linux-stable/kernel/pid.c
Eric W. Biederman c0ee554906 pid: Handle failure to allocate the first pid in a pid namespace
With the replacement of the pid bitmap and hashtable with an idr in
alloc_pid started occassionally failing when allocating the first pid
in a pid namespace.  Things were not completely reset resulting in
the first allocated pid getting the number 2 (not 1).  Which
further resulted in ns->proc_mnt not getting set and eventually
causing an oops in proc_flush_task.

Oops: 0000 [#1] SMP
CPU: 2 PID: 6743 Comm: trinity-c117 Not tainted 4.15.0-rc4-think+ #2
RIP: 0010:proc_flush_task+0x8e/0x1b0
RSP: 0018:ffffc9000bbffc40 EFLAGS: 00010286
RAX: 0000000000000001 RBX: 0000000000000001 RCX: 00000000fffffffb
RDX: 0000000000000000 RSI: ffffc9000bbffc50 RDI: 0000000000000000
RBP: ffffc9000bbffc63 R08: 0000000000000000 R09: 0000000000000002
R10: ffffc9000bbffb70 R11: ffffc9000bbffc64 R12: 0000000000000003
R13: 0000000000000000 R14: 0000000000000003 R15: ffff8804c10d7840
FS:  00007f7cb8965700(0000) GS:ffff88050a200000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 00000003e21ae003 CR4: 00000000001606e0
DR0: 00007fb1d6c22000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000600
Call Trace:
 ? release_task+0xaf/0x680
 release_task+0xd2/0x680
 ? wait_consider_task+0xb82/0xce0
 wait_consider_task+0xbe9/0xce0
 ? do_wait+0xe1/0x330
 do_wait+0x151/0x330
 kernel_wait4+0x8d/0x150
 ? task_stopped_code+0x50/0x50
 SYSC_wait4+0x95/0xa0
 ? rcu_read_lock_sched_held+0x6c/0x80
 ? syscall_trace_enter+0x2d7/0x340
 ? do_syscall_64+0x60/0x210
 do_syscall_64+0x60/0x210
 entry_SYSCALL64_slow_path+0x25/0x25
RIP: 0033:0x7f7cb82603aa
RSP: 002b:00007ffd60770bc8 EFLAGS: 00000246
 ORIG_RAX: 000000000000003d
RAX: ffffffffffffffda RBX: 00007f7cb6cd4000 RCX: 00007f7cb82603aa
RDX: 000000000000000b RSI: 00007ffd60770bd0 RDI: 0000000000007cca
RBP: 0000000000007cca R08: 00007f7cb8965700 R09: 00007ffd607c7080
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007ffd60770bd0 R14: 00007f7cb6cd4058 R15: 00000000cccccccd
Code: c1 e2 04 44 8b 60 30 48 8b 40 38 44 8b 34 11 48 c7 c2 60 3a f5 81 44 89 e1 4c 8b 68 58 e8 4b b4 77 00 89 44 24 14 48 8d 74 24 10 <49> 8b 7d 00 e8 b9 6a f9 ff 48 85 c0 74 1a 48 89 c7 48 89 44 24
RIP: proc_flush_task+0x8e/0x1b0 RSP: ffffc9000bbffc40
CR2: 0000000000000000
---[ end trace 53d67a6481059862 ]---

Improve the quality of the implementation by resetting the place to
start allocating pids on failure to allocate the first pid.

As improving the quality of the implementation is the goal remove the now
unnecesarry disable_pid_allocations call when we fail to mount proc.

Fixes: 95846ecf9d ("pid: replace pid bitmap implementation with IDR API")
Fixes: 8ef047aaae ("pid namespaces: make alloc_pid(), free_pid() and put_pid() work with struct upid")
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2017-12-23 21:00:09 -06:00

445 lines
11 KiB
C

/*
* Generic pidhash and scalable, time-bounded PID allocator
*
* (C) 2002-2003 Nadia Yvette Chambers, IBM
* (C) 2004 Nadia Yvette Chambers, 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).
*
* Pid namespaces:
* (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
* (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
* Many thanks to Oleg Nesterov for comments and help
*
*/
#include <linux/mm.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/rculist.h>
#include <linux/bootmem.h>
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
#include <linux/syscalls.h>
#include <linux/proc_ns.h>
#include <linux/proc_fs.h>
#include <linux/sched/task.h>
#include <linux/idr.h>
struct pid init_struct_pid = INIT_STRUCT_PID;
int pid_max = PID_MAX_DEFAULT;
#define RESERVED_PIDS 300
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
/*
* 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.
*/
struct pid_namespace init_pid_ns = {
.kref = KREF_INIT(2),
.idr = IDR_INIT,
.pid_allocated = PIDNS_ADDING,
.level = 0,
.child_reaper = &init_task,
.user_ns = &init_user_ns,
.ns.inum = PROC_PID_INIT_INO,
#ifdef CONFIG_PID_NS
.ns.ops = &pidns_operations,
#endif
};
EXPORT_SYMBOL_GPL(init_pid_ns);
/*
* 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);
void put_pid(struct pid *pid)
{
struct pid_namespace *ns;
if (!pid)
return;
ns = pid->numbers[pid->level].ns;
if ((atomic_read(&pid->count) == 1) ||
atomic_dec_and_test(&pid->count)) {
kmem_cache_free(ns->pid_cachep, pid);
put_pid_ns(ns);
}
}
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);
}
void free_pid(struct pid *pid)
{
/* We can be called with write_lock_irq(&tasklist_lock) held */
int i;
unsigned long flags;
spin_lock_irqsave(&pidmap_lock, flags);
for (i = 0; i <= pid->level; i++) {
struct upid *upid = pid->numbers + i;
struct pid_namespace *ns = upid->ns;
switch (--ns->pid_allocated) {
case 2:
case 1:
/* When all that is left in the pid namespace
* is the reaper wake up the reaper. The reaper
* may be sleeping in zap_pid_ns_processes().
*/
wake_up_process(ns->child_reaper);
break;
case PIDNS_ADDING:
/* Handle a fork failure of the first process */
WARN_ON(ns->child_reaper);
ns->pid_allocated = 0;
/* fall through */
case 0:
schedule_work(&ns->proc_work);
break;
}
idr_remove(&ns->idr, upid->nr);
}
spin_unlock_irqrestore(&pidmap_lock, flags);
call_rcu(&pid->rcu, delayed_put_pid);
}
struct pid *alloc_pid(struct pid_namespace *ns)
{
struct pid *pid;
enum pid_type type;
int i, nr;
struct pid_namespace *tmp;
struct upid *upid;
int retval = -ENOMEM;
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
return ERR_PTR(retval);
tmp = ns;
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
int pid_min = 1;
idr_preload(GFP_KERNEL);
spin_lock_irq(&pidmap_lock);
/*
* init really needs pid 1, but after reaching the maximum
* wrap back to RESERVED_PIDS
*/
if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS)
pid_min = RESERVED_PIDS;
/*
* Store a null pointer so find_pid_ns does not find
* a partially initialized PID (see below).
*/
nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min,
pid_max, GFP_ATOMIC);
spin_unlock_irq(&pidmap_lock);
idr_preload_end();
if (nr < 0) {
retval = nr;
goto out_free;
}
pid->numbers[i].nr = nr;
pid->numbers[i].ns = tmp;
tmp = tmp->parent;
}
if (unlikely(is_child_reaper(pid))) {
if (pid_ns_prepare_proc(ns))
goto out_free;
}
get_pid_ns(ns);
atomic_set(&pid->count, 1);
for (type = 0; type < PIDTYPE_MAX; ++type)
INIT_HLIST_HEAD(&pid->tasks[type]);
upid = pid->numbers + ns->level;
spin_lock_irq(&pidmap_lock);
if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
for ( ; upid >= pid->numbers; --upid) {
/* Make the PID visible to find_pid_ns. */
idr_replace(&upid->ns->idr, pid, upid->nr);
upid->ns->pid_allocated++;
}
spin_unlock_irq(&pidmap_lock);
return pid;
out_unlock:
spin_unlock_irq(&pidmap_lock);
put_pid_ns(ns);
out_free:
spin_lock_irq(&pidmap_lock);
while (++i <= ns->level)
idr_remove(&ns->idr, (pid->numbers + i)->nr);
/* On failure to allocate the first pid, reset the state */
if (ns->pid_allocated == PIDNS_ADDING)
idr_set_cursor(&ns->idr, 0);
spin_unlock_irq(&pidmap_lock);
kmem_cache_free(ns->pid_cachep, pid);
return ERR_PTR(retval);
}
void disable_pid_allocation(struct pid_namespace *ns)
{
spin_lock_irq(&pidmap_lock);
ns->pid_allocated &= ~PIDNS_ADDING;
spin_unlock_irq(&pidmap_lock);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
return idr_find(&ns->idr, nr);
}
EXPORT_SYMBOL_GPL(find_pid_ns);
struct pid *find_vpid(int nr)
{
return find_pid_ns(nr, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(find_vpid);
/*
* attach_pid() must be called with the tasklist_lock write-held.
*/
void attach_pid(struct task_struct *task, enum pid_type type)
{
struct pid_link *link = &task->pids[type];
hlist_add_head_rcu(&link->node, &link->pid->tasks[type]);
}
static void __change_pid(struct task_struct *task, enum pid_type type,
struct pid *new)
{
struct pid_link *link;
struct pid *pid;
int tmp;
link = &task->pids[type];
pid = link->pid;
hlist_del_rcu(&link->node);
link->pid = new;
for (tmp = PIDTYPE_MAX; --tmp >= 0; )
if (!hlist_empty(&pid->tasks[tmp]))
return;
free_pid(pid);
}
void detach_pid(struct task_struct *task, enum pid_type type)
{
__change_pid(task, type, NULL);
}
void change_pid(struct task_struct *task, enum pid_type type,
struct pid *pid)
{
__change_pid(task, type, pid);
attach_pid(task, type);
}
/* transfer_pid is an optimization of attach_pid(new), detach_pid(old) */
void transfer_pid(struct task_struct *old, struct task_struct *new,
enum pid_type type)
{
new->pids[type].pid = old->pids[type].pid;
hlist_replace_rcu(&old->pids[type].node, &new->pids[type].node);
}
struct task_struct *pid_task(struct pid *pid, enum pid_type type)
{
struct task_struct *result = NULL;
if (pid) {
struct hlist_node *first;
first = rcu_dereference_check(hlist_first_rcu(&pid->tasks[type]),
lockdep_tasklist_lock_is_held());
if (first)
result = hlist_entry(first, struct task_struct, pids[(type)].node);
}
return result;
}
EXPORT_SYMBOL(pid_task);
/*
* Must be called under rcu_read_lock().
*/
struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns)
{
RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
"find_task_by_pid_ns() needs rcu_read_lock() protection");
return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID);
}
struct task_struct *find_task_by_vpid(pid_t vnr)
{
return find_task_by_pid_ns(vnr, task_active_pid_ns(current));
}
struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
{
struct pid *pid;
rcu_read_lock();
if (type != PIDTYPE_PID)
task = task->group_leader;
pid = get_pid(rcu_dereference(task->pids[type].pid));
rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(get_task_pid);
struct task_struct *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;
}
EXPORT_SYMBOL_GPL(get_pid_task);
struct pid *find_get_pid(pid_t nr)
{
struct pid *pid;
rcu_read_lock();
pid = get_pid(find_vpid(nr));
rcu_read_unlock();
return pid;
}
EXPORT_SYMBOL_GPL(find_get_pid);
pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns)
{
struct upid *upid;
pid_t nr = 0;
if (pid && ns->level <= pid->level) {
upid = &pid->numbers[ns->level];
if (upid->ns == ns)
nr = upid->nr;
}
return nr;
}
EXPORT_SYMBOL_GPL(pid_nr_ns);
pid_t pid_vnr(struct pid *pid)
{
return pid_nr_ns(pid, task_active_pid_ns(current));
}
EXPORT_SYMBOL_GPL(pid_vnr);
pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
struct pid_namespace *ns)
{
pid_t nr = 0;
rcu_read_lock();
if (!ns)
ns = task_active_pid_ns(current);
if (likely(pid_alive(task))) {
if (type != PIDTYPE_PID) {
if (type == __PIDTYPE_TGID)
type = PIDTYPE_PID;
task = task->group_leader;
}
nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
}
rcu_read_unlock();
return nr;
}
EXPORT_SYMBOL(__task_pid_nr_ns);
struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
{
return ns_of_pid(task_pid(tsk));
}
EXPORT_SYMBOL_GPL(task_active_pid_ns);
/*
* Used by proc to find the first pid that is greater than or equal to nr.
*
* If there is a pid at nr this function is exactly the same as find_pid_ns.
*/
struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
{
return idr_get_next(&ns->idr, &nr);
}
void __init pid_idr_init(void)
{
/* Verify no one has done anything silly: */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_ADDING);
/* bump default and minimum pid_max based on number of cpus */
pid_max = min(pid_max_max, max_t(int, pid_max,
PIDS_PER_CPU_DEFAULT * num_possible_cpus()));
pid_max_min = max_t(int, pid_max_min,
PIDS_PER_CPU_MIN * num_possible_cpus());
pr_info("pid_max: default: %u minimum: %u\n", pid_max, pid_max_min);
idr_init(&init_pid_ns.idr);
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
}