diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/context_tracking.c | 80 | ||||
| -rw-r--r-- | kernel/events/core.c | 21 | ||||
| -rw-r--r-- | kernel/irq/internals.h | 5 | ||||
| -rw-r--r-- | kernel/irq/pm.c | 3 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 2 | ||||
| -rw-r--r-- | kernel/livepatch/core.c | 6 | ||||
| -rw-r--r-- | kernel/panic.c | 5 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 2 | ||||
| -rw-r--r-- | kernel/signal.c | 2 | ||||
| -rw-r--r-- | kernel/time/timer.c | 22 | ||||
| -rw-r--r-- | kernel/trace/Kconfig | 2 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 16 | ||||
| -rw-r--r-- | kernel/trace/trace.h | 1 | ||||
| -rw-r--r-- | kernel/trace/trace_functions_graph.c | 6 |
14 files changed, 102 insertions, 71 deletions
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 0a495ab35bc7..d8560ee3bab7 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -58,36 +58,13 @@ static void context_tracking_recursion_exit(void) * instructions to execute won't use any RCU read side critical section * because this function sets RCU in extended quiescent state. */ -void context_tracking_enter(enum ctx_state state) +void __context_tracking_enter(enum ctx_state state) { - unsigned long flags; - - /* - * Repeat the user_enter() check here because some archs may be calling - * this from asm and if no CPU needs context tracking, they shouldn't - * go further. Repeat the check here until they support the inline static - * key check. - */ - if (!context_tracking_is_enabled()) - return; - - /* - * Some contexts may involve an exception occuring in an irq, - * leading to that nesting: - * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() - * This would mess up the dyntick_nesting count though. And rcu_irq_*() - * helpers are enough to protect RCU uses inside the exception. So - * just return immediately if we detect we are in an IRQ. - */ - if (in_interrupt()) - return; - /* Kernel threads aren't supposed to go to userspace */ WARN_ON_ONCE(!current->mm); - local_irq_save(flags); if (!context_tracking_recursion_enter()) - goto out_irq_restore; + return; if ( __this_cpu_read(context_tracking.state) != state) { if (__this_cpu_read(context_tracking.active)) { @@ -120,7 +97,27 @@ void context_tracking_enter(enum ctx_state state) __this_cpu_write(context_tracking.state, state); } context_tracking_recursion_exit(); -out_irq_restore: +} +NOKPROBE_SYMBOL(__context_tracking_enter); +EXPORT_SYMBOL_GPL(__context_tracking_enter); + +void context_tracking_enter(enum ctx_state state) +{ + unsigned long flags; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + local_irq_save(flags); + __context_tracking_enter(state); local_irq_restore(flags); } NOKPROBE_SYMBOL(context_tracking_enter); @@ -128,7 +125,7 @@ EXPORT_SYMBOL_GPL(context_tracking_enter); void context_tracking_user_enter(void) { - context_tracking_enter(CONTEXT_USER); + user_enter(); } NOKPROBE_SYMBOL(context_tracking_user_enter); @@ -144,19 +141,10 @@ NOKPROBE_SYMBOL(context_tracking_user_enter); * This call supports re-entrancy. This way it can be called from any exception * handler without needing to know if we came from userspace or not. */ -void context_tracking_exit(enum ctx_state state) +void __context_tracking_exit(enum ctx_state state) { - unsigned long flags; - - if (!context_tracking_is_enabled()) - return; - - if (in_interrupt()) - return; - - local_irq_save(flags); if (!context_tracking_recursion_enter()) - goto out_irq_restore; + return; if (__this_cpu_read(context_tracking.state) == state) { if (__this_cpu_read(context_tracking.active)) { @@ -173,7 +161,19 @@ void context_tracking_exit(enum ctx_state state) __this_cpu_write(context_tracking.state, CONTEXT_KERNEL); } context_tracking_recursion_exit(); -out_irq_restore: +} +NOKPROBE_SYMBOL(__context_tracking_exit); +EXPORT_SYMBOL_GPL(__context_tracking_exit); + +void context_tracking_exit(enum ctx_state state) +{ + unsigned long flags; + + if (in_interrupt()) + return; + + local_irq_save(flags); + __context_tracking_exit(state); local_irq_restore(flags); } NOKPROBE_SYMBOL(context_tracking_exit); @@ -181,7 +181,7 @@ EXPORT_SYMBOL_GPL(context_tracking_exit); void context_tracking_user_exit(void) { - context_tracking_exit(CONTEXT_USER); + user_exit(); } NOKPROBE_SYMBOL(context_tracking_user_exit); diff --git a/kernel/events/core.c b/kernel/events/core.c index 1a734e0adfa7..36babfd20648 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1050,13 +1050,13 @@ retry: /* * One of the few rules of preemptible RCU is that one cannot do * rcu_read_unlock() while holding a scheduler (or nested) lock when - * part of the read side critical section was preemptible -- see + * part of the read side critical section was irqs-enabled -- see * rcu_read_unlock_special(). * * Since ctx->lock nests under rq->lock we must ensure the entire read - * side critical section is non-preemptible. + * side critical section has interrupts disabled. */ - preempt_disable(); + local_irq_save(*flags); rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp[ctxn]); if (ctx) { @@ -1070,21 +1070,22 @@ retry: * if so. If we locked the right context, then it * can't get swapped on us any more. */ - raw_spin_lock_irqsave(&ctx->lock, *flags); + raw_spin_lock(&ctx->lock); if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) { - raw_spin_unlock_irqrestore(&ctx->lock, *flags); + raw_spin_unlock(&ctx->lock); rcu_read_unlock(); - preempt_enable(); + local_irq_restore(*flags); goto retry; } if (!atomic_inc_not_zero(&ctx->refcount)) { - raw_spin_unlock_irqrestore(&ctx->lock, *flags); + raw_spin_unlock(&ctx->lock); ctx = NULL; } } rcu_read_unlock(); - preempt_enable(); + if (!ctx) + local_irq_restore(*flags); return ctx; } @@ -6913,6 +6914,10 @@ static int perf_tp_filter_match(struct perf_event *event, { void *record = data->raw->data; + /* only top level events have filters set */ + if (event->parent) + event = event->parent; + if (likely(!event->filter) || filter_match_preds(event->filter, record)) return 1; return 0; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 05c2188271b8..fcab63c66905 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -199,6 +199,11 @@ static inline int irq_desc_get_node(struct irq_desc *desc) return irq_common_data_get_node(&desc->irq_common_data); } +static inline int irq_desc_is_chained(struct irq_desc *desc) +{ + return (desc->action && desc->action == &chained_action); +} + #ifdef CONFIG_PM_SLEEP bool irq_pm_check_wakeup(struct irq_desc *desc); void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action); diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c index e80c4400118a..cea1de0161f1 100644 --- a/kernel/irq/pm.c +++ b/kernel/irq/pm.c @@ -70,7 +70,8 @@ void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) static bool suspend_device_irq(struct irq_desc *desc) { - if (!desc->action || desc->no_suspend_depth) + if (!desc->action || irq_desc_is_chained(desc) || + desc->no_suspend_depth) return false; if (irqd_is_wakeup_set(&desc->irq_data)) { diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index a916cf144b65..a2c02fd5d6d0 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -475,7 +475,7 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(j) any_count |= kstat_irqs_cpu(i, j); action = desc->action; - if ((!action || action == &chained_action) && !any_count) + if ((!action || irq_desc_is_chained(desc)) && !any_count) goto out; seq_printf(p, "%*d: ", prec, i); diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 6e5344112419..db545cbcdb89 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -294,6 +294,12 @@ static int klp_write_object_relocations(struct module *pmod, for (reloc = obj->relocs; reloc->name; reloc++) { if (!klp_is_module(obj)) { + +#if defined(CONFIG_RANDOMIZE_BASE) + /* If KASLR has been enabled, adjust old value accordingly */ + if (kaslr_enabled()) + reloc->val += kaslr_offset(); +#endif ret = klp_verify_vmlinux_symbol(reloc->name, reloc->val); if (ret) diff --git a/kernel/panic.c b/kernel/panic.c index 4579dbb7ed87..4b150bc0c6c1 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -152,8 +152,11 @@ void panic(const char *fmt, ...) * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the - * result. The release will also print the buffers out. + * result. The release will also print the buffers out. Locks debug + * should be disabled to avoid reporting bad unlock balance when + * panic() is not being callled from OOPS. */ + debug_locks_off(); console_trylock(); console_unlock(); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 824aa9f501a3..f04fda8f669c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2302,7 +2302,7 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) now = curr->se.sum_exec_runtime; period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; - if (now - curr->node_stamp > period) { + if (now > curr->node_stamp + period) { if (!curr->node_stamp) curr->numa_scan_period = task_scan_min(curr); curr->node_stamp += period; diff --git a/kernel/signal.c b/kernel/signal.c index c0b01fe24bbd..f3f1f7a972fd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3503,7 +3503,7 @@ SYSCALL_DEFINE0(pause) #endif -int sigsuspend(sigset_t *set) +static int sigsuspend(sigset_t *set) { current->saved_sigmask = current->blocked; set_current_blocked(set); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 74591ba9474f..bbc5d1114583 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -977,13 +977,29 @@ EXPORT_SYMBOL(add_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu); + struct tvec_base *new_base = per_cpu_ptr(&tvec_bases, cpu); + struct tvec_base *base; unsigned long flags; timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); - spin_lock_irqsave(&base->lock, flags); - timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; + + /* + * If @timer was on a different CPU, it should be migrated with the + * old base locked to prevent other operations proceeding with the + * wrong base locked. See lock_timer_base(). + */ + base = lock_timer_base(timer, &flags); + if (base != new_base) { + timer->flags |= TIMER_MIGRATING; + + spin_unlock(&base->lock); + base = new_base; + spin_lock(&base->lock); + WRITE_ONCE(timer->flags, + (timer->flags & ~TIMER_BASEMASK) | cpu); + } + debug_activate(timer, timer->expires); internal_add_timer(base, timer); spin_unlock_irqrestore(&base->lock, flags); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8d6363f42169..e45db6b0d878 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -434,7 +434,7 @@ config UPROBE_EVENT config BPF_EVENTS depends on BPF_SYSCALL - depends on KPROBE_EVENT || UPROBE_EVENT + depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS bool default y help diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 2198a630ef58..87fb9801bd9e 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -100,8 +100,6 @@ static DEFINE_PER_CPU(bool, trace_cmdline_save); */ static int tracing_disabled = 1; -DEFINE_PER_CPU(int, ftrace_cpu_disabled); - cpumask_var_t __read_mostly tracing_buffer_mask; /* @@ -1775,10 +1773,6 @@ trace_function(struct trace_array *tr, struct ring_buffer_event *event; struct ftrace_entry *entry; - /* If we are reading the ring buffer, don't trace */ - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return; - event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry), flags, pc); if (!event) @@ -4554,6 +4548,8 @@ out: return ret; } +#ifdef CONFIG_TRACER_MAX_TRACE + static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) @@ -4568,6 +4564,8 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf, return tracing_nsecs_write(filp->private_data, ubuf, cnt, ppos); } +#endif + static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; @@ -5469,12 +5467,14 @@ static const struct file_operations tracing_thresh_fops = { .llseek = generic_file_llseek, }; +#ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic, .read = tracing_max_lat_read, .write = tracing_max_lat_write, .llseek = generic_file_llseek, }; +#endif static const struct file_operations set_tracer_fops = { .open = tracing_open_generic, @@ -6847,7 +6847,9 @@ struct dentry *tracing_init_dentry(void) if (tr->dir) return NULL; - if (WARN_ON(!debugfs_initialized())) + if (WARN_ON(!tracefs_initialized()) || + (IS_ENABLED(CONFIG_DEBUG_FS) && + WARN_ON(!debugfs_initialized()))) return ERR_PTR(-ENODEV); /* diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index dd7620802e72..919d9d07686f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -667,7 +667,6 @@ extern int DYN_FTRACE_TEST_NAME2(void); extern bool ring_buffer_expanded; extern bool tracing_selftest_disabled; -DECLARE_PER_CPU(int, ftrace_cpu_disabled); #ifdef CONFIG_FTRACE_STARTUP_TEST extern int trace_selftest_startup_function(struct tracer *trace, diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 92382af7a213..a663cbb84107 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -288,9 +288,6 @@ int __trace_graph_entry(struct trace_array *tr, struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ent_entry *entry; - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return 0; - event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT, sizeof(*entry), flags, pc); if (!event) @@ -403,9 +400,6 @@ void __trace_graph_return(struct trace_array *tr, struct ring_buffer *buffer = tr->trace_buffer.buffer; struct ftrace_graph_ret_entry *entry; - if (unlikely(__this_cpu_read(ftrace_cpu_disabled))) - return; - event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET, sizeof(*entry), flags, pc); if (!event) |