From 4f58424da3deead2605e39a9df65f5f06107a3cb Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 10 Jan 2018 04:35:12 -0800 Subject: cgroup: make cgroup.threads delegatable Make cgroup.threads file delegatable. The behavior of cgroup.threads should follow the behavior of cgroup.procs. Signed-off-by: Roman Gushchin Discovered-by: Michael Kerrisk Cc: Tejun Heo Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 2cf06c274e4c..7e4c44538119 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4447,6 +4447,7 @@ static struct cftype cgroup_base_files[] = { }, { .name = "cgroup.threads", + .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, -- cgit v1.2.3 From 62635ea8c18f0f62df4cc58379e4f1d33afd5801 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 11 Jan 2018 09:53:35 +0900 Subject: workqueue: avoid hard lockups in show_workqueue_state() show_workqueue_state() can print out a lot of messages while being in atomic context, e.g. sysrq-t -> show_workqueue_state(). If the console device is slow it may end up triggering NMI hard lockup watchdog. Signed-off-by: Sergey Senozhatsky Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v4.5+ --- kernel/workqueue.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'kernel') diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 43d18cb46308..f699122dab32 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -48,6 +48,7 @@ #include #include #include +#include #include "workqueue_internal.h" @@ -4463,6 +4464,12 @@ void show_workqueue_state(void) if (pwq->nr_active || !list_empty(&pwq->delayed_works)) show_pwq(pwq); spin_unlock_irqrestore(&pwq->pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering + * hard lockup. + */ + touch_nmi_watchdog(); } } @@ -4490,6 +4497,12 @@ void show_workqueue_state(void) pr_cont("\n"); next_pool: spin_unlock_irqrestore(&pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_workqueue_state(). Avoid triggering + * hard lockup. + */ + touch_nmi_watchdog(); } rcu_read_unlock_sched(); -- cgit v1.2.3 From c366287ebd698ef5e3de300d90cd62ee9ee7373e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 12 Jan 2018 17:43:23 -0800 Subject: bpf: fix divides by zero Divides by zero are not nice, lets avoid them if possible. Also do_div() seems not needed when dealing with 32bit operands, but this seems a minor detail. Fixes: bd4cf0ed331a ("net: filter: rework/optimize internal BPF interpreter's instruction set") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: Alexei Starovoitov --- kernel/bpf/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 51ec2dda7f08..7949e8b8f94e 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -956,7 +956,7 @@ select_insn: DST = tmp; CONT; ALU_MOD_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; DST = do_div(tmp, (u32) SRC); @@ -975,7 +975,7 @@ select_insn: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: - if (unlikely(SRC == 0)) + if (unlikely((u32)SRC == 0)) return 0; tmp = (u32) DST; do_div(tmp, (u32) SRC); -- cgit v1.2.3 From c1e2f0eaf015fb7076d51a339011f2383e6dd389 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 8 Dec 2017 13:49:39 +0100 Subject: futex: Avoid violating the 10th rule of futex Julia reported futex state corruption in the following scenario: waiter waker stealer (prio > waiter) futex(WAIT_REQUEUE_PI, uaddr, uaddr2, timeout=[N ms]) futex_wait_requeue_pi() futex_wait_queue_me() freezable_schedule() futex(LOCK_PI, uaddr2) futex(CMP_REQUEUE_PI, uaddr, uaddr2, 1, 0) /* requeues waiter to uaddr2 */ futex(UNLOCK_PI, uaddr2) wake_futex_pi() cmp_futex_value_locked(uaddr2, waiter) wake_up_q() task> futex(LOCK_PI, uaddr2) __rt_mutex_start_proxy_lock() try_to_take_rt_mutex() /* steals lock */ rt_mutex_set_owner(lock, stealer) rt_mutex_wait_proxy_lock() __rt_mutex_slowlock() try_to_take_rt_mutex() /* fails, lock held by stealer */ if (timeout && !timeout->task) return -ETIMEDOUT; fixup_owner() /* lock wasn't acquired, so, fixup_pi_state_owner skipped */ return -ETIMEDOUT; /* At this point, we've returned -ETIMEDOUT to userspace, but the * futex word shows waiter to be the owner, and the pi_mutex has * stealer as the owner */ futex_lock(LOCK_PI, uaddr2) -> bails with EDEADLK, futex word says we're owner. And suggested that what commit: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") removes from fixup_owner() looks to be just what is needed. And indeed it is -- I completely missed that requeue_pi could also result in this case. So we need to restore that, except that subsequent patches, like commit: 16ffa12d7425 ("futex: Pull rt_mutex_futex_unlock() out from under hb->lock") changed all the locking rules. Even without that, the sequence: - if (rt_mutex_futex_trylock(&q->pi_state->pi_mutex)) { - locked = 1; - goto out; - } - raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); - owner = rt_mutex_owner(&q->pi_state->pi_mutex); - if (!owner) - owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); - ret = fixup_pi_state_owner(uaddr, q, owner); already suggests there were races; otherwise we'd never have to look at next_owner. So instead of doing 3 consecutive wait_lock sections with who knows what races, we do it all in a single section. Additionally, the usage of pi_state->owner in fixup_owner() was only safe because only the rt_mutex owner would modify it, which this additional case wrecks. Luckily the values can only change away and not to the value we're testing, this means we can do a speculative test and double check once we have the wait_lock. Fixes: 73d786bd043e ("futex: Rework inconsistent rt_mutex/futex_q state") Reported-by: Julia Cartwright Reported-by: Gratian Crisan Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Julia Cartwright Tested-by: Gratian Crisan Cc: Darren Hart Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20171208124939.7livp7no2ov65rrc@hirez.programming.kicks-ass.net --- kernel/futex.c | 83 +++++++++++++++++++++++++++++++++-------- kernel/locking/rtmutex.c | 26 +++++++++---- kernel/locking/rtmutex_common.h | 1 + 3 files changed, 87 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 57d0b3657e16..9e69589b9248 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2294,21 +2294,17 @@ static void unqueue_me_pi(struct futex_q *q) spin_unlock(q->lock_ptr); } -/* - * Fixup the pi_state owner with the new owner. - * - * Must be called with hash bucket lock held and mm->sem held for non - * private futexes. - */ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, - struct task_struct *newowner) + struct task_struct *argowner) { - u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; struct futex_pi_state *pi_state = q->pi_state; u32 uval, uninitialized_var(curval), newval; - struct task_struct *oldowner; + struct task_struct *oldowner, *newowner; + u32 newtid; int ret; + lockdep_assert_held(q->lock_ptr); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); oldowner = pi_state->owner; @@ -2317,11 +2313,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, newtid |= FUTEX_OWNER_DIED; /* - * We are here either because we stole the rtmutex from the - * previous highest priority waiter or we are the highest priority - * waiter but have failed to get the rtmutex the first time. + * We are here because either: + * + * - we stole the lock and pi_state->owner needs updating to reflect + * that (@argowner == current), * - * We have to replace the newowner TID in the user space variable. + * or: + * + * - someone stole our lock and we need to fix things to point to the + * new owner (@argowner == NULL). + * + * Either way, we have to replace the TID in the user space variable. * This must be atomic as we have to preserve the owner died bit here. * * Note: We write the user space value _before_ changing the pi_state @@ -2334,6 +2336,42 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q, * in the PID check in lookup_pi_state. */ retry: + if (!argowner) { + if (oldowner != current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + + if (__rt_mutex_futex_trylock(&pi_state->pi_mutex)) { + /* We got the lock after all, nothing to fix. */ + ret = 0; + goto out_unlock; + } + + /* + * Since we just failed the trylock; there must be an owner. + */ + newowner = rt_mutex_owner(&pi_state->pi_mutex); + BUG_ON(!newowner); + } else { + WARN_ON_ONCE(argowner != current); + if (oldowner == current) { + /* + * We raced against a concurrent self; things are + * already fixed up. Nothing to do. + */ + ret = 0; + goto out_unlock; + } + newowner = argowner; + } + + newtid = task_pid_vnr(newowner) | FUTEX_WAITERS; + if (get_futex_value_locked(&uval, uaddr)) goto handle_fault; @@ -2434,15 +2472,28 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * Got the lock. We might not be the anticipated owner if we * did a lock-steal - fix up the PI-state in that case: * - * We can safely read pi_state->owner without holding wait_lock - * because we now own the rt_mutex, only the owner will attempt - * to change it. + * Speculative pi_state->owner read (we don't hold wait_lock); + * since we own the lock pi_state->owner == current is the + * stable state, anything else needs more attention. */ if (q->pi_state->owner != current) ret = fixup_pi_state_owner(uaddr, q, current); goto out; } + /* + * If we didn't get the lock; check if anybody stole it from us. In + * that case, we need to fix up the uval to point to them instead of + * us, otherwise bad things happen. [10] + * + * Another speculative read; pi_state->owner == current is unstable + * but needs our attention. + */ + if (q->pi_state->owner == current) { + ret = fixup_pi_state_owner(uaddr, q, NULL); + goto out; + } + /* * Paranoia check. If we did not take the lock, then we should not be * the owner of the rt_mutex. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 6f3dba6e4e9e..65cc0cb984e6 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1290,6 +1290,19 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, return ret; } +static inline int __rt_mutex_slowtrylock(struct rt_mutex *lock) +{ + int ret = try_to_take_rt_mutex(lock, current, NULL); + + /* + * try_to_take_rt_mutex() sets the lock waiters bit + * unconditionally. Clean this up. + */ + fixup_rt_mutex_waiters(lock); + + return ret; +} + /* * Slow path try-lock function: */ @@ -1312,13 +1325,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ raw_spin_lock_irqsave(&lock->wait_lock, flags); - ret = try_to_take_rt_mutex(lock, current, NULL); - - /* - * try_to_take_rt_mutex() sets the lock waiters bit - * unconditionally. Clean this up. - */ - fixup_rt_mutex_waiters(lock); + ret = __rt_mutex_slowtrylock(lock); raw_spin_unlock_irqrestore(&lock->wait_lock, flags); @@ -1505,6 +1512,11 @@ int __sched rt_mutex_futex_trylock(struct rt_mutex *lock) return rt_mutex_slowtrylock(lock); } +int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock) +{ + return __rt_mutex_slowtrylock(lock); +} + /** * rt_mutex_timed_lock - lock a rt_mutex interruptible * the timeout structure is provided diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 124e98ca0b17..68686b3ec3c1 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -148,6 +148,7 @@ extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter); extern int rt_mutex_futex_trylock(struct rt_mutex *l); +extern int __rt_mutex_futex_trylock(struct rt_mutex *l); extern void rt_mutex_futex_unlock(struct rt_mutex *lock); extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, -- cgit v1.2.3 From fbe0e839d1e22d88810f3ee3e2f1479be4c0aa4a Mon Sep 17 00:00:00 2001 From: Li Jinyue Date: Thu, 14 Dec 2017 17:04:54 +0800 Subject: futex: Prevent overflow by strengthen input validation UBSAN reports signed integer overflow in kernel/futex.c: UBSAN: Undefined behaviour in kernel/futex.c:2041:18 signed integer overflow: 0 - -2147483648 cannot be represented in type 'int' Add a sanity check to catch negative values of nr_wake and nr_requeue. Signed-off-by: Li Jinyue Signed-off-by: Thomas Gleixner Cc: peterz@infradead.org Cc: dvhart@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/1513242294-31786-1-git-send-email-lijinyue@huawei.com --- kernel/futex.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/futex.c b/kernel/futex.c index 9e69589b9248..8c5424dd5924 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1878,6 +1878,9 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags, struct futex_q *this, *next; DEFINE_WAKE_Q(wake_q); + if (nr_wake < 0 || nr_requeue < 0) + return -EINVAL; + /* * When PI not supported: return -ENOSYS if requeue_pi is true, * consequently the compiler knows requeue_pi is always false past -- cgit v1.2.3 From 68fda450a7df51cff9e5a4d4a4d9d0d5f2589153 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 12 Jan 2018 18:59:52 -0800 Subject: bpf: fix 32-bit divide by zero due to some JITs doing if (src_reg == 0) check in 64-bit mode for div/mod operations mask upper 32-bits of src register before doing the check Fixes: 622582786c9e ("net: filter: x86: internal BPF JIT") Fixes: 7a12b5031c6b ("sparc64: Add eBPF JIT.") Reported-by: syzbot+48340bb518e88849e2e3@syzkaller.appspotmail.com Signed-off-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann --- kernel/bpf/verifier.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 20eb04fd155e..b7448347e6b6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4445,6 +4445,24 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) int i, cnt, delta = 0; for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code == (BPF_ALU | BPF_MOD | BPF_X) || + insn->code == (BPF_ALU | BPF_DIV | BPF_X)) { + /* due to JIT bugs clear upper 32-bits of src register + * before div/mod operation + */ + insn_buf[0] = BPF_MOV32_REG(insn->src_reg, insn->src_reg); + insn_buf[1] = *insn; + cnt = 2; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; -- cgit v1.2.3 From ed4bbf7910b28ce3c691aef28d245585eaabda06 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 14 Jan 2018 23:19:49 +0100 Subject: timers: Unconditionally check deferrable base When the timer base is checked for expired timers then the deferrable base must be checked as well. This was missed when making the deferrable base independent of base::nohz_active. Fixes: ced6d5c11d3e ("timers: Use deferrable base independent of base::nohz_active") Signed-off-by: Thomas Gleixner Cc: Anna-Maria Gleixner Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Paul McKenney Cc: stable@vger.kernel.org Cc: rt@linutronix.de --- kernel/time/timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 89a9e1b4264a..0bcf00e3ce48 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1696,7 +1696,7 @@ void run_local_timers(void) hrtimer_run_queues(); /* Raise the softirq only if required. */ if (time_before(jiffies, base->clk)) { - if (!IS_ENABLED(CONFIG_NO_HZ_COMMON) || !base->nohz_active) + if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) return; /* CPU is awake, so check the deferrable base. */ base++; -- cgit v1.2.3 From c96f5471ce7d2aefd0dda560cc23f08ab00bc65d Mon Sep 17 00:00:00 2001 From: Josh Snyder Date: Mon, 18 Dec 2017 16:15:10 +0000 Subject: delayacct: Account blkio completion on the correct task Before commit: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") delayacct_blkio_end() was called after context-switching into the task which completed I/O. This resulted in double counting: the task would account a delay both waiting for I/O and for time spent in the runqueue. With e33a9bba85a8, delayacct_blkio_end() is called by try_to_wake_up(). In ttwu, we have not yet context-switched. This is more correct, in that the delay accounting ends when the I/O is complete. But delayacct_blkio_end() relies on 'get_current()', and we have not yet context-switched into the task whose I/O completed. This results in the wrong task having its delay accounting statistics updated. Instead of doing that, pass the task_struct being woken to delayacct_blkio_end(), so that it can update the statistics of the correct task. Signed-off-by: Josh Snyder Acked-by: Tejun Heo Acked-by: Balbir Singh Cc: Cc: Brendan Gregg Cc: Jens Axboe Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-block@vger.kernel.org Fixes: e33a9bba85a8 ("sched/core: move IO scheduling accounting from io_schedule_timeout() into scheduler") Link: http://lkml.kernel.org/r/1513613712-571-1-git-send-email-joshs@netflix.com Signed-off-by: Ingo Molnar --- kernel/delayacct.c | 42 ++++++++++++++++++++++++++---------------- kernel/sched/core.c | 6 +++--- 2 files changed, 29 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 4a1c33416b6a..e2764d767f18 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -51,16 +51,16 @@ void __delayacct_tsk_init(struct task_struct *tsk) * Finish delay accounting for a statistic using its timestamps (@start), * accumalator (@total) and @count */ -static void delayacct_end(u64 *start, u64 *total, u32 *count) +static void delayacct_end(spinlock_t *lock, u64 *start, u64 *total, u32 *count) { s64 ns = ktime_get_ns() - *start; unsigned long flags; if (ns > 0) { - spin_lock_irqsave(¤t->delays->lock, flags); + spin_lock_irqsave(lock, flags); *total += ns; (*count)++; - spin_unlock_irqrestore(¤t->delays->lock, flags); + spin_unlock_irqrestore(lock, flags); } } @@ -69,17 +69,25 @@ void __delayacct_blkio_start(void) current->delays->blkio_start = ktime_get_ns(); } -void __delayacct_blkio_end(void) +/* + * We cannot rely on the `current` macro, as we haven't yet switched back to + * the process being woken. + */ +void __delayacct_blkio_end(struct task_struct *p) { - if (current->delays->flags & DELAYACCT_PF_SWAPIN) - /* Swapin block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->swapin_delay, - ¤t->delays->swapin_count); - else /* Other block I/O */ - delayacct_end(¤t->delays->blkio_start, - ¤t->delays->blkio_delay, - ¤t->delays->blkio_count); + struct task_delay_info *delays = p->delays; + u64 *total; + u32 *count; + + if (p->delays->flags & DELAYACCT_PF_SWAPIN) { + total = &delays->swapin_delay; + count = &delays->swapin_count; + } else { + total = &delays->blkio_delay; + count = &delays->blkio_count; + } + + delayacct_end(&delays->lock, &delays->blkio_start, total, count); } int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -153,8 +161,10 @@ void __delayacct_freepages_start(void) void __delayacct_freepages_end(void) { - delayacct_end(¤t->delays->freepages_start, - ¤t->delays->freepages_delay, - ¤t->delays->freepages_count); + delayacct_end( + ¤t->delays->lock, + ¤t->delays->freepages_start, + ¤t->delays->freepages_delay, + ¤t->delays->freepages_count); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 644fa2e3d993..a7bf32aabfda 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2056,7 +2056,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->state = TASK_WAKING; if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2069,7 +2069,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #else /* CONFIG_SMP */ if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } @@ -2122,7 +2122,7 @@ static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) if (!task_on_rq_queued(p)) { if (p->in_iowait) { - delayacct_blkio_end(); + delayacct_blkio_end(p); atomic_dec(&rq->nr_iowait); } ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); -- cgit v1.2.3 From f37a8cb84cce18762e8f86a70bd6a49a66ab964c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 16 Jan 2018 23:30:10 +0100 Subject: bpf: reject stores into ctx via st and xadd Alexei found that verifier does not reject stores into context via BPF_ST instead of BPF_STX. And while looking at it, we also should not allow XADD variant of BPF_STX. The context rewriter is only assuming either BPF_LDX_MEM- or BPF_STX_MEM-type operations, thus reject anything other than that so that assumptions in the rewriter properly hold. Add test cases as well for BPF selftests. Fixes: d691f9e8d440 ("bpf: allow programs to write to certain skb fields") Reported-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b7448347e6b6..eb062b0fbf27 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -978,6 +978,13 @@ static bool is_pointer_value(struct bpf_verifier_env *env, int regno) return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno); } +static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = cur_regs(env) + regno; + + return reg->type == PTR_TO_CTX; +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1258,6 +1265,12 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return -EACCES; } + if (is_ctx_reg(env, insn->dst_reg)) { + verbose(env, "BPF_XADD stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check whether atomic_add can read the memory */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_READ, -1); @@ -3993,6 +4006,12 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; + if (is_ctx_reg(env, insn->dst_reg)) { + verbose(env, "BPF_ST stores into R%d context is not allowed\n", + insn->dst_reg); + return -EACCES; + } + /* check that memory (dst_reg + off) is writeable */ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, BPF_SIZE(insn->code), BPF_WRITE, -- cgit v1.2.3 From 6f16101e6a8b4324c36e58a29d9e0dbb287cdedb Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 18 Jan 2018 01:15:21 +0100 Subject: bpf: mark dst unknown on inconsistent {s, u}bounds adjustments syzkaller generated a BPF proglet and triggered a warning with the following: 0: (b7) r0 = 0 1: (d5) if r0 s<= 0x0 goto pc+0 R0=inv0 R1=ctx(id=0,off=0,imm=0) R10=fp0 2: (1f) r0 -= r1 R0=inv0 R1=ctx(id=0,off=0,imm=0) R10=fp0 verifier internal error: known but bad sbounds What happens is that in the first insn, r0's min/max value are both 0 due to the immediate assignment, later in the jsle test the bounds are updated for the min value in the false path, meaning, they yield smin_val = 1, smax_val = 0, and when ctx pointer is subtracted from r0, verifier bails out with the internal error and throwing a WARN since smin_val != smax_val for the known constant. For min_val > max_val scenario it means that reg_set_min_max() and reg_set_min_max_inv() (which both refine existing bounds) demonstrated that such branch cannot be taken at runtime. In above scenario for the case where it will be taken, the existing [0, 0] bounds are kept intact. Meaning, the rejection is not due to a verifier internal error, and therefore the WARN() is not necessary either. We could just reject such cases in adjust_{ptr,scalar}_min_max_vals() when either known scalars have smin_val != smax_val or umin_val != umax_val or any scalar reg with bounds smin_val > smax_val or umin_val > umax_val. However, there may be a small risk of breakage of buggy programs, so handle this more gracefully and in adjust_{ptr,scalar}_min_max_vals() just taint the dst reg as unknown scalar when we see ops with such kind of src reg. Reported-by: syzbot+6d362cadd45dc0a12ba4@syzkaller.appspotmail.com Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb062b0fbf27..13551e623501 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1895,17 +1895,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; - if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(env, env->cur_state); - verbose(env, - "verifier internal error: known but bad sbounds\n"); - return -EINVAL; - } - if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(env, env->cur_state); - verbose(env, - "verifier internal error: known but bad ubounds\n"); - return -EINVAL; + if ((known && (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds derived from + * e.g. dead branches. + */ + __mark_reg_unknown(dst_reg); + return 0; } if (BPF_CLASS(insn->code) != BPF_ALU64) { @@ -2097,6 +2093,15 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, src_known = tnum_is_const(src_reg.var_off); dst_known = tnum_is_const(dst_reg->var_off); + if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds derived from + * e.g. dead branches. + */ + __mark_reg_unknown(dst_reg); + return 0; + } + if (!src_known && opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { __mark_reg_unknown(dst_reg); -- cgit v1.2.3 From 0164e0d7e803af3ee1c63770978c728f8778ad01 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 18 Jan 2018 15:42:09 -0500 Subject: ring-buffer: Fix duplicate results in mapping context to bits in recursive lock In bringing back the context checks, the code checks first if its normal (non-interrupt) context, and then for NMI then IRQ then softirq. The final check is redundant. Since the if branch is only hit if the context is one of NMI, IRQ, or SOFTIRQ, if it's not NMI or IRQ there's no reason to check if it is SOFTIRQ. The current code returns the same result even if its not a SOFTIRQ. Which is confusing. pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ Is redundant as RB_CTX_SOFTIRQ *is* 2! Fixes: a0e3a18f4baf ("ring-buffer: Bring back context level recursive checks") Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ring_buffer.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 0cddf60186da..5af2842dea96 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2579,8 +2579,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) bit = RB_CTX_NORMAL; else bit = pc & NMI_MASK ? RB_CTX_NMI : - pc & HARDIRQ_MASK ? RB_CTX_IRQ : - pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; if (unlikely(val & (1 << bit))) return 1; -- cgit v1.2.3 From 1ebe1eaf2f02784921759992ae1fde1a9bec8fd0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Thu, 18 Jan 2018 15:53:10 -0500 Subject: tracing: Fix converting enum's from the map in trace_event_eval_update() Since enums do not get converted by the TRACE_EVENT macro into their values, the event format displaces the enum name and not the value. This breaks tools like perf and trace-cmd that need to interpret the raw binary data. To solve this, an enum map was created to convert these enums into their actual numbers on boot up. This is done by TRACE_EVENTS() adding a TRACE_DEFINE_ENUM() macro. Some enums were not being converted. This was caused by an optization that had a bug in it. All calls get checked against this enum map to see if it should be converted or not, and it compares the call's system to the system that the enum map was created under. If they match, then they call is processed. To cut down on the number of iterations needed to find the maps with a matching system, since calls and maps are grouped by system, when a match is made, the index into the map array is saved, so that the next call, if it belongs to the same system as the previous call, could start right at that array index and not have to scan all the previous arrays. The problem was, the saved index was used as the variable to know if this is a call in a new system or not. If the index was zero, it was assumed that the call is in a new system and would keep incrementing the saved index until it found a matching system. The issue arises when the first matching system was at index zero. The next map, if it belonged to the same system, would then think it was the first match and increment the index to one. If the next call belong to the same system, it would begin its search of the maps off by one, and miss the first enum that should be converted. This left a single enum not converted properly. Also add a comment to describe exactly what that index was for. It took me a bit too long to figure out what I was thinking when debugging this issue. Link: http://lkml.kernel.org/r/717BE572-2070-4C1E-9902-9F2E0FEDA4F8@oracle.com Cc: stable@vger.kernel.org Fixes: 0c564a538aa93 ("tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values") Reported-by: Chuck Lever Teste-by: Chuck Lever Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index ec0f9aa4e151..1b87157edbff 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2213,6 +2213,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) { struct trace_event_call *call, *p; const char *last_system = NULL; + bool first = false; int last_i; int i; @@ -2220,15 +2221,28 @@ void trace_event_eval_update(struct trace_eval_map **map, int len) list_for_each_entry_safe(call, p, &ftrace_events, list) { /* events are usually grouped together with systems */ if (!last_system || call->class->system != last_system) { + first = true; last_i = 0; last_system = call->class->system; } + /* + * Since calls are grouped by systems, the likelyhood that the + * next call in the iteration belongs to the same system as the + * previous call is high. As an optimization, we skip seaching + * for a map[] that matches the call's system if the last call + * was from the same system. That's what last_i is for. If the + * call has the same system as the previous call, then last_i + * will be the index of the first map[] that has a matching + * system. + */ for (i = last_i; i < len; i++) { if (call->class->system == map[i]->system) { /* Save the first system if need be */ - if (!last_i) + if (first) { last_i = i; + first = false; + } update_event_printk(call, map[i]); } } -- cgit v1.2.3