diff options
Diffstat (limited to 'kernel')
83 files changed, 1582 insertions, 838 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index ce77f0265660..5644abd5f8a8 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -132,4 +132,14 @@ config SCHED_CORE which is the likely usage by Linux distributions, there should be no measurable impact on performance. - +config ARCH_WANTS_RT_DELAYED_SIGNALS + bool + help + This option is selected by architectures where raising signals + can happen in atomic contexts on PREEMPT_RT enabled kernels. This + option delays raising the signal until the return to user space + loop where it is also delivered. X86 requires this to deliver + signals from trap handlers which run on IST stacks. + +config RT_DELAYED_SIGNALS + def_bool PREEMPT_RT && ARCH_WANTS_RT_DELAYED_SIGNALS diff --git a/kernel/async.c b/kernel/async.c index b8d7a663497f..b2c4ba5686ee 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -205,9 +205,6 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* mark that this task has queued an async job, used by module init */ - current->flags |= PF_USED_ASYNC; - /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); diff --git a/kernel/audit.c b/kernel/audit.c index e4bbe2c70c26..7690c29d4ee4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -541,20 +541,22 @@ static void kauditd_printk_skb(struct sk_buff *skb) /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record + * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ -static void kauditd_rehold_skb(struct sk_buff *skb) +static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { - /* put the record back in the queue at the same place */ - skb_queue_head(&audit_hold_queue, skb); + /* put the record back in the queue */ + skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record + * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this @@ -564,19 +566,31 @@ static void kauditd_rehold_skb(struct sk_buff *skb) * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ -static void kauditd_hold_skb(struct sk_buff *skb) +static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ - if (!audit_default) { - kfree_skb(skb); - return; + if (!audit_default) + goto drop; + + /* the hold queue is only for when the daemon goes away completely, + * not -EAGAIN failures; if we are in a -EAGAIN state requeue the + * record on the retry queue unless it's full, in which case drop it + */ + if (error == -EAGAIN) { + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + audit_log_lost("kauditd retry queue overflow"); + goto drop; } - /* if we have room, queue the message */ + /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); @@ -585,24 +599,32 @@ static void kauditd_hold_skb(struct sk_buff *skb) /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); +drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record + * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ -static void kauditd_retry_skb(struct sk_buff *skb) +static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { - /* NOTE: because records should only live in the retry queue for a - * short period of time, before either being sent or moved to the hold - * queue, we don't currently enforce a limit on this queue */ - skb_queue_tail(&audit_retry_queue, skb); + if (!audit_backlog_limit || + skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { + skb_queue_tail(&audit_retry_queue, skb); + return; + } + + /* we have to drop the record, send it via printk as a last effort */ + kauditd_printk_skb(skb); + audit_log_lost("kauditd retry queue overflow"); + kfree_skb(skb); } /** @@ -640,7 +662,7 @@ static void auditd_reset(const struct auditd_connection *ac) /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) - kauditd_hold_skb(skb); + kauditd_hold_skb(skb, -ECONNREFUSED); } /** @@ -714,16 +736,18 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), - void (*err_hook)(struct sk_buff *skb)) + void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; - struct sk_buff *skb; + struct sk_buff *skb = NULL; + struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ - while ((skb = skb_dequeue(queue))) { + skb_tail = skb_peek_tail(queue); + while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); @@ -731,7 +755,7 @@ static int kauditd_send_queue(struct sock *sk, u32 portid, /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, -ECONNREFUSED); continue; } @@ -745,7 +769,7 @@ retry: rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) - (*err_hook)(skb); + (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 0efd75e4730f..ea2ee1181921 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -185,7 +185,7 @@ static int audit_match_perm(struct audit_context *ctx, int mask) case AUDITSC_EXECVE: return mask & AUDIT_PERM_EXEC; case AUDITSC_OPENAT2: - return mask & ACC_MODE((u32)((struct open_how *)ctx->argv[2])->flags); + return mask & ACC_MODE((u32)ctx->openat2.flags); default: return 0; } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 06062370c3b8..9e4ecc990647 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -207,7 +207,7 @@ BTF_ID(func, bpf_lsm_socket_socketpair) BTF_ID(func, bpf_lsm_syslog) BTF_ID(func, bpf_lsm_task_alloc) -BTF_ID(func, bpf_lsm_task_getsecid_subj) +BTF_ID(func, bpf_lsm_current_getsecid_subj) BTF_ID(func, bpf_lsm_task_getsecid_obj) BTF_ID(func, bpf_lsm_task_prctl) BTF_ID(func, bpf_lsm_task_setscheduler) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index e16dafeb2450..3e23b3fa79ff 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5688,7 +5688,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, } if (check_ptr_off_reg(env, reg, regno)) return -EINVAL; - } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { + } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || + (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { const struct btf_type *reg_ref_t; const struct btf *reg_btf; const char *reg_ref_tname; @@ -5706,7 +5707,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, reg_ref_id = reg->btf_id; } else { reg_btf = btf_vmlinux; - reg_ref_id = *reg2btf_ids[reg->type]; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01cfdf40c838..55c084251fab 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2,6 +2,7 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bpf-cgroup.h> #include <linux/rcupdate.h> #include <linux/random.h> @@ -1075,6 +1076,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) void *key; u32 idx; + BTF_TYPE_EMIT(struct bpf_timer); callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); if (!callback_fn) goto out; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 638d7fd7b375..710ba9de12ce 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -104,7 +104,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) } rb = vmap(pages, nr_meta_pages + 2 * nr_data_pages, - VM_ALLOC | VM_USERMAP, PAGE_KERNEL); + VM_MAP | VM_USERMAP, PAGE_KERNEL); if (rb) { kmemleak_not_leak(pages); rb->pages = pages; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 49e567209c6b..22c8ae94e4c1 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -472,13 +472,14 @@ BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { struct pt_regs *regs; - long res; + long res = -EINVAL; if (!try_get_task_stack(task)) return -EFAULT; regs = task_pt_regs(task); - res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (regs) + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); put_task_stack(task); return res; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fa4505f9b611..ca70fe6fba38 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1355,6 +1355,7 @@ int generic_map_delete_batch(struct bpf_map *map, maybe_wait_bpf_programs(map); if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; @@ -1412,6 +1413,7 @@ int generic_map_update_batch(struct bpf_map *map, if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) @@ -1509,6 +1511,7 @@ int generic_map_lookup_batch(struct bpf_map *map, swap(prev_key, key); retry = MAP_LOOKUP_RETRIES; cp++; + cond_resched(); } if (err == -EFAULT) diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 4b6974a195c1..5e7edf913060 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -550,11 +550,12 @@ static __always_inline u64 notrace bpf_prog_start_time(void) static void notrace inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; + unsigned int flags; stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); - u64_stats_update_end(&stats->syncp); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } /* The logic is similar to bpf_prog_run(), but with an explicit diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 41e0837a5a0b..afc6c0e9c966 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -546,9 +546,19 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; + struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + ctx = of->priv; + if ((ctx->ns->user_ns != &init_user_ns) || + !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EPERM; + cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; @@ -954,6 +964,12 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); + /* + * Release agent gets called with all capabilities, + * require capabilities to set release agent. + */ + if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) + return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b31e1465868a..a557eea7166f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { @@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&ctx->psi.trigger, new); - + smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; @@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; - psi_trigger_replace(&ctx->psi.trigger, NULL); + psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) @@ -6161,6 +6166,20 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) if (ret) goto err; + /* + * Spawning a task directly into a cgroup works by passing a file + * descriptor to the target cgroup directory. This can even be an O_PATH + * file descriptor. But it can never be a cgroup.procs file descriptor. + * This was done on purpose so spawning into a cgroup could be + * conceptualized as an atomic + * + * fd = openat(dfd_cgroup, "cgroup.procs", ...); + * write(fd, <child-pid>, ...); + * + * sequence, i.e. it's a shorthand for the caller opening and writing + * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us + * to always use the caller's credentials. + */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index dc653ab26e50..5de18448016c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -591,6 +591,35 @@ static inline void free_cpuset(struct cpuset *cs) } /* + * validate_change_legacy() - Validate conditions specific to legacy (v1) + * behavior. + */ +static int validate_change_legacy(struct cpuset *cur, struct cpuset *trial) +{ + struct cgroup_subsys_state *css; + struct cpuset *c, *par; + int ret; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + /* Each of our child cpusets must be a subset of us */ + ret = -EBUSY; + cpuset_for_each_child(c, css, cur) + if (!is_cpuset_subset(c, trial)) + goto out; + + /* On legacy hierarchy, we must be a subset of our parent cpuset. */ + ret = -EACCES; + par = parent_cs(cur); + if (par && !is_cpuset_subset(trial, par)) + goto out; + + ret = 0; +out: + return ret; +} + +/* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * @@ -614,20 +643,21 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; - int ret; - - /* The checks don't apply to root cpuset */ - if (cur == &top_cpuset) - return 0; + int ret = 0; rcu_read_lock(); - par = parent_cs(cur); - /* On legacy hierarchy, we must be a subset of our parent cpuset. */ - ret = -EACCES; - if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) + if (!is_in_v2_mode()) + ret = validate_change_legacy(cur, trial); + if (ret) + goto out; + + /* Remaining checks don't apply to root cpuset */ + if (cur == &top_cpuset) goto out; + par = parent_cs(cur); + /* * If either I or some sibling (!= me) is exclusive, we can't * overlap @@ -1175,9 +1205,7 @@ enum subparts_cmd { * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be - * permitted when checked by validate_change(). The validate_change() - * function will also prevent any changes to the cpu list if it is not - * a superset of children's cpu lists. + * permitted when checked by validate_change(). */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, @@ -1522,10 +1550,15 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct cpuset *sibling; struct cgroup_subsys_state *pos_css; + percpu_rwsem_assert_held(&cpuset_rwsem); + /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. + * + * The update_cpumasks_hier() function may sleep. So we have to + * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { @@ -1533,8 +1566,13 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, continue; if (!sibling->use_parent_ecpus) continue; + if (!css_tryget_online(&sibling->css)) + continue; + rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); + rcu_read_lock(); + css_put(&sibling->css); } rcu_read_unlock(); } @@ -1607,8 +1645,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { - cpumask_andnot(cs->subparts_cpus, cs->subparts_cpus, - cs->cpus_allowed); + cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); @@ -2252,6 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2305,6 +2343,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); + cpus_read_unlock(); } /* The various types of files and directories in a cpuset file system */ @@ -3485,8 +3524,8 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) return cs; } -/** - * cpuset_node_allowed - Can we allocate on a memory node? +/* + * __cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * @@ -3657,8 +3696,8 @@ void cpuset_print_current_mems_allowed(void) int cpuset_memory_pressure_enabled __read_mostly; -/** - * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. +/* + * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. @@ -3673,7 +3712,7 @@ int cpuset_memory_pressure_enabled __read_mostly; * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. - **/ + */ void __cpuset_memory_pressure_bump(void) { diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index e9ffb0cc1eec..e8db8d938661 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -17,6 +17,7 @@ CONFIG_SYMBOLIC_ERRNAME=y # Compile-time checks and compiler options # CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_FRAME_WARN=2048 CONFIG_SECTION_MISMATCH_WARN_ONLY=y diff --git a/kernel/cpu.c b/kernel/cpu.c index 407a2568f35e..238cba15449f 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -34,6 +34,7 @@ #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> +#include <linux/random.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS @@ -1659,6 +1660,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, + [CPUHP_RANDOM_PREPARE] = { + .name = "random:prepare", + .startup.single = random_prepare_cpu, + .teardown.single = NULL, + }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, @@ -1782,6 +1788,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, + [CPUHP_AP_RANDOM_ONLINE] = { + .name = "random:online", + .startup.single = random_online_cpu, + .teardown.single = NULL, + }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, diff --git a/kernel/cred.c b/kernel/cred.c index 473d17c431f3..933155c96922 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -665,21 +665,16 @@ EXPORT_SYMBOL(cred_fscmp); int set_cred_ucounts(struct cred *new) { - struct task_struct *task = current; - const struct cred *old = task->real_cred; struct ucounts *new_ucounts, *old_ucounts = new->ucounts; - if (new->user == old->user && new->user_ns == old->user_ns) - return 0; - /* * This optimization is needed because alloc_ucounts() uses locks * for table lookups. */ - if (old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid)) + if (old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->uid)) return 0; - if (!(new_ucounts = alloc_ucounts(new->user_ns, new->euid))) + if (!(new_ucounts = alloc_ucounts(new->user_ns, new->uid))) return -EAGAIN; new->ucounts = new_ucounts; diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index f1e7ea160b43..6db1c475ec82 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -627,9 +627,14 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, for (i = 0; i < nr_slots(alloc_size + offset); i++) mem->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(mem->start, index) + offset; - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); + /* + * When dir == DMA_FROM_DEVICE we could omit the copy from the orig + * to the tlb buffer, if we knew for sure the device will + * overwirte the entire current content. But we don't. Thus + * unconditional bounce may prevent leaking swiotlb content (i.e. + * kernel memory) to user-space. + */ + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); return tlb_addr; } @@ -696,10 +701,13 @@ void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); - else - BUG_ON(dir != DMA_FROM_DEVICE); + /* + * Unconditional bounce is necessary to avoid corruption on + * sync_*_for_cpu or dma_ummap_* when the device didn't overwrite + * the whole lengt of the bounce buffer. + */ + swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); + BUG_ON(!valid_dma_direction(dir)); } void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, diff --git a/kernel/entry/common.c b/kernel/entry/common.c index bad713684c2e..0543a2c92f20 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -148,6 +148,18 @@ static void handle_signal_work(struct pt_regs *regs, unsigned long ti_work) arch_do_signal_or_restart(regs, ti_work & _TIF_SIGPENDING); } +#ifdef CONFIG_RT_DELAYED_SIGNALS +static inline void raise_delayed_signal(void) +{ + if (unlikely(current->forced_info.si_signo)) { + force_sig_info(¤t->forced_info); + current->forced_info.si_signo = 0; + } +} +#else +static inline void raise_delayed_signal(void) { } +#endif + static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work) { @@ -162,6 +174,8 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, if (ti_work & _TIF_NEED_RESCHED) schedule(); + raise_delayed_signal(); + if (ti_work & _TIF_UPROBE) uprobe_notify_resume(regs); diff --git a/kernel/events/core.c b/kernel/events/core.c index fc18664f49b0..6859229497b1 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -674,6 +674,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) WRITE_ONCE(event->state, state); } +/* + * UP store-release, load-acquire + */ + +#define __store_release(ptr, val) \ +do { \ + barrier(); \ + WRITE_ONCE(*(ptr), (val)); \ +} while (0) + +#define __load_acquire(ptr) \ +({ \ + __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ + barrier(); \ + ___p; \ +}) + #ifdef CONFIG_CGROUP_PERF static inline bool @@ -719,34 +736,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return t->time; } -static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { - struct perf_cgroup_info *info; - u64 now; - - now = perf_clock(); + struct perf_cgroup_info *t; - info = this_cpu_ptr(cgrp->info); + t = per_cpu_ptr(event->cgrp->info, event->cpu); + if (!__load_acquire(&t->active)) + return t->time; + now += READ_ONCE(t->timeoffset); + return now; +} - info->time += now - info->timestamp; +static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) +{ + if (adv) + info->time += now - info->timestamp; info->timestamp = now; + /* + * see update_context_time() + */ + WRITE_ONCE(info->timeoffset, info->time - info->timestamp); } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; + struct perf_cgroup_info *info; if (cgrp) { + u64 now = perf_clock(); + for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); - __update_cgrp_time(cgrp); + info = this_cpu_ptr(cgrp->info); + + __update_cgrp_time(info, now, true); + if (final) + __store_release(&info->active, 0); } } } static inline void update_cgrp_time_from_event(struct perf_event *event) { + struct perf_cgroup_info *info; struct perf_cgroup *cgrp; /* @@ -760,8 +794,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - __update_cgrp_time(event->cgrp); + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { + info = this_cpu_ptr(event->cgrp->info); + __update_cgrp_time(info, perf_clock(), true); + } } static inline void @@ -785,7 +821,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + __update_cgrp_time(info, ctx->timestamp, false); + __store_release(&info->active, 1); } } @@ -802,7 +839,7 @@ static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list); */ static void perf_cgroup_switch(struct task_struct *task, int mode) { - struct perf_cpu_context *cpuctx; + struct perf_cpu_context *cpuctx, *tmp; struct list_head *list; unsigned long flags; @@ -813,7 +850,7 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) local_irq_save(flags); list = this_cpu_ptr(&cgrp_cpuctx_list); - list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) { + list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) { WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); perf_ctx_lock(cpuctx, cpuctx->task_ctx); @@ -982,14 +1019,6 @@ out: } static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) -{ - struct perf_cgroup_info *t; - t = per_cpu_ptr(event->cgrp->info, event->cpu); - event->shadow_ctx_time = now - t->timestamp; -} - -static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { struct perf_cpu_context *cpuctx; @@ -1066,7 +1095,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) { } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, + bool final) { } @@ -1098,12 +1128,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } -static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +static inline u64 perf_cgroup_event_time(struct perf_event *event) { + return 0; } -static inline u64 perf_cgroup_event_time(struct perf_event *event) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } @@ -1525,22 +1555,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) /* * Update the record of the current time in a context. */ -static void update_context_time(struct perf_event_context *ctx) +static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock(); - ctx->time += now - ctx->timestamp; + if (adv) + ctx->time += now - ctx->timestamp; ctx->timestamp = now; + + /* + * The above: time' = time + (now - timestamp), can be re-arranged + * into: time` = now + (time - timestamp), which gives a single value + * offset to compute future time without locks on. + * + * See perf_event_time_now(), which can be used from NMI context where + * it's (obviously) not possible to acquire ctx->lock in order to read + * both the above values in a consistent manner. + */ + WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); +} + +static void update_context_time(struct perf_event_context *ctx) +{ + __update_context_time(ctx, true); } static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; + if (unlikely(!ctx)) + return 0; + if (is_cgroup_event(event)) return perf_cgroup_event_time(event); - return ctx ? ctx->time : 0; + return ctx->time; +} + +static u64 perf_event_time_now(struct perf_event *event, u64 now) +{ + struct perf_event_context *ctx = event->ctx; + + if (unlikely(!ctx)) + return 0; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time_now(event, now); + + if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) + return ctx->time; + + now += READ_ONCE(ctx->timeoffset); + return now; } static enum event_type_t get_event_type(struct perf_event *event) @@ -2350,7 +2417,7 @@ __perf_remove_from_context(struct perf_event *event, if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, false); } event_sched_out(event, cpuctx, ctx); @@ -2361,6 +2428,9 @@ __perf_remove_from_context(struct perf_event *event, list_del_event(event, ctx); if (!ctx->nr_events && ctx->is_active) { + if (ctx == &cpuctx->ctx) + update_cgrp_time_from_cpuctx(cpuctx, true); + ctx->is_active = 0; ctx->rotate_necessary = 0; if (ctx->task) { @@ -2392,7 +2462,11 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla * event_function_call() user. */ raw_spin_lock_irq(&ctx->lock); - if (!ctx->is_active) { + /* + * Cgroup events are per-cpu events, and must IPI because of + * cgrp_cpuctx_list. + */ + if (!ctx->is_active && !is_cgroup_event(event)) { __perf_remove_from_context(event, __get_cpu_context(ctx), ctx, (void *)flags); raw_spin_unlock_irq(&ctx->lock); @@ -2482,40 +2556,6 @@ void perf_event_disable_inatomic(struct perf_event *event) irq_work_queue(&event->pending); } -static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx) -{ - /* - * use the correct time source for the time snapshot - * - * We could get by without this by leveraging the - * fact that to get to this function, the caller - * has most likely already called update_context_time() - * and update_cgrp_time_xx() and thus both timestamp - * are identical (or very close). Given that tstamp is, - * already adjusted for cgroup, we could say that: - * tstamp - ctx->timestamp - * is equivalent to - * tstamp - cgrp->timestamp. - * - * Then, in perf_output_read(), the calculation would - * work with no changes because: - * - event is guaranteed scheduled in - * - no scheduled out in between - * - thus the timestamp would be the same - * - * But this is a bit hairy. - * - * So instead, we have an explicit cgroup call to remain - * within the time source all along. We believe it - * is cleaner and simpler to understand. - */ - if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, event->tstamp); - else - event->shadow_ctx_time = event->tstamp - ctx->timestamp; -} - #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); @@ -2556,8 +2596,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - perf_set_shadow_time(event, ctx); - perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { @@ -2861,11 +2899,14 @@ perf_install_in_context(struct perf_event_context *ctx, * perf_event_attr::disabled events will not run and can be initialized * without IPI. Except when this is the first event for the context, in * that case we need the magic of the IPI to set ctx->is_active. + * Similarly, cgroup events for the context also needs the IPI to + * manipulate the cgrp_cpuctx_list. * * The IOC_ENABLE that is sure to follow the creation of a disabled * event will issue the IPI and reprogram the hardware. */ - if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && ctx->nr_events) { + if (__perf_effective_state(event) == PERF_EVENT_STATE_OFF && + ctx->nr_events && !is_cgroup_event(event)) { raw_spin_lock_irq(&ctx->lock); if (ctx->task == TASK_TOMBSTONE) { raw_spin_unlock_irq(&ctx->lock); @@ -3197,6 +3238,15 @@ static int perf_event_modify_breakpoint(struct perf_event *bp, return err; } +/* + * Copy event-type-independent attributes that may be modified. + */ +static void perf_event_modify_copy_attr(struct perf_event_attr *to, + const struct perf_event_attr *from) +{ + to->sig_data = from->sig_data; +} + static int perf_event_modify_attr(struct perf_event *event, struct perf_event_attr *attr) { @@ -3219,10 +3269,17 @@ static int perf_event_modify_attr(struct perf_event *event, WARN_ON_ONCE(event->ctx->parent_ctx); mutex_lock(&event->child_mutex); + /* + * Event-type-independent attributes must be copied before event-type + * modification, which will validate that final attributes match the + * source attributes after all relevant attributes have been copied. + */ + perf_event_modify_copy_attr(&event->attr, attr); err = func(event, attr); if (err) goto out; list_for_each_entry(child, &event->child_list, child_list) { + perf_event_modify_copy_attr(&child->attr, attr); err = func(child, attr); if (err) goto out; @@ -3251,16 +3308,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, return; } - ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - - if (ctx->task) { - WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) - cpuctx->task_ctx = NULL; - } - /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last @@ -3274,7 +3321,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ @@ -3711,13 +3773,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +/* + * Because the userpage is strictly per-event (there is no concept of context, + * so there cannot be a context indirection), every userpage must be updated + * when context time starts :-( + * + * IOW, we must not miss EVENT_TIME edges. + */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false; perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_update_userpage(event); return true; @@ -3801,13 +3869,23 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { int is_active = ctx->is_active; - u64 now; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) return; + if (is_active ^ EVENT_TIME) { + /* start ctx time */ + __update_context_time(ctx, false); + perf_cgroup_set_timestamp(task, ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) @@ -3818,13 +3896,6 @@ ctx_sched_in(struct perf_event_context *ctx, is_active ^= ctx->is_active; /* changed bits */ - if (is_active & EVENT_TIME) { - /* start ctx time */ - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); - } - /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -4418,6 +4489,18 @@ static inline u64 perf_event_count(struct perf_event *event) return local64_read(&event->count) + atomic64_read(&event->child_count); } +static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = perf_event_time_now(event, *now); + __perf_update_times(event, ctx_time, enabled, running); +} + /* * NMI-safe method to read a local event, that is an event that * is: @@ -4477,10 +4560,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value, *value = local64_read(&event->count); if (enabled || running) { - u64 now = event->shadow_ctx_time + perf_clock(); - u64 __enabled, __running; + u64 __enabled, __running, __now;; - __perf_update_times(event, now, &__enabled, &__running); + calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) @@ -5802,18 +5884,6 @@ static int perf_event_index(struct perf_event *event) return event->pmu->event_idx(event); } -static void calc_timer_values(struct perf_event *event, - u64 *now, - u64 *enabled, - u64 *running) -{ - u64 ctx_time; - - *now = perf_clock(); - ctx_time = event->shadow_ctx_time + *now; - __perf_update_times(event, ctx_time, enabled, running); -} - static void perf_event_init_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; @@ -5938,6 +6008,8 @@ static void ring_buffer_attach(struct perf_event *event, struct perf_buffer *old_rb = NULL; unsigned long flags; + WARN_ON_ONCE(event->parent); + if (event->rb) { /* * Should be impossible, we set this when removing @@ -5995,6 +6067,9 @@ static void ring_buffer_wakeup(struct perf_event *event) { struct perf_buffer *rb; + if (event->parent) + event = event->parent; + rcu_read_lock(); rb = rcu_dereference(event->rb); if (rb) { @@ -6008,6 +6083,9 @@ struct perf_buffer *ring_buffer_get(struct perf_event *event) { struct perf_buffer *rb; + if (event->parent) + event = event->parent; + rcu_read_lock(); rb = rcu_dereference(event->rb); if (rb) { @@ -6353,7 +6431,6 @@ accounting: ring_buffer_attach(event, rb); perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { @@ -6717,7 +6794,7 @@ static unsigned long perf_prepare_sample_aux(struct perf_event *event, if (WARN_ON_ONCE(READ_ONCE(sampler->oncpu) != smp_processor_id())) goto out; - rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + rb = ring_buffer_get(sampler); if (!rb) goto out; @@ -6783,7 +6860,7 @@ static void perf_aux_sample_output(struct perf_event *event, if (WARN_ON_ONCE(!sampler || !data->aux_size)) return; - rb = ring_buffer_get(sampler->parent ? sampler->parent : sampler); + rb = ring_buffer_get(sampler); if (!rb) return; diff --git a/kernel/exit.c b/kernel/exit.c index b00a25bb4ab9..192b90a9ce16 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -735,7 +735,7 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; - WARN_ON(blk_needs_flush_plug(tsk)); + WARN_ON(tsk->plug); /* * If do_dead is called because this processes oopsed, it's possible @@ -845,6 +845,7 @@ void __noreturn do_exit(long code) put_page(tsk->task_frag.page); validate_creds_for_do_exit(tsk); + exit_task_stack_account(tsk); check_stack_usage(); preempt_disable(); diff --git a/kernel/fork.c b/kernel/fork.c index d75a528f7b21..d74c30b6733b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -97,6 +97,7 @@ #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> +#include <linux/sched/mm.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> @@ -185,7 +186,7 @@ static inline void free_task_struct(struct task_struct *tsk) */ # if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) -#ifdef CONFIG_VMAP_STACK +# ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. @@ -193,6 +194,41 @@ static inline void free_task_struct(struct task_struct *tsk) #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); +struct vm_stack { + struct rcu_head rcu; + struct vm_struct *stack_vm_area; +}; + +static bool try_release_thread_stack_to_cache(struct vm_struct *vm) +{ + unsigned int i; + + for (i = 0; i < NR_CACHED_STACKS; i++) { + if (this_cpu_cmpxchg(cached_stacks[i], NULL, vm) != NULL) + continue; + return true; + } + return false; +} + +static void thread_stack_free_rcu(struct rcu_head *rh) +{ + struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); + + if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) + return; + + vfree(vm_stack); +} + +static void thread_stack_delayed_free(struct task_struct *tsk) +{ + struct vm_stack *vm_stack = tsk->stack; + + vm_stack->stack_vm_area = tsk->stack_vm_area; + call_rcu(&vm_stack->rcu, thread_stack_free_rcu); +} + static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu); @@ -210,11 +246,35 @@ static int free_vm_stack_cache(unsigned int cpu) return 0; } -#endif -static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) +static int memcg_charge_kernel_stack(struct vm_struct *vm) { -#ifdef CONFIG_VMAP_STACK + int i; + int ret; + + BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); + BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); + + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); + if (ret) + goto err; + } + return 0; +err: + /* + * If memcg_kmem_charge_page() fails, page's memory cgroup pointer is + * NULL, and memcg_kmem_uncharge_page() in free_thread_stack() will + * ignore this page. + */ + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) + memcg_kmem_uncharge_page(vm->pages[i], 0); + return ret; +} + +static int alloc_thread_stack_node(struct task_struct *tsk, int node) +{ + struct vm_struct *vm; void *stack; int i; @@ -232,9 +292,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) /* Clear stale pointers from reused stack. */ memset(s->addr, 0, THREAD_SIZE); + if (memcg_charge_kernel_stack(s)) { + vfree(s->addr); + return -ENOMEM; + } + tsk->stack_vm_area = s; tsk->stack = s->addr; - return s->addr; + return 0; } /* @@ -247,71 +312,95 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); + if (!stack) + return -ENOMEM; + vm = find_vm_area(stack); + if (memcg_charge_kernel_stack(vm)) { + vfree(stack); + return -ENOMEM; + } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ - if (stack) { - tsk->stack_vm_area = find_vm_area(stack); - tsk->stack = stack; - } - return stack; -#else + tsk->stack_vm_area = vm; + tsk->stack = stack; + return 0; +} + +static void free_thread_stack(struct task_struct *tsk) +{ + if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) + thread_stack_delayed_free(tsk); + + tsk->stack = NULL; + tsk->stack_vm_area = NULL; +} + +# else /* !CONFIG_VMAP_STACK */ + +static void thread_stack_free_rcu(struct rcu_head *rh) +{ + __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); +} + +static void thread_stack_delayed_free(struct task_struct *tsk) +{ + struct rcu_head *rh = tsk->stack; + + call_rcu(rh, thread_stack_free_rcu); +} + +static int alloc_thread_stack_node(struct task_struct *tsk, int node) +{ struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); - return tsk->stack; + return 0; } - return NULL; -#endif + return -ENOMEM; } -static inline void free_thread_stack(struct task_struct *tsk) +static void free_thread_stack(struct task_struct *tsk) { -#ifdef CONFIG_VMAP_STACK - struct vm_struct *vm = task_stack_vm_area(tsk); - - if (vm) { - int i; + thread_stack_delayed_free(tsk); + tsk->stack = NULL; +} - for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) - memcg_kmem_uncharge_page(vm->pages[i], 0); +# endif /* CONFIG_VMAP_STACK */ +# else /* !(THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)) */ - for (i = 0; i < NR_CACHED_STACKS; i++) { - if (this_cpu_cmpxchg(cached_stacks[i], - NULL, tsk->stack_vm_area) != NULL) - continue; +static struct kmem_cache *thread_stack_cache; - return; - } +static void thread_stack_free_rcu(struct rcu_head *rh) +{ + kmem_cache_free(thread_stack_cache, rh); +} - vfree_atomic(tsk->stack); - return; - } -#endif +static void thread_stack_delayed_free(struct task_struct *tsk) +{ + struct rcu_head *rh = tsk->stack; - __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER); + call_rcu(rh, thread_stack_free_rcu); } -# else -static struct kmem_cache *thread_stack_cache; -static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, - int node) +static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; - return stack; + return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { - kmem_cache_free(thread_stack_cache, tsk->stack); + thread_stack_delayed_free(tsk); + tsk->stack = NULL; } void thread_stack_cache_init(void) @@ -321,8 +410,26 @@ void thread_stack_cache_init(void) THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } -# endif -#endif + +# endif /* THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) */ +#else /* CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ + +static int alloc_thread_stack_node(struct task_struct *tsk, int node) +{ + unsigned long *stack; + + stack = arch_alloc_thread_stack_node(tsk, node); + tsk->stack = stack; + return stack ? 0 : -ENOMEM; +} + +static void free_thread_stack(struct task_struct *tsk) +{ + arch_free_thread_stack(tsk); + tsk->stack = NULL; +} + +#endif /* !CONFIG_ARCH_THREAD_STACK_ALLOCATOR */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; @@ -366,63 +473,47 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; - dup_vma_anon_name(orig, new); + dup_anon_vma_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { - free_vma_anon_name(vma); + free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); } static void account_kernel_stack(struct task_struct *tsk, int account) { - void *stack = task_stack_page(tsk); - struct vm_struct *vm = task_stack_vm_area(tsk); - - if (vm) { + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + struct vm_struct *vm = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { + void *stack = task_stack_page(tsk); + /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } -static int memcg_charge_kernel_stack(struct task_struct *tsk) +void exit_task_stack_account(struct task_struct *tsk) { -#ifdef CONFIG_VMAP_STACK - struct vm_struct *vm = task_stack_vm_area(tsk); - int ret; - - BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); + account_kernel_stack(tsk, -1); - if (vm) { + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + struct vm_struct *vm; int i; - BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); - - for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { - /* - * If memcg_kmem_charge_page() fails, page's - * memory cgroup pointer is NULL, and - * memcg_kmem_uncharge_page() in free_thread_stack() - * will ignore this page. - */ - ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, - 0); - if (ret) - return ret; - } + vm = task_stack_vm_area(tsk); + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) + memcg_kmem_uncharge_page(vm->pages[i], 0); } -#endif - return 0; } static void release_task_stack(struct task_struct *tsk) @@ -430,12 +521,7 @@ static void release_task_stack(struct task_struct *tsk) if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ - account_kernel_stack(tsk, -1); free_thread_stack(tsk); - tsk->stack = NULL; -#ifdef CONFIG_VMAP_STACK - tsk->stack_vm_area = NULL; -#endif } #ifdef CONFIG_THREAD_INFO_IN_TASK @@ -874,8 +960,6 @@ void set_task_stack_end_magic(struct task_struct *tsk) static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; - unsigned long *stack; - struct vm_struct *stack_vm_area __maybe_unused; int err; if (node == NUMA_NO_NODE) @@ -884,32 +968,18 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!tsk) return NULL; - stack = alloc_thread_stack_node(tsk, node); - if (!stack) + err = arch_dup_task_struct(tsk, orig); + if (err) goto free_tsk; - if (memcg_charge_kernel_stack(tsk)) - goto free_stack; - - stack_vm_area = task_stack_vm_area(tsk); - - err = arch_dup_task_struct(tsk, orig); + err = alloc_thread_stack_node(tsk, node); + if (err) + goto free_tsk; - /* - * arch_dup_task_struct() clobbers the stack-related fields. Make - * sure they're properly initialized before using any stack-related - * functions again. - */ - tsk->stack = stack; -#ifdef CONFIG_VMAP_STACK - tsk->stack_vm_area = stack_vm_area; -#endif #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif - - if (err) - goto free_stack; + account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) @@ -953,8 +1023,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->wake_q.next = NULL; tsk->worker_private = NULL; - account_kernel_stack(tsk, 1); - kcov_task_init(tsk); kmap_local_fork(tsk); @@ -967,12 +1035,17 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->use_memdelay = 0; #endif +#ifdef CONFIG_IOMMU_SVA + tsk->pasid_activated = 0; +#endif + #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif return tsk; free_stack: + exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); @@ -1019,13 +1092,6 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } -static void mm_init_pasid(struct mm_struct *mm) -{ -#ifdef CONFIG_IOMMU_SUPPORT - mm->pasid = INIT_PASID; -#endif -} - static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES @@ -1054,7 +1120,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); - mm_init_pasid(mm); + mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); @@ -1121,6 +1187,7 @@ static inline void __mmput(struct mm_struct *mm) } if (mm->binfmt) module_put(mm->binfmt->module); + mm_pasid_drop(mm); mmdrop(mm); } @@ -2021,18 +2088,18 @@ static __latent_entropy struct task_struct *copy_process( #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif + retval = copy_creds(p, clone_flags); + if (retval < 0) + goto bad_fork_free; + retval = -EAGAIN; if (is_ucounts_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) - goto bad_fork_free; + goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; - retval = copy_creds(p, clone_flags); - if (retval < 0) - goto bad_fork_free; - /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there @@ -2267,6 +2334,17 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_put_pidfd; /* + * Now that the cgroups are pinned, re-clone the parent cgroup and put + * the new task on the correct runqueue. All this *before* the task + * becomes visible. + * + * This isn't part of ->can_fork() because while the re-cloning is + * cgroup specific, it unconditionally needs to place the task on a + * runqueue. + */ + sched_cgroup_fork(p, args); + + /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by @@ -2323,10 +2401,6 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_cancel_cgroup; } - /* past the last point of failure */ - if (pidfile) - fd_install(pidfd, pidfile); - init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); @@ -2375,8 +2449,11 @@ static __latent_entropy struct task_struct *copy_process( syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); + if (pidfile) + fd_install(pidfd, pidfile); + proc_fork_connector(p); - sched_post_fork(p, args); + sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); @@ -2441,6 +2518,7 @@ bad_fork_cleanup_count: exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); + exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index c09324663088..54af0deb239b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -38,7 +38,7 @@ struct irqaction chained_action = { * @irq: irq number * @chip: pointer to irq chip description structure */ -int irq_set_chip(unsigned int irq, struct irq_chip *chip) +int irq_set_chip(unsigned int irq, const struct irq_chip *chip) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); @@ -46,10 +46,7 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip) if (!desc) return -EINVAL; - if (!chip) - chip = &no_irq_chip; - - desc->irq_data.chip = chip; + desc->irq_data.chip = (struct irq_chip *)(chip ?: &no_irq_chip); irq_put_desc_unlock(desc, flags); /* * For !CONFIG_SPARSE_IRQ make the irq show up in @@ -1073,7 +1070,7 @@ irq_set_chained_handler_and_data(unsigned int irq, irq_flow_handler_t handle, EXPORT_SYMBOL_GPL(irq_set_chained_handler_and_data); void -irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, +irq_set_chip_and_handler_name(unsigned int irq, const struct irq_chip *chip, irq_flow_handler_t handle, const char *name) { irq_set_chip(irq, chip); @@ -1558,6 +1555,14 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return 0; } +static struct device *irq_get_parent_device(struct irq_data *data) +{ + if (data->domain) + return data->domain->dev; + + return NULL; +} + /** * irq_chip_pm_get - Enable power for an IRQ chip * @data: Pointer to interrupt specific data @@ -1567,12 +1572,13 @@ int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) */ int irq_chip_pm_get(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) { - retval = pm_runtime_get_sync(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) { + retval = pm_runtime_get_sync(dev); if (retval < 0) { - pm_runtime_put_noidle(data->chip->parent_device); + pm_runtime_put_noidle(dev); return retval; } } @@ -1590,10 +1596,11 @@ int irq_chip_pm_get(struct irq_data *data) */ int irq_chip_pm_put(struct irq_data *data) { + struct device *dev = irq_get_parent_device(data); int retval = 0; - if (IS_ENABLED(CONFIG_PM) && data->chip->parent_device) - retval = pm_runtime_put(data->chip->parent_device); + if (IS_ENABLED(CONFIG_PM) && dev) + retval = pm_runtime_put(dev); return (retval < 0) ? retval : 0; } diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index e4cff358b437..2b43f5f5033d 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -69,8 +69,12 @@ irq_debug_show_chip(struct seq_file *m, struct irq_data *data, int ind) seq_printf(m, "chip: None\n"); return; } - seq_printf(m, "%*schip: %s\n", ind, "", chip->name); - seq_printf(m, "%*sflags: 0x%lx\n", ind + 1, "", chip->flags); + seq_printf(m, "%*schip: ", ind, ""); + if (chip->irq_print_chip) + chip->irq_print_chip(data, m); + else + seq_printf(m, "%s", chip->name); + seq_printf(m, "\n%*sflags: 0x%lx\n", ind + 1, "", chip->flags); irq_debug_show_bits(m, ind, chip->flags, irqchip_flags, ARRAY_SIZE(irqchip_flags)); } diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 2267e6527db3..939d21cd55c3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -640,7 +640,7 @@ int handle_irq_desc(struct irq_desc *desc) return -EINVAL; data = irq_desc_get_irq_data(desc); - if (WARN_ON_ONCE(!in_irq() && handle_enforce_irqctx(data))) + if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); @@ -662,6 +662,29 @@ int generic_handle_irq(unsigned int irq) } EXPORT_SYMBOL_GPL(generic_handle_irq); +/** + * generic_handle_irq_safe - Invoke the handler for a particular irq from any + * context. + * @irq: The irq number to handle + * + * Returns: 0 on success, a negative value on error. + * + * This function can be called from any context (IRQ or process context). It + * will report an error if not invoked from IRQ context and the irq has been + * marked to enforce IRQ-context only. + */ +int generic_handle_irq_safe(unsigned int irq) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = handle_irq_desc(irq_to_desc(irq)); + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(generic_handle_irq_safe); + #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging @@ -676,7 +699,7 @@ EXPORT_SYMBOL_GPL(generic_handle_irq); */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { - WARN_ON_ONCE(!in_irq()); + WARN_ON_ONCE(!in_hardirq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index bf38c546aa25..d5ce96510549 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1319,7 +1319,8 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @chip_data: The associated chip data */ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, + const struct irq_chip *chip, void *chip_data) { struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); @@ -1328,7 +1329,7 @@ int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, return -ENOENT; irq_data->hwirq = hwirq; - irq_data->chip = chip ? chip : &no_irq_chip; + irq_data->chip = (struct irq_chip *)(chip ? chip : &no_irq_chip); irq_data->chip_data = chip_data; return 0; @@ -1347,7 +1348,7 @@ EXPORT_SYMBOL_GPL(irq_domain_set_hwirq_and_chip); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { @@ -1853,7 +1854,7 @@ EXPORT_SYMBOL_GPL(irq_domain_get_irq_data); * @handler_name: The interrupt handler name */ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq, struct irq_chip *chip, + irq_hw_number_t hwirq, const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler, void *handler_data, const char *handler_name) { diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 4a882f83aeb9..f8a0212189ca 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3462,7 +3462,7 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) u16 chain_hlock = chain_hlocks[chain->base + i]; unsigned int class_idx = chain_hlock_class_idx(chain_hlock); - return lock_classes + class_idx - 1; + return lock_classes + class_idx; } /* @@ -3530,7 +3530,7 @@ static void print_chain_keys_chain(struct lock_chain *chain) hlock_id = chain_hlocks[chain->base + i]; chain_key = print_chain_key_iteration(hlock_id, chain_key); - print_lock_name(lock_classes + chain_hlock_class_idx(hlock_id) - 1); + print_lock_name(lock_classes + chain_hlock_class_idx(hlock_id)); printk("\n"); } } diff --git a/kernel/module.c b/kernel/module.c index 24dab046e16c..46a5c2ed1928 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3725,12 +3725,6 @@ static noinline int do_init_module(struct module *mod) } freeinit->module_init = mod->init_layout.base; - /* - * We want to find out whether @mod uses async during init. Clear - * PF_USED_ASYNC. async_schedule*() will set it. - */ - current->flags &= ~PF_USED_ASYNC; - do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) @@ -3756,22 +3750,13 @@ static noinline int do_init_module(struct module *mod) /* * We need to finish all async code before the module init sequence - * is done. This has potential to deadlock. For example, a newly - * detected block device can trigger request_module() of the - * default iosched from async probing task. Once userland helper - * reaches here, async_synchronize_full() will wait on the async - * task waiting on request_module() and deadlock. - * - * This deadlock is avoided by perfomring async_synchronize_full() - * iff module init queued any async jobs. This isn't a full - * solution as it will deadlock the same if module loading from - * async jobs nests more than once; however, due to the various - * constraints, this hack seems to be the best option for now. - * Please refer to the following thread for details. + * is done. This has potential to deadlock if synchronous module + * loading is requested from async (which is not allowed!). * - * http://thread.gmane.org/gmane.linux.kernel/1420814 + * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous + * request_module() from async workers") for more details. */ - if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC)) + if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + diff --git a/kernel/module_decompress.c b/kernel/module_decompress.c index b01c69c2ff99..ffef98a20320 100644 --- a/kernel/module_decompress.c +++ b/kernel/module_decompress.c @@ -250,6 +250,7 @@ void module_decompress_cleanup(struct load_info *info) info->max_pages = info->used_pages = 0; } +#ifdef CONFIG_SYSFS static ssize_t compression_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -269,3 +270,4 @@ static int __init module_decompress_sysfs_init(void) return 0; } late_initcall(module_decompress_sysfs_init); +#endif diff --git a/kernel/padata.c b/kernel/padata.c index 18d3a5c699d8..e5819bb8bd1d 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -181,7 +181,7 @@ int padata_do_parallel(struct padata_shell *ps, goto out; if (!cpumask_test_cpu(*cb_cpu, pd->cpumask.cbcpu)) { - if (!cpumask_weight(pd->cpumask.cbcpu)) + if (cpumask_empty(pd->cpumask.cbcpu)) goto out; /* Select an alternate fallback CPU and notify the caller. */ diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index e6af502c2fd7..938d5c78b421 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -28,7 +28,6 @@ #include <linux/gfp.h> #include <linux/syscore_ops.h> #include <linux/ctype.h> -#include <linux/genhd.h> #include <linux/ktime.h> #include <linux/security.h> #include <linux/secretmem.h> @@ -689,8 +688,10 @@ static int load_image_and_restore(void) lock_device_hotplug(); error = create_basic_memory_bitmaps(); - if (error) + if (error) { + swsusp_close(FMODE_READ | FMODE_EXCL); goto Unlock; + } error = swsusp_read(&flags); swsusp_close(FMODE_READ | FMODE_EXCL); @@ -1328,7 +1329,7 @@ static int __init resumedelay_setup(char *str) int rc = kstrtouint(str, 0, &resume_delay); if (rc) - return rc; + pr_warn("resumedelay: bad option string '%s'\n", str); return 1; } diff --git a/kernel/power/main.c b/kernel/power/main.c index 44169f3081fd..7e646079fbeb 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -504,7 +504,10 @@ static ssize_t pm_wakeup_irq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return pm_wakeup_irq ? sprintf(buf, "%u\n", pm_wakeup_irq) : -ENODATA; + if (!pm_wakeup_irq()) + return -ENODATA; + + return sprintf(buf, "%u\n", pm_wakeup_irq()); } power_attr_ro(pm_wakeup_irq); diff --git a/kernel/power/process.c b/kernel/power/process.c index b7e7798637b8..11b570fcf049 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -134,7 +134,7 @@ int freeze_processes(void) if (!pm_freezing) atomic_inc(&system_freezing_cnt); - pm_wakeup_clear(true); + pm_wakeup_clear(0); pr_info("Freezing user space processes ... "); pm_freezing = true; error = try_to_freeze_tasks(true); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f7a986078213..330d49937692 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -978,8 +978,7 @@ static void memory_bm_recycle(struct memory_bitmap *bm) * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ -void __init __register_nosave_region(unsigned long start_pfn, - unsigned long end_pfn, int use_kmalloc) +void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; @@ -995,18 +994,12 @@ void __init __register_nosave_region(unsigned long start_pfn, goto Report; } } - if (use_kmalloc) { - /* During init, this shouldn't fail */ - region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); - BUG_ON(!region); - } else { - /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), - SMP_CACHE_BYTES); - if (!region) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct nosave_region)); - } + /* This allocation cannot fail */ + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); + if (!region) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 80cc1f0f502b..6fcdee7e87a5 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -136,8 +136,6 @@ static void s2idle_loop(void) break; } - pm_wakeup_clear(false); - s2idle_enter(); } diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index d20526c5be15..b663a97f5867 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -157,22 +157,22 @@ static int __init setup_test_suspend(char *value) value++; suspend_type = strsep(&value, ","); if (!suspend_type) - return 0; + return 1; repeat = strsep(&value, ","); if (repeat) { if (kstrtou32(repeat, 0, &test_repeat_count_max)) - return 0; + return 1; } for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) if (!strcmp(pm_labels[i], suspend_type)) { test_state_label = pm_labels[i]; - return 0; + return 1; } printk(warn_bad_state, suspend_type); - return 0; + return 1; } __setup("test_suspend", setup_test_suspend); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index ad10359030a4..91fffdd2c7fb 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -16,7 +16,6 @@ #include <linux/file.h> #include <linux/delay.h> #include <linux/bitops.h> -#include <linux/genhd.h> #include <linux/device.h> #include <linux/bio.h> #include <linux/blkdev.h> @@ -89,7 +88,7 @@ struct swap_map_page_list { struct swap_map_page_list *next; }; -/** +/* * The swap_map_handle structure is used for handling swap in * a file-alike way */ @@ -117,7 +116,7 @@ struct swsusp_header { static struct swsusp_header *swsusp_header; -/** +/* * The following functions are used for tracing the allocated * swap pages, so that they can be freed in case of an error. */ @@ -171,7 +170,7 @@ static int swsusp_extents_insert(unsigned long swap_offset) return 0; } -/** +/* * alloc_swapdev_block - allocate a swap page and register that it has * been allocated, so that it can be freed in case of an error. */ @@ -190,7 +189,7 @@ sector_t alloc_swapdev_block(int swap) return 0; } -/** +/* * free_all_swap_pages - free swap pages allocated for saving image data. * It also frees the extents used to register which swap entries had been * allocated. @@ -277,10 +276,9 @@ static int hib_submit_io(int op, int op_flags, pgoff_t page_off, void *addr, struct bio *bio; int error = 0; - bio = bio_alloc(GFP_NOIO | __GFP_HIGH, 1); + bio = bio_alloc(hib_resume_bdev, 1, op | op_flags, + GFP_NOIO | __GFP_HIGH); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); - bio_set_dev(bio, hib_resume_bdev); - bio_set_op_attrs(bio, op, op_flags); if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { pr_err("Adding page to bio failed at %llu\n", diff --git a/kernel/power/wakelock.c b/kernel/power/wakelock.c index 105df4dfc783..52571dcad768 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -39,23 +39,20 @@ ssize_t pm_show_wakelocks(char *buf, bool show_active) { struct rb_node *node; struct wakelock *wl; - char *str = buf; - char *end = buf + PAGE_SIZE; + int len = 0; mutex_lock(&wakelocks_lock); for (node = rb_first(&wakelocks_tree); node; node = rb_next(node)) { wl = rb_entry(node, struct wakelock, node); if (wl->ws->active == show_active) - str += scnprintf(str, end - str, "%s ", wl->name); + len += sysfs_emit_at(buf, len, "%s ", wl->name); } - if (str > buf) - str--; - str += scnprintf(str, end - str, "\n"); + len += sysfs_emit_at(buf, len, "\n"); mutex_unlock(&wakelocks_lock); - return (str - buf); + return len; } #if CONFIG_PM_WAKELOCKS_LIMIT > 0 diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index 653ae04aab7f..c228343eeb97 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -12,7 +12,7 @@ static const int ten_thousand = 10000; static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index e373fbe44da5..431cee212467 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -56,13 +56,13 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp, int flags) { - rsclp->flags |= flags; + WRITE_ONCE(rsclp->flags, rsclp->flags | flags); } static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp, int flags) { - rsclp->flags &= ~flags; + WRITE_ONCE(rsclp->flags, rsclp->flags & ~flags); } static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 422f7e4cc08d..55d049c39608 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -284,7 +284,7 @@ static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); -static bool rcu_fwd_cb_nodelay; /* Short rcu_torture_delay() delays. */ +static atomic_t rcu_fwd_cb_nodelay; /* Short rcu_torture_delay() delays. */ /* * Allocate an element from the rcu_tortures pool. @@ -387,7 +387,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) * period, and we want a long delay occasionally to trigger * force_quiescent_state. */ - if (!READ_ONCE(rcu_fwd_cb_nodelay) && + if (!atomic_read(&rcu_fwd_cb_nodelay) && !(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) { started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); @@ -674,6 +674,7 @@ static struct rcu_torture_ops srcu_ops = { .call = srcu_torture_call, .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, + .cbflood_max = 50000, .irq_capable = 1, .no_pi_lock = IS_ENABLED(CONFIG_TINY_SRCU), .name = "srcu" @@ -708,6 +709,7 @@ static struct rcu_torture_ops srcud_ops = { .call = srcu_torture_call, .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, + .cbflood_max = 50000, .irq_capable = 1, .no_pi_lock = IS_ENABLED(CONFIG_TINY_SRCU), .name = "srcud" @@ -997,7 +999,7 @@ static int rcu_torture_boost(void *arg) goto checkwait; /* Wait for the next test interval. */ - oldstarttime = boost_starttime; + oldstarttime = READ_ONCE(boost_starttime); while (time_before(jiffies, oldstarttime)) { schedule_timeout_interruptible(oldstarttime - jiffies); if (stutter_wait("rcu_torture_boost")) @@ -1041,10 +1043,11 @@ static int rcu_torture_boost(void *arg) * interval. Besides, we are running at RT priority, * so delays should be relatively rare. */ - while (oldstarttime == boost_starttime && !kthread_should_stop()) { + while (oldstarttime == READ_ONCE(boost_starttime) && !kthread_should_stop()) { if (mutex_trylock(&boost_mutex)) { if (oldstarttime == boost_starttime) { - boost_starttime = jiffies + test_boost_interval * HZ; + WRITE_ONCE(boost_starttime, + jiffies + test_boost_interval * HZ); n_rcu_torture_boosts++; } mutex_unlock(&boost_mutex); @@ -1276,7 +1279,7 @@ rcu_torture_writer(void *arg) boot_ended = rcu_inkernel_boot_has_ended(); stutter_waited = stutter_wait("rcu_torture_writer"); if (stutter_waited && - !READ_ONCE(rcu_fwd_cb_nodelay) && + !atomic_read(&rcu_fwd_cb_nodelay) && !cur_ops->slow_gps && !torture_must_stop() && boot_ended) @@ -2180,7 +2183,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp) for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--) if (rfp->n_launders_hist[i].n_launders > 0) break; - mutex_lock(&rcu_fwd_mutex); // Serialize histograms. pr_alert("%s: Callback-invocation histogram %d (duration %lu jiffies):", __func__, rfp->rcu_fwd_id, jiffies - rfp->rcu_fwd_startat); gps_old = rfp->rcu_launder_gp_seq_start; @@ -2193,7 +2195,6 @@ static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp) gps_old = gps; } pr_cont("\n"); - mutex_unlock(&rcu_fwd_mutex); } /* Callback function for continuous-flood RCU callbacks. */ @@ -2281,6 +2282,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, unsigned long stopat; static DEFINE_TORTURE_RANDOM(trs); + pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id); if (!cur_ops->sync) return; // Cannot do need_resched() forward progress testing without ->sync. if (cur_ops->call && cur_ops->cb_barrier) { @@ -2289,7 +2291,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, } /* Tight loop containing cond_resched(). */ - WRITE_ONCE(rcu_fwd_cb_nodelay, true); + atomic_inc(&rcu_fwd_cb_nodelay); cur_ops->sync(); /* Later readers see above write. */ if (selfpropcb) { WRITE_ONCE(fcs.stop, 0); @@ -2325,6 +2327,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, if (selfpropcb) { WRITE_ONCE(fcs.stop, 1); cur_ops->sync(); /* Wait for running CB to complete. */ + pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id); cur_ops->cb_barrier(); /* Wait for queued callbacks. */ } @@ -2333,7 +2336,7 @@ static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, destroy_rcu_head_on_stack(&fcs.rh); } schedule_timeout_uninterruptible(HZ / 10); /* Let kthreads recover. */ - WRITE_ONCE(rcu_fwd_cb_nodelay, false); + atomic_dec(&rcu_fwd_cb_nodelay); } /* Carry out call_rcu() forward-progress testing. */ @@ -2353,13 +2356,14 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) unsigned long stopat; unsigned long stoppedat; + pr_alert("%s: Starting forward-progress test %d\n", __func__, rfp->rcu_fwd_id); if (READ_ONCE(rcu_fwd_emergency_stop)) return; /* Get out of the way quickly, no GP wait! */ if (!cur_ops->call) return; /* Can't do call_rcu() fwd prog without ->call. */ /* Loop continuously posting RCU callbacks. */ - WRITE_ONCE(rcu_fwd_cb_nodelay, true); + atomic_inc(&rcu_fwd_cb_nodelay); cur_ops->sync(); /* Later readers see above write. */ WRITE_ONCE(rfp->rcu_fwd_startat, jiffies); stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES; @@ -2414,6 +2418,7 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb); cver = READ_ONCE(rcu_torture_current_version) - cver; gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps); + pr_alert("%s: Waiting for CBs: %pS() %d\n", __func__, cur_ops->cb_barrier, rfp->rcu_fwd_id); cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */ (void)rcu_torture_fwd_prog_cbfree(rfp); @@ -2427,11 +2432,13 @@ static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) n_launders, n_launders_sa, n_max_gps, n_max_cbs, cver, gps); atomic_long_add(n_max_cbs, &rcu_fwd_max_cbs); + mutex_lock(&rcu_fwd_mutex); // Serialize histograms. rcu_torture_fwd_cb_hist(rfp); + mutex_unlock(&rcu_fwd_mutex); } schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */ tick_dep_clear_task(current, TICK_DEP_BIT_RCU); - WRITE_ONCE(rcu_fwd_cb_nodelay, false); + atomic_dec(&rcu_fwd_cb_nodelay); } @@ -2511,7 +2518,7 @@ static int rcu_torture_fwd_prog(void *args) firsttime = false; WRITE_ONCE(rcu_fwd_seq, rcu_fwd_seq + 1); } else { - while (READ_ONCE(rcu_fwd_seq) == oldseq) + while (READ_ONCE(rcu_fwd_seq) == oldseq && !torture_must_stop()) schedule_timeout_interruptible(1); oldseq = READ_ONCE(rcu_fwd_seq); } @@ -2905,8 +2912,10 @@ rcu_torture_cleanup(void) int i; if (torture_cleanup_begin()) { - if (cur_ops->cb_barrier != NULL) + if (cur_ops->cb_barrier != NULL) { + pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier); cur_ops->cb_barrier(); + } return; } if (!cur_ops) { @@ -2961,8 +2970,10 @@ rcu_torture_cleanup(void) * Wait for all RCU callbacks to fire, then do torture-type-specific * cleanup operations. */ - if (cur_ops->cb_barrier != NULL) + if (cur_ops->cb_barrier != NULL) { + pr_info("%s: Invoking %pS().\n", __func__, cur_ops->cb_barrier); cur_ops->cb_barrier(); + } if (cur_ops->cleanup != NULL) cur_ops->cleanup(); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 84f1d91604cc..ac17348187e4 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -123,7 +123,7 @@ static struct rcu_tasks rt_name = \ .call_func = call, \ .rtpcpu = &rt_name ## __percpu, \ .name = n, \ - .percpu_enqueue_shift = ilog2(CONFIG_NR_CPUS), \ + .percpu_enqueue_shift = order_base_2(CONFIG_NR_CPUS), \ .percpu_enqueue_lim = 1, \ .percpu_dequeue_lim = 1, \ .barrier_q_mutex = __MUTEX_INITIALIZER(rt_name.barrier_q_mutex), \ @@ -216,6 +216,7 @@ static void cblist_init_generic(struct rcu_tasks *rtp) int cpu; unsigned long flags; int lim; + int shift; raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rcu_task_enqueue_lim < 0) { @@ -229,7 +230,10 @@ static void cblist_init_generic(struct rcu_tasks *rtp) if (lim > nr_cpu_ids) lim = nr_cpu_ids; - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids / lim)); + shift = ilog2(nr_cpu_ids / lim); + if (((nr_cpu_ids - 1) >> shift) >= lim) + shift++; + WRITE_ONCE(rtp->percpu_enqueue_shift, shift); WRITE_ONCE(rtp->percpu_dequeue_lim, lim); smp_store_release(&rtp->percpu_enqueue_lim, lim); for_each_possible_cpu(cpu) { @@ -298,7 +302,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, if (unlikely(needadjust)) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim != nr_cpu_ids) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, 0); WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids); smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids); pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name); @@ -413,7 +417,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim > 1) { - WRITE_ONCE(rtp->percpu_enqueue_shift, ilog2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids)); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index a4c25a6283b0..a4b8189455d5 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -87,11 +87,12 @@ static struct rcu_state rcu_state = { .gp_state = RCU_GP_IDLE, .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, .barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex), + .barrier_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.barrier_lock), .name = RCU_NAME, .abbr = RCU_ABBR, .exp_mutex = __MUTEX_INITIALIZER(rcu_state.exp_mutex), .exp_wake_mutex = __MUTEX_INITIALIZER(rcu_state.exp_wake_mutex), - .ofl_lock = __RAW_SPIN_LOCK_UNLOCKED(rcu_state.ofl_lock), + .ofl_lock = __ARCH_SPIN_LOCK_UNLOCKED, }; /* Dump rcu_node combining tree at boot to verify correct setup. */ @@ -153,7 +154,7 @@ static void sync_sched_exp_online_cleanup(int cpu); static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); -/* rcuc/rcub kthread realtime priority */ +/* rcuc/rcub/rcuop kthread realtime priority */ static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0; module_param(kthread_prio, int, 0444); @@ -222,6 +223,16 @@ static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) } /* + * Is the CPU corresponding to the specified rcu_data structure online + * from RCU's perspective? This perspective is given by that structure's + * ->qsmaskinitnext field rather than by the global cpu_online_mask. + */ +static bool rcu_rdp_cpu_online(struct rcu_data *rdp) +{ + return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode)); +} + +/* * Return true if an RCU grace period is in progress. The READ_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. @@ -1086,9 +1097,8 @@ void rcu_irq_enter_irqson(void) * Just check whether or not this CPU has non-offloaded RCU callbacks * queued. */ -int rcu_needs_cpu(u64 basemono, u64 *nextevt) +int rcu_needs_cpu(void) { - *nextevt = KTIME_MAX; return !rcu_segcblist_empty(&this_cpu_ptr(&rcu_data)->cblist) && !rcu_rdp_is_offloaded(this_cpu_ptr(&rcu_data)); } @@ -1167,15 +1177,20 @@ void rcu_request_urgent_qs_task(struct task_struct *t) bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; - struct rcu_node *rnp; bool ret = false; if (in_nmi() || !rcu_scheduler_fully_active) return true; preempt_disable_notrace(); rdp = this_cpu_ptr(&rcu_data); - rnp = rdp->mynode; - if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1) + /* + * Strictly, we care here about the case where the current CPU is + * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask + * not being up to date. So arch_spin_is_locked() might have a + * false positive if it's held by some *other* CPU, but that's + * OK because that just means a false *negative* on the warning. + */ + if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock)) ret = true; preempt_enable_notrace(); return ret; @@ -1260,8 +1275,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * For more detail, please refer to the "Hotplug CPU" section * of RCU's Requirements documentation. */ - if (WARN_ON_ONCE(!(rdp->grpmask & rcu_rnp_online_cpus(rnp)))) { - bool onl; + if (WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp))) { struct rcu_node *rnp1; pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n", @@ -1270,9 +1284,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent) pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n", __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask); - onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n", - __func__, rdp->cpu, ".o"[onl], + __func__, rdp->cpu, ".o"[rcu_rdp_cpu_online(rdp)], (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); return 1; /* Break things loose after complaining. */ @@ -1739,7 +1752,6 @@ static void rcu_strict_gp_boundary(void *unused) */ static noinline_for_stack bool rcu_gp_init(void) { - unsigned long firstseq; unsigned long flags; unsigned long oldmask; unsigned long mask; @@ -1782,22 +1794,17 @@ static noinline_for_stack bool rcu_gp_init(void) * of RCU's Requirements documentation. */ WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF); + /* Exclude CPU hotplug operations. */ rcu_for_each_leaf_node(rnp) { - // Wait for CPU-hotplug operations that might have - // started before this grace period did. - smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values. - firstseq = READ_ONCE(rnp->ofl_seq); - if (firstseq & 0x1) - while (firstseq == READ_ONCE(rnp->ofl_seq)) - schedule_timeout_idle(1); // Can't wake unless RCU is watching. - smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values. - raw_spin_lock(&rcu_state.ofl_lock); - raw_spin_lock_irq_rcu_node(rnp); + local_irq_save(flags); + arch_spin_lock(&rcu_state.ofl_lock); + raw_spin_lock_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && !rnp->wait_blkd_tasks) { /* Nothing to do on this leaf rcu_node structure. */ - raw_spin_unlock_irq_rcu_node(rnp); - raw_spin_unlock(&rcu_state.ofl_lock); + raw_spin_unlock_rcu_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); continue; } @@ -1832,8 +1839,9 @@ static noinline_for_stack bool rcu_gp_init(void) rcu_cleanup_dead_rnp(rnp); } - raw_spin_unlock_irq_rcu_node(rnp); - raw_spin_unlock(&rcu_state.ofl_lock); + raw_spin_unlock_rcu_node(rnp); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); } rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */ @@ -2850,10 +2858,12 @@ static void rcu_cpu_kthread(unsigned int cpu) { unsigned int *statusp = this_cpu_ptr(&rcu_data.rcu_cpu_kthread_status); char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work); + unsigned long *j = this_cpu_ptr(&rcu_data.rcuc_activity); int spincnt; trace_rcu_utilization(TPS("Start CPU kthread@rcu_run")); for (spincnt = 0; spincnt < 10; spincnt++) { + WRITE_ONCE(*j, jiffies); local_bh_disable(); *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); @@ -2874,6 +2884,7 @@ static void rcu_cpu_kthread(unsigned int cpu) schedule_timeout_idle(2); trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); *statusp = RCU_KTHREAD_WAITING; + WRITE_ONCE(*j, jiffies); } static struct smp_hotplug_thread rcu_cpu_thread_spec = { @@ -2894,7 +2905,7 @@ static int __init rcu_spawn_core_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_data.rcu_cpu_has_work, cpu) = 0; - if (!IS_ENABLED(CONFIG_RCU_BOOST) && use_softirq) + if (use_softirq) return 0; WARN_ONCE(smpboot_register_percpu_thread(&rcu_cpu_thread_spec), "%s: Could not start rcuc kthread, OOM is now expected behavior\n", __func__); @@ -2995,9 +3006,47 @@ static void check_cb_ovld(struct rcu_data *rdp) raw_spin_unlock_rcu_node(rnp); } -/* Helper function for call_rcu() and friends. */ -static void -__call_rcu(struct rcu_head *head, rcu_callback_t func) +/** + * call_rcu() - Queue an RCU callback for invocation after a grace period. + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all pre-existing RCU read-side + * critical sections have completed. However, the callback function + * might well execute concurrently with RCU read-side critical sections + * that started after call_rcu() was invoked. + * + * RCU read-side critical sections are delimited by rcu_read_lock() + * and rcu_read_unlock(), and may be nested. In addition, but only in + * v5.0 and later, regions of code across which interrupts, preemption, + * or softirqs have been disabled also serve as RCU read-side critical + * sections. This includes hardware interrupt handlers, softirq handlers, + * and NMI handlers. + * + * Note that all CPUs must agree that the grace period extended beyond + * all pre-existing RCU read-side critical section. On systems with more + * than one CPU, this means that when "func()" is invoked, each CPU is + * guaranteed to have executed a full memory barrier since the end of its + * last RCU read-side critical section whose beginning preceded the call + * to call_rcu(). It also means that each CPU executing an RCU read-side + * critical section that continues beyond the start of "func()" must have + * executed a memory barrier after the call_rcu() but before the beginning + * of that RCU read-side critical section. Note that these guarantees + * include CPUs that are offline, idle, or executing in user mode, as + * well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the + * resulting RCU callback function "func()", then both CPU A and CPU B are + * guaranteed to execute a full memory barrier during the time interval + * between the call to call_rcu() and the invocation of "func()" -- even + * if CPU A and CPU B are the same CPU (but again only if the system has + * more than one CPU). + * + * Implementation of these memory-ordering guarantees is described here: + * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. + */ +void call_rcu(struct rcu_head *head, rcu_callback_t func) { static atomic_t doublefrees; unsigned long flags; @@ -3011,7 +3060,7 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) /* * Probable double call_rcu(), so leak the callback. * Use rcu:rcu_callback trace event to find the previous - * time callback was passed to __call_rcu(). + * time callback was passed to call_rcu(). */ if (atomic_inc_return(&doublefrees) < 4) { pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func); @@ -3022,8 +3071,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) } head->func = func; head->next = NULL; - local_irq_save(flags); kasan_record_aux_stack_noalloc(head); + local_irq_save(flags); rdp = this_cpu_ptr(&rcu_data); /* Add the callback to our list. */ @@ -3060,51 +3109,6 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) local_irq_restore(flags); } } - -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: structure to be used for queueing the RCU updates. - * @func: actual callback function to be invoked after the grace period - * - * The callback function will be invoked some time after a full grace - * period elapses, in other words after all pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. - * - * RCU read-side critical sections are delimited by rcu_read_lock() - * and rcu_read_unlock(), and may be nested. In addition, but only in - * v5.0 and later, regions of code across which interrupts, preemption, - * or softirqs have been disabled also serve as RCU read-side critical - * sections. This includes hardware interrupt handlers, softirq handlers, - * and NMI handlers. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - * - * Implementation of these memory-ordering guarantees is described here: - * Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.rst. - */ -void call_rcu(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func); -} EXPORT_SYMBOL_GPL(call_rcu); @@ -3984,13 +3988,16 @@ static void rcu_barrier_callback(struct rcu_head *rhp) } /* - * Called with preemption disabled, and from cross-cpu IRQ context. + * If needed, entrain an rcu_barrier() callback on rdp->cblist. */ -static void rcu_barrier_func(void *cpu_in) +static void rcu_barrier_entrain(struct rcu_data *rdp) { - uintptr_t cpu = (uintptr_t)cpu_in; - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + unsigned long gseq = READ_ONCE(rcu_state.barrier_sequence); + unsigned long lseq = READ_ONCE(rdp->barrier_seq_snap); + lockdep_assert_held(&rcu_state.barrier_lock); + if (rcu_seq_state(lseq) || !rcu_seq_state(gseq) || rcu_seq_ctr(lseq) != rcu_seq_ctr(gseq)) + return; rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence); rdp->barrier_head.func = rcu_barrier_callback; debug_rcu_head_queue(&rdp->barrier_head); @@ -4000,10 +4007,26 @@ static void rcu_barrier_func(void *cpu_in) atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); - rcu_barrier_trace(TPS("IRQNQ"), -1, - rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence); } rcu_nocb_unlock(rdp); + smp_store_release(&rdp->barrier_seq_snap, gseq); +} + +/* + * Called with preemption disabled, and from cross-cpu IRQ context. + */ +static void rcu_barrier_handler(void *cpu_in) +{ + uintptr_t cpu = (uintptr_t)cpu_in; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + + lockdep_assert_irqs_disabled(); + WARN_ON_ONCE(cpu != rdp->cpu); + WARN_ON_ONCE(cpu != smp_processor_id()); + raw_spin_lock(&rcu_state.barrier_lock); + rcu_barrier_entrain(rdp); + raw_spin_unlock(&rcu_state.barrier_lock); } /** @@ -4017,6 +4040,8 @@ static void rcu_barrier_func(void *cpu_in) void rcu_barrier(void) { uintptr_t cpu; + unsigned long flags; + unsigned long gseq; struct rcu_data *rdp; unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence); @@ -4027,15 +4052,16 @@ void rcu_barrier(void) /* Did someone else do our work for us? */ if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { - rcu_barrier_trace(TPS("EarlyExit"), -1, - rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("EarlyExit"), -1, rcu_state.barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ mutex_unlock(&rcu_state.barrier_mutex); return; } /* Mark the start of the barrier operation. */ + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); rcu_seq_start(&rcu_state.barrier_sequence); + gseq = rcu_state.barrier_sequence; rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence); /* @@ -4047,7 +4073,7 @@ void rcu_barrier(void) */ init_completion(&rcu_state.barrier_completion); atomic_set(&rcu_state.barrier_cpu_count, 2); - cpus_read_lock(); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); /* * Force each CPU with callbacks to register a new callback. @@ -4056,29 +4082,31 @@ void rcu_barrier(void) */ for_each_possible_cpu(cpu) { rdp = per_cpu_ptr(&rcu_data, cpu); - if (cpu_is_offline(cpu) && - !rcu_rdp_is_offloaded(rdp)) +retry: + if (smp_load_acquire(&rdp->barrier_seq_snap) == gseq) continue; - if (rcu_segcblist_n_cbs(&rdp->cblist) && cpu_online(cpu)) { - rcu_barrier_trace(TPS("OnlineQ"), cpu, - rcu_state.barrier_sequence); - smp_call_function_single(cpu, rcu_barrier_func, (void *)cpu, 1); - } else if (rcu_segcblist_n_cbs(&rdp->cblist) && - cpu_is_offline(cpu)) { - rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu, - rcu_state.barrier_sequence); - local_irq_disable(); - rcu_barrier_func((void *)cpu); - local_irq_enable(); - } else if (cpu_is_offline(cpu)) { - rcu_barrier_trace(TPS("OfflineNoCBNoQ"), cpu, - rcu_state.barrier_sequence); - } else { - rcu_barrier_trace(TPS("OnlineNQ"), cpu, - rcu_state.barrier_sequence); + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); + if (!rcu_segcblist_n_cbs(&rdp->cblist)) { + WRITE_ONCE(rdp->barrier_seq_snap, gseq); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + rcu_barrier_trace(TPS("NQ"), cpu, rcu_state.barrier_sequence); + continue; + } + if (!rcu_rdp_cpu_online(rdp)) { + rcu_barrier_entrain(rdp); + WARN_ON_ONCE(READ_ONCE(rdp->barrier_seq_snap) != gseq); + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + rcu_barrier_trace(TPS("OfflineNoCBQ"), cpu, rcu_state.barrier_sequence); + continue; + } + raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags); + if (smp_call_function_single(cpu, rcu_barrier_handler, (void *)cpu, 1)) { + schedule_timeout_uninterruptible(1); + goto retry; } + WARN_ON_ONCE(READ_ONCE(rdp->barrier_seq_snap) != gseq); + rcu_barrier_trace(TPS("OnlineQ"), cpu, rcu_state.barrier_sequence); } - cpus_read_unlock(); /* * Now that we have an rcu_barrier_callback() callback on each @@ -4093,6 +4121,12 @@ void rcu_barrier(void) /* Mark the end of the barrier operation. */ rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence); rcu_seq_end(&rcu_state.barrier_sequence); + gseq = rcu_state.barrier_sequence; + for_each_possible_cpu(cpu) { + rdp = per_cpu_ptr(&rcu_data, cpu); + + WRITE_ONCE(rdp->barrier_seq_snap, gseq); + } /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rcu_state.barrier_mutex); @@ -4140,6 +4174,7 @@ rcu_boot_init_percpu_data(int cpu) INIT_WORK(&rdp->strict_work, strict_work_handler); WARN_ON_ONCE(rdp->dynticks_nesting != 1); WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp))); + rdp->barrier_seq_snap = rcu_state.barrier_sequence; rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; rdp->rcu_onl_gp_seq = rcu_state.gp_seq; @@ -4287,12 +4322,13 @@ void rcu_cpu_starting(unsigned int cpu) rnp = rdp->mynode; mask = rdp->grpmask; - WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); - WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); + local_irq_save(flags); + arch_spin_lock(&rcu_state.ofl_lock); rcu_dynticks_eqs_online(); - smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). - raw_spin_lock_irqsave_rcu_node(rnp, flags); + raw_spin_lock(&rcu_state.barrier_lock); + raw_spin_lock_rcu_node(rnp); WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); + raw_spin_unlock(&rcu_state.barrier_lock); newcpu = !(rnp->expmaskinitnext & mask); rnp->expmaskinitnext |= mask; /* Allow lockless access for expedited grace periods. */ @@ -4304,15 +4340,18 @@ void rcu_cpu_starting(unsigned int cpu) /* An incoming CPU should never be blocking a grace period. */ if (WARN_ON_ONCE(rnp->qsmask & mask)) { /* RCU waiting on incoming CPU? */ + /* rcu_report_qs_rnp() *really* wants some flags to restore */ + unsigned long flags2; + + local_irq_save(flags2); rcu_disable_urgency_upon_qs(rdp); /* Report QS -after- changing ->qsmaskinitnext! */ - rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags2); } else { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + raw_spin_unlock_rcu_node(rnp); } - smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). - WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); - WARN_ON_ONCE(rnp->ofl_seq & 0x1); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(flags); smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -4326,7 +4365,7 @@ void rcu_cpu_starting(unsigned int cpu) */ void rcu_report_dead(unsigned int cpu) { - unsigned long flags; + unsigned long flags, seq_flags; unsigned long mask; struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ @@ -4340,10 +4379,8 @@ void rcu_report_dead(unsigned int cpu) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; - WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); - WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); - smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). - raw_spin_lock(&rcu_state.ofl_lock); + local_irq_save(seq_flags); + arch_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags); @@ -4354,10 +4391,8 @@ void rcu_report_dead(unsigned int cpu) } WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - raw_spin_unlock(&rcu_state.ofl_lock); - smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). - WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); - WARN_ON_ONCE(rnp->ofl_seq & 0x1); + arch_spin_unlock(&rcu_state.ofl_lock); + local_irq_restore(seq_flags); rdp->cpu_started = false; } @@ -4380,7 +4415,9 @@ void rcutree_migrate_callbacks(int cpu) rcu_segcblist_empty(&rdp->cblist)) return; /* No callbacks to migrate. */ - local_irq_save(flags); + raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags); + WARN_ON_ONCE(rcu_rdp_cpu_online(rdp)); + rcu_barrier_entrain(rdp); my_rdp = this_cpu_ptr(&rcu_data); my_rnp = my_rdp->mynode; rcu_nocb_lock(my_rdp); /* irqs already disabled. */ @@ -4390,10 +4427,10 @@ void rcutree_migrate_callbacks(int cpu) needwake = rcu_advance_cbs(my_rnp, rdp) || rcu_advance_cbs(my_rnp, my_rdp); rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); + raw_spin_unlock(&rcu_state.barrier_lock); /* irqs remain disabled. */ needwake = needwake || rcu_advance_cbs(my_rnp, my_rdp); rcu_segcblist_disable(&rdp->cblist); - WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != - !rcu_segcblist_n_cbs(&my_rdp->cblist)); + WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != !rcu_segcblist_n_cbs(&my_rdp->cblist)); if (rcu_rdp_is_offloaded(my_rdp)) { raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */ __call_rcu_nocb_wake(my_rdp, true, flags); @@ -4440,26 +4477,10 @@ static int rcu_pm_notify(struct notifier_block *self, static int __init rcu_spawn_gp_kthread(void) { unsigned long flags; - int kthread_prio_in = kthread_prio; struct rcu_node *rnp; struct sched_param sp; struct task_struct *t; - /* Force priority into range. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 - && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) - kthread_prio = 2; - else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) - kthread_prio = 1; - else if (kthread_prio < 0) - kthread_prio = 0; - else if (kthread_prio > 99) - kthread_prio = 99; - - if (kthread_prio != kthread_prio_in) - pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n", - kthread_prio, kthread_prio_in); - rcu_scheduler_fully_active = 1; t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); if (WARN_ONCE(IS_ERR(t), "%s: Could not start grace-period kthread, OOM is now expected behavior\n", __func__)) @@ -4570,6 +4591,7 @@ static void __init rcu_init_one(void) init_waitqueue_head(&rnp->exp_wq[2]); init_waitqueue_head(&rnp->exp_wq[3]); spin_lock_init(&rnp->exp_lock); + mutex_init(&rnp->boost_kthread_mutex); } } @@ -4585,6 +4607,28 @@ static void __init rcu_init_one(void) } /* + * Force priority from the kernel command-line into range. + */ +static void __init sanitize_kthread_prio(void) +{ + int kthread_prio_in = kthread_prio; + + if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2 + && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST)) + kthread_prio = 2; + else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1) + kthread_prio = 1; + else if (kthread_prio < 0) + kthread_prio = 0; + else if (kthread_prio > 99) + kthread_prio = 99; + + if (kthread_prio != kthread_prio_in) + pr_alert("%s: Limited prio to %d from %d\n", + __func__, kthread_prio, kthread_prio_in); +} + +/* * Compute the rcu_node tree geometry from kernel parameters. This cannot * replace the definitions in tree.h because those are needed to size * the ->node array in the rcu_state structure. @@ -4744,6 +4788,7 @@ void __init rcu_init(void) kfree_rcu_batch_init(); rcu_bootup_announce(); + sanitize_kthread_prio(); rcu_init_geometry(); rcu_init_one(); if (dump_tree) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 486fc901bd08..926673ebe355 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -56,8 +56,6 @@ struct rcu_node { /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; - unsigned long ofl_seq; /* CPU-hotplug operation sequence count. */ - /* Online CPUs for next grace period. */ unsigned long expmask; /* CPUs or groups that need to check in */ /* to allow the current expedited GP */ /* to complete. */ @@ -110,6 +108,9 @@ struct rcu_node { /* side effect, not as a lock. */ unsigned long boost_time; /* When to start boosting (jiffies). */ + struct mutex boost_kthread_mutex; + /* Exclusion for thread spawning and affinity */ + /* manipulation. */ struct task_struct *boost_kthread_task; /* kthread that takes care of priority */ /* boosting for this rcu_node structure. */ @@ -190,6 +191,7 @@ struct rcu_data { bool rcu_forced_tick_exp; /* ... provide QS to expedited GP. */ /* 4) rcu_barrier(), OOM callbacks, and expediting. */ + unsigned long barrier_seq_snap; /* Snap of rcu_state.barrier_sequence. */ struct rcu_head barrier_head; int exp_dynticks_snap; /* Double-check need for IPI. */ @@ -203,6 +205,8 @@ struct rcu_data { int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ struct timer_list nocb_timer; /* Enforce finite deferral. */ unsigned long nocb_gp_adv_time; /* Last call_rcu() CB adv (jiffies). */ + struct mutex nocb_gp_kthread_mutex; /* Exclusion for nocb gp kthread */ + /* spawning */ /* The following fields are used by call_rcu, hence own cacheline. */ raw_spinlock_t nocb_bypass_lock ____cacheline_internodealigned_in_smp; @@ -237,6 +241,7 @@ struct rcu_data { /* rcuc per-CPU kthread or NULL. */ unsigned int rcu_cpu_kthread_status; char rcu_cpu_has_work; + unsigned long rcuc_activity; /* 7) Diagnostic data, including RCU CPU stall warnings. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ @@ -302,9 +307,8 @@ struct rcu_state { /* The following fields are guarded by the root rcu_node's lock. */ - u8 boost ____cacheline_internodealigned_in_smp; - /* Subject to priority boost. */ - unsigned long gp_seq; /* Grace-period sequence #. */ + unsigned long gp_seq ____cacheline_internodealigned_in_smp; + /* Grace-period sequence #. */ unsigned long gp_max; /* Maximum GP duration in */ /* jiffies. */ struct task_struct *gp_kthread; /* Task for grace periods. */ @@ -323,6 +327,8 @@ struct rcu_state { /* rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ + raw_spinlock_t barrier_lock; /* Protects ->barrier_seq_snap. */ + struct mutex exp_mutex; /* Serialize expedited GP. */ struct mutex exp_wake_mutex; /* Serialize wakeup. */ unsigned long expedited_sequence; /* Take a ticket. */ @@ -355,7 +361,7 @@ struct rcu_state { const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ - raw_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; + arch_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; /* Synchronize offline with */ /* GP pre-initialization. */ }; diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 237a79989aba..60197ea24ceb 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -502,7 +502,8 @@ static void synchronize_rcu_expedited_wait(void) if (synchronize_rcu_expedited_wait_once(1)) return; rcu_for_each_leaf_node(rnp) { - for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { + mask = READ_ONCE(rnp->expmask); + for_each_leaf_node_cpu_mask(rnp, cpu, mask) { rdp = per_cpu_ptr(&rcu_data, cpu); if (rdp->rcu_forced_tick_exp) continue; @@ -656,7 +657,7 @@ static void rcu_exp_handler(void *unused) */ if (!depth) { if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || - rcu_dynticks_curr_cpu_in_eqs()) { + rcu_is_cpu_rrupt_from_idle()) { rcu_report_exp_rdp(rdp); } else { WRITE_ONCE(rdp->cpu_no_qs.b.exp, true); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index eeafb546a7a0..636d0546a4e9 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1169,7 +1169,7 @@ void __init rcu_init_nohz(void) struct rcu_data *rdp; #if defined(CONFIG_NO_HZ_FULL) - if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) + if (tick_nohz_full_running && !cpumask_empty(tick_nohz_full_mask)) need_rcu_nocb_mask = true; #endif /* #if defined(CONFIG_NO_HZ_FULL) */ @@ -1226,6 +1226,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) raw_spin_lock_init(&rdp->nocb_gp_lock); timer_setup(&rdp->nocb_timer, do_nocb_deferred_wakeup_timer, 0); rcu_cblist_init(&rdp->nocb_bypass); + mutex_init(&rdp->nocb_gp_kthread_mutex); } /* @@ -1238,6 +1239,7 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_data *rdp_gp; struct task_struct *t; + struct sched_param sp; if (!rcu_scheduler_fully_active || !rcu_nocb_is_setup) return; @@ -1247,20 +1249,30 @@ static void rcu_spawn_cpu_nocb_kthread(int cpu) return; /* If we didn't spawn the GP kthread first, reorganize! */ + sp.sched_priority = kthread_prio; rdp_gp = rdp->nocb_gp_rdp; + mutex_lock(&rdp_gp->nocb_gp_kthread_mutex); if (!rdp_gp->nocb_gp_kthread) { t = kthread_run(rcu_nocb_gp_kthread, rdp_gp, "rcuog/%d", rdp_gp->cpu); - if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) + if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo GP kthread, OOM is now expected behavior\n", __func__)) { + mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex); return; + } WRITE_ONCE(rdp_gp->nocb_gp_kthread, t); + if (kthread_prio) + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } + mutex_unlock(&rdp_gp->nocb_gp_kthread_mutex); /* Spawn the kthread for this CPU. */ t = kthread_run(rcu_nocb_cb_kthread, rdp, "rcuo%c/%d", rcu_state.abbr, cpu); if (WARN_ONCE(IS_ERR(t), "%s: Could not start rcuo CB kthread, OOM is now expected behavior\n", __func__)) return; + + if (kthread_prio) + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); WRITE_ONCE(rdp->nocb_cb_kthread, t); WRITE_ONCE(rdp->nocb_gp_kthread, rdp_gp->nocb_gp_kthread); } @@ -1348,7 +1360,7 @@ static void __init rcu_organize_nocb_kthreads(void) */ void rcu_bind_current_to_nocb(void) { - if (cpumask_available(rcu_nocb_mask) && cpumask_weight(rcu_nocb_mask)) + if (cpumask_available(rcu_nocb_mask) && !cpumask_empty(rcu_nocb_mask)) WARN_ON(sched_setaffinity(current->pid, rcu_nocb_mask)); } EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index c5b45c2f68a1..6082dd23408f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -330,7 +330,7 @@ void rcu_note_context_switch(bool preempt) * then queue the task as required based on the states * of any ongoing and expedited grace periods. */ - WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); + WARN_ON_ONCE(!rcu_rdp_cpu_online(rdp)); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); trace_rcu_preempt_task(rcu_state.name, t->pid, @@ -556,16 +556,16 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } - /* Unboost if we were boosted. */ - if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) - rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); - /* * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) rcu_report_exp_rnp(rnp, true); + + /* Unboost if we were boosted. */ + if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) + rt_mutex_futex_unlock(&rnp->boost_mtx.rtmutex); } else { local_irq_restore(flags); } @@ -773,7 +773,6 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) int cpu; int i; struct list_head *lhp; - bool onl; struct rcu_data *rdp; struct rcu_node *rnp1; @@ -797,9 +796,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) pr_cont("\n"); for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { rdp = per_cpu_ptr(&rcu_data, cpu); - onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp)); pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n", - cpu, ".o"[onl], + cpu, ".o"[rcu_rdp_cpu_online(rdp)], (long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags, (long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags); } @@ -996,12 +994,15 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) */ static void rcu_cpu_kthread_setup(unsigned int cpu) { + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); #ifdef CONFIG_RCU_BOOST struct sched_param sp; sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); #endif /* #ifdef CONFIG_RCU_BOOST */ + + WRITE_ONCE(rdp->rcuc_activity, jiffies); } #ifdef CONFIG_RCU_BOOST @@ -1172,15 +1173,14 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) struct sched_param sp; struct task_struct *t; + mutex_lock(&rnp->boost_kthread_mutex); if (rnp->boost_kthread_task || !rcu_scheduler_fully_active) - return; - - rcu_state.boost = 1; + goto out; t = kthread_create(rcu_boost_kthread, (void *)rnp, "rcub/%d", rnp_index); if (WARN_ON_ONCE(IS_ERR(t))) - return; + goto out; raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; @@ -1188,6 +1188,9 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ + + out: + mutex_unlock(&rnp->boost_kthread_mutex); } /* @@ -1210,14 +1213,16 @@ static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) return; if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) return; + mutex_lock(&rnp->boost_kthread_mutex); for_each_leaf_node_possible_cpu(rnp, cpu) if ((mask & leaf_node_cpu_bit(rnp, cpu)) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); cpumask_and(cm, cm, housekeeping_cpumask(HK_FLAG_RCU)); - if (cpumask_weight(cm) == 0) + if (cpumask_empty(cm)) cpumask_copy(cm, housekeeping_cpumask(HK_FLAG_RCU)); set_cpus_allowed_ptr(t, cm); + mutex_unlock(&rnp->boost_kthread_mutex); free_cpumask_var(cm); } diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 21bebf7c9030..0c5d8516516a 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -379,6 +379,15 @@ static bool rcu_is_gp_kthread_starving(unsigned long *jp) return j > 2 * HZ; } +static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp) +{ + unsigned long j = jiffies - READ_ONCE(rdp->rcuc_activity); + + if (jp) + *jp = j; + return j > 2 * HZ; +} + /* * Print out diagnostic information for the specified stalled CPU. * @@ -430,6 +439,29 @@ static void print_cpu_stall_info(int cpu) falsepositive ? " (false positive?)" : ""); } +static void rcuc_kthread_dump(struct rcu_data *rdp) +{ + int cpu; + unsigned long j; + struct task_struct *rcuc; + + rcuc = rdp->rcu_cpu_kthread_task; + if (!rcuc) + return; + + cpu = task_cpu(rcuc); + if (cpu_is_offline(cpu) || idle_cpu(cpu)) + return; + + if (!rcu_is_rcuc_kthread_starving(rdp, &j)) + return; + + pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j); + sched_show_task(rcuc); + if (!trigger_single_cpu_backtrace(cpu)) + dump_cpu_task(cpu); +} + /* Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(void) { @@ -601,6 +633,9 @@ static void print_cpu_stall(unsigned long gps) rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); + if (!use_softirq) + rcuc_kthread_dump(rdp); + rcu_dump_cpu_stacks(); raw_spin_lock_irqsave_rcu_node(rnp, flags); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 156892c22bb5..180ff9c41fa8 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -407,6 +407,13 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, } EXPORT_SYMBOL_GPL(__wait_rcu_gp); +void finish_rcuwait(struct rcuwait *w) +{ + rcu_assign_pointer(w->task, NULL); + __set_current_state(TASK_RUNNING); +} +EXPORT_SYMBOL_GPL(finish_rcuwait); + #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head) { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2e4ae00e52d1..6c56ee848e2a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4424,6 +4424,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) init_entity_runnable_average(&p->se); + #ifdef CONFIG_SCHED_INFO if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); @@ -4439,18 +4440,23 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) return 0; } -void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) +void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) { unsigned long flags; -#ifdef CONFIG_CGROUP_SCHED - struct task_group *tg; -#endif + /* + * Because we're not yet on the pid-hash, p->pi_lock isn't strictly + * required yet, but lockdep gets upset if rules are violated. + */ raw_spin_lock_irqsave(&p->pi_lock, flags); #ifdef CONFIG_CGROUP_SCHED - tg = container_of(kargs->cset->subsys[cpu_cgrp_id], - struct task_group, css); - p->sched_task_group = autogroup_task_group(p, tg); + if (1) { + struct task_group *tg; + tg = container_of(kargs->cset->subsys[cpu_cgrp_id], + struct task_group, css); + tg = autogroup_task_group(p, tg); + p->sched_task_group = tg; + } #endif rseq_migrate(p); /* @@ -4461,7 +4467,10 @@ void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} +void sched_post_fork(struct task_struct *p) +{ uclamp_post_fork(p); } @@ -5822,8 +5831,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } if (schedstat_enabled() && rq->core->core_forceidle_count) { - if (cookie) - rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_start = rq_clock(rq->core); rq->core->core_forceidle_occupation = occ; } @@ -6345,8 +6353,7 @@ static inline void sched_submit_work(struct task_struct *tsk) * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. */ - if (blk_needs_flush_plug(tsk)) - blk_flush_plug(tsk->plug, true); + blk_flush_plug(tsk->plug, true); } static void sched_update_worker(struct task_struct *tsk) @@ -8219,9 +8226,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; spin_lock(lock); @@ -8239,9 +8244,7 @@ int __cond_resched_rwlock_read(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { read_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; read_lock(lock); @@ -8259,9 +8262,7 @@ int __cond_resched_rwlock_write(rwlock_t *lock) if (rwlock_needbreak(lock) || resched) { write_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; write_lock(lock); @@ -8378,9 +8379,7 @@ int io_schedule_prepare(void) int old_iowait = current->in_iowait; current->in_iowait = 1; - if (current->plug) - blk_flush_plug(current->plug, true); - + blk_flush_plug(current->plug, true); return old_iowait; } diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 1fb45672ec85..c8746a9a7ada 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -277,7 +277,7 @@ void __sched_core_account_forceidle(struct rq *rq) rq_i = cpu_rq(i); p = rq_i->core_pick ?: rq_i->curr; - if (!p->core_cookie) + if (p == rq_i->idle) continue; __schedstat_add(p->stats.core_forceidle_sum, delta); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 26778884d9ab..cffcd08f4ec8 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -539,7 +539,7 @@ ATTRIBUTE_GROUPS(sugov); static void sugov_tunables_free(struct kobject *kobj) { - struct gov_attr_set *attr_set = container_of(kobj, struct gov_attr_set, kobj); + struct gov_attr_set *attr_set = to_gov_attr_set(kobj); kfree(to_sugov_tunables(attr_set)); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 095b0aa378df..5146163bfabb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3028,9 +3028,11 @@ enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u32 divider = get_pelt_divider(&se->avg); sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } #else static inline void @@ -3381,7 +3383,6 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; } - /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3449,15 +3450,14 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3466,23 +3466,30 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq */ divider = get_pelt_divider(&cfs_rq->avg); + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; - se->avg.util_sum = se->avg.util_avg * divider; + new_sum = se->avg.util_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.util_sum; + se->avg.util_sum = new_sum; /* Update parent cfs_rq utilization */ - add_positive(&cfs_rq->avg.util_avg, delta); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + add_positive(&cfs_rq->avg.util_avg, delta_avg); + add_positive(&cfs_rq->avg.util_sum, delta_sum); + + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; - u32 divider; + long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* @@ -3493,19 +3500,25 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* Set new sched_entity's runnable */ se->avg.runnable_avg = gcfs_rq->avg.runnable_avg; - se->avg.runnable_sum = se->avg.runnable_avg * divider; + new_sum = se->avg.runnable_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.runnable_sum; + se->avg.runnable_sum = new_sum; /* Update parent cfs_rq runnable */ - add_positive(&cfs_rq->avg.runnable_avg, delta); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + add_positive(&cfs_rq->avg.runnable_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; + s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3532,7 +3545,7 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq * assuming all tasks are equally runnable. */ if (scale_load_down(gcfs_rq->load.weight)) { - load_sum = div_s64(gcfs_rq->avg.load_sum, + load_sum = div_u64(gcfs_rq->avg.load_sum, scale_load_down(gcfs_rq->load.weight)); } @@ -3549,19 +3562,22 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); - load_sum = (s64)se_weight(se) * runnable_sum; - load_avg = div_s64(load_sum, divider); - - se->avg.load_sum = runnable_sum; + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); - delta = load_avg - se->avg.load_avg; - if (!delta) + delta_avg = load_avg - se->avg.load_avg; + if (!delta_avg) return; - se->avg.load_avg = load_avg; + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - add_positive(&cfs_rq->avg.load_avg, delta); - cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3652,7 +3668,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum * * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. * - * Returns true if the load decayed or we removed load. + * Return: true if the load decayed or we removed load. * * Since both these conditions indicate a changed cfs_rq->avg.load we should * call update_tg_load_avg() when this function returns true. @@ -3677,15 +3693,32 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sa->load_sum = sa->load_avg * divider; + sub_positive(&sa->load_sum, r * divider); + /* See sa->util_sum below */ + sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER); r = removed_util; sub_positive(&sa->util_avg, r); - sa->util_sum = sa->util_avg * divider; + sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sa->runnable_sum = sa->runnable_avg * divider; + sub_positive(&sa->runnable_sum, r * divider); + /* See sa->util_sum above */ + sa->runnable_sum = max_t(u32, sa->runnable_sum, + sa->runnable_avg * PELT_MIN_DIVIDER); /* * removed_runnable is the unweighted version of removed_load so we @@ -3772,17 +3805,18 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - /* - * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. - * See ___update_load_avg() for details. - */ - u32 divider = get_pelt_divider(&cfs_rq->avg); - dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); + sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -8539,6 +8573,8 @@ group_type group_classify(unsigned int imbalance_pct, * * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings * of @dst_cpu are idle and @sg has lower priority. + * + * Return: true if @dst_cpu can pull tasks, false otherwise. */ static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, @@ -8614,6 +8650,7 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. + * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. * @sg_status: Holds flag indicating the status of the sched_group @@ -9421,12 +9458,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. + * @env: The load balancing environment. * * Also calculates the amount of runnable load which should be moved * to restore balance. * - * @env: The load balancing environment. - * * Return: - The busiest group if imbalance exists. */ static struct sched_group *find_busiest_group(struct lb_env *env) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index b5add64d9698..3d2825408e3a 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -147,11 +147,11 @@ #endif #ifdef CONFIG_RSEQ -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK \ +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ (MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ \ - | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ) #else -#define MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 +#define MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK 0 #endif #define MEMBARRIER_CMD_BITMASK \ @@ -159,7 +159,8 @@ | MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED \ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ - | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) static void ipi_mb(void *info) { diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index e06071bf3472..c336f5f481bc 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -37,9 +37,11 @@ update_irq_load_avg(struct rq *rq, u64 running) } #endif +#define PELT_MIN_DIVIDER (LOAD_AVG_MAX - 1024) + static inline u32 get_pelt_divider(struct sched_avg *avg) { - return LOAD_AVG_MAX - 1024 + avg->period_contrib; + return PELT_MIN_DIVIDER + avg->period_contrib; } static inline void cfs_se_util_change(struct sched_avg *avg) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..e14358178849 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1082,44 +1082,6 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -static int psi_io_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_IO); -} - -static int psi_memory_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_MEM); -} - -static int psi_cpu_show(struct seq_file *m, void *v) -{ - return psi_show(m, &psi_system, PSI_CPU); -} - -static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) -{ - if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return single_open(file, psi_show, NULL); -} - -static int psi_io_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_io_show); -} - -static int psi_memory_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_memory_show); -} - -static int psi_cpu_open(struct inode *inode, struct file *file) -{ - return psi_open(file, psi_cpu_show); -} - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res) { @@ -1162,7 +1124,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1152,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1200,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1219,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,27 +1228,57 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } +#ifdef CONFIG_PROC_FS +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_open(struct file *file, int (*psi_show)(struct seq_file *, void *)) +{ + if (file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) + return -EPERM; + + return single_open(file, psi_show, NULL); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_io_show); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_memory_show); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return psi_open(file, psi_cpu_show); +} + static ssize_t psi_write(struct file *file, const char __user *user_buf, size_t nbytes, enum psi_res res) { @@ -1316,14 +1299,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1351,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } @@ -1400,3 +1393,5 @@ static int __init psi_proc_init(void) return 0; } module_init(psi_proc_init); + +#endif /* CONFIG_PROC_FS */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 4d8f44a17727..db10e73d06e0 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -29,6 +29,9 @@ #include <linux/syscalls.h> #include <linux/sysctl.h> +/* Not exposed in headers: strictly internal use only. */ +#define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) + #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> #endif @@ -1010,6 +1013,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -1261,6 +1265,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_KILL_PROCESS: default: + current->seccomp.mode = SECCOMP_MODE_DEAD; seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ if (action != SECCOMP_RET_KILL_THREAD || @@ -1309,6 +1314,11 @@ int __secure_computing(const struct seccomp_data *sd) return 0; case SECCOMP_MODE_FILTER: return __seccomp_filter(this_syscall, sd, false); + /* Surviving SECCOMP_RET_KILL_* must be proactively impossible. */ + case SECCOMP_MODE_DEAD: + WARN_ON_ONCE(1); + do_exit(SIGKILL); + return -1; default: BUG(); } diff --git a/kernel/signal.c b/kernel/signal.c index 38602738866e..e93de6daa188 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1308,6 +1308,43 @@ enum sig_handler { }; /* + * On some archictectures, PREEMPT_RT has to delay sending a signal from a + * trap since it cannot enable preemption, and the signal code's + * spin_locks turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME + * which will send the signal on exit of the trap. + */ +#ifdef CONFIG_RT_DELAYED_SIGNALS +static inline bool force_sig_delayed(struct kernel_siginfo *info, + struct task_struct *t) +{ + if (!in_atomic()) + return false; + + if (WARN_ON_ONCE(t->forced_info.si_signo)) + return true; + + if (is_si_special(info)) { + WARN_ON_ONCE(info != SEND_SIG_PRIV); + t->forced_info.si_signo = info->si_signo; + t->forced_info.si_errno = 0; + t->forced_info.si_code = SI_KERNEL; + t->forced_info.si_pid = 0; + t->forced_info.si_uid = 0; + } else { + t->forced_info = *info; + } + set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); + return true; +} +#else +static inline bool force_sig_delayed(struct kernel_siginfo *info, + struct task_struct *t) +{ + return false; +} +#endif + +/* * Force a signal that the process can't ignore: if necessary * we unblock the signal and change any SIG_IGN to SIG_DFL. * @@ -1327,6 +1364,9 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, struct k_sigaction *action; int sig = info->si_signo; + if (force_sig_delayed(info, t)) + return 0; + spin_lock_irqsave(&t->sighand->siglock, flags); action = &t->sighand->action[sig-1]; ignored = action->sa.sa_handler == SIG_IGN; @@ -1342,9 +1382,10 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, } /* * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect - * debugging to leave init killable. + * debugging to leave init killable. But HANDLER_EXIT is always fatal. */ - if (action->sa.sa_handler == SIG_DFL && !t->ptrace) + if (action->sa.sa_handler == SIG_DFL && + (!t->ptrace || (handler == HANDLER_EXIT))) t->signal->flags &= ~SIGNAL_UNKILLABLE; ret = send_signal(sig, info, t, PIDTYPE_PID); spin_unlock_irqrestore(&t->sighand->siglock, flags); diff --git a/kernel/softirq.c b/kernel/softirq.c index 41f470929e99..fac801815554 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -222,7 +222,7 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) u32 pending; int curcnt; - WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(in_hardirq()); lockdep_assert_irqs_enabled(); local_irq_save(flags); @@ -305,7 +305,7 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) { unsigned long flags; - WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(in_hardirq()); raw_local_irq_save(flags); /* @@ -352,14 +352,14 @@ static void __local_bh_enable(unsigned int cnt) */ void _local_bh_enable(void) { - WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(in_hardirq()); __local_bh_enable(SOFTIRQ_DISABLE_OFFSET); } EXPORT_SYMBOL(_local_bh_enable); void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) { - WARN_ON_ONCE(in_irq()); + WARN_ON_ONCE(in_hardirq()); lockdep_assert_irqs_enabled(); #ifdef CONFIG_TRACE_IRQFLAGS local_irq_disable(); @@ -618,7 +618,7 @@ static inline void tick_irq_exit(void) /* Make sure that timer wheel updates are propagated */ if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) { - if (!in_irq()) + if (!in_hardirq()) tick_nohz_irq_exit(); } #endif diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 66b8af394e58..ddb5a7f48d69 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -70,7 +70,7 @@ late_initcall(stackleak_sysctls_init); #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void notrace stackleak_erase(void) +asmlinkage void noinstr stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -124,9 +124,8 @@ asmlinkage void notrace stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } -NOKPROBE_SYMBOL(stackleak_erase); -void __used __no_caller_saved_registers notrace stackleak_track_stack(void) +void __used __no_caller_saved_registers noinstr stackleak_track_stack(void) { unsigned long sp = current_stack_pointer; diff --git a/kernel/sys.c b/kernel/sys.c index ecc4cf019242..5b0e172c4d47 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> @@ -472,6 +473,16 @@ static int set_user(struct cred *new) if (!new_user) return -EAGAIN; + free_uid(new->user); + new->user = new_user; + return 0; +} + +static void flag_nproc_exceeded(struct cred *new) +{ + if (new->ucounts == current_ucounts()) + return; + /* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming @@ -480,15 +491,10 @@ static int set_user(struct cred *new) * failure to the execve() stage. */ if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) && - new_user != INIT_USER && - !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) + new->user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; - - free_uid(new->user); - new->user = new_user; - return 0; } /* @@ -563,6 +569,7 @@ long __sys_setreuid(uid_t ruid, uid_t euid) if (retval < 0) goto error; + flag_nproc_exceeded(new); return commit_creds(new); error: @@ -625,6 +632,7 @@ long __sys_setuid(uid_t uid) if (retval < 0) goto error; + flag_nproc_exceeded(new); return commit_creds(new); error: @@ -704,6 +712,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) if (retval < 0) goto error; + flag_nproc_exceeded(new); return commit_creds(new); error: @@ -2278,15 +2287,16 @@ static int prctl_set_vma(unsigned long opt, unsigned long addr, { struct mm_struct *mm = current->mm; const char __user *uname; - char *name, *pch; + struct anon_vma_name *anon_name = NULL; int error; switch (opt) { case PR_SET_VMA_ANON_NAME: uname = (const char __user *)arg; if (uname) { - name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + char *name, *pch; + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); @@ -2296,15 +2306,18 @@ static int prctl_set_vma(unsigned long opt, unsigned long addr, return -EINVAL; } } - } else { - /* Reset the name */ - name = NULL; + /* anon_vma has its own copy */ + anon_name = anon_vma_name_alloc(name); + kfree(name); + if (!anon_name) + return -ENOMEM; + } mmap_write_lock(mm); - error = madvise_set_anon_name(mm, addr, size, name); + error = madvise_set_anon_name(mm, addr, size, anon_name); mmap_write_unlock(mm); - kfree(name); + anon_vma_name_put(anon_name); break; default: error = -EINVAL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5ae443b2882e..730ab56d9e92 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -180,6 +180,10 @@ static int bpf_stats_handler(struct ctl_table *table, int write, return ret; } +void __weak unpriv_ebpf_notify(int new_state) +{ +} + static int bpf_unpriv_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -197,6 +201,9 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write, return -EPERM; *(int *)table->data = unpriv_enable; } + + unpriv_ebpf_notify(unpriv_enable); + return ret; } #endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 04bfd62f5e5c..27b7868b5c30 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -181,5 +181,14 @@ config HIGH_RES_TIMERS hardware is not capable then this option only increases the size of the kernel image. +config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US + int "Clocksource watchdog maximum allowable skew (in μs)" + depends on CLOCKSOURCE_WATCHDOG + range 50 1000 + default 100 + help + Specify the maximum amount of allowable watchdog skew in + microseconds before reporting the clocksource to be unstable. + endmenu endif diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 1cf73807b450..95d7ca35bdf2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -107,7 +107,13 @@ static u64 suspend_start; * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as * a lower bound for cs->uncertainty_margin values when registering clocks. */ -#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC) +#ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US +#define MAX_SKEW_USEC CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US +#else +#define MAX_SKEW_USEC 100 +#endif + +#define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC) #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 17a283ce2b20..2d76c91b85de 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -169,6 +169,8 @@ static ktime_t tick_init_jiffy_update(void) return period; } +#define MAX_STALLED_JIFFIES 5 + static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int cpu = smp_processor_id(); @@ -196,6 +198,21 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) if (tick_do_timer_cpu == cpu) tick_do_update_jiffies64(now); + /* + * If jiffies update stalled for too long (timekeeper in stop_machine() + * or VMEXIT'ed for several msecs), force an update. + */ + if (ts->last_tick_jiffies != jiffies) { + ts->stalled_jiffies = 0; + ts->last_tick_jiffies = READ_ONCE(jiffies); + } else { + if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) { + tick_do_update_jiffies64(now); + ts->stalled_jiffies = 0; + ts->last_tick_jiffies = READ_ONCE(jiffies); + } + } + if (ts->inidle) ts->got_idle_tick = 1; } @@ -768,7 +785,7 @@ static inline bool local_timer_softirq_pending(void) static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { - u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; + u64 basemono, next_tick, delta, expires; unsigned long basejiff; unsigned int seq; @@ -791,7 +808,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) * minimal delta which brings us back to this place * immediately. Lather, rinse and repeat... */ - if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || + if (rcu_needs_cpu() || arch_needs_cpu() || irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { @@ -802,10 +819,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) * disabled this also looks at the next expiring * hrtimer. */ - next_tmr = get_next_timer_interrupt(basejiff, basemono); - ts->next_timer = next_tmr; - /* Take the next rcu event into account */ - next_tick = next_rcu < next_tmr ? next_rcu : next_tmr; + next_tick = get_next_timer_interrupt(basejiff, basemono); + ts->next_timer = next_tick; } /* @@ -984,6 +999,45 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) __tick_nohz_full_update_tick(ts, ktime_get()); } +/* + * A pending softirq outside an IRQ (or softirq disabled section) context + * should be waiting for ksoftirqd to handle it. Therefore we shouldn't + * reach here due to the need_resched() early check in can_stop_idle_tick(). + * + * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the + * cpu_down() process, softirqs can still be raised while ksoftirqd is parked, + * triggering the below since wakep_softirqd() is ignored. + * + */ +static bool report_idle_softirq(void) +{ + static int ratelimit; + unsigned int pending = local_softirq_pending(); + + if (likely(!pending)) + return false; + + /* Some softirqs claim to be safe against hotplug and ksoftirqd parking */ + if (!cpu_active(smp_processor_id())) { + pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK; + if (!pending) + return false; + } + + if (ratelimit < 10) + return false; + + /* On RT, softirqs handling may be waiting on some lock */ + if (!local_bh_blocked()) + return false; + + pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n", + pending); + ratelimit++; + + return true; +} + static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { /* @@ -1010,17 +1064,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (need_resched()) return false; - if (unlikely(local_softirq_pending())) { - static int ratelimit; - - if (ratelimit < 10 && !local_bh_blocked() && - (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { - pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n", - (unsigned int) local_softirq_pending()); - ratelimit++; - } + if (unlikely(report_idle_softirq())) return false; - } if (tick_nohz_full_enabled()) { /* diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index d952ae393423..504649513399 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -49,6 +49,8 @@ enum tick_nohz_mode { * @timer_expires_base: Base time clock monotonic for @timer_expires * @next_timer: Expiry time of next expiring timer for debugging purpose only * @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick + * @last_tick_jiffies: Value of jiffies seen on last tick + * @stalled_jiffies: Number of stalled jiffies detected across ticks */ struct tick_sched { struct hrtimer sched_timer; @@ -77,6 +79,8 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; atomic_t tick_dep_mask; + unsigned long last_tick_jiffies; + unsigned int stalled_jiffies; }; extern struct tick_sched *tick_get_tick_sched(int cpu); diff --git a/kernel/torture.c b/kernel/torture.c index ef27a6c82451..789aeb0e1159 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -911,7 +911,7 @@ void torture_kthread_stopping(char *title) { char buf[128]; - snprintf(buf, sizeof(buf), "Stopping %s", title); + snprintf(buf, sizeof(buf), "%s is stopping", title); VERBOSE_TOROUT_STRING(buf); while (!kthread_should_stop()) { torture_shutdown_absorb(title); @@ -931,12 +931,14 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, int ret = 0; VERBOSE_TOROUT_STRING(m); - *tp = kthread_run(fn, arg, "%s", s); + *tp = kthread_create(fn, arg, "%s", s); if (IS_ERR(*tp)) { ret = PTR_ERR(*tp); TOROUT_ERRSTRING(f); *tp = NULL; + return ret; } + wake_up_process(*tp); // Process is sleeping, so ordering provided. torture_shuffle_task_register(*tp); return ret; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 752ed89a293b..a5eb5e7fd624 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -70,10 +70,16 @@ config HAVE_C_RECORDMCOUNT help C version of recordmcount available? +config HAVE_BUILDTIME_MCOUNT_SORT + bool + help + An architecture selects this if it sorts the mcount_loc section + at build time. + config BUILDTIME_MCOUNT_SORT bool default y - depends on BUILDTIME_TABLE_SORT && !S390 + depends on HAVE_BUILDTIME_MCOUNT_SORT && DYNAMIC_FTRACE help Sort the mcount_loc section at build time. diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index af68a67179b4..21dea90eaa93 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -310,10 +310,20 @@ record_it: local_irq_restore(flags); } -static void blk_trace_free(struct blk_trace *bt) +static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) { relay_close(bt->rchan); - debugfs_remove(bt->dir); + + /* + * If 'bt->dir' is not set, then both 'dropped' and 'msg' are created + * under 'q->debugfs_dir', thus lookup and remove them. + */ + if (!bt->dir) { + debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir)); + debugfs_remove(debugfs_lookup("msg", q->debugfs_dir)); + } else { + debugfs_remove(bt->dir); + } free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); @@ -335,10 +345,10 @@ static void put_probe_ref(void) mutex_unlock(&blk_probe_mutex); } -static void blk_trace_cleanup(struct blk_trace *bt) +static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt) { synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); put_probe_ref(); } @@ -352,7 +362,7 @@ static int __blk_trace_remove(struct request_queue *q) return -EINVAL; if (bt->trace_state != Blktrace_running) - blk_trace_cleanup(bt); + blk_trace_cleanup(q, bt); return 0; } @@ -572,7 +582,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: if (ret) - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } @@ -1616,7 +1626,7 @@ static int blk_trace_remove_queue(struct request_queue *q) put_probe_ref(); synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); return 0; } @@ -1647,7 +1657,7 @@ static int blk_trace_setup_queue(struct request_queue *q, return 0; free_bt: - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f9feb197b2da..6105b7036482 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7191,7 +7191,6 @@ static int __init ftrace_nodyn_init(void) core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } -static inline void ftrace_startup_enable(int command) { } static inline void ftrace_startup_all(int command) { } # define ftrace_startup_sysctl() do { } while (0) @@ -7791,7 +7790,7 @@ int ftrace_is_dead(void) /** * register_ftrace_function - register a function for profiling - * @ops - ops structure that holds the function for profiling. + * @ops: ops structure that holds the function for profiling. * * Register a function to be called by all functions in the * kernel. @@ -7818,7 +7817,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. - * @ops - ops structure that holds the function to unregister + * @ops: ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a569a0cb81ee..eb44418574f9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -235,7 +235,7 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); - return 0; + return 1; } __setup("trace_options=", set_trace_boot_options); @@ -246,12 +246,16 @@ static int __init set_trace_boot_clock(char *str) { strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); trace_boot_clock = trace_boot_clock_buf; - return 0; + return 1; } __setup("trace_clock=", set_trace_boot_clock); static int __init set_tracepoint_printk(char *str) { + /* Ignore the "tp_printk_stop_on_boot" param */ + if (*str == '_') + return 0; + if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) tracepoint_printk = 1; return 1; @@ -1470,10 +1474,12 @@ static int __init set_buf_size(char *str) if (!str) return 0; buf_size = memparse(str, &str); - /* nr_entries can not be zero */ - if (buf_size == 0) - return 0; - trace_buf_size = buf_size; + /* + * nr_entries can not be zero and the startup + * tests require some buffer space. Therefore + * ensure we have at least 4096 bytes of buffer. + */ + trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); @@ -7740,7 +7746,8 @@ static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr) err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) err = ERR_PTR(-ENOMEM); - tr->n_err_log_entries++; + else + tr->n_err_log_entries++; return err; } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d038ddbf1bea..c5b09c31e077 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -136,7 +136,6 @@ struct kprobe_trace_entry_head { struct eprobe_trace_entry_head { struct trace_entry ent; - unsigned int type; }; struct kretprobe_trace_entry_head { diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 191db32dec46..541aa13581b9 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -242,7 +242,6 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i) static int eprobe_event_define_fields(struct trace_event_call *event_call) { - int ret; struct eprobe_trace_entry_head field; struct trace_probe *tp; @@ -250,8 +249,6 @@ static int eprobe_event_define_fields(struct trace_event_call *event_call) if (WARN_ON_ONCE(!tp)) return -ENOENT; - DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0); - return traceprobe_define_arg_fields(event_call, sizeof(field), tp); } @@ -270,7 +267,9 @@ print_eprobe_event(struct trace_iterator *iter, int flags, struct trace_event_call *pevent; struct trace_event *probed_event; struct trace_seq *s = &iter->seq; + struct trace_eprobe *ep; struct trace_probe *tp; + unsigned int type; field = (struct eprobe_trace_entry_head *)iter->ent; tp = trace_probe_primary_from_call( @@ -278,15 +277,18 @@ print_eprobe_event(struct trace_iterator *iter, int flags, if (WARN_ON_ONCE(!tp)) goto out; + ep = container_of(tp, struct trace_eprobe, tp); + type = ep->event->event.type; + trace_seq_printf(s, "%s: (", trace_probe_name(tp)); - probed_event = ftrace_find_event(field->type); + probed_event = ftrace_find_event(type); if (probed_event) { pevent = container_of(probed_event, struct trace_event_call, event); trace_seq_printf(s, "%s.%s", pevent->class->system, trace_event_name(pevent)); } else { - trace_seq_printf(s, "%u", field->type); + trace_seq_printf(s, "%u", type); } trace_seq_putc(s, ')'); @@ -498,10 +500,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) return; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); - if (edata->ep->event) - entry->type = edata->ep->event->event.type; - else - entry->type = 0; store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 5e6a988a8a51..dc7f733b4cb3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2289,9 +2289,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, /* * For backward compatibility, if field_name * was "cpu", then we treat this the same as - * common_cpu. + * common_cpu. This also works for "CPU". */ - if (strcmp(field_name, "cpu") == 0) { + if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, @@ -2503,6 +2503,8 @@ static struct hist_field *parse_unary(struct hist_trigger_data *hist_data, (HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS); expr->fn = hist_field_unary_minus; expr->operands[0] = operand1; + expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = FIELD_OP_UNARY_MINUS; expr->name = expr_str(expr, 0); expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -2719,6 +2721,7 @@ static struct hist_field *parse_expr(struct hist_trigger_data *hist_data, /* The operand sizes should be the same, so just pick one */ expr->size = operand1->size; + expr->is_signed = operand1->is_signed; expr->operator = field_op; expr->type = kstrdup_const(operand1->type, GFP_KERNEL); @@ -3935,6 +3938,7 @@ static int trace_action_create(struct hist_trigger_data *hist_data, var_ref_idx = find_var_ref_idx(hist_data, var_ref); if (WARN_ON(var_ref_idx < 0)) { + kfree(p); ret = var_ref_idx; goto err; } @@ -4828,7 +4832,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data) if (hist_field->flags & HIST_FIELD_FL_STACKTRACE) cmp_fn = tracing_map_cmp_none; - else if (!field) + else if (!field || hist_field->flags & HIST_FIELD_FL_CPU) cmp_fn = tracing_map_cmp_num(hist_field->size, hist_field->is_signed); else if (is_string_field(field)) @@ -6163,7 +6167,9 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, lockdep_assert_held(&event_mutex); - if (glob && strlen(glob)) { + WARN_ON(!glob); + + if (strlen(glob)) { hist_err_clear(); last_cmd_set(file, param); } @@ -6196,7 +6202,7 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops, continue; } break; - } while (p); + } while (1); if (!p) param = NULL; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index d00fee705f9c..7eb9d04f1c2e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -84,6 +84,20 @@ event_triggers_call(struct trace_event_file *file, } EXPORT_SYMBOL_GPL(event_triggers_call); +bool __trace_trigger_soft_disabled(struct trace_event_file *file) +{ + unsigned long eflags = file->flags; + + if (eflags & EVENT_FILE_FL_TRIGGER_MODE) + event_triggers_call(file, NULL, NULL, NULL); + if (eflags & EVENT_FILE_FL_SOFT_DISABLED) + return true; + if (eflags & EVENT_FILE_FL_PID_FILTER) + return trace_event_ignore_this_pid(file); + return false; +} +EXPORT_SYMBOL_GPL(__trace_trigger_soft_disabled); + /** * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event @@ -1295,6 +1309,16 @@ traceon_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_on(file->tr); + return; + } + if (tracing_is_on()) return; @@ -1306,8 +1330,15 @@ traceon_count_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + } else { + if (tracing_is_on()) + return; + } if (!data->count) return; @@ -1315,7 +1346,10 @@ traceon_count_trigger(struct event_trigger_data *data, if (data->count != -1) (data->count)--; - tracing_on(); + if (file) + tracer_tracing_on(file->tr); + else + tracing_on(); } static void @@ -1323,6 +1357,16 @@ traceoff_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_off(file->tr); + return; + } + if (!tracing_is_on()) return; @@ -1334,8 +1378,15 @@ traceoff_count_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (!tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + } else { + if (!tracing_is_on()) + return; + } if (!data->count) return; @@ -1343,7 +1394,10 @@ traceoff_count_trigger(struct event_trigger_data *data, if (data->count != -1) (data->count)--; - tracing_off(); + if (file) + tracer_tracing_off(file->tr); + else + tracing_off(); } static int @@ -1540,7 +1594,12 @@ stacktrace_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - trace_dump_stack(STACK_SKIP); + struct trace_event_file *file = data->private_data; + + if (file) + __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP); + else + trace_dump_stack(STACK_SKIP); } static void diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 508f14af4f2c..b62fd785b599 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -32,7 +32,7 @@ static int __init set_kprobe_boot_events(char *str) strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); disable_tracing_selftest("running kprobe events"); - return 0; + return 1; } __setup("kprobe_event=", set_kprobe_boot_events); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 870a08da5b48..5e3c62a08fc0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1387,6 +1387,26 @@ static int run_osnoise(void) } /* + * In some cases, notably when running on a nohz_full CPU with + * a stopped tick PREEMPT_RCU has no way to account for QSs. + * This will eventually cause unwarranted noise as PREEMPT_RCU + * will force preemption as the means of ending the current + * grace period. We avoid this problem by calling + * rcu_momentary_dyntick_idle(), which performs a zero duration + * EQS allowing PREEMPT_RCU to end the current grace period. + * This call shouldn't be wrapped inside an RCU critical + * section. + * + * Note that in non PREEMPT_RCU kernels QSs are handled through + * cond_resched() + */ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { + local_irq_disable(); + rcu_momentary_dyntick_idle(); + local_irq_enable(); + } + + /* * For the non-preemptive kernel config: let threads runs, if * they so wish. */ @@ -1437,6 +1457,37 @@ static struct cpumask osnoise_cpumask; static struct cpumask save_cpumask; /* + * osnoise_sleep - sleep until the next period + */ +static void osnoise_sleep(void) +{ + u64 interval; + ktime_t wake_time; + + mutex_lock(&interface_lock); + interval = osnoise_data.sample_period - osnoise_data.sample_runtime; + mutex_unlock(&interface_lock); + + /* + * differently from hwlat_detector, the osnoise tracer can run + * without a pause because preemption is on. + */ + if (!interval) { + /* Let synchronize_rcu_tasks() make progress */ + cond_resched_tasks_rcu_qs(); + return; + } + + wake_time = ktime_add_us(ktime_get(), interval); + __set_current_state(TASK_INTERRUPTIBLE); + + while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) { + if (kthread_should_stop()) + break; + } +} + +/* * osnoise_main - The osnoise detection kernel thread * * Calls run_osnoise() function to measure the osnoise for the configured runtime, @@ -1444,30 +1495,10 @@ static struct cpumask save_cpumask; */ static int osnoise_main(void *data) { - u64 interval; while (!kthread_should_stop()) { - run_osnoise(); - - mutex_lock(&interface_lock); - interval = osnoise_data.sample_period - osnoise_data.sample_runtime; - mutex_unlock(&interface_lock); - - do_div(interval, USEC_PER_MSEC); - - /* - * differently from hwlat_detector, the osnoise tracer can run - * without a pause because preemption is on. - */ - if (interval < 1) { - /* Let synchronize_rcu_tasks() make progress */ - cond_resched_tasks_rcu_qs(); - continue; - } - - if (msleep_interruptible(interval)) - break; + osnoise_sleep(); } return 0; @@ -2189,6 +2220,17 @@ static void osnoise_workload_stop(void) if (osnoise_has_registered_instances()) return; + /* + * If callbacks were already disabled in a previous stop + * call, there is no need to disable then again. + * + * For instance, this happens when tracing is stopped via: + * echo 0 > tracing_on + * echo nop > current_tracer. + */ + if (!trace_osnoise_callback_enabled) + return; + trace_osnoise_callback_enabled = false; /* * Make sure that ftrace_nmi_enter/exit() see diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 73d90179b51b..80863c6508e5 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -871,15 +871,15 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, switch (ptype) { case PROBE_PRINT_NORMAL: fmt = "(%lx)"; - arg = "REC->" FIELD_STRING_IP; + arg = ", REC->" FIELD_STRING_IP; break; case PROBE_PRINT_RETURN: fmt = "(%lx <- %lx)"; - arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; + arg = ", REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; break; case PROBE_PRINT_EVENT: - fmt = "(%u)"; - arg = "REC->" FIELD_STRING_TYPE; + fmt = ""; + arg = ""; break; default: WARN_ON_ONCE(1); @@ -903,7 +903,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, parg->type->fmt); } - pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", arg); for (i = 0; i < tp->nr_args; i++) { parg = tp->args + i; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 99e7a5df025e..92cc149af0fd 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -38,7 +38,6 @@ #define FIELD_STRING_IP "__probe_ip" #define FIELD_STRING_RETIP "__probe_ret_ip" #define FIELD_STRING_FUNC "__probe_func" -#define FIELD_STRING_TYPE "__probe_type" #undef DEFINE_FIELD #define DEFINE_FIELD(type, item, name, is_signed) \ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index afd937a46496..abcadbe933bb 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -784,9 +784,7 @@ static struct fgraph_ops fgraph_ops __initdata = { .retfunc = &trace_graph_return, }; -#if defined(CONFIG_DYNAMIC_FTRACE) && \ - defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) -#define TEST_DIRECT_TRAMP +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS noinline __noclone static void trace_direct_tramp(void) { } #endif @@ -849,7 +847,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, goto out; } -#ifdef TEST_DIRECT_TRAMP +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); diff --git a/kernel/ucount.c b/kernel/ucount.c index 7b32c356ebc5..06ea04d44685 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -190,6 +190,7 @@ struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) kfree(new); } else { hlist_add_head(&new->node, hashent); + get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } @@ -210,6 +211,7 @@ void put_ucounts(struct ucounts *ucounts) if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); + put_user_ns(ucounts->ns); kfree(ucounts); } } @@ -348,7 +350,8 @@ bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsign if (rlimit > LONG_MAX) max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { - if (get_ucounts_value(iter, type) > max) + long val = get_ucounts_value(iter, type); + if (val < 0 || val > max) return true; max = READ_ONCE(iter->ns->ucount_max[type]); } diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 6b2e3ca7ee99..5481ba44a8d6 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -58,6 +58,18 @@ static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) cred->user_ns = user_ns; } +static unsigned long enforced_nproc_rlimit(void) +{ + unsigned long limit = RLIM_INFINITY; + + /* Is RLIMIT_NPROC currently enforced? */ + if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || + (current_user_ns() != &init_user_ns)) + limit = rlimit(RLIMIT_NPROC); + + return limit; +} + /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the @@ -122,7 +134,7 @@ int create_user_ns(struct cred *new) for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) { ns->ucount_max[i] = INT_MAX; } - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)); + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 9c9eb20dd2c5..3990e4df3d7b 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -54,6 +54,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, bit += page->index; set_bit(bit, wqueue->notes_bitmap); + generic_pipe_buf_release(pipe, buf); } // No try_steal function => no stealing @@ -112,7 +113,7 @@ static bool post_one_notification(struct watch_queue *wqueue, buf->offset = offset; buf->len = len; buf->flags = PIPE_BUF_FLAG_WHOLE; - pipe->head = head + 1; + smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { spin_unlock_irq(&pipe->rd_wait.lock); @@ -219,7 +220,6 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) struct page **pages; unsigned long *bitmap; unsigned long user_bufs; - unsigned int bmsize; int ret, i, nr_pages; if (!wqueue) @@ -243,7 +243,8 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; } - ret = pipe_resize_ring(pipe, nr_notes); + nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; @@ -258,21 +259,19 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; } - bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG; - bmsize *= sizeof(unsigned long); - bitmap = kmalloc(bmsize, GFP_KERNEL); + bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); if (!bitmap) goto error_p; - memset(bitmap, 0xff, bmsize); + bitmap_fill(bitmap, nr_notes); wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; - wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + wqueue->nr_notes = nr_notes; return 0; error_p: - for (i = 0; i < nr_pages; i++) + while (--i >= 0) __free_page(pages[i]); kfree(pages); error: @@ -320,7 +319,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ - if (tf[i].type >= sizeof(wfilter->type_filter) * 8) + if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } @@ -336,7 +335,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { - if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) + if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; @@ -371,6 +370,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); if (wfilter) @@ -395,6 +395,7 @@ static void free_watch(struct rcu_head *rcu) put_watch_queue(rcu_access_pointer(watch->queue)); atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); + kfree(watch); } static void __put_watch(struct kref *kref) @@ -566,7 +567,7 @@ void watch_queue_clear(struct watch_queue *wqueue) rcu_read_lock(); spin_lock_bh(&wqueue->lock); - /* Prevent new additions and prevent notifications from happening */ + /* Prevent new notifications from being stored. */ wqueue->defunct = true; while (!hlist_empty(&wqueue->watches)) { |