Hillf Danton <hdanton@xxxxxxxx> writes:
> On Fri, 15 Oct 2021 17:10:58 -0500 Eric W. Biederman wrote:
>>
>> In commit fda31c50292a ("signal: avoid double atomic counter
>> increments for user accounting") Linus made a clever optimization to
>> how rlimits and the struct user_struct. Unfortunately that
>> optimization does not work in the obvious way when moved to nested
>> rlimits. The problem is that the last decrement of the per user
>> namespace per user sigpending counter might also be the last decrement
>> of the sigpending counter in the parent user namespace as well. Which
>> means that simply freeing the leaf ucount in __free_sigqueue is not
>> enough.
>>
>> Maintain the optimization and handle the tricky cases by introducing
>> inc_rlimit_get_ucounts and dec_rlimit_put_ucounts.
>>
>> By moving the entire optimization into functions that perform all of
>> the work it becomes possible to ensure that every level is handled
>> properly.
>>
>> I wish we had a single user across all of the threads whose rlimit
>> could be charged so we did not need this complexity.
>>
>> Cc: stable@xxxxxxxxxxxxxxx
>> Fixes: d64696905554 ("Reimplement RLIMIT_SIGPENDING on top of ucounts")
>> Signed-off-by: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
>> ---
>>
>> With a lot of help from Alex who found a way I could reproduce this
>> I believe I have found the issue.
>>
>> Could people who are seeing this issue test and verify this solves the
>> problem for them?
>>
>> include/linux/user_namespace.h | 2 ++
>> kernel/signal.c | 25 +++++----------------
>> kernel/ucount.c | 41 ++++++++++++++++++++++++++++++++++
>> 3 files changed, 49 insertions(+), 19 deletions(-)
>>
>> diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
>> index eb70cabe6e7f..33a4240e6a6f 100644
>> --- a/include/linux/user_namespace.h
>> +++ b/include/linux/user_namespace.h
>> @@ -127,6 +127,8 @@ static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type t
>>
>> long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
>> bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
>> +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type);
>> +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type);
>> bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
>>
>> static inline void set_rlimit_ucount_max(struct user_namespace *ns,
>> diff --git a/kernel/signal.c b/kernel/signal.c
>> index a3229add4455..762de58c6e76 100644
>> --- a/kernel/signal.c
>> +++ b/kernel/signal.c
>> @@ -425,22 +425,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
>> */
>> rcu_read_lock();
>> ucounts = task_ucounts(t);
>> - sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
>> - switch (sigpending) {
>> - case 1:
>> - if (likely(get_ucounts(ucounts)))
>> - break;
>> - fallthrough;
>> - case LONG_MAX:
>> - /*
>> - * we need to decrease the ucount in the userns tree on any
>> - * failure to avoid counts leaking.
>> - */
>> - dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
>> - rcu_read_unlock();
>> - return NULL;
>> - }
>> + sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
>> rcu_read_unlock();
>> + if (sigpending == LONG_MAX)
>> + return NULL;
>>
>> if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
>> q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
>> @@ -449,8 +437,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
>> }
>>
>> if (unlikely(q == NULL)) {
>> - if (dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1))
>> - put_ucounts(ucounts);
>> + dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
>> } else {
>> INIT_LIST_HEAD(&q->list);
>> q->flags = sigqueue_flags;
>> @@ -463,8 +450,8 @@ static void __sigqueue_free(struct sigqueue *q)
>> {
>> if (q->flags & SIGQUEUE_PREALLOC)
>> return;
>> - if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) {
>> - put_ucounts(q->ucounts);
>> + if (q->ucounts) {
>> + dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING);
>> q->ucounts = NULL;
>> }
>> kmem_cache_free(sigqueue_cachep, q);
>> diff --git a/kernel/ucount.c b/kernel/ucount.c
>> index 3b7e176cf7a2..687d77aa66bb 100644
>> --- a/kernel/ucount.c
>> +++ b/kernel/ucount.c
>> @@ -285,6 +285,47 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
>> return (new == 0);
>> }
>>
>> +static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
>> + struct ucounts *last, enum ucount_type type)
>> +{
>> + struct ucounts *iter;
>> + for (iter = ucounts; iter != last; iter = iter->ns->ucounts) {
>> + long dec = atomic_long_add_return(-1, &iter->ucount[type]);
>> + WARN_ON_ONCE(dec < 0);
>> + if (dec == 0)
>> + put_ucounts(iter);
>> + }
>
> Given kfree in put_ucounts(), this has difficulty surviving tests like
> kasan if the put pairs with the get in the below
> inc_rlimit_get_ucounts().
I don't know if this is what you are thinking about but there is indeed
a bug in that loop caused by kfree.
The problem is that iter->ns->ucounts is read after put_ucounts. It
just needs to be read before hand.
>> +}
>> +
>> +void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
>> +{
>> + do_dec_rlimit_put_ucounts(ucounts, NULL, type);
>> +}
>> +
>> +long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
>> +{
>> + struct ucounts *iter;
>> + long dec, ret = 0;
>> +
>> + for (iter = ucounts; iter; iter = iter->ns->ucounts) {
>> + long max = READ_ONCE(iter->ns->ucount_max[type]);
>> + long new = atomic_long_add_return(1, &iter->ucount[type]);
>> + if (new < 0 || new > max)
>> + goto unwind;
>> + else if (iter == ucounts)
>> + ret = new;
>> + if ((new == 1) && (get_ucounts(iter) != iter))
>> + goto dec_unwind;
>
> Add a line of comment for get to ease readers.
/* you are not expected to understand this */
I think that is the classic comment from unix source. Seriously I can't
think of any comment that will make the situation more comprehensible.
> Hillf
>
>> + }
>> + return ret;
>> +dec_unwind:
>> + dec = atomic_long_add_return(1, &iter->ucount[type]);
>> + WARN_ON_ONCE(dec < 0);
>> +unwind:
>> + do_dec_rlimit_put_ucounts(ucounts, iter, type);
>> + return LONG_MAX;
>> +}
>> +
>> bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
>> {
>> struct ucounts *iter;
>> --
>> 2.20.1
Eric
