diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/Makefile | 6 | ||||
| -rw-r--r-- | kernel/bpf/core.c | 12 | ||||
| -rw-r--r-- | kernel/events/core.c | 41 | ||||
| -rw-r--r-- | kernel/irq/dummychip.c | 1 | ||||
| -rw-r--r-- | kernel/kexec.c | 2 | ||||
| -rw-r--r-- | kernel/locking/rtmutex.c | 12 | ||||
| -rw-r--r-- | kernel/rcu/tree.c | 16 | ||||
| -rw-r--r-- | kernel/sched/core.c | 69 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 16 | ||||
| -rw-r--r-- | kernel/time/clockevents.c | 6 | ||||
| -rw-r--r-- | kernel/trace/trace_output.c | 3 |
11 files changed, 91 insertions, 93 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 0f8f8b0bc1bf..60c302cfb4d3 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -197,9 +197,9 @@ x509.genkey: @echo >>x509.genkey "x509_extensions = myexts" @echo >>x509.genkey @echo >>x509.genkey "[ req_distinguished_name ]" - @echo >>x509.genkey "O = Magrathea" - @echo >>x509.genkey "CN = Glacier signing key" - @echo >>x509.genkey "emailAddress = slartibartfast@magrathea.h2g2" + @echo >>x509.genkey "#O = Unspecified company" + @echo >>x509.genkey "CN = Build time autogenerated kernel key" + @echo >>x509.genkey "#emailAddress = unspecified.user@unspecified.company" @echo >>x509.genkey @echo >>x509.genkey "[ myexts ]" @echo >>x509.genkey "basicConstraints=critical,CA:FALSE" diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4139a0f8b558..54f0e7fcd0e2 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -357,8 +357,8 @@ select_insn: ALU64_MOD_X: if (unlikely(SRC == 0)) return 0; - tmp = DST; - DST = do_div(tmp, SRC); + div64_u64_rem(DST, SRC, &tmp); + DST = tmp; CONT; ALU_MOD_X: if (unlikely(SRC == 0)) @@ -367,8 +367,8 @@ select_insn: DST = do_div(tmp, (u32) SRC); CONT; ALU64_MOD_K: - tmp = DST; - DST = do_div(tmp, IMM); + div64_u64_rem(DST, IMM, &tmp); + DST = tmp; CONT; ALU_MOD_K: tmp = (u32) DST; @@ -377,7 +377,7 @@ select_insn: ALU64_DIV_X: if (unlikely(SRC == 0)) return 0; - do_div(DST, SRC); + DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: if (unlikely(SRC == 0)) @@ -387,7 +387,7 @@ select_insn: DST = (u32) tmp; CONT; ALU64_DIV_K: - do_div(DST, IMM); + DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: tmp = (u32) DST; diff --git a/kernel/events/core.c b/kernel/events/core.c index 81aa3a4ece9f..1a3bf48743ce 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -913,10 +913,30 @@ static void put_ctx(struct perf_event_context *ctx) * Those places that change perf_event::ctx will hold both * perf_event_ctx::mutex of the 'old' and 'new' ctx value. * - * Lock ordering is by mutex address. There is one other site where - * perf_event_context::mutex nests and that is put_event(). But remember that - * that is a parent<->child context relation, and migration does not affect - * children, therefore these two orderings should not interact. + * Lock ordering is by mutex address. There are two other sites where + * perf_event_context::mutex nests and those are: + * + * - perf_event_exit_task_context() [ child , 0 ] + * __perf_event_exit_task() + * sync_child_event() + * put_event() [ parent, 1 ] + * + * - perf_event_init_context() [ parent, 0 ] + * inherit_task_group() + * inherit_group() + * inherit_event() + * perf_event_alloc() + * perf_init_event() + * perf_try_init_event() [ child , 1 ] + * + * While it appears there is an obvious deadlock here -- the parent and child + * nesting levels are inverted between the two. This is in fact safe because + * life-time rules separate them. That is an exiting task cannot fork, and a + * spawning task cannot (yet) exit. + * + * But remember that that these are parent<->child context relations, and + * migration does not affect children, therefore these two orderings should not + * interact. * * The change in perf_event::ctx does not affect children (as claimed above) * because the sys_perf_event_open() case will install a new event and break @@ -3657,9 +3677,6 @@ static void perf_remove_from_owner(struct perf_event *event) } } -/* - * Called when the last reference to the file is gone. - */ static void put_event(struct perf_event *event) { struct perf_event_context *ctx; @@ -3697,6 +3714,9 @@ int perf_event_release_kernel(struct perf_event *event) } EXPORT_SYMBOL_GPL(perf_event_release_kernel); +/* + * Called when the last reference to the file is gone. + */ static int perf_release(struct inode *inode, struct file *file) { put_event(file->private_data); @@ -7364,7 +7384,12 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) return -ENODEV; if (event->group_leader != event) { - ctx = perf_event_ctx_lock(event->group_leader); + /* + * This ctx->mutex can nest when we're called through + * inheritance. See the perf_event_ctx_lock_nested() comment. + */ + ctx = perf_event_ctx_lock_nested(event->group_leader, + SINGLE_DEPTH_NESTING); BUG_ON(!ctx); } diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c index 988dc58e8847..2feb6feca0cc 100644 --- a/kernel/irq/dummychip.c +++ b/kernel/irq/dummychip.c @@ -57,5 +57,6 @@ struct irq_chip dummy_irq_chip = { .irq_ack = noop, .irq_mask = noop, .irq_unmask = noop, + .flags = IRQCHIP_SKIP_SET_WAKE, }; EXPORT_SYMBOL_GPL(dummy_irq_chip); diff --git a/kernel/kexec.c b/kernel/kexec.c index 38c25b1f2fd5..7a36fdcca5bf 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -707,7 +707,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, do { unsigned long pfn, epfn, addr, eaddr; - pages = kimage_alloc_pages(GFP_KERNEL, order); + pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_pfn(pages); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b73279367087..b025295f4966 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task) } /* - * Called by sched_setscheduler() to check whether the priority change - * is overruled by a possible priority boosting. + * Called by sched_setscheduler() to get the priority which will be + * effective after the change. */ -int rt_mutex_check_prio(struct task_struct *task, int newprio) +int rt_mutex_get_effective_prio(struct task_struct *task, int newprio) { if (!task_has_pi_waiters(task)) - return 0; + return newprio; - return task_top_pi_waiter(task)->task->prio <= newprio; + if (task_top_pi_waiter(task)->task->prio <= newprio) + return task_top_pi_waiter(task)->task->prio; + return newprio; } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 233165da782f..8cf7304b2867 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -162,11 +162,14 @@ static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); static int kthread_prio = CONFIG_RCU_KTHREAD_PRIO; module_param(kthread_prio, int, 0644); -/* Delay in jiffies for grace-period initialization delays. */ -static int gp_init_delay = IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) - ? CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY - : 0; +/* Delay in jiffies for grace-period initialization delays, debug only. */ +#ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT +static int gp_init_delay = CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY; module_param(gp_init_delay, int, 0644); +#else /* #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ +static const int gp_init_delay; +#endif /* #else #ifdef CONFIG_RCU_TORTURE_TEST_SLOW_INIT */ +#define PER_RCU_NODE_PERIOD 10 /* Number of grace periods between delays. */ /* * Track the rcutorture test sequence number and the update version @@ -1843,9 +1846,8 @@ static int rcu_gp_init(struct rcu_state *rsp) raw_spin_unlock_irq(&rnp->lock); cond_resched_rcu_qs(); ACCESS_ONCE(rsp->gp_activity) = jiffies; - if (IS_ENABLED(CONFIG_RCU_TORTURE_TEST_SLOW_INIT) && - gp_init_delay > 0 && - !(rsp->gpnum % (rcu_num_nodes * 10))) + if (gp_init_delay > 0 && + !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD))) schedule_timeout_uninterruptible(gp_init_delay); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9123a82cbb6..57bd333bc4ab 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } -static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); - -void register_task_migration_notifier(struct notifier_block *n) -{ - atomic_notifier_chain_register(&task_migration_notifier, n); -} - #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { - struct task_migration_notifier tmn; - if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); - - tmn.task = p; - tmn.from_cpu = task_cpu(p); - tmn.to_cpu = new_cpu; - - atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); @@ -3315,15 +3300,18 @@ static void __setscheduler_params(struct task_struct *p, /* Actually do priority change: must hold pi & rq lock. */ static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr) + const struct sched_attr *attr, bool keep_boost) { __setscheduler_params(p, attr); /* - * If we get here, there was no pi waiters boosting the - * task. It is safe to use the normal prio. + * Keep a potential priority boosting if called from + * sched_setscheduler(). */ - p->prio = normal_prio(p); + if (keep_boost) + p->prio = rt_mutex_get_effective_prio(p, normal_prio(p)); + else + p->prio = normal_prio(p); if (dl_prio(p->prio)) p->sched_class = &dl_sched_class; @@ -3423,7 +3411,7 @@ static int __sched_setscheduler(struct task_struct *p, int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, queued, running; - int policy = attr->sched_policy; + int new_effective_prio, policy = attr->sched_policy; unsigned long flags; const struct sched_class *prev_class; struct rq *rq; @@ -3605,15 +3593,14 @@ change: oldprio = p->prio; /* - * Special case for priority boosted tasks. - * - * If the new priority is lower or equal (user space view) - * than the current (boosted) priority, we just store the new + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new * normal parameters and do not touch the scheduler class and * the runqueue. This will be done when the task deboost * itself. */ - if (rt_mutex_check_prio(p, newprio)) { + new_effective_prio = rt_mutex_get_effective_prio(p, newprio); + if (new_effective_prio == oldprio) { __setscheduler_params(p, attr); task_rq_unlock(rq, p, &flags); return 0; @@ -3627,7 +3614,7 @@ change: put_prev_task(rq, p); prev_class = p->sched_class; - __setscheduler(rq, p, attr); + __setscheduler(rq, p, attr, true); if (running) p->sched_class->set_curr_task(rq); @@ -7012,27 +6999,23 @@ static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, unsigned long flags; long cpu = (long)hcpu; struct dl_bw *dl_b; + bool overflow; + int cpus; - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { case CPU_DOWN_PREPARE: - /* explicitly allow suspend */ - if (!(action & CPU_TASKS_FROZEN)) { - bool overflow; - int cpus; - - rcu_read_lock_sched(); - dl_b = dl_bw_of(cpu); + rcu_read_lock_sched(); + dl_b = dl_bw_of(cpu); - raw_spin_lock_irqsave(&dl_b->lock, flags); - cpus = dl_bw_cpus(cpu); - overflow = __dl_overflow(dl_b, cpus, 0, 0); - raw_spin_unlock_irqrestore(&dl_b->lock, flags); + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); - rcu_read_unlock_sched(); + rcu_read_unlock_sched(); - if (overflow) - return notifier_from_errno(-EBUSY); - } + if (overflow) + return notifier_from_errno(-EBUSY); cpuset_update_active_cpus(false); break; case CPU_DOWN_PREPARE_FROZEN: @@ -7361,7 +7344,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) queued = task_on_rq_queued(p); if (queued) dequeue_task(rq, p, 0); - __setscheduler(rq, p, &attr); + __setscheduler(rq, p, &attr, false); if (queued) { enqueue_task(rq, p, 0); resched_curr(rq); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index deef1caa94c6..fefcb1fa5160 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,7 +81,6 @@ static void cpuidle_idle_call(void) struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); int next_state, entered_state; - unsigned int broadcast; bool reflect; /* @@ -150,17 +149,6 @@ static void cpuidle_idle_call(void) goto exit_idle; } - broadcast = drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP; - - /* - * Tell the time framework to switch to a broadcast timer - * because our local timer will be shutdown. If a local timer - * is used from another cpu as a broadcast timer, this call may - * fail if it is not available - */ - if (broadcast && tick_broadcast_enter()) - goto use_default; - /* Take note of the planned idle state. */ idle_set_state(this_rq(), &drv->states[next_state]); @@ -174,8 +162,8 @@ static void cpuidle_idle_call(void) /* The cpu is no longer idle or about to enter idle. */ idle_set_state(this_rq(), NULL); - if (broadcast) - tick_broadcast_exit(); + if (entered_state == -EBUSY) + goto use_default; /* * Give the governor an opportunity to reflect on the outcome diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 11dc22a6983b..637a09461c1d 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -117,11 +117,7 @@ static int __clockevents_set_state(struct clock_event_device *dev, /* Transition with new state-specific callbacks */ switch (state) { case CLOCK_EVT_STATE_DETACHED: - /* - * This is an internal state, which is guaranteed to go from - * SHUTDOWN to DETACHED. No driver interaction required. - */ - return 0; + /* The clockevent device is getting replaced. Shut it down. */ case CLOCK_EVT_STATE_SHUTDOWN: return dev->set_state_shutdown(dev); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 692bf7184c8c..25a086bcb700 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -178,12 +178,13 @@ ftrace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len) EXPORT_SYMBOL(ftrace_print_hex_seq); const char * -ftrace_print_array_seq(struct trace_seq *p, const void *buf, int buf_len, +ftrace_print_array_seq(struct trace_seq *p, const void *buf, int count, size_t el_size) { const char *ret = trace_seq_buffer_ptr(p); const char *prefix = ""; void *ptr = (void *)buf; + size_t buf_len = count * el_size; trace_seq_putc(p, '{'); |