[PATCH] pidhash: don't count idle threads

fork_idle() does unhash_process() just after copy_process().  Contrary,
boot_cpu's idle thread explicitely registers itself for each pid_type with nr
= 0.

copy_process() already checks p->pid != 0 before process_counts++, I think we
can just skip attach_pid() calls and job control inits for idle threads and
kill unhash_process().  We don't need to cleanup ->proc_dentry in fork_idle()
because with this patch idle threads are never hashed in
kernel/pid.c:pid_hash[].

We don't need to hash pid == 0 in pidmap_init().  free_pidmap() is never
called with pid == 0 arg, so it will never be reused.  So it is still possible
to use pid == 0 in any PIDTYPE_xxx namespace from kernel/pid.c's POV.

However with this patch we don't hash pid == 0 for PIDTYPE_PID case.  We still
have have PIDTYPE_PGID/PIDTYPE_SID entries with pid == 0: /sbin/init and
kernel threads which don't call daemonize().

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

5 files changed, 20 insertions, 46 deletions

diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c
index c8d8d0ac1a7f..511116aebaf7 100644
--- a/arch/um/kernel/smp.c
+++ b/arch/um/kernel/smp.c
@@ -143,7 +143,6 @@ void smp_prepare_cpus(unsigned int maxcpus)
                 idle = idle_thread(cpu);
 
                 init_idle(idle, cpu);
-                unhash_process(idle);
 
                 waittime = 200000000;
                 while (waittime-- && !cpu_isset(cpu, cpu_callin_map))
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1f16fb1fea22..ddc0df7f8bf5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1214,8 +1214,6 @@ static inline int thread_group_empty(task_t *p)
 #define delay_group_leader(p) \
                 (thread_group_leader(p) && !thread_group_empty(p))
 
-extern void unhash_process(struct task_struct *p);
-
 /*
  * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
diff --git a/kernel/exit.c b/kernel/exit.c
index f436a6bd3fb7..a94e1c31131b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -56,8 +56,7 @@ static void __unhash_process(struct task_struct *p)
                 detach_pid(p, PIDTYPE_SID);
 
                 list_del_init(&p->tasks);
-                if (p->pid)
-                        __get_cpu_var(process_counts)--;
+                __get_cpu_var(process_counts)--;
         }
 
         remove_parent(p);
@@ -118,21 +117,6 @@ repeat:
                 goto repeat;
 }
 
-/* we are using it only for SMP init */
-
-void unhash_process(struct task_struct *p)
-{
-        struct dentry *proc_dentry;
-
-        spin_lock(&p->proc_lock);
-        proc_dentry = proc_pid_unhash(p);
-        write_lock_irq(&tasklist_lock);
-        __unhash_process(p);
-        write_unlock_irq(&tasklist_lock);
-        spin_unlock(&p->proc_lock);
-        proc_pid_flush(proc_dentry);
-}
-
 /*
  * This checks not only the pgrp, but falls back on the pid if no
  * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
diff --git a/kernel/fork.c b/kernel/fork.c
index 74c67629ee62..0c32e28cdc5f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1181,25 +1181,26 @@ static task_t *copy_process(unsigned long clone_flags,
          */
         p->ioprio = current->ioprio;
 
-        add_parent(p);
-        if (unlikely(p->ptrace & PT_PTRACED))
-                __ptrace_link(p, current->parent);
-
-        if (thread_group_leader(p)) {
-                p->signal->tty = current->signal->tty;
-                p->signal->pgrp = process_group(current);
-                p->signal->session = current->signal->session;
-                attach_pid(p, PIDTYPE_PGID, process_group(p));
-                attach_pid(p, PIDTYPE_SID, p->signal->session);
-
-                list_add_tail(&p->tasks, &init_task.tasks);
-                if (p->pid)
+        if (likely(p->pid)) {
+                add_parent(p);
+                if (unlikely(p->ptrace & PT_PTRACED))
+                        __ptrace_link(p, current->parent);
+
+                if (thread_group_leader(p)) {
+                        p->signal->tty = current->signal->tty;
+                        p->signal->pgrp = process_group(current);
+                        p->signal->session = current->signal->session;
+                        attach_pid(p, PIDTYPE_PGID, process_group(p));
+                        attach_pid(p, PIDTYPE_SID, p->signal->session);
+
+                        list_add_tail(&p->tasks, &init_task.tasks);
                         __get_cpu_var(process_counts)++;
+                }
+                attach_pid(p, PIDTYPE_TGID, p->tgid);
+                attach_pid(p, PIDTYPE_PID, p->pid);
+                nr_threads++;
         }
-        attach_pid(p, PIDTYPE_TGID, p->tgid);
-        attach_pid(p, PIDTYPE_PID, p->pid);
 
-        nr_threads++;
         total_forks++;
         spin_unlock(&current->sighand->siglock);
         write_unlock_irq(&tasklist_lock);
@@ -1263,7 +1264,7 @@ task_t * __devinit fork_idle(int cpu)
         if (!task)
                 return ERR_PTR(-ENOMEM);
         init_idle(task, cpu);
-        unhash_process(task);
+
         return task;
 }
 
diff --git a/kernel/pid.c b/kernel/pid.c
index 7781d9999058..a9f2dfd006d2 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -247,16 +247,8 @@ void __init pidhash_init(void)
 
 void __init pidmap_init(void)
 {
-        int i;
-
         pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL);
+        /* Reserve PID 0. We never call free_pidmap(0) */
         set_bit(0, pidmap_array->page);
         atomic_dec(&pidmap_array->nr_free);
-
-        /*
-         * Allocate PID 0, and hash it via all PID types:
-         */
-
-        for (i = 0; i < PIDTYPE_MAX; i++)
-                attach_pid(current, i, 0);
 }