pid namespaces: changes to show virtual ids to user

This is the largest patch in the set. Make all (I hope) the places where
the pid is shown to or get from user operate on the virtual pids.

The idea is:
 - all in-kernel data structures must store either struct pid itself
   or the pid's global nr, obtained with pid_nr() call;
 - when seeking the task from kernel code with the stored id one
   should use find_task_by_pid() call that works with global pids;
 - when showing pid's numerical value to the user the virtual one
   should be used, but however when one shows task's pid outside this
   task's namespace the global one is to be used;
 - when getting the pid from userspace one need to consider this as
   the virtual one and use appropriate task/pid-searching functions.

[[email protected]: build fix]
[[email protected]: nuther build fix]
[[email protected]: yet nuther build fix]
[[email protected]: remove unneeded casts]
Signed-off-by: Pavel Emelyanov <[email protected]>
Signed-off-by: Alexey Dobriyan <[email protected]>
Cc: Sukadev Bhattiprolu <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Paul Menage <[email protected]>
Cc: "Eric W. Biederman" <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: xemul

arch/ia64/kernel/signal.c

@@ -227,7 +227,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
 	si.si_signo = SIGSEGV;
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
-	si.si_pid = current->pid;
+	si.si_pid = task_pid_vnr(current);
 	si.si_uid = current->uid;
 	si.si_addr = sc;
 	force_sig_info(SIGSEGV, &si, current);
@@ -332,7 +332,7 @@ force_sigsegv_info (int sig, void __user *addr)
 	si.si_signo = SIGSEGV;
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
-	si.si_pid = current->pid;
+	si.si_pid = task_pid_vnr(current);
 	si.si_uid = current->uid;
 	si.si_addr = addr;
 	force_sig_info(SIGSEGV, &si, current);

arch/parisc/kernel/signal.c

@@ -181,7 +181,7 @@ sys_rt_sigreturn(struct pt_regs *regs, int in_syscall)
 	si.si_signo = SIGSEGV;
 	si.si_errno = 0;
 	si.si_code = SI_KERNEL;
-	si.si_pid = current->pid;
+	si.si_pid = task_pid_vnr(current);
 	si.si_uid = current->uid;
 	si.si_addr = &frame->uc;
 	force_sig_info(SIGSEGV, &si, current);

arch/sparc/kernel/sys_sunos.c

@@ -866,7 +866,7 @@ asmlinkage int sunos_killpg(int pgrp, int sig)
 	rcu_read_lock();
 	ret = -EINVAL;
 	if (pgrp > 0)
-		ret = kill_pgrp(find_pid(pgrp), sig, 0);
+		ret = kill_pgrp(find_vpid(pgrp), sig, 0);
 	rcu_read_unlock();
 
 	return ret;

arch/sparc64/kernel/sys_sunos32.c

@@ -831,7 +831,7 @@ asmlinkage int sunos_killpg(int pgrp, int sig)
 	rcu_read_lock();
 	ret = -EINVAL;
 	if (pgrp > 0)
-		ret = kill_pgrp(find_pid(pgrp), sig, 0);
+		ret = kill_pgrp(find_vpid(pgrp), sig, 0);
 	rcu_read_unlock();
 
 	return ret;

drivers/char/tty_io.c

@@ -103,6 +103,7 @@
 #include <linux/selection.h>
 
 #include <linux/kmod.h>
+#include <linux/nsproxy.h>
 
 #undef TTY_DEBUG_HANGUP
 
@@ -3107,7 +3108,7 @@ static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
 	 */
 	if (tty == real_tty && current->signal->tty != real_tty)
 		return -ENOTTY;
-	return put_user(pid_nr(real_tty->pgrp), p);
+	return put_user(pid_vnr(real_tty->pgrp), p);
 }
 
 /**
@@ -3141,7 +3142,7 @@ static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t
 	if (pgrp_nr < 0)
 		return -EINVAL;
 	rcu_read_lock();
-	pgrp = find_pid(pgrp_nr);
+	pgrp = find_vpid(pgrp_nr);
 	retval = -ESRCH;
 	if (!pgrp)
 		goto out_unlock;
@@ -3178,7 +3179,7 @@ static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t _
 		return -ENOTTY;
 	if (!real_tty->session)
 		return -ENOTTY;
-	return put_user(pid_nr(real_tty->session), p);
+	return put_user(pid_vnr(real_tty->session), p);
 }
 
 /**

fs/binfmt_elf.c

@@ -1383,10 +1383,10 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 	prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
 	prstatus->pr_sigpend = p->pending.signal.sig[0];
 	prstatus->pr_sighold = p->blocked.sig[0];
-	prstatus->pr_pid = p->pid;
-	prstatus->pr_ppid = p->parent->pid;
-	prstatus->pr_pgrp = task_pgrp_nr(p);
-	prstatus->pr_sid = task_session_nr(p);
+	prstatus->pr_pid = task_pid_vnr(p);
+	prstatus->pr_ppid = task_pid_vnr(p->parent);
+	prstatus->pr_pgrp = task_pgrp_vnr(p);
+	prstatus->pr_sid = task_session_vnr(p);
 	if (thread_group_leader(p)) {
 		/*
 		 * This is the record for the group leader.  Add in the
@@ -1429,10 +1429,10 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 			psinfo->pr_psargs[i] = ' ';
 	psinfo->pr_psargs[len] = 0;
 
-	psinfo->pr_pid = p->pid;
-	psinfo->pr_ppid = p->parent->pid;
-	psinfo->pr_pgrp = task_pgrp_nr(p);
-	psinfo->pr_sid = task_session_nr(p);
+	psinfo->pr_pid = task_pid_vnr(p);
+	psinfo->pr_ppid = task_pid_vnr(p->parent);
+	psinfo->pr_pgrp = task_pgrp_vnr(p);
+	psinfo->pr_sid = task_session_vnr(p);
 
 	i = p->state ? ffz(~p->state) + 1 : 0;
 	psinfo->pr_state = i;

fs/binfmt_elf_fdpic.c

@@ -1342,10 +1342,10 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 	prstatus->pr_info.si_signo = prstatus->pr_cursig = signr;
 	prstatus->pr_sigpend = p->pending.signal.sig[0];
 	prstatus->pr_sighold = p->blocked.sig[0];
-	prstatus->pr_pid = p->pid;
-	prstatus->pr_ppid = p->parent->pid;
-	prstatus->pr_pgrp = task_pgrp_nr(p);
-	prstatus->pr_sid = task_session_nr(p);
+	prstatus->pr_pid = task_pid_vnr(p);
+	prstatus->pr_ppid = task_pid_vnr(p->parent);
+	prstatus->pr_pgrp = task_pgrp_vnr(p);
+	prstatus->pr_sid = task_session_vnr(p);
 	if (thread_group_leader(p)) {
 		/*
 		 * This is the record for the group leader.  Add in the
@@ -1391,10 +1391,10 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
 			psinfo->pr_psargs[i] = ' ';
 	psinfo->pr_psargs[len] = 0;
 
-	psinfo->pr_pid = p->pid;
-	psinfo->pr_ppid = p->parent->pid;
-	psinfo->pr_pgrp = task_pgrp_nr(p);
-	psinfo->pr_sid = task_session_nr(p);
+	psinfo->pr_pid = task_pid_vnr(p);
+	psinfo->pr_ppid = task_pid_vnr(p->parent);
+	psinfo->pr_pgrp = task_pgrp_vnr(p);
+	psinfo->pr_sid = task_session_vnr(p);
 
 	i = p->state ? ffz(~p->state) + 1 : 0;
 	psinfo->pr_state = i;

fs/exec.c

@@ -1433,7 +1433,7 @@ static int format_corename(char *corename, const char *pattern, long signr)
 			case 'p':
 				pid_in_pattern = 1;
 				rc = snprintf(out_ptr, out_end - out_ptr,
-					      "%d", current->tgid);
+					      "%d", task_tgid_vnr(current));
 				if (rc > out_end - out_ptr)
 					goto out;
 				out_ptr += rc;
@@ -1513,7 +1513,7 @@ static int format_corename(char *corename, const char *pattern, long signr)
 	if (!ispipe && !pid_in_pattern
             && (core_uses_pid || atomic_read(&current->mm->mm_users) != 1)) {
 		rc = snprintf(out_ptr, out_end - out_ptr,
-			      ".%d", current->tgid);
+			      ".%d", task_tgid_vnr(current));
 		if (rc > out_end - out_ptr)
 			goto out;
 		out_ptr += rc;

fs/fcntl.c

@@ -18,6 +18,7 @@
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -292,7 +293,7 @@ int f_setown(struct file *filp, unsigned long arg, int force)
 		who = -who;
 	}
 	rcu_read_lock();
-	pid = find_pid(who);
+	pid = find_vpid(who);
 	result = __f_setown(filp, pid, type, force);
 	rcu_read_unlock();
 	return result;
@@ -308,7 +309,7 @@ pid_t f_getown(struct file *filp)
 {
 	pid_t pid;
 	read_lock(&filp->f_owner.lock);
-	pid = pid_nr(filp->f_owner.pid);
+	pid = pid_nr_ns(filp->f_owner.pid, current->nsproxy->pid_ns);
 	if (filp->f_owner.pid_type == PIDTYPE_PGID)
 		pid = -pid;
 	read_unlock(&filp->f_owner.lock);

fs/ioprio.c

@@ -25,6 +25,7 @@
 #include <linux/capability.h>
 #include <linux/syscalls.h>
 #include <linux/security.h>
+#include <linux/pid_namespace.h>
 
 static int set_task_ioprio(struct task_struct *task, int ioprio)
 {
@@ -93,15 +94,16 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 			if (!who)
 				p = current;
 			else
-				p = find_task_by_pid(who);
+				p = find_task_by_pid_ns(who,
+						current->nsproxy->pid_ns);
 			if (p)
 				ret = set_task_ioprio(p, ioprio);
 			break;
 		case IOPRIO_WHO_PGRP:
 			if (!who)
 				pgrp = task_pgrp(current);
 			else
-				pgrp = find_pid(who);
+				pgrp = find_vpid(who);
 			do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
 				ret = set_task_ioprio(p, ioprio);
 				if (ret)
@@ -180,15 +182,16 @@ asmlinkage long sys_ioprio_get(int which, int who)
 			if (!who)
 				p = current;
 			else
-				p = find_task_by_pid(who);
+				p = find_task_by_pid_ns(who,
+						current->nsproxy->pid_ns);
 			if (p)
 				ret = get_task_ioprio(p);
 			break;
 		case IOPRIO_WHO_PGRP:
 			if (!who)
 				pgrp = task_pgrp(current);
 			else
-				pgrp = find_pid(who);
+				pgrp = find_vpid(who);
 			do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
 				tmpio = get_task_ioprio(p);
 				if (tmpio < 0)

fs/proc/array.c

@@ -77,6 +77,7 @@
 #include <linux/cpuset.h>
 #include <linux/rcupdate.h>
 #include <linux/delayacct.h>
+#include <linux/pid_namespace.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -161,8 +162,15 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 	struct group_info *group_info;
 	int g;
 	struct fdtable *fdt = NULL;
+	struct pid_namespace *ns;
+	pid_t ppid, tpid;
 
+	ns = current->nsproxy->pid_ns;
 	rcu_read_lock();
+	ppid = pid_alive(p) ?
+		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
+	tpid = pid_alive(p) && p->ptrace ?
+		task_ppid_nr_ns(rcu_dereference(p->parent), ns) : 0;
 	buffer += sprintf(buffer,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
@@ -172,9 +180,9 @@ static inline char *task_state(struct task_struct *p, char *buffer)
 		"Uid:\t%d\t%d\t%d\t%d\n"
 		"Gid:\t%d\t%d\t%d\t%d\n",
 		get_task_state(p),
-		p->tgid, p->pid,
-		pid_alive(p) ? rcu_dereference(p->real_parent)->tgid : 0,
-		pid_alive(p) && p->ptrace ? rcu_dereference(p->parent)->pid : 0,
+		task_tgid_nr_ns(p, ns),
+		task_pid_nr_ns(p, ns),
+		ppid, tpid,
 		p->uid, p->euid, p->suid, p->fsuid,
 		p->gid, p->egid, p->sgid, p->fsgid);
 
@@ -394,6 +402,9 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
+	struct pid_namespace *ns;
+
+	ns = current->nsproxy->pid_ns;
 
 	state = *get_task_state(task);
 	vsize = eip = esp = 0;
@@ -416,7 +427,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 		struct signal_struct *sig = task->signal;
 
 		if (sig->tty) {
-			tty_pgrp = pid_nr(sig->tty->pgrp);
+			tty_pgrp = pid_nr_ns(sig->tty->pgrp, ns);
 			tty_nr = new_encode_dev(tty_devnum(sig->tty));
 		}
 
@@ -449,9 +460,9 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 			gtime += cputime_add(gtime, sig->gtime);
 		}
 
-		sid = task_session_nr(task);
-		pgid = task_pgrp_nr(task);
-		ppid = rcu_dereference(task->real_parent)->tgid;
+		sid = task_session_nr_ns(task, ns);
+		pgid = task_pgrp_nr_ns(task, ns);
+		ppid = task_ppid_nr_ns(task, ns);
 
 		unlock_task_sighand(task, &flags);
 	}
@@ -483,7 +494,7 @@ static int do_task_stat(struct task_struct *task, char *buffer, int whole)
 	res = sprintf(buffer, "%d (%s) %c %d %d %d %d %d %u %lu \
 %lu %lu %lu %lu %lu %ld %ld %ld %ld %d 0 %llu %lu %ld %lu %lu %lu %lu %lu \
 %lu %lu %lu %lu %lu %lu %lu %lu %d %d %u %u %llu %lu %ld\n",
-		task->pid,
+		task_pid_nr_ns(task, ns),
 		tcomm,
 		state,
 		ppid,