diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/audit_watch.c | 12 | ||||
| -rw-r--r-- | kernel/events/core.c | 4 | ||||
| -rw-r--r-- | kernel/fork.c | 17 | ||||
| -rw-r--r-- | kernel/locking/osq_lock.c | 13 | ||||
| -rw-r--r-- | kernel/locking/rwsem-xadd.c | 27 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 3 | ||||
| -rw-r--r-- | kernel/time/timer.c | 29 | ||||
| -rw-r--r-- | kernel/trace/ring_buffer.c | 2 |
8 files changed, 87 insertions, 20 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 690e1e3c59f7..f036b6ada6ef 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -419,6 +419,13 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) struct path parent_path; int h, ret = 0; + /* + * When we will be calling audit_add_to_parent, krule->watch might have + * been updated and watch might have been freed. + * So we need to keep a reference of watch. + */ + audit_get_watch(watch); + mutex_unlock(&audit_filter_mutex); /* Avoid calling path_lookup under audit_filter_mutex. */ @@ -427,8 +434,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) /* caller expects mutex locked */ mutex_lock(&audit_filter_mutex); - if (ret) + if (ret) { + audit_put_watch(watch); return ret; + } /* either find an old parent or attach a new one */ parent = audit_find_parent(d_backing_inode(parent_path.dentry)); @@ -446,6 +455,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list) *list = &audit_inode_hash[h]; error: path_put(&parent_path); + audit_put_watch(watch); return ret; } diff --git a/kernel/events/core.c b/kernel/events/core.c index 6e6ec229c780..95bd00d9f2c3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5563,6 +5563,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, unsigned long sp; unsigned int rem; u64 dyn_size; + mm_segment_t fs; /* * We dump: @@ -5580,7 +5581,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, /* Data. */ sp = perf_user_stack_pointer(regs); + fs = get_fs(); + set_fs(USER_DS); rem = __output_copy_user(handle, (void *) sp, dump_size); + set_fs(fs); dyn_size = dump_size - rem; perf_output_skip(handle, rem); diff --git a/kernel/fork.c b/kernel/fork.c index 5d0e2f366766..73beb8dfa9df 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1532,6 +1532,18 @@ static __latent_entropy struct task_struct *copy_process( if (!p) goto fork_out; + /* + * This _must_ happen before we call free_task(), i.e. before we jump + * to any of the bad_fork_* labels. This is to avoid freeing + * p->set_child_tid which is (ab)used as a kthread's data pointer for + * kernel threads (PF_KTHREAD). + */ + p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; + /* + * Clear TID on mm_release()? + */ + p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; + ftrace_graph_init_task(p); rt_mutex_init_task(p); @@ -1693,11 +1705,6 @@ static __latent_entropy struct task_struct *copy_process( } } - p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; - /* - * Clear TID on mm_release()? - */ - p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr : NULL; #ifdef CONFIG_BLOCK p->plug = NULL; #endif diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 05a37857ab55..8d7047ecef4e 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -104,6 +104,19 @@ bool osq_lock(struct optimistic_spin_queue *lock) prev = decode_cpu(old); node->prev = prev; + + /* + * osq_lock() unqueue + * + * node->prev = prev osq_wait_next() + * WMB MB + * prev->next = node next->prev = prev // unqueue-C + * + * Here 'node->prev' and 'next->prev' are the same variable and we need + * to ensure these stores happen in-order to avoid corrupting the list. + */ + smp_wmb(); + WRITE_ONCE(prev->next, node); /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 2337b4bb2366..a4112dfcd0fb 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -574,6 +574,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) WAKE_Q(wake_q); /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f6e8727f7fa3..f81adb476c03 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8639,7 +8639,8 @@ static inline bool vruntime_normalized(struct task_struct *p) * - A task which has been woken up by try_to_wake_up() and * waiting for actually being woken up by sched_ttwu_pending(). */ - if (!se->sum_exec_runtime || p->state == TASK_WAKING) + if (!se->sum_exec_runtime || + (p->state == TASK_WAKING && p->sched_remote_wakeup)) return true; return false; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 7c477912f36d..b625cc7fcc1c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1649,6 +1649,22 @@ static inline void __run_timers(struct timer_base *base) spin_lock_irq(&base->lock); + /* + * timer_base::must_forward_clk must be cleared before running + * timers so that any timer functions that call mod_timer() will + * not try to forward the base. Idle tracking / clock forwarding + * logic is only used with BASE_STD timers. + * + * The must_forward_clk flag is cleared unconditionally also for + * the deferrable base. The deferrable base is not affected by idle + * tracking and never forwarded, so clearing the flag is a NOOP. + * + * The fact that the deferrable base is never forwarded can cause + * large variations in granularity for deferrable timers, but they + * can be deferred for long periods due to idle anyway. + */ + base->must_forward_clk = false; + while (time_after_eq(jiffies, base->clk)) { levels = collect_expired_timers(base, heads); @@ -1668,19 +1684,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * must_forward_clk must be cleared before running timers so that any - * timer functions that call mod_timer will not try to forward the - * base. idle trcking / clock forwarding logic is only used with - * BASE_STD timers. - * - * The deferrable base does not do idle tracking at all, so we do - * not forward it. This can result in very large variations in - * granularity for deferrable timers, but they can be deferred for - * long periods due to idle. - */ - base->must_forward_clk = false; - __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index dc29b600d2cb..f316e90ad538 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1504,6 +1504,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages) tmp_iter_page = first_page; do { + cond_resched(); + to_remove_page = tmp_iter_page; rb_inc_page(cpu_buffer, &tmp_iter_page); |