+ * A structure to contain pointers to all per-process
+ * namespaces - fs (mount), uts, network, sysvipc, etc.
+ *
+ * '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;
+	spinlock_t nslock;
+};
+extern struct nsproxy init_nsproxy;
+
+struct nsproxy *dup_namespaces(struct nsproxy *orig);
+int copy_namespaces(int flags, struct task_struct *tsk);
+void get_task_namespaces(struct task_struct *tsk);
+void free_nsproxy(struct nsproxy *ns);
+
+static inline void put_nsproxy(struct nsproxy *ns)
+{
+	if (atomic_dec_and_test(&ns->count)) {
+		free_nsproxy(ns);
+	}
+}
+
+static inline void exit_task_namespaces(struct task_struct *p)
+{
+	struct nsproxy *ns = p->nsproxy;
+	if (ns) {
+		put_nsproxy(ns);
+		p->nsproxy = NULL;
+	}
+}
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a7fff3304bd6..4fa631fa55e3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -239,6 +239,7 @@ extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
 
 struct namespace;
+struct nsproxy;
 
 /* Maximum number of active map areas.. This is a random (large) number */
 #define DEFAULT_MAX_MAP_COUNT	65536
@@ -898,6 +899,7 @@ struct task_struct {
 	struct files_struct *files;
 /* namespace */
 	struct namespace *namespace;
+	struct nsproxy *nsproxy;
 /* signal handlers */
 	struct signal_struct *signal;
 	struct sighand_struct *sighand;