diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/bpf/verifier.c | 1 | ||||
| -rw-r--r-- | kernel/cgroup/cgroup.c | 1 | ||||
| -rw-r--r-- | kernel/exit.c | 6 | ||||
| -rw-r--r-- | kernel/fork.c | 2 | ||||
| -rw-r--r-- | kernel/kprobes.c | 8 | ||||
| -rw-r--r-- | kernel/kthread.c | 41 | ||||
| -rw-r--r-- | kernel/sched/ext.c | 6 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 11 | ||||
| -rw-r--r-- | kernel/time/time.c | 2 | ||||
| -rw-r--r-- | kernel/trace/bpf_trace.c | 4 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_events.c | 58 | ||||
| -rw-r--r-- | kernel/workqueue.c | 2 |
13 files changed, 81 insertions, 67 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 74d645add518..648c4bd3e5a9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -24081,7 +24081,6 @@ BTF_ID(func, __x64_sys_exit_group) BTF_ID(func, do_exit) BTF_ID(func, do_group_exit) BTF_ID(func, kthread_complete_and_exit) -BTF_ID(func, kthread_exit) BTF_ID(func, make_task_dead) BTF_SET_END(noreturn_deny) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index fdee387f0d6b..da5f6f5400af 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2611,6 +2611,7 @@ static void cgroup_migrate_add_task(struct task_struct *task, mgctx->tset.nr_tasks++; + css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, diff --git a/kernel/exit.c b/kernel/exit.c index 9f74e8f1c431..c8c3ff935a84 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -897,11 +897,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code) void __noreturn do_exit(long code) { struct task_struct *tsk = current; + struct kthread *kthread; int group_dead; WARN_ON(irqs_disabled()); WARN_ON(tsk->plug); + kthread = tsk_is_kthread(tsk); + if (unlikely(kthread)) + kthread_do_exit(kthread, code); + kcov_task_exit(tsk); kmsan_task_exit(tsk); @@ -1008,6 +1013,7 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } +EXPORT_SYMBOL(do_exit); void __noreturn make_task_dead(int signr) { diff --git a/kernel/fork.c b/kernel/fork.c index 3da0f08615a9..924a9e10106b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -3040,7 +3040,7 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) return 0; /* don't need lock here; in the worst case we'll do useless copy */ - if (fs->users == 1) + if (!(unshare_flags & CLONE_NEWNS) && fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ab8f9fc1f0d1..87e6f4d61b95 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1070,12 +1070,12 @@ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, lockdep_assert_held(&kprobe_mutex); ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0); - if (WARN_ONCE(ret < 0, "Failed to arm kprobe-ftrace at %pS (error %d)\n", p->addr, ret)) + if (ret < 0) return ret; if (*cnt == 0) { ret = register_ftrace_function(ops); - if (WARN(ret < 0, "Failed to register kprobe-ftrace (error %d)\n", ret)) { + if (ret < 0) { /* * At this point, sinec ops is not registered, we should be sefe from * registering empty filter. @@ -1104,6 +1104,10 @@ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int ret; lockdep_assert_held(&kprobe_mutex); + if (unlikely(kprobe_ftrace_disabled)) { + /* Now ftrace is disabled forever, disarm is already done. */ + return 0; + } if (*cnt == 1) { ret = unregister_ftrace_function(ops); diff --git a/kernel/kthread.c b/kernel/kthread.c index 31b072e8d427..d2ee1d982a4d 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k) return k->worker_private; } -/* - * Variant of to_kthread() that doesn't assume @p is a kthread. - * - * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will - * always remain a kthread. For kthreads p->worker_private always - * points to a struct kthread. For tasks that are not kthreads - * p->worker_private is used to point to other things. - * - * Return NULL for any task that is not a kthread. - */ -static inline struct kthread *__to_kthread(struct task_struct *p) -{ - void *kthread = p->worker_private; - if (kthread && !(p->flags & PF_KTHREAD)) - kthread = NULL; - return kthread; -} - void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); @@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { - struct kthread *kthread = __to_kthread(current); + struct kthread *kthread = tsk_is_kthread(current); if (!kthread) return false; @@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); */ void *kthread_func(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); if (kthread) return kthread->threadfn; return NULL; @@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data); */ void *kthread_probe_data(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); void *data = NULL; if (kthread) @@ -309,19 +291,8 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -/** - * kthread_exit - Cause the current kthread return @result to kthread_stop(). - * @result: The integer value to return to kthread_stop(). - * - * While kthread_exit can be called directly, it exists so that - * functions which do some additional work in non-modular code such as - * module_put_and_kthread_exit can be implemented. - * - * Does not return. - */ -void __noreturn kthread_exit(long result) +void kthread_do_exit(struct kthread *kthread, long result) { - struct kthread *kthread = to_kthread(current); kthread->result = result; if (!list_empty(&kthread->hotplug_node)) { mutex_lock(&kthreads_hotplug_lock); @@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result) kthread->preferred_affinity = NULL; } } - do_exit(0); } -EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. @@ -682,7 +651,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu) bool kthread_is_per_cpu(struct task_struct *p) { - struct kthread *kthread = __to_kthread(p); + struct kthread *kthread = tsk_is_kthread(p); if (!kthread) return false; diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 2ff7034841c7..81d40b740d36 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1358,16 +1358,15 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at) p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT; } -static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags) +static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags) { struct scx_sched *sch = scx_root; int sticky_cpu = p->scx.sticky_cpu; + u64 enq_flags = core_enq_flags | rq->scx.extra_enq_flags; if (enq_flags & ENQUEUE_WAKEUP) rq->scx.flags |= SCX_RQ_IN_WAKEUP; - enq_flags |= rq->scx.extra_enq_flags; - if (sticky_cpu >= 0) p->scx.sticky_cpu = -1; @@ -3450,7 +3449,6 @@ static int scx_cgroup_init(struct scx_sched *sch) ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { - css_put(css); scx_error(sch, "ops.cgroup_init() failed (%d)", ret); return ret; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index ac9690805be4..d9c515da328e 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -219,7 +219,7 @@ static void cpuidle_idle_call(void) next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns); call_cpuidle(drv, dev, next_state); - } else { + } else if (drv->state_count > 1) { bool stop_tick = true; /* @@ -237,6 +237,15 @@ static void cpuidle_idle_call(void) * Give the governor an opportunity to reflect on the outcome */ cpuidle_reflect(dev, entered_state); + } else { + tick_nohz_idle_retain_tick(); + + /* + * If there is only a single idle state (or none), there is + * nothing meaningful for the governor to choose. Skip the + * governor and always use state 0. + */ + call_cpuidle(drv, dev, 0); } exit_idle: diff --git a/kernel/time/time.c b/kernel/time/time.c index 0ba8e3c50d62..155cf7def914 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -702,7 +702,7 @@ EXPORT_SYMBOL(clock_t_to_jiffies); * * Return: jiffies_64 value converted to 64-bit "clock_t" (CLOCKS_PER_SEC) */ -u64 jiffies_64_to_clock_t(u64 x) +notrace u64 jiffies_64_to_clock_t(u64 x) { #if (TICK_NSEC % (NSEC_PER_SEC / USER_HZ)) == 0 # if HZ < USER_HZ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ae64b261de8e..d8da00fe73f0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2441,8 +2441,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_kprobe_multi_link *kmulti_link; + bool has_cookies; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + has_cookies = !!kmulti_link->cookies; seq_printf(seq, "kprobe_cnt:\t%u\n" @@ -2454,7 +2456,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, for (int i = 0; i < kmulti_link->cnt; i++) { seq_printf(seq, "%llu\t %pS\n", - kmulti_link->cookies[i], + has_cookies ? kmulti_link->cookies[i] : 0, (void *)kmulti_link->addrs[i]); } } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 38fab063c368..ff5d0b6d52e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9849,7 +9849,7 @@ static void setup_trace_scratch(struct trace_array *tr, } static int -allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) +allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, unsigned long size) { enum ring_buffer_flags rb_flags; struct trace_scratch *tscratch; @@ -9904,7 +9904,7 @@ static void free_trace_buffer(struct array_buffer *buf) } } -static int allocate_trace_buffers(struct trace_array *tr, int size) +static int allocate_trace_buffers(struct trace_array *tr, unsigned long size) { int ret; @@ -11186,7 +11186,7 @@ __init static void enable_instances(void) __init static int tracer_alloc_buffers(void) { - int ring_buf_size; + unsigned long ring_buf_size; int ret = -ENOMEM; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index e4ce7f856f63..b86f128ff99f 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4342,7 +4342,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { - strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + if (bootup_event_buf[0] != '\0') + strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE); + + strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE); + trace_set_ring_buffer_expanded(NULL); disable_tracing_selftest("running event tracing"); @@ -4513,26 +4517,22 @@ static __init int event_trace_memsetup(void) return 0; } -__init void -early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +/* + * Helper function to enable or disable a comma-separated list of events + * from the bootup buffer. + */ +static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable) { char *token; - int ret; - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; + while ((token = strsep(&buf, ","))) { if (*token) { - /* Restarting syscalls requires that we stop them first */ - if (disable_first) + if (enable) { + if (ftrace_set_clr_event(tr, token, 1)) + pr_warn("Failed to enable trace event: %s\n", token); + } else { ftrace_set_clr_event(tr, token, 0); - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); + } } /* Put back the comma to allow this to be called again */ @@ -4541,6 +4541,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first) } } +/** + * early_enable_events - enable events from the bootup buffer + * @tr: The trace array to enable the events in + * @buf: The buffer containing the comma separated list of events + * @disable_first: If true, disable all events in @buf before enabling them + * + * This function enables events from the bootup buffer. If @disable_first + * is true, it will first disable all events in the buffer before enabling + * them. + * + * For syscall events, which rely on a global refcount to register the + * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must + * ensure the refcount hits zero before re-enabling them. A simple + * "disable then enable" per-event is not enough if multiple syscalls are + * used, as the refcount will stay above zero. Thus, we need a two-phase + * approach: disable all, then enable all. + */ +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +{ + if (disable_first) + __early_set_events(tr, buf, false); + + __early_set_events(tr, buf, true); +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 885a8b31f855..9111ef6ccfe6 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -6269,7 +6269,7 @@ static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; - if (pool->flags & WQ_BH) + if (pool->flags & POOL_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else |