diff options
Diffstat (limited to 'kernel')
33 files changed, 555 insertions, 280 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 229a5d5df977..3d55d95dcf49 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,7 +11,6 @@ */ #include <linux/bpf.h> #include <linux/err.h> -#include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> @@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE) return ERR_PTR(-ENOMEM); - /* allocate all map elements and zero-initialize them */ - array = kzalloc(array_size, GFP_USER | __GFP_NOWARN); - if (!array) { - array = vzalloc(array_size); - if (!array) - return ERR_PTR(-ENOMEM); - } + array = bpf_map_area_alloc(array_size); + if (!array) + return ERR_PTR(-ENOMEM); /* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) if (array_size >= U32_MAX - PAGE_SIZE || elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { - kvfree(array); + bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } out: @@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map) if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); - kvfree(array); + bpf_map_area_free(array); } static const struct bpf_map_ops array_ops = { @@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map) /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); - kvfree(array); + + bpf_map_area_free(array); } static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index a515f7b007c6..da0f53690295 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) e = rcu_dereference_protected(parent->bpf.effective[type], lockdep_is_held(&cgroup_mutex)); rcu_assign_pointer(cgrp->bpf.effective[type], e); + cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; } } @@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) * * Must be called with cgroup_mutex held. */ -void __cgroup_bpf_update(struct cgroup *cgrp, - struct cgroup *parent, - struct bpf_prog *prog, - enum bpf_attach_type type) +int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, + struct bpf_prog *prog, enum bpf_attach_type type, + bool new_overridable) { - struct bpf_prog *old_prog, *effective; + struct bpf_prog *old_prog, *effective = NULL; struct cgroup_subsys_state *pos; + bool overridable = true; - old_prog = xchg(cgrp->bpf.prog + type, prog); + if (parent) { + overridable = !parent->bpf.disallow_override[type]; + effective = rcu_dereference_protected(parent->bpf.effective[type], + lockdep_is_held(&cgroup_mutex)); + } + + if (prog && effective && !overridable) + /* if parent has non-overridable prog attached, disallow + * attaching new programs to descendent cgroup + */ + return -EPERM; + + if (prog && effective && overridable != new_overridable) + /* if parent has overridable prog attached, only + * allow overridable programs in descendent cgroup + */ + return -EPERM; - effective = (!prog && parent) ? - rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)) : - prog; + old_prog = cgrp->bpf.prog[type]; + + if (prog) { + overridable = new_overridable; + effective = prog; + if (old_prog && + cgrp->bpf.disallow_override[type] == new_overridable) + /* disallow attaching non-overridable on top + * of existing overridable in this cgroup + * and vice versa + */ + return -EPERM; + } + + if (!prog && !old_prog) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + + cgrp->bpf.prog[type] = prog; css_for_each_descendant_pre(pos, &cgrp->self) { struct cgroup *desc = container_of(pos, struct cgroup, self); /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) + if (desc->bpf.prog[type] && desc != cgrp) { pos = css_rightmost_descendant(pos); - else + } else { rcu_assign_pointer(desc->bpf.effective[type], effective); + desc->bpf.disallow_override[type] = !overridable; + } } if (prog) @@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp, bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } + return 0; } /** diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1eb4f1303756..503d4211988a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -146,10 +146,11 @@ void __bpf_prog_free(struct bpf_prog *fp) vfree(fp); } -int bpf_prog_calc_digest(struct bpf_prog *fp) +int bpf_prog_calc_tag(struct bpf_prog *fp) { const u32 bits_offset = SHA_MESSAGE_BYTES - sizeof(__be64); - u32 raw_size = bpf_prog_digest_scratch_size(fp); + u32 raw_size = bpf_prog_tag_scratch_size(fp); + u32 digest[SHA_DIGEST_WORDS]; u32 ws[SHA_WORKSPACE_WORDS]; u32 i, bsize, psize, blocks; struct bpf_insn *dst; @@ -162,7 +163,7 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) if (!raw) return -ENOMEM; - sha_init(fp->digest); + sha_init(digest); memset(ws, 0, sizeof(ws)); /* We need to take out the map fd for the digest calculation @@ -204,13 +205,14 @@ int bpf_prog_calc_digest(struct bpf_prog *fp) *bits = cpu_to_be64((psize - 1) << 3); while (blocks--) { - sha_transform(fp->digest, todo, ws); + sha_transform(digest, todo, ws); todo += SHA_MESSAGE_BYTES; } - result = (__force __be32 *)fp->digest; + result = (__force __be32 *)digest; for (i = 0; i < SHA_DIGEST_WORDS; i++) - result[i] = cpu_to_be32(fp->digest[i]); + result[i] = cpu_to_be32(digest[i]); + memcpy(fp->tag, result, sizeof(fp->tag)); vfree(raw); return 0; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3f2bb58952d8..a753bbe7df0a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -13,7 +13,6 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> -#include <linux/vmalloc.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" @@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab) free_percpu(pptr); } free_elems: - vfree(htab->elems); + bpf_map_area_free(htab->elems); } static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, @@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab) { int err = -ENOMEM, i; - htab->elems = vzalloc(htab->elem_size * htab->map.max_entries); + htab->elems = bpf_map_area_alloc(htab->elem_size * + htab->map.max_entries); if (!htab->elems) return -ENOMEM; @@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) goto free_htab; err = -ENOMEM; - htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket), - GFP_USER | __GFP_NOWARN); - - if (!htab->buckets) { - htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket)); - if (!htab->buckets) - goto free_htab; - } + htab->buckets = bpf_map_area_alloc(htab->n_buckets * + sizeof(struct bucket)); + if (!htab->buckets) + goto free_htab; for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_HEAD(&htab->buckets[i].head); @@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) free_extra_elems: free_percpu(htab->extra_elems); free_buckets: - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); free_htab: kfree(htab); return ERR_PTR(err); @@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map) prealloc_destroy(htab); free_percpu(htab->extra_elems); - kvfree(htab->buckets); + bpf_map_area_free(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 732ae16d12b7..be8519148c25 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,7 +7,6 @@ #include <linux/bpf.h> #include <linux/jhash.h> #include <linux/filter.h> -#include <linux/vmalloc.h> #include <linux/stacktrace.h> #include <linux/perf_event.h> #include "percpu_freelist.h" @@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size; int err; - smap->elems = vzalloc(elem_size * smap->map.max_entries); + smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries); if (!smap->elems) return -ENOMEM; @@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap) return 0; free_elems: - vfree(smap->elems); + bpf_map_area_free(smap->elems); return err; } @@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); - smap = kzalloc(cost, GFP_USER | __GFP_NOWARN); - if (!smap) { - smap = vzalloc(cost); - if (!smap) - return ERR_PTR(-ENOMEM); - } + smap = bpf_map_area_alloc(cost); + if (!smap) + return ERR_PTR(-ENOMEM); err = -E2BIG; cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); @@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) put_buffers: put_callchain_buffers(); free_smap: - kvfree(smap); + bpf_map_area_free(smap); return ERR_PTR(err); } @@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map) /* wait for bpf programs to complete before freeing stack map */ synchronize_rcu(); - vfree(smap->elems); + bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); - kvfree(smap); + bpf_map_area_free(smap); put_callchain_buffers(); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e89acea22ecf..bbb016adbaeb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -12,6 +12,8 @@ #include <linux/bpf.h> #include <linux/syscalls.h> #include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/file.h> #include <linux/license.h> @@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl) list_add(&tl->list_node, &bpf_map_types); } +void *bpf_map_area_alloc(size_t size) +{ + /* We definitely need __GFP_NORETRY, so OOM killer doesn't + * trigger under memory pressure as we really just want to + * fail instead. + */ + const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO; + void *area; + + if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { + area = kmalloc(size, GFP_USER | flags); + if (area != NULL) + return area; + } + + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags, + PAGE_KERNEL); +} + +void bpf_map_area_free(void *area) +{ + kvfree(area); +} + int bpf_map_precharge_memlock(u32 pages) { struct user_struct *user = get_current_user(); @@ -688,17 +714,17 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; - char prog_digest[sizeof(prog->digest) * 2 + 1] = { }; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - bin2hex(prog_digest, prog->digest, sizeof(prog->digest)); + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" - "prog_digest:\t%s\n" + "prog_tag:\t%s\n" "memlock:\t%llu\n", prog->type, prog->jited, - prog_digest, + prog_tag, prog->pages * 1ULL << PAGE_SHIFT); } #endif @@ -894,13 +920,14 @@ static int bpf_obj_get(const union bpf_attr *attr) #ifdef CONFIG_CGROUP_BPF -#define BPF_PROG_ATTACH_LAST_FIELD attach_type +#define BPF_PROG_ATTACH_LAST_FIELD attach_flags static int bpf_prog_attach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; struct bpf_prog *prog; struct cgroup *cgrp; - enum bpf_prog_type ptype; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -908,6 +935,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; + if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + return -EINVAL; + switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: @@ -930,10 +960,13 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - cgroup_bpf_update(cgrp, prog, attr->attach_type); + ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, + attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + if (ret) + bpf_prog_put(prog); cgroup_put(cgrp); - return 0; + return ret; } #define BPF_PROG_DETACH_LAST_FIELD attach_type @@ -941,6 +974,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { struct cgroup *cgrp; + int ret; if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -956,7 +990,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) if (IS_ERR(cgrp)) return PTR_ERR(cgrp); - cgroup_bpf_update(cgrp, NULL, attr->attach_type); + ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); cgroup_put(cgrp); break; @@ -964,7 +998,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) return -EINVAL; } - return 0; + return ret; } #endif /* CONFIG_CGROUP_BPF */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 83ed2f8f6f22..cdc43b899f28 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2936,7 +2936,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) int insn_cnt = env->prog->len; int i, j, err; - err = bpf_prog_calc_digest(env->prog); + err = bpf_prog_calc_tag(env->prog); if (err) return err; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2ee9ec3051b2..53bbca7c4859 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -5221,6 +5221,11 @@ err_free_css: return ERR_PTR(err); } +/* + * The returned cgroup is fully initialized including its control mask, but + * it isn't associated with its kernfs_node and doesn't have the control + * mask applied. + */ static struct cgroup *cgroup_create(struct cgroup *parent) { struct cgroup_root *root = parent->root; @@ -5288,11 +5293,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgroup_propagate_control(cgrp); - /* @cgrp doesn't have dir yet so the following will only create csses */ - ret = cgroup_apply_control_enable(cgrp); - if (ret) - goto out_destroy; - return cgrp; out_cancel_ref: @@ -5300,9 +5300,6 @@ out_cancel_ref: out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); -out_destroy: - cgroup_destroy_locked(cgrp); - return ERR_PTR(ret); } static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, @@ -6501,15 +6498,16 @@ static __init int cgroup_namespaces_init(void) subsys_initcall(cgroup_namespaces_init); #ifdef CONFIG_CGROUP_BPF -void cgroup_bpf_update(struct cgroup *cgrp, - struct bpf_prog *prog, - enum bpf_attach_type type) +int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, bool overridable) { struct cgroup *parent = cgroup_parent(cgrp); + int ret; mutex_lock(&cgroup_mutex); - __cgroup_bpf_update(cgrp, parent, prog, type); + ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); mutex_unlock(&cgroup_mutex); + return ret; } #endif /* CONFIG_CGROUP_BPF */ diff --git a/kernel/cpu.c b/kernel/cpu.c index f75c4d031eeb..0a5f630f5c54 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -764,7 +764,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; - bool hasdied = false; if (num_online_cpus() == 1) return -EBUSY; @@ -809,7 +808,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_kick_ap_work(cpu); } - hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE; out: cpu_hotplug_done(); return ret; @@ -1302,10 +1300,24 @@ static int cpuhp_cb_check(enum cpuhp_state state) */ static int cpuhp_reserve_state(enum cpuhp_state state) { - enum cpuhp_state i; + enum cpuhp_state i, end; + struct cpuhp_step *step; - for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) { - if (!cpuhp_ap_states[i].name) + switch (state) { + case CPUHP_AP_ONLINE_DYN: + step = cpuhp_ap_states + CPUHP_AP_ONLINE_DYN; + end = CPUHP_AP_ONLINE_DYN_END; + break; + case CPUHP_BP_PREPARE_DYN: + step = cpuhp_bp_states + CPUHP_BP_PREPARE_DYN; + end = CPUHP_BP_PREPARE_DYN_END; + break; + default: + return -EINVAL; + } + + for (i = state; i <= end; i++, step++) { + if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); @@ -1323,7 +1335,7 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, mutex_lock(&cpuhp_state_mutex); - if (state == CPUHP_AP_ONLINE_DYN) { + if (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN) { ret = cpuhp_reserve_state(state); if (ret < 0) goto out; diff --git a/kernel/events/core.c b/kernel/events/core.c index ab15509fab8c..e235bb991bdd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1469,7 +1469,6 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { - lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); @@ -1624,6 +1623,8 @@ static void perf_group_attach(struct perf_event *event) { struct perf_event *group_leader = event->group_leader, *pos; + lockdep_assert_held(&event->ctx->lock); + /* * We can have double attach due to group movement in perf_event_open. */ @@ -1697,6 +1698,8 @@ static void perf_group_detach(struct perf_event *event) struct perf_event *sibling, *tmp; struct list_head *list = NULL; + lockdep_assert_held(&event->ctx->lock); + /* * We can have double detach due to exit/hot-unplug + close. */ @@ -1895,9 +1898,29 @@ __perf_remove_from_context(struct perf_event *event, */ static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { - lockdep_assert_held(&event->ctx->mutex); + struct perf_event_context *ctx = event->ctx; + + lockdep_assert_held(&ctx->mutex); event_function_call(event, __perf_remove_from_context, (void *)flags); + + /* + * The above event_function_call() can NO-OP when it hits + * TASK_TOMBSTONE. In that case we must already have been detached + * from the context (by perf_event_exit_event()) but the grouping + * might still be in-tact. + */ + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); + if ((flags & DETACH_GROUP) && + (event->attach_state & PERF_ATTACH_GROUP)) { + /* + * Since in that case we cannot possibly be scheduled, simply + * detach now. + */ + raw_spin_lock_irq(&ctx->lock); + perf_group_detach(event); + raw_spin_unlock_irq(&ctx->lock); + } } /* @@ -2249,7 +2272,7 @@ static int __perf_install_in_context(void *info) struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - bool activate = true; + bool reprogram = true; int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); @@ -2257,27 +2280,26 @@ static int __perf_install_in_context(void *info) raw_spin_lock(&ctx->lock); task_ctx = ctx; - /* If we're on the wrong CPU, try again */ - if (task_cpu(ctx->task) != smp_processor_id()) { - ret = -ESRCH; - goto unlock; - } + reprogram = (ctx->task == current); /* - * If we're on the right CPU, see if the task we target is - * current, if not we don't have to activate the ctx, a future - * context switch will do that for us. + * If the task is running, it must be running on this CPU, + * otherwise we cannot reprogram things. + * + * If its not running, we don't care, ctx->lock will + * serialize against it becoming runnable. */ - if (ctx->task != current) - activate = false; - else - WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + if (task_curr(ctx->task) && !reprogram) { + ret = -ESRCH; + goto unlock; + } + WARN_ON_ONCE(reprogram && cpuctx->task_ctx && cpuctx->task_ctx != ctx); } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - if (activate) { + if (reprogram) { ctx_sched_out(ctx, cpuctx, EVENT_TIME); add_event_to_ctx(event, ctx); ctx_resched(cpuctx, task_ctx); @@ -2328,13 +2350,36 @@ perf_install_in_context(struct perf_event_context *ctx, /* * Installing events is tricky because we cannot rely on ctx->is_active * to be set in case this is the nr_events 0 -> 1 transition. + * + * Instead we use task_curr(), which tells us if the task is running. + * However, since we use task_curr() outside of rq::lock, we can race + * against the actual state. This means the result can be wrong. + * + * If we get a false positive, we retry, this is harmless. + * + * If we get a false negative, things are complicated. If we are after + * perf_event_context_sched_in() ctx::lock will serialize us, and the + * value must be correct. If we're before, it doesn't matter since + * perf_event_context_sched_in() will program the counter. + * + * However, this hinges on the remote context switch having observed + * our task->perf_event_ctxp[] store, such that it will in fact take + * ctx::lock in perf_event_context_sched_in(). + * + * We do this by task_function_call(), if the IPI fails to hit the task + * we know any future context switch of task must see the + * perf_event_ctpx[] store. */ -again: + /* - * Cannot use task_function_call() because we need to run on the task's - * CPU regardless of whether its current or not. + * This smp_mb() orders the task->perf_event_ctxp[] store with the + * task_cpu() load, such that if the IPI then does not find the task + * running, a future context switch of that task must observe the + * store. */ - if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + smp_mb(); +again: + if (!task_function_call(task, __perf_install_in_context, event)) return; raw_spin_lock_irq(&ctx->lock); @@ -2348,12 +2393,16 @@ again: raw_spin_unlock_irq(&ctx->lock); return; } - raw_spin_unlock_irq(&ctx->lock); /* - * Since !ctx->is_active doesn't mean anything, we must IPI - * unconditionally. + * If the task is not running, ctx->lock will avoid it becoming so, + * thus we can safely install the event. */ - goto again; + if (task_curr(task)) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + add_event_to_ctx(event, ctx); + raw_spin_unlock_irq(&ctx->lock); } /* @@ -3438,14 +3487,15 @@ struct perf_read_data { int ret; }; -static int find_cpu_to_read(struct perf_event *event, int local_cpu) +static int __perf_event_read_cpu(struct perf_event *event, int event_cpu) { - int event_cpu = event->oncpu; u16 local_pkg, event_pkg; if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) { - event_pkg = topology_physical_package_id(event_cpu); - local_pkg = topology_physical_package_id(local_cpu); + int local_cpu = smp_processor_id(); + + event_pkg = topology_physical_package_id(event_cpu); + local_pkg = topology_physical_package_id(local_cpu); if (event_pkg == local_pkg) return local_cpu; @@ -3575,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event) static int perf_event_read(struct perf_event *event, bool group) { - int ret = 0, cpu_to_read, local_cpu; + int event_cpu, ret = 0; /* * If event is enabled and currently active on a CPU, update the @@ -3588,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group) .ret = 0, }; - local_cpu = get_cpu(); - cpu_to_read = find_cpu_to_read(event, local_cpu); - put_cpu(); + event_cpu = READ_ONCE(event->oncpu); + if ((unsigned)event_cpu >= nr_cpu_ids) + return 0; + + preempt_disable(); + event_cpu = __perf_event_read_cpu(event, event_cpu); /* * Purposely ignore the smp_call_function_single() return * value. * - * If event->oncpu isn't a valid CPU it means the event got + * If event_cpu isn't a valid CPU it means the event got * scheduled out and that will have updated the event count. * * Therefore, either way, we'll have an up-to-date event count * after this. */ - (void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1); + (void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1); + preempt_enable(); ret = data.ret; } else if (event->state == PERF_EVENT_STATE_INACTIVE) { struct perf_event_context *ctx = event->ctx; @@ -6583,6 +6637,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) char *buf = NULL; char *name; + if (vma->vm_flags & VM_READ) + prot |= PROT_READ; + if (vma->vm_flags & VM_WRITE) + prot |= PROT_WRITE; + if (vma->vm_flags & VM_EXEC) + prot |= PROT_EXEC; + + if (vma->vm_flags & VM_MAYSHARE) + flags = MAP_SHARED; + else + flags = MAP_PRIVATE; + + if (vma->vm_flags & VM_DENYWRITE) + flags |= MAP_DENYWRITE; + if (vma->vm_flags & VM_MAYEXEC) + flags |= MAP_EXECUTABLE; + if (vma->vm_flags & VM_LOCKED) + flags |= MAP_LOCKED; + if (vma->vm_flags & VM_HUGETLB) + flags |= MAP_HUGETLB; + if (file) { struct inode *inode; dev_t dev; @@ -6609,27 +6684,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) maj = MAJOR(dev); min = MINOR(dev); - if (vma->vm_flags & VM_READ) - prot |= PROT_READ; - if (vma->vm_flags & VM_WRITE) - prot |= PROT_WRITE; - if (vma->vm_flags & VM_EXEC) - prot |= PROT_EXEC; - - if (vma->vm_flags & VM_MAYSHARE) - flags = MAP_SHARED; - else - flags = MAP_PRIVATE; - - if (vma->vm_flags & VM_DENYWRITE) - flags |= MAP_DENYWRITE; - if (vma->vm_flags & VM_MAYEXEC) - flags |= MAP_EXECUTABLE; - if (vma->vm_flags & VM_LOCKED) - flags |= MAP_LOCKED; - if (vma->vm_flags & VM_HUGETLB) - flags |= MAP_HUGETLB; - goto got_name; } else { if (vma->vm_ops && vma->vm_ops->name) { @@ -7034,25 +7088,12 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } -/* - * Generic event overflow handling, sampling. - */ - -static int __perf_event_overflow(struct perf_event *event, - int throttle, struct perf_sample_data *data, - struct pt_regs *regs) +static int +__perf_event_account_interrupt(struct perf_event *event, int throttle) { - int events = atomic_read(&event->event_limit); struct hw_perf_event *hwc = &event->hw; - u64 seq; int ret = 0; - - /* - * Non-sampling counters might still use the PMI to fold short - * hardware counters, ignore those. - */ - if (unlikely(!is_sampling_event(event))) - return 0; + u64 seq; seq = __this_cpu_read(perf_throttled_seq); if (seq != hwc->interrupts_seq) { @@ -7080,6 +7121,34 @@ static int __perf_event_overflow(struct perf_event *event, perf_adjust_period(event, delta, hwc->last_period, true); } + return ret; +} + +int perf_event_account_interrupt(struct perf_event *event) +{ + return __perf_event_account_interrupt(event, 1); +} + +/* + * Generic event overflow handling, sampling. + */ + +static int __perf_event_overflow(struct perf_event *event, + int throttle, struct perf_sample_data *data, + struct pt_regs *regs) +{ + int events = atomic_read(&event->event_limit); + int ret = 0; + + /* + * Non-sampling counters might still use the PMI to fold short + * hardware counters, ignore those. + */ + if (unlikely(!is_sampling_event(event))) + return 0; + + ret = __perf_event_account_interrupt(event, throttle); + /* * XXX event_limit might not quite work as expected on inherited * events @@ -9503,6 +9572,37 @@ static int perf_event_set_clock(struct perf_event *event, clockid_t clk_id) return 0; } +/* + * Variation on perf_event_ctx_lock_nested(), except we take two context + * mutexes. + */ +static struct perf_event_context * +__perf_event_ctx_lock_double(struct perf_event *group_leader, + struct perf_event_context *ctx) +{ + struct perf_event_context *gctx; + +again: + rcu_read_lock(); + gctx = READ_ONCE(group_leader->ctx); + if (!atomic_inc_not_zero(&gctx->refcount)) { + rcu_read_unlock(); + goto again; + } + rcu_read_unlock(); + + mutex_lock_double(&gctx->mutex, &ctx->mutex); + + if (group_leader->ctx != gctx) { + mutex_unlock(&ctx->mutex); + mutex_unlock(&gctx->mutex); + put_ctx(gctx); + goto again; + } + + return gctx; +} + /** * sys_perf_event_open - open a performance event, associate it to a task/cpu * @@ -9746,12 +9846,31 @@ SYSCALL_DEFINE5(perf_event_open, } if (move_group) { - gctx = group_leader->ctx; - mutex_lock_double(&gctx->mutex, &ctx->mutex); + gctx = __perf_event_ctx_lock_double(group_leader, ctx); + if (gctx->task == TASK_TOMBSTONE) { err = -ESRCH; goto err_locked; } + + /* + * Check if we raced against another sys_perf_event_open() call + * moving the software group underneath us. + */ + if (!(group_leader->group_caps & PERF_EV_CAP_SOFTWARE)) { + /* + * If someone moved the group out from under us, check + * if this new event wound up on the same ctx, if so + * its the regular !move_group case, otherwise fail. + */ + if (gctx != ctx) { + err = -EINVAL; + goto err_locked; + } else { + perf_event_ctx_unlock(group_leader, gctx); + move_group = 0; + } + } } else { mutex_lock(&ctx->mutex); } @@ -9853,7 +9972,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_unpin_context(ctx); if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); if (task) { @@ -9879,7 +9998,7 @@ SYSCALL_DEFINE5(perf_event_open, err_locked: if (move_group) - mutex_unlock(&gctx->mutex); + perf_event_ctx_unlock(group_leader, gctx); mutex_unlock(&ctx->mutex); /* err_file: */ fput(event_file); diff --git a/kernel/futex.c b/kernel/futex.c index 0842c8ca534b..cdf365036141 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -3323,4 +3323,4 @@ static int __init futex_init(void) return 0; } -__initcall(futex_init); +core_initcall(futex_init); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8c0a0ae43521..b59e6768c5e9 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1346,6 +1346,30 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, } EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); +static void __irq_domain_activate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (irq_data->parent_data) + __irq_domain_activate_irq(irq_data->parent_data); + if (domain->ops->activate) + domain->ops->activate(domain, irq_data); + } +} + +static void __irq_domain_deactivate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); + if (irq_data->parent_data) + __irq_domain_deactivate_irq(irq_data->parent_data); + } +} + /** * irq_domain_activate_irq - Call domain_ops->activate recursively to activate * interrupt @@ -1356,13 +1380,9 @@ EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent); */ void irq_domain_activate_irq(struct irq_data *irq_data) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; - - if (irq_data->parent_data) - irq_domain_activate_irq(irq_data->parent_data); - if (domain->ops->activate) - domain->ops->activate(domain, irq_data); + if (!irqd_is_activated(irq_data)) { + __irq_domain_activate_irq(irq_data); + irqd_set_activated(irq_data); } } @@ -1376,13 +1396,9 @@ void irq_domain_activate_irq(struct irq_data *irq_data) */ void irq_domain_deactivate_irq(struct irq_data *irq_data) { - if (irq_data && irq_data->domain) { - struct irq_domain *domain = irq_data->domain; - - if (domain->ops->deactivate) - domain->ops->deactivate(domain, irq_data); - if (irq_data->parent_data) - irq_domain_deactivate_irq(irq_data->parent_data); + if (irqd_is_activated(irq_data)) { + __irq_domain_deactivate_irq(irq_data); + irqd_clr_activated(irq_data); } } diff --git a/kernel/module.c b/kernel/module.c index 5088784c0cf9..3d8f126208e3 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -389,16 +389,16 @@ extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; extern const struct kernel_symbol __start___ksymtab_gpl_future[]; extern const struct kernel_symbol __stop___ksymtab_gpl_future[]; -extern const unsigned long __start___kcrctab[]; -extern const unsigned long __start___kcrctab_gpl[]; -extern const unsigned long __start___kcrctab_gpl_future[]; +extern const s32 __start___kcrctab[]; +extern const s32 __start___kcrctab_gpl[]; +extern const s32 __start___kcrctab_gpl_future[]; #ifdef CONFIG_UNUSED_SYMBOLS extern const struct kernel_symbol __start___ksymtab_unused[]; extern const struct kernel_symbol __stop___ksymtab_unused[]; extern const struct kernel_symbol __start___ksymtab_unused_gpl[]; extern const struct kernel_symbol __stop___ksymtab_unused_gpl[]; -extern const unsigned long __start___kcrctab_unused[]; -extern const unsigned long __start___kcrctab_unused_gpl[]; +extern const s32 __start___kcrctab_unused[]; +extern const s32 __start___kcrctab_unused_gpl[]; #endif #ifndef CONFIG_MODVERSIONS @@ -497,7 +497,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; - const unsigned long *crc; + const s32 *crc; const struct kernel_symbol *sym; }; @@ -563,7 +563,7 @@ static bool find_symbol_in_section(const struct symsearch *syms, * (optional) module which owns it. Needs preempt disabled or module_mutex. */ const struct kernel_symbol *find_symbol(const char *name, struct module **owner, - const unsigned long **crc, + const s32 **crc, bool gplok, bool warn) { @@ -1145,7 +1145,7 @@ static size_t module_flags_taint(struct module *mod, char *buf) for (i = 0; i < TAINT_FLAGS_COUNT; i++) { if (taint_flags[i].module && test_bit(i, &mod->taints)) - buf[l++] = taint_flags[i].true; + buf[l++] = taint_flags[i].c_true; } return l; @@ -1249,23 +1249,17 @@ static int try_to_force_load(struct module *mod, const char *reason) } #ifdef CONFIG_MODVERSIONS -/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */ -static unsigned long maybe_relocated(unsigned long crc, - const struct module *crc_owner) + +static u32 resolve_rel_crc(const s32 *crc) { -#ifdef ARCH_RELOCATES_KCRCTAB - if (crc_owner == NULL) - return crc - (unsigned long)reloc_start; -#endif - return crc; + return *(u32 *)((void *)crc + *crc); } static int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc, - const struct module *crc_owner) + const s32 *crc) { unsigned int i, num_versions; struct modversion_info *versions; @@ -1283,13 +1277,19 @@ static int check_version(Elf_Shdr *sechdrs, / sizeof(struct modversion_info); for (i = 0; i < num_versions; i++) { + u32 crcval; + if (strcmp(versions[i].name, symname) != 0) continue; - if (versions[i].crc == maybe_relocated(*crc, crc_owner)) + if (IS_ENABLED(CONFIG_MODULE_REL_CRCS)) + crcval = resolve_rel_crc(crc); + else + crcval = *crc; + if (versions[i].crc == crcval) return 1; - pr_debug("Found checksum %lX vs module %lX\n", - maybe_relocated(*crc, crc_owner), versions[i].crc); + pr_debug("Found checksum %X vs module %lX\n", + crcval, versions[i].crc); goto bad_version; } @@ -1307,7 +1307,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, unsigned int versindex, struct module *mod) { - const unsigned long *crc; + const s32 *crc; /* * Since this should be found in kernel (which can't be removed), no @@ -1321,8 +1321,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs, } preempt_enable(); return check_version(sechdrs, versindex, - VMLINUX_SYMBOL_STR(module_layout), mod, crc, - NULL); + VMLINUX_SYMBOL_STR(module_layout), mod, crc); } /* First part is kernel version, which we ignore if module has crcs. */ @@ -1340,8 +1339,7 @@ static inline int check_version(Elf_Shdr *sechdrs, unsigned int versindex, const char *symname, struct module *mod, - const unsigned long *crc, - const struct module *crc_owner) + const s32 *crc) { return 1; } @@ -1368,7 +1366,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, { struct module *owner; const struct kernel_symbol *sym; - const unsigned long *crc; + const s32 *crc; int err; /* @@ -1383,8 +1381,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod, if (!sym) goto unlock; - if (!check_version(info->sechdrs, info->index.vers, name, mod, crc, - owner)) { + if (!check_version(info->sechdrs, info->index.vers, name, mod, crc)) { sym = ERR_PTR(-EINVAL); goto getname; } diff --git a/kernel/panic.c b/kernel/panic.c index c51edaa04fce..08aa88dde7de 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -249,7 +249,7 @@ void panic(const char *fmt, ...) * Delay timeout seconds before rebooting the machine. * We can't use the "normal" timers since we just panicked. */ - pr_emerg("Rebooting in %d seconds..", panic_timeout); + pr_emerg("Rebooting in %d seconds..\n", panic_timeout); for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); @@ -355,7 +355,7 @@ const char *print_tainted(void) for (i = 0; i < TAINT_FLAGS_COUNT; i++) { const struct taint_flag *t = &taint_flags[i]; *s++ = test_bit(i, &tainted_mask) ? - t->true : t->false; + t->c_true : t->c_false; } *s = 0; } else diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index df9e8e9e0be7..eef2ce968636 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -151,8 +151,12 @@ out: static void delayed_free_pidns(struct rcu_head *p) { - kmem_cache_free(pid_ns_cachep, - container_of(p, struct pid_namespace, rcu)); + struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu); + + dec_pid_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + + kmem_cache_free(pid_ns_cachep, ns); } static void destroy_pid_namespace(struct pid_namespace *ns) @@ -162,8 +166,6 @@ static void destroy_pid_namespace(struct pid_namespace *ns) ns_free_inum(&ns->ns); for (i = 0; i < PIDMAP_ENTRIES; i++) kfree(ns->pidmap[i].page); - dec_pid_namespaces(ns->ucounts); - put_user_ns(ns->user_ns); call_rcu(&ns->rcu, delayed_free_pidns); } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f67ceb7768b8..15e6baef5c73 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = { const char *mem_sleep_states[PM_SUSPEND_MAX]; suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE; -suspend_state_t mem_sleep_default = PM_SUSPEND_MAX; +static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM; unsigned int pm_suspend_global_flags; EXPORT_SYMBOL_GPL(pm_suspend_global_flags); @@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops) } if (valid_state(PM_SUSPEND_MEM)) { mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM]; - if (mem_sleep_default >= PM_SUSPEND_MEM) + if (mem_sleep_default == PM_SUSPEND_MEM) mem_sleep_current = PM_SUSPEND_MEM; } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 8b2696420abb..4ba3d34938c0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1516,7 +1516,7 @@ static void call_console_drivers(int level, { struct console *con; - trace_console(text, len); + trace_console_rcuidle(text, len); if (!console_drivers) return; diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 80adef7d4c3d..0d6ff3e471be 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -136,6 +136,7 @@ int rcu_jiffies_till_stall_check(void); #define TPS(x) tracepoint_string(x) void rcu_early_boot_tests(void); +void rcu_test_sync_prims(void); /* * This function really isn't for public consumption, but RCU is special in diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 1898559e6b60..b23a4d076f3d 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -185,9 +185,6 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused * benefits of doing might_sleep() to reduce latency.) * * Cool, huh? (Due to Josh Triplett.) - * - * But we want to make this a static inline later. The cond_resched() - * currently makes this problematic. */ void synchronize_sched(void) { @@ -195,7 +192,6 @@ void synchronize_sched(void) lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_sched() in RCU read-side critical section"); - cond_resched(); } EXPORT_SYMBOL_GPL(synchronize_sched); diff --git a/kernel/rcu/tiny_plugin.h b/kernel/rcu/tiny_plugin.h index 196f0302e2f4..c64b827ecbca 100644 --- a/kernel/rcu/tiny_plugin.h +++ b/kernel/rcu/tiny_plugin.h @@ -60,12 +60,17 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); /* * During boot, we forgive RCU lockdep issues. After this function is - * invoked, we start taking RCU lockdep issues seriously. + * invoked, we start taking RCU lockdep issues seriously. Note that unlike + * Tree RCU, Tiny RCU transitions directly from RCU_SCHEDULER_INACTIVE + * to RCU_SCHEDULER_RUNNING, skipping the RCU_SCHEDULER_INIT stage. + * The reason for this is that Tiny RCU does not need kthreads, so does + * not have to care about the fact that the scheduler is half-initialized + * at a certain phase of the boot process. */ void __init rcu_scheduler_starting(void) { WARN_ON(nr_context_switches() > 0); - rcu_scheduler_active = 1; + rcu_scheduler_active = RCU_SCHEDULER_RUNNING; } #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 96c52e43f7ca..cb4e2056ccf3 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -127,13 +127,16 @@ int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */ int sysctl_panic_on_rcu_stall __read_mostly; /* - * The rcu_scheduler_active variable transitions from zero to one just - * before the first task is spawned. So when this variable is zero, RCU - * can assume that there is but one task, allowing RCU to (for example) + * The rcu_scheduler_active variable is initialized to the value + * RCU_SCHEDULER_INACTIVE and transitions RCU_SCHEDULER_INIT just before the + * first task is spawned. So when this variable is RCU_SCHEDULER_INACTIVE, + * RCU can assume that there is but one task, allowing RCU to (for example) * optimize synchronize_rcu() to a simple barrier(). When this variable - * is one, RCU must actually do all the hard work required to detect real - * grace periods. This variable is also used to suppress boot-time false - * positives from lockdep-RCU error checking. + * is RCU_SCHEDULER_INIT, RCU must actually do all the hard work required + * to detect real grace periods. This variable is also used to suppress + * boot-time false positives from lockdep-RCU error checking. Finally, it + * transitions from RCU_SCHEDULER_INIT to RCU_SCHEDULER_RUNNING after RCU + * is fully initialized, including all of its kthreads having been spawned. */ int rcu_scheduler_active __read_mostly; EXPORT_SYMBOL_GPL(rcu_scheduler_active); @@ -3980,18 +3983,22 @@ static int __init rcu_spawn_gp_kthread(void) early_initcall(rcu_spawn_gp_kthread); /* - * This function is invoked towards the end of the scheduler's initialization - * process. Before this is called, the idle task might contain - * RCU read-side critical sections (during which time, this idle - * task is booting the system). After this function is called, the - * idle tasks are prohibited from containing RCU read-side critical - * sections. This function also enables RCU lockdep checking. + * This function is invoked towards the end of the scheduler's + * initialization process. Before this is called, the idle task might + * contain synchronous grace-period primitives (during which time, this idle + * task is booting the system, and such primitives are no-ops). After this + * function is called, any synchronous grace-period primitives are run as + * expedited, with the requesting task driving the grace period forward. + * A later core_initcall() rcu_exp_runtime_mode() will switch to full + * runtime RCU functionality. */ void rcu_scheduler_starting(void) { WARN_ON(num_online_cpus() != 1); WARN_ON(nr_context_switches() > 0); - rcu_scheduler_active = 1; + rcu_test_sync_prims(); + rcu_scheduler_active = RCU_SCHEDULER_INIT; + rcu_test_sync_prims(); } /* diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d3053e99fdb6..e59e1849b89a 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -532,18 +532,28 @@ struct rcu_exp_work { }; /* + * Common code to drive an expedited grace period forward, used by + * workqueues and mid-boot-time tasks. + */ +static void rcu_exp_sel_wait_wake(struct rcu_state *rsp, + smp_call_func_t func, unsigned long s) +{ + /* Initialize the rcu_node tree in preparation for the wait. */ + sync_rcu_exp_select_cpus(rsp, func); + + /* Wait and clean up, including waking everyone. */ + rcu_exp_wait_wake(rsp, s); +} + +/* * Work-queue handler to drive an expedited grace period forward. */ static void wait_rcu_exp_gp(struct work_struct *wp) { struct rcu_exp_work *rewp; - /* Initialize the rcu_node tree in preparation for the wait. */ rewp = container_of(wp, struct rcu_exp_work, rew_work); - sync_rcu_exp_select_cpus(rewp->rew_rsp, rewp->rew_func); - - /* Wait and clean up, including waking everyone. */ - rcu_exp_wait_wake(rewp->rew_rsp, rewp->rew_s); + rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s); } /* @@ -569,12 +579,18 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp, if (exp_funnel_lock(rsp, s)) return; /* Someone else did our work for us. */ - /* Marshall arguments and schedule the expedited grace period. */ - rew.rew_func = func; - rew.rew_rsp = rsp; - rew.rew_s = s; - INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp); - schedule_work(&rew.rew_work); + /* Ensure that load happens before action based on it. */ + if (unlikely(rcu_scheduler_active == RCU_SCHEDULER_INIT)) { + /* Direct call during scheduler init and early_initcalls(). */ + rcu_exp_sel_wait_wake(rsp, func, s); + } else { + /* Marshall arguments & schedule the expedited grace period. */ + rew.rew_func = func; + rew.rew_rsp = rsp; + rew.rew_s = s; + INIT_WORK_ONSTACK(&rew.rew_work, wait_rcu_exp_gp); + schedule_work(&rew.rew_work); + } /* Wait for expedited grace period to complete. */ rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); @@ -676,6 +692,8 @@ void synchronize_rcu_expedited(void) { struct rcu_state *rsp = rcu_state_p; + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) + return; _synchronize_rcu_expedited(rsp, sync_rcu_exp_handler); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); @@ -693,3 +711,15 @@ void synchronize_rcu_expedited(void) EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + +/* + * Switch to run-time mode once Tree RCU has fully initialized. + */ +static int __init rcu_exp_runtime_mode(void) +{ + rcu_test_sync_prims(); + rcu_scheduler_active = RCU_SCHEDULER_RUNNING; + rcu_test_sync_prims(); + return 0; +} +core_initcall(rcu_exp_runtime_mode); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 85c5a883c6e3..56583e764ebf 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -670,7 +670,7 @@ void synchronize_rcu(void) lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_rcu() in RCU read-side critical section"); - if (!rcu_scheduler_active) + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return; if (rcu_gp_is_expedited()) synchronize_rcu_expedited(); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f19271dce0a9..4f6db7e6a117 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -121,11 +121,14 @@ EXPORT_SYMBOL(rcu_read_lock_sched_held); * Should expedited grace-period primitives always fall back to their * non-expedited counterparts? Intended for use within RCU. Note * that if the user specifies both rcu_expedited and rcu_normal, then - * rcu_normal wins. + * rcu_normal wins. (Except during the time period during boot from + * when the first task is spawned until the rcu_exp_runtime_mode() + * core_initcall() is invoked, at which point everything is expedited.) */ bool rcu_gp_is_normal(void) { - return READ_ONCE(rcu_normal); + return READ_ONCE(rcu_normal) && + rcu_scheduler_active != RCU_SCHEDULER_INIT; } EXPORT_SYMBOL_GPL(rcu_gp_is_normal); @@ -135,13 +138,14 @@ static atomic_t rcu_expedited_nesting = /* * Should normal grace-period primitives be expedited? Intended for * use within RCU. Note that this function takes the rcu_expedited - * sysfs/boot variable into account as well as the rcu_expedite_gp() - * nesting. So looping on rcu_unexpedite_gp() until rcu_gp_is_expedited() - * returns false is a -really- bad idea. + * sysfs/boot variable and rcu_scheduler_active into account as well + * as the rcu_expedite_gp() nesting. So looping on rcu_unexpedite_gp() + * until rcu_gp_is_expedited() returns false is a -really- bad idea. */ bool rcu_gp_is_expedited(void) { - return rcu_expedited || atomic_read(&rcu_expedited_nesting); + return rcu_expedited || atomic_read(&rcu_expedited_nesting) || + rcu_scheduler_active == RCU_SCHEDULER_INIT; } EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); @@ -257,7 +261,7 @@ EXPORT_SYMBOL_GPL(rcu_callback_map); int notrace debug_lockdep_rcu_enabled(void) { - return rcu_scheduler_active && debug_locks && + return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks && current->lockdep_recursion == 0; } EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled); @@ -591,7 +595,7 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks); void synchronize_rcu_tasks(void) { /* Complain if the scheduler has not started. */ - RCU_LOCKDEP_WARN(!rcu_scheduler_active, + RCU_LOCKDEP_WARN(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, "synchronize_rcu_tasks called too soon"); /* Wait for the grace period. */ @@ -813,6 +817,23 @@ static void rcu_spawn_tasks_kthread(void) #endif /* #ifdef CONFIG_TASKS_RCU */ +/* + * Test each non-SRCU synchronous grace-period wait API. This is + * useful just after a change in mode for these primitives, and + * during early boot. + */ +void rcu_test_sync_prims(void) +{ + if (!IS_ENABLED(CONFIG_PROVE_RCU)) + return; + synchronize_rcu(); + synchronize_rcu_bh(); + synchronize_sched(); + synchronize_rcu_expedited(); + synchronize_rcu_bh_expedited(); + synchronize_sched_expedited(); +} + #ifdef CONFIG_PROVE_RCU /* @@ -865,6 +886,7 @@ void rcu_early_boot_tests(void) early_boot_test_call_rcu_bh(); if (rcu_self_test_sched) early_boot_test_call_rcu_sched(); + rcu_test_sync_prims(); } static int rcu_verify_early_boot_tests(void) diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index b6e4c16377c7..9c15a9124e83 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces) if (WARN_ON(!trace->entries)) return; - for (i = 0; i < trace->nr_entries; i++) { - printk("%*c", 1 + spaces, ' '); - print_ip_sym(trace->entries[i]); - } + for (i = 0; i < trace->nr_entries; i++) + printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]); } EXPORT_SYMBOL_GPL(print_stack_trace); @@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size, struct stack_trace *trace, int spaces) { int i; - unsigned long ip; int generated; int total = 0; @@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size, return 0; for (i = 0; i < trace->nr_entries; i++) { - ip = trace->entries[i]; - generated = snprintf(buf, size, "%*c[<%p>] %pS\n", - 1 + spaces, ' ', (void *) ip, (void *) ip); + generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ', + (void *)trace->entries[i]); total += generated; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8dbaec0e4f7f..1aea594a54db 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2475,6 +2475,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int break; if (neg) continue; + val = convmul * val / convdiv; if ((min && val < *min) || (max && val > *max)) continue; *i = val; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 244c93544150..987e496bb51a 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -348,17 +348,16 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) * * Called when the system enters a state where affected tick devices * might stop. Note: TICK_BROADCAST_FORCE cannot be undone. - * - * Called with interrupts disabled, so clockevents_lock is not - * required here because the local clock event device cannot go away - * under us. */ void tick_broadcast_control(enum tick_broadcast_mode mode) { struct clock_event_device *bc, *dev; struct tick_device *td; int cpu, bc_stopped; + unsigned long flags; + /* Protects also the local clockevent device. */ + raw_spin_lock_irqsave(&tick_broadcast_lock, flags); td = this_cpu_ptr(&tick_cpu_device); dev = td->evtdev; @@ -366,12 +365,11 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) * Is the device not affected by the powerstate ? */ if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return; + goto out; if (!tick_device_is_functional(dev)) - return; + goto out; - raw_spin_lock(&tick_broadcast_lock); cpu = smp_processor_id(); bc = tick_broadcast_device.evtdev; bc_stopped = cpumask_empty(tick_broadcast_mask); @@ -421,7 +419,8 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) tick_broadcast_setup_oneshot(bc); } } - raw_spin_unlock(&tick_broadcast_lock); +out: + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } EXPORT_SYMBOL_GPL(tick_broadcast_control); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index ca9fb800336b..38bc4d2208e8 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -75,7 +75,7 @@ void tk_debug_account_sleep_time(struct timespec64 *t) int bin = min(fls(t->tv_sec), NUM_BINS-1); sleep_time_bin[bin]++; - pr_info("Suspended for %lld.%03lu seconds\n", (s64)t->tv_sec, - t->tv_nsec / NSEC_PER_MSEC); + printk_deferred(KERN_INFO "Suspended for %lld.%03lu seconds\n", + (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC); } diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index 775569ec50d0..af344a1bf0d0 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -266,7 +266,7 @@ out: static struct cpumask save_cpumask; static bool disable_migrate; -static void move_to_next_cpu(void) +static void move_to_next_cpu(bool initmask) { static struct cpumask *current_mask; int next_cpu; @@ -275,7 +275,7 @@ static void move_to_next_cpu(void) return; /* Just pick the first CPU on first iteration */ - if (!current_mask) { + if (initmask) { current_mask = &save_cpumask; get_online_cpus(); cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask); @@ -330,10 +330,12 @@ static void move_to_next_cpu(void) static int kthread_fn(void *data) { u64 interval; + bool initmask = true; while (!kthread_should_stop()) { - move_to_next_cpu(); + move_to_next_cpu(initmask); + initmask = false; local_irq_disable(); get_sample(); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index a133ecd741e4..7ad9e53ad174 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1372,7 +1372,7 @@ kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6) return a1 + a2 + a3 + a4 + a5 + a6; } -static struct __init trace_event_file * +static __init struct trace_event_file * find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr) { struct trace_event_file *file; diff --git a/kernel/ucount.c b/kernel/ucount.c index 9d20d5dd298a..95c6336fc2b3 100644 --- a/kernel/ucount.c +++ b/kernel/ucount.c @@ -128,10 +128,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) @@ -141,7 +141,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) new->uid = uid; atomic_set(&new->count, 0); - spin_lock(&ucounts_lock); + spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); @@ -152,16 +152,18 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid) } if (!atomic_add_unless(&ucounts->count, 1, INT_MAX)) ucounts = NULL; - spin_unlock(&ucounts_lock); + spin_unlock_irq(&ucounts_lock); return ucounts; } static void put_ucounts(struct ucounts *ucounts) { + unsigned long flags; + if (atomic_dec_and_test(&ucounts->count)) { - spin_lock(&ucounts_lock); + spin_lock_irqsave(&ucounts_lock, flags); hlist_del_init(&ucounts->node); - spin_unlock(&ucounts_lock); + spin_unlock_irqrestore(&ucounts_lock, flags); kfree(ucounts); } @@ -225,11 +227,10 @@ static __init int user_namespace_sysctl_init(void) * properly. */ user_header = register_sysctl("user", empty); + kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif return 0; } subsys_initcall(user_namespace_sysctl_init); - - diff --git a/kernel/watchdog.c b/kernel/watchdog.c index d4b0fa01cae3..63177be0159e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #define for_each_watchdog_cpu(cpu) \ for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) +atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); + /* * The 'watchdog_running' variable is set to 1 when the watchdog threads * are registered/started and is set to 0 when the watchdog threads are @@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; + if (atomic_read(&watchdog_park_in_progress) != 0) + return HRTIMER_NORESTART; + /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -467,12 +472,16 @@ static int watchdog_park_threads(void) { int cpu, ret = 0; + atomic_set(&watchdog_park_in_progress, 1); + for_each_watchdog_cpu(cpu) { ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); if (ret) break; } + atomic_set(&watchdog_park_in_progress, 0); + return ret; } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 84016c8aee6b..12b8dd640786 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event, /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; + if (atomic_read(&watchdog_park_in_progress) != 0) + return; + if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; |