1 files changed, 246 insertions, 70 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 19489b0d5554..39a3d7c969c5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -63,16 +63,19 @@
 #include <linux/mm.h>
 #include <linux/rcupdate.h>
 #include <linux/kallsyms.h>
+#include <linux/resource.h>
 #include <linux/module.h>
 #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:
@@ -199,27 +202,6 @@ static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vf
          (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \
          security_ptrace(current,task) == 0))
 
-static int proc_pid_environ(struct task_struct *task, char * buffer)
-{
-        int res = 0;
-        struct mm_struct *mm = get_task_mm(task);
-        if (mm) {
-                unsigned int len;
-
-                res = -ESRCH;
-                if (!ptrace_may_attach(task))
-                        goto out;
-
-                len  = mm->env_end - mm->env_start;
-                if (len > PAGE_SIZE)
-                        len = PAGE_SIZE;
-                res = access_process_vm(task, mm->env_start, buffer, len, 0);
-out:
-                mmput(mm);
-        }
-        return res;
-}
-
 static int proc_pid_cmdline(struct task_struct *task, char * buffer)
 {
         int res = 0;
@@ -304,7 +286,7 @@ static int proc_pid_schedstat(struct task_struct *task, char *buffer)
         return sprintf(buffer, "%llu %llu %lu\n",
                         task->sched_info.cpu_time,
                         task->sched_info.run_delay,
-                        task->sched_info.pcnt);
+                        task->sched_info.pcount);
 }
 #endif
 
@@ -322,6 +304,78 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
         return sprintf(buffer, "%lu\n", points);
 }
 
+struct limit_names {
+        char *name;
+        char *unit;
+};
+
+static const struct limit_names lnames[RLIM_NLIMITS] = {
+        [RLIMIT_CPU] = {"Max cpu time", "ms"},
+        [RLIMIT_FSIZE] = {"Max file size", "bytes"},
+        [RLIMIT_DATA] = {"Max data size", "bytes"},
+        [RLIMIT_STACK] = {"Max stack size", "bytes"},
+        [RLIMIT_CORE] = {"Max core file size", "bytes"},
+        [RLIMIT_RSS] = {"Max resident set", "bytes"},
+        [RLIMIT_NPROC] = {"Max processes", "processes"},
+        [RLIMIT_NOFILE] = {"Max open files", "files"},
+        [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"},
+        [RLIMIT_AS] = {"Max address space", "bytes"},
+        [RLIMIT_LOCKS] = {"Max file locks", "locks"},
+        [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"},
+        [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"},
+        [RLIMIT_NICE] = {"Max nice priority", NULL},
+        [RLIMIT_RTPRIO] = {"Max realtime priority", NULL},
+};
+
+/* Display limits for a process */
+static int proc_pid_limits(struct task_struct *task, char *buffer)
+{
+        unsigned int i;
+        int count = 0;
+        unsigned long flags;
+        char *bufptr = buffer;
+
+        struct rlimit rlim[RLIM_NLIMITS];
+
+        rcu_read_lock();
+        if (!lock_task_sighand(task,&flags)) {
+                rcu_read_unlock();
+                return 0;
+        }
+        memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS);
+        unlock_task_sighand(task, &flags);
+        rcu_read_unlock();
+
+        /*
+         * print the file header
+         */
+        count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n",
+                        "Limit", "Soft Limit", "Hard Limit", "Units");
+
+        for (i = 0; i < RLIM_NLIMITS; i++) {
+                if (rlim[i].rlim_cur == RLIM_INFINITY)
+                        count += sprintf(&bufptr[count], "%-25s %-20s ",
+                                         lnames[i].name, "unlimited");
+                else
+                        count += sprintf(&bufptr[count], "%-25s %-20lu ",
+                                         lnames[i].name, rlim[i].rlim_cur);
+
+                if (rlim[i].rlim_max == RLIM_INFINITY)
+                        count += sprintf(&bufptr[count], "%-20s ", "unlimited");
+                else
+                        count += sprintf(&bufptr[count], "%-20lu ",
+                                         rlim[i].rlim_max);
+
+                if (lnames[i].unit)
+                        count += sprintf(&bufptr[count], "%-10s\n",
+                                         lnames[i].unit);
+                else
+                        count += sprintf(&bufptr[count], "\n");
+        }
+
+        return count;
+}
+
 /************************************************************************/
 /*                       Here the fs part begins                        */
 /************************************************************************/
@@ -370,18 +424,21 @@ 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);
         }
 
@@ -444,16 +501,20 @@ 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);
                 }
 
@@ -492,7 +553,7 @@ static ssize_t proc_info_read(struct file * file, char __user * buf,
                 count = PROC_BLOCK_SIZE;
 
         length = -ENOMEM;
-        if (!(page = __get_free_page(GFP_KERNEL)))
+        if (!(page = __get_free_page(GFP_TEMPORARY)))
                 goto out;
 
         length = PROC_I(inode)->op.proc_read(task, (char*)page);
@@ -532,7 +593,7 @@ static ssize_t mem_read(struct file * file, char __user * buf,
                 goto out;
 
         ret = -ENOMEM;
-        page = (char *)__get_free_page(GFP_USER);
+        page = (char *)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 goto out;
 
@@ -602,7 +663,7 @@ static ssize_t mem_write(struct file * file, const char __user *buf,
                 goto out;
 
         copied = -ENOMEM;
-        page = (char *)__get_free_page(GFP_USER);
+        page = (char *)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 goto out;
 
@@ -658,6 +719,76 @@ static const struct file_operations proc_mem_operations = {
         .open           = mem_open,
 };
 
+static ssize_t environ_read(struct file *file, char __user *buf,
+                        size_t count, loff_t *ppos)
+{
+        struct task_struct *task = get_proc_task(file->f_dentry->d_inode);
+        char *page;
+        unsigned long src = *ppos;
+        int ret = -ESRCH;
+        struct mm_struct *mm;
+
+        if (!task)
+                goto out_no_task;
+
+        if (!ptrace_may_attach(task))
+                goto out;
+
+        ret = -ENOMEM;
+        page = (char *)__get_free_page(GFP_TEMPORARY);
+        if (!page)
+                goto out;
+
+        ret = 0;
+
+        mm = get_task_mm(task);
+        if (!mm)
+                goto out_free;
+
+        while (count > 0) {
+                int this_len, retval, max_len;
+
+                this_len = mm->env_end - (mm->env_start + src);
+
+                if (this_len <= 0)
+                        break;
+
+                max_len = (count > PAGE_SIZE) ? PAGE_SIZE : count;
+                this_len = (this_len > max_len) ? max_len : this_len;
+
+                retval = access_process_vm(task, (mm->env_start + src),
+                        page, this_len, 0);
+
+                if (retval <= 0) {
+                        ret = retval;
+                        break;
+                }
+
+                if (copy_to_user(buf, page, retval)) {
+                        ret = -EFAULT;
+                        break;
+                }
+
+                ret += retval;
+                src += retval;
+                buf += retval;
+                count -= retval;
+        }
+        *ppos = src;
+
+        mmput(mm);
+out_free:
+        free_page((unsigned long) page);
+out:
+        put_task_struct(task);
+out_no_task:
+        return ret;
+}
+
+static const struct file_operations proc_environ_operations = {
+        .read           = environ_read,
+};
+
 static ssize_t oom_adjust_read(struct file *file, char __user *buf,
                                 size_t count, loff_t *ppos)
 {
@@ -788,7 +919,7 @@ static ssize_t proc_loginuid_write(struct file * file, const char __user * buf,
                 /* No partial writes. */
                 return -EINVAL;
         }
-        page = (char*)__get_free_page(GFP_USER);
+        page = (char*)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 return -ENOMEM;
         length = -EFAULT;
@@ -954,7 +1085,8 @@ static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt,
                             char __user *buffer, int buflen)
 {
         struct inode * inode;
-        char *tmp = (char*)__get_free_page(GFP_KERNEL), *path;
+        char *tmp = (char*)__get_free_page(GFP_TEMPORARY);
+        char *path;
         int len;
 
         if (!tmp)
@@ -1387,7 +1519,7 @@ static int proc_readfd_common(struct file * filp, void * dirent,
         struct dentry *dentry = filp->f_path.dentry;
         struct inode *inode = dentry->d_inode;
         struct task_struct *p = get_proc_task(inode);
-        unsigned int fd, tid, ino;
+        unsigned int fd, ino;
         int retval;
         struct files_struct * files;
         struct fdtable *fdt;
@@ -1396,7 +1528,6 @@ static int proc_readfd_common(struct file * filp, void * dirent,
         if (!p)
                 goto out_no_task;
         retval = 0;
-        tid = p->pid;
 
         fd = filp->f_pos;
         switch (fd) {
@@ -1631,7 +1762,6 @@ static int proc_pident_readdir(struct file *filp,
                 const struct pid_entry *ents, unsigned int nents)
 {
         int i;
-        int pid;
         struct dentry *dentry = filp->f_path.dentry;
         struct inode *inode = dentry->d_inode;
         struct task_struct *task = get_proc_task(inode);
@@ -1644,7 +1774,6 @@ static int proc_pident_readdir(struct file *filp,
                 goto out_no_task;
 
         ret = 0;
-        pid = task->pid;
         i = filp->f_pos;
         switch (i) {
         case 0:
@@ -1726,7 +1855,7 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
                 goto out;
 
         length = -ENOMEM;
-        page = (char*)__get_free_page(GFP_USER);
+        page = (char*)__get_free_page(GFP_TEMPORARY);
         if (!page)
                 goto out;
 
@@ -1878,14 +2007,14 @@ static int proc_self_readlink(struct dentry *dentry, char __user *buffer,
                               int buflen)
 {
         char tmp[PROC_NUMBUF];
-        sprintf(tmp, "%d", current->tgid);
+        sprintf(tmp, "%d", task_tgid_vnr(current));
         return vfs_readlink(dentry,buffer,buflen,tmp);
 }
 
 static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
         char tmp[PROC_NUMBUF];
-        sprintf(tmp, "%d", current->tgid);
+        sprintf(tmp, "%d", task_tgid_vnr(current));
         return ERR_PTR(vfs_follow_link(nd,tmp));
 }
 
@@ -2048,9 +2177,10 @@ static const struct pid_entry tgid_base_stuff[] = {
         DIR("task",       S_IRUGO|S_IXUGO, task),
         DIR("fd",         S_IRUSR|S_IXUSR, fd),
         DIR("fdinfo",     S_IRUSR|S_IXUSR, fdinfo),
-        INF("environ",    S_IRUSR, pid_environ),
+        REG("environ",    S_IRUSR, environ),
         INF("auxv",       S_IRUSR, pid_auxv),
         INF("status",     S_IRUGO, pid_status),
+        INF("limits",     S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",      S_IRUGO|S_IWUSR, pid_sched),
 #endif
@@ -2080,9 +2210,12 @@ 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),
 #ifdef CONFIG_AUDITSYSCALL
@@ -2143,27 +2276,27 @@ 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;
 
@@ -2174,7 +2307,7 @@ 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);
@@ -2189,6 +2322,36 @@ 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)
@@ -2224,6 +2387,7 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct
         struct dentry *result = ERR_PTR(-ENOENT);
         struct task_struct *task;
         unsigned tgid;
+        struct pid_namespace *ns;
 
         result = proc_base_lookup(dir, dentry);
         if (!IS_ERR(result) || PTR_ERR(result) != -ENOENT)
@@ -2233,8 +2397,9 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct
         if (tgid == ~0U)
                 goto out;
 
+        ns = dentry->d_sb->s_fs_info;
         rcu_read_lock();
-        task = find_task_by_pid(tgid);
+        task = find_task_by_pid_ns(tgid, ns);
         if (task)
                 get_task_struct(task);
         rcu_read_unlock();
@@ -2251,7 +2416,8 @@ out:
  * Find the first task with tgid >= tgid
  *
  */
-static struct task_struct *next_tgid(unsigned int tgid)
+static struct task_struct *next_tgid(unsigned int tgid,
+                struct pid_namespace *ns)
 {
         struct task_struct *task;
         struct pid *pid;
@@ -2259,9 +2425,9 @@ 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, ns);
         if (pid) {
-                tgid = pid->nr + 1;
+                tgid = pid_nr_ns(pid, ns) + 1;
                 task = pid_task(pid, PIDTYPE_PID);
                 /* What we to know is if the pid we have find is the
                  * pid of a thread_group_leader.  Testing for task
@@ -2301,6 +2467,7 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
         struct task_struct *reaper = get_proc_task(filp->f_path.dentry->d_inode);
         struct task_struct *task;
         int tgid;
+        struct pid_namespace *ns;
 
         if (!reaper)
                 goto out_no_task;
@@ -2311,11 +2478,12 @@ int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
                         goto out;
         }
 
+        ns = filp->f_dentry->d_sb->s_fs_info;
         tgid = filp->f_pos - TGID_OFFSET;
-        for (task = next_tgid(tgid);
+        for (task = next_tgid(tgid, ns);
              task;
-             put_task_struct(task), task = next_tgid(tgid + 1)) {
-                tgid = task->pid;
+             put_task_struct(task), task = next_tgid(tgid + 1, ns)) {
+                tgid = task_pid_nr_ns(task, ns);
                 filp->f_pos = tgid + TGID_OFFSET;
                 if (proc_pid_fill_cache(filp, dirent, filldir, task, tgid) < 0) {
                         put_task_struct(task);
@@ -2335,9 +2503,10 @@ out_no_task:
 static const struct pid_entry tid_base_stuff[] = {
         DIR("fd",        S_IRUSR|S_IXUSR, fd),
         DIR("fdinfo",    S_IRUSR|S_IXUSR, fdinfo),
-        INF("environ",   S_IRUSR, pid_environ),
+        REG("environ",   S_IRUSR, environ),
         INF("auxv",      S_IRUSR, pid_auxv),
         INF("status",    S_IRUGO, pid_status),
+        INF("limits",    S_IRUSR, pid_limits),
 #ifdef CONFIG_SCHED_DEBUG
         REG("sched",     S_IRUGO|S_IWUSR, pid_sched),
 #endif
@@ -2366,9 +2535,12 @@ 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),
 #ifdef CONFIG_AUDITSYSCALL
@@ -2436,6 +2608,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
         struct task_struct *task;
         struct task_struct *leader = get_proc_task(dir);
         unsigned tid;
+        struct pid_namespace *ns;
 
         if (!leader)
                 goto out_no_task;
@@ -2444,14 +2617,15 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
         if (tid == ~0U)
                 goto out;
 
+        ns = dentry->d_sb->s_fs_info;
         rcu_read_lock();
-        task = find_task_by_pid(tid);
+        task = find_task_by_pid_ns(tid, ns);
         if (task)
                 get_task_struct(task);
         rcu_read_unlock();
         if (!task)
                 goto out;
-        if (leader->tgid != task->tgid)
+        if (!same_thread_group(leader, task))
                 goto out_drop_task;
 
         result = proc_task_instantiate(dir, dentry, task, NULL);
@@ -2476,14 +2650,14 @@ out_no_task:
  * threads past it.
  */
 static struct task_struct *first_tid(struct task_struct *leader,
-                                        int tid, int nr)
+                int tid, int nr, struct pid_namespace *ns)
 {
         struct task_struct *pos;
 
         rcu_read_lock();
         /* Attempt to start with the pid of a thread */
         if (tid && (nr > 0)) {
-                pos = find_task_by_pid(tid);
+                pos = find_task_by_pid_ns(tid, ns);
                 if (pos && (pos->group_leader == leader))
                         goto found;
         }
@@ -2552,6 +2726,7 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
         ino_t ino;
         int tid;
         unsigned long pos = filp->f_pos;  /* avoiding "long long" filp->f_pos */
+        struct pid_namespace *ns;
 
         task = get_proc_task(inode);
         if (!task)
@@ -2585,16 +2760,17 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
         /* f_version caches the tgid value that the last readdir call couldn't
          * return. lseek aka telldir automagically resets f_version to 0.
          */
-        tid = filp->f_version;
+        ns = filp->f_dentry->d_sb->s_fs_info;
+        tid = (int)filp->f_version;
         filp->f_version = 0;
-        for (task = first_tid(leader, tid, pos - 2);
+        for (task = first_tid(leader, tid, pos - 2, ns);
              task;
              task = next_tid(task), pos++) {
-                tid = task->pid;
+                tid = task_pid_nr_ns(task, ns);
                 if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) {
                         /* returning this tgid failed, save it as the first
                          * pid for the next readir call */
-                        filp->f_version = tid;
+                        filp->f_version = (u64)tid;
                         put_task_struct(task);
                         break;
                 }