Revision 6fd4b15603124c1b56e03db29b41ec39d8a077b9 authored by Steve Cornelius on 15 June 2015, 23:52:56 UTC, committed by Herbert Xu on 16 June 2015, 06:20:38 UTC
Multiple function in asynchronous hashing use a saved-state block, a.k.a. struct caam_hash_state, which holds a stash of information between requests (init/update/final). Certain values in this state block are loaded for processing using an inline-if, and when this is done, the potential for uninitialized data can pose conflicts. Therefore, this patch improves initialization of state data to prevent false assignments using uninitialized data in the state block. This patch addresses the following traceback, originating in ahash_final_ctx(), although a problem like this could certainly exhibit other symptoms: kernel BUG at arch/arm/mm/dma-mapping.c:465! Unable to handle kernel NULL pointer dereference at virtual address 00000000 pgd = 80004000 [00000000] *pgd=00000000 Internal error: Oops: 805 [#1] PREEMPT SMP Modules linked in: CPU: 0 Not tainted (3.0.15-01752-gdd441b9-dirty #40) PC is at __bug+0x1c/0x28 LR is at __bug+0x18/0x28 pc : [<80043240>] lr : [<8004323c>] psr: 60000013 sp : e423fd98 ip : 60000013 fp : 0000001c r10: e4191b84 r9 : 00000020 r8 : 00000009 r7 : 88005038 r6 : 00000001 r5 : 2d676572 r4 : e4191a60 r3 : 00000000 r2 : 00000001 r1 : 60000093 r0 : 00000033 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c53c7d Table: 1000404a DAC: 00000015 Process cryptomgr_test (pid: 1306, stack limit = 0xe423e2f0) Stack: (0xe423fd98 to 0xe4240000) fd80: 11807fd1 80048544 fda0: 88005000 e4191a00 e5178040 8039dda0 00000000 00000014 2d676572 e4191008 fdc0: 88005018 e4191a60 00100100 e4191a00 00000000 8039ce0c e423fea8 00000007 fde0: e4191a00 e4227000 e5178000 8039ce18 e419183c 80203808 80a94a44 00000006 fe00: 00000000 80207180 00000000 00000006 e423ff08 00000000 00000007 e5178000 fe20: e41918a4 80a949b4 8c4844e2 00000000 00000049 74227000 8c4844e2 00000e90 fe40: 0000000e 74227e90 ffff8c58 80ac29e0 e423fed4 8006a350 8c81625c e423ff5c fe60: 00008576 e4002500 00000003 00030010 e4002500 00000003 e5180000 e4002500 fe80: e5178000 800e6d24 007fffff 00000000 00000010 e4001280 e4002500 60000013 fea0: 000000d0 804df078 00000000 00000000 00000000 00000000 00000000 00000000 fec0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 fee0: 00000000 00000000 e4227000 e4226000 e4753000 e4752000 e40a5000 e40a4000 ff00: e41e7000 e41e6000 00000000 00000000 00000000 e423ff14 e423ff14 00000000 ff20: 00000400 804f9080 e5178000 e4db0b40 00000000 e4db0b80 0000047c 00000400 ff40: 00000000 8020758c 00000400 ffffffff 0000008a 00000000 e4db0b40 80206e00 ff60: e4049dbc 00000000 00000000 00000003 e423ffa4 80062978 e41a8bfc 00000000 ff80: 00000000 e4049db4 00000013 e4049db0 00000013 00000000 00000000 00000000 ffa0: e4db0b40 e4db0b40 80204cbc 00000013 00000000 00000000 00000000 80204cfc ffc0: e4049da0 80089544 80040a40 00000000 e4db0b40 00000000 00000000 00000000 ffe0: e423ffe0 e423ffe0 e4049da0 800894c4 80040a40 80040a40 00000000 00000000 [<80043240>] (__bug+0x1c/0x28) from [<80048544>] (___dma_single_dev_to_cpu+0x84) [<80048544>] (___dma_single_dev_to_cpu+0x84/0x94) from [<8039dda0>] (ahash_fina) [<8039dda0>] (ahash_final_ctx+0x180/0x428) from [<8039ce18>] (ahash_final+0xc/0) [<8039ce18>] (ahash_final+0xc/0x10) from [<80203808>] (crypto_ahash_op+0x28/0xc) [<80203808>] (crypto_ahash_op+0x28/0xc0) from [<80207180>] (test_hash+0x214/0x5) [<80207180>] (test_hash+0x214/0x5b8) from [<8020758c>] (alg_test_hash+0x68/0x8c) [<8020758c>] (alg_test_hash+0x68/0x8c) from [<80206e00>] (alg_test+0x7c/0x1b8) [<80206e00>] (alg_test+0x7c/0x1b8) from [<80204cfc>] (cryptomgr_test+0x40/0x48) [<80204cfc>] (cryptomgr_test+0x40/0x48) from [<80089544>] (kthread+0x80/0x88) [<80089544>] (kthread+0x80/0x88) from [<80040a40>] (kernel_thread_exit+0x0/0x8) Code: e59f0010 e1a01003 eb126a8d e3a03000 (e5833000) ---[ end trace d52a403a1d1eaa86 ]--- Cc: stable@vger.kernel.org Signed-off-by: Steve Cornelius <steve.cornelius@freescale.com> Signed-off-by: Victoria Milhoan <vicki.milhoan@freescale.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
1 parent f858c7b
pid.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>
#define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
static struct hlist_head *pid_hash;
static unsigned int pidhash_shift = 4;
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;
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)
/*
* 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 = {
.refcount = ATOMIC_INIT(2),
},
.pidmap = {
[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
},
.last_pid = 0,
.nr_hashed = PIDNS_HASH_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);
static void free_pidmap(struct upid *upid)
{
int nr = upid->nr;
struct pidmap *map = upid->ns->pidmap + nr / BITS_PER_PAGE;
int offset = nr & BITS_PER_PAGE_MASK;
clear_bit(offset, map->page);
atomic_inc(&map->nr_free);
}
/*
* If we started walking pids at 'base', is 'a' seen before 'b'?
*/
static int pid_before(int base, int a, int b)
{
/*
* This is the same as saying
*
* (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT
* and that mapping orders 'a' and 'b' with respect to 'base'.
*/
return (unsigned)(a - base) < (unsigned)(b - base);
}
/*
* We might be racing with someone else trying to set pid_ns->last_pid
* at the pid allocation time (there's also a sysctl for this, but racing
* with this one is OK, see comment in kernel/pid_namespace.c about it).
* We want the winner to have the "later" value, because if the
* "earlier" value prevails, then a pid may get reused immediately.
*
* Since pids rollover, it is not sufficient to just pick the bigger
* value. We have to consider where we started counting from.
*
* 'base' is the value of pid_ns->last_pid that we observed when
* we started looking for a pid.
*
* 'pid' is the pid that we eventually found.
*/
static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid)
{
int prev;
int last_write = base;
do {
prev = last_write;
last_write = cmpxchg(&pid_ns->last_pid, prev, pid);
} while ((prev != last_write) && (pid_before(base, last_write, pid)));
}
static int alloc_pidmap(struct pid_namespace *pid_ns)
{
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 = &pid_ns->pidmap[pid/BITS_PER_PAGE];
/*
* If last_pid points into the middle of the map->page we
* want to scan this bitmap block twice, the second time
* we start with offset == 0 (or RESERVED_PIDS).
*/
max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset;
for (i = 0; i <= max_scan; ++i) {
if (unlikely(!map->page)) {
void *page = kzalloc(PAGE_SIZE, GFP_KERNEL);
/*
* Free the page if someone raced with us
* installing it:
*/
spin_lock_irq(&pidmap_lock);
if (!map->page) {
map->page = page;
page = NULL;
}
spin_unlock_irq(&pidmap_lock);
kfree(page);
if (unlikely(!map->page))
break;
}
if (likely(atomic_read(&map->nr_free))) {
for ( ; ; ) {
if (!test_and_set_bit(offset, map->page)) {
atomic_dec(&map->nr_free);
set_last_pid(pid_ns, last, pid);
return pid;
}
offset = find_next_offset(map, offset);
if (offset >= BITS_PER_PAGE)
break;
pid = mk_pid(pid_ns, map, offset);
if (pid >= pid_max)
break;
}
}
if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) {
++map;
offset = 0;
} else {
map = &pid_ns->pidmap[0];
offset = RESERVED_PIDS;
if (unlikely(last == offset))
break;
}
pid = mk_pid(pid_ns, map, offset);
}
return -1;
}
int next_pidmap(struct pid_namespace *pid_ns, unsigned int last)
{
int offset;
struct pidmap *map, *end;
if (last >= PID_MAX_LIMIT)
return -1;
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;
}
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;
hlist_del_rcu(&upid->pid_chain);
switch(--ns->nr_hashed) {
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_HASH_ADDING:
/* Handle a fork failure of the first process */
WARN_ON(ns->child_reaper);
ns->nr_hashed = 0;
/* fall through */
case 0:
schedule_work(&ns->proc_work);
break;
}
}
spin_unlock_irqrestore(&pidmap_lock, flags);
for (i = 0; i <= pid->level; i++)
free_pidmap(pid->numbers + i);
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;
pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL);
if (!pid)
goto out;
tmp = ns;
pid->level = ns->level;
for (i = ns->level; i >= 0; i--) {
nr = alloc_pidmap(tmp);
if (nr < 0)
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->nr_hashed & PIDNS_HASH_ADDING))
goto out_unlock;
for ( ; upid >= pid->numbers; --upid) {
hlist_add_head_rcu(&upid->pid_chain,
&pid_hash[pid_hashfn(upid->nr, upid->ns)]);
upid->ns->nr_hashed++;
}
spin_unlock_irq(&pidmap_lock);
out:
return pid;
out_unlock:
spin_unlock_irq(&pidmap_lock);
put_pid_ns(ns);
out_free:
while (++i <= ns->level)
free_pidmap(pid->numbers + i);
kmem_cache_free(ns->pid_cachep, pid);
pid = NULL;
goto out;
}
void disable_pid_allocation(struct pid_namespace *ns)
{
spin_lock_irq(&pidmap_lock);
ns->nr_hashed &= ~PIDNS_HASH_ADDING;
spin_unlock_irq(&pidmap_lock);
}
struct pid *find_pid_ns(int nr, struct pid_namespace *ns)
{
struct upid *pnr;
hlist_for_each_entry_rcu(pnr,
&pid_hash[pid_hashfn(nr, ns)], pid_chain)
if (pnr->nr == nr && pnr->ns == ns)
return container_of(pnr, struct pid,
numbers[ns->level]);
return NULL;
}
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_assert(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(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)
task = task->group_leader;
nr = pid_nr_ns(task->pids[type].pid, ns);
}
rcu_read_unlock();
return nr;
}
EXPORT_SYMBOL(__task_pid_nr_ns);
pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
{
return pid_nr_ns(task_tgid(tsk), ns);
}
EXPORT_SYMBOL(task_tgid_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)
{
struct pid *pid;
do {
pid = find_pid_ns(nr, ns);
if (pid)
break;
nr = next_pidmap(ns, nr);
} while (nr > 0);
return pid;
}
/*
* 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)
{
unsigned int i, pidhash_size;
pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
HASH_EARLY | HASH_SMALL,
&pidhash_shift, NULL,
0, 4096);
pidhash_size = 1U << pidhash_shift;
for (i = 0; i < pidhash_size; i++)
INIT_HLIST_HEAD(&pid_hash[i]);
}
void __init pidmap_init(void)
{
/* Veryify no one has done anything silly */
BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_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);
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);
init_pid_ns.pid_cachep = KMEM_CACHE(pid,
SLAB_HWCACHE_ALIGN | SLAB_PANIC);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...