[PATCH] pidspace: is_init()

This is an updated version of Eric Biederman's is_init() patch.
(http://lkml.org/lkml/2006/2/6/280).  It applies cleanly to 2.6.18-rc3 and
replaces a few more instances of ->pid == 1 with is_init().

Further, is_init() checks pid and thus removes dependency on Eric's other
patches for now.

Eric's original description:

	There are a lot of places in the kernel where we test for init
	because we give it special properties.  Most  significantly init
	must not die.  This results in code all over the kernel test
	->pid == 1.

	Introduce is_init to capture this case.

	With multiple pid spaces for all of the cases affected we are
	looking for only the first process on the system, not some other
	process that has pid == 1.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: <lxc-devel@lists.sourceforge.net>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/alpha/mm/fault.c

@@ -193,7 +193,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr,
 	/* We ran out of memory, or some other thing happened to us that
 	   made us unable to handle the page fault gracefully.  */
  out_of_memory:
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/arm/mm/fault.c

@@ -198,7 +198,7 @@ survive:
 		return fault;
 	}
 
-	if (tsk->pid != 1)
+	if (!is_init(tsk))
 		goto out;
 
 	/*

arch/arm26/mm/fault.c

@@ -185,7 +185,7 @@ survive:
 	}
 
 	fault = -3; /* out of memory */
-	if (tsk->pid != 1)
+	if (!is_init(tsk))
 		goto out;
 
 	/*

arch/i386/lib/usercopy.c

@@ -739,7 +739,7 @@ survive:
 			retval = get_user_pages(current, current->mm,
 					(unsigned long )to, 1, 1, 0, &pg, NULL);
 
-			if (retval == -ENOMEM && current->pid == 1) {
+			if (retval == -ENOMEM && is_init(current)) {
 				up_read(&current->mm->mmap_sem);
 				blk_congestion_wait(WRITE, HZ/50);
 				goto survive;

arch/i386/mm/fault.c

@@ -589,7 +589,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (tsk->pid == 1) {
+	if (is_init(tsk)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/ia64/mm/fault.c

@@ -280,7 +280,7 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 
   out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/m32r/mm/fault.c

@@ -299,7 +299,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (tsk->pid == 1) {
+	if (is_init(tsk)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/m68k/mm/fault.c

@@ -181,7 +181,7 @@ good_area:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/mips/mm/fault.c

@@ -171,7 +171,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (tsk->pid == 1) {
+	if (is_init(tsk)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/powerpc/mm/fault.c

@@ -386,7 +386,7 @@ bad_area_nosemaphore:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/powerpc/platforms/pseries/ras.c

@@ -337,7 +337,7 @@ static int recover_mce(struct pt_regs *regs, struct rtas_error_log * err)
 		   err->disposition == RTAS_DISP_NOT_RECOVERED &&
 		   err->target == RTAS_TARGET_MEMORY &&
 		   err->type == RTAS_TYPE_ECC_UNCORR &&
-		   !(current->pid == 0 || current->pid == 1)) {
+		   !(current->pid == 0 || is_init(current))) {
 		/* Kill off a user process with an ECC error */
 		printk(KERN_ERR "MCE: uncorrectable ecc error for pid %d\n",
 		       current->pid);

arch/ppc/kernel/traps.c

@@ -119,7 +119,7 @@ void _exception(int signr, struct pt_regs *regs, int code, unsigned long addr)
 	 * generate the same exception over and over again and we get
 	 * nowhere.  Better to kill it and let the kernel panic.
 	 */
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		__sighandler_t handler;
 
 		spin_lock_irq(&current->sighand->siglock);

arch/ppc/mm/fault.c

@@ -291,7 +291,7 @@ bad_area:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/s390/mm/fault.c

@@ -353,7 +353,7 @@ no_context:
 */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (tsk->pid == 1) {
+	if (is_init(tsk)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/sh/mm/fault.c

@@ -149,7 +149,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/sh64/mm/fault.c

@@ -277,7 +277,7 @@ bad_area:
 			show_regs(regs);
 #endif
 		}
-		if (tsk->pid == 1) {
+		if (is_init(tsk)) {
 			panic("INIT had user mode bad_area\n");
 		}
 		tsk->thread.address = address;
@@ -319,14 +319,14 @@ no_context:
  * us unable to handle the page fault gracefully.
  */
 out_of_memory:
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		panic("INIT out of memory\n");
 		yield();
 		goto survive;
 	}
 	printk("fault:Out of memory\n");
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

arch/um/kernel/trap.c

@@ -120,7 +120,7 @@ out_nosemaphore:
  * us unable to handle the page fault gracefully.
  */
 out_of_memory:
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		up_read(&mm->mmap_sem);
 		yield();
 		down_read(&mm->mmap_sem);

arch/x86_64/mm/fault.c

@@ -244,7 +244,7 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 
 int unhandled_signal(struct task_struct *tsk, int sig)
 {
-	if (tsk->pid == 1)
+	if (is_init(tsk))
 		return 1;
 	if (tsk->ptrace & PT_PTRACED)
 		return 0;
@@ -580,7 +580,7 @@ no_context:
  */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) { 
+	if (is_init(current)) {
 		yield();
 		goto again;
 	}

arch/xtensa/mm/fault.c

@@ -144,7 +144,7 @@ bad_area:
 	 */
 out_of_memory:
 	up_read(&mm->mmap_sem);
-	if (current->pid == 1) {
+	if (is_init(current)) {
 		yield();
 		down_read(&mm->mmap_sem);
 		goto survive;

drivers/char/sysrq.c

@@ -208,7 +208,7 @@ static void send_sig_all(int sig)
 	struct task_struct *p;
 
 	for_each_process(p) {
-		if (p->mm && p->pid != 1)
+		if (p->mm && !is_init(p))
 			/* Not swapper, init nor kernel thread */
 			force_sig(sig, p);
 	}

include/linux/sched.h

@@ -1033,6 +1033,16 @@ static inline int pid_alive(struct task_struct *p)
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
 
+/**
+ * is_init - check if a task structure is the first user space
+ *	     task the kernel created.
+ * @p: Task structure to be checked.
+ */
+static inline int is_init(struct task_struct *tsk)
+{
+	return tsk->pid == 1;
+}
+
 extern void free_task(struct task_struct *tsk);
 #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
 

kernel/capability.c

@@ -133,7 +133,7 @@ static inline int cap_set_all(kernel_cap_t *effective,
      int found = 0;
 
      do_each_thread(g, target) {
-             if (target == current || target->pid == 1)
+             if (target == current || is_init(target))
                      continue;
              found = 1;
 	     if (security_capset_check(target, effective, inheritable,

kernel/cpuset.c

@@ -240,7 +240,7 @@ static struct super_block *cpuset_sb;
  * A cpuset can only be deleted if both its 'count' of using tasks
  * is zero, and its list of 'children' cpusets is empty.  Since all
  * tasks in the system use _some_ cpuset, and since there is always at
- * least one task in the system (init, pid == 1), therefore, top_cpuset
+ * least one task in the system (init), therefore, top_cpuset
  * always has either children cpusets and/or using tasks.  So we don't
  * need a special hack to ensure that top_cpuset cannot be deleted.
  *

kernel/exit.c

@@ -219,7 +219,7 @@ static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task)
 	do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
 		if (p == ignored_task
 				|| p->exit_state
-				|| p->real_parent->pid == 1)
+				|| is_init(p->real_parent))
 			continue;
 		if (process_group(p->real_parent) != pgrp
 			    && p->real_parent->signal->session == p->signal->session) {

kernel/kexec.c

@@ -40,7 +40,7 @@ struct resource crashk_res = {
 
 int kexec_should_crash(struct task_struct *p)
 {
-	if (in_interrupt() || !p->pid || p->pid == 1 || panic_on_oops)
+	if (in_interrupt() || !p->pid || is_init(p) || panic_on_oops)
 		return 1;
 	return 0;
 }

kernel/ptrace.c

@@ -440,6 +440,7 @@ struct task_struct *ptrace_get_task_struct(pid_t pid)
 	child = find_task_by_pid(pid);
 	if (child)
 		get_task_struct(child);
+
 	read_unlock(&tasklist_lock);
 	if (!child)
 		return ERR_PTR(-ESRCH);

kernel/sysctl.c

@@ -1915,7 +1915,7 @@ int proc_dointvec_bset(ctl_table *table, int write, struct file *filp,
 		return -EPERM;
 	}
 
-	op = (current->pid == 1) ? OP_SET : OP_AND;
+	op = is_init(current) ? OP_SET : OP_AND;
 	return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
 				do_proc_dointvec_bset_conv,&op);
 }

mm/oom_kill.c

@@ -255,7 +255,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints)
  */
 static void __oom_kill_task(struct task_struct *p, const char *message)
 {
-	if (p->pid == 1) {
+	if (is_init(p)) {
 		WARN_ON(1);
 		printk(KERN_WARNING "tried to kill init!\n");
 		return;

security/commoncap.c

@@ -169,7 +169,7 @@ void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
 	/* For init, we want to retain the capabilities set
 	 * in the init_task struct. Thus we skip the usual
 	 * capability rules */
-	if (current->pid != 1) {
+	if (!is_init(current)) {
 		current->cap_permitted = new_permitted;
 		current->cap_effective =
 		    cap_intersect (new_permitted, bprm->cap_effective);