diff options
Diffstat (limited to 'kernel')
37 files changed, 1324 insertions, 825 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..7b62df86be1d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ select_insn: struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 959c9a07f318..e093d9a2c4dd 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -75,8 +75,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr) static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; + int err = -EINVAL; u64 cost; - int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -108,6 +108,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (err) goto free_dtab; + err = -ENOMEM; + /* A per cpu bitfield with a bit per possible net device */ dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), __alignof__(unsigned long)); @@ -128,7 +130,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) free_dtab: free_percpu(dtab->flush_needed); kfree(dtab); - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb17e1cd1d43..25d074920a00 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -186,15 +186,17 @@ static int bpf_map_alloc_id(struct bpf_map *map) static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { + unsigned long flags; + if (do_idr_lock) - spin_lock_bh(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); if (do_idr_lock) - spin_unlock_bh(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 799b2451ef2d..b914fbe1383e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4205,7 +4205,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } if (insn->imm == BPF_FUNC_redirect_map) { - u64 addr = (unsigned long)prog; + /* Note, we cannot use prog directly as imm as subsequent + * rewrites would still change the prog pointer. The only + * stable address we can use is aux, which also works with + * prog clones during blinding. + */ + u64 addr = (unsigned long)prog->aux; struct bpf_insn r4_ld[] = { BPF_LD_IMM64(BPF_REG_4, addr), *insn, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..44857278eb8a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51..d851df22f5c5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> @@ -46,11 +47,13 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -58,18 +61,39 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -123,13 +147,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -137,7 +164,17 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +189,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +199,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -178,12 +226,39 @@ err: hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -271,14 +346,79 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_ap_thread(st, st->bringup); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -286,12 +426,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -317,32 +455,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -350,7 +462,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +474,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -379,7 +491,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -389,69 +502,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) + + if (WARN_ON_ONCE(!st->should_run)) return; - st->should_run = false; + cpuhp_lock_acquire(bringup); - lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); + + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); - undo_cpu_down(cpu, st); - st->rollback = false; + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } - lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + +next: + cpuhp_lock_release(bringup); + + if (!st->should_run) + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -460,62 +594,64 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + + st->rollback = false; + st->last = NULL; + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; + + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); + + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -581,6 +717,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -594,8 +731,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -639,7 +781,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -658,7 +800,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -676,11 +818,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -699,13 +862,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -720,6 +883,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -727,13 +892,17 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } @@ -754,11 +923,15 @@ out: cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -772,11 +945,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } @@ -794,7 +972,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ @@ -829,7 +1007,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1296,6 +1474,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; @@ -1307,9 +1489,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; @@ -1641,9 +1823,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e691b75b2db..6bc21e202ae4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,6 +8171,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) } } event->tp_event->prog = prog; + event->tp_event->bpf_prog_owner = event; return 0; } @@ -8185,7 +8186,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) return; prog = event->tp_event->prog; - if (prog) { + if (prog && event->tp_event->bpf_prog_owner == event) { event->tp_event->prog = NULL; bpf_prog_put(prog); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e12ee..f684d8e5fa2b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ err: return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } diff --git a/kernel/exit.c b/kernel/exit.c index 3481ababd06a..f2cd53e92147 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412401a1..9aa1cc41ecf7 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. @@ -127,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..e702cb9ffbd8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -946,6 +946,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf05492..0518a0bfc746 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f51b7b6d2451..6fc89fd93824 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -202,7 +202,7 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) irqd_clr_managed_shutdown(d); - if (cpumask_any_and(aff, cpu_online_mask) > nr_cpu_ids) { + if (cpumask_any_and(aff, cpu_online_mask) >= nr_cpu_ids) { /* * Catch code which fiddles with enable_irq() on a managed * and potentially shutdown IRQ. Chained interrupt diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b78ad6e..5270a54b9fa4 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b7056bb08..ac4644e92b49 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ out_free_desc: /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52b0806..d00132b5c325 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..055bb2962a0b 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f660666ab8..1fefe6dcafd7 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -613,6 +613,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) DEFINE_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/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fd..403ab9cdb949 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355..cc9108c2a1fd 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } @@ -600,7 +597,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 3e2b4f519009..ccd2d20e6b06 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -120,22 +120,26 @@ static void s2idle_loop(void) * frozen processes + suspended devices + idle processors. * Thus s2idle_enter() should be called right after * all devices have been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, + * so prevent them from terminating the loop right away. */ error = dpm_noirq_suspend_devices(PMSG_SUSPEND); if (!error) s2idle_enter(); + else if (error == -EBUSY && pm_wakeup_pending()) + error = 0; - dpm_noirq_resume_devices(PMSG_RESUME); - if (error && (error != -EBUSY || !pm_wakeup_pending())) { - dpm_noirq_end(); - break; - } - - if (s2idle_ops && s2idle_ops->wake) + if (!error && s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); + if (error) + break; + if (s2idle_ops && s2idle_ops->sync) s2idle_ops->sync(); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1250e4bd4b85..b0ad62b0e7b8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -882,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1015,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966567da..d17c5da523a0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb5a5de..2f93e4a2d9f6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 98b59b5db90b..bb3a38005b9c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -17,11 +17,13 @@ #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> +#include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> +#include <linux/sysctl.h> #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> @@ -42,6 +44,7 @@ * get/put helpers should be used when accessing an instance * outside of a lifetime-guarded section. In general, this * is only needed for handling filters shared across tasks. + * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @@ -57,6 +60,7 @@ */ struct seccomp_filter { refcount_t usage; + bool log; struct seccomp_filter *prev; struct bpf_prog *prog; }; @@ -171,10 +175,15 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters + * @match: stores struct seccomp_filter that resulted in the return value, + * unless filter returned SECCOMP_RET_ALLOW, in which case it will + * be unchanged. * * Returns valid seccomp BPF response codes. */ -static u32 seccomp_run_filters(const struct seccomp_data *sd) +#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) +static u32 seccomp_run_filters(const struct seccomp_data *sd, + struct seccomp_filter **match) { struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; @@ -184,7 +193,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd) /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) - return SECCOMP_RET_KILL; + return SECCOMP_RET_KILL_PROCESS; if (!sd) { populate_seccomp_data(&sd_local); @@ -198,8 +207,10 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd) for (; f; f = f->prev) { u32 cur_ret = BPF_PROG_RUN(f->prog, sd); - if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) + if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; + *match = f; + } } return ret; } @@ -444,6 +455,10 @@ static long seccomp_attach_filter(unsigned int flags, return ret; } + /* Set log flag, if present. */ + if (flags & SECCOMP_FILTER_FLAG_LOG) + filter->log = true; + /* * If there is an existing filter, make it the prev and don't drop its * task reference. @@ -458,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -476,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -488,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -514,6 +538,65 @@ static void seccomp_send_sigsys(int syscall, int reason) } #endif /* CONFIG_SECCOMP_FILTER */ +/* For use with seccomp_actions_logged */ +#define SECCOMP_LOG_KILL_PROCESS (1 << 0) +#define SECCOMP_LOG_KILL_THREAD (1 << 1) +#define SECCOMP_LOG_TRAP (1 << 2) +#define SECCOMP_LOG_ERRNO (1 << 3) +#define SECCOMP_LOG_TRACE (1 << 4) +#define SECCOMP_LOG_LOG (1 << 5) +#define SECCOMP_LOG_ALLOW (1 << 6) + +static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | + SECCOMP_LOG_KILL_THREAD | + SECCOMP_LOG_TRAP | + SECCOMP_LOG_ERRNO | + SECCOMP_LOG_TRACE | + SECCOMP_LOG_LOG; + +static inline void seccomp_log(unsigned long syscall, long signr, u32 action, + bool requested) +{ + bool log = false; + + switch (action) { + case SECCOMP_RET_ALLOW: + break; + case SECCOMP_RET_TRAP: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP; + break; + case SECCOMP_RET_ERRNO: + log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO; + break; + case SECCOMP_RET_TRACE: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; + break; + case SECCOMP_RET_LOG: + log = seccomp_actions_logged & SECCOMP_LOG_LOG; + break; + case SECCOMP_RET_KILL_THREAD: + log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; + break; + case SECCOMP_RET_KILL_PROCESS: + default: + log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS; + } + + /* + * Force an audit message to be emitted when the action is RET_KILL_*, + * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is + * allowed to be logged by the admin. + */ + if (log) + return __audit_seccomp(syscall, signr, action); + + /* + * Let the audit subsystem decide if the action should be audited based + * on whether the current task itself is being audited. + */ + return audit_seccomp(syscall, signr, action); +} + /* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit @@ -539,7 +622,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL); + seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -566,6 +649,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { u32 filter_ret, action; + struct seccomp_filter *match = NULL; int data; /* @@ -574,9 +658,9 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, */ rmb(); - filter_ret = seccomp_run_filters(sd); + filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; - action = filter_ret & SECCOMP_RET_ACTION; + action = filter_ret & SECCOMP_RET_ACTION_FULL; switch (action) { case SECCOMP_RET_ERRNO: @@ -637,14 +721,25 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; + case SECCOMP_RET_LOG: + seccomp_log(this_syscall, 0, action, true); + return 0; + case SECCOMP_RET_ALLOW: + /* + * Note that the "match" filter will always be NULL for + * this action since SECCOMP_RET_ALLOW is the starting + * state in seccomp_run_filters(). + */ return 0; - case SECCOMP_RET_KILL: + case SECCOMP_RET_KILL_THREAD: + case SECCOMP_RET_KILL_PROCESS: default: - audit_seccomp(this_syscall, SIGSYS, action); + seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ - if (get_nr_threads(current) == 1) { + if (action == SECCOMP_RET_KILL_PROCESS || + get_nr_threads(current) == 1) { siginfo_t info; /* Show the original registers in the dump. */ @@ -653,13 +748,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, seccomp_init_siginfo(&info, this_syscall, data); do_coredump(&info); } - do_exit(SIGSYS); + if (action == SECCOMP_RET_KILL_PROCESS) + do_group_exit(SIGSYS); + else + do_exit(SIGSYS); } unreachable(); skip: - audit_seccomp(this_syscall, 0, action); + seccomp_log(this_syscall, 0, action, match ? match->log : false); return -1; } #else @@ -794,6 +892,29 @@ static inline long seccomp_set_mode_filter(unsigned int flags, } #endif +static long seccomp_get_action_avail(const char __user *uaction) +{ + u32 action; + + if (copy_from_user(&action, uaction, sizeof(action))) + return -EFAULT; + + switch (action) { + case SECCOMP_RET_KILL_PROCESS: + case SECCOMP_RET_KILL_THREAD: + case SECCOMP_RET_TRAP: + case SECCOMP_RET_ERRNO: + case SECCOMP_RET_TRACE: + case SECCOMP_RET_LOG: + case SECCOMP_RET_ALLOW: + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, const char __user *uargs) @@ -805,6 +926,11 @@ static long do_seccomp(unsigned int op, unsigned int flags, return seccomp_set_mode_strict(); case SECCOMP_SET_MODE_FILTER: return seccomp_set_mode_filter(flags, uargs); + case SECCOMP_GET_ACTION_AVAIL: + if (flags != 0) + return -EINVAL; + + return seccomp_get_action_avail(uargs); default: return -EINVAL; } @@ -908,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: @@ -922,3 +1048,185 @@ out: return ret; } #endif + +#ifdef CONFIG_SYSCTL + +/* Human readable action names for friendly sysctl interaction */ +#define SECCOMP_RET_KILL_PROCESS_NAME "kill_process" +#define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" +#define SECCOMP_RET_TRAP_NAME "trap" +#define SECCOMP_RET_ERRNO_NAME "errno" +#define SECCOMP_RET_TRACE_NAME "trace" +#define SECCOMP_RET_LOG_NAME "log" +#define SECCOMP_RET_ALLOW_NAME "allow" + +static const char seccomp_actions_avail[] = + SECCOMP_RET_KILL_PROCESS_NAME " " + SECCOMP_RET_KILL_THREAD_NAME " " + SECCOMP_RET_TRAP_NAME " " + SECCOMP_RET_ERRNO_NAME " " + SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_LOG_NAME " " + SECCOMP_RET_ALLOW_NAME; + +struct seccomp_log_name { + u32 log; + const char *name; +}; + +static const struct seccomp_log_name seccomp_log_names[] = { + { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME }, + { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, + { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, + { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, + { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, + { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, + { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, + { } +}; + +static bool seccomp_names_from_actions_logged(char *names, size_t size, + u32 actions_logged) +{ + const struct seccomp_log_name *cur; + bool append_space = false; + + for (cur = seccomp_log_names; cur->name && size; cur++) { + ssize_t ret; + + if (!(actions_logged & cur->log)) + continue; + + if (append_space) { + ret = strscpy(names, " ", size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } else + append_space = true; + + ret = strscpy(names, cur->name, size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } + + return true; +} + +static bool seccomp_action_logged_from_name(u32 *action_logged, + const char *name) +{ + const struct seccomp_log_name *cur; + + for (cur = seccomp_log_names; cur->name; cur++) { + if (!strcmp(cur->name, name)) { + *action_logged = cur->log; + return true; + } + } + + return false; +} + +static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) +{ + char *name; + + *actions_logged = 0; + while ((name = strsep(&names, " ")) && *name) { + u32 action_logged = 0; + + if (!seccomp_action_logged_from_name(&action_logged, name)) + return false; + + *actions_logged |= action_logged; + } + + return true; +} + +static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + char names[sizeof(seccomp_actions_avail)]; + struct ctl_table table; + int ret; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + memset(names, 0, sizeof(names)); + + if (!write) { + if (!seccomp_names_from_actions_logged(names, sizeof(names), + seccomp_actions_logged)) + return -EINVAL; + } + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + ret = proc_dostring(&table, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (write) { + u32 actions_logged; + + if (!seccomp_actions_logged_from_names(&actions_logged, + table.data)) + return -EINVAL; + + if (actions_logged & SECCOMP_LOG_ALLOW) + return -EINVAL; + + seccomp_actions_logged = actions_logged; + } + + return 0; +} + +static struct ctl_path seccomp_sysctl_path[] = { + { .procname = "kernel", }, + { .procname = "seccomp", }, + { } +}; + +static struct ctl_table seccomp_sysctl_table[] = { + { + .procname = "actions_avail", + .data = (void *) &seccomp_actions_avail, + .maxlen = sizeof(seccomp_actions_avail), + .mode = 0444, + .proc_handler = proc_dostring, + }, + { + .procname = "actions_logged", + .mode = 0644, + .proc_handler = seccomp_actions_logged_handler, + }, + { } +}; + +static int __init seccomp_sysctl_init(void) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); + if (!hdr) + pr_warn("seccomp: sysctl registration failed\n"); + else + kmemleak_not_leak(hdr); + + return 0; +} + +device_initcall(seccomp_sysctl_init) + +#endif /* CONFIG_SYSCTL */ diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..5043e7433f4b 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..d9c31bc2eaea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { @@ -871,9 +872,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -889,16 +890,12 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", @@ -910,9 +907,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, @@ -2187,8 +2184,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b45b73b..45a3928544ce 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6abfafd7f173..8319e09e15b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4954,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -6808,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5360b7aec57a..752e5daf0896 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4020,11 +4020,17 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); + struct trace_buffer *trace_buf = &tr->trace_buffer; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->current_trace->print_max) + trace_buf = &tr->max_buffer; +#endif if (cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(trace_buf); else - tracing_reset(&tr->trace_buffer, cpu); + tracing_reset(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { @@ -5358,6 +5364,13 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t == tr->current_trace) goto out; + /* Some tracers won't work on kernel command line */ + if (system_state < SYSTEM_RUNNING && t->noboot) { + pr_warn("Tracer '%s' is not allowed on command line, ignored\n", + t->name); + goto out; + } + /* Some tracers are only allowed for the top level buffer */ if (!trace_ok_for_array(t, tr)) { ret = -EINVAL; @@ -5667,7 +5680,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracing_is_on() && iter->pos) + if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index fb5d54d0d1b3..652c682707cd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -444,6 +444,8 @@ struct tracer { #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif + /* True if tracer cannot be enabled in kernel param */ + bool noboot; }; diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index cd7480d0a201..dca78fc48439 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -282,6 +282,7 @@ static struct tracer mmio_tracer __read_mostly = .close = mmio_close, .read = mmio_read, .print_line = mmio_print_line, + .noboot = true, }; __init static int init_mmio_trace(void) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629af2285..c738e764e2a5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b67646..0c331978b1a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67cbc711..49cb41412eec 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..6bcb854909c0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -29,20 +29,29 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); - -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; + +struct cpumask watchdog_allowed_mask __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif - -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif - -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; +# ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its @@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended; */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + +/** + * watchdog_nmi_stop - Stop the watchdog for reconfiguration + * + * The reconfiguration steps are: + * watchdog_nmi_stop(); + * update_variables(); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration + * + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +void __weak watchdog_nmi_start(void) { } + +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_available && nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -164,50 +181,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); - - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + /* Initialize timestamp */ __touch_watchdog(); + /* Enable the perf event */ + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); + + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { @@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) +static void softlockup_update_smpboot_threads(void) { - int cpu, ret = 0; + lockdep_assert_held(&watchdog_mutex); - atomic_set(&watchdog_park_in_progress, 1); + if (!softlockup_threads_initialized) + return; - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); } -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) { - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); } -static int update_watchdog_all_cpus(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); } -static int watchdog_enable_all_cpus(void) +static void lockup_detector_reconfigure(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; + cpus_read_lock(); + watchdog_nmi_stop(); + softlockup_park_all_threads(); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_unpark_threads(); + watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } -static void watchdog_disable_all_cpus(void) +/* + * Create the watchdog thread infrastructure and configure the detector(s). + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void lockup_detector_setup(void) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} + int ret; -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + lockup_detector_update_enable(); -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; -static void watchdog_unpark_threads(void) -{ -} + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } -static int watchdog_enable_all_cpus(void) -{ - return 0; + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); } -static void watchdog_disable_all_cpus(void) +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static void lockup_detector_reconfigure(void) { + cpus_read_lock(); + watchdog_nmi_stop(); + lockup_detector_update_enable(); + watchdog_nmi_start(); + cpus_read_unlock(); } - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static inline void lockup_detector_setup(void) { - return 0; + lockup_detector_reconfigure(); } -#endif +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -static void set_sample_period(void) +static void __lockup_detector_cleanup(void) { + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); } -#endif /* SOFTLOCKUP */ -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. */ -int lockup_detector_suspend(void) +void lockup_detector_cleanup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); } -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. */ -void lockup_detector_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog threads */ +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -951,6 +783,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; + lockup_detector_setup(); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d..71a62ceacdc8 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -21,8 +21,10 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; @@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) +static int hardlockup_detector_event_create(void) { + unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; + struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Shutting down hard lockup detector on all cpus\n"); - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; + perf_event_enable(this_cpu_read(watchdog_ev)); } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); + watchdog_cpus--; + } +} + +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); per_cpu(watchdog_ev, cpu) = NULL; + } + cpumask_clear(&dead_events_mask); +} + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + if (ret) { + pr_info("Perf NMI watchdog permanently disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); } + return ret; } |