X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=kernel%2Fpid.c;h=07c5d91e1ab30aa80e9ac3c4833946bf185440b2;hb=refs%2Fheads%2Fvserver;hp=a864bf8a4535887977d8f4db81a63b55d326b5e7;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/kernel/pid.c b/kernel/pid.c index a864bf8a4..07c5d91e1 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -26,24 +26,30 @@ #include #include #include -#include +#include +#include #define pid_hashfn(nr) hash_long((unsigned long)nr, pidhash_shift) -static struct hlist_head *pid_hash[PIDTYPE_MAX]; +static struct hlist_head *pid_hash; static int pidhash_shift; +static struct kmem_cache *pid_cachep; 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)) + +static inline int mk_pid(struct pid_namespace *pid_ns, + struct pidmap *map, int off) +{ + return (map - pid_ns->pidmap)*BITS_PER_PAGE + off; +} + #define find_next_offset(map, off) \ find_next_zero_bit((map)->page, BITS_PER_PAGE, off) @@ -53,49 +59,66 @@ int pid_max_max = PID_MAX_LIMIT; * 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; +struct pid_namespace init_pid_ns = { + .kref = { + .refcount = ATOMIC_INIT(2), + }, + .pidmap = { + [ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } + }, + .last_pid = 0, + .child_reaper = &init_task +}; -static pidmap_t pidmap_array[PIDMAP_ENTRIES] = - { [ 0 ... PIDMAP_ENTRIES-1 ] = { ATOMIC_INIT(BITS_PER_PAGE), NULL } }; +/* + * Note: disable interrupts while the pidmap_lock is held as an + * interrupt might come in and do read_lock(&tasklist_lock). + * + * If we don't disable interrupts there is a nasty deadlock between + * detach_pid()->free_pid() and another cpu that does + * spin_lock(&pidmap_lock) followed by an interrupt routine that does + * read_lock(&tasklist_lock); + * + * After we clean up the tasklist_lock and know there are no + * irq handlers that take it we can leave the interrupts enabled. + * For now it is easier to be safe than to prove it can't happen. + */ static __cacheline_aligned_in_smp DEFINE_SPINLOCK(pidmap_lock); -fastcall void free_pidmap(int pid) +static fastcall void free_pidmap(struct pid_namespace *pid_ns, int pid) { - pidmap_t *map = pidmap_array + pid / BITS_PER_PAGE; + struct pidmap *map = pid_ns->pidmap + 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) +static int alloc_pidmap(struct pid_namespace *pid_ns) { - int i, offset, max_scan, pid, last = last_pid; - pidmap_t *map; + int i, offset, max_scan, pid, last = pid_ns->last_pid; + struct pidmap *map; pid = last + 1; if (pid >= pid_max) pid = RESERVED_PIDS; offset = pid & BITS_PER_PAGE_MASK; - map = &pidmap_array[pid/BITS_PER_PAGE]; + map = &pid_ns->pidmap[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); + void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); /* * Free the page if someone raced with us * installing it: */ - spin_lock(&pidmap_lock); + spin_lock_irq(&pidmap_lock); if (map->page) - free_page(page); + kfree(page); else - map->page = (void *)page; - spin_unlock(&pidmap_lock); + map->page = page; + spin_unlock_irq(&pidmap_lock); if (unlikely(!map->page)) break; } @@ -103,11 +126,11 @@ int alloc_pidmap(void) do { if (!test_and_set_bit(offset, map->page)) { atomic_dec(&map->nr_free); - last_pid = pid; + pid_ns->last_pid = pid; return pid; } offset = find_next_offset(map, offset); - pid = mk_pid(map, offset); + pid = mk_pid(pid_ns, map, offset); /* * find_next_offset() found a bit, the pid from it * is in-bounds, and if we fell back to the last @@ -118,139 +141,257 @@ int alloc_pidmap(void) (i != max_scan || pid < last || !((last+1) & BITS_PER_PAGE_MASK))); } - if (map < &pidmap_array[(pid_max-1)/BITS_PER_PAGE]) { + if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) { ++map; offset = 0; } else { - map = &pidmap_array[0]; + map = &pid_ns->pidmap[0]; offset = RESERVED_PIDS; if (unlikely(last == offset)) break; } - pid = mk_pid(map, offset); + pid = mk_pid(pid_ns, map, offset); + } + return -1; +} + +static int next_pidmap(struct pid_namespace *pid_ns, int last) +{ + int offset; + struct pidmap *map, *end; + + offset = (last + 1) & BITS_PER_PAGE_MASK; + map = &pid_ns->pidmap[(last + 1)/BITS_PER_PAGE]; + end = &pid_ns->pidmap[PIDMAP_ENTRIES]; + for (; map < end; map++, offset = 0) { + if (unlikely(!map->page)) + continue; + offset = find_next_bit((map)->page, BITS_PER_PAGE, offset); + if (offset < BITS_PER_PAGE) + return mk_pid(pid_ns, map, offset); } return -1; } -struct pid * fastcall find_pid(enum pid_type type, int nr) +fastcall void put_pid(struct pid *pid) +{ + if (!pid) + return; + if ((atomic_read(&pid->count) == 1) || + atomic_dec_and_test(&pid->count)) + kmem_cache_free(pid_cachep, pid); +} +EXPORT_SYMBOL_GPL(put_pid); + +static void delayed_put_pid(struct rcu_head *rhp) +{ + struct pid *pid = container_of(rhp, struct pid, rcu); + put_pid(pid); +} + +fastcall void free_pid(struct pid *pid) +{ + /* We can be called with write_lock_irq(&tasklist_lock) held */ + unsigned long flags; + + spin_lock_irqsave(&pidmap_lock, flags); + hlist_del_rcu(&pid->pid_chain); + spin_unlock_irqrestore(&pidmap_lock, flags); + + free_pidmap(&init_pid_ns, pid->nr); + call_rcu(&pid->rcu, delayed_put_pid); +} + +struct pid *alloc_pid(void) +{ + struct pid *pid; + enum pid_type type; + int nr = -1; + + pid = kmem_cache_alloc(pid_cachep, GFP_KERNEL); + if (!pid) + goto out; + + nr = alloc_pidmap(current->nsproxy->pid_ns); + if (nr < 0) + goto out_free; + + atomic_set(&pid->count, 1); + pid->nr = nr; + for (type = 0; type < PIDTYPE_MAX; ++type) + INIT_HLIST_HEAD(&pid->tasks[type]); + + spin_lock_irq(&pidmap_lock); + hlist_add_head_rcu(&pid->pid_chain, &pid_hash[pid_hashfn(pid->nr)]); + spin_unlock_irq(&pidmap_lock); + +out: + return pid; + +out_free: + kmem_cache_free(pid_cachep, pid); + pid = NULL; + goto out; +} + +struct pid * fastcall find_pid(int nr) { struct hlist_node *elem; struct pid *pid; hlist_for_each_entry_rcu(pid, elem, - &pid_hash[type][pid_hashfn(nr)], pid_chain) { + &pid_hash[pid_hashfn(nr)], pid_chain) { if (pid->nr == nr) return pid; } return NULL; } +EXPORT_SYMBOL_GPL(find_pid); -int fastcall attach_pid(task_t *task, enum pid_type type, int nr) +int fastcall attach_pid(struct task_struct *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); - } + struct pid_link *link; + struct pid *pid; + + link = &task->pids[type]; + link->pid = pid = find_pid(nr); + hlist_add_head_rcu(&link->node, &pid->tasks[type]); return 0; } -static fastcall int __detach_pid(task_t *task, enum pid_type type) +void fastcall detach_pid(struct task_struct *task, enum pid_type type) { - struct pid *pid, *pid_next; - int nr = 0; + struct pid_link *link; + struct pid *pid; + int tmp; - pid = &task->pids[type]; - if (!hlist_unhashed(&pid->pid_chain)) { + link = &task->pids[type]; + pid = link->pid; - 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); - } - } + hlist_del_rcu(&link->node); + link->pid = NULL; - list_del_rcu(&pid->pid_list); - pid->nr = 0; + for (tmp = PIDTYPE_MAX; --tmp >= 0; ) + if (!hlist_empty(&pid->tasks[tmp])) + return; - return nr; + free_pid(pid); } -void fastcall detach_pid(task_t *task, enum pid_type type) +/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */ +void fastcall transfer_pid(struct task_struct *old, struct task_struct *new, + 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); + new->pids[type].pid = old->pids[type].pid; + hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node); + old->pids[type].pid = NULL; } -task_t *find_task_by_pid_type(int type, int nr) +struct task_struct * fastcall pid_task(struct pid *pid, enum pid_type type) { - struct pid *pid; + struct task_struct *result = NULL; if (type == PIDTYPE_REALPID) type = PIDTYPE_PID; - else if (type == PIDTYPE_PID) + if (pid) { + struct hlist_node *first; + first = rcu_dereference(pid->tasks[type].first); + if (first) + result = hlist_entry(first, struct task_struct, pids[(type)].node); + } + return result; +} + +/* + * Must be called under rcu_read_lock() or with tasklist_lock read-held. + */ +struct task_struct *find_task_by_pid_type(int type, int nr) +{ + struct task_struct *task; + + if (type == PIDTYPE_PID) nr = vx_rmap_pid(nr); - pid = find_pid(type, nr); - if (!pid) + task = pid_task(find_pid(nr), type); + if (task && (type != PIDTYPE_REALPID) && + /* maybe VS_WATCH_P in the future? */ + !vx_check(task->xid, VS_WATCH|VS_IDENT)) return NULL; - - return pid_task(&pid->pid_list, type); + return task; } EXPORT_SYMBOL(find_task_by_pid_type); +struct pid *get_task_pid(struct task_struct *task, enum pid_type type) +{ + struct pid *pid; + rcu_read_lock(); + pid = get_pid(task->pids[type].pid); + rcu_read_unlock(); + return pid; +} + +struct task_struct *fastcall get_pid_task(struct pid *pid, enum pid_type type) +{ + struct task_struct *result; + rcu_read_lock(); + result = pid_task(pid, type); + if (result) + get_task_struct(result); + rcu_read_unlock(); + return result; +} + +struct pid *find_get_pid(pid_t nr) +{ + struct pid *pid; + + rcu_read_lock(); + pid = get_pid(find_pid(nr)); + rcu_read_unlock(); + + return pid; +} + /* - * This function switches the PIDs if a non-leader thread calls - * sys_execve() - this must be done without releasing the PID. - * (which a detach_pid() would eventually do.) + * Used by proc to find the first pid that is greater then or equal to nr. + * + * If there is a pid at nr this function is exactly the same as find_pid. */ -void switch_exec_pids(task_t *leader, task_t *thread) +struct pid *find_ge_pid(int nr) { - __detach_pid(leader, PIDTYPE_PID); - __detach_pid(leader, PIDTYPE_TGID); - __detach_pid(leader, PIDTYPE_PGID); - __detach_pid(leader, PIDTYPE_SID); - - __detach_pid(thread, PIDTYPE_PID); - __detach_pid(thread, PIDTYPE_TGID); - - leader->pid = leader->tgid = thread->pid; - thread->pid = thread->tgid; - - attach_pid(thread, PIDTYPE_PID, thread->pid); - attach_pid(thread, PIDTYPE_TGID, thread->tgid); - attach_pid(thread, PIDTYPE_PGID, thread->signal->pgrp); - attach_pid(thread, PIDTYPE_SID, thread->signal->session); - list_add_tail(&thread->tasks, &init_task.tasks); - - attach_pid(leader, PIDTYPE_PID, leader->pid); - attach_pid(leader, PIDTYPE_TGID, leader->tgid); - attach_pid(leader, PIDTYPE_PGID, leader->signal->pgrp); - attach_pid(leader, PIDTYPE_SID, leader->signal->session); + struct pid *pid; + + do { + pid = find_pid(nr); + if (pid) + break; + nr = next_pidmap(current->nsproxy->pid_ns, nr); + } while (nr > 0); + + return pid; +} +EXPORT_SYMBOL_GPL(find_get_pid); + +int copy_pid_ns(int flags, struct task_struct *tsk) +{ + struct pid_namespace *old_ns = tsk->nsproxy->pid_ns; + int err = 0; + + if (!old_ns) + return 0; + + get_pid_ns(old_ns); + return err; +} + +void free_pid_ns(struct kref *kref) +{ + struct pid_namespace *ns; + + ns = container_of(kref, struct pid_namespace, kref); + kfree(ns); } /* @@ -260,7 +401,7 @@ void switch_exec_pids(task_t *leader, task_t *thread) */ void __init pidhash_init(void) { - int i, j, pidhash_size; + int i, pidhash_size; unsigned long megabytes = nr_kernel_pages >> (20 - PAGE_SHIFT); pidhash_shift = max(4, fls(megabytes * 4)); @@ -269,30 +410,23 @@ void __init pidhash_init(void) 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]); - } + pidhash_size * sizeof(struct hlist_head)); + + pid_hash = alloc_bootmem(pidhash_size * sizeof(*(pid_hash))); + if (!pid_hash) + panic("Could not alloc pidhash!\n"); + for (i = 0; i < pidhash_size; i++) + INIT_HLIST_HEAD(&pid_hash[i]); } void __init pidmap_init(void) { - int i; - - pidmap_array->page = (void *)get_zeroed_page(GFP_KERNEL); - 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); + init_pid_ns.pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL); + /* Reserve PID 0. We never call free_pidmap(0) */ + set_bit(0, init_pid_ns.pidmap[0].page); + atomic_dec(&init_pid_ns.pidmap[0].nr_free); + + pid_cachep = kmem_cache_create("pid", sizeof(struct pid), + __alignof__(struct pid), + SLAB_PANIC, NULL, NULL); }