pid namespaces: initialize the namespace's proc_mnt

[linux-2.6] / fs / proc / base.c

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4fe74d156416f0936b686d57dc6ee7bd2518dba5..21510c9aa89cb51688581c982547c967539c0e90 100644 (file)
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -67,12 +67,14 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 #include <linux/ptrace.h>
+#include <linux/cgroup.h>
 #include <linux/cpuset.h>
 #include <linux/audit.h>
 #include <linux/poll.h>
 #include <linux/nsproxy.h>
 #include <linux/oom.h>
 #include <linux/elf.h>
+#include <linux/pid_namespace.h>
 #include "internal.h"
 
 /* NOTE:
@@ -349,18 +351,21 @@ struct proc_mounts {
 static int mounts_open(struct inode *inode, struct file *file)
 {
        struct task_struct *task = get_proc_task(inode);
+       struct nsproxy *nsp;
        struct mnt_namespace *ns = NULL;
        struct proc_mounts *p;
        int ret = -EINVAL;
 
        if (task) {
-               task_lock(task);
-               if (task->nsproxy) {
-                       ns = task->nsproxy->mnt_ns;
+               rcu_read_lock();
+               nsp = task_nsproxy(task);
+               if (nsp) {
+                       ns = nsp->mnt_ns;
                        if (ns)
                                get_mnt_ns(ns);
                }
-               task_unlock(task);
+               rcu_read_unlock();
+
                put_task_struct(task);
        }
 
@@ -423,16 +428,20 @@ static int mountstats_open(struct inode *inode, struct file *file)
 
        if (!ret) {
                struct seq_file *m = file->private_data;
+               struct nsproxy *nsp;
                struct mnt_namespace *mnt_ns = NULL;
                struct task_struct *task = get_proc_task(inode);
 
                if (task) {
-                       task_lock(task);
-                       if (task->nsproxy)
-                               mnt_ns = task->nsproxy->mnt_ns;
-                       if (mnt_ns)
-                               get_mnt_ns(mnt_ns);
-                       task_unlock(task);
+                       rcu_read_lock();
+                       nsp = task_nsproxy(task);
+                       if (nsp) {
+                               mnt_ns = nsp->mnt_ns;
+                               if (mnt_ns)
+                                       get_mnt_ns(mnt_ns);
+                       }
+                       rcu_read_unlock();
+
                        put_task_struct(task);
                }
 
@@ -2130,8 +2139,11 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_SCHEDSTATS
        INF("schedstat",  S_IRUGO, pid_schedstat),
 #endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_PROC_PID_CPUSET
        REG("cpuset",     S_IRUGO, cpuset),
+#endif
+#ifdef CONFIG_CGROUPS
+       REG("cgroup",  S_IRUGO, cgroup),
 #endif
        INF("oom_score",  S_IRUGO, oom_score),
        REG("oom_adj",    S_IRUGO|S_IWUSR, oom_adjust),
@@ -2193,27 +2205,27 @@ static const struct inode_operations proc_tgid_base_inode_operations = {
  *       that no dcache entries will exist at process exit time it
  *       just makes it very unlikely that any will persist.
  */
-void proc_flush_task(struct task_struct *task)
+static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
 {
        struct dentry *dentry, *leader, *dir;
        char buf[PROC_NUMBUF];
        struct qstr name;
 
        name.name = buf;
-       name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
-       dentry = d_hash_and_lookup(proc_mnt->mnt_root, &name);
+       name.len = snprintf(buf, sizeof(buf), "%d", pid);
+       dentry = d_hash_and_lookup(mnt->mnt_root, &name);
        if (dentry) {
                shrink_dcache_parent(dentry);
                d_drop(dentry);
                dput(dentry);
        }
 
-       if (thread_group_leader(task))
+       if (tgid == 0)
                goto out;
 
        name.name = buf;
-       name.len = snprintf(buf, sizeof(buf), "%d", task->tgid);
-       leader = d_hash_and_lookup(proc_mnt->mnt_root, &name);
+       name.len = snprintf(buf, sizeof(buf), "%d", tgid);
+       leader = d_hash_and_lookup(mnt->mnt_root, &name);
        if (!leader)
                goto out;
 
@@ -2224,7 +2236,7 @@ void proc_flush_task(struct task_struct *task)
                goto out_put_leader;
 
        name.name = buf;
-       name.len = snprintf(buf, sizeof(buf), "%d", task->pid);
+       name.len = snprintf(buf, sizeof(buf), "%d", pid);
        dentry = d_hash_and_lookup(dir, &name);
        if (dentry) {
                shrink_dcache_parent(dentry);
@@ -2239,6 +2251,36 @@ out:
        return;
 }
 
+/*
+ * when flushing dentries from proc one need to flush them from global
+ * proc (proc_mnt) and from all the namespaces' procs this task was seen
+ * in. this call is supposed to make all this job.
+ */
+
+void proc_flush_task(struct task_struct *task)
+{
+       int i, leader;
+       struct pid *pid, *tgid;
+       struct upid *upid;
+
+       leader = thread_group_leader(task);
+       proc_flush_task_mnt(proc_mnt, task->pid, leader ? task->tgid : 0);
+       pid = task_pid(task);
+       if (pid->level == 0)
+               return;
+
+       tgid = task_tgid(task);
+       for (i = 1; i <= pid->level; i++) {
+               upid = &pid->numbers[i];
+               proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr,
+                               leader ? 0 : tgid->numbers[i].nr);
+       }
+
+       upid = &pid->numbers[pid->level];
+       if (upid->nr == 1)
+               pid_ns_release_proc(upid->ns);
+}
+
 static struct dentry *proc_pid_instantiate(struct inode *dir,
                                           struct dentry * dentry,
                                           struct task_struct *task, const void *ptr)
@@ -2309,7 +2351,7 @@ static struct task_struct *next_tgid(unsigned int tgid)
        rcu_read_lock();
 retry:
        task = NULL;
-       pid = find_ge_pid(tgid);
+       pid = find_ge_pid(tgid, &init_pid_ns);
        if (pid) {
                tgid = pid->nr + 1;
                task = pid_task(pid, PIDTYPE_PID);
@@ -2416,8 +2458,11 @@ static const struct pid_entry tid_base_stuff[] = {
 #ifdef CONFIG_SCHEDSTATS
        INF("schedstat", S_IRUGO, pid_schedstat),
 #endif
-#ifdef CONFIG_CPUSETS
+#ifdef CONFIG_PROC_PID_CPUSET
        REG("cpuset",    S_IRUGO, cpuset),
+#endif
+#ifdef CONFIG_CGROUPS
+       REG("cgroup",  S_IRUGO, cgroup),
 #endif
        INF("oom_score", S_IRUGO, oom_score),
        REG("oom_adj",   S_IRUGO|S_IWUSR, oom_adjust),