![Oleg Nesterov](/assets/img/avatar_default.png)
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>
255 lines
6.5 KiB
C
255 lines
6.5 KiB
C
/*
|
|
* Generic pidhash and scalable, time-bounded PID allocator
|
|
*
|
|
* (C) 2002-2003 William Irwin, IBM
|
|
* (C) 2004 William Irwin, Oracle
|
|
* (C) 2002-2004 Ingo Molnar, Red Hat
|
|
*
|
|
* pid-structures are backing objects for tasks sharing a given ID to chain
|
|
* against. There is very little to them aside from hashing them and
|
|
* parking tasks using given ID's on a list.
|
|
*
|
|
* The hash is always changed with the tasklist_lock write-acquired,
|
|
* and the hash is only accessed with the tasklist_lock at least
|
|
* read-acquired, so there's no additional SMP locking needed here.
|
|
*
|
|
* We have a list of bitmap pages, which bitmaps represent the PID space.
|
|
* Allocating and freeing PIDs is completely lockless. The worst-case
|
|
* allocation scenario when all but one out of 1 million PIDs possible are
|
|
* allocated already: the scanning of 32 list entries and at most PAGE_SIZE
|
|
* bytes. The typical fastpath is a single successful setbit. Freeing is O(1).
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/hash.h>
|
|
|
|
#define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift)
|
|
static struct hlist_head *pid_hash[PIDTYPE_MAX];
|
|
static int pidhash_shift;
|
|
|
|
int pid_max = PID_MAX_DEFAULT;
|
|
int last_pid;
|
|
|
|
#define RESERVED_PIDS 300
|
|
|
|
int pid_max_min = RESERVED_PIDS + 1;
|
|
int pid_max_max = PID_MAX_LIMIT;
|
|
|
|
#define PIDMAP_ENTRIES ((PID_MAX_LIMIT + 8*PAGE_SIZE - 1)/PAGE_SIZE/8)
|
|
#define BITS_PER_PAGE (PAGE_SIZE*8)
|
|
#define BITS_PER_PAGE_MASK (BITS_PER_PAGE-1)
|
|
#define mk_pid(map, off) (((map) - pidmap_array)*BITS_PER_PAGE + (off))
|
|
#define find_next_offset(map, off) \
|
|
find_next_zero_bit((map)->page, BITS_PER_PAGE, off)
|
|
|
|
/*
|
|
* PID-map pages start out as NULL, they get allocated upon
|
|
* first use and are never deallocated. This way a low pid_max
|
|
* value does not cause lots of bitmaps to be allocated, but
|
|
* the scheme scales to up to 4 million PIDs, runtime.
|
|
*/
|
|
typedef struct pidmap {
|
|
atomic_t nr_free;
|
|
void *page;
|
|
} pidmap_t;
|
|
|
|
static pidmap_t pidmap_array[PIDMAP_ENTRIES] =
|
|
{ [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } };
|
|
|
|
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock);
|
|
|
|
fastcall void free_pidmap(int pid)
|
|
{
|
|
pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE;
|
|
int offset = pid & BITS_PER_PAGE_MASK;
|
|
|
|
clear_bit(offset, map->page);
|
|
atomic_inc(&map->nr_free);
|
|
}
|
|
|
|
int alloc_pidmap(void)
|
|
{
|
|
int i, offset, max_scan, pid, last = last_pid;
|
|
pidmap_t *map;
|
|
|
|
pid = last + 1;
|
|
if (pid >= pid_max)
|
|
pid = RESERVED_PIDS;
|
|
offset = pid & BITS_PER_PAGE_MASK;
|
|
map = &pidmap_array[pid/BITS_PER_PAGE];
|
|
max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset;
|
|
for (i = 0; i <= max_scan; ++i) {
|
|
if (unlikely(!map->page)) {
|
|
unsigned long page = get_zeroed_page(GFP_KERNEL);
|
|
/*
|
|
* Free the page if someone raced with us
|
|
* installing it:
|
|
*/
|
|
spin_lock(&pidmap_lock);
|
|
if (map->page)
|
|
free_page(page);
|
|
else
|
|
map->page = (void *)page;
|
|
spin_unlock(&pidmap_lock);
|
|
if (unlikely(!map->page))
|
|
break;
|
|
}
|
|
if (likely(atomic_read(&map->nr_free))) {
|
|
do {
|
|
if (!test_and_set_bit(offset, map->page)) {
|
|
atomic_dec(&map->nr_free);
|
|
last_pid = pid;
|
|
return pid;
|
|
}
|
|
offset = find_next_offset(map, offset);
|
|
pid = mk_pid(map, offset);
|
|
/*
|
|
* find_next_offset() found a bit, the pid from it
|
|
* is in-bounds, and if we fell back to the last
|
|
* bitmap block and the final block was the same
|
|
* as the starting point, pid is before last_pid.
|
|
*/
|
|
} while (offset < BITS_PER_PAGE && pid < pid_max &&
|
|
(i != max_scan || pid < last ||
|
|
!((last+1) & BITS_PER_PAGE_MASK)));
|
|
}
|
|
if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) {
|
|
++map;
|
|
offset = 0;
|
|
} else {
|
|
map = &pidmap_array[0];
|
|
offset = RESERVED_PIDS;
|
|
if (unlikely(last == offset))
|
|
break;
|
|
}
|
|
pid = mk_pid(map, offset);
|
|
}
|
|
return -1;
|
|
}
|
|
|
|
struct pid * fastcall find_pid(enum pid_type type, int nr)
|
|
{
|
|
struct hlist_node *elem;
|
|
struct pid *pid;
|
|
|
|
hlist_for_each_entry_rcu(pid, elem,
|
|
&pid_hash[type][pid_hashfn(nr)], pid_chain) {
|
|
if (pid->nr == nr)
|
|
return pid;
|
|
}
|
|
return NULL;
|
|
}
|
|
|
|
int fastcall attach_pid(task_t *task, enum pid_type type, int nr)
|
|
{
|
|
struct pid *pid, *task_pid;
|
|
|
|
task_pid = &task->pids[type];
|
|
pid = find_pid(type, nr);
|
|
task_pid->nr = nr;
|
|
if (pid == NULL) {
|
|
INIT_LIST_HEAD(&task_pid->pid_list);
|
|
hlist_add_head_rcu(&task_pid->pid_chain,
|
|
&pid_hash[type][pid_hashfn(nr)]);
|
|
} else {
|
|
INIT_HLIST_NODE(&task_pid->pid_chain);
|
|
list_add_tail_rcu(&task_pid->pid_list, &pid->pid_list);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static fastcall int __detach_pid(task_t *task, enum pid_type type)
|
|
{
|
|
struct pid *pid, *pid_next;
|
|
int nr = 0;
|
|
|
|
pid = &task->pids[type];
|
|
if (!hlist_unhashed(&pid->pid_chain)) {
|
|
|
|
if (list_empty(&pid->pid_list)) {
|
|
nr = pid->nr;
|
|
hlist_del_rcu(&pid->pid_chain);
|
|
} else {
|
|
pid_next = list_entry(pid->pid_list.next,
|
|
struct pid, pid_list);
|
|
/* insert next pid from pid_list to hash */
|
|
hlist_replace_rcu(&pid->pid_chain,
|
|
&pid_next->pid_chain);
|
|
}
|
|
}
|
|
|
|
list_del_rcu(&pid->pid_list);
|
|
pid->nr = 0;
|
|
|
|
return nr;
|
|
}
|
|
|
|
void fastcall detach_pid(task_t *task, enum pid_type type)
|
|
{
|
|
int tmp, nr;
|
|
|
|
nr = __detach_pid(task, type);
|
|
if (!nr)
|
|
return;
|
|
|
|
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
|
|
if (tmp != type && find_pid(tmp, nr))
|
|
return;
|
|
|
|
free_pidmap(nr);
|
|
}
|
|
|
|
task_t *find_task_by_pid_type(int type, int nr)
|
|
{
|
|
struct pid *pid;
|
|
|
|
pid = find_pid(type, nr);
|
|
if (!pid)
|
|
return NULL;
|
|
|
|
return pid_task(&pid->pid_list, type);
|
|
}
|
|
|
|
EXPORT_SYMBOL(find_task_by_pid_type);
|
|
|
|
/*
|
|
* The pid hash table is scaled according to the amount of memory in the
|
|
* machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
|
|
* more.
|
|
*/
|
|
void __init pidhash_init(void)
|
|
{
|
|
int i, j, pidhash_size;
|
|
unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT);
|
|
|
|
pidhash_shift = max(4, fls(megabytes * 4));
|
|
pidhash_shift = min(12, pidhash_shift);
|
|
pidhash_size = 1 << pidhash_shift;
|
|
|
|
printk("PID hash table entries: %d (order: %d, %Zd bytes)\n",
|
|
pidhash_size, pidhash_shift,
|
|
PIDTYPE_MAX * pidhash_size * sizeof(struct hlist_head));
|
|
|
|
for (i = 0; i < PIDTYPE_MAX; i++) {
|
|
pid_hash[i] = alloc_bootmem(pidhash_size *
|
|
sizeof(*(pid_hash[i])));
|
|
if (!pid_hash[i])
|
|
panic("Could not alloc pidhash!\n");
|
|
for (j = 0; j < pidhash_size; j++)
|
|
INIT_HLIST_HEAD(&pid_hash[i][j]);
|
|
}
|
|
}
|
|
|
|
void __init pidmap_init(void)
|
|
{
|
|
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);
|
|
}
|