diff options
Diffstat (limited to 'kernel')
109 files changed, 6603 insertions, 7005 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 0488b8258321..4c2fa3ac56f6 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -3,7 +3,7 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) @@ -13,11 +13,6 @@ ifeq ($(CONFIG_XDP_SOCKETS),y) obj-$(CONFIG_BPF_SYSCALL) += xskmap.o endif obj-$(CONFIG_BPF_SYSCALL) += offload.o -ifeq ($(CONFIG_STREAM_PARSER),y) -ifeq ($(CONFIG_INET),y) -obj-$(CONFIG_BPF_SYSCALL) += sockmap.o -endif -endif endif ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0c17aab3ce5f..24583da9ffd1 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -358,6 +358,29 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + seq_printf(m, "%u: {\n", *(u32 *)key); + pptr = array->pptrs[index & array->index_mask]; + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + static int array_map_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) @@ -398,6 +421,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; @@ -425,7 +449,7 @@ static void fd_array_map_free(struct bpf_map *map) static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key) { - return NULL; + return ERR_PTR(-EOPNOTSUPP); } /* only called from syscall */ @@ -529,6 +553,29 @@ static void bpf_fd_array_map_clear(struct bpf_map *map) fd_array_map_delete_elem(map, &i); } +static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void **elem, *ptr; + u32 prog_id; + + rcu_read_lock(); + + elem = array_map_lookup_elem(map, key); + if (elem) { + ptr = READ_ONCE(*elem); + if (ptr) { + seq_printf(m, "%u: ", *(u32 *)key); + prog_id = prog_fd_array_sys_lookup_elem(ptr); + btf_type_seq_show(map->btf, map->btf_value_type_id, + &prog_id, m); + seq_puts(m, "\n"); + } + } + + rcu_read_unlock(); +} + const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, @@ -540,7 +587,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = bpf_fd_array_map_clear, - .map_check_btf = map_check_no_btf, + .map_seq_show_elem = prog_array_map_seq_show_elem, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 138f0302692e..ee4c82667d65 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2067,50 +2067,44 @@ static int btf_check_sec_info(struct btf_verifier_env *env, return 0; } -static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data, - u32 btf_data_size) +static int btf_parse_hdr(struct btf_verifier_env *env) { + u32 hdr_len, hdr_copy, btf_data_size; const struct btf_header *hdr; - u32 hdr_len, hdr_copy; - /* - * Minimal part of the "struct btf_header" that - * contains the hdr_len. - */ - struct btf_min_header { - u16 magic; - u8 version; - u8 flags; - u32 hdr_len; - } __user *min_hdr; struct btf *btf; int err; btf = env->btf; - min_hdr = btf_data; + btf_data_size = btf->data_size; - if (btf_data_size < sizeof(*min_hdr)) { + if (btf_data_size < + offsetof(struct btf_header, hdr_len) + sizeof(hdr->hdr_len)) { btf_verifier_log(env, "hdr_len not found"); return -EINVAL; } - if (get_user(hdr_len, &min_hdr->hdr_len)) - return -EFAULT; - + hdr = btf->data; + hdr_len = hdr->hdr_len; if (btf_data_size < hdr_len) { btf_verifier_log(env, "btf_header not found"); return -EINVAL; } - err = bpf_check_uarg_tail_zero(btf_data, sizeof(btf->hdr), hdr_len); - if (err) { - if (err == -E2BIG) - btf_verifier_log(env, "Unsupported btf_header"); - return err; + /* Ensure the unsupported header fields are zero */ + if (hdr_len > sizeof(btf->hdr)) { + u8 *expected_zero = btf->data + sizeof(btf->hdr); + u8 *end = btf->data + hdr_len; + + for (; expected_zero < end; expected_zero++) { + if (*expected_zero) { + btf_verifier_log(env, "Unsupported btf_header"); + return -E2BIG; + } + } } hdr_copy = min_t(u32, hdr_len, sizeof(btf->hdr)); - if (copy_from_user(&btf->hdr, btf_data, hdr_copy)) - return -EFAULT; + memcpy(&btf->hdr, btf->data, hdr_copy); hdr = &btf->hdr; @@ -2183,10 +2177,6 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, } env->btf = btf; - err = btf_parse_hdr(env, btf_data, btf_data_size); - if (err) - goto errout; - data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); if (!data) { err = -ENOMEM; @@ -2195,13 +2185,18 @@ static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, btf->data = data; btf->data_size = btf_data_size; - btf->nohdr_data = btf->data + btf->hdr.hdr_len; if (copy_from_user(data, btf_data, btf_data_size)) { err = -EFAULT; goto errout; } + err = btf_parse_hdr(env); + if (err) + goto errout; + + btf->nohdr_data = btf->data + btf->hdr.hdr_len; + err = btf_parse_str_sec(env); if (err) goto errout; diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6a7d931bbc55..9425c2fb872f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -25,6 +25,7 @@ EXPORT_SYMBOL(cgroup_bpf_enabled_key); */ void cgroup_bpf_put(struct cgroup *cgrp) { + enum bpf_cgroup_storage_type stype; unsigned int type; for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { @@ -34,8 +35,10 @@ void cgroup_bpf_put(struct cgroup *cgrp) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); bpf_prog_put(pl->prog); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -97,6 +100,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array __rcu **array) { + enum bpf_cgroup_storage_type stype; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; @@ -125,7 +129,9 @@ static int compute_effective_progs(struct cgroup *cgrp, continue; progs->items[cnt].prog = pl->prog; - progs->items[cnt].cgroup_storage = pl->storage; + for_each_cgroup_storage_type(stype) + progs->items[cnt].cgroup_storage[stype] = + pl->storage[stype]; cnt++; } } while ((p = cgroup_parent(p))); @@ -232,7 +238,9 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, { struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; - struct bpf_cgroup_storage *storage, *old_storage = NULL; + struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE], + *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL}; + enum bpf_cgroup_storage_type stype; struct bpf_prog_list *pl; bool pl_was_allocated; int err; @@ -254,34 +262,44 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; - storage = bpf_cgroup_storage_alloc(prog); - if (IS_ERR(storage)) - return -ENOMEM; + for_each_cgroup_storage_type(stype) { + storage[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storage[stype])) { + storage[stype] = NULL; + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); + return -ENOMEM; + } + } if (flags & BPF_F_ALLOW_MULTI) { list_for_each_entry(pl, progs, node) { if (pl->prog == prog) { /* disallow attaching the same prog twice */ - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -EINVAL; } } pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; list_add_tail(&pl->node, progs); } else { if (list_empty(progs)) { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - bpf_cgroup_storage_free(storage); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } pl_was_allocated = true; @@ -289,12 +307,15 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } else { pl = list_first_entry(progs, typeof(*pl), node); old_prog = pl->prog; - old_storage = pl->storage; - bpf_cgroup_storage_unlink(old_storage); + for_each_cgroup_storage_type(stype) { + old_storage[stype] = pl->storage[stype]; + bpf_cgroup_storage_unlink(old_storage[stype]); + } pl_was_allocated = false; } pl->prog = prog; - pl->storage = storage; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; } cgrp->bpf.flags[type] = flags; @@ -304,21 +325,27 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, goto cleanup; static_branch_inc(&cgroup_bpf_enabled_key); - if (old_storage) - bpf_cgroup_storage_free(old_storage); + for_each_cgroup_storage_type(stype) { + if (!old_storage[stype]) + continue; + bpf_cgroup_storage_free(old_storage[stype]); + } if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } - bpf_cgroup_storage_link(storage, cgrp, type); + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_link(storage[stype], cgrp, type); return 0; cleanup: /* and cleanup the prog list */ pl->prog = old_prog; - bpf_cgroup_storage_free(pl->storage); - pl->storage = old_storage; - bpf_cgroup_storage_link(old_storage, cgrp, type); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_free(pl->storage[stype]); + pl->storage[stype] = old_storage[stype]; + bpf_cgroup_storage_link(old_storage[stype], cgrp, type); + } if (pl_was_allocated) { list_del(&pl->node); kfree(pl); @@ -339,6 +366,7 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 unused_flags) { struct list_head *progs = &cgrp->bpf.progs[type]; + enum bpf_cgroup_storage_type stype; u32 flags = cgrp->bpf.flags[type]; struct bpf_prog *old_prog = NULL; struct bpf_prog_list *pl; @@ -385,8 +413,10 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); - bpf_cgroup_storage_unlink(pl->storage); - bpf_cgroup_storage_free(pl->storage); + for_each_cgroup_storage_type(stype) { + bpf_cgroup_storage_unlink(pl->storage[stype]); + bpf_cgroup_storage_free(pl->storage[stype]); + } kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ @@ -523,6 +553,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, { unsigned int offset = skb->data - skb_network_header(skb); struct sock *save_sk; + void *saved_data_end; struct cgroup *cgrp; int ret; @@ -536,8 +567,13 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, save_sk = skb->sk; skb->sk = sk; __skb_push(skb, offset); + + /* compute pointers for the bpf prog */ + bpf_compute_and_save_data_end(skb, &saved_data_end); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, bpf_prog_run_save_cb); + bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; return ret == 1 ? 0 : -EPERM; @@ -677,6 +713,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_get_current_cgroup_id: + return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_trace_printk: if (capable(CAP_SYS_ADMIN)) return bpf_get_trace_printk_proto(); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3f5bf1af0826..6377225b2082 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -365,10 +365,13 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) } #ifdef CONFIG_BPF_JIT +# define BPF_JIT_LIMIT_DEFAULT (PAGE_SIZE * 40000) + /* All BPF JIT sysctl knobs here. */ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); int bpf_jit_harden __read_mostly; int bpf_jit_kallsyms __read_mostly; +int bpf_jit_limit __read_mostly = BPF_JIT_LIMIT_DEFAULT; static __always_inline void bpf_get_prog_addr_region(const struct bpf_prog *prog, @@ -577,27 +580,64 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; } +static atomic_long_t bpf_jit_current; + +#if defined(MODULES_VADDR) +static int __init bpf_jit_charge_init(void) +{ + /* Only used as heuristic here to derive limit. */ + bpf_jit_limit = min_t(u64, round_up((MODULES_END - MODULES_VADDR) >> 2, + PAGE_SIZE), INT_MAX); + return 0; +} +pure_initcall(bpf_jit_charge_init); +#endif + +static int bpf_jit_charge_modmem(u32 pages) +{ + if (atomic_long_add_return(pages, &bpf_jit_current) > + (bpf_jit_limit >> PAGE_SHIFT)) { + if (!capable(CAP_SYS_ADMIN)) { + atomic_long_sub(pages, &bpf_jit_current); + return -EPERM; + } + } + + return 0; +} + +static void bpf_jit_uncharge_modmem(u32 pages) +{ + atomic_long_sub(pages, &bpf_jit_current); +} + struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_binary_header *hdr; - unsigned int size, hole, start; + u32 size, hole, start, pages; /* Most of BPF filters are really small, but if some of them * fill a page, allow at least 128 extra bytes to insert a * random section of illegal instructions. */ size = round_up(proglen + sizeof(*hdr) + 128, PAGE_SIZE); + pages = size / PAGE_SIZE; + + if (bpf_jit_charge_modmem(pages)) + return NULL; hdr = module_alloc(size); - if (hdr == NULL) + if (!hdr) { + bpf_jit_uncharge_modmem(pages); return NULL; + } /* Fill space with illegal/arch-dep instructions. */ bpf_fill_ill_insns(hdr, size); - hdr->pages = size / PAGE_SIZE; + hdr->pages = pages; hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)), PAGE_SIZE - sizeof(*hdr)); start = (get_random_int() % hole) & ~(alignment - 1); @@ -610,7 +650,10 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, void bpf_jit_binary_free(struct bpf_binary_header *hdr) { + u32 pages = hdr->pages; + module_memfree(hdr); + bpf_jit_uncharge_modmem(pages); } /* This symbol is only overridden by archs that have different @@ -1783,6 +1826,9 @@ BPF_CALL_0(bpf_user_rnd_u32) const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_map_push_elem_proto __weak; +const struct bpf_func_proto bpf_map_pop_elem_proto __weak; +const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; @@ -1792,8 +1838,6 @@ const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; -const struct bpf_func_proto bpf_sock_map_update_proto __weak; -const struct bpf_func_proto bpf_sock_hash_update_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 141710b82a6c..191b79948424 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -512,8 +512,7 @@ static int dev_map_notification(struct notifier_block *notifier, struct bpf_dtab_netdev *dev, *odev; dev = READ_ONCE(dtab->netdev_map[i]); - if (!dev || - dev->dev->ifindex != netdev->ifindex) + if (!dev || netdev != dev->dev) continue; odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); if (dev == odev) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 03cc59ee9c95..2c1790288138 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1285,6 +1285,35 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, return ret; } +static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct htab_elem *l; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + l = __htab_map_lookup_elem(map, key); + if (!l) { + rcu_read_unlock(); + return; + } + + btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); + seq_puts(m, ": {\n"); + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + const struct bpf_map_ops htab_percpu_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1293,6 +1322,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_lookup_elem = htab_percpu_map_lookup_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1303,6 +1333,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_lookup_elem = htab_lru_percpu_map_lookup_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1991466b8327..a74972b07e74 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -76,6 +76,47 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; +BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags) +{ + return map->ops->map_push_elem(map, value, flags); +} + +const struct bpf_func_proto bpf_map_push_elem_proto = { + .func = bpf_map_push_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_pop_elem(map, value); +} + +const struct bpf_func_proto bpf_map_pop_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + +BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_peek_elem(map, value); +} + +const struct bpf_func_proto bpf_map_peek_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + const struct bpf_func_proto bpf_get_prandom_u32_proto = { .func = bpf_user_rnd_u32, .gpl_only = false, @@ -194,16 +235,28 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; -DECLARE_PER_CPU(void*, bpf_cgroup_storage); +#ifdef CONFIG_CGROUP_BPF +DECLARE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { - /* map and flags arguments are not used now, - * but provide an ability to extend the API - * for other types of local storages. - * verifier checks that their values are correct. + /* flags argument is not used now, + * but provides an ability to extend the API. + * verifier checks that its value is correct. */ - return (unsigned long) this_cpu_read(bpf_cgroup_storage); + enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); + struct bpf_cgroup_storage *storage; + void *ptr; + + storage = this_cpu_read(bpf_cgroup_storage[stype]); + + if (stype == BPF_CGROUP_STORAGE_SHARED) + ptr = &READ_ONCE(storage->buf)->data[0]; + else + ptr = this_cpu_ptr(storage->percpu_buf); + + return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { @@ -214,3 +267,4 @@ const struct bpf_func_proto bpf_get_local_storage_proto = { .arg2_type = ARG_ANYTHING, }; #endif +#endif diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 22ad967d1e5f..c97a8f968638 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -7,7 +7,8 @@ #include <linux/rbtree.h> #include <linux/slab.h> -DEFINE_PER_CPU(void*, bpf_cgroup_storage); +DEFINE_PER_CPU(struct bpf_cgroup_storage*, + bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); #ifdef CONFIG_CGROUP_BPF @@ -129,7 +130,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; - if (flags & BPF_NOEXIST) + if (flags != BPF_ANY && flags != BPF_EXIST) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, @@ -151,6 +152,71 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return 0; } +int bpf_percpu_cgroup_storage_copy(struct bpf_map *_map, void *_key, + void *value) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* per_cpu areas are zero-filled and bpf programs can only + * access 'value_size' of them, so copying rounded areas + * will not leak any kernel data + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(value + off, + per_cpu_ptr(storage->percpu_buf, cpu), size); + off += size; + } + rcu_read_unlock(); + return 0; +} + +int bpf_percpu_cgroup_storage_update(struct bpf_map *_map, void *_key, + void *value, u64 map_flags) +{ + struct bpf_cgroup_storage_map *map = map_to_storage(_map); + struct bpf_cgroup_storage_key *key = _key; + struct bpf_cgroup_storage *storage; + int cpu, off = 0; + u32 size; + + if (map_flags != BPF_ANY && map_flags != BPF_EXIST) + return -EINVAL; + + rcu_read_lock(); + storage = cgroup_storage_lookup(map, key, false); + if (!storage) { + rcu_read_unlock(); + return -ENOENT; + } + + /* the user space will provide round_up(value_size, 8) bytes that + * will be copied into per-cpu area. bpf programs can only access + * value_size of it. During lookup the same extra bytes will be + * returned or zeros which were zero-filled by percpu_alloc, + * so no kernel data leaks possible + */ + size = round_up(_map->value_size, 8); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(per_cpu_ptr(storage->percpu_buf, cpu), + value + off, size); + off += size; + } + rcu_read_unlock(); + return 0; +} + static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key, void *_next_key) { @@ -195,6 +261,9 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) if (attr->key_size != sizeof(struct bpf_cgroup_storage_key)) return ERR_PTR(-EINVAL); + if (attr->value_size == 0) + return ERR_PTR(-EINVAL); + if (attr->value_size > PAGE_SIZE) return ERR_PTR(-E2BIG); @@ -251,6 +320,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = { int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); int ret = -EBUSY; @@ -258,11 +328,12 @@ int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map) if (map->prog && map->prog != prog) goto unlock; - if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map) + if (prog->aux->cgroup_storage[stype] && + prog->aux->cgroup_storage[stype] != _map) goto unlock; map->prog = prog; - prog->aux->cgroup_storage = _map; + prog->aux->cgroup_storage[stype] = _map; ret = 0; unlock: spin_unlock_bh(&map->lock); @@ -272,70 +343,117 @@ unlock: void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map) { + enum bpf_cgroup_storage_type stype = cgroup_storage_type(_map); struct bpf_cgroup_storage_map *map = map_to_storage(_map); spin_lock_bh(&map->lock); if (map->prog == prog) { - WARN_ON(prog->aux->cgroup_storage != _map); + WARN_ON(prog->aux->cgroup_storage[stype] != _map); map->prog = NULL; - prog->aux->cgroup_storage = NULL; + prog->aux->cgroup_storage[stype] = NULL; } spin_unlock_bh(&map->lock); } -struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog) +static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) +{ + size_t size; + + if (cgroup_storage_type(map) == BPF_CGROUP_STORAGE_SHARED) { + size = sizeof(struct bpf_storage_buffer) + map->value_size; + *pages = round_up(sizeof(struct bpf_cgroup_storage) + size, + PAGE_SIZE) >> PAGE_SHIFT; + } else { + size = map->value_size; + *pages = round_up(round_up(size, 8) * num_possible_cpus(), + PAGE_SIZE) >> PAGE_SHIFT; + } + + return size; +} + +struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, + enum bpf_cgroup_storage_type stype) { struct bpf_cgroup_storage *storage; struct bpf_map *map; + gfp_t flags; + size_t size; u32 pages; - map = prog->aux->cgroup_storage; + map = prog->aux->cgroup_storage[stype]; if (!map) return NULL; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + size = bpf_cgroup_storage_calculate_size(map, &pages); + if (bpf_map_charge_memlock(map, pages)) return ERR_PTR(-EPERM); storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), __GFP_ZERO | GFP_USER, map->numa_node); - if (!storage) { - bpf_map_uncharge_memlock(map, pages); - return ERR_PTR(-ENOMEM); - } + if (!storage) + goto enomem; - storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, - map->numa_node); - if (!storage->buf) { - bpf_map_uncharge_memlock(map, pages); - kfree(storage); - return ERR_PTR(-ENOMEM); + flags = __GFP_ZERO | GFP_USER; + + if (stype == BPF_CGROUP_STORAGE_SHARED) { + storage->buf = kmalloc_node(size, flags, map->numa_node); + if (!storage->buf) + goto enomem; + } else { + storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + if (!storage->percpu_buf) + goto enomem; } storage->map = (struct bpf_cgroup_storage_map *)map; return storage; + +enomem: + bpf_map_uncharge_memlock(map, pages); + kfree(storage); + return ERR_PTR(-ENOMEM); +} + +static void free_shared_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + kfree(storage->buf); + kfree(storage); +} + +static void free_percpu_cgroup_storage_rcu(struct rcu_head *rcu) +{ + struct bpf_cgroup_storage *storage = + container_of(rcu, struct bpf_cgroup_storage, rcu); + + free_percpu(storage->percpu_buf); + kfree(storage); } void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { - u32 pages; + enum bpf_cgroup_storage_type stype; struct bpf_map *map; + u32 pages; if (!storage) return; map = &storage->map->map; - pages = round_up(sizeof(struct bpf_cgroup_storage) + - sizeof(struct bpf_storage_buffer) + - map->value_size, PAGE_SIZE) >> PAGE_SHIFT; + + bpf_cgroup_storage_calculate_size(map, &pages); bpf_map_uncharge_memlock(map, pages); - kfree_rcu(storage->buf, rcu); - kfree_rcu(storage, rcu); + stype = cgroup_storage_type(map); + if (stype == BPF_CGROUP_STORAGE_SHARED) + call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); + else + call_rcu(&storage->rcu, free_percpu_cgroup_storage_rcu); } void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage, diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 3bfbf4464416..99d243e1ad6e 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -24,7 +24,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) * in the verifier is not enough. */ if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY || - inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) { + inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { fdput(f); return ERR_PTR(-ENOTSUPP); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 177a52436394..8e93c47f0779 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -172,6 +172,24 @@ int bpf_prog_offload_verify_insn(struct bpf_verifier_env *env, return ret; } +int bpf_prog_offload_finalize(struct bpf_verifier_env *env) +{ + struct bpf_prog_offload *offload; + int ret = -ENODEV; + + down_read(&bpf_devs_lock); + offload = env->prog->aux->offload; + if (offload) { + if (offload->dev_ops->finalize) + ret = offload->dev_ops->finalize(env); + else + ret = 0; + } + up_read(&bpf_devs_lock); + + return ret; +} + static void __bpf_prog_offload_destroy(struct bpf_prog *prog) { struct bpf_prog_offload *offload = prog->aux->offload; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c new file mode 100644 index 000000000000..8bbd72d3a121 --- /dev/null +++ b/kernel/bpf/queue_stack_maps.c @@ -0,0 +1,290 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * queue_stack_maps.c: BPF queue and stack maps + * + * Copyright (c) 2018 Politecnico di Torino + */ +#include <linux/bpf.h> +#include <linux/list.h> +#include <linux/slab.h> +#include "percpu_freelist.h" + +#define QUEUE_STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + + +struct bpf_queue_stack { + struct bpf_map map; + raw_spinlock_t lock; + u32 head, tail; + u32 size; /* max_entries + 1 */ + + char elements[0] __aligned(8); +}; + +static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map) +{ + return container_of(map, struct bpf_queue_stack, map); +} + +static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs) +{ + return qs->head == qs->tail; +} + +static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) +{ + u32 head = qs->head + 1; + + if (unlikely(head >= qs->size)) + head = 0; + + return head == qs->tail; +} + +/* Called from syscall */ +static int queue_stack_map_alloc_check(union bpf_attr *attr) +{ + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 0 || + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + return -EINVAL; + + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + +static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) +{ + int ret, numa_node = bpf_map_attr_numa_node(attr); + struct bpf_queue_stack *qs; + u32 size, value_size; + u64 queue_size, cost; + + size = attr->max_entries + 1; + value_size = attr->value_size; + + queue_size = sizeof(*qs) + (u64) value_size * size; + + cost = queue_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); + + qs = bpf_map_area_alloc(queue_size, numa_node); + if (!qs) + return ERR_PTR(-ENOMEM); + + memset(qs, 0, sizeof(*qs)); + + bpf_map_init_from_attr(&qs->map, attr); + + qs->map.pages = cost; + qs->size = size; + + raw_spin_lock_init(&qs->lock); + + return &qs->map; +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void queue_stack_map_free(struct bpf_map *map) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + bpf_map_area_free(qs); +} + +static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); + err = -ENOENT; + goto out; + } + + ptr = &qs->elements[qs->tail * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) { + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + + +static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + u32 index; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); + err = -ENOENT; + goto out; + } + + index = qs->head - 1; + if (unlikely(index >= qs->size)) + index = qs->size - 1; + + ptr = &qs->elements[index * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) + qs->head = index; + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static int queue_map_peek_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_peek_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int queue_map_pop_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_pop_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long irq_flags; + int err = 0; + void *dst; + + /* BPF_EXIST is used to force making room for a new element in case the + * map is full + */ + bool replace = (flags & BPF_EXIST); + + /* Check supported flags for queue and stack maps */ + if (flags & BPF_NOEXIST || flags > BPF_EXIST) + return -EINVAL; + + raw_spin_lock_irqsave(&qs->lock, irq_flags); + + if (queue_stack_map_is_full(qs)) { + if (!replace) { + err = -E2BIG; + goto out; + } + /* advance tail pointer to overwrite oldest element */ + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + + dst = &qs->elements[qs->head * qs->map.value_size]; + memcpy(dst, value, qs->map.value_size); + + if (unlikely(++qs->head >= qs->size)) + qs->head = 0; + +out: + raw_spin_unlock_irqrestore(&qs->lock, irq_flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +/* Called from syscall */ +static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -EINVAL; +} + +const struct bpf_map_ops queue_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = queue_map_pop_elem, + .map_peek_elem = queue_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; + +const struct bpf_map_ops stack_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = stack_map_pop_elem, + .map_peek_elem = stack_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c deleted file mode 100644 index 488ef9663c01..000000000000 --- a/kernel/bpf/sockmap.c +++ /dev/null @@ -1,2580 +0,0 @@ -/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ - -/* A BPF sock_map is used to store sock objects. This is primarly used - * for doing socket redirect with BPF helper routines. - * - * A sock map may have BPF programs attached to it, currently a program - * used to parse packets and a program to provide a verdict and redirect - * decision on the packet are supported. Any programs attached to a sock - * map are inherited by sock objects when they are added to the map. If - * no BPF programs are attached the sock object may only be used for sock - * redirect. - * - * A sock object may be in multiple maps, but can only inherit a single - * parse or verdict program. If adding a sock object to a map would result - * in having multiple parsing programs the update will return an EBUSY error. - * - * For reference this program is similar to devmap used in XDP context - * reviewing these together may be useful. For an example please review - * ./samples/bpf/sockmap/. - */ -#include <linux/bpf.h> -#include <net/sock.h> -#include <linux/filter.h> -#include <linux/errno.h> -#include <linux/file.h> -#include <linux/kernel.h> -#include <linux/net.h> -#include <linux/skbuff.h> -#include <linux/workqueue.h> -#include <linux/list.h> -#include <linux/mm.h> -#include <net/strparser.h> -#include <net/tcp.h> -#include <linux/ptr_ring.h> -#include <net/inet_common.h> -#include <linux/sched/signal.h> - -#define SOCK_CREATE_FLAG_MASK \ - (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) - -struct bpf_sock_progs { - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; -}; - -struct bpf_stab { - struct bpf_map map; - struct sock **sock_map; - struct bpf_sock_progs progs; - raw_spinlock_t lock; -}; - -struct bucket { - struct hlist_head head; - raw_spinlock_t lock; -}; - -struct bpf_htab { - struct bpf_map map; - struct bucket *buckets; - atomic_t count; - u32 n_buckets; - u32 elem_size; - struct bpf_sock_progs progs; - struct rcu_head rcu; -}; - -struct htab_elem { - struct rcu_head rcu; - struct hlist_node hash_node; - u32 hash; - struct sock *sk; - char key[0]; -}; - -enum smap_psock_state { - SMAP_TX_RUNNING, -}; - -struct smap_psock_map_entry { - struct list_head list; - struct bpf_map *map; - struct sock **entry; - struct htab_elem __rcu *hash_link; -}; - -struct smap_psock { - struct rcu_head rcu; - refcount_t refcnt; - - /* datapath variables */ - struct sk_buff_head rxqueue; - bool strp_enabled; - - /* datapath error path cache across tx work invocations */ - int save_rem; - int save_off; - struct sk_buff *save_skb; - - /* datapath variables for tx_msg ULP */ - struct sock *sk_redir; - int apply_bytes; - int cork_bytes; - int sg_size; - int eval; - struct sk_msg_buff *cork; - struct list_head ingress; - - struct strparser strp; - struct bpf_prog *bpf_tx_msg; - struct bpf_prog *bpf_parse; - struct bpf_prog *bpf_verdict; - struct list_head maps; - spinlock_t maps_lock; - - /* Back reference used when sock callback trigger sockmap operations */ - struct sock *sock; - unsigned long state; - - struct work_struct tx_work; - struct work_struct gc_work; - - struct proto *sk_proto; - void (*save_close)(struct sock *sk, long timeout); - void (*save_data_ready)(struct sock *sk); - void (*save_write_space)(struct sock *sk); -}; - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len); -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -static void bpf_tcp_close(struct sock *sk, long timeout); - -static inline struct smap_psock *smap_psock_sk(const struct sock *sk) -{ - return rcu_dereference_sk_user_data(sk); -} - -static bool bpf_tcp_stream_read(const struct sock *sk) -{ - struct smap_psock *psock; - bool empty = true; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - empty = list_empty(&psock->ingress); -out: - rcu_read_unlock(); - return !empty; -} - -enum { - SOCKMAP_IPV4, - SOCKMAP_IPV6, - SOCKMAP_NUM_PROTS, -}; - -enum { - SOCKMAP_BASE, - SOCKMAP_TX, - SOCKMAP_NUM_CONFIGS, -}; - -static struct proto *saved_tcpv6_prot __read_mostly; -static DEFINE_SPINLOCK(tcpv6_prot_lock); -static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS]; -static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], - struct proto *base) -{ - prot[SOCKMAP_BASE] = *base; - prot[SOCKMAP_BASE].close = bpf_tcp_close; - prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; - prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; - - prot[SOCKMAP_TX] = prot[SOCKMAP_BASE]; - prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg; - prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage; -} - -static void update_sk_prot(struct sock *sk, struct smap_psock *psock) -{ - int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4; - int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE; - - sk->sk_prot = &bpf_tcp_prots[family][conf]; -} - -static int bpf_tcp_init(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return -EINVAL; - } - - if (unlikely(psock->sk_proto)) { - rcu_read_unlock(); - return -EBUSY; - } - - psock->save_close = sk->sk_prot->close; - psock->sk_proto = sk->sk_prot; - - /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */ - if (sk->sk_family == AF_INET6 && - unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { - spin_lock_bh(&tcpv6_prot_lock); - if (likely(sk->sk_prot != saved_tcpv6_prot)) { - build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot); - smp_store_release(&saved_tcpv6_prot, sk->sk_prot); - } - spin_unlock_bh(&tcpv6_prot_lock); - } - update_sk_prot(sk, psock); - rcu_read_unlock(); - return 0; -} - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); - -static void bpf_tcp_release(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - if (psock->sk_proto) { - sk->sk_prot = psock->sk_proto; - psock->sk_proto = NULL; - } -out: - rcu_read_unlock(); -} - -static struct htab_elem *lookup_elem_raw(struct hlist_head *head, - u32 hash, void *key, u32 key_size) -{ - struct htab_elem *l; - - hlist_for_each_entry_rcu(l, head, hash_node) { - if (l->hash == hash && !memcmp(&l->key, key, key_size)) - return l; - } - - return NULL; -} - -static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &htab->buckets[hash & (htab->n_buckets - 1)]; -} - -static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash) -{ - return &__select_bucket(htab, hash)->head; -} - -static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) -{ - atomic_dec(&htab->count); - kfree_rcu(l, rcu); -} - -static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, - struct smap_psock *psock) -{ - struct smap_psock_map_entry *e; - - spin_lock_bh(&psock->maps_lock); - e = list_first_entry_or_null(&psock->maps, - struct smap_psock_map_entry, - list); - if (e) - list_del(&e->list); - spin_unlock_bh(&psock->maps_lock); - return e; -} - -static void bpf_tcp_close(struct sock *sk, long timeout) -{ - void (*close_fun)(struct sock *sk, long timeout); - struct smap_psock_map_entry *e; - struct sk_msg_buff *md, *mtmp; - struct smap_psock *psock; - struct sock *osk; - - lock_sock(sk); - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - - /* The psock may be destroyed anytime after exiting the RCU critial - * section so by the time we use close_fun the psock may no longer - * be valid. However, bpf_tcp_close is called with the sock lock - * held so the close hook and sk are still valid. - */ - close_fun = psock->save_close; - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - psock->cork = NULL; - } - - list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { - list_del(&md->list); - free_start_sg(psock->sock, md, true); - kfree(md); - } - - e = psock_map_pop(sk, psock); - while (e) { - if (e->entry) { - struct bpf_stab *stab = container_of(e->map, struct bpf_stab, map); - - raw_spin_lock_bh(&stab->lock); - osk = *e->entry; - if (osk == sk) { - *e->entry = NULL; - smap_release_sock(psock, sk); - } - raw_spin_unlock_bh(&stab->lock); - } else { - struct htab_elem *link = rcu_dereference(e->hash_link); - struct bpf_htab *htab = container_of(e->map, struct bpf_htab, map); - struct hlist_head *head; - struct htab_elem *l; - struct bucket *b; - - b = __select_bucket(htab, link->hash); - head = &b->head; - raw_spin_lock_bh(&b->lock); - l = lookup_elem_raw(head, - link->hash, link->key, - htab->map.key_size); - /* If another thread deleted this object skip deletion. - * The refcnt on psock may or may not be zero. - */ - if (l && l == link) { - hlist_del_rcu(&link->hash_node); - smap_release_sock(psock, link->sk); - free_htab_elem(htab, link); - } - raw_spin_unlock_bh(&b->lock); - } - kfree(e); - e = psock_map_pop(sk, psock); - } - rcu_read_unlock(); - release_sock(sk); - close_fun(sk, timeout); -} - -enum __sk_action { - __SK_DROP = 0, - __SK_PASS, - __SK_REDIRECT, - __SK_NONE, -}; - -static struct tcp_ulp_ops bpf_tcp_ulp_ops __read_mostly = { - .name = "bpf_tcp", - .uid = TCP_ULP_BPF, - .user_visible = false, - .owner = NULL, - .init = bpf_tcp_init, - .release = bpf_tcp_release, -}; - -static int memcopy_from_iter(struct sock *sk, - struct sk_msg_buff *md, - struct iov_iter *from, int bytes) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_curr, rc = -ENOSPC; - - do { - int copy; - char *to; - - if (md->sg_copybreak >= sg[i].length) { - md->sg_copybreak = 0; - - if (++i == MAX_SKB_FRAGS) - i = 0; - - if (i == md->sg_end) - break; - } - - copy = sg[i].length - md->sg_copybreak; - to = sg_virt(&sg[i]) + md->sg_copybreak; - md->sg_copybreak += copy; - - if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) - rc = copy_from_iter_nocache(to, copy, from); - else - rc = copy_from_iter(to, copy, from); - - if (rc != copy) { - rc = -EFAULT; - goto out; - } - - bytes -= copy; - if (!bytes) - break; - - md->sg_copybreak = 0; - if (++i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -out: - md->sg_curr = i; - return rc; -} - -static int bpf_tcp_push(struct sock *sk, int apply_bytes, - struct sk_msg_buff *md, - int flags, bool uncharge) -{ - bool apply = apply_bytes; - struct scatterlist *sg; - int offset, ret = 0; - struct page *p; - size_t size; - - while (1) { - sg = md->sg_data + md->sg_start; - size = (apply && apply_bytes < sg->length) ? - apply_bytes : sg->length; - offset = sg->offset; - - tcp_rate_check_app_limited(sk); - p = sg_page(sg); -retry: - ret = do_tcp_sendpages(sk, p, offset, size, flags); - if (ret != size) { - if (ret > 0) { - if (apply) - apply_bytes -= ret; - - sg->offset += ret; - sg->length -= ret; - size -= ret; - offset += ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - goto retry; - } - - return ret; - } - - if (apply) - apply_bytes -= ret; - sg->offset += ret; - sg->length -= ret; - if (uncharge) - sk_mem_uncharge(sk, ret); - - if (!sg->length) { - put_page(p); - md->sg_start++; - if (md->sg_start == MAX_SKB_FRAGS) - md->sg_start = 0; - sg_init_table(sg, 1); - - if (md->sg_start == md->sg_end) - break; - } - - if (apply && !apply_bytes) - break; - } - return 0; -} - -static inline void bpf_compute_data_pointers_sg(struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data + md->sg_start; - - if (md->sg_copy[md->sg_start]) { - md->data = md->data_end = 0; - } else { - md->data = sg_virt(sg); - md->data_end = md->data + sg->length; - } -} - -static void return_mem_sg(struct sock *sk, int bytes, struct sk_msg_buff *md) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start; - - do { - int uncharge = (bytes < sg[i].length) ? bytes : sg[i].length; - - sk_mem_uncharge(sk, uncharge); - bytes -= uncharge; - if (!bytes) - break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - } while (i != md->sg_end); -} - -static void free_bytes_sg(struct sock *sk, int bytes, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = md->sg_start, free; - - while (bytes && sg[i].length) { - free = sg[i].length; - if (bytes < free) { - sg[i].length -= bytes; - sg[i].offset += bytes; - if (charge) - sk_mem_uncharge(sk, bytes); - break; - } - - if (charge) - sk_mem_uncharge(sk, sg[i].length); - put_page(sg_page(&sg[i])); - bytes -= sg[i].length; - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - md->sg_start = i; -} - -static int free_sg(struct sock *sk, int start, - struct sk_msg_buff *md, bool charge) -{ - struct scatterlist *sg = md->sg_data; - int i = start, free = 0; - - while (sg[i].length) { - free += sg[i].length; - if (charge) - sk_mem_uncharge(sk, sg[i].length); - if (!md->skb) - put_page(sg_page(&sg[i])); - sg[i].length = 0; - sg[i].page_link = 0; - sg[i].offset = 0; - i++; - - if (i == MAX_SKB_FRAGS) - i = 0; - } - if (md->skb) - consume_skb(md->skb); - - return free; -} - -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) -{ - int free = free_sg(sk, md->sg_start, md, charge); - - md->sg_start = md->sg_end; - return free; -} - -static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) -{ - return free_sg(sk, md->sg_curr, md, true); -} - -static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) -{ - return ((_rc == SK_PASS) ? - (md->sk_redir ? __SK_REDIRECT : __SK_PASS) : - __SK_DROP); -} - -static unsigned int smap_do_tx_msg(struct sock *sk, - struct smap_psock *psock, - struct sk_msg_buff *md) -{ - struct bpf_prog *prog; - unsigned int rc, _rc; - - preempt_disable(); - rcu_read_lock(); - - /* If the policy was removed mid-send then default to 'accept' */ - prog = READ_ONCE(psock->bpf_tx_msg); - if (unlikely(!prog)) { - _rc = SK_PASS; - goto verdict; - } - - bpf_compute_data_pointers_sg(md); - md->sk = sk; - rc = (*prog->bpf_func)(md, prog->insnsi); - psock->apply_bytes = md->apply_bytes; - - /* Moving return codes from UAPI namespace into internal namespace */ - _rc = bpf_map_msg_verdict(rc, md); - - /* The psock has a refcount on the sock but not on the map and because - * we need to drop rcu read lock here its possible the map could be - * removed between here and when we need it to execute the sock - * redirect. So do the map lookup now for future use. - */ - if (_rc == __SK_REDIRECT) { - if (psock->sk_redir) - sock_put(psock->sk_redir); - psock->sk_redir = do_msg_redirect_map(md); - if (!psock->sk_redir) { - _rc = __SK_DROP; - goto verdict; - } - sock_hold(psock->sk_redir); - } -verdict: - rcu_read_unlock(); - preempt_enable(); - - return _rc; -} - -static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, - struct smap_psock *psock, - struct sk_msg_buff *md, int flags) -{ - bool apply = apply_bytes; - size_t size, copied = 0; - struct sk_msg_buff *r; - int err = 0, i; - - r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_KERNEL); - if (unlikely(!r)) - return -ENOMEM; - - lock_sock(sk); - r->sg_start = md->sg_start; - i = md->sg_start; - - do { - size = (apply && apply_bytes < md->sg_data[i].length) ? - apply_bytes : md->sg_data[i].length; - - if (!sk_wmem_schedule(sk, size)) { - if (!copied) - err = -ENOMEM; - break; - } - - sk_mem_charge(sk, size); - r->sg_data[i] = md->sg_data[i]; - r->sg_data[i].length = size; - md->sg_data[i].length -= size; - md->sg_data[i].offset += size; - copied += size; - - if (md->sg_data[i].length) { - get_page(sg_page(&r->sg_data[i])); - r->sg_end = (i + 1) == MAX_SKB_FRAGS ? 0 : i + 1; - } else { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - r->sg_end = i; - } - - if (apply) { - apply_bytes -= size; - if (!apply_bytes) - break; - } - } while (i != md->sg_end); - - md->sg_start = i; - - if (!err) { - list_add_tail(&r->list, &psock->ingress); - sk->sk_data_ready(sk); - } else { - free_start_sg(sk, r, true); - kfree(r); - } - - release_sock(sk); - return err; -} - -static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, - struct sk_msg_buff *md, - int flags) -{ - bool ingress = !!(md->flags & BPF_F_INGRESS); - struct smap_psock *psock; - int err = 0; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out_rcu; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto out_rcu; - - rcu_read_unlock(); - - if (ingress) { - err = bpf_tcp_ingress(sk, send, psock, md, flags); - } else { - lock_sock(sk); - err = bpf_tcp_push(sk, send, md, flags, false); - release_sock(sk); - } - smap_release_sock(psock, sk); - return err; -out_rcu: - rcu_read_unlock(); - return 0; -} - -static inline void bpf_md_init(struct smap_psock *psock) -{ - if (!psock->apply_bytes) { - psock->eval = __SK_NONE; - if (psock->sk_redir) { - sock_put(psock->sk_redir); - psock->sk_redir = NULL; - } - } -} - -static void apply_bytes_dec(struct smap_psock *psock, int i) -{ - if (psock->apply_bytes) { - if (psock->apply_bytes < i) - psock->apply_bytes = 0; - else - psock->apply_bytes -= i; - } -} - -static int bpf_exec_tx_verdict(struct smap_psock *psock, - struct sk_msg_buff *m, - struct sock *sk, - int *copied, int flags) -{ - bool cork = false, enospc = (m->sg_start == m->sg_end); - struct sock *redir; - int err = 0; - int send; - -more_data: - if (psock->eval == __SK_NONE) - psock->eval = smap_do_tx_msg(sk, psock, m); - - if (m->cork_bytes && - m->cork_bytes > psock->sg_size && !enospc) { - psock->cork_bytes = m->cork_bytes - psock->sg_size; - if (!psock->cork) { - psock->cork = kcalloc(1, - sizeof(struct sk_msg_buff), - GFP_ATOMIC | __GFP_NOWARN); - - if (!psock->cork) { - err = -ENOMEM; - goto out_err; - } - } - memcpy(psock->cork, m, sizeof(*m)); - goto out_err; - } - - send = psock->sg_size; - if (psock->apply_bytes && psock->apply_bytes < send) - send = psock->apply_bytes; - - switch (psock->eval) { - case __SK_PASS: - err = bpf_tcp_push(sk, send, m, flags, true); - if (unlikely(err)) { - *copied -= free_start_sg(sk, m, true); - break; - } - - apply_bytes_dec(psock, send); - psock->sg_size -= send; - break; - case __SK_REDIRECT: - redir = psock->sk_redir; - apply_bytes_dec(psock, send); - - if (psock->cork) { - cork = true; - psock->cork = NULL; - } - - return_mem_sg(sk, send, m); - release_sock(sk); - - err = bpf_tcp_sendmsg_do_redirect(redir, send, m, flags); - lock_sock(sk); - - if (unlikely(err < 0)) { - int free = free_start_sg(sk, m, false); - - psock->sg_size = 0; - if (!cork) - *copied -= free; - } else { - psock->sg_size -= send; - } - - if (cork) { - free_start_sg(sk, m, true); - psock->sg_size = 0; - kfree(m); - m = NULL; - err = 0; - } - break; - case __SK_DROP: - default: - free_bytes_sg(sk, send, m, true); - apply_bytes_dec(psock, send); - *copied -= send; - psock->sg_size -= send; - err = -EACCES; - break; - } - - if (likely(!err)) { - bpf_md_init(psock); - if (m && - m->sg_data[m->sg_start].page_link && - m->sg_data[m->sg_start].length) - goto more_data; - } - -out_err: - return err; -} - -static int bpf_wait_data(struct sock *sk, - struct smap_psock *psk, int flags, - long timeo, int *err) -{ - int rc; - - DEFINE_WAIT_FUNC(wait, woken_wake_function); - - add_wait_queue(sk_sleep(sk), &wait); - sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - rc = sk_wait_event(sk, &timeo, - !list_empty(&psk->ingress) || - !skb_queue_empty(&sk->sk_receive_queue), - &wait); - sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); - remove_wait_queue(sk_sleep(sk), &wait); - - return rc; -} - -static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, - int nonblock, int flags, int *addr_len) -{ - struct iov_iter *iter = &msg->msg_iter; - struct smap_psock *psock; - int copied = 0; - - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto out; - - if (unlikely(!refcount_inc_not_zero(&psock->refcnt))) - goto out; - rcu_read_unlock(); - - lock_sock(sk); -bytes_ready: - while (copied != len) { - struct scatterlist *sg; - struct sk_msg_buff *md; - int i; - - md = list_first_entry_or_null(&psock->ingress, - struct sk_msg_buff, list); - if (unlikely(!md)) - break; - i = md->sg_start; - do { - struct page *page; - int n, copy; - - sg = &md->sg_data[i]; - copy = sg->length; - page = sg_page(sg); - - if (copied + copy > len) - copy = len - copied; - - n = copy_page_to_iter(page, sg->offset, copy, iter); - if (n != copy) { - md->sg_start = i; - release_sock(sk); - smap_release_sock(psock, sk); - return -EFAULT; - } - - copied += copy; - sg->offset += copy; - sg->length -= copy; - sk_mem_uncharge(sk, copy); - - if (!sg->length) { - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (!md->skb) - put_page(page); - } - if (copied == len) - break; - } while (i != md->sg_end); - md->sg_start = i; - - if (!sg->length && md->sg_start == md->sg_end) { - list_del(&md->list); - if (md->skb) - consume_skb(md->skb); - kfree(md); - } - } - - if (!copied) { - long timeo; - int data; - int err = 0; - - timeo = sock_rcvtimeo(sk, nonblock); - data = bpf_wait_data(sk, psock, flags, timeo, &err); - - if (data) { - if (!skb_queue_empty(&sk->sk_receive_queue)) { - release_sock(sk); - smap_release_sock(psock, sk); - copied = tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - return copied; - } - goto bytes_ready; - } - - if (err) - copied = err; - } - - release_sock(sk); - smap_release_sock(psock, sk); - return copied; -out: - rcu_read_unlock(); - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); -} - - -static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) -{ - int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS; - struct sk_msg_buff md = {0}; - unsigned int sg_copy = 0; - struct smap_psock *psock; - int copied = 0, err = 0; - struct scatterlist *sg; - long timeo; - - /* Its possible a sock event or user removed the psock _but_ the ops - * have not been reprogrammed yet so we get here. In this case fallback - * to tcp_sendmsg. Note this only works because we _only_ ever allow - * a single ULP there is no hierarchy here. - */ - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - /* Increment the psock refcnt to ensure its not released while sending a - * message. Required because sk lookup and bpf programs are used in - * separate rcu critical sections. Its OK if we lose the map entry - * but we can't lose the sock reference. - */ - if (!refcount_inc_not_zero(&psock->refcnt)) { - rcu_read_unlock(); - return tcp_sendmsg(sk, msg, size); - } - - sg = md.sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - rcu_read_unlock(); - - lock_sock(sk); - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); - - while (msg_data_left(msg)) { - struct sk_msg_buff *m = NULL; - bool enospc = false; - int copy; - - if (sk->sk_err) { - err = -sk->sk_err; - goto out_err; - } - - copy = msg_data_left(msg); - if (!sk_stream_memory_free(sk)) - goto wait_for_sndbuf; - - m = psock->cork_bytes ? psock->cork : &md; - m->sg_curr = m->sg_copybreak ? m->sg_curr : m->sg_end; - err = sk_alloc_sg(sk, copy, m->sg_data, - m->sg_start, &m->sg_end, &sg_copy, - m->sg_end - 1); - if (err) { - if (err != -ENOSPC) - goto wait_for_memory; - enospc = true; - copy = sg_copy; - } - - err = memcopy_from_iter(sk, m, &msg->msg_iter, copy); - if (err < 0) { - free_curr_sg(sk, m); - goto out_err; - } - - psock->sg_size += copy; - copied += copy; - sg_copy = 0; - - /* When bytes are being corked skip running BPF program and - * applying verdict unless there is no more buffer space. In - * the ENOSPC case simply run BPF prorgram with currently - * accumulated data. We don't have much choice at this point - * we could try extending the page frags or chaining complex - * frags but even in these cases _eventually_ we will hit an - * OOM scenario. More complex recovery schemes may be - * implemented in the future, but BPF programs must handle - * the case where apply_cork requests are not honored. The - * canonical method to verify this is to check data length. - */ - if (psock->cork_bytes) { - if (copy > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= copy; - - if (psock->cork_bytes && !enospc) - goto out_cork; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags); - if (unlikely(err < 0)) - goto out_err; - continue; -wait_for_sndbuf: - set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); -wait_for_memory: - err = sk_stream_wait_memory(sk, &timeo); - if (err) { - if (m && m != psock->cork) - free_start_sg(sk, m, true); - goto out_err; - } - } -out_err: - if (err < 0) - err = sk_stream_error(sk, msg->msg_flags, err); -out_cork: - release_sock(sk); - smap_release_sock(psock, sk); - return copied ? copied : err; -} - -static int bpf_tcp_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct sk_msg_buff md = {0}, *m = NULL; - int err = 0, copied = 0; - struct smap_psock *psock; - struct scatterlist *sg; - bool enospc = false; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) - goto accept; - - if (!refcount_inc_not_zero(&psock->refcnt)) - goto accept; - rcu_read_unlock(); - - lock_sock(sk); - - if (psock->cork_bytes) { - m = psock->cork; - sg = &m->sg_data[m->sg_end]; - } else { - m = &md; - sg = m->sg_data; - sg_init_marker(sg, MAX_SKB_FRAGS); - } - - /* Catch case where ring is full and sendpage is stalled. */ - if (unlikely(m->sg_end == m->sg_start && - m->sg_data[m->sg_end].length)) - goto out_err; - - psock->sg_size += size; - sg_set_page(sg, page, size, offset); - get_page(page); - m->sg_copy[m->sg_end] = true; - sk_mem_charge(sk, size); - m->sg_end++; - copied = size; - - if (m->sg_end == MAX_SKB_FRAGS) - m->sg_end = 0; - - if (m->sg_end == m->sg_start) - enospc = true; - - if (psock->cork_bytes) { - if (size > psock->cork_bytes) - psock->cork_bytes = 0; - else - psock->cork_bytes -= size; - - if (psock->cork_bytes && !enospc) - goto out_err; - - /* All cork bytes accounted for re-run filter */ - psock->eval = __SK_NONE; - psock->cork_bytes = 0; - } - - err = bpf_exec_tx_verdict(psock, m, sk, &copied, flags); -out_err: - release_sock(sk); - smap_release_sock(psock, sk); - return copied ? copied : err; -accept: - rcu_read_unlock(); - return tcp_sendpage(sk, page, offset, size, flags); -} - -static void bpf_tcp_msg_add(struct smap_psock *psock, - struct sock *sk, - struct bpf_prog *tx_msg) -{ - struct bpf_prog *orig_tx_msg; - - orig_tx_msg = xchg(&psock->bpf_tx_msg, tx_msg); - if (orig_tx_msg) - bpf_prog_put(orig_tx_msg); -} - -static int bpf_tcp_ulp_register(void) -{ - build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot); - /* Once BPF TX ULP is registered it is never unregistered. It - * will be in the ULP list for the lifetime of the system. Doing - * duplicate registers is not a problem. - */ - return tcp_register_ulp(&bpf_tcp_ulp_ops); -} - -static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) -{ - struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); - int rc; - - if (unlikely(!prog)) - return __SK_DROP; - - skb_orphan(skb); - /* We need to ensure that BPF metadata for maps is also cleared - * when we orphan the skb so that we don't have the possibility - * to reference a stale map. - */ - TCP_SKB_CB(skb)->bpf.sk_redir = NULL; - skb->sk = psock->sock; - bpf_compute_data_end_sk_skb(skb); - preempt_disable(); - rc = (*prog->bpf_func)(skb, prog->insnsi); - preempt_enable(); - skb->sk = NULL; - - /* Moving return codes from UAPI namespace into internal namespace */ - return rc == SK_PASS ? - (TCP_SKB_CB(skb)->bpf.sk_redir ? __SK_REDIRECT : __SK_PASS) : - __SK_DROP; -} - -static int smap_do_ingress(struct smap_psock *psock, struct sk_buff *skb) -{ - struct sock *sk = psock->sock; - int copied = 0, num_sg; - struct sk_msg_buff *r; - - r = kzalloc(sizeof(struct sk_msg_buff), __GFP_NOWARN | GFP_ATOMIC); - if (unlikely(!r)) - return -EAGAIN; - - if (!sk_rmem_schedule(sk, skb, skb->len)) { - kfree(r); - return -EAGAIN; - } - - sg_init_table(r->sg_data, MAX_SKB_FRAGS); - num_sg = skb_to_sgvec(skb, r->sg_data, 0, skb->len); - if (unlikely(num_sg < 0)) { - kfree(r); - return num_sg; - } - sk_mem_charge(sk, skb->len); - copied = skb->len; - r->sg_start = 0; - r->sg_end = num_sg == MAX_SKB_FRAGS ? 0 : num_sg; - r->skb = skb; - list_add_tail(&r->list, &psock->ingress); - sk->sk_data_ready(sk); - return copied; -} - -static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) -{ - struct smap_psock *peer; - struct sock *sk; - __u32 in; - int rc; - - rc = smap_verdict_func(psock, skb); - switch (rc) { - case __SK_REDIRECT: - sk = do_sk_redirect_map(skb); - if (!sk) { - kfree_skb(skb); - break; - } - - peer = smap_psock_sk(sk); - in = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS; - - if (unlikely(!peer || sock_flag(sk, SOCK_DEAD) || - !test_bit(SMAP_TX_RUNNING, &peer->state))) { - kfree_skb(skb); - break; - } - - if (!in && sock_writeable(sk)) { - skb_set_owner_w(skb, sk); - skb_queue_tail(&peer->rxqueue, skb); - schedule_work(&peer->tx_work); - break; - } else if (in && - atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_queue_tail(&peer->rxqueue, skb); - schedule_work(&peer->tx_work); - break; - } - /* Fall through and free skb otherwise */ - case __SK_DROP: - default: - kfree_skb(skb); - } -} - -static void smap_report_sk_error(struct smap_psock *psock, int err) -{ - struct sock *sk = psock->sock; - - sk->sk_err = err; - sk->sk_error_report(sk); -} - -static void smap_read_sock_strparser(struct strparser *strp, - struct sk_buff *skb) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = container_of(strp, struct smap_psock, strp); - smap_do_verdict(psock, skb); - rcu_read_unlock(); -} - -/* Called with lock held on socket */ -static void smap_data_ready(struct sock *sk) -{ - struct smap_psock *psock; - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (likely(psock)) { - write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->strp); - write_unlock_bh(&sk->sk_callback_lock); - } - rcu_read_unlock(); -} - -static void smap_tx_work(struct work_struct *w) -{ - struct smap_psock *psock; - struct sk_buff *skb; - int rem, off, n; - - psock = container_of(w, struct smap_psock, tx_work); - - /* lock sock to avoid losing sk_socket at some point during loop */ - lock_sock(psock->sock); - if (psock->save_skb) { - skb = psock->save_skb; - rem = psock->save_rem; - off = psock->save_off; - psock->save_skb = NULL; - goto start; - } - - while ((skb = skb_dequeue(&psock->rxqueue))) { - __u32 flags; - - rem = skb->len; - off = 0; -start: - flags = (TCP_SKB_CB(skb)->bpf.flags) & BPF_F_INGRESS; - do { - if (likely(psock->sock->sk_socket)) { - if (flags) - n = smap_do_ingress(psock, skb); - else - n = skb_send_sock_locked(psock->sock, - skb, off, rem); - } else { - n = -EINVAL; - } - - if (n <= 0) { - if (n == -EAGAIN) { - /* Retry when space is available */ - psock->save_skb = skb; - psock->save_rem = rem; - psock->save_off = off; - goto out; - } - /* Hard errors break pipe and stop xmit */ - smap_report_sk_error(psock, n ? -n : EPIPE); - clear_bit(SMAP_TX_RUNNING, &psock->state); - kfree_skb(skb); - goto out; - } - rem -= n; - off += n; - } while (rem); - - if (!flags) - kfree_skb(skb); - } -out: - release_sock(psock->sock); -} - -static void smap_write_space(struct sock *sk) -{ - struct smap_psock *psock; - void (*write_space)(struct sock *sk); - - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) - schedule_work(&psock->tx_work); - write_space = psock->save_write_space; - rcu_read_unlock(); - write_space(sk); -} - -static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) -{ - if (!psock->strp_enabled) - return; - sk->sk_data_ready = psock->save_data_ready; - sk->sk_write_space = psock->save_write_space; - psock->save_data_ready = NULL; - psock->save_write_space = NULL; - strp_stop(&psock->strp); - psock->strp_enabled = false; -} - -static void smap_destroy_psock(struct rcu_head *rcu) -{ - struct smap_psock *psock = container_of(rcu, - struct smap_psock, rcu); - - /* Now that a grace period has passed there is no longer - * any reference to this sock in the sockmap so we can - * destroy the psock, strparser, and bpf programs. But, - * because we use workqueue sync operations we can not - * do it in rcu context - */ - schedule_work(&psock->gc_work); -} - -static bool psock_is_smap_sk(struct sock *sk) -{ - return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops; -} - -static void smap_release_sock(struct smap_psock *psock, struct sock *sock) -{ - if (refcount_dec_and_test(&psock->refcnt)) { - if (psock_is_smap_sk(sock)) - tcp_cleanup_ulp(sock); - write_lock_bh(&sock->sk_callback_lock); - smap_stop_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - clear_bit(SMAP_TX_RUNNING, &psock->state); - rcu_assign_sk_user_data(sock, NULL); - call_rcu_sched(&psock->rcu, smap_destroy_psock); - } -} - -static int smap_parse_func_strparser(struct strparser *strp, - struct sk_buff *skb) -{ - struct smap_psock *psock; - struct bpf_prog *prog; - int rc; - - rcu_read_lock(); - psock = container_of(strp, struct smap_psock, strp); - prog = READ_ONCE(psock->bpf_parse); - - if (unlikely(!prog)) { - rcu_read_unlock(); - return skb->len; - } - - /* Attach socket for bpf program to use if needed we can do this - * because strparser clones the skb before handing it to a upper - * layer, meaning skb_orphan has been called. We NULL sk on the - * way out to ensure we don't trigger a BUG_ON in skb/sk operations - * later and because we are not charging the memory of this skb to - * any socket yet. - */ - skb->sk = psock->sock; - bpf_compute_data_end_sk_skb(skb); - rc = (*prog->bpf_func)(skb, prog->insnsi); - skb->sk = NULL; - rcu_read_unlock(); - return rc; -} - -static int smap_read_sock_done(struct strparser *strp, int err) -{ - return err; -} - -static int smap_init_sock(struct smap_psock *psock, - struct sock *sk) -{ - static const struct strp_callbacks cb = { - .rcv_msg = smap_read_sock_strparser, - .parse_msg = smap_parse_func_strparser, - .read_sock_done = smap_read_sock_done, - }; - - return strp_init(&psock->strp, sk, &cb); -} - -static void smap_init_progs(struct smap_psock *psock, - struct bpf_prog *verdict, - struct bpf_prog *parse) -{ - struct bpf_prog *orig_parse, *orig_verdict; - - orig_parse = xchg(&psock->bpf_parse, parse); - orig_verdict = xchg(&psock->bpf_verdict, verdict); - - if (orig_verdict) - bpf_prog_put(orig_verdict); - if (orig_parse) - bpf_prog_put(orig_parse); -} - -static void smap_start_sock(struct smap_psock *psock, struct sock *sk) -{ - if (sk->sk_data_ready == smap_data_ready) - return; - psock->save_data_ready = sk->sk_data_ready; - psock->save_write_space = sk->sk_write_space; - sk->sk_data_ready = smap_data_ready; - sk->sk_write_space = smap_write_space; - psock->strp_enabled = true; -} - -static void sock_map_remove_complete(struct bpf_stab *stab) -{ - bpf_map_area_free(stab->sock_map); - kfree(stab); -} - -static void smap_gc_work(struct work_struct *w) -{ - struct smap_psock_map_entry *e, *tmp; - struct sk_msg_buff *md, *mtmp; - struct smap_psock *psock; - - psock = container_of(w, struct smap_psock, gc_work); - - /* no callback lock needed because we already detached sockmap ops */ - if (psock->strp_enabled) - strp_done(&psock->strp); - - cancel_work_sync(&psock->tx_work); - __skb_queue_purge(&psock->rxqueue); - - /* At this point all strparser and xmit work must be complete */ - if (psock->bpf_parse) - bpf_prog_put(psock->bpf_parse); - if (psock->bpf_verdict) - bpf_prog_put(psock->bpf_verdict); - if (psock->bpf_tx_msg) - bpf_prog_put(psock->bpf_tx_msg); - - if (psock->cork) { - free_start_sg(psock->sock, psock->cork, true); - kfree(psock->cork); - } - - list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { - list_del(&md->list); - free_start_sg(psock->sock, md, true); - kfree(md); - } - - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - list_del(&e->list); - kfree(e); - } - - if (psock->sk_redir) - sock_put(psock->sk_redir); - - sock_put(psock->sock); - kfree(psock); -} - -static struct smap_psock *smap_init_psock(struct sock *sock, int node) -{ - struct smap_psock *psock; - - psock = kzalloc_node(sizeof(struct smap_psock), - GFP_ATOMIC | __GFP_NOWARN, - node); - if (!psock) - return ERR_PTR(-ENOMEM); - - psock->eval = __SK_NONE; - psock->sock = sock; - skb_queue_head_init(&psock->rxqueue); - INIT_WORK(&psock->tx_work, smap_tx_work); - INIT_WORK(&psock->gc_work, smap_gc_work); - INIT_LIST_HEAD(&psock->maps); - INIT_LIST_HEAD(&psock->ingress); - refcount_set(&psock->refcnt, 1); - spin_lock_init(&psock->maps_lock); - - rcu_assign_sk_user_data(sock, psock); - sock_hold(sock); - return psock; -} - -static struct bpf_map *sock_map_alloc(union bpf_attr *attr) -{ - struct bpf_stab *stab; - u64 cost; - int err; - - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - - /* check sanity of attributes */ - if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); - - err = bpf_tcp_ulp_register(); - if (err && err != -EEXIST) - return ERR_PTR(err); - - stab = kzalloc(sizeof(*stab), GFP_USER); - if (!stab) - return ERR_PTR(-ENOMEM); - - bpf_map_init_from_attr(&stab->map, attr); - raw_spin_lock_init(&stab->lock); - - /* make sure page count doesn't overflow */ - cost = (u64) stab->map.max_entries * sizeof(struct sock *); - err = -EINVAL; - if (cost >= U32_MAX - PAGE_SIZE) - goto free_stab; - - stab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - - /* if map size is larger than memlock limit, reject it early */ - err = bpf_map_precharge_memlock(stab->map.pages); - if (err) - goto free_stab; - - err = -ENOMEM; - stab->sock_map = bpf_map_area_alloc(stab->map.max_entries * - sizeof(struct sock *), - stab->map.numa_node); - if (!stab->sock_map) - goto free_stab; - - return &stab->map; -free_stab: - kfree(stab); - return ERR_PTR(err); -} - -static void smap_list_map_remove(struct smap_psock *psock, - struct sock **entry) -{ - struct smap_psock_map_entry *e, *tmp; - - spin_lock_bh(&psock->maps_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - if (e->entry == entry) { - list_del(&e->list); - kfree(e); - } - } - spin_unlock_bh(&psock->maps_lock); -} - -static void smap_list_hash_remove(struct smap_psock *psock, - struct htab_elem *hash_link) -{ - struct smap_psock_map_entry *e, *tmp; - - spin_lock_bh(&psock->maps_lock); - list_for_each_entry_safe(e, tmp, &psock->maps, list) { - struct htab_elem *c = rcu_dereference(e->hash_link); - - if (c == hash_link) { - list_del(&e->list); - kfree(e); - } - } - spin_unlock_bh(&psock->maps_lock); -} - -static void sock_map_free(struct bpf_map *map) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - int i; - - synchronize_rcu(); - - /* At this point no update, lookup or delete operations can happen. - * However, be aware we can still get a socket state event updates, - * and data ready callabacks that reference the psock from sk_user_data - * Also psock worker threads are still in-flight. So smap_release_sock - * will only free the psock after cancel_sync on the worker threads - * and a grace period expire to ensure psock is really safe to remove. - */ - rcu_read_lock(); - raw_spin_lock_bh(&stab->lock); - for (i = 0; i < stab->map.max_entries; i++) { - struct smap_psock *psock; - struct sock *sock; - - sock = stab->sock_map[i]; - if (!sock) - continue; - stab->sock_map[i] = NULL; - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get the - * sk_callback_lock before this case but after xchg happens - * causing the refcnt to hit zero and sock user data (psock) - * to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_map_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, sock); - } - } - raw_spin_unlock_bh(&stab->lock); - rcu_read_unlock(); - - sock_map_remove_complete(stab); -} - -static int sock_map_get_next_key(struct bpf_map *map, void *key, void *next_key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - u32 i = key ? *(u32 *)key : U32_MAX; - u32 *next = (u32 *)next_key; - - if (i >= stab->map.max_entries) { - *next = 0; - return 0; - } - - if (i == stab->map.max_entries - 1) - return -ENOENT; - - *next = i + 1; - return 0; -} - -struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - if (key >= map->max_entries) - return NULL; - - return READ_ONCE(stab->sock_map[key]); -} - -static int sock_map_delete_elem(struct bpf_map *map, void *key) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct smap_psock *psock; - int k = *(u32 *)key; - struct sock *sock; - - if (k >= map->max_entries) - return -EINVAL; - - raw_spin_lock_bh(&stab->lock); - sock = stab->sock_map[k]; - stab->sock_map[k] = NULL; - raw_spin_unlock_bh(&stab->lock); - if (!sock) - return -EINVAL; - - psock = smap_psock_sk(sock); - if (!psock) - return 0; - if (psock->bpf_parse) { - write_lock_bh(&sock->sk_callback_lock); - smap_stop_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - } - smap_list_map_remove(psock, &stab->sock_map[k]); - smap_release_sock(psock, sock); - return 0; -} - -/* Locking notes: Concurrent updates, deletes, and lookups are allowed and are - * done inside rcu critical sections. This ensures on updates that the psock - * will not be released via smap_release_sock() until concurrent updates/deletes - * complete. All operations operate on sock_map using cmpxchg and xchg - * operations to ensure we do not get stale references. Any reads into the - * map must be done with READ_ONCE() because of this. - * - * A psock is destroyed via call_rcu and after any worker threads are cancelled - * and syncd so we are certain all references from the update/lookup/delete - * operations as well as references in the data path are no longer in use. - * - * Psocks may exist in multiple maps, but only a single set of parse/verdict - * programs may be inherited from the maps it belongs to. A reference count - * is kept with the total number of references to the psock from all maps. The - * psock will not be released until this reaches zero. The psock and sock - * user data data use the sk_callback_lock to protect critical data structures - * from concurrent access. This allows us to avoid two updates from modifying - * the user data in sock and the lock is required anyways for modifying - * callbacks, we simply increase its scope slightly. - * - * Rules to follow, - * - psock must always be read inside RCU critical section - * - sk_user_data must only be modified inside sk_callback_lock and read - * inside RCU critical section. - * - psock->maps list must only be read & modified inside sk_callback_lock - * - sock_map must use READ_ONCE and (cmp)xchg operations - * - BPF verdict/parse programs must use READ_ONCE and xchg operations - */ - -static int __sock_map_ctx_update_elem(struct bpf_map *map, - struct bpf_sock_progs *progs, - struct sock *sock, - void *key) -{ - struct bpf_prog *verdict, *parse, *tx_msg; - struct smap_psock *psock; - bool new = false; - int err = 0; - - /* 1. If sock map has BPF programs those will be inherited by the - * sock being added. If the sock is already attached to BPF programs - * this results in an error. - */ - verdict = READ_ONCE(progs->bpf_verdict); - parse = READ_ONCE(progs->bpf_parse); - tx_msg = READ_ONCE(progs->bpf_tx_msg); - - if (parse && verdict) { - /* bpf prog refcnt may be zero if a concurrent attach operation - * removes the program after the above READ_ONCE() but before - * we increment the refcnt. If this is the case abort with an - * error. - */ - verdict = bpf_prog_inc_not_zero(verdict); - if (IS_ERR(verdict)) - return PTR_ERR(verdict); - - parse = bpf_prog_inc_not_zero(parse); - if (IS_ERR(parse)) { - bpf_prog_put(verdict); - return PTR_ERR(parse); - } - } - - if (tx_msg) { - tx_msg = bpf_prog_inc_not_zero(tx_msg); - if (IS_ERR(tx_msg)) { - if (parse && verdict) { - bpf_prog_put(parse); - bpf_prog_put(verdict); - } - return PTR_ERR(tx_msg); - } - } - - psock = smap_psock_sk(sock); - - /* 2. Do not allow inheriting programs if psock exists and has - * already inherited programs. This would create confusion on - * which parser/verdict program is running. If no psock exists - * create one. Inside sk_callback_lock to ensure concurrent create - * doesn't update user data. - */ - if (psock) { - if (!psock_is_smap_sk(sock)) { - err = -EBUSY; - goto out_progs; - } - if (READ_ONCE(psock->bpf_parse) && parse) { - err = -EBUSY; - goto out_progs; - } - if (READ_ONCE(psock->bpf_tx_msg) && tx_msg) { - err = -EBUSY; - goto out_progs; - } - if (!refcount_inc_not_zero(&psock->refcnt)) { - err = -EAGAIN; - goto out_progs; - } - } else { - psock = smap_init_psock(sock, map->numa_node); - if (IS_ERR(psock)) { - err = PTR_ERR(psock); - goto out_progs; - } - - set_bit(SMAP_TX_RUNNING, &psock->state); - new = true; - } - - /* 3. At this point we have a reference to a valid psock that is - * running. Attach any BPF programs needed. - */ - if (tx_msg) - bpf_tcp_msg_add(psock, sock, tx_msg); - if (new) { - err = tcp_set_ulp_id(sock, TCP_ULP_BPF); - if (err) - goto out_free; - } - - if (parse && verdict && !psock->strp_enabled) { - err = smap_init_sock(psock, sock); - if (err) - goto out_free; - smap_init_progs(psock, verdict, parse); - write_lock_bh(&sock->sk_callback_lock); - smap_start_sock(psock, sock); - write_unlock_bh(&sock->sk_callback_lock); - } - - return err; -out_free: - smap_release_sock(psock, sock); -out_progs: - if (parse && verdict) { - bpf_prog_put(parse); - bpf_prog_put(verdict); - } - if (tx_msg) - bpf_prog_put(tx_msg); - return err; -} - -static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 flags) -{ - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - struct bpf_sock_progs *progs = &stab->progs; - struct sock *osock, *sock = skops->sk; - struct smap_psock_map_entry *e; - struct smap_psock *psock; - u32 i = *(u32 *)key; - int err; - - if (unlikely(flags > BPF_EXIST)) - return -EINVAL; - if (unlikely(i >= stab->map.max_entries)) - return -E2BIG; - - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) - return -ENOMEM; - - err = __sock_map_ctx_update_elem(map, progs, sock, key); - if (err) - goto out; - - /* psock guaranteed to be present. */ - psock = smap_psock_sk(sock); - raw_spin_lock_bh(&stab->lock); - osock = stab->sock_map[i]; - if (osock && flags == BPF_NOEXIST) { - err = -EEXIST; - goto out_unlock; - } - if (!osock && flags == BPF_EXIST) { - err = -ENOENT; - goto out_unlock; - } - - e->entry = &stab->sock_map[i]; - e->map = map; - spin_lock_bh(&psock->maps_lock); - list_add_tail(&e->list, &psock->maps); - spin_unlock_bh(&psock->maps_lock); - - stab->sock_map[i] = sock; - if (osock) { - psock = smap_psock_sk(osock); - smap_list_map_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, osock); - } - raw_spin_unlock_bh(&stab->lock); - return 0; -out_unlock: - smap_release_sock(psock, sock); - raw_spin_unlock_bh(&stab->lock); -out: - kfree(e); - return err; -} - -int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type) -{ - struct bpf_sock_progs *progs; - struct bpf_prog *orig; - - if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - progs = &stab->progs; - } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH) { - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - - progs = &htab->progs; - } else { - return -EINVAL; - } - - switch (type) { - case BPF_SK_MSG_VERDICT: - orig = xchg(&progs->bpf_tx_msg, prog); - break; - case BPF_SK_SKB_STREAM_PARSER: - orig = xchg(&progs->bpf_parse, prog); - break; - case BPF_SK_SKB_STREAM_VERDICT: - orig = xchg(&progs->bpf_verdict, prog); - break; - default: - return -EOPNOTSUPP; - } - - if (orig) - bpf_prog_put(orig); - - return 0; -} - -int sockmap_get_from_fd(const union bpf_attr *attr, int type, - struct bpf_prog *prog) -{ - int ufd = attr->target_fd; - struct bpf_map *map; - struct fd f; - int err; - - f = fdget(ufd); - map = __bpf_map_get(f); - if (IS_ERR(map)) - return PTR_ERR(map); - - err = sock_map_prog(map, prog, attr->attach_type); - fdput(f); - return err; -} - -static void *sock_map_lookup(struct bpf_map *map, void *key) -{ - return NULL; -} - -static int sock_map_update_elem(struct bpf_map *map, - void *key, void *value, u64 flags) -{ - struct bpf_sock_ops_kern skops; - u32 fd = *(u32 *)value; - struct socket *socket; - int err; - - socket = sockfd_lookup(fd, &err); - if (!socket) - return err; - - skops.sk = socket->sk; - if (!skops.sk) { - fput(socket->file); - return -EINVAL; - } - - if (skops.sk->sk_type != SOCK_STREAM || - skops.sk->sk_protocol != IPPROTO_TCP) { - fput(socket->file); - return -EOPNOTSUPP; - } - - lock_sock(skops.sk); - preempt_disable(); - rcu_read_lock(); - err = sock_map_ctx_update_elem(&skops, map, key, flags); - rcu_read_unlock(); - preempt_enable(); - release_sock(skops.sk); - fput(socket->file); - return err; -} - -static void sock_map_release(struct bpf_map *map) -{ - struct bpf_sock_progs *progs; - struct bpf_prog *orig; - - if (map->map_type == BPF_MAP_TYPE_SOCKMAP) { - struct bpf_stab *stab = container_of(map, struct bpf_stab, map); - - progs = &stab->progs; - } else { - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - - progs = &htab->progs; - } - - orig = xchg(&progs->bpf_parse, NULL); - if (orig) - bpf_prog_put(orig); - orig = xchg(&progs->bpf_verdict, NULL); - if (orig) - bpf_prog_put(orig); - - orig = xchg(&progs->bpf_tx_msg, NULL); - if (orig) - bpf_prog_put(orig); -} - -static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) -{ - struct bpf_htab *htab; - int i, err; - u64 cost; - - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); - - /* check sanity of attributes */ - if (attr->max_entries == 0 || - attr->key_size == 0 || - attr->value_size != 4 || - attr->map_flags & ~SOCK_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); - - if (attr->key_size > MAX_BPF_STACK) - /* eBPF programs initialize keys on stack, so they cannot be - * larger than max stack size - */ - return ERR_PTR(-E2BIG); - - err = bpf_tcp_ulp_register(); - if (err && err != -EEXIST) - return ERR_PTR(err); - - htab = kzalloc(sizeof(*htab), GFP_USER); - if (!htab) - return ERR_PTR(-ENOMEM); - - bpf_map_init_from_attr(&htab->map, attr); - - htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); - htab->elem_size = sizeof(struct htab_elem) + - round_up(htab->map.key_size, 8); - err = -EINVAL; - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) - goto free_htab; - - cost = (u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries; - - if (cost >= U32_MAX - PAGE_SIZE) - goto free_htab; - - htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; - err = bpf_map_precharge_memlock(htab->map.pages); - if (err) - goto free_htab; - - err = -ENOMEM; - htab->buckets = bpf_map_area_alloc( - htab->n_buckets * sizeof(struct bucket), - htab->map.numa_node); - if (!htab->buckets) - goto free_htab; - - for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_HEAD(&htab->buckets[i].head); - raw_spin_lock_init(&htab->buckets[i].lock); - } - - return &htab->map; -free_htab: - kfree(htab); - return ERR_PTR(err); -} - -static void __bpf_htab_free(struct rcu_head *rcu) -{ - struct bpf_htab *htab; - - htab = container_of(rcu, struct bpf_htab, rcu); - bpf_map_area_free(htab->buckets); - kfree(htab); -} - -static void sock_hash_free(struct bpf_map *map) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - int i; - - synchronize_rcu(); - - /* At this point no update, lookup or delete operations can happen. - * However, be aware we can still get a socket state event updates, - * and data ready callabacks that reference the psock from sk_user_data - * Also psock worker threads are still in-flight. So smap_release_sock - * will only free the psock after cancel_sync on the worker threads - * and a grace period expire to ensure psock is really safe to remove. - */ - rcu_read_lock(); - for (i = 0; i < htab->n_buckets; i++) { - struct bucket *b = __select_bucket(htab, i); - struct hlist_head *head; - struct hlist_node *n; - struct htab_elem *l; - - raw_spin_lock_bh(&b->lock); - head = &b->head; - hlist_for_each_entry_safe(l, n, head, hash_node) { - struct sock *sock = l->sk; - struct smap_psock *psock; - - hlist_del_rcu(&l->hash_node); - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get - * the sk_callback_lock before this case but after xchg - * causing the refcnt to hit zero and sock user data - * (psock) to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_hash_remove(psock, l); - smap_release_sock(psock, sock); - } - free_htab_elem(htab, l); - } - raw_spin_unlock_bh(&b->lock); - } - rcu_read_unlock(); - call_rcu(&htab->rcu, __bpf_htab_free); -} - -static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, - void *key, u32 key_size, u32 hash, - struct sock *sk, - struct htab_elem *old_elem) -{ - struct htab_elem *l_new; - - if (atomic_inc_return(&htab->count) > htab->map.max_entries) { - if (!old_elem) { - atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); - } - } - l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); - if (!l_new) { - atomic_dec(&htab->count); - return ERR_PTR(-ENOMEM); - } - - memcpy(l_new->key, key, key_size); - l_new->sk = sk; - l_new->hash = hash; - return l_new; -} - -static inline u32 htab_map_hash(const void *key, u32 key_len) -{ - return jhash(key, key_len, 0); -} - -static int sock_hash_get_next_key(struct bpf_map *map, - void *key, void *next_key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct htab_elem *l, *next_l; - struct hlist_head *h; - u32 hash, key_size; - int i = 0; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - key_size = map->key_size; - if (!key) - goto find_first_elem; - hash = htab_map_hash(key, key_size); - h = select_bucket(htab, hash); - - l = lookup_elem_raw(h, hash, key, key_size); - if (!l) - goto find_first_elem; - next_l = hlist_entry_safe( - rcu_dereference_raw(hlist_next_rcu(&l->hash_node)), - struct htab_elem, hash_node); - if (next_l) { - memcpy(next_key, next_l->key, key_size); - return 0; - } - - /* no more elements in this hash list, go to the next bucket */ - i = hash & (htab->n_buckets - 1); - i++; - -find_first_elem: - /* iterate over buckets */ - for (; i < htab->n_buckets; i++) { - h = select_bucket(htab, i); - - /* pick first element in the bucket */ - next_l = hlist_entry_safe( - rcu_dereference_raw(hlist_first_rcu(h)), - struct htab_elem, hash_node); - if (next_l) { - /* if it's not empty, just return it */ - memcpy(next_key, next_l->key, key_size); - return 0; - } - } - - /* iterated over all buckets and all elements */ - return -ENOENT; -} - -static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops, - struct bpf_map *map, - void *key, u64 map_flags) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct bpf_sock_progs *progs = &htab->progs; - struct htab_elem *l_new = NULL, *l_old; - struct smap_psock_map_entry *e = NULL; - struct hlist_head *head; - struct smap_psock *psock; - u32 key_size, hash; - struct sock *sock; - struct bucket *b; - int err; - - sock = skops->sk; - - if (sock->sk_type != SOCK_STREAM || - sock->sk_protocol != IPPROTO_TCP) - return -EOPNOTSUPP; - - if (unlikely(map_flags > BPF_EXIST)) - return -EINVAL; - - e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN); - if (!e) - return -ENOMEM; - - WARN_ON_ONCE(!rcu_read_lock_held()); - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - err = __sock_map_ctx_update_elem(map, progs, sock, key); - if (err) - goto err; - - /* psock is valid here because otherwise above *ctx_update_elem would - * have thrown an error. It is safe to skip error check. - */ - psock = smap_psock_sk(sock); - raw_spin_lock_bh(&b->lock); - l_old = lookup_elem_raw(head, hash, key, key_size); - if (l_old && map_flags == BPF_NOEXIST) { - err = -EEXIST; - goto bucket_err; - } - if (!l_old && map_flags == BPF_EXIST) { - err = -ENOENT; - goto bucket_err; - } - - l_new = alloc_sock_hash_elem(htab, key, key_size, hash, sock, l_old); - if (IS_ERR(l_new)) { - err = PTR_ERR(l_new); - goto bucket_err; - } - - rcu_assign_pointer(e->hash_link, l_new); - e->map = map; - spin_lock_bh(&psock->maps_lock); - list_add_tail(&e->list, &psock->maps); - spin_unlock_bh(&psock->maps_lock); - - /* add new element to the head of the list, so that - * concurrent search will find it before old elem - */ - hlist_add_head_rcu(&l_new->hash_node, head); - if (l_old) { - psock = smap_psock_sk(l_old->sk); - - hlist_del_rcu(&l_old->hash_node); - smap_list_hash_remove(psock, l_old); - smap_release_sock(psock, l_old->sk); - free_htab_elem(htab, l_old); - } - raw_spin_unlock_bh(&b->lock); - return 0; -bucket_err: - smap_release_sock(psock, sock); - raw_spin_unlock_bh(&b->lock); -err: - kfree(e); - return err; -} - -static int sock_hash_update_elem(struct bpf_map *map, - void *key, void *value, u64 flags) -{ - struct bpf_sock_ops_kern skops; - u32 fd = *(u32 *)value; - struct socket *socket; - int err; - - socket = sockfd_lookup(fd, &err); - if (!socket) - return err; - - skops.sk = socket->sk; - if (!skops.sk) { - fput(socket->file); - return -EINVAL; - } - - lock_sock(skops.sk); - preempt_disable(); - rcu_read_lock(); - err = sock_hash_ctx_update_elem(&skops, map, key, flags); - rcu_read_unlock(); - preempt_enable(); - release_sock(skops.sk); - fput(socket->file); - return err; -} - -static int sock_hash_delete_elem(struct bpf_map *map, void *key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; - struct bucket *b; - struct htab_elem *l; - u32 hash, key_size; - int ret = -ENOENT; - - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - raw_spin_lock_bh(&b->lock); - l = lookup_elem_raw(head, hash, key, key_size); - if (l) { - struct sock *sock = l->sk; - struct smap_psock *psock; - - hlist_del_rcu(&l->hash_node); - psock = smap_psock_sk(sock); - /* This check handles a racing sock event that can get the - * sk_callback_lock before this case but after xchg happens - * causing the refcnt to hit zero and sock user data (psock) - * to be null and queued for garbage collection. - */ - if (likely(psock)) { - smap_list_hash_remove(psock, l); - smap_release_sock(psock, sock); - } - free_htab_elem(htab, l); - ret = 0; - } - raw_spin_unlock_bh(&b->lock); - return ret; -} - -struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key) -{ - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - struct hlist_head *head; - struct htab_elem *l; - u32 key_size, hash; - struct bucket *b; - struct sock *sk; - - key_size = map->key_size; - hash = htab_map_hash(key, key_size); - b = __select_bucket(htab, hash); - head = &b->head; - - l = lookup_elem_raw(head, hash, key, key_size); - sk = l ? l->sk : NULL; - return sk; -} - -const struct bpf_map_ops sock_map_ops = { - .map_alloc = sock_map_alloc, - .map_free = sock_map_free, - .map_lookup_elem = sock_map_lookup, - .map_get_next_key = sock_map_get_next_key, - .map_update_elem = sock_map_update_elem, - .map_delete_elem = sock_map_delete_elem, - .map_release_uref = sock_map_release, - .map_check_btf = map_check_no_btf, -}; - -const struct bpf_map_ops sock_hash_ops = { - .map_alloc = sock_hash_alloc, - .map_free = sock_hash_free, - .map_lookup_elem = sock_map_lookup, - .map_get_next_key = sock_hash_get_next_key, - .map_update_elem = sock_hash_update_elem, - .map_delete_elem = sock_hash_delete_elem, - .map_release_uref = sock_map_release, - .map_check_btf = map_check_no_btf, -}; - -BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, void *, key, u64, flags) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return sock_map_ctx_update_elem(bpf_sock, map, key, flags); -} - -const struct bpf_func_proto bpf_sock_map_update_proto = { - .func = bpf_sock_map_update, - .gpl_only = false, - .pkt_access = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; - -BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, - struct bpf_map *, map, void *, key, u64, flags) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); -} - -const struct bpf_func_proto bpf_sock_hash_update_proto = { - .func = bpf_sock_hash_update, - .gpl_only = false, - .pkt_access = true, - .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_CONST_MAP_PTR, - .arg3_type = ARG_PTR_TO_MAP_KEY, - .arg4_type = ARG_ANYTHING, -}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 8061a439ef18..90daf285de03 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -505,7 +505,7 @@ const struct bpf_func_proto bpf_get_stack_proto = { /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { - return NULL; + return ERR_PTR(-EOPNOTSUPP); } /* Called from syscall */ @@ -600,7 +600,7 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } -const struct bpf_map_ops stack_map_ops = { +const struct bpf_map_ops stack_trace_map_ops = { .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8339d81cba1d..ccb93277aae2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -30,7 +30,6 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> -#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -652,6 +651,17 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) return -ENOTSUPP; } +static void *__bpf_copy_key(void __user *ukey, u64 key_size) +{ + if (key_size) + return memdup_user(ukey, key_size); + + if (ukey) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value @@ -679,7 +689,7 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -687,7 +697,8 @@ static int map_lookup_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) value_size = sizeof(u32); @@ -706,6 +717,8 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map)) { @@ -714,13 +727,21 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); } else { rcu_read_lock(); ptr = map->ops->map_lookup_elem(map, key); - if (ptr) + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + } else if (!ptr) { + err = -ENOENT; + } else { + err = 0; memcpy(value, ptr, value_size); + } rcu_read_unlock(); - err = ptr ? 0 : -ENOENT; } if (err) @@ -741,6 +762,17 @@ err_put: return err; } +static void maybe_wait_bpf_programs(struct bpf_map *map) +{ + /* Wait for any running BPF programs to complete so that + * userspace, when we return to it, knows that all programs + * that could be running use the new map value. + */ + if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || + map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) + synchronize_rcu(); +} + #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr) @@ -767,7 +799,7 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -775,7 +807,8 @@ static int map_update_elem(union bpf_attr *attr) if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) value_size = round_up(map->value_size, 8) * num_possible_cpus(); else value_size = map->value_size; @@ -810,6 +843,9 @@ static int map_update_elem(union bpf_attr *attr) err = bpf_percpu_hash_update(map, key, value, attr->flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + attr->flags); } else if (IS_FD_ARRAY(map)) { rcu_read_lock(); err = bpf_fd_array_map_update_elem(map, f.file, key, value, @@ -824,6 +860,9 @@ static int map_update_elem(union bpf_attr *attr) /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); @@ -831,6 +870,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); + maybe_wait_bpf_programs(map); out: free_value: kfree(value); @@ -865,7 +905,7 @@ static int map_delete_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -883,6 +923,7 @@ static int map_delete_elem(union bpf_attr *attr) rcu_read_unlock(); __this_cpu_dec(bpf_prog_active); preempt_enable(); + maybe_wait_bpf_programs(map); out: kfree(key); err_put: @@ -917,7 +958,7 @@ static int map_get_next_key(union bpf_attr *attr) } if (ukey) { - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -958,6 +999,69 @@ err_put: return err; } +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value + +static int map_lookup_and_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_user_ptr(attr->key); + void __user *uvalue = u64_to_user_ptr(attr->value); + int ufd = attr->map_fd; + struct bpf_map *map; + void *key, *value; + u32 value_size; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + key = __bpf_copy_key(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + goto err_put; + } + + value_size = map->value_size; + + err = -ENOMEM; + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) + goto free_key; + + if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_pop_elem(map, value); + } else { + err = -ENOTSUPP; + } + + if (err) + goto free_value; + + if (copy_to_user(uvalue, value, value_size) != 0) + goto free_value; + + err = 0; + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -989,10 +1093,15 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) /* drop refcnt on maps used by eBPF program and free auxilary data */ static void free_used_maps(struct bpf_prog_aux *aux) { + enum bpf_cgroup_storage_type stype; int i; - if (aux->cgroup_storage) - bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage); + for_each_cgroup_storage_type(stype) { + if (!aux->cgroup_storage[stype]) + continue; + bpf_cgroup_storage_release(aux->prog, + aux->cgroup_storage[stype]); + } for (i = 0; i < aux->used_map_cnt; i++) bpf_map_put(aux->used_maps[i]); @@ -1616,6 +1725,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_LIRC_MODE2: ptype = BPF_PROG_TYPE_LIRC_MODE2; break; + case BPF_FLOW_DISSECTOR: + ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; + break; default: return -EINVAL; } @@ -1632,11 +1744,14 @@ static int bpf_prog_attach(const union bpf_attr *attr) switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: - ret = sockmap_get_from_fd(attr, ptype, prog); + ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; + case BPF_PROG_TYPE_FLOW_DISSECTOR: + ret = skb_flow_dissector_bpf_prog_attach(attr, prog); + break; default: ret = cgroup_bpf_prog_attach(attr, ptype, prog); } @@ -1683,12 +1798,14 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL); + return sock_map_get_from_fd(attr, NULL); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); + case BPF_FLOW_DISSECTOR: + return skb_flow_dissector_bpf_prog_detach(attr); default: return -EINVAL; } @@ -2418,6 +2535,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr); break; + case BPF_MAP_LOOKUP_AND_DELETE_ELEM: + err = map_lookup_and_delete_elem(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bb07e74b34a2..171a2c88e77d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1,5 +1,6 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook + * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -80,8 +81,8 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * (like pointer plus pointer becomes SCALAR_VALUE type) * * When verifier sees load or store instructions the type of base register - * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer - * types recognized by check_mem_access() function. + * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are + * four pointer types recognized by check_mem_access() function. * * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value' * and the range of [ptr, ptr + map's value_size) is accessible. @@ -140,6 +141,24 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { * * After the call R0 is set to return type of the function and registers R1-R5 * are set to NOT_INIT to indicate that they are no longer readable. + * + * The following reference types represent a potential reference to a kernel + * resource which, after first being allocated, must be checked and freed by + * the BPF program: + * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET + * + * When the verifier sees a helper call return a reference type, it allocates a + * pointer id for the reference and stores it in the current function state. + * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into + * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type + * passes through a NULL-check conditional. For the branch wherein the state is + * changed to CONST_IMM, the verifier releases the reference. + * + * For each helper function that allocates a reference, such as + * bpf_sk_lookup_tcp(), there is a corresponding release function, such as + * bpf_sk_release(). When a reference type passes into the release function, + * the verifier also releases the reference. If any unchecked or unreleased + * reference remains at the end of the program, the verifier rejects it. */ /* verifier_state + insn_idx are pushed to stack when branch is encountered */ @@ -189,6 +208,7 @@ struct bpf_call_arg_meta { int access_size; s64 msize_smax_value; u64 msize_umax_value; + int ptr_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -249,6 +269,46 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type) type == PTR_TO_PACKET_META; } +static bool reg_type_may_be_null(enum bpf_reg_type type) +{ + return type == PTR_TO_MAP_VALUE_OR_NULL || + type == PTR_TO_SOCKET_OR_NULL; +} + +static bool type_is_refcounted(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET; +} + +static bool type_is_refcounted_or_null(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL; +} + +static bool reg_is_refcounted(const struct bpf_reg_state *reg) +{ + return type_is_refcounted(reg->type); +} + +static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) +{ + return type_is_refcounted_or_null(reg->type); +} + +static bool arg_type_is_refcounted(enum bpf_arg_type type) +{ + return type == ARG_PTR_TO_SOCKET; +} + +/* Determine whether the function releases some resources allocated by another + * function call. The first reference type argument will be assumed to be + * released by release_reference(). + */ +static bool is_release_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_release; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -261,6 +321,16 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET] = "pkt", [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", +}; + +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', }; static void print_liveness(struct bpf_verifier_env *env, @@ -349,72 +419,179 @@ static void print_verifier_state(struct bpf_verifier_env *env, } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] == STACK_SPILL) { - verbose(env, " fp%d", - (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); + char types_buf[BPF_REG_SIZE + 1]; + bool valid = false; + int j; + + for (j = 0; j < BPF_REG_SIZE; j++) { + if (state->stack[i].slot_type[j] != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[ + state->stack[i].slot_type[j]]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, state->stack[i].spilled_ptr.live); + if (state->stack[i].slot_type[0] == STACK_SPILL) verbose(env, "=%s", reg_type_str[state->stack[i].spilled_ptr.type]); - } - if (state->stack[i].slot_type[0] == STACK_ZERO) - verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE); + else + verbose(env, "=%s", types_buf); + } + if (state->acquired_refs && state->refs[0].id) { + verbose(env, " refs=%d", state->refs[0].id); + for (i = 1; i < state->acquired_refs; i++) + if (state->refs[i].id) + verbose(env, ",%d", state->refs[i].id); } verbose(env, "\n"); } -static int copy_stack_state(struct bpf_func_state *dst, - const struct bpf_func_state *src) -{ - if (!src->stack) - return 0; - if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) { - /* internal bug, make state invalid to reject the program */ - memset(dst, 0, sizeof(*dst)); - return -EFAULT; - } - memcpy(dst->stack, src->stack, - sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE)); - return 0; -} +#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int copy_##NAME##_state(struct bpf_func_state *dst, \ + const struct bpf_func_state *src) \ +{ \ + if (!src->FIELD) \ + return 0; \ + if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \ + /* internal bug, make state invalid to reject the program */ \ + memset(dst, 0, sizeof(*dst)); \ + return -EFAULT; \ + } \ + memcpy(dst->FIELD, src->FIELD, \ + sizeof(*src->FIELD) * (src->COUNT / SIZE)); \ + return 0; \ +} +/* copy_reference_state() */ +COPY_STATE_FN(reference, acquired_refs, refs, 1) +/* copy_stack_state() */ +COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef COPY_STATE_FN + +#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \ +static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \ + bool copy_old) \ +{ \ + u32 old_size = state->COUNT; \ + struct bpf_##NAME##_state *new_##FIELD; \ + int slot = size / SIZE; \ + \ + if (size <= old_size || !size) { \ + if (copy_old) \ + return 0; \ + state->COUNT = slot * SIZE; \ + if (!size && old_size) { \ + kfree(state->FIELD); \ + state->FIELD = NULL; \ + } \ + return 0; \ + } \ + new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \ + GFP_KERNEL); \ + if (!new_##FIELD) \ + return -ENOMEM; \ + if (copy_old) { \ + if (state->FIELD) \ + memcpy(new_##FIELD, state->FIELD, \ + sizeof(*new_##FIELD) * (old_size / SIZE)); \ + memset(new_##FIELD + old_size / SIZE, 0, \ + sizeof(*new_##FIELD) * (size - old_size) / SIZE); \ + } \ + state->COUNT = slot * SIZE; \ + kfree(state->FIELD); \ + state->FIELD = new_##FIELD; \ + return 0; \ +} +/* realloc_reference_state() */ +REALLOC_STATE_FN(reference, acquired_refs, refs, 1) +/* realloc_stack_state() */ +REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE) +#undef REALLOC_STATE_FN /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which this function copies over. It points to previous bpf_verifier_state - * which is never reallocated + * which realloc_stack_state() copies over. It points to previous + * bpf_verifier_state which is never reallocated. + */ +static int realloc_func_state(struct bpf_func_state *state, int stack_size, + int refs_size, bool copy_old) +{ + int err = realloc_reference_state(state, refs_size, copy_old); + if (err) + return err; + return realloc_stack_state(state, stack_size, copy_old); +} + +/* Acquire a pointer id from the env and update the state->refs to include + * this new pointer reference. + * On success, returns a valid pointer id to associate with the register + * On failure, returns a negative errno. */ -static int realloc_func_state(struct bpf_func_state *state, int size, - bool copy_old) +static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) +{ + struct bpf_func_state *state = cur_func(env); + int new_ofs = state->acquired_refs; + int id, err; + + err = realloc_reference_state(state, state->acquired_refs + 1, true); + if (err) + return err; + id = ++env->id_gen; + state->refs[new_ofs].id = id; + state->refs[new_ofs].insn_idx = insn_idx; + + return id; +} + +/* release function corresponding to acquire_reference_state(). Idempotent. */ +static int __release_reference_state(struct bpf_func_state *state, int ptr_id) { - u32 old_size = state->allocated_stack; - struct bpf_stack_state *new_stack; - int slot = size / BPF_REG_SIZE; + int i, last_idx; - if (size <= old_size || !size) { - if (copy_old) + if (!ptr_id) + return -EFAULT; + + last_idx = state->acquired_refs - 1; + for (i = 0; i < state->acquired_refs; i++) { + if (state->refs[i].id == ptr_id) { + if (last_idx && i != last_idx) + memcpy(&state->refs[i], &state->refs[last_idx], + sizeof(*state->refs)); + memset(&state->refs[last_idx], 0, sizeof(*state->refs)); + state->acquired_refs--; return 0; - state->allocated_stack = slot * BPF_REG_SIZE; - if (!size && old_size) { - kfree(state->stack); - state->stack = NULL; } - return 0; } - new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state), - GFP_KERNEL); - if (!new_stack) - return -ENOMEM; - if (copy_old) { - if (state->stack) - memcpy(new_stack, state->stack, - sizeof(*new_stack) * (old_size / BPF_REG_SIZE)); - memset(new_stack + old_size / BPF_REG_SIZE, 0, - sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE); - } - state->allocated_stack = slot * BPF_REG_SIZE; - kfree(state->stack); - state->stack = new_stack; + return -EFAULT; +} + +/* variation on the above for cases where we expect that there must be an + * outstanding reference for the specified ptr_id. + */ +static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) +{ + struct bpf_func_state *state = cur_func(env); + int err; + + err = __release_reference_state(state, ptr_id); + if (WARN_ON_ONCE(err != 0)) + verbose(env, "verifier internal error: can't release reference\n"); + return err; +} + +static int transfer_reference_state(struct bpf_func_state *dst, + struct bpf_func_state *src) +{ + int err = realloc_reference_state(dst, src->acquired_refs, false); + if (err) + return err; + err = copy_reference_state(dst, src); + if (err) + return err; return 0; } @@ -422,6 +599,7 @@ static void free_func_state(struct bpf_func_state *state) { if (!state) return; + kfree(state->refs); kfree(state->stack); kfree(state); } @@ -447,10 +625,14 @@ static int copy_func_state(struct bpf_func_state *dst, { int err; - err = realloc_func_state(dst, src->allocated_stack, false); + err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs, + false); + if (err) + return err; + memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs)); + err = copy_reference_state(dst, src); if (err) return err; - memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack)); return copy_stack_state(dst, src); } @@ -466,7 +648,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->frame[i] = NULL; } dst_state->curframe = src->curframe; - dst_state->parent = src->parent; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -553,7 +734,9 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg); */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - reg->id = 0; + /* Clear id, off, and union(map_ptr, range) */ + memset(((u8 *)reg) + sizeof(reg->type), 0, + offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); reg->var_off = tnum_const(imm); reg->smin_value = (s64)imm; reg->smax_value = (s64)imm; @@ -572,7 +755,6 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) static void __mark_reg_const_zero(struct bpf_reg_state *reg) { __mark_reg_known(reg, 0); - reg->off = 0; reg->type = SCALAR_VALUE; } @@ -683,9 +865,12 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg) /* Mark a register as having a completely unknown (scalar) value. */ static void __mark_reg_unknown(struct bpf_reg_state *reg) { + /* + * Clear type, id, off, and union(map_ptr, range) and + * padding between 'type' and union + */ + memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; - reg->id = 0; - reg->off = 0; reg->var_off = tnum_unknown; reg->frameno = 0; __mark_reg_unbounded(reg); @@ -732,6 +917,7 @@ static void init_reg_state(struct bpf_verifier_env *env, for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; + regs[i].parent = NULL; } /* frame pointer */ @@ -823,10 +1009,6 @@ static int check_subprogs(struct bpf_verifier_env *env) verbose(env, "function calls to other bpf functions are allowed for root only\n"); return -EPERM; } - if (bpf_prog_is_dev_bound(env->prog->aux)) { - verbose(env, "function calls in offloaded programs are not supported yet\n"); - return -EINVAL; - } ret = add_subprog(env, i + insn[i].imm + 1); if (ret < 0) return ret; @@ -876,74 +1058,21 @@ next: return 0; } -static -struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) -{ - struct bpf_verifier_state *tmp = NULL; - - /* 'parent' could be a state of caller and - * 'state' could be a state of callee. In such case - * parent->curframe < state->curframe - * and it's ok for r1 - r5 registers - * - * 'parent' could be a callee's state after it bpf_exit-ed. - * In such case parent->curframe > state->curframe - * and it's ok for r0 only - */ - if (parent->curframe == state->curframe || - (parent->curframe < state->curframe && - regno >= BPF_REG_1 && regno <= BPF_REG_5) || - (parent->curframe > state->curframe && - regno == BPF_REG_0)) - return parent; - - if (parent->curframe > state->curframe && - regno >= BPF_REG_6) { - /* for callee saved regs we have to skip the whole chain - * of states that belong to callee and mark as LIVE_READ - * the registers before the call - */ - tmp = parent; - while (tmp && tmp->curframe != state->curframe) { - tmp = tmp->parent; - } - if (!tmp) - goto bug; - parent = tmp; - } else { - goto bug; - } - return parent; -bug: - verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp); - verbose(env, "regno %d parent frame %d current frame %d\n", - regno, parent->curframe, state->curframe); - return NULL; -} - +/* Parentage chain of this register (or stack slot) should take care of all + * issues like callee-saved registers, stack slot allocation time, etc. + */ static int mark_reg_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) + const struct bpf_reg_state *state, + struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ - if (regno == BPF_REG_FP) - /* We don't need to worry about FP liveness because it's read-only */ - return 0; - while (parent) { /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN) + if (writes && state->live & REG_LIVE_WRITTEN) break; - parent = skip_callee(env, state, parent, regno); - if (!parent) - return -EFAULT; /* ... then we depend on parent's value */ - parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ; + parent->live |= REG_LIVE_READ; state = parent; parent = state->parent; writes = true; @@ -969,7 +1098,10 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - return mark_reg_read(env, vstate, vstate->parent, regno); + /* We don't need to worry about FP liveness because it's read-only */ + if (regno != BPF_REG_FP) + return mark_reg_read(env, ®s[regno], + regs[regno].parent); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -993,7 +1125,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_PACKET: case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: return true; default: return false; @@ -1018,7 +1153,7 @@ static int check_stack_write(struct bpf_verifier_env *env, enum bpf_reg_type type; err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE), - true); + state->acquired_refs, true); if (err) return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, @@ -1080,8 +1215,8 @@ static int check_stack_write(struct bpf_verifier_env *env, } else { u8 type = STACK_MISC; - /* regular write of data into stack */ - state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; + /* regular write of data into stack destroys any spilled ptr */ + state->stack[spi].spilled_ptr.type = NOT_INIT; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1106,61 +1241,6 @@ static int check_stack_write(struct bpf_verifier_env *env, return 0; } -/* registers of every function are unique and mark_reg_read() propagates - * the liveness in the following cases: - * - from callee into caller for R1 - R5 that were used as arguments - * - from caller into callee for R0 that used as result of the call - * - from caller to the same caller skipping states of the callee for R6 - R9, - * since R6 - R9 are callee saved by implicit function prologue and - * caller's R6 != callee's R6, so when we propagate liveness up to - * parent states we need to skip callee states for R6 - R9. - * - * stack slot marking is different, since stacks of caller and callee are - * accessible in both (since caller can pass a pointer to caller's stack to - * callee which can pass it to another function), hence mark_stack_slot_read() - * has to propagate the stack liveness to all parent states at given frame number. - * Consider code: - * f1() { - * ptr = fp - 8; - * *ptr = ctx; - * call f2 { - * .. = *ptr; - * } - * .. = *ptr; - * } - * First *ptr is reading from f1's stack and mark_stack_slot_read() has - * to mark liveness at the f1's frame and not f2's frame. - * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has - * to propagate liveness to f2 states at f1's frame level and further into - * f1 states at f1's frame level until write into that stack slot - */ -static void mark_stack_slot_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - int slot, int frameno) -{ - bool writes = parent == state->parent; /* Observe write marks */ - - while (parent) { - if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE) - /* since LIVE_WRITTEN mark is only done for full 8-byte - * write the read marks are conservative and parent - * state may not even have the stack allocated. In such case - * end the propagation, since the loop reached beginning - * of the function - */ - break; - /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) - break; - /* ... then we depend on parent's value */ - parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ; - state = parent; - parent = state->parent; - writes = true; - } -} - static int check_stack_read(struct bpf_verifier_env *env, struct bpf_func_state *reg_state /* func where register points to */, int off, int size, int value_regno) @@ -1198,8 +1278,8 @@ static int check_stack_read(struct bpf_verifier_env *env, */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); return 0; } else { int zeros = 0; @@ -1215,8 +1295,8 @@ static int check_stack_read(struct bpf_verifier_env *env, off, i, size); return -EACCES; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, @@ -1307,14 +1387,18 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, enum bpf_access_type t) { switch (env->prog->type) { + /* Program types only with direct read access go here! */ case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_REUSEPORT: - /* dst_input() and dst_output() can't write for now */ + case BPF_PROG_TYPE_FLOW_DISSECTOR: + case BPF_PROG_TYPE_CGROUP_SKB: if (t == BPF_WRITE) return false; /* fallthrough */ + + /* Program types with direct read + write access go here! */ case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: @@ -1404,6 +1488,40 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, return -EACCES; } +static int check_flow_keys_access(struct bpf_verifier_env *env, int off, + int size) +{ + if (size < 0 || off < 0 || + (u64)off + size > sizeof(struct bpf_flow_keys)) { + verbose(env, "invalid access to flow keys off=%d size=%d\n", + off, size); + return -EACCES; + } + return 0; +} + +static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, + int size, enum bpf_access_type t) +{ + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = ®s[regno]; + struct bpf_insn_access_aux info; + + if (reg->smin_value < 0) { + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + regno); + return -EACCES; + } + + if (!bpf_sock_is_valid_access(off, size, t, &info)) { + verbose(env, "invalid bpf_sock access off=%d size=%d\n", + off, size); + return -EACCES; + } + + return 0; +} + static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -1413,25 +1531,39 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno) +{ + return cur_regs(env) + regno; +} + static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { - return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno); + return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno)); } static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { - const struct bpf_reg_state *reg = cur_regs(env) + regno; + const struct bpf_reg_state *reg = reg_state(env, regno); - return reg->type == PTR_TO_CTX; + return reg->type == PTR_TO_CTX || + reg->type == PTR_TO_SOCKET; } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) { - const struct bpf_reg_state *reg = cur_regs(env) + regno; + const struct bpf_reg_state *reg = reg_state(env, regno); return type_is_pkt_pointer(reg->type); } +static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */ + return reg->type == PTR_TO_FLOW_KEYS; +} + static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int off, int size, bool strict) @@ -1505,6 +1637,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, * right in front, treat it the very same way. */ return check_pkt_ptr_alignment(env, reg, off, size, strict); + case PTR_TO_FLOW_KEYS: + pointer_desc = "flow keys "; + break; case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1519,6 +1654,9 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, */ strict = true; break; + case PTR_TO_SOCKET: + pointer_desc = "sock "; + break; default: break; } @@ -1727,9 +1865,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn else mark_reg_known_zero(env, regs, value_regno); - regs[value_regno].id = 0; - regs[value_regno].off = 0; - regs[value_regno].range = 0; regs[value_regno].type = reg_type; } @@ -1778,6 +1913,25 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_packet_access(env, regno, off, size, false); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_FLOW_KEYS) { + if (t == BPF_WRITE && value_regno >= 0 && + is_pointer_value(env, value_regno)) { + verbose(env, "R%d leaks addr into flow keys\n", + value_regno); + return -EACCES; + } + + err = check_flow_keys_access(env, off, size); + if (!err && t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_SOCKET) { + if (t == BPF_WRITE) { + verbose(env, "cannot write into socket\n"); + return -EACCES; + } + err = check_sock_access(env, regno, off, size, t); + if (!err && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str[reg->type]); @@ -1818,10 +1972,11 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins } if (is_ctx_reg(env, insn->dst_reg) || - is_pkt_reg(env, insn->dst_reg)) { + is_pkt_reg(env, insn->dst_reg) || + is_flow_key_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", - insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ? - "context" : "packet"); + insn->dst_reg, + reg_type_str[reg_state(env, insn->dst_reg)->type]); return -EACCES; } @@ -1846,7 +2001,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { - struct bpf_reg_state *reg = cur_regs(env) + regno; + struct bpf_reg_state *reg = reg_state(env, regno); struct bpf_func_state *state = func(env, reg); int off, i, slot, spi; @@ -1908,8 +2063,8 @@ mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ - mark_stack_slot_read(env, env->cur_state, env->cur_state->parent, - spi, state->frameno); + mark_reg_read(env, &state->stack[spi].spilled_ptr, + state->stack[spi].spilled_ptr.parent); } return update_stack_depth(env, state, off); } @@ -1978,7 +2133,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (arg_type == ARG_PTR_TO_MAP_KEY || - arg_type == ARG_PTR_TO_MAP_VALUE) { + arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { expected_type = PTR_TO_STACK; if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) @@ -1999,6 +2155,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCKET) { + expected_type = PTR_TO_SOCKET; + if (type != expected_type) + goto err_type; + if (meta->ptr_id || !reg->id) { + verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n", + meta->ptr_id, reg->id); + return -EFAULT; + } + meta->ptr_id = reg->id; } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2038,7 +2204,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { + } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ @@ -2047,9 +2214,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } + meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, - NULL); + meta); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); @@ -2129,6 +2297,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_MAP_TYPE_CGROUP_STORAGE: + case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: if (func_id != BPF_FUNC_get_local_storage) goto error; break; @@ -2171,6 +2340,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -2219,13 +2395,21 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_get_local_storage: - if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && + map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) goto error; break; case BPF_FUNC_sk_select_reuseport: if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_pop_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK) + goto error; + break; default: break; } @@ -2286,10 +2470,32 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn) return true; } +static bool check_refcount_ok(const struct bpf_func_proto *fn) +{ + int count = 0; + + if (arg_type_is_refcounted(fn->arg1_type)) + count++; + if (arg_type_is_refcounted(fn->arg2_type)) + count++; + if (arg_type_is_refcounted(fn->arg3_type)) + count++; + if (arg_type_is_refcounted(fn->arg4_type)) + count++; + if (arg_type_is_refcounted(fn->arg5_type)) + count++; + + /* We only support one arg being unreferenced at the moment, + * which is sufficient for the helper functions we have right now. + */ + return count <= 1; +} + static int check_func_proto(const struct bpf_func_proto *fn) { return check_raw_mode_ok(fn) && - check_arg_pair_ok(fn) ? 0 : -EINVAL; + check_arg_pair_ok(fn) && + check_refcount_ok(fn) ? 0 : -EINVAL; } /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] @@ -2305,10 +2511,9 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env, if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(env, regs, i); - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg_is_pkt_pointer_any(reg)) __mark_reg_unknown(reg); } @@ -2323,12 +2528,45 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) __clear_all_pkt_pointers(env, vstate->frame[i]); } +static void release_reg_references(struct bpf_verifier_env *env, + struct bpf_func_state *state, int id) +{ + struct bpf_reg_state *regs = state->regs, *reg; + int i; + + for (i = 0; i < MAX_BPF_REG; i++) + if (regs[i].id == id) + mark_reg_unknown(env, regs, i); + + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) + continue; + if (reg_is_refcounted(reg) && reg->id == id) + __mark_reg_unknown(reg); + } +} + +/* The pointer with the specified id has released its reference to kernel + * resources. Identify all copies of the same pointer and clear the reference. + */ +static int release_reference(struct bpf_verifier_env *env, + struct bpf_call_arg_meta *meta) +{ + struct bpf_verifier_state *vstate = env->cur_state; + int i; + + for (i = 0; i <= vstate->curframe; i++) + release_reg_references(env, vstate->frame[i], meta->ptr_id); + + return release_reference_state(env, meta->ptr_id); +} + static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; - int i, subprog, target_insn; + int i, err, subprog, target_insn; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -2366,11 +2604,18 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); - /* copy r1 - r5 args that callee can access */ + /* Transfer references to the callee */ + err = transfer_reference_state(callee, caller); + if (err) + return err; + + /* copy r1 - r5 args that callee can access. The copy includes parent + * pointers, which connects us up to the liveness chain + */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* after the call regsiters r0 - r5 were scratched */ + /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, caller->regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); @@ -2396,6 +2641,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + int err; callee = state->frame[state->curframe]; r0 = &callee->regs[BPF_REG_0]; @@ -2415,6 +2661,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; + /* Transfer references to the caller */ + err = transfer_reference_state(caller, callee); + if (err) + return err; + *insn_idx = callee->callsite + 1; if (env->log.level) { verbose(env, "returning from callee:\n"); @@ -2454,7 +2705,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && - func_id != BPF_FUNC_map_delete_elem) + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_map_push_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_peek_elem) return 0; if (meta->map_ptr == NULL) { @@ -2471,6 +2725,18 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, return 0; } +static int check_reference_leak(struct bpf_verifier_env *env) +{ + struct bpf_func_state *state = cur_func(env); + int i; + + for (i = 0; i < state->acquired_refs; i++) { + verbose(env, "Unreleased reference id=%d alloc_insn=%d\n", + state->refs[i].id, state->refs[i].insn_idx); + } + return state->acquired_refs ? -EINVAL : 0; +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2549,6 +2815,18 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + if (func_id == BPF_FUNC_tail_call) { + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + } else if (is_release_function(func_id)) { + err = release_reference(env, &meta); + if (err) + return err; + } + regs = cur_regs(env); /* check that flags argument in get_local_storage(map, flags) is 0, @@ -2580,7 +2858,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() @@ -2592,6 +2869,13 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].id = ++env->id_gen; + } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + int id = acquire_reference_state(env, insn_idx); + if (id < 0) + return id; + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].id = id; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -2722,20 +3006,20 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); - return -EACCES; - } - if (ptr_reg->type == CONST_PTR_TO_MAP) { - verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); + switch (ptr_reg->type) { + case PTR_TO_MAP_VALUE_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; - } - if (ptr_reg->type == PTR_TO_PACKET_END) { - verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + case CONST_PTR_TO_MAP: + case PTR_TO_PACKET_END: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + verbose(env, "R%d pointer arithmetic on %s prohibited\n", + dst, reg_type_str[ptr_reg->type]); return -EACCES; + default: + break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -2896,6 +3180,15 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, u64 umin_val, umax_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; + if (insn_bitness == 32) { + /* Relevant for 32-bit RSH: Information can propagate towards + * LSB, so it isn't sufficient to only truncate the output to + * 32 bits. + */ + coerce_reg_to_size(dst_reg, 4); + coerce_reg_to_size(&src_reg, 4); + } + smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; @@ -3131,7 +3424,6 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops are (32,32)->32 */ coerce_reg_to_size(dst_reg, 4); - coerce_reg_to_size(&src_reg, 4); } __reg_deduce_bounds(dst_reg); @@ -3447,10 +3739,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - reg = &state->stack[i].spilled_ptr; if (reg->type == type && reg->id == dst_reg->id) reg->range = max(reg->range, new_range); } @@ -3656,12 +3947,11 @@ static void reg_combine_min_max(struct bpf_reg_state *true_src, } } -static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, - bool is_null) +static void mark_ptr_or_null_reg(struct bpf_func_state *state, + struct bpf_reg_state *reg, u32 id, + bool is_null) { - struct bpf_reg_state *reg = ®s[regno]; - - if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) { + if (reg_type_may_be_null(reg->type) && reg->id == id) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer * arithmetic on pointers that might be NULL. @@ -3674,40 +3964,49 @@ static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id, } if (is_null) { reg->type = SCALAR_VALUE; - } else if (reg->map_ptr->inner_map_meta) { - reg->type = CONST_PTR_TO_MAP; - reg->map_ptr = reg->map_ptr->inner_map_meta; - } else { - reg->type = PTR_TO_MAP_VALUE; + } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) { + if (reg->map_ptr->inner_map_meta) { + reg->type = CONST_PTR_TO_MAP; + reg->map_ptr = reg->map_ptr->inner_map_meta; + } else { + reg->type = PTR_TO_MAP_VALUE; + } + } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { + reg->type = PTR_TO_SOCKET; + } + if (is_null || !reg_is_refcounted(reg)) { + /* We don't need id from this point onwards anymore, + * thus we should better reset it, so that state + * pruning has chances to take effect. + */ + reg->id = 0; } - /* We don't need id from this point onwards anymore, thus we - * should better reset it, so that state pruning has chances - * to take effect. - */ - reg->id = 0; } } /* The logic is similar to find_good_pkt_pointers(), both could eventually * be folded together at some point. */ -static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno, - bool is_null) +static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, + bool is_null) { struct bpf_func_state *state = vstate->frame[vstate->curframe]; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *reg, *regs = state->regs; u32 id = regs[regno].id; int i, j; + if (reg_is_refcounted_or_null(®s[regno]) && is_null) + __release_reference_state(state, id); + for (i = 0; i < MAX_BPF_REG; i++) - mark_map_reg(regs, i, id, is_null); + mark_ptr_or_null_reg(state, ®s[i], id, is_null); for (j = 0; j <= vstate->curframe; j++) { state = vstate->frame[j]; - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) + bpf_for_each_spilled_reg(i, state, reg) { + if (!reg) continue; - mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + mark_ptr_or_null_reg(state, reg, id, is_null); } } } @@ -3909,12 +4208,14 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */ if (BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - /* Mark all identical map registers in each branch as either + reg_type_may_be_null(dst_reg->type)) { + /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ - mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); - mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); + mark_ptr_or_null_regs(this_branch, insn->dst_reg, + opcode == BPF_JNE); + mark_ptr_or_null_regs(other_branch, insn->dst_reg, + opcode == BPF_JEQ); } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], this_branch, other_branch) && is_pointer_value(env, insn->dst_reg)) { @@ -4037,6 +4338,16 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) if (err) return err; + /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as + * gen_ld_abs() may terminate the program at runtime, leading to + * reference leak. + */ + err = check_reference_leak(env); + if (err) { + verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n"); + return err; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -4370,7 +4681,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, /* explored state didn't use this */ return true; - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0; + equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to @@ -4451,6 +4762,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_CTX: case CONST_PTR_TO_MAP: case PTR_TO_PACKET_END: + case PTR_TO_FLOW_KEYS: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -4526,6 +4840,14 @@ static bool stacksafe(struct bpf_func_state *old, return true; } +static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +{ + if (old->acquired_refs != cur->acquired_refs) + return false; + return !memcmp(old->refs, cur->refs, + sizeof(*old->refs) * old->acquired_refs); +} + /* compare two verifier states * * all states stored in state_list are known to be valid, since @@ -4571,6 +4893,9 @@ static bool func_states_equal(struct bpf_func_state *old, if (!stacksafe(old, cur, idmap)) goto out_free; + + if (!refsafe(old, cur)) + goto out_free; ret = true; out_free: kfree(idmap); @@ -4603,7 +4928,7 @@ static bool states_equal(struct bpf_verifier_env *env, * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison - * in mark_reg_read() and mark_stack_slot_read() is for. + * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, @@ -4624,7 +4949,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) continue; if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, vstate, vparent, i); + err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], + &vparent->frame[vstate->curframe]->regs[i]); if (err) return err; } @@ -4639,7 +4965,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) continue; if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) - mark_stack_slot_read(env, vstate, vparent, i, frame); + mark_reg_read(env, &state->stack[i].spilled_ptr, + &parent->stack[i].spilled_ptr); } } return err; @@ -4649,7 +4976,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; - struct bpf_verifier_state *cur = env->cur_state; + struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err; sl = env->explored_states[insn_idx]; @@ -4691,16 +5018,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return -ENOMEM; /* add new state to the head of linked list */ - err = copy_verifier_state(&new_sl->state, cur); + new = &new_sl->state; + err = copy_verifier_state(new, cur); if (err) { - free_verifier_state(&new_sl->state, false); + free_verifier_state(new, false); kfree(new_sl); return err; } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; /* connect new state to parentage chain */ - cur->parent = &new_sl->state; + for (i = 0; i < BPF_REG_FP; i++) + cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -4713,13 +5042,48 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; + struct bpf_func_state *newframe = new->frame[j]; - for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) + for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; + frame->stack[i].spilled_ptr.parent = + &newframe->stack[i].spilled_ptr; + } } return 0; } +/* Return true if it's OK to have the same insn return a different type. */ +static bool reg_type_mismatch_ok(enum bpf_reg_type type) +{ + switch (type) { + case PTR_TO_CTX: + case PTR_TO_SOCKET: + case PTR_TO_SOCKET_OR_NULL: + return false; + default: + return true; + } +} + +/* If an instruction was previously used with particular pointer types, then we + * need to be careful to avoid cases such as the below, where it may be ok + * for one branch accessing the pointer, but not ok for the other branch: + * + * R1 = sock_ptr + * goto X; + * ... + * R1 = some_other_valid_ptr; + * goto X; + * ... + * R2 = *(u32 *)(R1 + 0); + */ +static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) +{ + return src != prev && (!reg_type_mismatch_ok(src) || + !reg_type_mismatch_ok(prev)); +} + static int do_check(struct bpf_verifier_env *env) { struct bpf_verifier_state *state; @@ -4734,7 +5098,6 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; - state->parent = NULL; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); @@ -4814,6 +5177,7 @@ static int do_check(struct bpf_verifier_env *env) regs = cur_regs(env); env->insn_aux_data[insn_idx].seen = true; + if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -4853,9 +5217,7 @@ static int do_check(struct bpf_verifier_env *env) */ *prev_src_type = src_reg_type; - } else if (src_reg_type != *prev_src_type && - (src_reg_type == PTR_TO_CTX || - *prev_src_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) { /* ABuser program is trying to use the same insn * dst_reg = *(u32*) (src_reg + off) * with different pointer types: @@ -4900,9 +5262,7 @@ static int do_check(struct bpf_verifier_env *env) if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; - } else if (dst_reg_type != *prev_dst_type && - (dst_reg_type == PTR_TO_CTX || - *prev_dst_type == PTR_TO_CTX)) { + } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) { verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -4919,8 +5279,9 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_ctx_reg(env, insn->dst_reg)) { - verbose(env, "BPF_ST stores into R%d context is not allowed\n", - insn->dst_reg); + verbose(env, "BPF_ST stores into R%d %s is not allowed\n", + insn->dst_reg, + reg_type_str[reg_state(env, insn->dst_reg)->type]); return -EACCES; } @@ -4982,6 +5343,10 @@ static int do_check(struct bpf_verifier_env *env) continue; } + err = check_reference_leak(env); + if (err) + return err; + /* eBPF calling convetion is such that R0 is used * to return the value from eBPF program. * Make sure that it's readable at this time @@ -5095,6 +5460,12 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return 0; } +static bool bpf_map_is_cgroup_storage(struct bpf_map *map) +{ + return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE || + map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE); +} + /* look for pseudo eBPF instructions that access map FDs and * replace them with actual map pointers */ @@ -5185,10 +5556,9 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) } env->used_maps[env->used_map_cnt++] = map; - if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE && + if (bpf_map_is_cgroup_storage(map) && bpf_cgroup_storage_assign(env->prog, map)) { - verbose(env, - "only one cgroup storage is allowed\n"); + verbose(env, "only one cgroup storage of each type is allowed\n"); fdput(f); return -EBUSY; } @@ -5217,11 +5587,15 @@ next_insn: /* drop refcnt of maps used by the rejected program */ static void release_maps(struct bpf_verifier_env *env) { + enum bpf_cgroup_storage_type stype; int i; - if (env->prog->aux->cgroup_storage) + for_each_cgroup_storage_type(stype) { + if (!env->prog->aux->cgroup_storage[stype]) + continue; bpf_cgroup_storage_release(env->prog, - env->prog->aux->cgroup_storage); + env->prog->aux->cgroup_storage[stype]); + } for (i = 0; i < env->used_map_cnt; i++) bpf_map_put(env->used_maps[i]); @@ -5319,8 +5693,10 @@ static void sanitize_dead_code(struct bpf_verifier_env *env) } } -/* convert load instructions that access fields of 'struct __sk_buff' - * into sequence of instructions that access fields of 'struct sk_buff' +/* convert load instructions that access fields of a context type into a + * sequence of instructions that access fields of the underlying structure: + * struct __sk_buff -> struct sk_buff + * struct bpf_sock_ops -> struct sock */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { @@ -5333,7 +5709,11 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) bool is_narrower_load; u32 target_size; - if (ops->gen_prologue) { + if (ops->gen_prologue || env->seen_direct_write) { + if (!ops->gen_prologue) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { @@ -5349,12 +5729,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_dev_bound(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; for (i = 0; i < insn_cnt; i++, insn++) { + bpf_convert_ctx_access_t convert_ctx_access; + if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) || insn->code == (BPF_LDX | BPF_MEM | BPF_H) || insn->code == (BPF_LDX | BPF_MEM | BPF_W) || @@ -5396,8 +5778,18 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) continue; } - if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX) + switch (env->insn_aux_data[i + delta].ptr_type) { + case PTR_TO_CTX: + if (!ops->convert_ctx_access) + continue; + convert_ctx_access = ops->convert_ctx_access; + break; + case PTR_TO_SOCKET: + convert_ctx_access = bpf_sock_convert_ctx_access; + break; + default: continue; + } ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size; size = BPF_LDST_BYTES(insn); @@ -5429,8 +5821,8 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } target_size = 0; - cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog, - &target_size); + cnt = convert_ctx_access(type, insn, insn_buf, env->prog, + &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { verbose(env, "bpf verifier is misconfigured\n"); @@ -5621,10 +6013,10 @@ static int fixup_call_args(struct bpf_verifier_env *env) struct bpf_insn *insn = prog->insnsi; int i, depth; #endif - int err; + int err = 0; - err = 0; - if (env->prog->jit_requested) { + if (env->prog->jit_requested && + !bpf_prog_is_dev_bound(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; @@ -5793,7 +6185,10 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) if (prog->jit_requested && BITS_PER_LONG == 64 && (insn->imm == BPF_FUNC_map_lookup_elem || insn->imm == BPF_FUNC_map_update_elem || - insn->imm == BPF_FUNC_map_delete_elem)) { + insn->imm == BPF_FUNC_map_delete_elem || + insn->imm == BPF_FUNC_map_push_elem || + insn->imm == BPF_FUNC_map_pop_elem || + insn->imm == BPF_FUNC_map_peek_elem)) { aux = &env->insn_aux_data[i + delta]; if (bpf_map_ptr_poisoned(aux)) goto patch_call_imm; @@ -5826,6 +6221,14 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) BUILD_BUG_ON(!__same_type(ops->map_update_elem, (int (*)(struct bpf_map *map, void *key, void *value, u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_push_elem, + (int (*)(struct bpf_map *map, void *value, + u64 flags))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_pop_elem, + (int (*)(struct bpf_map *map, void *value))NULL)); + BUILD_BUG_ON(!__same_type(ops->map_peek_elem, + (int (*)(struct bpf_map *map, void *value))NULL)); + switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - @@ -5839,6 +6242,18 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - __bpf_call_base; continue; + case BPF_FUNC_map_push_elem: + insn->imm = BPF_CAST_CALL(ops->map_push_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_pop_elem: + insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - + __bpf_call_base; + continue; + case BPF_FUNC_map_peek_elem: + insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - + __bpf_call_base; + continue; } goto patch_call_imm; @@ -5962,6 +6377,9 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->cur_state = NULL; } + if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + ret = bpf_prog_offload_finalize(env); + skip_full_check: while (!pop_stack(env, NULL, NULL)); free_states(env); diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 9f8463afda9c..686d244e798d 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -154,7 +154,7 @@ void __xsk_map_flush(struct bpf_map *map) static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { - return NULL; + return ERR_PTR(-EOPNOTSUPP); } static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, @@ -192,11 +192,8 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, sock_hold(sock->sk); old_xs = xchg(&m->xsk_map[i], xs); - if (old_xs) { - /* Make sure we've flushed everything. */ - synchronize_net(); + if (old_xs) sock_put((struct sock *)old_xs); - } sockfd_put(sock); return 0; @@ -212,11 +209,8 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; old_xs = xchg(&m->xsk_map[k], NULL); - if (old_xs) { - /* Make sure we've flushed everything. */ - synchronize_net(); + if (old_xs) sock_put((struct sock *)old_xs); - } return 0; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index aae10baf1902..8b79318810ad 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -55,6 +55,7 @@ #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/sched/cputime.h> +#include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS @@ -492,7 +493,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, } /** - * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem + * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * @@ -501,8 +502,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ -static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, - struct cgroup_subsys *ss) +static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, + struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); @@ -523,6 +524,35 @@ static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, } /** + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem + * @cgrp: the cgroup of interest + * @ss: the subsystem of interest + * + * Find and get the effective css of @cgrp for @ss. The effective css is + * defined as the matching css of the nearest ancestor including self which + * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, + * the root css is returned, so this function always returns a valid css. + * + * The returned css is not guaranteed to be online, and therefore it is the + * callers responsiblity to tryget a reference for it. + */ +struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) +{ + struct cgroup_subsys_state *css; + + do { + css = cgroup_css(cgrp, ss); + + if (css) + return css; + cgrp = cgroup_parent(cgrp); + } while (cgrp); + + return init_css_set.subsys[ss->id]; +} + +/** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest @@ -604,10 +634,11 @@ EXPORT_SYMBOL_GPL(of_css); * * Should be called under cgroup_[tree_]mutex. */ -#define for_each_e_css(css, ssid, cgrp) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ - ; \ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css_by_mask(cgrp, \ + cgroup_subsys[(ssid)]))) \ + ; \ else /** @@ -832,7 +863,7 @@ static void css_set_move_task(struct task_struct *task, */ WARN_ON_ONCE(task->flags & PF_EXITING); - rcu_assign_pointer(task->cgroups, to_cset); + cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } @@ -1006,7 +1037,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ - template[i] = cgroup_e_css(cgrp, ss); + template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want @@ -2836,11 +2867,12 @@ restart: } /** - * cgroup_save_control - save control masks of a subtree + * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * - * Save ->subtree_control and ->subtree_ss_mask to the respective old_ - * prefixed fields for @cgrp's subtree including @cgrp itself. + * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the + * respective old_ prefixed fields for @cgrp's subtree including @cgrp + * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { @@ -2850,6 +2882,7 @@ static void cgroup_save_control(struct cgroup *cgrp) cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; + dsct->old_dom_cgrp = dsct->dom_cgrp; } } @@ -2875,11 +2908,12 @@ static void cgroup_propagate_control(struct cgroup *cgrp) } /** - * cgroup_restore_control - restore control masks of a subtree + * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * - * Restore ->subtree_control and ->subtree_ss_mask from the respective old_ - * prefixed fields for @cgrp's subtree including @cgrp itself. + * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the + * respective old_ prefixed fields for @cgrp's subtree including @cgrp + * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { @@ -2889,6 +2923,7 @@ static void cgroup_restore_control(struct cgroup *cgrp) cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; + dsct->dom_cgrp = dsct->old_dom_cgrp; } } @@ -3019,7 +3054,7 @@ static int cgroup_apply_control(struct cgroup *cgrp) return ret; /* - * At this point, cgroup_e_css() results reflect the new csses + * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ @@ -3196,6 +3231,8 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; + struct cgroup *dsct; + struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); @@ -3225,12 +3262,13 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) */ cgroup_save_control(cgrp); - cgrp->dom_cgrp = dom_cgrp; + cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) + if (dsct == cgrp || cgroup_is_threaded(dsct)) + dsct->dom_cgrp = dom_cgrp; + ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; - else - cgrp->dom_cgrp = cgrp; cgroup_finalize_control(cgrp, ret); return ret; @@ -3409,6 +3447,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) return ret; } +#ifdef CONFIG_PSI +static int cgroup_io_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_IO); +} +static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_MEM); +} +static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) +{ + return psi_show(seq, &seq_css(seq)->cgroup->psi, PSI_CPU); +} +#endif + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4539,6 +4592,23 @@ static struct cftype cgroup_base_files[] = { .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cpu_stat_show, }, +#ifdef CONFIG_PSI + { + .name = "io.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_io_pressure_show, + }, + { + .name = "memory.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_memory_pressure_show, + }, + { + .name = "cpu.pressure", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_cpu_pressure_show, + }, +#endif { } /* terminate */ }; @@ -4599,6 +4669,7 @@ static void css_free_rwork_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + psi_cgroup_free(cgrp); if (cgroup_on_dfl(cgrp)) cgroup_rstat_exit(cgrp); kfree(cgrp); @@ -4855,10 +4926,15 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; - ret = cgroup_bpf_inherit(cgrp); + + ret = psi_cgroup_alloc(cgrp); if (ret) goto out_idr_free; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_psi_free; + for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4896,6 +4972,8 @@ static struct cgroup *cgroup_create(struct cgroup *parent) return cgrp; +out_psi_free: + psi_cgroup_free(cgrp); out_idr_free: cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_stat_exit: diff --git a/kernel/compat.c b/kernel/compat.c index 8e40efc2928a..089d00d0da9c 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -93,28 +93,28 @@ int compat_put_timex(struct compat_timex __user *utp, const struct timex *txc) return 0; } -static int __compat_get_timeval(struct timeval *tv, const struct compat_timeval __user *ctv) +static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) { return (!access_ok(VERIFY_READ, ctv, sizeof(*ctv)) || __get_user(tv->tv_sec, &ctv->tv_sec) || __get_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } -static int __compat_put_timeval(const struct timeval *tv, struct compat_timeval __user *ctv) +static int __compat_put_timeval(const struct timeval *tv, struct old_timeval32 __user *ctv) { return (!access_ok(VERIFY_WRITE, ctv, sizeof(*ctv)) || __put_user(tv->tv_sec, &ctv->tv_sec) || __put_user(tv->tv_usec, &ctv->tv_usec)) ? -EFAULT : 0; } -static int __compat_get_timespec(struct timespec *ts, const struct compat_timespec __user *cts) +static int __compat_get_timespec(struct timespec *ts, const struct old_timespec32 __user *cts) { return (!access_ok(VERIFY_READ, cts, sizeof(*cts)) || __get_user(ts->tv_sec, &cts->tv_sec) || __get_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; } -static int __compat_put_timespec(const struct timespec *ts, struct compat_timespec __user *cts) +static int __compat_put_timespec(const struct timespec *ts, struct old_timespec32 __user *cts) { return (!access_ok(VERIFY_WRITE, cts, sizeof(*cts)) || __put_user(ts->tv_sec, &cts->tv_sec) || diff --git a/kernel/cpu.c b/kernel/cpu.c index 0097acec1c71..3c7f3b4c453c 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -315,6 +315,16 @@ void lockdep_assert_cpus_held(void) percpu_rwsem_assert_held(&cpu_hotplug_lock); } +static void lockdep_acquire_cpus_lock(void) +{ + rwsem_acquire(&cpu_hotplug_lock.rw_sem.dep_map, 0, 0, _THIS_IP_); +} + +static void lockdep_release_cpus_lock(void) +{ + rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, 1, _THIS_IP_); +} + /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects @@ -344,6 +354,17 @@ void cpu_hotplug_enable(void) cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); + +#else + +static void lockdep_acquire_cpus_lock(void) +{ +} + +static void lockdep_release_cpus_lock(void) +{ +} + #endif /* CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_HOTPLUG_SMT @@ -362,6 +383,7 @@ void __init cpu_smt_disable(bool force) pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { + pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } } @@ -616,6 +638,12 @@ static void cpuhp_thread_fun(unsigned int cpu) */ smp_mb(); + /* + * The BP holds the hotplug lock, but we're now running on the AP, + * ensure that anybody asserting the lock is held, will actually find + * it so. + */ + lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { @@ -661,6 +689,7 @@ static void cpuhp_thread_fun(unsigned int cpu) } cpuhp_lock_release(bringup); + lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); @@ -2026,6 +2055,12 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } +/* + * Architectures that need SMT-specific errata handling during SMT hotplug + * should override this. + */ +void __weak arch_smt_update(void) { }; + static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; @@ -2052,8 +2087,10 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) */ cpuhp_offline_cpu_device(cpu); } - if (!ret) + if (!ret) { cpu_smt_control = ctrlval; + arch_smt_update(); + } cpu_maps_update_done(); return ret; } @@ -2064,6 +2101,7 @@ static int cpuhp_smt_enable(void) cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; + arch_smt_update(); for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 2ddfce8f1e8f..bb4fe4e1a601 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -2556,16 +2556,11 @@ static int kdb_summary(int argc, const char **argv) } kdb_printf("%02ld:%02ld\n", val.uptime/(60*60), (val.uptime/60)%60); - /* lifted from fs/proc/proc_misc.c::loadavg_read_proc() */ - -#define LOAD_INT(x) ((x) >> FSHIFT) -#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) kdb_printf("load avg %ld.%02ld %ld.%02ld %ld.%02ld\n", LOAD_INT(val.loads[0]), LOAD_FRAC(val.loads[0]), LOAD_INT(val.loads[1]), LOAD_FRAC(val.loads[1]), LOAD_INT(val.loads[2]), LOAD_FRAC(val.loads[2])); -#undef LOAD_INT -#undef LOAD_FRAC + /* Display in kilobytes */ #define K(x) ((x) << (PAGE_SHIFT - 10)) kdb_printf("\nMemTotal: %8lu kB\nMemFree: %8lu kB\n" diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac2824f0b..2a12b988c717 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) ¤t->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->thrashing_start, + ¤t->delays->thrashing_delay, + ¤t->delays->thrashing_count); +} diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig index 9bd54304446f..645c7a2ecde8 100644 --- a/kernel/dma/Kconfig +++ b/kernel/dma/Kconfig @@ -13,6 +13,9 @@ config NEED_DMA_MAP_STATE config ARCH_DMA_ADDR_T_64BIT def_bool 64BIT || PHYS_ADDR_T_64BIT +config ARCH_HAS_DMA_COHERENCE_H + bool + config HAVE_GENERIC_DMA_COHERENT bool @@ -23,22 +26,22 @@ config ARCH_HAS_SYNC_DMA_FOR_CPU bool select NEED_DMA_MAP_STATE -config DMA_DIRECT_OPS +config ARCH_HAS_SYNC_DMA_FOR_CPU_ALL bool - depends on HAS_DMA -config DMA_NONCOHERENT_OPS +config ARCH_HAS_DMA_COHERENT_TO_PFN bool - depends on HAS_DMA - select DMA_DIRECT_OPS -config DMA_NONCOHERENT_MMAP +config ARCH_HAS_DMA_MMAP_PGPROT bool - depends on DMA_NONCOHERENT_OPS + +config DMA_DIRECT_OPS + bool + depends on HAS_DMA config DMA_NONCOHERENT_CACHE_SYNC bool - depends on DMA_NONCOHERENT_OPS + depends on DMA_DIRECT_OPS config DMA_VIRT_OPS bool diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile index 6de44e4eb454..7d581e4eea4a 100644 --- a/kernel/dma/Makefile +++ b/kernel/dma/Makefile @@ -4,7 +4,6 @@ obj-$(CONFIG_HAS_DMA) += mapping.o obj-$(CONFIG_DMA_CMA) += contiguous.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o -obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o obj-$(CONFIG_DMA_VIRT_OPS) += virt.o obj-$(CONFIG_DMA_API_DEBUG) += debug.o obj-$(CONFIG_SWIOTLB) += swiotlb.o diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index 286d82329eb0..b2a87905846d 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -49,7 +49,11 @@ static phys_addr_t limit_cmdline; static int __init early_cma(char *p) { - pr_debug("%s(%s)\n", __func__, p); + if (!p) { + pr_err("Config string not provided\n"); + return -EINVAL; + } + size_cmdline = memparse(p, &p); if (*p != '@') return 0; diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index c007d25bee09..231ca4628062 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -1312,6 +1312,22 @@ static void check_sg_segment(struct device *dev, struct scatterlist *sg) #endif } +void debug_dma_map_single(struct device *dev, const void *addr, + unsigned long len) +{ + if (unlikely(dma_debug_disabled())) + return; + + if (!virt_addr_valid(addr)) + err_printk(dev, NULL, "DMA-API: device driver maps memory from invalid area [addr=%p] [len=%lu]\n", + addr, len); + + if (is_vmalloc_addr(addr)) + err_printk(dev, NULL, "DMA-API: device driver maps memory from vmalloc area [addr=%p] [len=%lu]\n", + addr, len); +} +EXPORT_SYMBOL(debug_dma_map_single); + void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, int direction, dma_addr_t dma_addr, bool map_single) diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index de87b0282e74..f14c376937e5 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -1,18 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 /* - * DMA operations that map physical memory directly without using an IOMMU or - * flushing caches. + * Copyright (C) 2018 Christoph Hellwig. + * + * DMA operations that map physical memory directly without using an IOMMU. */ +#include <linux/bootmem.h> /* for max_pfn */ #include <linux/export.h> #include <linux/mm.h> #include <linux/dma-direct.h> #include <linux/scatterlist.h> #include <linux/dma-contiguous.h> +#include <linux/dma-noncoherent.h> #include <linux/pfn.h> #include <linux/set_memory.h> -#define DIRECT_MAPPING_ERROR 0 - /* * Most architectures use ZONE_DMA for the first 16 Megabytes, but * some use it for entirely different regions: @@ -41,40 +42,83 @@ check_addr(struct device *dev, dma_addr_t dma_addr, size_t size, return false; } - if (*dev->dma_mask >= DMA_BIT_MASK(32)) { + if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_mask) { dev_err(dev, - "%s: overflow %pad+%zu of device mask %llx\n", - caller, &dma_addr, size, *dev->dma_mask); + "%s: overflow %pad+%zu of device mask %llx bus mask %llx\n", + caller, &dma_addr, size, + *dev->dma_mask, dev->bus_dma_mask); } return false; } return true; } +static inline dma_addr_t phys_to_dma_direct(struct device *dev, + phys_addr_t phys) +{ + if (force_dma_unencrypted()) + return __phys_to_dma(dev, phys); + return phys_to_dma(dev, phys); +} + +u64 dma_direct_get_required_mask(struct device *dev) +{ + u64 max_dma = phys_to_dma_direct(dev, (max_pfn - 1) << PAGE_SHIFT); + + if (dev->bus_dma_mask && dev->bus_dma_mask < max_dma) + max_dma = dev->bus_dma_mask; + + return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; +} + +static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, + u64 *phys_mask) +{ + if (dev->bus_dma_mask && dev->bus_dma_mask < dma_mask) + dma_mask = dev->bus_dma_mask; + + if (force_dma_unencrypted()) + *phys_mask = __dma_to_phys(dev, dma_mask); + else + *phys_mask = dma_to_phys(dev, dma_mask); + + /* + * Optimistically try the zone that the physical address mask falls + * into first. If that returns memory that isn't actually addressable + * we will fallback to the next lower zone and try again. + * + * Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding + * zones. + */ + if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + return GFP_DMA; + if (*phys_mask <= DMA_BIT_MASK(32)) + return GFP_DMA32; + return 0; +} + static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { - dma_addr_t addr = force_dma_unencrypted() ? - __phys_to_dma(dev, phys) : phys_to_dma(dev, phys); - return addr + size - 1 <= dev->coherent_dma_mask; + return phys_to_dma_direct(dev, phys) + size - 1 <= + min_not_zero(dev->coherent_dma_mask, dev->bus_dma_mask); } -void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) +void *dma_direct_alloc_pages(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; int page_order = get_order(size); struct page *page = NULL; + u64 phys_mask; void *ret; + if (attrs & DMA_ATTR_NO_WARN) + gfp |= __GFP_NOWARN; + /* we always manually zero the memory once we are done: */ gfp &= ~__GFP_ZERO; - - /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */ - if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) - gfp |= GFP_DMA; - if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) - gfp |= GFP_DMA32; - + gfp |= __dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); again: /* CMA can be used only in the context which permits sleeping */ if (gfpflags_allow_blocking(gfp)) { @@ -93,15 +137,14 @@ again: page = NULL; if (IS_ENABLED(CONFIG_ZONE_DMA32) && - dev->coherent_dma_mask < DMA_BIT_MASK(64) && + phys_mask < DMA_BIT_MASK(64) && !(gfp & (GFP_DMA32 | GFP_DMA))) { gfp |= GFP_DMA32; goto again; } if (IS_ENABLED(CONFIG_ZONE_DMA) && - dev->coherent_dma_mask < DMA_BIT_MASK(32) && - !(gfp & GFP_DMA)) { + phys_mask < DMA_BIT_MASK(32) && !(gfp & GFP_DMA)) { gfp = (gfp & ~GFP_DMA32) | GFP_DMA; goto again; } @@ -124,7 +167,7 @@ again: * NOTE: this function must never look at the dma_addr argument, because we want * to be able to use it as a helper for iommu implementations as well. */ -void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, +void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; @@ -136,14 +179,96 @@ void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, free_pages((unsigned long)cpu_addr, page_order); } +void *dma_direct_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); + return dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); +} + +void dma_direct_free(struct device *dev, size_t size, + void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) +{ + if (!dev_is_dma_coherent(dev)) + arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); + else + dma_direct_free_pages(dev, size, cpu_addr, dma_addr, attrs); +} + +static void dma_direct_sync_single_for_device(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + if (dev_is_dma_coherent(dev)) + return; + arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); +} + +static void dma_direct_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (dev_is_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); +} + +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) +static void dma_direct_sync_single_for_cpu(struct device *dev, + dma_addr_t addr, size_t size, enum dma_data_direction dir) +{ + if (dev_is_dma_coherent(dev)) + return; + arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); + arch_sync_dma_for_cpu_all(dev); +} + +static void dma_direct_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nents, enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (dev_is_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nents, i) + arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); + arch_sync_dma_for_cpu_all(dev); +} + +static void dma_direct_unmap_page(struct device *dev, dma_addr_t addr, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_cpu(dev, addr, size, dir); +} + +static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, + int nents, enum dma_data_direction dir, unsigned long attrs) +{ + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_sg_for_cpu(dev, sgl, nents, dir); +} +#endif + dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) { - dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset; + phys_addr_t phys = page_to_phys(page) + offset; + dma_addr_t dma_addr = phys_to_dma(dev, phys); if (!check_addr(dev, dma_addr, size, __func__)) return DIRECT_MAPPING_ERROR; + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_single_for_device(dev, dma_addr, size, dir); return dma_addr; } @@ -162,31 +287,29 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, sg_dma_len(sg) = sg->length; } + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + dma_direct_sync_sg_for_device(dev, sgl, nents, dir); return nents; } +/* + * Because 32-bit DMA masks are so common we expect every architecture to be + * able to satisfy them - either by not supporting more physical memory, or by + * providing a ZONE_DMA32. If neither is the case, the architecture needs to + * use an IOMMU instead of the direct mapping. + */ int dma_direct_supported(struct device *dev, u64 mask) { -#ifdef CONFIG_ZONE_DMA - if (mask < phys_to_dma(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))) - return 0; -#else - /* - * Because 32-bit DMA masks are so common we expect every architecture - * to be able to satisfy them - either by not supporting more physical - * memory, or by providing a ZONE_DMA32. If neither is the case, the - * architecture needs to use an IOMMU instead of the direct mapping. - */ - if (mask < phys_to_dma(dev, DMA_BIT_MASK(32))) - return 0; -#endif - /* - * Upstream PCI/PCIe bridges or SoC interconnects may not carry - * as many DMA address bits as the device itself supports. - */ - if (dev->bus_dma_mask && mask > dev->bus_dma_mask) - return 0; - return 1; + u64 min_mask; + + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS); + else + min_mask = DMA_BIT_MASK(32); + + min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); + + return mask >= phys_to_dma(dev, min_mask); } int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr) @@ -199,7 +322,20 @@ const struct dma_map_ops dma_direct_ops = { .free = dma_direct_free, .map_page = dma_direct_map_page, .map_sg = dma_direct_map_sg, +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) + .sync_single_for_device = dma_direct_sync_single_for_device, + .sync_sg_for_device = dma_direct_sync_sg_for_device, +#endif +#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ + defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) + .sync_single_for_cpu = dma_direct_sync_single_for_cpu, + .sync_sg_for_cpu = dma_direct_sync_sg_for_cpu, + .unmap_page = dma_direct_unmap_page, + .unmap_sg = dma_direct_unmap_sg, +#endif + .get_required_mask = dma_direct_get_required_mask, .dma_supported = dma_direct_supported, .mapping_error = dma_direct_mapping_error, + .cache_sync = arch_dma_cache_sync, }; EXPORT_SYMBOL(dma_direct_ops); diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index d2a92ddaac4d..58dec7a92b7b 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -7,7 +7,7 @@ */ #include <linux/acpi.h> -#include <linux/dma-mapping.h> +#include <linux/dma-noncoherent.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/of_device.h> @@ -202,17 +202,26 @@ EXPORT_SYMBOL(dmam_release_declared_memory); * Create scatter-list for the already allocated DMA buffer. */ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t handle, size_t size) + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) { - struct page *page = virt_to_page(cpu_addr); + struct page *page; int ret; - ret = sg_alloc_table(sgt, 1, GFP_KERNEL); - if (unlikely(ret)) - return ret; + if (!dev_is_dma_coherent(dev)) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) + return -ENXIO; - sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); - return 0; + page = pfn_to_page(arch_dma_coherent_to_pfn(dev, cpu_addr, + dma_addr)); + } else { + page = virt_to_page(cpu_addr); + } + + ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + if (!ret) + sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0); + return ret; } EXPORT_SYMBOL(dma_common_get_sgtable); @@ -220,27 +229,37 @@ EXPORT_SYMBOL(dma_common_get_sgtable); * Create userspace mapping for the DMA-coherent memory. */ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) + void *cpu_addr, dma_addr_t dma_addr, size_t size, + unsigned long attrs) { - int ret = -ENXIO; #ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP unsigned long user_count = vma_pages(vma); unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + unsigned long pfn; + int ret = -ENXIO; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs); if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; - if (off < count && user_count <= (count - off)) - ret = remap_pfn_range(vma, vma->vm_start, - page_to_pfn(virt_to_page(cpu_addr)) + off, - user_count << PAGE_SHIFT, - vma->vm_page_prot); -#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ + if (off >= count || user_count > count - off) + return -ENXIO; - return ret; + if (!dev_is_dma_coherent(dev)) { + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_COHERENT_TO_PFN)) + return -ENXIO; + pfn = arch_dma_coherent_to_pfn(dev, cpu_addr, dma_addr); + } else { + pfn = page_to_pfn(virt_to_page(cpu_addr)); + } + + return remap_pfn_range(vma, vma->vm_start, pfn + vma->vm_pgoff, + user_count << PAGE_SHIFT, vma->vm_page_prot); +#else + return -ENXIO; +#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */ } EXPORT_SYMBOL(dma_common_mmap); @@ -327,19 +346,3 @@ void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags) vunmap(cpu_addr); } #endif - -/* - * enables DMA API use for a device - */ -int dma_configure(struct device *dev) -{ - if (dev->bus->dma_configure) - return dev->bus->dma_configure(dev); - return 0; -} - -void dma_deconfigure(struct device *dev) -{ - of_dma_deconfigure(dev); - acpi_dma_deconfigure(dev); -} diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c deleted file mode 100644 index 031fe235d958..000000000000 --- a/kernel/dma/noncoherent.c +++ /dev/null @@ -1,106 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2018 Christoph Hellwig. - * - * DMA operations that map physical memory directly without providing cache - * coherence. - */ -#include <linux/export.h> -#include <linux/mm.h> -#include <linux/dma-direct.h> -#include <linux/dma-noncoherent.h> -#include <linux/scatterlist.h> - -static void dma_noncoherent_sync_single_for_device(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir); -} - -static void dma_noncoherent_sync_sg_for_device(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir); -} - -static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - dma_addr_t addr; - - addr = dma_direct_map_page(dev, page, offset, size, dir, attrs); - if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - arch_sync_dma_for_device(dev, page_to_phys(page) + offset, - size, dir); - return addr; -} - -static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs); - if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir); - return nents; -} - -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) -static void dma_noncoherent_sync_single_for_cpu(struct device *dev, - dma_addr_t addr, size_t size, enum dma_data_direction dir) -{ - arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir); - arch_sync_dma_for_cpu_all(dev); -} - -static void dma_noncoherent_sync_sg_for_cpu(struct device *dev, - struct scatterlist *sgl, int nents, enum dma_data_direction dir) -{ - struct scatterlist *sg; - int i; - - for_each_sg(sgl, sg, nents, i) - arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir); - arch_sync_dma_for_cpu_all(dev); -} - -static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir); -} - -static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl, - int nents, enum dma_data_direction dir, unsigned long attrs) -{ - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) - dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir); -} -#endif - -const struct dma_map_ops dma_noncoherent_ops = { - .alloc = arch_dma_alloc, - .free = arch_dma_free, - .mmap = arch_dma_mmap, - .sync_single_for_device = dma_noncoherent_sync_single_for_device, - .sync_sg_for_device = dma_noncoherent_sync_sg_for_device, - .map_page = dma_noncoherent_map_page, - .map_sg = dma_noncoherent_map_sg, -#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \ - defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) - .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu, - .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu, - .unmap_page = dma_noncoherent_unmap_page, - .unmap_sg = dma_noncoherent_unmap_sg, -#endif - .dma_supported = dma_direct_supported, - .mapping_error = dma_direct_mapping_error, - .cache_sync = arch_dma_cache_sync, -}; -EXPORT_SYMBOL(dma_noncoherent_ops); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 4f8a6dbf0b60..ebecaf255ea2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -21,6 +21,7 @@ #include <linux/cache.h> #include <linux/dma-direct.h> +#include <linux/dma-noncoherent.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/spinlock.h> @@ -73,13 +74,6 @@ static phys_addr_t io_tlb_start, io_tlb_end; static unsigned long io_tlb_nslabs; /* - * When the IOMMU overflows we return a fallback buffer. This sets the size. - */ -static unsigned long io_tlb_overflow = 32*1024; - -static phys_addr_t io_tlb_overflow_buffer; - -/* * This is a free list describing the number of free entries available from * each index */ @@ -126,7 +120,6 @@ setup_io_tlb_npages(char *str) return 0; } early_param("swiotlb", setup_io_tlb_npages); -/* make io_tlb_overflow tunable too? */ unsigned long swiotlb_nr_tbl(void) { @@ -194,16 +187,10 @@ void __init swiotlb_update_mem_attributes(void) bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); memset(vaddr, 0, bytes); - - vaddr = phys_to_virt(io_tlb_overflow_buffer); - bytes = PAGE_ALIGN(io_tlb_overflow); - set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) { - void *v_overflow_buffer; unsigned long i, bytes; bytes = nslabs << IO_TLB_SHIFT; @@ -213,17 +200,6 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) io_tlb_end = io_tlb_start + bytes; /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = memblock_virt_alloc_low_nopanic( - PAGE_ALIGN(io_tlb_overflow), - PAGE_SIZE); - if (!v_overflow_buffer) - return -ENOMEM; - - io_tlb_overflow_buffer = __pa(v_overflow_buffer); - - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. @@ -330,7 +306,6 @@ int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) { unsigned long i, bytes; - unsigned char *v_overflow_buffer; bytes = nslabs << IO_TLB_SHIFT; @@ -342,19 +317,6 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs) memset(tlb, 0, bytes); /* - * Get the overflow emergency buffer - */ - v_overflow_buffer = (void *)__get_free_pages(GFP_DMA, - get_order(io_tlb_overflow)); - if (!v_overflow_buffer) - goto cleanup2; - - set_memory_decrypted((unsigned long)v_overflow_buffer, - io_tlb_overflow >> PAGE_SHIFT); - memset(v_overflow_buffer, 0, io_tlb_overflow); - io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer); - - /* * Allocate and initialize the free list array. This array is used * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. @@ -390,10 +352,6 @@ cleanup4: sizeof(int))); io_tlb_list = NULL; cleanup3: - free_pages((unsigned long)v_overflow_buffer, - get_order(io_tlb_overflow)); - io_tlb_overflow_buffer = 0; -cleanup2: io_tlb_end = 0; io_tlb_start = 0; io_tlb_nslabs = 0; @@ -407,8 +365,6 @@ void __init swiotlb_exit(void) return; if (late_alloc) { - free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer), - get_order(io_tlb_overflow)); free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs * sizeof(phys_addr_t))); free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs * @@ -416,8 +372,6 @@ void __init swiotlb_exit(void) free_pages((unsigned long)phys_to_virt(io_tlb_start), get_order(io_tlb_nslabs << IO_TLB_SHIFT)); } else { - memblock_free_late(io_tlb_overflow_buffer, - PAGE_ALIGN(io_tlb_overflow)); memblock_free_late(__pa(io_tlb_orig_addr), PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t))); memblock_free_late(__pa(io_tlb_list), @@ -429,7 +383,7 @@ void __init swiotlb_exit(void) max_segment = 0; } -int is_swiotlb_buffer(phys_addr_t paddr) +static int is_swiotlb_buffer(phys_addr_t paddr) { return paddr >= io_tlb_start && paddr < io_tlb_end; } @@ -591,26 +545,6 @@ found: } /* - * Allocates bounce buffer and returns its physical address. - */ -static phys_addr_t -map_single(struct device *hwdev, phys_addr_t phys, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - dma_addr_t start_dma_addr; - - if (swiotlb_force == SWIOTLB_NO_FORCE) { - dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n", - &phys); - return SWIOTLB_MAP_ERROR; - } - - start_dma_addr = __phys_to_dma(hwdev, io_tlb_start); - return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, - dir, attrs); -} - -/* * tlb_addr is the physical address of the bounce buffer to unmap. */ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, @@ -689,104 +623,32 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } } -static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr, - size_t size) -{ - u64 mask = DMA_BIT_MASK(32); - - if (dev && dev->coherent_dma_mask) - mask = dev->coherent_dma_mask; - return addr + size - 1 <= mask; -} - -static void * -swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, - unsigned long attrs) +static dma_addr_t swiotlb_bounce_page(struct device *dev, phys_addr_t *phys, + size_t size, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t phys_addr; - - if (swiotlb_force == SWIOTLB_NO_FORCE) - goto out_warn; - - phys_addr = swiotlb_tbl_map_single(dev, - __phys_to_dma(dev, io_tlb_start), - 0, size, DMA_FROM_DEVICE, attrs); - if (phys_addr == SWIOTLB_MAP_ERROR) - goto out_warn; - - *dma_handle = __phys_to_dma(dev, phys_addr); - if (!dma_coherent_ok(dev, *dma_handle, size)) - goto out_unmap; - - memset(phys_to_virt(phys_addr), 0, size); - return phys_to_virt(phys_addr); + dma_addr_t dma_addr; -out_unmap: - dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n", - (unsigned long long)dev->coherent_dma_mask, - (unsigned long long)*dma_handle); - - /* - * DMA_TO_DEVICE to avoid memcpy in unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); -out_warn: - if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { - dev_warn(dev, - "swiotlb: coherent allocation failed, size=%zu\n", - size); - dump_stack(); + if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { + dev_warn_ratelimited(dev, + "Cannot do DMA to address %pa\n", phys); + return DIRECT_MAPPING_ERROR; } - return NULL; -} - -static bool swiotlb_free_buffer(struct device *dev, size_t size, - dma_addr_t dma_addr) -{ - phys_addr_t phys_addr = dma_to_phys(dev, dma_addr); - WARN_ON_ONCE(irqs_disabled()); - - if (!is_swiotlb_buffer(phys_addr)) - return false; - - /* - * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single. - * DMA_ATTR_SKIP_CPU_SYNC is optional. - */ - swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - return true; -} - -static void -swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir, - int do_panic) -{ - if (swiotlb_force == SWIOTLB_NO_FORCE) - return; - - /* - * Ran out of IOMMU space for this operation. This is very bad. - * Unfortunately the drivers cannot handle this operation properly. - * unless they check for dma_mapping_error (most don't) - * When the mapping is small enough return a static buffer to limit - * the damage, or panic when the transfer is too big. - */ - dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n", - size); + /* Oh well, have to allocate and map a bounce buffer. */ + *phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), + *phys, size, dir, attrs); + if (*phys == SWIOTLB_MAP_ERROR) + return DIRECT_MAPPING_ERROR; - if (size <= io_tlb_overflow || !do_panic) - return; + /* Ensure that the address returned is DMA'ble */ + dma_addr = __phys_to_dma(dev, *phys); + if (unlikely(!dma_capable(dev, dma_addr, size))) { + swiotlb_tbl_unmap_single(dev, *phys, size, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); + return DIRECT_MAPPING_ERROR; + } - if (dir == DMA_BIDIRECTIONAL) - panic("DMA: Random memory could be DMA accessed\n"); - if (dir == DMA_FROM_DEVICE) - panic("DMA: Random memory could be DMA written\n"); - if (dir == DMA_TO_DEVICE) - panic("DMA: Random memory could be DMA read\n"); + return dma_addr; } /* @@ -801,7 +663,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, enum dma_data_direction dir, unsigned long attrs) { - phys_addr_t map, phys = page_to_phys(page) + offset; + phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dev_addr = phys_to_dma(dev, phys); BUG_ON(dir == DMA_NONE); @@ -810,28 +672,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, * we can safely return the device addr and not worry about bounce * buffering it. */ - if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE) - return dev_addr; - - trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - - /* Oh well, have to allocate and map a bounce buffer. */ - map = map_single(dev, phys, size, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { - swiotlb_full(dev, size, dir, 1); - return __phys_to_dma(dev, io_tlb_overflow_buffer); + if (!dma_capable(dev, dev_addr, size) || + swiotlb_force == SWIOTLB_FORCE) { + trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); + dev_addr = swiotlb_bounce_page(dev, &phys, size, dir, attrs); } - dev_addr = __phys_to_dma(dev, map); + if (!dev_is_dma_coherent(dev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + arch_sync_dma_for_device(dev, phys, size, dir); - /* Ensure that the address returned is DMA'ble */ - if (dma_capable(dev, dev_addr, size)) - return dev_addr; - - attrs |= DMA_ATTR_SKIP_CPU_SYNC; - swiotlb_tbl_unmap_single(dev, map, size, dir, attrs); - - return __phys_to_dma(dev, io_tlb_overflow_buffer); + return dev_addr; } /* @@ -842,14 +693,18 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, * After this call, reads by the cpu to the buffer are guaranteed to see * whatever the device wrote there. */ -static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) +void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + unsigned long attrs) { phys_addr_t paddr = dma_to_phys(hwdev, dev_addr); BUG_ON(dir == DMA_NONE); + if (!dev_is_dma_coherent(hwdev) && + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + arch_sync_dma_for_cpu(hwdev, paddr, size, dir); + if (is_swiotlb_buffer(paddr)) { swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs); return; @@ -867,13 +722,6 @@ static void unmap_single(struct device *hwdev, dma_addr_t dev_addr, dma_mark_clean(phys_to_virt(paddr), size); } -void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ - unmap_single(hwdev, dev_addr, size, dir, attrs); -} - /* * Make physical memory consistent for a single streaming mode DMA translation * after a transfer. @@ -893,15 +741,17 @@ swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr, BUG_ON(dir == DMA_NONE); - if (is_swiotlb_buffer(paddr)) { + if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_CPU) + arch_sync_dma_for_cpu(hwdev, paddr, size, dir); + + if (is_swiotlb_buffer(paddr)) swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target); - return; - } - if (dir != DMA_FROM_DEVICE) - return; + if (!dev_is_dma_coherent(hwdev) && target == SYNC_FOR_DEVICE) + arch_sync_dma_for_device(hwdev, paddr, size, dir); - dma_mark_clean(phys_to_virt(paddr), size); + if (!is_swiotlb_buffer(paddr) && dir == DMA_FROM_DEVICE) + dma_mark_clean(phys_to_virt(paddr), size); } void @@ -925,48 +775,31 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, * appropriate dma address and length. They are obtained via * sg_dma_{address,length}(SG). * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * * Device ownership issues as mentioned above for swiotlb_map_page are the * same here. */ int -swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems, +swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl, int nelems, enum dma_data_direction dir, unsigned long attrs) { struct scatterlist *sg; int i; - BUG_ON(dir == DMA_NONE); - for_each_sg(sgl, sg, nelems, i) { - phys_addr_t paddr = sg_phys(sg); - dma_addr_t dev_addr = phys_to_dma(hwdev, paddr); - - if (swiotlb_force == SWIOTLB_FORCE || - !dma_capable(hwdev, dev_addr, sg->length)) { - phys_addr_t map = map_single(hwdev, sg_phys(sg), - sg->length, dir, attrs); - if (map == SWIOTLB_MAP_ERROR) { - /* Don't panic here, we expect map_sg users - to do proper error handling. */ - swiotlb_full(hwdev, sg->length, dir, 0); - attrs |= DMA_ATTR_SKIP_CPU_SYNC; - swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir, - attrs); - sg_dma_len(sgl) = 0; - return 0; - } - sg->dma_address = __phys_to_dma(hwdev, map); - } else - sg->dma_address = dev_addr; + sg->dma_address = swiotlb_map_page(dev, sg_page(sg), sg->offset, + sg->length, dir, attrs); + if (sg->dma_address == DIRECT_MAPPING_ERROR) + goto out_error; sg_dma_len(sg) = sg->length; } + return nelems; + +out_error: + swiotlb_unmap_sg_attrs(dev, sgl, i, dir, + attrs | DMA_ATTR_SKIP_CPU_SYNC); + sg_dma_len(sgl) = 0; + return 0; } /* @@ -984,7 +817,7 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl, BUG_ON(dir == DMA_NONE); for_each_sg(sgl, sg, nelems, i) - unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir, + swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg), dir, attrs); } @@ -1022,12 +855,6 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE); } -int -swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer)); -} - /* * Return whether the given device DMA address mask can be supported * properly. For example, if your device can only drive the low 24-bits @@ -1040,39 +867,10 @@ swiotlb_dma_supported(struct device *hwdev, u64 mask) return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask; } -void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) -{ - void *vaddr; - - /* temporary workaround: */ - if (gfp & __GFP_NOWARN) - attrs |= DMA_ATTR_NO_WARN; - - /* - * Don't print a warning when the first allocation attempt fails. - * swiotlb_alloc_coherent() will print a warning when the DMA memory - * allocation ultimately failed. - */ - gfp |= __GFP_NOWARN; - - vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs); - return vaddr; -} - -void swiotlb_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr, unsigned long attrs) -{ - if (!swiotlb_free_buffer(dev, size, dma_addr)) - dma_direct_free(dev, size, vaddr, dma_addr, attrs); -} - const struct dma_map_ops swiotlb_dma_ops = { - .mapping_error = swiotlb_dma_mapping_error, - .alloc = swiotlb_alloc, - .free = swiotlb_free, + .mapping_error = dma_direct_mapping_error, + .alloc = dma_direct_alloc, + .free = dma_direct_free, .sync_single_for_cpu = swiotlb_sync_single_for_cpu, .sync_single_for_device = swiotlb_sync_single_for_device, .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu, diff --git a/kernel/events/core.c b/kernel/events/core.c index 65b30773af3e..8c490130c4fb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3935,6 +3935,12 @@ int perf_event_read_local(struct perf_event *event, u64 *value, goto out; } + /* If this is a pinned event it must be running on this CPU */ + if (event->attr.pinned && event->oncpu != smp_processor_id()) { + ret = -EBUSY; + goto out; + } + /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise @@ -8308,6 +8314,8 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, goto unlock; list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->cpu != smp_processor_id()) + continue; if (event->attr.type != PERF_TYPE_TRACEPOINT) continue; if (event->attr.config != entry->type) @@ -9454,9 +9462,7 @@ static void free_pmu_context(struct pmu *pmu) if (pmu->task_ctx_nr > perf_invalid_context) return; - mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); - mutex_unlock(&pmus_lock); } /* @@ -9712,12 +9718,8 @@ EXPORT_SYMBOL_GPL(perf_pmu_register); void perf_pmu_unregister(struct pmu *pmu) { - int remove_device; - mutex_lock(&pmus_lock); - remove_device = pmu_bus_running; list_del_rcu(&pmu->entry); - mutex_unlock(&pmus_lock); /* * We dereference the pmu list under both SRCU and regular RCU, so @@ -9729,13 +9731,14 @@ void perf_pmu_unregister(struct pmu *pmu) free_percpu(pmu->pmu_disable_count); if (pmu->type >= PERF_TYPE_MAX) idr_remove(&pmu_idr, pmu->type); - if (remove_device) { + if (pmu_bus_running) { if (pmu->nr_addr_filters) device_remove_file(pmu->dev, &dev_attr_nr_addr_filters); device_del(pmu->dev); put_device(pmu->dev); } free_pmu_context(pmu); + mutex_unlock(&pmus_lock); } EXPORT_SYMBOL_GPL(perf_pmu_unregister); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 5d3cf407e374..4a9937076331 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -459,10 +459,20 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) if (size || handle->aux_flags) { /* * Only send RECORD_AUX if we have something useful to communicate + * + * Note: the OVERWRITE records by themselves are not considered + * useful, as they don't communicate any *new* information, + * aside from the short-lived offset, that becomes history at + * the next event sched-in and therefore isn't useful. + * The userspace that needs to copy out AUX data in overwrite + * mode should know to use user_page::aux_head for the actual + * offset. So, from now on we don't output AUX records that + * have *only* OVERWRITE flag set. */ - perf_event_aux_event(handle->event, aux_head, size, - handle->aux_flags); + if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE) + perf_event_aux_event(handle->event, aux_head, size, + handle->aux_flags); } rb->user_page->aux_head = rb->aux_head; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 96fb51f3994f..96d4bee83489 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2122,7 +2122,7 @@ static void handle_trampoline(struct pt_regs *regs) sigill: uprobe_warn(current, "handle uretprobe, sending SIGILL."); - force_sig_info(SIGILL, SEND_SIG_FORCED, current); + force_sig(SIGILL, current); } @@ -2230,7 +2230,7 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) if (unlikely(err)) { uprobe_warn(current, "execute the probed insn, sending SIGILL."); - force_sig_info(SIGILL, SEND_SIG_FORCED, current); + force_sig(SIGILL, current); } } diff --git a/kernel/fork.c b/kernel/fork.c index f0b58479534f..8f82a3bdcb8f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -223,9 +223,14 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) return s->addr; } + /* + * Allocated stacks are cached and later reused by new threads, + * so memcg accounting is performed manually on assigning/releasing + * stacks to tasks. Drop __GFP_ACCOUNT. + */ stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN, VMALLOC_START, VMALLOC_END, - THREADINFO_GFP, + THREADINFO_GFP & ~__GFP_ACCOUNT, PAGE_KERNEL, 0, node, __builtin_return_address(0)); @@ -248,9 +253,19 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) static inline void free_thread_stack(struct task_struct *tsk) { #ifdef CONFIG_VMAP_STACK - if (task_stack_vm_area(tsk)) { + struct vm_struct *vm = task_stack_vm_area(tsk); + + if (vm) { int i; + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + -(int)(PAGE_SIZE / 1024)); + + memcg_kmem_uncharge(vm->pages[i], 0); + } + for (i = 0; i < NR_CACHED_STACKS; i++) { if (this_cpu_cmpxchg(cached_stacks[i], NULL, tsk->stack_vm_area) != NULL) @@ -351,10 +366,6 @@ static void account_kernel_stack(struct task_struct *tsk, int account) NR_KERNEL_STACK_KB, PAGE_SIZE / 1024 * account); } - - /* All stack pages belong to the same memcg. */ - mod_memcg_page_state(vm->pages[0], MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); } else { /* * All stack pages are in the same zone and belong to the @@ -370,6 +381,35 @@ static void account_kernel_stack(struct task_struct *tsk, int account) } } +static int memcg_charge_kernel_stack(struct task_struct *tsk) +{ +#ifdef CONFIG_VMAP_STACK + struct vm_struct *vm = task_stack_vm_area(tsk); + int ret; + + if (vm) { + int i; + + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + /* + * If memcg_kmem_charge() fails, page->mem_cgroup + * pointer is NULL, and both memcg_kmem_uncharge() + * and mod_memcg_page_state() in free_thread_stack() + * will ignore this page. So it's safe. + */ + ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0); + if (ret) + return ret; + + mod_memcg_page_state(vm->pages[i], + MEMCG_KERNEL_STACK_KB, + PAGE_SIZE / 1024); + } + } +#endif + return 0; +} + static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(tsk->state != TASK_DEAD)) @@ -807,6 +847,9 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!stack) 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); @@ -1779,6 +1822,10 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); diff --git a/kernel/futex.c b/kernel/futex.c index 11fc3bb456d6..3e2de8fc1891 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1365,9 +1365,9 @@ static void __unqueue_futex(struct futex_q *q) { struct futex_hash_bucket *hb; - if (WARN_ON_SMP(!q->lock_ptr || !spin_is_locked(q->lock_ptr)) - || WARN_ON(plist_node_empty(&q->list))) + if (WARN_ON_SMP(!q->lock_ptr) || WARN_ON(plist_node_empty(&q->list))) return; + lockdep_assert_held(q->lock_ptr); hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock); plist_del(&q->list, &hb->chain); diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 83f830acbb5f..410a77a8f6e2 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -173,7 +173,7 @@ err_unlock: } COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - struct compat_timespec __user *, utime, u32 __user *, uaddr2, + struct old_timespec32 __user *, utime, u32 __user *, uaddr2, u32, val3) { struct timespec ts; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b9132d1269ef..cb8e3e8ac7b9 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -15,6 +15,7 @@ #include <linux/lockdep.h> #include <linux/export.h> #include <linux/sysctl.h> +#include <linux/suspend.h> #include <linux/utsname.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> @@ -242,6 +243,28 @@ void reset_hung_task_detector(void) } EXPORT_SYMBOL_GPL(reset_hung_task_detector); +static bool hung_detector_suspended; + +static int hungtask_pm_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case PM_SUSPEND_PREPARE: + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + hung_detector_suspended = true; + break; + case PM_POST_SUSPEND: + case PM_POST_HIBERNATION: + case PM_POST_RESTORE: + hung_detector_suspended = false; + break; + default: + break; + } + return NOTIFY_OK; +} + /* * kthread which checks for tasks stuck in D state */ @@ -261,7 +284,8 @@ static int watchdog(void *dummy) interval = min_t(unsigned long, interval, timeout); t = hung_timeout_jiffies(hung_last_checked, interval); if (t <= 0) { - if (!atomic_xchg(&reset_hung_task, 0)) + if (!atomic_xchg(&reset_hung_task, 0) && + !hung_detector_suspended) check_hung_uninterruptible_tasks(timeout); hung_last_checked = jiffies; continue; @@ -275,6 +299,10 @@ static int watchdog(void *dummy) static int __init hung_task_init(void) { atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + /* Disable hung task detector on suspend */ + pm_notifier(hungtask_pm_notify, 0); + watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); return 0; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 5d9fc01b60a6..3366d11c3e02 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -183,7 +183,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size, * unhappy about. Replace them with ':', which does * the trick and is not as offensive as '\'... */ - name = kstrdup(of_node_full_name(of_node), GFP_KERNEL); + name = kasprintf(GFP_KERNEL, "%pOF", of_node); if (!name) { kfree(domain); return NULL; @@ -867,7 +867,7 @@ void irq_dispose_mapping(unsigned int virq) EXPORT_SYMBOL_GPL(irq_dispose_mapping); /** - * irq_find_mapping() - Find a linux irq from an hw irq number. + * irq_find_mapping() - Find a linux irq from a hw irq number. * @domain: domain owning this hardware interrupt * @hwirq: hardware irq number in that domain space */ @@ -1741,6 +1741,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { debugfs_remove(d->debugfs_file); + d->debugfs_file = NULL; } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index fb86146037a7..9dbdccab3b6a 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -927,6 +927,9 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action) local_bh_disable(); ret = action->thread_fn(action->irq, action->dev_id); + if (ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + irq_finalize_oneshot(desc, action); local_bh_enable(); return ret; @@ -943,6 +946,9 @@ static irqreturn_t irq_thread_fn(struct irq_desc *desc, irqreturn_t ret; ret = action->thread_fn(action->irq, action->dev_id); + if (ret == IRQ_HANDLED) + atomic_inc(&desc->threads_handled); + irq_finalize_oneshot(desc, action); return ret; } @@ -1020,8 +1026,6 @@ static int irq_thread(void *data) irq_thread_check_affinity(desc, action); action_ret = handler_fn(desc, action); - if (action_ret == IRQ_HANDLED) - atomic_inc(&desc->threads_handled); if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 5092494bf261..6e6d467f3dec 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -124,6 +124,27 @@ static unsigned int matrix_alloc_area(struct irq_matrix *m, struct cpumap *cm, return area; } +/* Find the best CPU which has the lowest vector allocation count */ +static unsigned int matrix_find_best_cpu(struct irq_matrix *m, + const struct cpumask *msk) +{ + unsigned int cpu, best_cpu, maxavl = 0; + struct cpumap *cm; + + best_cpu = UINT_MAX; + + for_each_cpu(cpu, msk) { + cm = per_cpu_ptr(m->maps, cpu); + + if (!cm->online || cm->available <= maxavl) + continue; + + best_cpu = cpu; + maxavl = cm->available; + } + return best_cpu; +} + /** * irq_matrix_assign_system - Assign system wide entry in the matrix * @m: Matrix pointer @@ -239,11 +260,21 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) * @m: Matrix pointer * @cpu: On which CPU the interrupt should be allocated */ -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu) { - struct cpumap *cm = per_cpu_ptr(m->maps, cpu); - unsigned int bit, end = m->alloc_end; + unsigned int bit, cpu, end = m->alloc_end; + struct cpumap *cm; + + if (cpumask_empty(msk)) + return -EINVAL; + + cpu = matrix_find_best_cpu(m, msk); + if (cpu == UINT_MAX) + return -ENOSPC; + cm = per_cpu_ptr(m->maps, cpu); + end = m->alloc_end; /* Get managed bit which are not allocated */ bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); bit = find_first_bit(m->scratch_map, end); @@ -252,6 +283,7 @@ int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) set_bit(bit, cm->alloc_map); cm->allocated++; m->total_allocated++; + *mapped_cpu = cpu; trace_irq_matrix_alloc_managed(bit, cpu, m, cm); return bit; } @@ -322,37 +354,27 @@ void irq_matrix_remove_reserved(struct irq_matrix *m) int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, bool reserved, unsigned int *mapped_cpu) { - unsigned int cpu, best_cpu, maxavl = 0; + unsigned int cpu, bit; struct cpumap *cm; - unsigned int bit; - - best_cpu = UINT_MAX; - for_each_cpu(cpu, msk) { - cm = per_cpu_ptr(m->maps, cpu); - if (!cm->online || cm->available <= maxavl) - continue; + cpu = matrix_find_best_cpu(m, msk); + if (cpu == UINT_MAX) + return -ENOSPC; - best_cpu = cpu; - maxavl = cm->available; - } + cm = per_cpu_ptr(m->maps, cpu); + bit = matrix_alloc_area(m, cm, 1, false); + if (bit >= m->alloc_end) + return -ENOSPC; + cm->allocated++; + cm->available--; + m->total_allocated++; + m->global_available--; + if (reserved) + m->global_reserved--; + *mapped_cpu = cpu; + trace_irq_matrix_alloc(bit, cpu, m, cm); + return bit; - if (maxavl) { - cm = per_cpu_ptr(m->maps, best_cpu); - bit = matrix_alloc_area(m, cm, 1, false); - if (bit < m->alloc_end) { - cm->allocated++; - cm->available--; - m->total_allocated++; - m->global_available--; - if (reserved) - m->global_reserved--; - *mapped_cpu = best_cpu; - trace_irq_matrix_alloc(bit, best_cpu, m, cm); - return bit; - } - } - return -ENOSPC; } /** diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 2e62503bea0d..b28028b08d44 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -38,23 +38,43 @@ static int jump_label_cmp(const void *a, const void *b) const struct jump_entry *jea = a; const struct jump_entry *jeb = b; - if (jea->key < jeb->key) + if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; - if (jea->key > jeb->key) + if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; return 0; } +static void jump_label_swap(void *a, void *b, int size) +{ + long delta = (unsigned long)a - (unsigned long)b; + struct jump_entry *jea = a; + struct jump_entry *jeb = b; + struct jump_entry tmp = *jea; + + jea->code = jeb->code - delta; + jea->target = jeb->target - delta; + jea->key = jeb->key - delta; + + jeb->code = tmp.code + delta; + jeb->target = tmp.target + delta; + jeb->key = tmp.key + delta; +} + static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; + void *swapfn = NULL; + + if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) + swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); - sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL); + sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); @@ -85,6 +105,7 @@ void static_key_slow_inc_cpuslocked(struct static_key *key) int v, v1; STATIC_KEY_CHECK_USE(key); + lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc() calls; @@ -130,6 +151,7 @@ EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); + lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); @@ -160,6 +182,7 @@ EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); + lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); @@ -185,6 +208,8 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key, unsigned long rate_limit, struct delayed_work *work) { + lockdep_assert_cpus_held(); + /* * The negative count check is valid even when a negative * key->enabled is in use by static_key_slow_inc(); a @@ -261,8 +286,8 @@ EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { - if (entry->code <= (unsigned long)end && - entry->code + JUMP_LABEL_NOP_SIZE > (unsigned long)start) + if (jump_entry_code(entry) <= (unsigned long)end && + jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE > (unsigned long)start) return 1; return 0; @@ -321,16 +346,6 @@ static inline void static_key_set_linked(struct static_key *key) key->type |= JUMP_TYPE_LINKED; } -static inline struct static_key *jump_entry_key(struct jump_entry *entry) -{ - return (struct static_key *)((unsigned long)entry->key & ~1UL); -} - -static bool jump_entry_branch(struct jump_entry *entry) -{ - return (unsigned long)entry->key & 1UL; -} - /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in @@ -355,7 +370,7 @@ static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); - bool branch = jump_entry_branch(entry); + bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; @@ -363,19 +378,20 @@ static enum jump_label_type jump_label_type(struct jump_entry *entry) static void __jump_label_update(struct static_key *key, struct jump_entry *entry, - struct jump_entry *stop) + struct jump_entry *stop, + bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { /* * An entry->code of 0 indicates an entry which has been * disabled because it was in an init text area. */ - if (entry->code) { - if (kernel_text_address(entry->code)) + if (init || !jump_entry_is_init(entry)) { + if (kernel_text_address(jump_entry_code(entry))) arch_jump_label_transform(entry, jump_label_type(entry)); else WARN_ONCE(1, "can't patch jump_label at %pS", - (void *)(unsigned long)entry->code); + (void *)jump_entry_code(entry)); } } } @@ -410,6 +426,9 @@ void __init jump_label_init(void) if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); + if (init_section_contains((void *)jump_entry_code(iter), 1)) + jump_entry_set_init(iter); + iterk = jump_entry_key(iter); if (iterk == key) continue; @@ -422,26 +441,13 @@ void __init jump_label_init(void) cpus_read_unlock(); } -/* Disable any jump label entries in __init/__exit code */ -void __init jump_label_invalidate_initmem(void) -{ - struct jump_entry *iter_start = __start___jump_table; - struct jump_entry *iter_stop = __stop___jump_table; - struct jump_entry *iter; - - for (iter = iter_start; iter < iter_stop; iter++) { - if (init_section_contains((void *)(unsigned long)iter->code, 1)) - iter->code = 0; - } -} - #ifdef CONFIG_MODULES static enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); - bool branch = jump_entry_branch(entry); + bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; @@ -455,7 +461,7 @@ struct static_key_mod { static inline struct static_key_mod *static_key_mod(struct static_key *key) { - WARN_ON_ONCE(!(key->type & JUMP_TYPE_LINKED)); + WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } @@ -514,7 +520,8 @@ static void __jump_label_mod_update(struct static_key *key) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; - __jump_label_update(key, mod->entries, stop); + __jump_label_update(key, mod->entries, stop, + m && m->state == MODULE_STATE_COMING); } } @@ -560,12 +567,15 @@ static int jump_label_add_module(struct module *mod) for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; + if (within_module_init(jump_entry_code(iter), mod)) + jump_entry_set_init(iter); + iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; - if (within_module(iter->key, mod)) { + if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } @@ -595,7 +605,7 @@ static int jump_label_add_module(struct module *mod) /* Only update if we've changed from our initial state */ if (jump_label_type(iter) != jump_label_init_type(iter)) - __jump_label_update(key, iter, iter_stop); + __jump_label_update(key, iter, iter_stop, true); } return 0; @@ -615,7 +625,7 @@ static void jump_label_del_module(struct module *mod) key = jump_entry_key(iter); - if (within_module(iter->key, mod)) + if (within_module((unsigned long)key, mod)) continue; /* No memory during module load */ @@ -651,19 +661,6 @@ static void jump_label_del_module(struct module *mod) } } -/* Disable any jump label entries in module init code */ -static void jump_label_invalidate_module_init(struct module *mod) -{ - struct jump_entry *iter_start = mod->jump_entries; - struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; - struct jump_entry *iter; - - for (iter = iter_start; iter < iter_stop; iter++) { - if (within_module_init(iter->code, mod)) - iter->code = 0; - } -} - static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) @@ -685,9 +682,6 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, case MODULE_STATE_GOING: jump_label_del_module(mod); break; - case MODULE_STATE_LIVE: - jump_label_invalidate_module_init(mod); - break; } jump_label_unlock(); @@ -757,7 +751,8 @@ static void jump_label_update(struct static_key *key) entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) - __jump_label_update(key, entry, stop); + __jump_label_update(key, entry, stop, + system_state < SYSTEM_RUNNING); } #ifdef CONFIG_STATIC_KEYS_SELFTEST diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 02a0b01380d8..f3a04994e063 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -37,7 +37,7 @@ extern const u8 kallsyms_names[] __weak; * Tell the compiler that the count isn't in the small data section if the arch * has one (eg: FRV). */ -extern const unsigned long kallsyms_num_syms +extern const unsigned int kallsyms_num_syms __attribute__((weak, section(".rodata"))); extern const unsigned long kallsyms_relative_base @@ -46,7 +46,7 @@ __attribute__((weak, section(".rodata"))); extern const u8 kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; -extern const unsigned long kallsyms_markers[] __weak; +extern const unsigned int kallsyms_markers[] __weak; /* * Expand a compressed symbol data into the resulting uncompressed string, diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 23a83a4da38a..86ef06d3dbe3 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -471,6 +471,10 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, } } + /* Ensure that these pages are decrypted if SME is enabled. */ + if (pages) + arch_kexec_post_alloc_pages(page_address(pages), 1 << order, 0); + return pages; } @@ -867,6 +871,7 @@ static int kimage_load_crash_segment(struct kimage *image, result = -ENOMEM; goto out; } + arch_kexec_post_alloc_pages(page_address(page), 1, 0); ptr = kmap(page); ptr += maddr & ~PAGE_MASK; mchunk = min_t(size_t, mbytes, @@ -884,6 +889,7 @@ static int kimage_load_crash_segment(struct kimage *image, result = copy_from_user(ptr, buf, uchunk); kexec_flush_icache_page(page); kunmap(page); + arch_kexec_pre_free_pages(page_address(page), 1); if (result) { result = -EFAULT; goto out; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ab257be4d924..90e98e233647 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -546,8 +546,14 @@ static void do_free_cleaned_kprobes(void) struct optimized_kprobe *op, *tmp; list_for_each_entry_safe(op, tmp, &freeing_list, list) { - BUG_ON(!kprobe_unused(&op->kp)); list_del_init(&op->list); + if (WARN_ON_ONCE(!kprobe_unused(&op->kp))) { + /* + * This must not happen, but if there is a kprobe + * still in use, keep it on kprobes hash list. + */ + continue; + } free_aggr_kprobe(&op->kp); } } @@ -700,11 +706,11 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) } /* Cancel unoptimizing for reusing */ -static void reuse_unused_kprobe(struct kprobe *ap) +static int reuse_unused_kprobe(struct kprobe *ap) { struct optimized_kprobe *op; + int ret; - BUG_ON(!kprobe_unused(ap)); /* * Unused kprobe MUST be on the way of delayed unoptimizing (means * there is still a relative jump) and disabled. @@ -714,8 +720,12 @@ static void reuse_unused_kprobe(struct kprobe *ap) /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; /* Optimize it again (remove from op->list) */ - BUG_ON(!kprobe_optready(ap)); + ret = kprobe_optready(ap); + if (ret) + return ret; + optimize_kprobe(ap); + return 0; } /* Remove optimized instructions */ @@ -940,11 +950,16 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) #define kprobe_disarmed(p) kprobe_disabled(p) #define wait_for_kprobe_optimizer() do {} while (0) -/* There should be no unused kprobes can be reused without optimization */ -static void reuse_unused_kprobe(struct kprobe *ap) +static int reuse_unused_kprobe(struct kprobe *ap) { + /* + * If the optimized kprobe is NOT supported, the aggr kprobe is + * released at the same time that the last aggregated kprobe is + * unregistered. + * Thus there should be no chance to reuse unused kprobe. + */ printk(KERN_ERR "Error: There should be no unused kprobe here.\n"); - BUG_ON(kprobe_unused(ap)); + return -EINVAL; } static void free_aggr_kprobe(struct kprobe *p) @@ -1259,8 +1274,6 @@ NOKPROBE_SYMBOL(cleanup_rp_inst); /* Add the new probe to ap->list */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { - BUG_ON(kprobe_gone(ap) || kprobe_gone(p)); - if (p->post_handler) unoptimize_kprobe(ap, true); /* Fall back to normal kprobe */ @@ -1318,9 +1331,12 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) goto out; } init_aggr_kprobe(ap, orig_p); - } else if (kprobe_unused(ap)) + } else if (kprobe_unused(ap)) { /* This probe is going to die. Rescue it */ - reuse_unused_kprobe(ap); + ret = reuse_unused_kprobe(ap); + if (ret) + goto out; + } if (kprobe_gone(ap)) { /* @@ -1704,7 +1720,6 @@ noclean: return 0; disarmed: - BUG_ON(!kprobe_disarmed(ap)); hlist_del_rcu(&ap->hlist); return 0; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index dd13f865ad40..1efada2dd9dd 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -138,7 +138,7 @@ static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; * get freed - this significantly simplifies the debugging code. */ unsigned long nr_lock_classes; -static struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; +struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; static inline struct lock_class *hlock_class(struct held_lock *hlock) { @@ -1391,7 +1391,9 @@ static void print_lock_class_header(struct lock_class *class, int depth) printk("%*s->", depth, ""); print_lock_name(class); - printk(KERN_CONT " ops: %lu", class->ops); +#ifdef CONFIG_DEBUG_LOCKDEP + printk(KERN_CONT " ops: %lu", debug_class_ops_read(class)); +#endif printk(KERN_CONT " {\n"); for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { @@ -2148,76 +2150,6 @@ static int check_no_collision(struct task_struct *curr, } /* - * This is for building a chain between just two different classes, - * instead of adding a new hlock upon current, which is done by - * add_chain_cache(). - * - * This can be called in any context with two classes, while - * add_chain_cache() must be done within the lock owener's context - * since it uses hlock which might be racy in another context. - */ -static inline int add_chain_cache_classes(unsigned int prev, - unsigned int next, - unsigned int irq_context, - u64 chain_key) -{ - struct hlist_head *hash_head = chainhashentry(chain_key); - struct lock_chain *chain; - - /* - * Allocate a new chain entry from the static array, and add - * it to the hash: - */ - - /* - * We might need to take the graph lock, ensure we've got IRQs - * disabled to make this an IRQ-safe lock.. for recursion reasons - * lockdep won't complain about its own locking errors. - */ - if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) - return 0; - - if (unlikely(nr_lock_chains >= MAX_LOCKDEP_CHAINS)) { - if (!debug_locks_off_graph_unlock()) - return 0; - - print_lockdep_off("BUG: MAX_LOCKDEP_CHAINS too low!"); - dump_stack(); - return 0; - } - - chain = lock_chains + nr_lock_chains++; - chain->chain_key = chain_key; - chain->irq_context = irq_context; - chain->depth = 2; - if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { - chain->base = nr_chain_hlocks; - nr_chain_hlocks += chain->depth; - chain_hlocks[chain->base] = prev - 1; - chain_hlocks[chain->base + 1] = next -1; - } -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * Important for check_no_collision(). - */ - else { - if (!debug_locks_off_graph_unlock()) - return 0; - - print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!"); - dump_stack(); - return 0; - } -#endif - - hlist_add_head_rcu(&chain->entry, hash_head); - debug_atomic_inc(chain_lookup_misses); - inc_chains(); - - return 1; -} - -/* * Adds a dependency chain into chain hashtable. And must be called with * graph_lock held. * @@ -3262,6 +3194,10 @@ static int __lock_is_held(const struct lockdep_map *lock, int read); /* * This gets called for every mutex_lock*()/spin_lock*() operation. * We maintain the dependency maps and validate the locking attempt: + * + * The callers must make sure that IRQs are disabled before calling it, + * otherwise we could get an interrupt which would want to take locks, + * which would end up in lockdep again. */ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, int hardirqs_off, @@ -3279,14 +3215,6 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (unlikely(!debug_locks)) return 0; - /* - * Lockdep should run with IRQs disabled, otherwise we could - * get an interrupt which would want to take locks, which would - * end up in lockdep and have you got a head-ache already? - */ - if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) - return 0; - if (!prove_locking || lock->key == &__lockdep_no_validate__) check = 0; @@ -3300,7 +3228,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (!class) return 0; } - atomic_inc((atomic_t *)&class->ops); + + debug_class_ops_inc(class); + if (very_verbose(class)) { printk("\nacquire class [%px] %s", class->key, class->name); if (class->name_version > 1) @@ -3543,6 +3473,9 @@ static int reacquire_held_locks(struct task_struct *curr, unsigned int depth, { struct held_lock *hlock; + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return 0; + for (hlock = curr->held_locks + idx; idx < depth; idx++, hlock++) { if (!__lock_acquire(hlock->instance, hlock_class(hlock)->subclass, @@ -3696,6 +3629,13 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip) curr->lockdep_depth = i; curr->curr_chain_key = hlock->prev_chain_key; + /* + * The most likely case is when the unlock is on the innermost + * lock. In this case, we are done! + */ + if (i == depth-1) + return 1; + if (reacquire_held_locks(curr, depth, i + 1)) return 0; @@ -3703,10 +3643,14 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip) * We had N bottles of beer on the wall, we drank one, but now * there's not N-1 bottles of beer left on the wall... */ - if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1)) - return 0; + DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth-1); - return 1; + /* + * Since reacquire_held_locks() would have called check_chain_key() + * indirectly via __lock_acquire(), we don't need to do it again + * on return. + */ + return 0; } static int __lock_is_held(const struct lockdep_map *lock, int read) @@ -4122,7 +4066,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - if (unlikely(!lock_stat)) + if (unlikely(!lock_stat || !debug_locks)) return; if (unlikely(current->lockdep_recursion)) @@ -4142,7 +4086,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - if (unlikely(!lock_stat)) + if (unlikely(!lock_stat || !debug_locks)) return; if (unlikely(current->lockdep_recursion)) diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index d459d624ba2a..88c847a41c8a 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -152,9 +152,15 @@ struct lockdep_stats { int nr_find_usage_forwards_recursions; int nr_find_usage_backwards_checks; int nr_find_usage_backwards_recursions; + + /* + * Per lock class locking operation stat counts + */ + unsigned long lock_class_ops[MAX_LOCKDEP_KEYS]; }; DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats); +extern struct lock_class lock_classes[MAX_LOCKDEP_KEYS]; #define __debug_atomic_inc(ptr) \ this_cpu_inc(lockdep_stats.ptr); @@ -179,9 +185,30 @@ DECLARE_PER_CPU(struct lockdep_stats, lockdep_stats); } \ __total; \ }) + +static inline void debug_class_ops_inc(struct lock_class *class) +{ + int idx; + + idx = class - lock_classes; + __debug_atomic_inc(lock_class_ops[idx]); +} + +static inline unsigned long debug_class_ops_read(struct lock_class *class) +{ + int idx, cpu; + unsigned long ops = 0; + + idx = class - lock_classes; + for_each_possible_cpu(cpu) + ops += per_cpu(lockdep_stats.lock_class_ops[idx], cpu); + return ops; +} + #else # define __debug_atomic_inc(ptr) do { } while (0) # define debug_atomic_inc(ptr) do { } while (0) # define debug_atomic_dec(ptr) do { } while (0) # define debug_atomic_read(ptr) 0 +# define debug_class_ops_inc(ptr) do { } while (0) #endif diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 3dd980dfba2d..3d31f9b0059e 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -68,7 +68,7 @@ static int l_show(struct seq_file *m, void *v) seq_printf(m, "%p", class->key); #ifdef CONFIG_DEBUG_LOCKDEP - seq_printf(m, " OPS:%8ld", class->ops); + seq_printf(m, " OPS:%8ld", debug_class_ops_read(class)); #endif #ifdef CONFIG_PROVE_LOCKING seq_printf(m, " FD:%5ld", lockdep_count_forward_deps(class)); diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index bfaeb05123ff..8a8c3c208c5e 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -74,12 +74,24 @@ */ #include "mcs_spinlock.h" +#define MAX_NODES 4 +/* + * On 64-bit architectures, the mcs_spinlock structure will be 16 bytes in + * size and four of them will fit nicely in one 64-byte cacheline. For + * pvqspinlock, however, we need more space for extra data. To accommodate + * that, we insert two more long words to pad it up to 32 bytes. IOW, only + * two of them can fit in a cacheline in this case. That is OK as it is rare + * to have more than 2 levels of slowpath nesting in actual use. We don't + * want to penalize pvqspinlocks to optimize for a rare case in native + * qspinlocks. + */ +struct qnode { + struct mcs_spinlock mcs; #ifdef CONFIG_PARAVIRT_SPINLOCKS -#define MAX_NODES 8 -#else -#define MAX_NODES 4 + long reserved[2]; #endif +}; /* * The pending bit spinning loop count. @@ -101,7 +113,7 @@ * * PV doubles the storage and uses the second cacheline for PV state. */ -static DEFINE_PER_CPU_ALIGNED(struct mcs_spinlock, mcs_nodes[MAX_NODES]); +static DEFINE_PER_CPU_ALIGNED(struct qnode, qnodes[MAX_NODES]); /* * We must be able to distinguish between no-tail and the tail at 0:0, @@ -126,7 +138,13 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail) int cpu = (tail >> _Q_TAIL_CPU_OFFSET) - 1; int idx = (tail & _Q_TAIL_IDX_MASK) >> _Q_TAIL_IDX_OFFSET; - return per_cpu_ptr(&mcs_nodes[idx], cpu); + return per_cpu_ptr(&qnodes[idx].mcs, cpu); +} + +static inline __pure +struct mcs_spinlock *grab_mcs_node(struct mcs_spinlock *base, int idx) +{ + return &((struct qnode *)base + idx)->mcs; } #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK) @@ -232,6 +250,20 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail) #endif /* _Q_PENDING_BITS == 8 */ /** + * queued_fetch_set_pending_acquire - fetch the whole lock value and set pending + * @lock : Pointer to queued spinlock structure + * Return: The previous lock value + * + * *,*,* -> *,1,* + */ +#ifndef queued_fetch_set_pending_acquire +static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) +{ + return atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val); +} +#endif + +/** * set_locked - Set the lock bit and own the lock * @lock: Pointer to queued spinlock structure * @@ -326,43 +358,48 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) /* * trylock || pending * - * 0,0,0 -> 0,0,1 ; trylock - * 0,0,1 -> 0,1,1 ; pending + * 0,0,* -> 0,1,* -> 0,0,1 pending, trylock */ - val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val); - if (!(val & ~_Q_LOCKED_MASK)) { - /* - * We're pending, wait for the owner to go away. - * - * *,1,1 -> *,1,0 - * - * this wait loop must be a load-acquire such that we match the - * store-release that clears the locked bit and create lock - * sequentiality; this is because not all - * clear_pending_set_locked() implementations imply full - * barriers. - */ - if (val & _Q_LOCKED_MASK) { - atomic_cond_read_acquire(&lock->val, - !(VAL & _Q_LOCKED_MASK)); - } + val = queued_fetch_set_pending_acquire(lock); - /* - * take ownership and clear the pending bit. - * - * *,1,0 -> *,0,1 - */ - clear_pending_set_locked(lock); - qstat_inc(qstat_lock_pending, true); - return; + /* + * If we observe contention, there is a concurrent locker. + * + * Undo and queue; our setting of PENDING might have made the + * n,0,0 -> 0,0,0 transition fail and it will now be waiting + * on @next to become !NULL. + */ + if (unlikely(val & ~_Q_LOCKED_MASK)) { + + /* Undo PENDING if we set it. */ + if (!(val & _Q_PENDING_MASK)) + clear_pending(lock); + + goto queue; } /* - * If pending was clear but there are waiters in the queue, then - * we need to undo our setting of pending before we queue ourselves. + * We're pending, wait for the owner to go away. + * + * 0,1,1 -> 0,1,0 + * + * this wait loop must be a load-acquire such that we match the + * store-release that clears the locked bit and create lock + * sequentiality; this is because not all + * clear_pending_set_locked() implementations imply full + * barriers. + */ + if (val & _Q_LOCKED_MASK) + atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK)); + + /* + * take ownership and clear the pending bit. + * + * 0,1,0 -> 0,0,1 */ - if (!(val & _Q_PENDING_MASK)) - clear_pending(lock); + clear_pending_set_locked(lock); + qstat_inc(qstat_lock_pending, true); + return; /* * End of pending bit optimistic spinning and beginning of MCS @@ -371,11 +408,16 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) queue: qstat_inc(qstat_lock_slowpath, true); pv_queue: - node = this_cpu_ptr(&mcs_nodes[0]); + node = this_cpu_ptr(&qnodes[0].mcs); idx = node->count++; tail = encode_tail(smp_processor_id(), idx); - node += idx; + node = grab_mcs_node(node, idx); + + /* + * Keep counts of non-zero index values: + */ + qstat_inc(qstat_lock_idx1 + idx - 1, idx); /* * Ensure that we increment the head node->count before initialising @@ -476,16 +518,25 @@ locked: */ /* - * In the PV case we might already have _Q_LOCKED_VAL set. + * In the PV case we might already have _Q_LOCKED_VAL set, because + * of lock stealing; therefore we must also allow: + * + * n,0,1 -> 0,0,1 * - * The atomic_cond_read_acquire() call above has provided the - * necessary acquire semantics required for locking. + * Note: at this point: (val & _Q_PENDING_MASK) == 0, because of the + * above wait condition, therefore any concurrent setting of + * PENDING will make the uncontended transition fail. */ - if (((val & _Q_TAIL_MASK) == tail) && - atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL)) - goto release; /* No contention */ + if ((val & _Q_TAIL_MASK) == tail) { + if (atomic_try_cmpxchg_relaxed(&lock->val, &val, _Q_LOCKED_VAL)) + goto release; /* No contention */ + } - /* Either somebody is queued behind us or _Q_PENDING_VAL is set */ + /* + * Either somebody is queued behind us or _Q_PENDING_VAL got set + * which will then detect the remaining tail and queue behind us + * ensuring we'll see a @next. + */ set_locked(lock); /* @@ -501,7 +552,7 @@ release: /* * release the node */ - __this_cpu_dec(mcs_nodes[0].count); + __this_cpu_dec(qnodes[0].mcs.count); } EXPORT_SYMBOL(queued_spin_lock_slowpath); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 5a0cf5f9008c..0130e488ebfe 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -49,8 +49,6 @@ enum vcpu_state { struct pv_node { struct mcs_spinlock mcs; - struct mcs_spinlock __res[3]; - int cpu; u8 state; }; @@ -281,7 +279,7 @@ static void pv_init_node(struct mcs_spinlock *node) { struct pv_node *pn = (struct pv_node *)node; - BUILD_BUG_ON(sizeof(struct pv_node) > 5*sizeof(struct mcs_spinlock)); + BUILD_BUG_ON(sizeof(struct pv_node) > sizeof(struct qnode)); pn->cpu = smp_processor_id(); pn->state = vcpu_running; diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 6bd78c0740fc..42d3d8dc8f49 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -55,6 +55,9 @@ enum qlock_stats { qstat_pv_wait_node, qstat_lock_pending, qstat_lock_slowpath, + qstat_lock_idx1, + qstat_lock_idx2, + qstat_lock_idx3, qstat_num, /* Total number of statistical counters */ qstat_reset_cnts = qstat_num, }; @@ -82,6 +85,9 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_wait_node] = "pv_wait_node", [qstat_lock_pending] = "lock_pending", [qstat_lock_slowpath] = "lock_slowpath", + [qstat_lock_idx1] = "lock_index1", + [qstat_lock_idx2] = "lock_index2", + [qstat_lock_idx3] = "lock_index3", [qstat_reset_cnts] = "reset_counters", }; diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 2823d4163a37..581edcc63c26 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1485,9 +1485,9 @@ void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) __rt_mutex_lock(lock, subclass); } EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); -#endif -#ifndef CONFIG_DEBUG_LOCK_ALLOC +#else /* !CONFIG_DEBUG_LOCK_ALLOC */ + /** * rt_mutex_lock - lock a rt_mutex * diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 3064c50e181e..09b180063ee1 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -180,7 +180,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, * but it gives the spinners an early indication that the * readers now have the lock. */ - rwsem_set_reader_owned(sem); + __rwsem_set_reader_owned(sem, waiter->task); } /* @@ -233,8 +233,19 @@ __rwsem_down_read_failed_common(struct rw_semaphore *sem, int state) waiter.type = RWSEM_WAITING_FOR_READ; raw_spin_lock_irq(&sem->wait_lock); - if (list_empty(&sem->wait_list)) + if (list_empty(&sem->wait_list)) { + /* + * In case the wait queue is empty and the lock isn't owned + * by a writer, this reader can exit the slowpath and return + * immediately as its RWSEM_ACTIVE_READ_BIAS has already + * been set in the count. + */ + if (atomic_long_read(&sem->count) >= 0) { + raw_spin_unlock_irq(&sem->wait_lock); + return sem; + } adjustment += RWSEM_WAITING_BIAS; + } list_add_tail(&waiter.list, &sem->wait_list); /* we're now waiting on the lock, but no longer actively locking */ diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 776308d2fa9e..e586f0d03ad3 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -117,8 +117,9 @@ EXPORT_SYMBOL(down_write_trylock); void up_read(struct rw_semaphore *sem) { rwsem_release(&sem->dep_map, 1, _RET_IP_); - DEBUG_RWSEMS_WARN_ON(sem->owner != RWSEM_READER_OWNED); + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED)); + rwsem_clear_reader_owned(sem); __up_read(sem); } @@ -181,7 +182,7 @@ void down_read_non_owner(struct rw_semaphore *sem) might_sleep(); __down_read(sem); - rwsem_set_reader_owned(sem); + __rwsem_set_reader_owned(sem, NULL); } EXPORT_SYMBOL(down_read_non_owner); @@ -215,7 +216,7 @@ EXPORT_SYMBOL(down_write_killable_nested); void up_read_non_owner(struct rw_semaphore *sem) { - DEBUG_RWSEMS_WARN_ON(sem->owner != RWSEM_READER_OWNED); + DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED)); __up_read(sem); } diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index b9d0e72aa80f..bad2bca0268b 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -1,24 +1,30 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * The owner field of the rw_semaphore structure will be set to - * RWSEM_READER_OWNED when a reader grabs the lock. A writer will clear - * the owner field when it unlocks. A reader, on the other hand, will - * not touch the owner field when it unlocks. + * The least significant 2 bits of the owner value has the following + * meanings when set. + * - RWSEM_READER_OWNED (bit 0): The rwsem is owned by readers + * - RWSEM_ANONYMOUSLY_OWNED (bit 1): The rwsem is anonymously owned, + * i.e. the owner(s) cannot be readily determined. It can be reader + * owned or the owning writer is indeterminate. * - * In essence, the owner field now has the following 4 states: - * 1) 0 - * - lock is free or the owner hasn't set the field yet - * 2) RWSEM_READER_OWNED - * - lock is currently or previously owned by readers (lock is free - * or not set by owner yet) - * 3) RWSEM_ANONYMOUSLY_OWNED bit set with some other bits set as well - * - lock is owned by an anonymous writer, so spinning on the lock - * owner should be disabled. - * 4) Other non-zero value - * - a writer owns the lock and other writers can spin on the lock owner. + * When a writer acquires a rwsem, it puts its task_struct pointer + * into the owner field. It is cleared after an unlock. + * + * When a reader acquires a rwsem, it will also puts its task_struct + * pointer into the owner field with both the RWSEM_READER_OWNED and + * RWSEM_ANONYMOUSLY_OWNED bits set. On unlock, the owner field will + * largely be left untouched. So for a free or reader-owned rwsem, + * the owner value may contain information about the last reader that + * acquires the rwsem. The anonymous bit is set because that particular + * reader may or may not still own the lock. + * + * That information may be helpful in debugging cases where the system + * seems to hang on a reader owned rwsem especially if only one reader + * is involved. Ideally we would like to track all the readers that own + * a rwsem, but the overhead is simply too big. */ -#define RWSEM_ANONYMOUSLY_OWNED (1UL << 0) -#define RWSEM_READER_OWNED ((struct task_struct *)RWSEM_ANONYMOUSLY_OWNED) +#define RWSEM_READER_OWNED (1UL << 0) +#define RWSEM_ANONYMOUSLY_OWNED (1UL << 1) #ifdef CONFIG_DEBUG_RWSEMS # define DEBUG_RWSEMS_WARN_ON(c) DEBUG_LOCKS_WARN_ON(c) @@ -44,15 +50,26 @@ static inline void rwsem_clear_owner(struct rw_semaphore *sem) WRITE_ONCE(sem->owner, NULL); } +/* + * The task_struct pointer of the last owning reader will be left in + * the owner field. + * + * Note that the owner value just indicates the task has owned the rwsem + * previously, it may not be the real owner or one of the real owners + * anymore when that field is examined, so take it with a grain of salt. + */ +static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem, + struct task_struct *owner) +{ + unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED + | RWSEM_ANONYMOUSLY_OWNED; + + WRITE_ONCE(sem->owner, (struct task_struct *)val); +} + static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) { - /* - * We check the owner value first to make sure that we will only - * do a write to the rwsem cacheline when it is really necessary - * to minimize cacheline contention. - */ - if (READ_ONCE(sem->owner) != RWSEM_READER_OWNED) - WRITE_ONCE(sem->owner, RWSEM_READER_OWNED); + __rwsem_set_reader_owned(sem, current); } /* @@ -72,6 +89,25 @@ static inline bool rwsem_has_anonymous_owner(struct task_struct *owner) { return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED; } + +#ifdef CONFIG_DEBUG_RWSEMS +/* + * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there + * is a task pointer in owner of a reader-owned rwsem, it will be the + * real owner or one of the real owners. The only exception is when the + * unlock is done by up_read_non_owner(). + */ +#define rwsem_clear_reader_owned rwsem_clear_reader_owned +static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) +{ + unsigned long val = (unsigned long)current | RWSEM_READER_OWNED + | RWSEM_ANONYMOUSLY_OWNED; + if (READ_ONCE(sem->owner) == (struct task_struct *)val) + cmpxchg_relaxed((unsigned long *)&sem->owner, val, + RWSEM_READER_OWNED | RWSEM_ANONYMOUSLY_OWNED); +} +#endif + #else static inline void rwsem_set_owner(struct rw_semaphore *sem) { @@ -81,7 +117,18 @@ static inline void rwsem_clear_owner(struct rw_semaphore *sem) { } +static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem, + struct task_struct *owner) +{ +} + static inline void rwsem_set_reader_owned(struct rw_semaphore *sem) { } #endif + +#ifndef rwsem_clear_reader_owned +static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) +{ +} +#endif diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0be047dbd897..65a3b7e55b9f 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work) { struct test_cycle *cycle = container_of(work, typeof(*cycle), work); struct ww_acquire_ctx ctx; - int err; + int err, erra = 0; ww_acquire_init(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); @@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work) err = ww_mutex_lock(cycle->b_mutex, &ctx); if (err == -EDEADLK) { + err = 0; ww_mutex_unlock(&cycle->a_mutex); ww_mutex_lock_slow(cycle->b_mutex, &ctx); - err = ww_mutex_lock(&cycle->a_mutex, &ctx); + erra = ww_mutex_lock(&cycle->a_mutex, &ctx); } if (!err) ww_mutex_unlock(cycle->b_mutex); - ww_mutex_unlock(&cycle->a_mutex); + if (!erra) + ww_mutex_unlock(&cycle->a_mutex); ww_acquire_fini(&ctx); - cycle->result = err; + cycle->result = err ?: erra; } static int __test_cycle(unsigned int nthreads) diff --git a/kernel/memremap.c b/kernel/memremap.c index 5b8600d39931..9eced2cc9f94 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -1,47 +1,21 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2015 Intel Corporation. All rights reserved. */ -#include <linux/radix-tree.h> #include <linux/device.h> -#include <linux/types.h> -#include <linux/pfn_t.h> #include <linux/io.h> #include <linux/kasan.h> -#include <linux/mm.h> #include <linux/memory_hotplug.h> +#include <linux/mm.h> +#include <linux/pfn_t.h> #include <linux/swap.h> #include <linux/swapops.h> +#include <linux/types.h> #include <linux/wait_bit.h> +#include <linux/xarray.h> -static DEFINE_MUTEX(pgmap_lock); -static RADIX_TREE(pgmap_radix, GFP_KERNEL); +static DEFINE_XARRAY(pgmap_array); #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) #define SECTION_SIZE (1UL << PA_SECTION_SHIFT) -static unsigned long order_at(struct resource *res, unsigned long pgoff) -{ - unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff; - unsigned long nr_pages, mask; - - nr_pages = PHYS_PFN(resource_size(res)); - if (nr_pages == pgoff) - return ULONG_MAX; - - /* - * What is the largest aligned power-of-2 range available from - * this resource pgoff to the end of the resource range, - * considering the alignment of the current pgoff? - */ - mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff); - if (!mask) - return ULONG_MAX; - - return find_first_bit(&mask, BITS_PER_LONG); -} - -#define foreach_order_pgoff(res, order, pgoff) \ - for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \ - pgoff += 1UL << order, order = order_at((res), pgoff)) - #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, unsigned long addr, @@ -70,18 +44,10 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma, EXPORT_SYMBOL(device_private_entry_fault); #endif /* CONFIG_DEVICE_PRIVATE */ -static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff) +static void pgmap_array_delete(struct resource *res) { - unsigned long pgoff, order; - - mutex_lock(&pgmap_lock); - foreach_order_pgoff(res, order, pgoff) { - if (pgoff >= end_pgoff) - break; - radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff); - } - mutex_unlock(&pgmap_lock); - + xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end), + NULL, GFP_KERNEL); synchronize_rcu(); } @@ -142,7 +108,7 @@ static void devm_memremap_pages_release(void *data) mem_hotplug_done(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); - pgmap_radix_release(res, -1); + pgmap_array_delete(res); dev_WARN_ONCE(dev, pgmap->altmap.alloc, "%s: failed to free all reserved pages\n", __func__); } @@ -175,10 +141,9 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) struct vmem_altmap *altmap = pgmap->altmap_valid ? &pgmap->altmap : NULL; struct resource *res = &pgmap->res; - unsigned long pfn, pgoff, order; + struct dev_pagemap *conflict_pgmap; pgprot_t pgprot = PAGE_KERNEL; int error, nid, is_ram; - struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -216,20 +181,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) pgmap->dev = dev; - mutex_lock(&pgmap_lock); - error = 0; - - foreach_order_pgoff(res, order, pgoff) { - error = __radix_tree_insert(&pgmap_radix, - PHYS_PFN(res->start) + pgoff, order, pgmap); - if (error) { - dev_err(dev, "%s: failed: %d\n", __func__, error); - break; - } - } - mutex_unlock(&pgmap_lock); + error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start), + PHYS_PFN(res->end), pgmap, GFP_KERNEL)); if (error) - goto err_radix; + goto err_array; nid = dev_to_node(dev); if (nid < 0) @@ -256,19 +211,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (error) goto err_add_memory; - for_each_device_pfn(pfn, pgmap) { - struct page *page = pfn_to_page(pfn); - - /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back - * pointer. It is a bug if a ZONE_DEVICE page is ever - * freed or placed on a driver-private list. Seed the - * storage with LIST_POISON* values. - */ - list_del(&page->lru); - page->pgmap = pgmap; - percpu_ref_get(pgmap->ref); - } + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, pgmap); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); devm_add_action(dev, devm_memremap_pages_release, pgmap); @@ -279,8 +229,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) err_kasan: untrack_pfn(NULL, PHYS_PFN(align_start), align_size); err_pfn_remap: - err_radix: - pgmap_radix_release(res, pgoff); + pgmap_array_delete(res); + err_array: return ERR_PTR(error); } EXPORT_SYMBOL(devm_memremap_pages); @@ -320,7 +270,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, /* fall back to slow path lookup */ rcu_read_lock(); - pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys)); + pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) pgmap = NULL; rcu_read_unlock(); diff --git a/kernel/module.c b/kernel/module.c index 6746c85511fe..49a405891587 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3317,6 +3317,15 @@ static struct module *layout_and_allocate(struct load_info *info, int flags) ndx = find_sec(info, ".data..ro_after_init"); if (ndx) info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT; + /* + * Mark the __jump_table section as ro_after_init as well: these data + * structures are never modified, with the exception of entries that + * refer to code in the __init section, which are annotated as such + * at module load time. + */ + ndx = find_sec(info, "__jump_table"); + if (ndx) + info->sechdrs[ndx].sh_flags |= SHF_RO_AFTER_INIT; /* Determine total sizes, and put offsets in sh_entsize. For now this is done generically; there doesn't appear to be any diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 2a2ac53d8b8b..aa6e72fb7c08 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -216,7 +216,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) idr_for_each_entry_continue(&pid_ns->idr, pid, nr) { task = pid_task(pid, PIDTYPE_PID); if (task && !__fatal_signal_pending(task)) - send_sig_info(SIGKILL, SEND_SIG_FORCED, task); + group_send_sig_info(SIGKILL, SEND_SIG_PRIV, task, PIDTYPE_MAX); } read_unlock(&tasklist_lock); rcu_read_unlock(); diff --git a/kernel/power/process.c b/kernel/power/process.c index 7381d49a44db..4b6a54da7e65 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -96,7 +96,7 @@ static int try_to_freeze_tasks(bool user_only) if (wq_busy) show_workqueue_state(); - if (!wakeup) { + if (!wakeup || pm_debug_messages_on) { read_lock(&tasklist_lock); for_each_process_thread(g, p) { if (p != current && !freezer_should_skip(p) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 5342f6fc022e..0bd595a0b610 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -63,6 +63,12 @@ static DECLARE_SWAIT_QUEUE_HEAD(s2idle_wait_head); enum s2idle_states __read_mostly s2idle_state; static DEFINE_RAW_SPINLOCK(s2idle_lock); +bool pm_suspend_via_s2idle(void) +{ + return mem_sleep_current == PM_SUSPEND_TO_IDLE; +} +EXPORT_SYMBOL_GPL(pm_suspend_via_s2idle); + void s2idle_set_ops(const struct platform_s2idle_ops *ops) { lock_system_sleep(); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 9bf5404397e0..b77150ad1965 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -16,6 +16,8 @@ * 01Mar01 Andrew Morton */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/mm.h> #include <linux/tty.h> @@ -192,16 +194,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, return 0; } -/* - * Number of registered extended console drivers. - * - * If extended consoles are present, in-kernel cont reassembly is disabled - * and each fragment is stored as a separate log entry with proper - * continuation flag so that every emitted message has full metadata. This - * doesn't change the result for regular consoles or /proc/kmsg. For - * /dev/kmsg, as long as the reader concatenates messages according to - * consecutive continuation flags, the end result should be the same too. - */ +/* Number of registered extended console drivers. */ static int nr_ext_console_drivers; /* @@ -423,6 +416,7 @@ static u32 log_next_idx; /* the next printk record to write to the console */ static u64 console_seq; static u32 console_idx; +static u64 exclusive_console_stop_seq; /* the next printk record to read after the last 'clear' command */ static u64 clear_seq; @@ -437,6 +431,7 @@ static u32 clear_idx; /* record buffer */ #define LOG_ALIGN __alignof__(struct printk_log) #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT) +#define LOG_BUF_LEN_MAX (u32)(1 << 31) static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN); static char *log_buf = __log_buf; static u32 log_buf_len = __LOG_BUF_LEN; @@ -1037,18 +1032,28 @@ void log_buf_vmcoreinfo_setup(void) static unsigned long __initdata new_log_buf_len; /* we practice scaling the ring buffer by powers of 2 */ -static void __init log_buf_len_update(unsigned size) +static void __init log_buf_len_update(u64 size) { + if (size > (u64)LOG_BUF_LEN_MAX) { + size = (u64)LOG_BUF_LEN_MAX; + pr_err("log_buf over 2G is not supported.\n"); + } + if (size) size = roundup_pow_of_two(size); if (size > log_buf_len) - new_log_buf_len = size; + new_log_buf_len = (unsigned long)size; } /* save requested log_buf_len since it's too early to process it */ static int __init log_buf_len_setup(char *str) { - unsigned size = memparse(str, &str); + u64 size; + + if (!str) + return -EINVAL; + + size = memparse(str, &str); log_buf_len_update(size); @@ -1093,7 +1098,7 @@ void __init setup_log_buf(int early) { unsigned long flags; char *new_log_buf; - int free; + unsigned int free; if (log_buf != __log_buf) return; @@ -1113,7 +1118,7 @@ void __init setup_log_buf(int early) } if (unlikely(!new_log_buf)) { - pr_err("log_buf_len: %ld bytes not available\n", + pr_err("log_buf_len: %lu bytes not available\n", new_log_buf_len); return; } @@ -1126,8 +1131,8 @@ void __init setup_log_buf(int early) memcpy(log_buf, __log_buf, __LOG_BUF_LEN); logbuf_unlock_irqrestore(flags); - pr_info("log_buf_len: %d bytes\n", log_buf_len); - pr_info("early log buf free: %d(%d%%)\n", + pr_info("log_buf_len: %u bytes\n", log_buf_len); + pr_info("early log buf free: %u(%u%%)\n", free, (free * 100) / __LOG_BUF_LEN); } @@ -1767,12 +1772,8 @@ static void cont_flush(void) static bool cont_add(int facility, int level, enum log_flags flags, const char *text, size_t len) { - /* - * If ext consoles are present, flush and skip in-kernel - * continuation. See nr_ext_console_drivers definition. Also, if - * the line gets too long, split it up in separate records. - */ - if (nr_ext_console_drivers || cont.len + len > sizeof(cont.buf)) { + /* If the line gets too long, split it up in separate records. */ + if (cont.len + len > sizeof(cont.buf)) { cont_flush(); return false; } @@ -1795,9 +1796,6 @@ static bool cont_add(int facility, int level, enum log_flags flags, const char * cont_flush(); } - if (cont.len > (sizeof(cont.buf) * 80) / 100) - cont_flush(); - return true; } @@ -1889,8 +1887,9 @@ asmlinkage int vprintk_emit(int facility, int level, const char *fmt, va_list args) { int printed_len; - bool in_sched = false; + bool in_sched = false, pending_output; unsigned long flags; + u64 curr_log_seq; if (level == LOGLEVEL_SCHED) { level = LOGLEVEL_DEFAULT; @@ -1902,11 +1901,13 @@ asmlinkage int vprintk_emit(int facility, int level, /* This stops the holder of console_sem just where we want him */ logbuf_lock_irqsave(flags); + curr_log_seq = log_next_seq; printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args); + pending_output = (curr_log_seq != log_next_seq); logbuf_unlock_irqrestore(flags); /* If called from the scheduler, we can not call up(). */ - if (!in_sched) { + if (!in_sched && pending_output) { /* * Disable preemption to avoid being preempted while holding * console_sem which would prevent anyone from printing to @@ -1923,7 +1924,8 @@ asmlinkage int vprintk_emit(int facility, int level, preempt_enable(); } - wake_up_klogd(); + if (pending_output) + wake_up_klogd(); return printed_len; } EXPORT_SYMBOL(vprintk_emit); @@ -2009,6 +2011,7 @@ static u64 syslog_seq; static u32 syslog_idx; static u64 console_seq; static u32 console_idx; +static u64 exclusive_console_stop_seq; static u64 log_first_seq; static u32 log_first_idx; static u64 log_next_seq; @@ -2351,8 +2354,9 @@ again: printk_safe_enter_irqsave(flags); raw_spin_lock(&logbuf_lock); if (console_seq < log_first_seq) { - len = sprintf(text, "** %u printk messages dropped **\n", - (unsigned)(log_first_seq - console_seq)); + len = sprintf(text, + "** %llu printk messages dropped **\n", + log_first_seq - console_seq); /* messages are gone, move to first one */ console_seq = log_first_seq; @@ -2376,6 +2380,12 @@ skip: goto skip; } + /* Output to all consoles once old messages replayed. */ + if (unlikely(exclusive_console && + console_seq >= exclusive_console_stop_seq)) { + exclusive_console = NULL; + } + len += msg_print_text(msg, console_msg_format & MSG_FORMAT_SYSLOG, text + len, @@ -2418,10 +2428,6 @@ skip: console_locked = 0; - /* Release the exclusive_console once it is used */ - if (unlikely(exclusive_console)) - exclusive_console = NULL; - raw_spin_unlock(&logbuf_lock); up_console_sem(); @@ -2688,8 +2694,7 @@ void register_console(struct console *newcon) } if (newcon->flags & CON_EXTENDED) - if (!nr_ext_console_drivers++) - pr_info("printk: continuation disabled due to ext consoles, expect more fragments in /dev/kmsg\n"); + nr_ext_console_drivers++; if (newcon->flags & CON_PRINTBUFFER) { /* @@ -2699,13 +2704,18 @@ void register_console(struct console *newcon) logbuf_lock_irqsave(flags); console_seq = syslog_seq; console_idx = syslog_idx; - logbuf_unlock_irqrestore(flags); /* * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to * the already-registered consoles. + * + * Set exclusive_console with disabled interrupts to reduce + * race window with eventual console_flush_on_panic() that + * ignores console_lock. */ exclusive_console = newcon; + exclusive_console_stop_seq = console_seq; + logbuf_unlock_irqrestore(flags); } console_unlock(); console_sysfs_notify(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 21fec73d45d4..80b34dffdfb9 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -261,6 +261,9 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { + if (mode & PTRACE_MODE_SCHED) + return false; + if (mode & PTRACE_MODE_NOAUDIT) return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); else @@ -328,9 +331,16 @@ ok: !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; + if (mode & PTRACE_MODE_SCHED) + return 0; return security_ptrace_access_check(task, mode); } +bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode) +{ + return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED); +} + bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; @@ -396,7 +406,7 @@ static int ptrace_attach(struct task_struct *task, long request, /* SEIZE doesn't trap tracee on attach */ if (!seize) - send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); spin_lock(&task->sighand->siglock); @@ -563,7 +573,7 @@ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) - send_sig_info(SIGKILL, SEND_SIG_FORCED, p); + send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); @@ -651,7 +661,7 @@ static int ptrace_setoptions(struct task_struct *child, unsigned long data) return 0; } -static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) +static int ptrace_getsiginfo(struct task_struct *child, kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; @@ -667,7 +677,7 @@ static int ptrace_getsiginfo(struct task_struct *child, siginfo_t *info) return error; } -static int ptrace_setsiginfo(struct task_struct *child, const siginfo_t *info) +static int ptrace_setsiginfo(struct task_struct *child, const kernel_siginfo_t *info) { unsigned long flags; int error = -ESRCH; @@ -709,7 +719,7 @@ static int ptrace_peek_siginfo(struct task_struct *child, pending = &child->pending; for (i = 0; i < arg.nr; ) { - siginfo_t info; + kernel_siginfo_t info; s32 off = arg.off + i; spin_lock_irq(&child->sighand->siglock); @@ -885,7 +895,7 @@ int ptrace_request(struct task_struct *child, long request, { bool seized = child->ptrace & PT_SEIZED; int ret = -EIO; - siginfo_t siginfo, *si; + kernel_siginfo_t siginfo, *si; void __user *datavp = (void __user *) data; unsigned long __user *datalp = datavp; unsigned long flags; @@ -919,9 +929,8 @@ int ptrace_request(struct task_struct *child, long request, break; case PTRACE_SETSIGINFO: - if (copy_from_user(&siginfo, datavp, sizeof siginfo)) - ret = -EFAULT; - else + ret = copy_siginfo_from_user(&siginfo, datavp); + if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; @@ -1181,7 +1190,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, { compat_ulong_t __user *datap = compat_ptr(data); compat_ulong_t word; - siginfo_t siginfo; + kernel_siginfo_t siginfo; int ret; switch (request) { @@ -1215,10 +1224,9 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, break; case PTRACE_SETSIGINFO: - if (copy_siginfo_from_user32( - &siginfo, (struct compat_siginfo __user *) datap)) - ret = -EFAULT; - else + ret = copy_siginfo_from_user32( + &siginfo, (struct compat_siginfo __user *) datap); + if (!ret) ret = ptrace_setsiginfo(child, &siginfo); break; #ifdef CONFIG_HAVE_ARCH_TRACEHOOK diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 9210379c0353..939a2056c87a 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -196,7 +196,7 @@ config RCU_BOOST This option boosts the priority of preempted RCU readers that block the current preemptible RCU grace period for too long. This option also prevents heavy loads from blocking RCU - callback invocation for all flavors of RCU. + callback invocation. Say Y here if you are working with real-time apps or heavy loads Say N here if you are unsure. @@ -225,12 +225,12 @@ config RCU_NOCB_CPU callback invocation to energy-efficient CPUs in battery-powered asymmetric multiprocessors. - This option offloads callback invocation from the set of - CPUs specified at boot time by the rcu_nocbs parameter. - For each such CPU, a kthread ("rcuox/N") will be created to - invoke callbacks, where the "N" is the CPU being offloaded, - and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and - "s" for RCU-sched. Nothing prevents this kthread from running + This option offloads callback invocation from the set of CPUs + specified at boot time by the rcu_nocbs parameter. For each + such CPU, a kthread ("rcuox/N") will be created to invoke + callbacks, where the "N" is the CPU being offloaded, and where + the "p" for RCU-preempt (PREEMPT kernels) and "s" for RCU-sched + (!PREEMPT kernels). Nothing prevents this kthread from running on the specified CPUs, but (1) the kthreads may be preempted between each callback, and (2) affinity or cgroups can be used to force the kthreads to run on whatever set of CPUs is desired. diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 4d04683c31b2..2866166863f0 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -176,8 +176,9 @@ static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old) /* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally - * by call_rcu() and rcu callback execution, and are therefore not part of the - * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. + * by call_rcu() and rcu callback execution, and are therefore not part + * of the RCU API. These are in rcupdate.h because they are used by all + * RCU implementations. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD @@ -223,6 +224,7 @@ void kfree(const void *); */ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) { + rcu_callback_t f; unsigned long offset = (unsigned long)head->func; rcu_lock_acquire(&rcu_callback_map); @@ -233,7 +235,9 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head) return true; } else { RCU_TRACE(trace_rcu_invoke_callback(rn, head);) - head->func(head); + f = head->func; + WRITE_ONCE(head->func, (rcu_callback_t)0L); + f(head); rcu_lock_release(&rcu_callback_map); return false; } @@ -328,40 +332,35 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt) } } -/* Returns first leaf rcu_node of the specified RCU flavor. */ -#define rcu_first_leaf_node(rsp) ((rsp)->level[rcu_num_lvls - 1]) +/* Returns a pointer to the first leaf rcu_node structure. */ +#define rcu_first_leaf_node() (rcu_state.level[rcu_num_lvls - 1]) /* Is this rcu_node a leaf? */ #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1) /* Is this rcu_node the last leaf? */ -#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1]) +#define rcu_is_last_leaf_node(rnp) ((rnp) == &rcu_state.node[rcu_num_nodes - 1]) /* - * Do a full breadth-first scan of the rcu_node structures for the - * specified rcu_state structure. + * Do a full breadth-first scan of the {s,}rcu_node structures for the + * specified state structure (for SRCU) or the only rcu_state structure + * (for RCU). */ -#define rcu_for_each_node_breadth_first(rsp, rnp) \ - for ((rnp) = &(rsp)->node[0]; \ - (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) +#define srcu_for_each_node_breadth_first(sp, rnp) \ + for ((rnp) = &(sp)->node[0]; \ + (rnp) < &(sp)->node[rcu_num_nodes]; (rnp)++) +#define rcu_for_each_node_breadth_first(rnp) \ + srcu_for_each_node_breadth_first(&rcu_state, rnp) /* - * Do a breadth-first scan of the non-leaf rcu_node structures for the - * specified rcu_state structure. Note that if there is a singleton - * rcu_node tree with but one rcu_node structure, this loop is a no-op. + * Scan the leaves of the rcu_node hierarchy for the rcu_state structure. + * Note that if there is a singleton rcu_node tree with but one rcu_node + * structure, this loop -will- visit the rcu_node structure. It is still + * a leaf node, even if it is also the root node. */ -#define rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) \ - for ((rnp) = &(rsp)->node[0]; !rcu_is_leaf_node(rsp, rnp); (rnp)++) - -/* - * Scan the leaves of the rcu_node hierarchy for the specified rcu_state - * structure. Note that if there is a singleton rcu_node tree with but - * one rcu_node structure, this loop -will- visit the rcu_node structure. - * It is still a leaf node, even if it is also the root node. - */ -#define rcu_for_each_leaf_node(rsp, rnp) \ - for ((rnp) = rcu_first_leaf_node(rsp); \ - (rnp) < &(rsp)->node[rcu_num_nodes]; (rnp)++) +#define rcu_for_each_leaf_node(rnp) \ + for ((rnp) = rcu_first_leaf_node(); \ + (rnp) < &rcu_state.node[rcu_num_nodes]; (rnp)++) /* * Iterate over all possible CPUs in a leaf RCU node. @@ -435,6 +434,12 @@ do { \ #endif /* #if defined(SRCU) || !defined(TINY_RCU) */ +#ifdef CONFIG_SRCU +void srcu_init(void); +#else /* #ifdef CONFIG_SRCU */ +static inline void srcu_init(void) { } +#endif /* #else #ifdef CONFIG_SRCU */ + #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ static inline bool rcu_gp_is_normal(void) { return true; } @@ -515,29 +520,19 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type, #ifdef CONFIG_TINY_RCU static inline unsigned long rcu_get_gp_seq(void) { return 0; } -static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; } -static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; } static inline unsigned long rcu_exp_batches_completed(void) { return 0; } -static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; } static inline unsigned long srcu_batches_completed(struct srcu_struct *sp) { return 0; } static inline void rcu_force_quiescent_state(void) { } -static inline void rcu_bh_force_quiescent_state(void) { } -static inline void rcu_sched_force_quiescent_state(void) { } static inline void show_rcu_gp_kthreads(void) { } static inline int rcu_get_gp_kthreads_prio(void) { return 0; } #else /* #ifdef CONFIG_TINY_RCU */ unsigned long rcu_get_gp_seq(void); -unsigned long rcu_bh_get_gp_seq(void); -unsigned long rcu_sched_get_gp_seq(void); unsigned long rcu_exp_batches_completed(void); -unsigned long rcu_exp_batches_completed_sched(void); unsigned long srcu_batches_completed(struct srcu_struct *sp); void show_rcu_gp_kthreads(void); int rcu_get_gp_kthreads_prio(void); void rcu_force_quiescent_state(void); -void rcu_bh_force_quiescent_state(void); -void rcu_sched_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; extern struct workqueue_struct *rcu_par_gp_wq; #endif /* #else #ifdef CONFIG_TINY_RCU */ diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 34244523550e..b459da70b4fc 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -190,36 +190,6 @@ static struct rcu_perf_ops rcu_ops = { }; /* - * Definitions for rcu_bh perf testing. - */ - -static int rcu_bh_perf_read_lock(void) __acquires(RCU_BH) -{ - rcu_read_lock_bh(); - return 0; -} - -static void rcu_bh_perf_read_unlock(int idx) __releases(RCU_BH) -{ - rcu_read_unlock_bh(); -} - -static struct rcu_perf_ops rcu_bh_ops = { - .ptype = RCU_BH_FLAVOR, - .init = rcu_sync_perf_init, - .readlock = rcu_bh_perf_read_lock, - .readunlock = rcu_bh_perf_read_unlock, - .get_gp_seq = rcu_bh_get_gp_seq, - .gp_diff = rcu_seq_diff, - .exp_completed = rcu_exp_batches_completed_sched, - .async = call_rcu_bh, - .gp_barrier = rcu_barrier_bh, - .sync = synchronize_rcu_bh, - .exp_sync = synchronize_rcu_bh_expedited, - .name = "rcu_bh" -}; - -/* * Definitions for srcu perf testing. */ @@ -306,36 +276,6 @@ static struct rcu_perf_ops srcud_ops = { }; /* - * Definitions for sched perf testing. - */ - -static int sched_perf_read_lock(void) -{ - preempt_disable(); - return 0; -} - -static void sched_perf_read_unlock(int idx) -{ - preempt_enable(); -} - -static struct rcu_perf_ops sched_ops = { - .ptype = RCU_SCHED_FLAVOR, - .init = rcu_sync_perf_init, - .readlock = sched_perf_read_lock, - .readunlock = sched_perf_read_unlock, - .get_gp_seq = rcu_sched_get_gp_seq, - .gp_diff = rcu_seq_diff, - .exp_completed = rcu_exp_batches_completed_sched, - .async = call_rcu_sched, - .gp_barrier = rcu_barrier_sched, - .sync = synchronize_sched, - .exp_sync = synchronize_sched_expedited, - .name = "sched" -}; - -/* * Definitions for RCU-tasks perf testing. */ @@ -611,7 +551,7 @@ rcu_perf_cleanup(void) kfree(writer_n_durations); } - /* Do flavor-specific cleanup operations. */ + /* Do torture-type-specific cleanup operations. */ if (cur_ops->cleanup != NULL) cur_ops->cleanup(); @@ -661,8 +601,7 @@ rcu_perf_init(void) long i; int firsterr = 0; static struct rcu_perf_ops *perf_ops[] = { - &rcu_ops, &rcu_bh_ops, &srcu_ops, &srcud_ops, &sched_ops, - &tasks_ops, + &rcu_ops, &srcu_ops, &srcud_ops, &tasks_ops, }; if (!torture_init_begin(perf_type, verbose)) @@ -680,6 +619,7 @@ rcu_perf_init(void) for (i = 0; i < ARRAY_SIZE(perf_ops); i++) pr_cont(" %s", perf_ops[i]->name); pr_cont("\n"); + WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST)); firsterr = -EINVAL; goto unwind; } diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index c596c6f1e457..210c77460365 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -66,15 +66,19 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos /* Bits for ->extendables field, extendables param, and related definitions. */ #define RCUTORTURE_RDR_SHIFT 8 /* Put SRCU index in upper bits. */ #define RCUTORTURE_RDR_MASK ((1 << RCUTORTURE_RDR_SHIFT) - 1) -#define RCUTORTURE_RDR_BH 0x1 /* Extend readers by disabling bh. */ -#define RCUTORTURE_RDR_IRQ 0x2 /* ... disabling interrupts. */ -#define RCUTORTURE_RDR_PREEMPT 0x4 /* ... disabling preemption. */ -#define RCUTORTURE_RDR_RCU 0x8 /* ... entering another RCU reader. */ -#define RCUTORTURE_RDR_NBITS 4 /* Number of bits defined above. */ -#define RCUTORTURE_MAX_EXTEND (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \ - RCUTORTURE_RDR_PREEMPT) +#define RCUTORTURE_RDR_BH 0x01 /* Extend readers by disabling bh. */ +#define RCUTORTURE_RDR_IRQ 0x02 /* ... disabling interrupts. */ +#define RCUTORTURE_RDR_PREEMPT 0x04 /* ... disabling preemption. */ +#define RCUTORTURE_RDR_RBH 0x08 /* ... rcu_read_lock_bh(). */ +#define RCUTORTURE_RDR_SCHED 0x10 /* ... rcu_read_lock_sched(). */ +#define RCUTORTURE_RDR_RCU 0x20 /* ... entering another RCU reader. */ +#define RCUTORTURE_RDR_NBITS 6 /* Number of bits defined above. */ +#define RCUTORTURE_MAX_EXTEND \ + (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | RCUTORTURE_RDR_PREEMPT | \ + RCUTORTURE_RDR_RBH | RCUTORTURE_RDR_SCHED) #define RCUTORTURE_RDR_MAX_LOOPS 0x7 /* Maximum reader extensions. */ /* Must be power of two minus one. */ +#define RCUTORTURE_RDR_MAX_SEGS (RCUTORTURE_RDR_MAX_LOOPS + 3) torture_param(int, cbflood_inter_holdoff, HZ, "Holdoff between floods (jiffies)"); @@ -89,6 +93,12 @@ torture_param(int, fqs_duration, 0, "Duration of fqs bursts (us), 0 to disable"); torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)"); torture_param(int, fqs_stutter, 3, "Wait time between fqs bursts (s)"); +torture_param(bool, fwd_progress, 1, "Test grace-period forward progress"); +torture_param(int, fwd_progress_div, 4, "Fraction of CPU stall to wait"); +torture_param(int, fwd_progress_holdoff, 60, + "Time between forward-progress tests (s)"); +torture_param(bool, fwd_progress_need_resched, 1, + "Hide cond_resched() behind need_resched()"); torture_param(bool, gp_cond, false, "Use conditional/async GP wait primitives"); torture_param(bool, gp_exp, false, "Use expedited GP wait primitives"); torture_param(bool, gp_normal, false, @@ -125,7 +135,7 @@ torture_param(int, verbose, 1, static char *torture_type = "rcu"; module_param(torture_type, charp, 0444); -MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, ...)"); +MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)"); static int nrealreaders; static int ncbflooders; @@ -137,6 +147,7 @@ static struct task_struct **cbflood_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; static struct task_struct *stall_task; +static struct task_struct *fwd_prog_task; static struct task_struct **barrier_cbs_tasks; static struct task_struct *barrier_task; @@ -197,6 +208,18 @@ static const char * const rcu_torture_writer_state_names[] = { "RTWS_STOPPING", }; +/* Record reader segment types and duration for first failing read. */ +struct rt_read_seg { + int rt_readstate; + unsigned long rt_delay_jiffies; + unsigned long rt_delay_ms; + unsigned long rt_delay_us; + bool rt_preempted; +}; +static int err_segs_recorded; +static struct rt_read_seg err_segs[RCUTORTURE_RDR_MAX_SEGS]; +static int rt_read_nsegs; + static const char *rcu_torture_writer_state_getname(void) { unsigned int i = READ_ONCE(rcu_torture_writer_state); @@ -278,7 +301,8 @@ struct rcu_torture_ops { void (*init)(void); void (*cleanup)(void); int (*readlock)(void); - void (*read_delay)(struct torture_random_state *rrsp); + void (*read_delay)(struct torture_random_state *rrsp, + struct rt_read_seg *rtrsp); void (*readunlock)(int idx); unsigned long (*get_gp_seq)(void); unsigned long (*gp_diff)(unsigned long new, unsigned long old); @@ -291,6 +315,7 @@ struct rcu_torture_ops { void (*cb_barrier)(void); void (*fqs)(void); void (*stats)(void); + int (*stall_dur)(void); int irq_capable; int can_boost; int extendables; @@ -310,12 +335,13 @@ static int rcu_torture_read_lock(void) __acquires(RCU) return 0; } -static void rcu_read_delay(struct torture_random_state *rrsp) +static void +rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) { unsigned long started; unsigned long completed; const unsigned long shortdelay_us = 200; - const unsigned long longdelay_ms = 50; + unsigned long longdelay_ms = 300; unsigned long long ts; /* We want a short delay sometimes to make a reader delay the grace @@ -325,16 +351,23 @@ static void rcu_read_delay(struct torture_random_state *rrsp) if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) { started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); + if (preempt_count() & (SOFTIRQ_MASK | HARDIRQ_MASK)) + longdelay_ms = 5; /* Avoid triggering BH limits. */ mdelay(longdelay_ms); + rtrsp->rt_delay_ms = longdelay_ms; completed = cur_ops->get_gp_seq(); do_trace_rcu_torture_read(cur_ops->name, NULL, ts, started, completed); } - if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) + if (!(torture_random(rrsp) % (nrealreaders * 2 * shortdelay_us))) { udelay(shortdelay_us); + rtrsp->rt_delay_us = shortdelay_us; + } if (!preempt_count() && - !(torture_random(rrsp) % (nrealreaders * 500))) + !(torture_random(rrsp) % (nrealreaders * 500))) { torture_preempt_schedule(); /* QS only if preemptible. */ + rtrsp->rt_preempted = true; + } } static void rcu_torture_read_unlock(int idx) __releases(RCU) @@ -429,53 +462,14 @@ static struct rcu_torture_ops rcu_ops = { .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, .stats = NULL, + .stall_dur = rcu_jiffies_till_stall_check, .irq_capable = 1, .can_boost = rcu_can_boost(), + .extendables = RCUTORTURE_MAX_EXTEND, .name = "rcu" }; /* - * Definitions for rcu_bh torture testing. - */ - -static int rcu_bh_torture_read_lock(void) __acquires(RCU_BH) -{ - rcu_read_lock_bh(); - return 0; -} - -static void rcu_bh_torture_read_unlock(int idx) __releases(RCU_BH) -{ - rcu_read_unlock_bh(); -} - -static void rcu_bh_torture_deferred_free(struct rcu_torture *p) -{ - call_rcu_bh(&p->rtort_rcu, rcu_torture_cb); -} - -static struct rcu_torture_ops rcu_bh_ops = { - .ttype = RCU_BH_FLAVOR, - .init = rcu_sync_torture_init, - .readlock = rcu_bh_torture_read_lock, - .read_delay = rcu_read_delay, /* just reuse rcu's version. */ - .readunlock = rcu_bh_torture_read_unlock, - .get_gp_seq = rcu_bh_get_gp_seq, - .gp_diff = rcu_seq_diff, - .deferred_free = rcu_bh_torture_deferred_free, - .sync = synchronize_rcu_bh, - .exp_sync = synchronize_rcu_bh_expedited, - .call = call_rcu_bh, - .cb_barrier = rcu_barrier_bh, - .fqs = rcu_bh_force_quiescent_state, - .stats = NULL, - .irq_capable = 1, - .extendables = (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ), - .ext_irq_conflict = RCUTORTURE_RDR_RCU, - .name = "rcu_bh" -}; - -/* * Don't even think about trying any of these in real life!!! * The names includes "busted", and they really means it! * The only purpose of these functions is to provide a buggy RCU @@ -531,7 +525,8 @@ static int srcu_torture_read_lock(void) __acquires(srcu_ctlp) return srcu_read_lock(srcu_ctlp); } -static void srcu_read_delay(struct torture_random_state *rrsp) +static void +srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) { long delay; const long uspertick = 1000000 / HZ; @@ -541,10 +536,12 @@ static void srcu_read_delay(struct torture_random_state *rrsp) delay = torture_random(rrsp) % (nrealreaders * 2 * longdelay * uspertick); - if (!delay && in_task()) + if (!delay && in_task()) { schedule_timeout_interruptible(longdelay); - else - rcu_read_delay(rrsp); + rtrsp->rt_delay_jiffies = longdelay; + } else { + rcu_read_delay(rrsp, rtrsp); + } } static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp) @@ -663,48 +660,6 @@ static struct rcu_torture_ops busted_srcud_ops = { }; /* - * Definitions for sched torture testing. - */ - -static int sched_torture_read_lock(void) -{ - preempt_disable(); - return 0; -} - -static void sched_torture_read_unlock(int idx) -{ - preempt_enable(); -} - -static void rcu_sched_torture_deferred_free(struct rcu_torture *p) -{ - call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); -} - -static struct rcu_torture_ops sched_ops = { - .ttype = RCU_SCHED_FLAVOR, - .init = rcu_sync_torture_init, - .readlock = sched_torture_read_lock, - .read_delay = rcu_read_delay, /* just reuse rcu's version. */ - .readunlock = sched_torture_read_unlock, - .get_gp_seq = rcu_sched_get_gp_seq, - .gp_diff = rcu_seq_diff, - .deferred_free = rcu_sched_torture_deferred_free, - .sync = synchronize_sched, - .exp_sync = synchronize_sched_expedited, - .get_state = get_state_synchronize_sched, - .cond_sync = cond_synchronize_sched, - .call = call_rcu_sched, - .cb_barrier = rcu_barrier_sched, - .fqs = rcu_sched_force_quiescent_state, - .stats = NULL, - .irq_capable = 1, - .extendables = RCUTORTURE_MAX_EXTEND, - .name = "sched" -}; - -/* * Definitions for RCU-tasks torture testing. */ @@ -1116,7 +1071,8 @@ rcu_torture_writer(void *arg) break; } } - rcu_torture_current_version++; + WRITE_ONCE(rcu_torture_current_version, + rcu_torture_current_version + 1); /* Cycle through nesting levels of rcu_expedite_gp() calls. */ if (can_expedite && !(torture_random(&rand) & 0xff & (!!expediting - 1))) { @@ -1132,7 +1088,10 @@ rcu_torture_writer(void *arg) !rcu_gp_is_normal(); } rcu_torture_writer_state = RTWS_STUTTER; - stutter_wait("rcu_torture_writer"); + if (stutter_wait("rcu_torture_writer")) + for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++) + if (list_empty(&rcu_tortures[i].rtort_free)) + WARN_ON_ONCE(1); } while (!torture_must_stop()); /* Reset expediting back to unexpedited. */ if (expediting > 0) @@ -1199,7 +1158,8 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp) * change, do a ->read_delay(). */ static void rcutorture_one_extend(int *readstate, int newstate, - struct torture_random_state *trsp) + struct torture_random_state *trsp, + struct rt_read_seg *rtrsp) { int idxnew = -1; int idxold = *readstate; @@ -1208,6 +1168,7 @@ static void rcutorture_one_extend(int *readstate, int newstate, WARN_ON_ONCE(idxold < 0); WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1); + rtrsp->rt_readstate = newstate; /* First, put new protection in place to avoid critical-section gap. */ if (statesnew & RCUTORTURE_RDR_BH) @@ -1216,6 +1177,10 @@ static void rcutorture_one_extend(int *readstate, int newstate, local_irq_disable(); if (statesnew & RCUTORTURE_RDR_PREEMPT) preempt_disable(); + if (statesnew & RCUTORTURE_RDR_RBH) + rcu_read_lock_bh(); + if (statesnew & RCUTORTURE_RDR_SCHED) + rcu_read_lock_sched(); if (statesnew & RCUTORTURE_RDR_RCU) idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT; @@ -1226,12 +1191,16 @@ static void rcutorture_one_extend(int *readstate, int newstate, local_bh_enable(); if (statesold & RCUTORTURE_RDR_PREEMPT) preempt_enable(); + if (statesold & RCUTORTURE_RDR_RBH) + rcu_read_unlock_bh(); + if (statesold & RCUTORTURE_RDR_SCHED) + rcu_read_unlock_sched(); if (statesold & RCUTORTURE_RDR_RCU) cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT); /* Delay if neither beginning nor end and there was a change. */ if ((statesnew || statesold) && *readstate && newstate) - cur_ops->read_delay(trsp); + cur_ops->read_delay(trsp, rtrsp); /* Update the reader state. */ if (idxnew == -1) @@ -1260,18 +1229,19 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) { int mask = rcutorture_extend_mask_max(); unsigned long randmask1 = torture_random(trsp) >> 8; - unsigned long randmask2 = randmask1 >> 1; + unsigned long randmask2 = randmask1 >> 3; WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT); - /* Half the time lots of bits, half the time only one bit. */ - if (randmask1 & 0x1) + /* Most of the time lots of bits, half the time only one bit. */ + if (!(randmask1 & 0x7)) mask = mask & randmask2; else mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS)); + /* Can't enable bh w/irq disabled. */ if ((mask & RCUTORTURE_RDR_IRQ) && - !(mask & RCUTORTURE_RDR_BH) && - (oldmask & RCUTORTURE_RDR_BH)) - mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */ + ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) || + (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH)))) + mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH; if ((mask & RCUTORTURE_RDR_IRQ) && !(mask & cur_ops->ext_irq_conflict) && (oldmask & cur_ops->ext_irq_conflict)) @@ -1283,20 +1253,25 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp) * Do a randomly selected number of extensions of an existing RCU read-side * critical section. */ -static void rcutorture_loop_extend(int *readstate, - struct torture_random_state *trsp) +static struct rt_read_seg * +rcutorture_loop_extend(int *readstate, struct torture_random_state *trsp, + struct rt_read_seg *rtrsp) { int i; + int j; int mask = rcutorture_extend_mask_max(); WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */ if (!((mask - 1) & mask)) - return; /* Current RCU flavor not extendable. */ - i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS; - while (i--) { + return rtrsp; /* Current RCU reader not extendable. */ + /* Bias towards larger numbers of loops. */ + i = (torture_random(trsp) >> 3); + i = ((i | (i >> 3)) & RCUTORTURE_RDR_MAX_LOOPS) + 1; + for (j = 0; j < i; j++) { mask = rcutorture_extend_mask(*readstate, trsp); - rcutorture_one_extend(readstate, mask, trsp); + rcutorture_one_extend(readstate, mask, trsp, &rtrsp[j]); } + return &rtrsp[j]; } /* @@ -1306,16 +1281,20 @@ static void rcutorture_loop_extend(int *readstate, */ static bool rcu_torture_one_read(struct torture_random_state *trsp) { + int i; unsigned long started; unsigned long completed; int newstate; struct rcu_torture *p; int pipe_count; int readstate = 0; + struct rt_read_seg rtseg[RCUTORTURE_RDR_MAX_SEGS] = { { 0 } }; + struct rt_read_seg *rtrsp = &rtseg[0]; + struct rt_read_seg *rtrsp1; unsigned long long ts; newstate = rcutorture_extend_mask(readstate, trsp); - rcutorture_one_extend(&readstate, newstate, trsp); + rcutorture_one_extend(&readstate, newstate, trsp, rtrsp++); started = cur_ops->get_gp_seq(); ts = rcu_trace_clock_local(); p = rcu_dereference_check(rcu_torture_current, @@ -1325,12 +1304,12 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp) torturing_tasks()); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ - rcutorture_one_extend(&readstate, 0, trsp); + rcutorture_one_extend(&readstate, 0, trsp, rtrsp); return false; } if (p->rtort_mbtest == 0) atomic_inc(&n_rcu_torture_mberror); - rcutorture_loop_extend(&readstate, trsp); + rtrsp = rcutorture_loop_extend(&readstate, trsp, rtrsp); preempt_disable(); pipe_count = p->rtort_pipe_count; if (pipe_count > RCU_TORTURE_PIPE_LEN) { @@ -1351,8 +1330,17 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp) } __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); - rcutorture_one_extend(&readstate, 0, trsp); + rcutorture_one_extend(&readstate, 0, trsp, rtrsp); WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK); + + /* If error or close call, record the sequence of reader protections. */ + if ((pipe_count > 1 || completed > 1) && !xchg(&err_segs_recorded, 1)) { + i = 0; + for (rtrsp1 = &rtseg[0]; rtrsp1 < rtrsp; rtrsp1++) + err_segs[i++] = *rtrsp1; + rt_read_nsegs = i; + } + return true; } @@ -1387,6 +1375,9 @@ static void rcu_torture_timer(struct timer_list *unused) static int rcu_torture_reader(void *arg) { + unsigned long lastsleep = jiffies; + long myid = (long)arg; + int mynumonline = myid; DEFINE_TORTURE_RANDOM(rand); struct timer_list t; @@ -1402,6 +1393,12 @@ rcu_torture_reader(void *arg) } if (!rcu_torture_one_read(&rand)) schedule_timeout_interruptible(HZ); + if (time_after(jiffies, lastsleep)) { + schedule_timeout_interruptible(1); + lastsleep = jiffies + 10; + } + while (num_online_cpus() < mynumonline && !torture_must_stop()) + schedule_timeout_interruptible(HZ / 5); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1655,6 +1652,121 @@ static int __init rcu_torture_stall_init(void) return torture_create_kthread(rcu_torture_stall, NULL, stall_task); } +/* State structure for forward-progress self-propagating RCU callback. */ +struct fwd_cb_state { + struct rcu_head rh; + int stop; +}; + +/* + * Forward-progress self-propagating RCU callback function. Because + * callbacks run from softirq, this function is an implicit RCU read-side + * critical section. + */ +static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp) +{ + struct fwd_cb_state *fcsp = container_of(rhp, struct fwd_cb_state, rh); + + if (READ_ONCE(fcsp->stop)) { + WRITE_ONCE(fcsp->stop, 2); + return; + } + cur_ops->call(&fcsp->rh, rcu_torture_fwd_prog_cb); +} + +/* Carry out grace-period forward-progress testing. */ +static int rcu_torture_fwd_prog(void *args) +{ + unsigned long cver; + unsigned long dur; + struct fwd_cb_state fcs; + unsigned long gps; + int idx; + int sd; + int sd4; + bool selfpropcb = false; + unsigned long stopat; + int tested = 0; + int tested_tries = 0; + static DEFINE_TORTURE_RANDOM(trs); + + VERBOSE_TOROUT_STRING("rcu_torture_fwd_progress task started"); + if (!IS_ENABLED(CONFIG_SMP) || !IS_ENABLED(CONFIG_RCU_BOOST)) + set_user_nice(current, MAX_NICE); + if (cur_ops->call && cur_ops->sync && cur_ops->cb_barrier) { + init_rcu_head_on_stack(&fcs.rh); + selfpropcb = true; + } + do { + schedule_timeout_interruptible(fwd_progress_holdoff * HZ); + if (selfpropcb) { + WRITE_ONCE(fcs.stop, 0); + cur_ops->call(&fcs.rh, rcu_torture_fwd_prog_cb); + } + cver = READ_ONCE(rcu_torture_current_version); + gps = cur_ops->get_gp_seq(); + sd = cur_ops->stall_dur() + 1; + sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div; + dur = sd4 + torture_random(&trs) % (sd - sd4); + stopat = jiffies + dur; + while (time_before(jiffies, stopat) && !torture_must_stop()) { + idx = cur_ops->readlock(); + udelay(10); + cur_ops->readunlock(idx); + if (!fwd_progress_need_resched || need_resched()) + cond_resched(); + } + tested_tries++; + if (!time_before(jiffies, stopat) && !torture_must_stop()) { + tested++; + cver = READ_ONCE(rcu_torture_current_version) - cver; + gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps); + WARN_ON(!cver && gps < 2); + pr_alert("%s: Duration %ld cver %ld gps %ld\n", __func__, dur, cver, gps); + } + if (selfpropcb) { + WRITE_ONCE(fcs.stop, 1); + cur_ops->sync(); /* Wait for running CB to complete. */ + cur_ops->cb_barrier(); /* Wait for queued callbacks. */ + } + /* Avoid slow periods, better to test when busy. */ + stutter_wait("rcu_torture_fwd_prog"); + } while (!torture_must_stop()); + if (selfpropcb) { + WARN_ON(READ_ONCE(fcs.stop) != 2); + destroy_rcu_head_on_stack(&fcs.rh); + } + /* Short runs might not contain a valid forward-progress attempt. */ + WARN_ON(!tested && tested_tries >= 5); + pr_alert("%s: tested %d tested_tries %d\n", __func__, tested, tested_tries); + torture_kthread_stopping("rcu_torture_fwd_prog"); + return 0; +} + +/* If forward-progress checking is requested and feasible, spawn the thread. */ +static int __init rcu_torture_fwd_prog_init(void) +{ + if (!fwd_progress) + return 0; /* Not requested, so don't do it. */ + if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0) { + VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, unsupported by RCU flavor under test"); + return 0; + } + if (stall_cpu > 0) { + VERBOSE_TOROUT_STRING("rcu_torture_fwd_prog_init: Disabled, conflicts with CPU-stall testing"); + if (IS_MODULE(CONFIG_RCU_TORTURE_TESTS)) + return -EINVAL; /* In module, can fail back to user. */ + WARN_ON(1); /* Make sure rcutorture notices conflict. */ + return 0; + } + if (fwd_progress_holdoff <= 0) + fwd_progress_holdoff = 1; + if (fwd_progress_div <= 0) + fwd_progress_div = 4; + return torture_create_kthread(rcu_torture_fwd_prog, + NULL, fwd_prog_task); +} + /* Callback function for RCU barrier testing. */ static void rcu_torture_barrier_cbf(struct rcu_head *rcu) { @@ -1817,6 +1929,7 @@ static enum cpuhp_state rcutor_hp; static void rcu_torture_cleanup(void) { + int firsttime; int flags = 0; unsigned long gp_seq = 0; int i; @@ -1828,6 +1941,7 @@ rcu_torture_cleanup(void) } rcu_torture_barrier_cleanup(); + torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task); torture_stop_kthread(rcu_torture_stall, stall_task); torture_stop_kthread(rcu_torture_writer, writer_task); @@ -1860,7 +1974,7 @@ rcu_torture_cleanup(void) cpuhp_remove_state(rcutor_hp); /* - * Wait for all RCU callbacks to fire, then do flavor-specific + * Wait for all RCU callbacks to fire, then do torture-type-specific * cleanup operations. */ if (cur_ops->cb_barrier != NULL) @@ -1870,6 +1984,33 @@ rcu_torture_cleanup(void) rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ + if (err_segs_recorded) { + pr_alert("Failure/close-call rcutorture reader segments:\n"); + if (rt_read_nsegs == 0) + pr_alert("\t: No segments recorded!!!\n"); + firsttime = 1; + for (i = 0; i < rt_read_nsegs; i++) { + pr_alert("\t%d: %#x ", i, err_segs[i].rt_readstate); + if (err_segs[i].rt_delay_jiffies != 0) { + pr_cont("%s%ldjiffies", firsttime ? "" : "+", + err_segs[i].rt_delay_jiffies); + firsttime = 0; + } + if (err_segs[i].rt_delay_ms != 0) { + pr_cont("%s%ldms", firsttime ? "" : "+", + err_segs[i].rt_delay_ms); + firsttime = 0; + } + if (err_segs[i].rt_delay_us != 0) { + pr_cont("%s%ldus", firsttime ? "" : "+", + err_segs[i].rt_delay_us); + firsttime = 0; + } + pr_cont("%s\n", + err_segs[i].rt_preempted ? "preempted" : ""); + + } + } if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); else if (torture_onoff_failures()) @@ -1939,12 +2080,12 @@ static void rcu_test_debug_objects(void) static int __init rcu_torture_init(void) { - int i; + long i; int cpu; int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { - &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, - &busted_srcud_ops, &sched_ops, &tasks_ops, + &rcu_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops, + &busted_srcud_ops, &tasks_ops, }; if (!torture_init_begin(torture_type, verbose)) @@ -1963,6 +2104,7 @@ rcu_torture_init(void) for (i = 0; i < ARRAY_SIZE(torture_ops); i++) pr_cont(" %s", torture_ops[i]->name); pr_cont("\n"); + WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST)); firsterr = -EINVAL; goto unwind; } @@ -2013,6 +2155,8 @@ rcu_torture_init(void) per_cpu(rcu_torture_batch, cpu)[i] = 0; } } + err_segs_recorded = 0; + rt_read_nsegs = 0; /* Start up the kthreads. */ @@ -2044,7 +2188,7 @@ rcu_torture_init(void) goto unwind; } for (i = 0; i < nrealreaders; i++) { - firsterr = torture_create_kthread(rcu_torture_reader, NULL, + firsterr = torture_create_kthread(rcu_torture_reader, (void *)i, reader_tasks[i]); if (firsterr) goto unwind; @@ -2100,6 +2244,9 @@ rcu_torture_init(void) firsterr = rcu_torture_stall_init(); if (firsterr) goto unwind; + firsterr = rcu_torture_fwd_prog_init(); + if (firsterr) + goto unwind; firsterr = rcu_torture_barrier_init(); if (firsterr) goto unwind; diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 04fc2ed71af8..b46e6683f8c9 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -34,6 +34,8 @@ #include "rcu.h" int rcu_scheduler_active __read_mostly; +static LIST_HEAD(srcu_boot_list); +static bool srcu_init_done; static int init_srcu_struct_fields(struct srcu_struct *sp) { @@ -46,6 +48,7 @@ static int init_srcu_struct_fields(struct srcu_struct *sp) sp->srcu_gp_waiting = false; sp->srcu_idx = 0; INIT_WORK(&sp->srcu_work, srcu_drive_gp); + INIT_LIST_HEAD(&sp->srcu_work.entry); return 0; } @@ -179,8 +182,12 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, *sp->srcu_cb_tail = rhp; sp->srcu_cb_tail = &rhp->next; local_irq_restore(flags); - if (!READ_ONCE(sp->srcu_gp_running)) - schedule_work(&sp->srcu_work); + if (!READ_ONCE(sp->srcu_gp_running)) { + if (likely(srcu_init_done)) + schedule_work(&sp->srcu_work); + else if (list_empty(&sp->srcu_work.entry)) + list_add(&sp->srcu_work.entry, &srcu_boot_list); + } } EXPORT_SYMBOL_GPL(call_srcu); @@ -204,3 +211,21 @@ void __init rcu_scheduler_starting(void) { rcu_scheduler_active = RCU_SCHEDULER_RUNNING; } + +/* + * Queue work for srcu_struct structures with early boot callbacks. + * The work won't actually execute until the workqueue initialization + * phase that takes place after the scheduler starts. + */ +void __init srcu_init(void) +{ + struct srcu_struct *sp; + + srcu_init_done = true; + while (!list_empty(&srcu_boot_list)) { + sp = list_first_entry(&srcu_boot_list, + struct srcu_struct, srcu_work.entry); + list_del_init(&sp->srcu_work.entry); + schedule_work(&sp->srcu_work); + } +} diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 6c9866a854b1..a8846ed7f352 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -51,6 +51,10 @@ module_param(exp_holdoff, ulong, 0444); static ulong counter_wrap_check = (ULONG_MAX >> 2); module_param(counter_wrap_check, ulong, 0444); +/* Early-boot callback-management, so early that no lock is required! */ +static LIST_HEAD(srcu_boot_list); +static bool __read_mostly srcu_init_done; + static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay); static void process_srcu(struct work_struct *work); @@ -105,7 +109,7 @@ static void init_srcu_struct_nodes(struct srcu_struct *sp, bool is_static) rcu_init_levelspread(levelspread, num_rcu_lvl); /* Each pass through this loop initializes one srcu_node structure. */ - rcu_for_each_node_breadth_first(sp, snp) { + srcu_for_each_node_breadth_first(sp, snp) { spin_lock_init(&ACCESS_PRIVATE(snp, lock)); WARN_ON_ONCE(ARRAY_SIZE(snp->srcu_have_cbs) != ARRAY_SIZE(snp->srcu_data_have_cbs)); @@ -235,7 +239,6 @@ static void check_init_srcu_struct(struct srcu_struct *sp) { unsigned long flags; - WARN_ON_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INIT); /* The smp_load_acquire() pairs with the smp_store_release(). */ if (!rcu_seq_state(smp_load_acquire(&sp->srcu_gp_seq_needed))) /*^^^*/ return; /* Already initialized. */ @@ -561,7 +564,7 @@ static void srcu_gp_end(struct srcu_struct *sp) /* Initiate callback invocation as needed. */ idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); - rcu_for_each_node_breadth_first(sp, snp) { + srcu_for_each_node_breadth_first(sp, snp) { spin_lock_irq_rcu_node(snp); cbs = false; last_lvl = snp >= sp->level[rcu_num_lvls - 1]; @@ -701,7 +704,11 @@ static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp, rcu_seq_state(sp->srcu_gp_seq) == SRCU_STATE_IDLE) { WARN_ON_ONCE(ULONG_CMP_GE(sp->srcu_gp_seq, sp->srcu_gp_seq_needed)); srcu_gp_start(sp); - queue_delayed_work(rcu_gp_wq, &sp->work, srcu_get_delay(sp)); + if (likely(srcu_init_done)) + queue_delayed_work(rcu_gp_wq, &sp->work, + srcu_get_delay(sp)); + else if (list_empty(&sp->work.work.entry)) + list_add(&sp->work.work.entry, &srcu_boot_list); } spin_unlock_irqrestore_rcu_node(sp, flags); } @@ -980,7 +987,7 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); * There are memory-ordering constraints implied by synchronize_srcu(). * On systems with more than one CPU, when synchronize_srcu() returns, * each CPU is guaranteed to have executed a full memory barrier since - * the end of its last corresponding SRCU-sched read-side critical section + * the end of its last corresponding SRCU read-side critical section * whose beginning preceded the call to synchronize_srcu(). In addition, * each CPU having an SRCU read-side critical section that extends beyond * the return from synchronize_srcu() is guaranteed to have executed a @@ -1308,3 +1315,17 @@ static int __init srcu_bootup_announce(void) return 0; } early_initcall(srcu_bootup_announce); + +void __init srcu_init(void) +{ + struct srcu_struct *sp; + + srcu_init_done = true; + while (!list_empty(&srcu_boot_list)) { + sp = list_first_entry(&srcu_boot_list, struct srcu_struct, + work.work.entry); + check_init_srcu_struct(sp); + list_del_init(&sp->work.work.entry); + queue_work(rcu_gp_wq, &sp->work.work); + } +} diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index befc9321a89c..5f5963ba313e 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -46,69 +46,27 @@ struct rcu_ctrlblk { }; /* Definition for rcupdate control block. */ -static struct rcu_ctrlblk rcu_sched_ctrlblk = { - .donetail = &rcu_sched_ctrlblk.rcucblist, - .curtail = &rcu_sched_ctrlblk.rcucblist, +static struct rcu_ctrlblk rcu_ctrlblk = { + .donetail = &rcu_ctrlblk.rcucblist, + .curtail = &rcu_ctrlblk.rcucblist, }; -static struct rcu_ctrlblk rcu_bh_ctrlblk = { - .donetail = &rcu_bh_ctrlblk.rcucblist, - .curtail = &rcu_bh_ctrlblk.rcucblist, -}; - -void rcu_barrier_bh(void) -{ - wait_rcu_gp(call_rcu_bh); -} -EXPORT_SYMBOL(rcu_barrier_bh); - -void rcu_barrier_sched(void) -{ - wait_rcu_gp(call_rcu_sched); -} -EXPORT_SYMBOL(rcu_barrier_sched); - -/* - * Helper function for rcu_sched_qs() and rcu_bh_qs(). - * Also irqs are disabled to avoid confusion due to interrupt handlers - * invoking call_rcu(). - */ -static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) -{ - if (rcp->donetail != rcp->curtail) { - rcp->donetail = rcp->curtail; - return 1; - } - - return 0; -} - -/* - * Record an rcu quiescent state. And an rcu_bh quiescent state while we - * are at it, given that any rcu quiescent state is also an rcu_bh - * quiescent state. Use "+" instead of "||" to defeat short circuiting. - */ -void rcu_sched_qs(void) +void rcu_barrier(void) { - unsigned long flags; - - local_irq_save(flags); - if (rcu_qsctr_help(&rcu_sched_ctrlblk) + - rcu_qsctr_help(&rcu_bh_ctrlblk)) - raise_softirq(RCU_SOFTIRQ); - local_irq_restore(flags); + wait_rcu_gp(call_rcu); } +EXPORT_SYMBOL(rcu_barrier); -/* - * Record an rcu_bh quiescent state. - */ -void rcu_bh_qs(void) +/* Record an rcu quiescent state. */ +void rcu_qs(void) { unsigned long flags; local_irq_save(flags); - if (rcu_qsctr_help(&rcu_bh_ctrlblk)) + if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) { + rcu_ctrlblk.donetail = rcu_ctrlblk.curtail; raise_softirq(RCU_SOFTIRQ); + } local_irq_restore(flags); } @@ -120,34 +78,33 @@ void rcu_bh_qs(void) */ void rcu_check_callbacks(int user) { - if (user) - rcu_sched_qs(); - if (user || !in_softirq()) - rcu_bh_qs(); + if (user) { + rcu_qs(); + } else if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) { + set_tsk_need_resched(current); + set_preempt_need_resched(); + } } -/* - * Invoke the RCU callbacks on the specified rcu_ctrlkblk structure - * whose grace period has elapsed. - */ -static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) +/* Invoke the RCU callbacks whose grace period has elapsed. */ +static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { struct rcu_head *next, *list; unsigned long flags; /* Move the ready-to-invoke callbacks to a local list. */ local_irq_save(flags); - if (rcp->donetail == &rcp->rcucblist) { + if (rcu_ctrlblk.donetail == &rcu_ctrlblk.rcucblist) { /* No callbacks ready, so just leave. */ local_irq_restore(flags); return; } - list = rcp->rcucblist; - rcp->rcucblist = *rcp->donetail; - *rcp->donetail = NULL; - if (rcp->curtail == rcp->donetail) - rcp->curtail = &rcp->rcucblist; - rcp->donetail = &rcp->rcucblist; + list = rcu_ctrlblk.rcucblist; + rcu_ctrlblk.rcucblist = *rcu_ctrlblk.donetail; + *rcu_ctrlblk.donetail = NULL; + if (rcu_ctrlblk.curtail == rcu_ctrlblk.donetail) + rcu_ctrlblk.curtail = &rcu_ctrlblk.rcucblist; + rcu_ctrlblk.donetail = &rcu_ctrlblk.rcucblist; local_irq_restore(flags); /* Invoke the callbacks on the local list. */ @@ -162,37 +119,31 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) } } -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) -{ - __rcu_process_callbacks(&rcu_sched_ctrlblk); - __rcu_process_callbacks(&rcu_bh_ctrlblk); -} - /* * Wait for a grace period to elapse. But it is illegal to invoke - * synchronize_sched() from within an RCU read-side critical section. - * Therefore, any legal call to synchronize_sched() is a quiescent - * state, and so on a UP system, synchronize_sched() need do nothing. - * Ditto for synchronize_rcu_bh(). (But Lai Jiangshan points out the - * benefits of doing might_sleep() to reduce latency.) + * synchronize_rcu() from within an RCU read-side critical section. + * Therefore, any legal call to synchronize_rcu() is a quiescent + * state, and so on a UP system, synchronize_rcu() need do nothing. + * (But Lai Jiangshan points out the benefits of doing might_sleep() + * to reduce latency.) * * Cool, huh? (Due to Josh Triplett.) */ -void synchronize_sched(void) +void synchronize_rcu(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_sched() in RCU read-side critical section"); + "Illegal synchronize_rcu() in RCU read-side critical section"); } -EXPORT_SYMBOL_GPL(synchronize_sched); +EXPORT_SYMBOL_GPL(synchronize_rcu); /* - * Helper function for call_rcu() and call_rcu_bh(). + * Post an RCU callback to be invoked after the end of an RCU grace + * period. But since we have but one CPU, that would be after any + * quiescent state. */ -static void __call_rcu(struct rcu_head *head, - rcu_callback_t func, - struct rcu_ctrlblk *rcp) +void call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; @@ -201,39 +152,20 @@ static void __call_rcu(struct rcu_head *head, head->next = NULL; local_irq_save(flags); - *rcp->curtail = head; - rcp->curtail = &head->next; + *rcu_ctrlblk.curtail = head; + rcu_ctrlblk.curtail = &head->next; local_irq_restore(flags); if (unlikely(is_idle_task(current))) { - /* force scheduling for rcu_sched_qs() */ + /* force scheduling for rcu_qs() */ resched_cpu(0); } } - -/* - * Post an RCU callback to be invoked after the end of an RCU-sched grace - * period. But since we have but one CPU, that would be after any - * quiescent state. - */ -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func, &rcu_sched_ctrlblk); -} -EXPORT_SYMBOL_GPL(call_rcu_sched); - -/* - * Post an RCU bottom-half callback to be invoked after any subsequent - * quiescent state. - */ -void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func, &rcu_bh_ctrlblk); -} -EXPORT_SYMBOL_GPL(call_rcu_bh); +EXPORT_SYMBOL_GPL(call_rcu); void __init rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); rcu_early_boot_tests(); + srcu_init(); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0b760c1369f7..121f833acd04 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -61,6 +61,7 @@ #include <linux/trace_events.h> #include <linux/suspend.h> #include <linux/ftrace.h> +#include <linux/tick.h> #include "tree.h" #include "rcu.h" @@ -73,45 +74,31 @@ /* Data structures. */ /* - * In order to export the rcu_state name to the tracing tools, it - * needs to be added in the __tracepoint_string section. - * This requires defining a separate variable tp_<sname>_varname - * that points to the string being used, and this will allow - * the tracing userspace tools to be able to decipher the string - * address to the matching string. + * Steal a bit from the bottom of ->dynticks for idle entry/exit + * control. Initially this is for TLB flushing. */ -#ifdef CONFIG_TRACING -# define DEFINE_RCU_TPS(sname) \ -static char sname##_varname[] = #sname; \ -static const char *tp_##sname##_varname __used __tracepoint_string = sname##_varname; -# define RCU_STATE_NAME(sname) sname##_varname -#else -# define DEFINE_RCU_TPS(sname) -# define RCU_STATE_NAME(sname) __stringify(sname) +#define RCU_DYNTICK_CTRL_MASK 0x1 +#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1) +#ifndef rcu_eqs_special_exit +#define rcu_eqs_special_exit() do { } while (0) #endif -#define RCU_STATE_INITIALIZER(sname, sabbr, cr) \ -DEFINE_RCU_TPS(sname) \ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, sname##_data); \ -struct rcu_state sname##_state = { \ - .level = { &sname##_state.node[0] }, \ - .rda = &sname##_data, \ - .call = cr, \ - .gp_state = RCU_GP_IDLE, \ - .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \ - .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .name = RCU_STATE_NAME(sname), \ - .abbr = sabbr, \ - .exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \ - .exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \ - .ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \ -} - -RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched); -RCU_STATE_INITIALIZER(rcu_bh, 'b', call_rcu_bh); - -static struct rcu_state *const rcu_state_p; -LIST_HEAD(rcu_struct_flavors); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { + .dynticks_nesting = 1, + .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, + .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), +}; +struct rcu_state rcu_state = { + .level = { &rcu_state.node[0] }, + .gp_state = RCU_GP_IDLE, + .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, + .barrier_mutex = __MUTEX_INITIALIZER(rcu_state.barrier_mutex), + .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), +}; /* Dump rcu_node combining tree at boot to verify correct setup. */ static bool dump_tree; @@ -158,16 +145,14 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active); */ static int rcu_scheduler_fully_active __read_mostly; -static void -rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long gps, unsigned long flags); +static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, + unsigned long gps, unsigned long flags); static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); -static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); -static void rcu_report_exp_rdp(struct rcu_state *rsp, - struct rcu_data *rdp, bool wake); +static void invoke_rcu_callbacks(struct rcu_data *rdp); +static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); /* rcuc/rcub kthread realtime priority */ @@ -183,7 +168,7 @@ module_param(gp_init_delay, int, 0444); static int gp_cleanup_delay; module_param(gp_cleanup_delay, int, 0444); -/* Retreive RCU kthreads priority for rcutorture */ +/* Retrieve RCU kthreads priority for rcutorture */ int rcu_get_gp_kthreads_prio(void) { return kthread_prio; @@ -217,67 +202,24 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. */ -static int rcu_gp_in_progress(struct rcu_state *rsp) +static int rcu_gp_in_progress(void) { - return rcu_seq_state(rcu_seq_current(&rsp->gp_seq)); -} - -/* - * Note a quiescent state. Because we do not need to know - * how many quiescent states passed, just if there was at least - * one since the start of the grace period, this just sets a flag. - * The caller must have disabled preemption. - */ -void rcu_sched_qs(void) -{ - RCU_LOCKDEP_WARN(preemptible(), "rcu_sched_qs() invoked with preemption enabled!!!"); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) - return; - trace_rcu_grace_period(TPS("rcu_sched"), - __this_cpu_read(rcu_sched_data.gp_seq), - TPS("cpuqs")); - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false); - if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) - return; - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(&rcu_sched_data), true); + return rcu_seq_state(rcu_seq_current(&rcu_state.gp_seq)); } -void rcu_bh_qs(void) +void rcu_softirq_qs(void) { - RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); - if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) { - trace_rcu_grace_period(TPS("rcu_bh"), - __this_cpu_read(rcu_bh_data.gp_seq), - TPS("cpuqs")); - __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); - } + rcu_qs(); + rcu_preempt_deferred_qs(current); } /* - * Steal a bit from the bottom of ->dynticks for idle entry/exit - * control. Initially this is for TLB flushing. - */ -#define RCU_DYNTICK_CTRL_MASK 0x1 -#define RCU_DYNTICK_CTRL_CTR (RCU_DYNTICK_CTRL_MASK + 1) -#ifndef rcu_eqs_special_exit -#define rcu_eqs_special_exit() do { } while (0) -#endif - -static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = 1, - .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, - .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), -}; - -/* * Record entry into an extended quiescent state. This is only to be * called when not already in an extended quiescent state. */ static void rcu_dynticks_eqs_enter(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); int seq; /* @@ -285,7 +227,7 @@ static void rcu_dynticks_eqs_enter(void) * critical sections, and we also must force ordering with the * next idle sojourn. */ - seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); /* Better be in an extended quiescent state! */ WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && (seq & RCU_DYNTICK_CTRL_CTR)); @@ -300,7 +242,7 @@ static void rcu_dynticks_eqs_enter(void) */ static void rcu_dynticks_eqs_exit(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); int seq; /* @@ -308,11 +250,11 @@ static void rcu_dynticks_eqs_exit(void) * and we also must force ordering with the next RCU read-side * critical section. */ - seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + seq = atomic_add_return(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(seq & RCU_DYNTICK_CTRL_CTR)); if (seq & RCU_DYNTICK_CTRL_MASK) { - atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks); + atomic_andnot(RCU_DYNTICK_CTRL_MASK, &rdp->dynticks); smp_mb__after_atomic(); /* _exit after clearing mask. */ /* Prefer duplicate flushes to losing a flush. */ rcu_eqs_special_exit(); @@ -331,11 +273,11 @@ static void rcu_dynticks_eqs_exit(void) */ static void rcu_dynticks_eqs_online(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - if (atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR) + if (atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR) return; - atomic_add(RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + atomic_add(RCU_DYNTICK_CTRL_CTR, &rdp->dynticks); } /* @@ -345,18 +287,18 @@ static void rcu_dynticks_eqs_online(void) */ bool rcu_dynticks_curr_cpu_in_eqs(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - return !(atomic_read(&rdtp->dynticks) & RCU_DYNTICK_CTRL_CTR); + return !(atomic_read(&rdp->dynticks) & RCU_DYNTICK_CTRL_CTR); } /* * Snapshot the ->dynticks counter with full ordering so as to allow * stable comparison of this counter with past and future snapshots. */ -int rcu_dynticks_snap(struct rcu_dynticks *rdtp) +int rcu_dynticks_snap(struct rcu_data *rdp) { - int snap = atomic_add_return(0, &rdtp->dynticks); + int snap = atomic_add_return(0, &rdp->dynticks); return snap & ~RCU_DYNTICK_CTRL_MASK; } @@ -371,13 +313,13 @@ static bool rcu_dynticks_in_eqs(int snap) } /* - * Return true if the CPU corresponding to the specified rcu_dynticks + * Return true if the CPU corresponding to the specified rcu_data * structure has spent some time in an extended quiescent state since * rcu_dynticks_snap() returned the specified snapshot. */ -static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap) +static bool rcu_dynticks_in_eqs_since(struct rcu_data *rdp, int snap) { - return snap != rcu_dynticks_snap(rdtp); + return snap != rcu_dynticks_snap(rdp); } /* @@ -391,14 +333,14 @@ bool rcu_eqs_special_set(int cpu) { int old; int new; - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); do { - old = atomic_read(&rdtp->dynticks); + old = atomic_read(&rdp->dynticks); if (old & RCU_DYNTICK_CTRL_CTR) return false; new = old | RCU_DYNTICK_CTRL_MASK; - } while (atomic_cmpxchg(&rdtp->dynticks, old, new) != old); + } while (atomic_cmpxchg(&rdp->dynticks, old, new) != old); return true; } @@ -413,82 +355,30 @@ bool rcu_eqs_special_set(int cpu) * * The caller must have disabled interrupts and must not be idle. */ -static void rcu_momentary_dyntick_idle(void) +static void __maybe_unused rcu_momentary_dyntick_idle(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); int special; - raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false); - special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks); + raw_cpu_write(rcu_data.rcu_need_heavy_qs, false); + special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, + &this_cpu_ptr(&rcu_data)->dynticks); /* It is illegal to call this from idle state. */ WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR)); + rcu_preempt_deferred_qs(current); } -/* - * Note a context switch. This is a quiescent state for RCU-sched, - * and requires special handling for preemptible RCU. - * The caller must have disabled interrupts. - */ -void rcu_note_context_switch(bool preempt) -{ - barrier(); /* Avoid RCU read-side critical sections leaking down. */ - trace_rcu_utilization(TPS("Start context switch")); - rcu_sched_qs(); - rcu_preempt_note_context_switch(preempt); - /* Load rcu_urgent_qs before other flags. */ - if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) - goto out; - this_cpu_write(rcu_dynticks.rcu_urgent_qs, false); - if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) - rcu_momentary_dyntick_idle(); - this_cpu_inc(rcu_dynticks.rcu_qs_ctr); - if (!preempt) - rcu_tasks_qs(current); -out: - trace_rcu_utilization(TPS("End context switch")); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ -} -EXPORT_SYMBOL_GPL(rcu_note_context_switch); - -/* - * Register a quiescent state for all RCU flavors. If there is an - * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight - * dyntick-idle quiescent state visible to other CPUs (but only for those - * RCU flavors in desperate need of a quiescent state, which will normally - * be none of them). Either way, do a lightweight quiescent state for - * all RCU flavors. - * - * The barrier() calls are redundant in the common case when this is - * called externally, but just in case this is called from within this - * file. +/** + * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle * + * If the current CPU is idle or running at a first-level (not nested) + * interrupt from idle, return true. The caller must have at least + * disabled preemption. */ -void rcu_all_qs(void) +static int rcu_is_cpu_rrupt_from_idle(void) { - unsigned long flags; - - if (!raw_cpu_read(rcu_dynticks.rcu_urgent_qs)) - return; - preempt_disable(); - /* Load rcu_urgent_qs before other flags. */ - if (!smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) { - preempt_enable(); - return; - } - this_cpu_write(rcu_dynticks.rcu_urgent_qs, false); - barrier(); /* Avoid RCU read-side critical sections leaking down. */ - if (unlikely(raw_cpu_read(rcu_dynticks.rcu_need_heavy_qs))) { - local_irq_save(flags); - rcu_momentary_dyntick_idle(); - local_irq_restore(flags); - } - if (unlikely(raw_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))) - rcu_sched_qs(); - this_cpu_inc(rcu_dynticks.rcu_qs_ctr); - barrier(); /* Avoid RCU read-side critical sections leaking up. */ - preempt_enable(); + return __this_cpu_read(rcu_data.dynticks_nesting) <= 0 && + __this_cpu_read(rcu_data.dynticks_nmi_nesting) <= 1; } -EXPORT_SYMBOL_GPL(rcu_all_qs); #define DEFAULT_RCU_BLIMIT 10 /* Maximum callbacks per rcu_do_batch. */ static long blimit = DEFAULT_RCU_BLIMIT; @@ -505,13 +395,47 @@ static ulong jiffies_till_first_fqs = ULONG_MAX; static ulong jiffies_till_next_fqs = ULONG_MAX; static bool rcu_kick_kthreads; +/* + * How long the grace period must be before we start recruiting + * quiescent-state help from rcu_note_context_switch(). + */ +static ulong jiffies_till_sched_qs = ULONG_MAX; +module_param(jiffies_till_sched_qs, ulong, 0444); +static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */ +module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */ + +/* + * Make sure that we give the grace-period kthread time to detect any + * idle CPUs before taking active measures to force quiescent states. + * However, don't go below 100 milliseconds, adjusted upwards for really + * large systems. + */ +static void adjust_jiffies_till_sched_qs(void) +{ + unsigned long j; + + /* If jiffies_till_sched_qs was specified, respect the request. */ + if (jiffies_till_sched_qs != ULONG_MAX) { + WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs); + return; + } + j = READ_ONCE(jiffies_till_first_fqs) + + 2 * READ_ONCE(jiffies_till_next_fqs); + if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV) + j = HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV; + pr_info("RCU calculated value of scheduler-enlistment delay is %ld jiffies.\n", j); + WRITE_ONCE(jiffies_to_sched_qs, j); +} + static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp) { ulong j; int ret = kstrtoul(val, 0, &j); - if (!ret) + if (!ret) { WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j); + adjust_jiffies_till_sched_qs(); + } return ret; } @@ -520,8 +444,10 @@ static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param ulong j; int ret = kstrtoul(val, 0, &j); - if (!ret) + if (!ret) { WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1)); + adjust_jiffies_till_sched_qs(); + } return ret; } @@ -539,15 +465,8 @@ module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_fi module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644); module_param(rcu_kick_kthreads, bool, 0644); -/* - * How long the grace period must be before we start recruiting - * quiescent-state help from rcu_note_context_switch(). - */ -static ulong jiffies_till_sched_qs = HZ / 10; -module_param(jiffies_till_sched_qs, ulong, 0444); - -static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)); -static void force_quiescent_state(struct rcu_state *rsp); +static void force_qs_rnp(int (*f)(struct rcu_data *rdp)); +static void force_quiescent_state(void); static int rcu_pending(void); /* @@ -555,29 +474,11 @@ static int rcu_pending(void); */ unsigned long rcu_get_gp_seq(void) { - return READ_ONCE(rcu_state_p->gp_seq); + return READ_ONCE(rcu_state.gp_seq); } EXPORT_SYMBOL_GPL(rcu_get_gp_seq); /* - * Return the number of RCU-sched GPs completed thus far for debug & stats. - */ -unsigned long rcu_sched_get_gp_seq(void) -{ - return READ_ONCE(rcu_sched_state.gp_seq); -} -EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq); - -/* - * Return the number of RCU-bh GPs completed thus far for debug & stats. - */ -unsigned long rcu_bh_get_gp_seq(void) -{ - return READ_ONCE(rcu_bh_state.gp_seq); -} -EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); - -/* * Return the number of RCU expedited batches completed thus far for * debug & stats. Odd numbers mean that a batch is in progress, even * numbers mean idle. The value returned will thus be roughly double @@ -585,48 +486,20 @@ EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq); */ unsigned long rcu_exp_batches_completed(void) { - return rcu_state_p->expedited_sequence; + return rcu_state.expedited_sequence; } EXPORT_SYMBOL_GPL(rcu_exp_batches_completed); /* - * Return the number of RCU-sched expedited batches completed thus far - * for debug & stats. Similar to rcu_exp_batches_completed(). - */ -unsigned long rcu_exp_batches_completed_sched(void) -{ - return rcu_sched_state.expedited_sequence; -} -EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); - -/* * Force a quiescent state. */ void rcu_force_quiescent_state(void) { - force_quiescent_state(rcu_state_p); + force_quiescent_state(); } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); /* - * Force a quiescent state for RCU BH. - */ -void rcu_bh_force_quiescent_state(void) -{ - force_quiescent_state(&rcu_bh_state); -} -EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); - -/* - * Force a quiescent state for RCU-sched. - */ -void rcu_sched_force_quiescent_state(void) -{ - force_quiescent_state(&rcu_sched_state); -} -EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); - -/* * Show the state of the grace-period kthreads. */ void show_rcu_gp_kthreads(void) @@ -634,31 +507,28 @@ void show_rcu_gp_kthreads(void) int cpu; struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; - for_each_rcu_flavor(rsp) { - pr_info("%s: wait state: %d ->state: %#lx\n", - rsp->name, rsp->gp_state, rsp->gp_kthread->state); - rcu_for_each_node_breadth_first(rsp, rnp) { - if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed)) - continue; - pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n", - rnp->grplo, rnp->grphi, rnp->gp_seq, - rnp->gp_seq_needed); - if (!rcu_is_leaf_node(rnp)) + pr_info("%s: wait state: %d ->state: %#lx\n", rcu_state.name, + rcu_state.gp_state, rcu_state.gp_kthread->state); + rcu_for_each_node_breadth_first(rnp) { + if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed)) + continue; + pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n", + rnp->grplo, rnp->grphi, rnp->gp_seq, + rnp->gp_seq_needed); + if (!rcu_is_leaf_node(rnp)) + continue; + for_each_leaf_node_possible_cpu(rnp, cpu) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->gpwrap || + ULONG_CMP_GE(rcu_state.gp_seq, + rdp->gp_seq_needed)) continue; - for_each_leaf_node_possible_cpu(rnp, cpu) { - rdp = per_cpu_ptr(rsp->rda, cpu); - if (rdp->gpwrap || - ULONG_CMP_GE(rsp->gp_seq, - rdp->gp_seq_needed)) - continue; - pr_info("\tcpu %d ->gp_seq_needed %lu\n", - cpu, rdp->gp_seq_needed); - } + pr_info("\tcpu %d ->gp_seq_needed %lu\n", + cpu, rdp->gp_seq_needed); } - /* sched_show_task(rsp->gp_kthread); */ } + /* sched_show_task(rcu_state.gp_kthread); */ } EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); @@ -668,34 +538,25 @@ EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads); void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, unsigned long *gp_seq) { - struct rcu_state *rsp = NULL; - switch (test_type) { case RCU_FLAVOR: - rsp = rcu_state_p; - break; case RCU_BH_FLAVOR: - rsp = &rcu_bh_state; - break; case RCU_SCHED_FLAVOR: - rsp = &rcu_sched_state; + *flags = READ_ONCE(rcu_state.gp_flags); + *gp_seq = rcu_seq_current(&rcu_state.gp_seq); break; default: break; } - if (rsp == NULL) - return; - *flags = READ_ONCE(rsp->gp_flags); - *gp_seq = rcu_seq_current(&rsp->gp_seq); } EXPORT_SYMBOL_GPL(rcutorture_get_gp_data); /* - * Return the root node of the specified rcu_state structure. + * Return the root node of the rcu_state structure. */ -static struct rcu_node *rcu_get_root(struct rcu_state *rsp) +static struct rcu_node *rcu_get_root(void) { - return &rsp->node[0]; + return &rcu_state.node[0]; } /* @@ -708,28 +569,25 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) */ static void rcu_eqs_enter(bool user) { - struct rcu_state *rsp; - struct rcu_data *rdp; - struct rcu_dynticks *rdtp; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); - rdtp = this_cpu_ptr(&rcu_dynticks); - WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); + WARN_ON_ONCE(rdp->dynticks_nmi_nesting != DYNTICK_IRQ_NONIDLE); + WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && - rdtp->dynticks_nesting == 0); - if (rdtp->dynticks_nesting != 1) { - rdtp->dynticks_nesting--; + rdp->dynticks_nesting == 0); + if (rdp->dynticks_nesting != 1) { + rdp->dynticks_nesting--; return; } lockdep_assert_irqs_disabled(); - trace_rcu_dyntick(TPS("Start"), rdtp->dynticks_nesting, 0, rdtp->dynticks); + trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - do_nocb_deferred_wakeup(rdp); - } + rdp = this_cpu_ptr(&rcu_data); + do_nocb_deferred_wakeup(rdp); rcu_prepare_for_idle(); - WRITE_ONCE(rdtp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ + rcu_preempt_deferred_qs(current); + WRITE_ONCE(rdp->dynticks_nesting, 0); /* Avoid irq-access tearing. */ rcu_dynticks_eqs_enter(); rcu_dynticks_task_enter(); } @@ -770,44 +628,61 @@ void rcu_user_enter(void) } #endif /* CONFIG_NO_HZ_FULL */ -/** - * rcu_nmi_exit - inform RCU of exit from NMI context - * +/* * If we are returning from the outermost NMI handler that interrupted an - * RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting + * RCU-idle period, update rdp->dynticks and rdp->dynticks_nmi_nesting * to let the RCU grace-period handling know that the CPU is back to * being RCU-idle. * - * If you add or remove a call to rcu_nmi_exit(), be sure to test + * If you add or remove a call to rcu_nmi_exit_common(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ -void rcu_nmi_exit(void) +static __always_inline void rcu_nmi_exit_common(bool irq) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); /* * Check for ->dynticks_nmi_nesting underflow and bad ->dynticks. * (We are exiting an NMI handler, so RCU better be paying attention * to us!) */ - WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0); + WARN_ON_ONCE(rdp->dynticks_nmi_nesting <= 0); WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs()); /* * If the nesting level is not 1, the CPU wasn't RCU-idle, so * leave it in non-RCU-idle state. */ - if (rdtp->dynticks_nmi_nesting != 1) { - trace_rcu_dyntick(TPS("--="), rdtp->dynticks_nmi_nesting, rdtp->dynticks_nmi_nesting - 2, rdtp->dynticks); - WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* No store tearing. */ - rdtp->dynticks_nmi_nesting - 2); + if (rdp->dynticks_nmi_nesting != 1) { + trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks); + WRITE_ONCE(rdp->dynticks_nmi_nesting, /* No store tearing. */ + rdp->dynticks_nmi_nesting - 2); return; } /* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */ - trace_rcu_dyntick(TPS("Startirq"), rdtp->dynticks_nmi_nesting, 0, rdtp->dynticks); - WRITE_ONCE(rdtp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ + trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks); + WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ + + if (irq) + rcu_prepare_for_idle(); + rcu_dynticks_eqs_enter(); + + if (irq) + rcu_dynticks_task_enter(); +} + +/** + * rcu_nmi_exit - inform RCU of exit from NMI context + * @irq: Is this call from rcu_irq_exit? + * + * If you add or remove a call to rcu_nmi_exit(), be sure to test + * with CONFIG_RCU_EQS_DEBUG=y. + */ +void rcu_nmi_exit(void) +{ + rcu_nmi_exit_common(false); } /** @@ -831,14 +706,8 @@ void rcu_nmi_exit(void) */ void rcu_irq_exit(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - lockdep_assert_irqs_disabled(); - if (rdtp->dynticks_nmi_nesting == 1) - rcu_prepare_for_idle(); - rcu_nmi_exit(); - if (rdtp->dynticks_nmi_nesting == 0) - rcu_dynticks_task_enter(); + rcu_nmi_exit_common(true); } /* @@ -866,24 +735,25 @@ void rcu_irq_exit_irqson(void) */ static void rcu_eqs_exit(bool user) { - struct rcu_dynticks *rdtp; + struct rcu_data *rdp; long oldval; lockdep_assert_irqs_disabled(); - rdtp = this_cpu_ptr(&rcu_dynticks); - oldval = rdtp->dynticks_nesting; + rdp = this_cpu_ptr(&rcu_data); + oldval = rdp->dynticks_nesting; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && oldval < 0); if (oldval) { - rdtp->dynticks_nesting++; + rdp->dynticks_nesting++; return; } rcu_dynticks_task_exit(); rcu_dynticks_eqs_exit(); rcu_cleanup_after_idle(); - trace_rcu_dyntick(TPS("End"), rdtp->dynticks_nesting, 1, rdtp->dynticks); + trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); - WRITE_ONCE(rdtp->dynticks_nesting, 1); - WRITE_ONCE(rdtp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); + WRITE_ONCE(rdp->dynticks_nesting, 1); + WARN_ON_ONCE(rdp->dynticks_nmi_nesting); + WRITE_ONCE(rdp->dynticks_nmi_nesting, DYNTICK_IRQ_NONIDLE); } /** @@ -921,24 +791,25 @@ void rcu_user_exit(void) #endif /* CONFIG_NO_HZ_FULL */ /** - * rcu_nmi_enter - inform RCU of entry to NMI context + * rcu_nmi_enter_common - inform RCU of entry to NMI context + * @irq: Is this call from rcu_irq_enter? * - * If the CPU was idle from RCU's viewpoint, update rdtp->dynticks and - * rdtp->dynticks_nmi_nesting to let the RCU grace-period handling know + * If the CPU was idle from RCU's viewpoint, update rdp->dynticks and + * rdp->dynticks_nmi_nesting to let the RCU grace-period handling know * that the CPU is active. This implementation permits nested NMIs, as * long as the nesting level does not overflow an int. (You will probably * run out of stack space first.) * - * If you add or remove a call to rcu_nmi_enter(), be sure to test + * If you add or remove a call to rcu_nmi_enter_common(), be sure to test * with CONFIG_RCU_EQS_DEBUG=y. */ -void rcu_nmi_enter(void) +static __always_inline void rcu_nmi_enter_common(bool irq) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); long incby = 2; /* Complain about underflow. */ - WARN_ON_ONCE(rdtp->dynticks_nmi_nesting < 0); + WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0); /* * If idle from RCU viewpoint, atomically increment ->dynticks @@ -949,18 +820,34 @@ void rcu_nmi_enter(void) * period (observation due to Andy Lutomirski). */ if (rcu_dynticks_curr_cpu_in_eqs()) { + + if (irq) + rcu_dynticks_task_exit(); + rcu_dynticks_eqs_exit(); + + if (irq) + rcu_cleanup_after_idle(); + incby = 1; } trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), - rdtp->dynticks_nmi_nesting, - rdtp->dynticks_nmi_nesting + incby, rdtp->dynticks); - WRITE_ONCE(rdtp->dynticks_nmi_nesting, /* Prevent store tearing. */ - rdtp->dynticks_nmi_nesting + incby); + rdp->dynticks_nmi_nesting, + rdp->dynticks_nmi_nesting + incby, rdp->dynticks); + WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */ + rdp->dynticks_nmi_nesting + incby); barrier(); } /** + * rcu_nmi_enter - inform RCU of entry to NMI context + */ +void rcu_nmi_enter(void) +{ + rcu_nmi_enter_common(false); +} + +/** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle * * Enter an interrupt handler, which might possibly result in exiting @@ -984,14 +871,8 @@ void rcu_nmi_enter(void) */ void rcu_irq_enter(void) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); - lockdep_assert_irqs_disabled(); - if (rdtp->dynticks_nmi_nesting == 0) - rcu_dynticks_task_exit(); - rcu_nmi_enter(); - if (rdtp->dynticks_nmi_nesting == 1) - rcu_cleanup_after_idle(); + rcu_nmi_enter_common(true); } /* @@ -1043,7 +924,7 @@ void rcu_request_urgent_qs_task(struct task_struct *t) cpu = task_cpu(t); if (!task_curr(t)) return; /* This task is not running on that CPU. */ - smp_store_release(per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, cpu), true); + smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true); } #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) @@ -1054,11 +935,7 @@ void rcu_request_urgent_qs_task(struct task_struct *t) * Disable preemption to avoid false positives that could otherwise * happen due to the current CPU number being sampled, this task being * preempted, its old CPU being taken offline, resuming on some other CPU, - * then determining that its old CPU is now offline. Because there are - * multiple flavors of RCU, and because this function can be called in the - * midst of updating the flavors while a given CPU coming online or going - * offline, it is necessary to check all flavors. If any of the flavors - * believe that given CPU is online, it is considered to be online. + * then determining that its old CPU is now offline. * * Disable checking if in an NMI handler because we cannot safely * report errors from NMI handlers anyway. In addition, it is OK to use @@ -1069,39 +946,22 @@ bool rcu_lockdep_current_cpu_online(void) { struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; + bool ret = false; if (in_nmi() || !rcu_scheduler_fully_active) return true; preempt_disable(); - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - rnp = rdp->mynode; - if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) { - preempt_enable(); - return true; - } - } + rdp = this_cpu_ptr(&rcu_data); + rnp = rdp->mynode; + if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) + ret = true; preempt_enable(); - return false; + return ret; } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); #endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ -/** - * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle - * - * If the current CPU is idle or running at a first-level (not nested) - * interrupt from idle, return true. The caller must have at least - * disabled preemption. - */ -static int rcu_is_cpu_rrupt_from_idle(void) -{ - return __this_cpu_read(rcu_dynticks.dynticks_nesting) <= 0 && - __this_cpu_read(rcu_dynticks.dynticks_nmi_nesting) <= 1; -} - /* * We are reporting a quiescent state on behalf of some other CPU, so * it is our responsibility to check for and handle potential overflow @@ -1126,9 +986,9 @@ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp) */ static int dyntick_save_progress_counter(struct rcu_data *rdp) { - rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks); + rdp->dynticks_snap = rcu_dynticks_snap(rdp); if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); + trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rdp->mynode, rdp); return 1; } @@ -1177,35 +1037,15 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) * read-side critical section that started before the beginning * of the current RCU grace period. */ - if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti")); - rdp->dynticks_fqs++; - rcu_gpnum_ovf(rnp, rdp); - return 1; - } - - /* - * Has this CPU encountered a cond_resched() since the beginning - * of the grace period? For this to be the case, the CPU has to - * have noticed the current grace period. This might not be the - * case for nohz_full CPUs looping in the kernel. - */ - jtsq = jiffies_till_sched_qs; - ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu); - if (time_after(jiffies, rdp->rsp->gp_start + jtsq) && - READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) && - rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) { - trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc")); + if (rcu_dynticks_in_eqs_since(rdp, rdp->dynticks_snap)) { + trace_rcu_fqs(rcu_state.name, rdp->gp_seq, rdp->cpu, TPS("dti")); rcu_gpnum_ovf(rnp, rdp); return 1; - } else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) { - /* Load rcu_qs_ctr before store to rcu_urgent_qs. */ - smp_store_release(ruqp, true); } /* If waiting too long on an offline CPU, complain. */ if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) && - time_after(jiffies, rdp->rsp->gp_start + HZ)) { + time_after(jiffies, rcu_state.gp_start + HZ)) { bool onl; struct rcu_node *rnp1; @@ -1226,39 +1066,56 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) /* * A CPU running for an extended time within the kernel can - * delay RCU grace periods. When the CPU is in NO_HZ_FULL mode, - * even context-switching back and forth between a pair of - * in-kernel CPU-bound tasks cannot advance grace periods. - * So if the grace period is old enough, make the CPU pay attention. - * Note that the unsynchronized assignments to the per-CPU - * rcu_need_heavy_qs variable are safe. Yes, setting of - * bits can be lost, but they will be set again on the next - * force-quiescent-state pass. So lost bit sets do not result - * in incorrect behavior, merely in a grace period lasting - * a few jiffies longer than it might otherwise. Because - * there are at most four threads involved, and because the - * updates are only once every few jiffies, the probability of - * lossage (and thus of slight grace-period extension) is - * quite low. + * delay RCU grace periods: (1) At age jiffies_to_sched_qs, + * set .rcu_urgent_qs, (2) At age 2*jiffies_to_sched_qs, set + * both .rcu_need_heavy_qs and .rcu_urgent_qs. Note that the + * unsynchronized assignments to the per-CPU rcu_need_heavy_qs + * variable are safe because the assignments are repeated if this + * CPU failed to pass through a quiescent state. This code + * also checks .jiffies_resched in case jiffies_to_sched_qs + * is set way high. */ - rnhqp = &per_cpu(rcu_dynticks.rcu_need_heavy_qs, rdp->cpu); + jtsq = READ_ONCE(jiffies_to_sched_qs); + ruqp = per_cpu_ptr(&rcu_data.rcu_urgent_qs, rdp->cpu); + rnhqp = &per_cpu(rcu_data.rcu_need_heavy_qs, rdp->cpu); if (!READ_ONCE(*rnhqp) && - (time_after(jiffies, rdp->rsp->gp_start + jtsq) || - time_after(jiffies, rdp->rsp->jiffies_resched))) { + (time_after(jiffies, rcu_state.gp_start + jtsq * 2) || + time_after(jiffies, rcu_state.jiffies_resched))) { WRITE_ONCE(*rnhqp, true); /* Store rcu_need_heavy_qs before rcu_urgent_qs. */ smp_store_release(ruqp, true); - rdp->rsp->jiffies_resched += jtsq; /* Re-enable beating. */ + } else if (time_after(jiffies, rcu_state.gp_start + jtsq)) { + WRITE_ONCE(*ruqp, true); } /* - * If more than halfway to RCU CPU stall-warning time, do a - * resched_cpu() to try to loosen things up a bit. Also check to - * see if the CPU is getting hammered with interrupts, but only - * once per grace period, just to keep the IPIs down to a dull roar. + * NO_HZ_FULL CPUs can run in-kernel without rcu_check_callbacks! + * The above code handles this, but only for straight cond_resched(). + * And some in-kernel loops check need_resched() before calling + * cond_resched(), which defeats the above code for CPUs that are + * running in-kernel with scheduling-clock interrupts disabled. + * So hit them over the head with the resched_cpu() hammer! */ - if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) { + if (tick_nohz_full_cpu(rdp->cpu) && + time_after(jiffies, + READ_ONCE(rdp->last_fqs_resched) + jtsq * 3)) { resched_cpu(rdp->cpu); + WRITE_ONCE(rdp->last_fqs_resched, jiffies); + } + + /* + * If more than halfway to RCU CPU stall-warning time, invoke + * resched_cpu() more frequently to try to loosen things up a bit. + * Also check to see if the CPU is getting hammered with interrupts, + * but only once per grace period, just to keep the IPIs down to + * a dull roar. + */ + if (time_after(jiffies, rcu_state.jiffies_resched)) { + if (time_after(jiffies, + READ_ONCE(rdp->last_fqs_resched) + jtsq)) { + resched_cpu(rdp->cpu); + WRITE_ONCE(rdp->last_fqs_resched, jiffies); + } if (IS_ENABLED(CONFIG_IRQ_WORK) && !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq && (rnp->ffmask & rdp->grpmask)) { @@ -1272,17 +1129,17 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 0; } -static void record_gp_stall_check_time(struct rcu_state *rsp) +static void record_gp_stall_check_time(void) { unsigned long j = jiffies; unsigned long j1; - rsp->gp_start = j; + rcu_state.gp_start = j; j1 = rcu_jiffies_till_stall_check(); /* Record ->gp_start before ->jiffies_stall. */ - smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */ - rsp->jiffies_resched = j + j1 / 2; - rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs); + smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */ + rcu_state.jiffies_resched = j + j1 / 2; + rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs); } /* @@ -1298,25 +1155,23 @@ static const char *gp_state_getname(short gs) /* * Complain about starvation of grace-period kthread. */ -static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) +static void rcu_check_gp_kthread_starvation(void) { - unsigned long gpa; + struct task_struct *gpk = rcu_state.gp_kthread; unsigned long j; - j = jiffies; - gpa = READ_ONCE(rsp->gp_activity); - if (j - gpa > 2 * HZ) { + j = jiffies - READ_ONCE(rcu_state.gp_activity); + if (j > 2 * HZ) { pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", - rsp->name, j - gpa, - (long)rcu_seq_current(&rsp->gp_seq), - rsp->gp_flags, - gp_state_getname(rsp->gp_state), rsp->gp_state, - rsp->gp_kthread ? rsp->gp_kthread->state : ~0, - rsp->gp_kthread ? task_cpu(rsp->gp_kthread) : -1); - if (rsp->gp_kthread) { + rcu_state.name, j, + (long)rcu_seq_current(&rcu_state.gp_seq), + rcu_state.gp_flags, + gp_state_getname(rcu_state.gp_state), rcu_state.gp_state, + gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1); + if (gpk) { pr_err("RCU grace-period kthread stack dump:\n"); - sched_show_task(rsp->gp_kthread); - wake_up_process(rsp->gp_kthread); + sched_show_task(gpk); + wake_up_process(gpk); } } } @@ -1327,13 +1182,13 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp) * that don't support NMI-based stack dumps. The NMI-triggered stack * traces are more accurate because they are printed by the target CPU. */ -static void rcu_dump_cpu_stacks(struct rcu_state *rsp) +static void rcu_dump_cpu_stacks(void) { int cpu; unsigned long flags; struct rcu_node *rnp; - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); for_each_leaf_node_possible_cpu(rnp, cpu) if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) @@ -1347,19 +1202,20 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp) * If too much time has passed in the current grace period, and if * so configured, go kick the relevant kthreads. */ -static void rcu_stall_kick_kthreads(struct rcu_state *rsp) +static void rcu_stall_kick_kthreads(void) { unsigned long j; if (!rcu_kick_kthreads) return; - j = READ_ONCE(rsp->jiffies_kick_kthreads); - if (time_after(jiffies, j) && rsp->gp_kthread && - (rcu_gp_in_progress(rsp) || READ_ONCE(rsp->gp_flags))) { - WARN_ONCE(1, "Kicking %s grace-period kthread\n", rsp->name); + j = READ_ONCE(rcu_state.jiffies_kick_kthreads); + if (time_after(jiffies, j) && rcu_state.gp_kthread && + (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) { + WARN_ONCE(1, "Kicking %s grace-period kthread\n", + rcu_state.name); rcu_ftrace_dump(DUMP_ALL); - wake_up_process(rsp->gp_kthread); - WRITE_ONCE(rsp->jiffies_kick_kthreads, j + HZ); + wake_up_process(rcu_state.gp_kthread); + WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ); } } @@ -1369,18 +1225,18 @@ static void panic_on_rcu_stall(void) panic("RCU Stall\n"); } -static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) +static void print_other_cpu_stall(unsigned long gp_seq) { int cpu; unsigned long flags; unsigned long gpa; unsigned long j; int ndetected = 0; - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); long totqlen = 0; /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(rsp); + rcu_stall_kick_kthreads(); if (rcu_cpu_stall_suppress) return; @@ -1389,15 +1245,15 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name); + pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name); print_cpu_stall_info_begin(); - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); ndetected += rcu_print_task_stall(rnp); if (rnp->qsmask != 0) { for_each_leaf_node_possible_cpu(rnp, cpu) if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { - print_cpu_stall_info(rsp, cpu); + print_cpu_stall_info(cpu); ndetected++; } } @@ -1406,52 +1262,52 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq) print_cpu_stall_info_end(); for_each_possible_cpu(cpu) - totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, + totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data, cpu)->cblist); pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n", - smp_processor_id(), (long)(jiffies - rsp->gp_start), - (long)rcu_seq_current(&rsp->gp_seq), totqlen); + smp_processor_id(), (long)(jiffies - rcu_state.gp_start), + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); if (ndetected) { - rcu_dump_cpu_stacks(rsp); + rcu_dump_cpu_stacks(); /* Complain about tasks blocking the grace period. */ - rcu_print_detail_task_stall(rsp); + rcu_print_detail_task_stall(); } else { - if (rcu_seq_current(&rsp->gp_seq) != gp_seq) { + if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) { pr_err("INFO: Stall ended before state dump start\n"); } else { j = jiffies; - gpa = READ_ONCE(rsp->gp_activity); + gpa = READ_ONCE(rcu_state.gp_activity); pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n", - rsp->name, j - gpa, j, gpa, - jiffies_till_next_fqs, - rcu_get_root(rsp)->qsmask); + rcu_state.name, j - gpa, j, gpa, + READ_ONCE(jiffies_till_next_fqs), + rcu_get_root()->qsmask); /* In this case, the current CPU might be at fault. */ sched_show_task(current); } } /* Rewrite if needed in case of slow consoles. */ - if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) - WRITE_ONCE(rsp->jiffies_stall, + if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) + WRITE_ONCE(rcu_state.jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); - rcu_check_gp_kthread_starvation(rsp); + rcu_check_gp_kthread_starvation(); panic_on_rcu_stall(); - force_quiescent_state(rsp); /* Kick them all. */ + force_quiescent_state(); /* Kick them all. */ } -static void print_cpu_stall(struct rcu_state *rsp) +static void print_cpu_stall(void) { int cpu; unsigned long flags; - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + struct rcu_node *rnp = rcu_get_root(); long totqlen = 0; /* Kick and suppress, if so configured. */ - rcu_stall_kick_kthreads(rsp); + rcu_stall_kick_kthreads(); if (rcu_cpu_stall_suppress) return; @@ -1460,27 +1316,27 @@ static void print_cpu_stall(struct rcu_state *rsp) * See Documentation/RCU/stallwarn.txt for info on how to debug * RCU CPU stall warnings. */ - pr_err("INFO: %s self-detected stall on CPU", rsp->name); + pr_err("INFO: %s self-detected stall on CPU", rcu_state.name); print_cpu_stall_info_begin(); raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags); - print_cpu_stall_info(rsp, smp_processor_id()); + print_cpu_stall_info(smp_processor_id()); raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); print_cpu_stall_info_end(); for_each_possible_cpu(cpu) - totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda, + totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(&rcu_data, cpu)->cblist); pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n", - jiffies - rsp->gp_start, - (long)rcu_seq_current(&rsp->gp_seq), totqlen); + jiffies - rcu_state.gp_start, + (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); - rcu_check_gp_kthread_starvation(rsp); + rcu_check_gp_kthread_starvation(); - rcu_dump_cpu_stacks(rsp); + rcu_dump_cpu_stacks(); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Rewrite if needed in case of slow consoles. */ - if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall))) - WRITE_ONCE(rsp->jiffies_stall, + if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall))) + WRITE_ONCE(rcu_state.jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -1493,10 +1349,11 @@ static void print_cpu_stall(struct rcu_state *rsp) * progress and it could be we're stuck in kernel space without context * switches for an entirely unreasonable amount of time. */ - resched_cpu(smp_processor_id()); + set_tsk_need_resched(current); + set_preempt_need_resched(); } -static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) +static void check_cpu_stall(struct rcu_data *rdp) { unsigned long gs1; unsigned long gs2; @@ -1507,54 +1364,55 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) struct rcu_node *rnp; if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) || - !rcu_gp_in_progress(rsp)) + !rcu_gp_in_progress()) return; - rcu_stall_kick_kthreads(rsp); + rcu_stall_kick_kthreads(); j = jiffies; /* * Lots of memory barriers to reject false positives. * - * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall, - * then rsp->gp_start, and finally another copy of rsp->gp_seq. - * These values are updated in the opposite order with memory - * barriers (or equivalent) during grace-period initialization - * and cleanup. Now, a false positive can occur if we get an new - * value of rsp->gp_start and a old value of rsp->jiffies_stall. - * But given the memory barriers, the only way that this can happen - * is if one grace period ends and another starts between these - * two fetches. This is detected by comparing the second fetch - * of rsp->gp_seq with the previous fetch from rsp->gp_seq. + * The idea is to pick up rcu_state.gp_seq, then + * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally + * another copy of rcu_state.gp_seq. These values are updated in + * the opposite order with memory barriers (or equivalent) during + * grace-period initialization and cleanup. Now, a false positive + * can occur if we get an new value of rcu_state.gp_start and a old + * value of rcu_state.jiffies_stall. But given the memory barriers, + * the only way that this can happen is if one grace period ends + * and another starts between these two fetches. This is detected + * by comparing the second fetch of rcu_state.gp_seq with the + * previous fetch from rcu_state.gp_seq. * - * Given this check, comparisons of jiffies, rsp->jiffies_stall, - * and rsp->gp_start suffice to forestall false positives. + * Given this check, comparisons of jiffies, rcu_state.jiffies_stall, + * and rcu_state.gp_start suffice to forestall false positives. */ - gs1 = READ_ONCE(rsp->gp_seq); + gs1 = READ_ONCE(rcu_state.gp_seq); smp_rmb(); /* Pick up ->gp_seq first... */ - js = READ_ONCE(rsp->jiffies_stall); + js = READ_ONCE(rcu_state.jiffies_stall); smp_rmb(); /* ...then ->jiffies_stall before the rest... */ - gps = READ_ONCE(rsp->gp_start); + gps = READ_ONCE(rcu_state.gp_start); smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */ - gs2 = READ_ONCE(rsp->gp_seq); + gs2 = READ_ONCE(rcu_state.gp_seq); if (gs1 != gs2 || ULONG_CMP_LT(j, js) || ULONG_CMP_GE(gps, js)) return; /* No stall or GP completed since entering function. */ rnp = rdp->mynode; jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3; - if (rcu_gp_in_progress(rsp) && + if (rcu_gp_in_progress() && (READ_ONCE(rnp->qsmask) & rdp->grpmask) && - cmpxchg(&rsp->jiffies_stall, js, jn) == js) { + cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { /* We haven't checked in, so go dump stack. */ - print_cpu_stall(rsp); + print_cpu_stall(); - } else if (rcu_gp_in_progress(rsp) && + } else if (rcu_gp_in_progress() && ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) && - cmpxchg(&rsp->jiffies_stall, js, jn) == js) { + cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) { /* They had a few time units to dump stack, so complain. */ - print_other_cpu_stall(rsp, gs2); + print_other_cpu_stall(gs2); } } @@ -1569,17 +1427,14 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) */ void rcu_cpu_stall_reset(void) { - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2); + WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2); } /* Trace-event wrapper function for trace_rcu_future_grace_period. */ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp, unsigned long gp_seq_req, const char *s) { - trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req, + trace_rcu_future_grace_period(rcu_state.name, rnp->gp_seq, gp_seq_req, rnp->level, rnp->grplo, rnp->grphi, s); } @@ -1603,7 +1458,6 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, unsigned long gp_seq_req) { bool ret = false; - struct rcu_state *rsp = rdp->rsp; struct rcu_node *rnp; /* @@ -1647,18 +1501,18 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp, } /* If GP already in progress, just leave, otherwise start one. */ - if (rcu_gp_in_progress(rsp)) { + if (rcu_gp_in_progress()) { trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot")); goto unlock_out; } trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot")); - WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT); - rsp->gp_req_activity = jiffies; - if (!rsp->gp_kthread) { + WRITE_ONCE(rcu_state.gp_flags, rcu_state.gp_flags | RCU_GP_FLAG_INIT); + rcu_state.gp_req_activity = jiffies; + if (!rcu_state.gp_kthread) { trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread")); goto unlock_out; } - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq")); + trace_rcu_grace_period(rcu_state.name, READ_ONCE(rcu_state.gp_seq), TPS("newreq")); ret = true; /* Caller must wake GP kthread. */ unlock_out: /* Push furthest requested GP to leaf node and rcu_data structure. */ @@ -1675,10 +1529,10 @@ unlock_out: * Clean up any old requests for the just-ended grace period. Also return * whether any additional grace periods have been requested. */ -static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static bool rcu_future_gp_cleanup(struct rcu_node *rnp) { bool needmore; - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed); if (!needmore) @@ -1689,19 +1543,18 @@ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) } /* - * Awaken the grace-period kthread for the specified flavor of RCU. - * Don't do a self-awaken, and don't bother awakening when there is - * nothing for the grace-period kthread to do (as in several CPUs - * raced to awaken, and we lost), and finally don't try to awaken - * a kthread that has not yet been created. + * Awaken the grace-period kthread. Don't do a self-awaken, and don't + * bother awakening when there is nothing for the grace-period kthread + * to do (as in several CPUs raced to awaken, and we lost), and finally + * don't try to awaken a kthread that has not yet been created. */ -static void rcu_gp_kthread_wake(struct rcu_state *rsp) +static void rcu_gp_kthread_wake(void) { - if (current == rsp->gp_kthread || - !READ_ONCE(rsp->gp_flags) || - !rsp->gp_kthread) + if (current == rcu_state.gp_kthread || + !READ_ONCE(rcu_state.gp_flags) || + !rcu_state.gp_kthread) return; - swake_up_one(&rsp->gp_wq); + swake_up_one(&rcu_state.gp_wq); } /* @@ -1716,8 +1569,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) * * The caller must hold rnp->lock with interrupts disabled. */ -static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { unsigned long gp_seq_req; bool ret = false; @@ -1738,15 +1590,15 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * accelerating callback invocation to an earlier grace-period * number. */ - gp_seq_req = rcu_seq_snap(&rsp->gp_seq); + gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq); if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB")); + trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccWaitCB")); else - trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB")); + trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("AccReadyCB")); return ret; } @@ -1757,25 +1609,24 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * that a new grace-period request be made, invokes rcu_accelerate_cbs() * while holding the leaf rcu_node structure's ->lock. */ -static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp, - struct rcu_node *rnp, +static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, struct rcu_data *rdp) { unsigned long c; bool needwake; lockdep_assert_irqs_disabled(); - c = rcu_seq_snap(&rsp->gp_seq); + c = rcu_seq_snap(&rcu_state.gp_seq); if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { /* Old request still live, so mark recent callbacks. */ (void)rcu_segcblist_accelerate(&rdp->cblist, c); return; } raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rnp, rdp); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); } /* @@ -1788,8 +1639,7 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp, * * The caller must hold rnp->lock with interrupts disabled. */ -static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { raw_lockdep_assert_held_rcu_node(rnp); @@ -1804,7 +1654,7 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); /* Classify any remaining callbacks. */ - return rcu_accelerate_cbs(rsp, rnp, rdp); + return rcu_accelerate_cbs(rnp, rdp); } /* @@ -1813,8 +1663,7 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp, * structure corresponding to the current CPU, and must have irqs disabled. * Returns true if the grace-period kthread needs to be awakened. */ -static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +static bool __note_gp_changes(struct rcu_node *rnp, struct rcu_data *rdp) { bool ret; bool need_gp; @@ -1827,10 +1676,10 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, /* Handle the ends of any preceding grace periods first. */ if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) || unlikely(READ_ONCE(rdp->gpwrap))) { - ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */ - trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend")); + ret = rcu_advance_cbs(rnp, rdp); /* Advance callbacks. */ + trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuend")); } else { - ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */ + ret = rcu_accelerate_cbs(rnp, rdp); /* Recent callbacks. */ } /* Now handle the beginnings of any new-to-this-CPU grace periods. */ @@ -1841,10 +1690,9 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, * set up to detect a quiescent state, otherwise don't * go looking for one. */ - trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart")); + trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, TPS("cpustart")); need_gp = !!(rnp->qsmask & rdp->grpmask); rdp->cpu_no_qs.b.norm = need_gp; - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); rdp->core_needs_qs = need_gp; zero_cpu_stall_ticks(rdp); } @@ -1856,7 +1704,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp, return ret; } -static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) +static void note_gp_changes(struct rcu_data *rdp) { unsigned long flags; bool needwake; @@ -1870,16 +1718,16 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_restore(flags); return; } - needwake = __note_gp_changes(rsp, rnp, rdp); + needwake = __note_gp_changes(rnp, rdp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); } -static void rcu_gp_slow(struct rcu_state *rsp, int delay) +static void rcu_gp_slow(int delay) { if (delay > 0 && - !(rcu_seq_ctr(rsp->gp_seq) % + !(rcu_seq_ctr(rcu_state.gp_seq) % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay))) schedule_timeout_uninterruptible(delay); } @@ -1887,24 +1735,24 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay) /* * Initialize a new grace period. Return false if no grace period required. */ -static bool rcu_gp_init(struct rcu_state *rsp) +static bool rcu_gp_init(void) { unsigned long flags; unsigned long oldmask; unsigned long mask; struct rcu_data *rdp; - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); - if (!READ_ONCE(rsp->gp_flags)) { + if (!READ_ONCE(rcu_state.gp_flags)) { /* Spurious wakeup, tell caller to go back to sleep. */ raw_spin_unlock_irq_rcu_node(rnp); return false; } - WRITE_ONCE(rsp->gp_flags, 0); /* Clear all flags: New grace period. */ + WRITE_ONCE(rcu_state.gp_flags, 0); /* Clear all flags: New GP. */ - if (WARN_ON_ONCE(rcu_gp_in_progress(rsp))) { + if (WARN_ON_ONCE(rcu_gp_in_progress())) { /* * Grace period already in progress, don't start another. * Not supposed to be able to happen. @@ -1914,10 +1762,10 @@ static bool rcu_gp_init(struct rcu_state *rsp) } /* Advance to a new grace period and initialize state. */ - record_gp_stall_check_time(rsp); + record_gp_stall_check_time(); /* Record GP times before starting GP, hence rcu_seq_start(). */ - rcu_seq_start(&rsp->gp_seq); - trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start")); + rcu_seq_start(&rcu_state.gp_seq); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("start")); raw_spin_unlock_irq_rcu_node(rnp); /* @@ -1926,15 +1774,15 @@ static bool rcu_gp_init(struct rcu_state *rsp) * for subsequent online CPUs, and that quiescent-state forcing * will handle subsequent offline CPUs. */ - rsp->gp_state = RCU_GP_ONOFF; - rcu_for_each_leaf_node(rsp, rnp) { - spin_lock(&rsp->ofl_lock); + rcu_state.gp_state = RCU_GP_ONOFF; + rcu_for_each_leaf_node(rnp) { + raw_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irq_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); - spin_unlock(&rsp->ofl_lock); + raw_spin_unlock(&rcu_state.ofl_lock); continue; } @@ -1970,45 +1818,45 @@ static bool rcu_gp_init(struct rcu_state *rsp) } raw_spin_unlock_irq_rcu_node(rnp); - spin_unlock(&rsp->ofl_lock); + raw_spin_unlock(&rcu_state.ofl_lock); } - rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */ + rcu_gp_slow(gp_preinit_delay); /* Races with CPU hotplug. */ /* * Set the quiescent-state-needed bits in all the rcu_node - * structures for all currently online CPUs in breadth-first order, - * starting from the root rcu_node structure, relying on the layout - * of the tree within the rsp->node[] array. Note that other CPUs - * will access only the leaves of the hierarchy, thus seeing that no - * grace period is in progress, at least until the corresponding - * leaf node has been initialized. + * structures for all currently online CPUs in breadth-first + * order, starting from the root rcu_node structure, relying on the + * layout of the tree within the rcu_state.node[] array. Note that + * other CPUs will access only the leaves of the hierarchy, thus + * seeing that no grace period is in progress, at least until the + * corresponding leaf node has been initialized. * * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ - rsp->gp_state = RCU_GP_INIT; - rcu_for_each_node_breadth_first(rsp, rnp) { - rcu_gp_slow(rsp, gp_init_delay); + rcu_state.gp_state = RCU_GP_INIT; + rcu_for_each_node_breadth_first(rnp) { + rcu_gp_slow(gp_init_delay); raw_spin_lock_irqsave_rcu_node(rnp, flags); - rdp = this_cpu_ptr(rsp->rda); - rcu_preempt_check_blocked_tasks(rsp, rnp); + rdp = this_cpu_ptr(&rcu_data); + rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; - WRITE_ONCE(rnp->gp_seq, rsp->gp_seq); + WRITE_ONCE(rnp->gp_seq, rcu_state.gp_seq); if (rnp == rdp->mynode) - (void)__note_gp_changes(rsp, rnp, rdp); + (void)__note_gp_changes(rnp, rdp); rcu_preempt_boost_start_gp(rnp); - trace_rcu_grace_period_init(rsp->name, rnp->gp_seq, + trace_rcu_grace_period_init(rcu_state.name, rnp->gp_seq, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); /* Quiescent states for tasks on any now-offline CPUs. */ mask = rnp->qsmask & ~rnp->qsmaskinitnext; rnp->rcu_gp_init_mask = mask; if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp)) - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); else raw_spin_unlock_irq_rcu_node(rnp); cond_resched_tasks_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); } return true; @@ -2018,12 +1866,12 @@ static bool rcu_gp_init(struct rcu_state *rsp) * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state * time. */ -static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) +static bool rcu_gp_fqs_check_wake(int *gfp) { - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); /* Someone like call_rcu() requested a force-quiescent-state scan. */ - *gfp = READ_ONCE(rsp->gp_flags); + *gfp = READ_ONCE(rcu_state.gp_flags); if (*gfp & RCU_GP_FLAG_FQS) return true; @@ -2037,45 +1885,110 @@ static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp) /* * Do one round of quiescent-state forcing. */ -static void rcu_gp_fqs(struct rcu_state *rsp, bool first_time) +static void rcu_gp_fqs(bool first_time) { - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); - WRITE_ONCE(rsp->gp_activity, jiffies); - rsp->n_force_qs++; + WRITE_ONCE(rcu_state.gp_activity, jiffies); + rcu_state.n_force_qs++; if (first_time) { /* Collect dyntick-idle snapshots. */ - force_qs_rnp(rsp, dyntick_save_progress_counter); + force_qs_rnp(dyntick_save_progress_counter); } else { /* Handle dyntick-idle and offline CPUs. */ - force_qs_rnp(rsp, rcu_implicit_dynticks_qs); + force_qs_rnp(rcu_implicit_dynticks_qs); } /* Clear flag to prevent immediate re-entry. */ - if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_lock_irq_rcu_node(rnp); - WRITE_ONCE(rsp->gp_flags, - READ_ONCE(rsp->gp_flags) & ~RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, + READ_ONCE(rcu_state.gp_flags) & ~RCU_GP_FLAG_FQS); raw_spin_unlock_irq_rcu_node(rnp); } } /* + * Loop doing repeated quiescent-state forcing until the grace period ends. + */ +static void rcu_gp_fqs_loop(void) +{ + bool first_gp_fqs; + int gf; + unsigned long j; + int ret; + struct rcu_node *rnp = rcu_get_root(); + + first_gp_fqs = true; + j = READ_ONCE(jiffies_till_first_fqs); + ret = 0; + for (;;) { + if (!ret) { + rcu_state.jiffies_force_qs = jiffies + j; + WRITE_ONCE(rcu_state.jiffies_kick_kthreads, + jiffies + 3 * j); + } + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), + TPS("fqswait")); + rcu_state.gp_state = RCU_GP_WAIT_FQS; + ret = swait_event_idle_timeout_exclusive( + rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j); + rcu_state.gp_state = RCU_GP_DOING_FQS; + /* Locking provides needed memory barriers. */ + /* If grace period done, leave loop. */ + if (!READ_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)) + break; + /* If time for quiescent-state forcing, do it. */ + if (ULONG_CMP_GE(jiffies, rcu_state.jiffies_force_qs) || + (gf & RCU_GP_FLAG_FQS)) { + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), + TPS("fqsstart")); + rcu_gp_fqs(first_gp_fqs); + first_gp_fqs = false; + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), + TPS("fqsend")); + cond_resched_tasks_rcu_qs(); + WRITE_ONCE(rcu_state.gp_activity, jiffies); + ret = 0; /* Force full wait till next FQS. */ + j = READ_ONCE(jiffies_till_next_fqs); + } else { + /* Deal with stray signal. */ + cond_resched_tasks_rcu_qs(); + WRITE_ONCE(rcu_state.gp_activity, jiffies); + WARN_ON(signal_pending(current)); + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), + TPS("fqswaitsig")); + ret = 1; /* Keep old FQS timing. */ + j = jiffies; + if (time_after(jiffies, rcu_state.jiffies_force_qs)) + j = 1; + else + j = rcu_state.jiffies_force_qs - j; + } + } +} + +/* * Clean up after the old grace period. */ -static void rcu_gp_cleanup(struct rcu_state *rsp) +static void rcu_gp_cleanup(void) { unsigned long gp_duration; bool needgp = false; unsigned long new_gp_seq; struct rcu_data *rdp; - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); struct swait_queue_head *sq; - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); - gp_duration = jiffies - rsp->gp_start; - if (gp_duration > rsp->gp_max) - rsp->gp_max = gp_duration; + gp_duration = jiffies - rcu_state.gp_start; + if (gp_duration > rcu_state.gp_max) + rcu_state.gp_max = gp_duration; /* * We know the grace period is complete, but to everyone else @@ -2096,48 +2009,50 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) * the rcu_node structures before the beginning of the next grace * period is recorded in any of the rcu_node structures. */ - new_gp_seq = rsp->gp_seq; + new_gp_seq = rcu_state.gp_seq; rcu_seq_end(&new_gp_seq); - rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_for_each_node_breadth_first(rnp) { raw_spin_lock_irq_rcu_node(rnp); if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) - dump_blkd_tasks(rsp, rnp, 10); + dump_blkd_tasks(rnp, 10); WARN_ON_ONCE(rnp->qsmask); WRITE_ONCE(rnp->gp_seq, new_gp_seq); - rdp = this_cpu_ptr(rsp->rda); + rdp = this_cpu_ptr(&rcu_data); if (rnp == rdp->mynode) - needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; + needgp = __note_gp_changes(rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ - needgp = rcu_future_gp_cleanup(rsp, rnp) || needgp; + needgp = rcu_future_gp_cleanup(rnp) || needgp; sq = rcu_nocb_gp_get(rnp); raw_spin_unlock_irq_rcu_node(rnp); rcu_nocb_gp_cleanup(sq); cond_resched_tasks_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - rcu_gp_slow(rsp, gp_cleanup_delay); + WRITE_ONCE(rcu_state.gp_activity, jiffies); + rcu_gp_slow(gp_cleanup_delay); } - rnp = rcu_get_root(rsp); - raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */ + rnp = rcu_get_root(); + raw_spin_lock_irq_rcu_node(rnp); /* GP before ->gp_seq update. */ /* Declare grace period done. */ - rcu_seq_end(&rsp->gp_seq); - trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end")); - rsp->gp_state = RCU_GP_IDLE; + rcu_seq_end(&rcu_state.gp_seq); + trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end")); + rcu_state.gp_state = RCU_GP_IDLE; /* Check for GP requests since above loop. */ - rdp = this_cpu_ptr(rsp->rda); + rdp = this_cpu_ptr(&rcu_data); if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed, TPS("CleanupMore")); needgp = true; } /* Advance CBs to reduce false positives below. */ - if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) { - WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT); - rsp->gp_req_activity = jiffies; - trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), + if (!rcu_accelerate_cbs(rnp, rdp) && needgp) { + WRITE_ONCE(rcu_state.gp_flags, RCU_GP_FLAG_INIT); + rcu_state.gp_req_activity = jiffies; + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), TPS("newreq")); } else { - WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT); + WRITE_ONCE(rcu_state.gp_flags, + rcu_state.gp_flags & RCU_GP_FLAG_INIT); } raw_spin_unlock_irq_rcu_node(rnp); } @@ -2145,116 +2060,60 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* * Body of kthread that handles grace periods. */ -static int __noreturn rcu_gp_kthread(void *arg) +static int __noreturn rcu_gp_kthread(void *unused) { - bool first_gp_fqs; - int gf; - unsigned long j; - int ret; - struct rcu_state *rsp = arg; - struct rcu_node *rnp = rcu_get_root(rsp); - rcu_bind_gp_kthread(); for (;;) { /* Handle grace-period start. */ for (;;) { - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), TPS("reqwait")); - rsp->gp_state = RCU_GP_WAIT_GPS; - swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & - RCU_GP_FLAG_INIT); - rsp->gp_state = RCU_GP_DONE_GPS; + rcu_state.gp_state = RCU_GP_WAIT_GPS; + swait_event_idle_exclusive(rcu_state.gp_wq, + READ_ONCE(rcu_state.gp_flags) & + RCU_GP_FLAG_INIT); + rcu_state.gp_state = RCU_GP_DONE_GPS; /* Locking provides needed memory barrier. */ - if (rcu_gp_init(rsp)) + if (rcu_gp_init()) break; cond_resched_tasks_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); + WRITE_ONCE(rcu_state.gp_activity, jiffies); WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), + trace_rcu_grace_period(rcu_state.name, + READ_ONCE(rcu_state.gp_seq), TPS("reqwaitsig")); } /* Handle quiescent-state forcing. */ - first_gp_fqs = true; - j = jiffies_till_first_fqs; - ret = 0; - for (;;) { - if (!ret) { - rsp->jiffies_force_qs = jiffies + j; - WRITE_ONCE(rsp->jiffies_kick_kthreads, - jiffies + 3 * j); - } - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), - TPS("fqswait")); - rsp->gp_state = RCU_GP_WAIT_FQS; - ret = swait_event_idle_timeout_exclusive(rsp->gp_wq, - rcu_gp_fqs_check_wake(rsp, &gf), j); - rsp->gp_state = RCU_GP_DOING_FQS; - /* Locking provides needed memory barriers. */ - /* If grace period done, leave loop. */ - if (!READ_ONCE(rnp->qsmask) && - !rcu_preempt_blocked_readers_cgp(rnp)) - break; - /* If time for quiescent-state forcing, do it. */ - if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) || - (gf & RCU_GP_FLAG_FQS)) { - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), - TPS("fqsstart")); - rcu_gp_fqs(rsp, first_gp_fqs); - first_gp_fqs = false; - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), - TPS("fqsend")); - cond_resched_tasks_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - ret = 0; /* Force full wait till next FQS. */ - j = jiffies_till_next_fqs; - } else { - /* Deal with stray signal. */ - cond_resched_tasks_rcu_qs(); - WRITE_ONCE(rsp->gp_activity, jiffies); - WARN_ON(signal_pending(current)); - trace_rcu_grace_period(rsp->name, - READ_ONCE(rsp->gp_seq), - TPS("fqswaitsig")); - ret = 1; /* Keep old FQS timing. */ - j = jiffies; - if (time_after(jiffies, rsp->jiffies_force_qs)) - j = 1; - else - j = rsp->jiffies_force_qs - j; - } - } + rcu_gp_fqs_loop(); /* Handle grace-period end. */ - rsp->gp_state = RCU_GP_CLEANUP; - rcu_gp_cleanup(rsp); - rsp->gp_state = RCU_GP_CLEANED; + rcu_state.gp_state = RCU_GP_CLEANUP; + rcu_gp_cleanup(); + rcu_state.gp_state = RCU_GP_CLEANED; } } /* - * Report a full set of quiescent states to the specified rcu_state data - * structure. Invoke rcu_gp_kthread_wake() to awaken the grace-period - * kthread if another grace period is required. Whether we wake - * the grace-period kthread or it awakens itself for the next round - * of quiescent-state forcing, that kthread will clean up after the - * just-completed grace period. Note that the caller must hold rnp->lock, - * which is released before return. + * Report a full set of quiescent states to the rcu_state data structure. + * Invoke rcu_gp_kthread_wake() to awaken the grace-period kthread if + * another grace period is required. Whether we wake the grace-period + * kthread or it awakens itself for the next round of quiescent-state + * forcing, that kthread will clean up after the just-completed grace + * period. Note that the caller must hold rnp->lock, which is released + * before return. */ -static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +static void rcu_report_qs_rsp(unsigned long flags) + __releases(rcu_get_root()->lock) { - raw_lockdep_assert_held_rcu_node(rcu_get_root(rsp)); - WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); - raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); - rcu_gp_kthread_wake(rsp); + raw_lockdep_assert_held_rcu_node(rcu_get_root()); + WARN_ON_ONCE(!rcu_gp_in_progress()); + WRITE_ONCE(rcu_state.gp_flags, + READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS); + raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(), flags); + rcu_gp_kthread_wake(); } /* @@ -2271,9 +2130,8 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * disabled. This allows propagating quiescent state due to resumed tasks * during grace-period initialization. */ -static void -rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long gps, unsigned long flags) +static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, + unsigned long gps, unsigned long flags) __releases(rnp->lock) { unsigned long oldmask = 0; @@ -2296,7 +2154,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, WARN_ON_ONCE(!rcu_is_leaf_node(rnp) && rcu_preempt_blocked_readers_cgp(rnp)); rnp->qsmask &= ~mask; - trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq, + trace_rcu_quiescent_state_report(rcu_state.name, rnp->gp_seq, mask, rnp->qsmask, rnp->level, rnp->grplo, rnp->grphi, !!rnp->gp_tasks); @@ -2326,19 +2184,18 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * state for this grace period. Invoke rcu_report_qs_rsp() * to clean up and start the next grace period if one is needed. */ - rcu_report_qs_rsp(rsp, flags); /* releases rnp->lock. */ + rcu_report_qs_rsp(flags); /* releases rnp->lock. */ } /* * Record a quiescent state for all tasks that were previously queued * on the specified rcu_node structure and that were blocking the current - * RCU grace period. The caller must hold the specified rnp->lock with + * RCU grace period. The caller must hold the corresponding rnp->lock with * irqs disabled, and this lock is released upon return, but irqs remain * disabled. */ static void __maybe_unused -rcu_report_unblock_qs_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, unsigned long flags) +rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) __releases(rnp->lock) { unsigned long gps; @@ -2346,8 +2203,7 @@ rcu_report_unblock_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) || - WARN_ON_ONCE(rsp != rcu_state_p) || + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)) || WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2361,7 +2217,7 @@ rcu_report_unblock_qs_rnp(struct rcu_state *rsp, * Only one rcu_node structure in the tree, so don't * try to report up to its nonexistent parent! */ - rcu_report_qs_rsp(rsp, flags); + rcu_report_qs_rsp(flags); return; } @@ -2370,7 +2226,7 @@ rcu_report_unblock_qs_rnp(struct rcu_state *rsp, mask = rnp->grpmask; raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ raw_spin_lock_rcu_node(rnp_p); /* irqs already disabled. */ - rcu_report_qs_rnp(mask, rsp, rnp_p, gps, flags); + rcu_report_qs_rnp(mask, rnp_p, gps, flags); } /* @@ -2378,7 +2234,7 @@ rcu_report_unblock_qs_rnp(struct rcu_state *rsp, * structure. This must be called from the specified CPU. */ static void -rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) +rcu_report_qs_rdp(int cpu, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; @@ -2397,7 +2253,6 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * within the current grace period. */ rdp->cpu_no_qs.b.norm = true; /* need qs for new gp. */ - rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } @@ -2411,12 +2266,12 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * This GP can't end until cpu checks in, so all of our * callbacks can be processed during the next GP. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rnp, rdp); - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); /* ^^^ Released rnp->lock */ if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); } } @@ -2427,10 +2282,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) * quiescent state for this grace period, and record that fact if so. */ static void -rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) +rcu_check_quiescent_state(struct rcu_data *rdp) { /* Check for grace-period ends and beginnings. */ - note_gp_changes(rsp, rdp); + note_gp_changes(rdp); /* * Does this CPU still need to do its part for current grace period? @@ -2450,24 +2305,26 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Tell RCU we are done (but rcu_report_qs_rdp() will be the * judge of that). */ - rcu_report_qs_rdp(rdp->cpu, rsp, rdp); + rcu_report_qs_rdp(rdp->cpu, rdp); } /* - * Trace the fact that this CPU is going offline. + * Near the end of the offline process. Trace the fact that this CPU + * is going offline. */ -static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) +int rcutree_dying_cpu(unsigned int cpu) { RCU_TRACE(bool blkd;) - RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);) + RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(&rcu_data);) RCU_TRACE(struct rcu_node *rnp = rdp->mynode;) if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; + return 0; RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);) - trace_rcu_grace_period(rsp->name, rnp->gp_seq, + trace_rcu_grace_period(rcu_state.name, rnp->gp_seq, blkd ? TPS("cpuofl") : TPS("cpuofl-bgp")); + return 0; } /* @@ -2521,23 +2378,26 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) * There can only be one CPU hotplug operation at a time, so no need for * explicit locking. */ -static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) +int rcutree_dead_cpu(unsigned int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return; + return 0; /* Adjust any no-longer-needed kthreads. */ rcu_boost_kthread_setaffinity(rnp, -1); + /* Do any needed no-CB deferred wakeups from this CPU. */ + do_nocb_deferred_wakeup(per_cpu_ptr(&rcu_data, cpu)); + return 0; } /* * Invoke any RCU callbacks that have made it to the end of their grace * period. Thottle as specified by rdp->blimit. */ -static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) +static void rcu_do_batch(struct rcu_data *rdp) { unsigned long flags; struct rcu_head *rhp; @@ -2546,10 +2406,10 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* If no callbacks are ready, just return. */ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) { - trace_rcu_batch_start(rsp->name, + trace_rcu_batch_start(rcu_state.name, rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist), 0); - trace_rcu_batch_end(rsp->name, 0, + trace_rcu_batch_end(rcu_state.name, 0, !rcu_segcblist_empty(&rdp->cblist), need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); @@ -2564,7 +2424,8 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); bl = rdp->blimit; - trace_rcu_batch_start(rsp->name, rcu_segcblist_n_lazy_cbs(&rdp->cblist), + trace_rcu_batch_start(rcu_state.name, + rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist), bl); rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); local_irq_restore(flags); @@ -2573,7 +2434,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rhp = rcu_cblist_dequeue(&rcl); for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) { debug_rcu_head_unqueue(rhp); - if (__rcu_reclaim(rsp->name, rhp)) + if (__rcu_reclaim(rcu_state.name, rhp)) rcu_cblist_dequeued_lazy(&rcl); /* * Stop only if limit reached and CPU has something to do. @@ -2587,7 +2448,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) local_irq_save(flags); count = -rcl.len; - trace_rcu_batch_end(rsp->name, count, !!rcl.head, need_resched(), + trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); /* Update counts and requeue any remaining callbacks. */ @@ -2603,7 +2464,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */ if (count == 0 && rdp->qlen_last_fqs_check != 0) { rdp->qlen_last_fqs_check = 0; - rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->n_force_qs_snap = rcu_state.n_force_qs; } else if (count < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = count; @@ -2631,37 +2492,17 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) void rcu_check_callbacks(int user) { trace_rcu_utilization(TPS("Start scheduler-tick")); - increment_cpu_stall_ticks(); - if (user || rcu_is_cpu_rrupt_from_idle()) { - - /* - * Get here if this CPU took its interrupt from user - * mode or from the idle loop, and if this is not a - * nested interrupt. In this case, the CPU is in - * a quiescent state, so note it. - * - * No memory barrier is required here because both - * rcu_sched_qs() and rcu_bh_qs() reference only CPU-local - * variables that other CPUs neither access nor modify, - * at least not while the corresponding CPU is online. - */ - - rcu_sched_qs(); - rcu_bh_qs(); - rcu_note_voluntary_context_switch(current); - - } else if (!in_softirq()) { - - /* - * Get here if this CPU did not take its interrupt from - * softirq, in other words, if it is not interrupting - * a rcu_bh read-side critical section. This is an _bh - * critical section, so note it. - */ - - rcu_bh_qs(); + raw_cpu_inc(rcu_data.ticks_this_gp); + /* The load-acquire pairs with the store-release setting to true. */ + if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) { + /* Idle and userspace execution already are quiescent states. */ + if (!rcu_is_cpu_rrupt_from_idle() && !user) { + set_tsk_need_resched(current); + set_preempt_need_resched(); + } + __this_cpu_write(rcu_data.rcu_urgent_qs, false); } - rcu_preempt_check_callbacks(); + rcu_flavor_check_callbacks(user); if (rcu_pending()) invoke_rcu_core(); @@ -2675,20 +2516,19 @@ void rcu_check_callbacks(int user) * * The caller must have suppressed start of new grace periods. */ -static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) +static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) { int cpu; unsigned long flags; unsigned long mask; struct rcu_node *rnp; - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { cond_resched_tasks_rcu_qs(); mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { - if (rcu_state_p == &rcu_sched_state || - rsp != rcu_state_p || + if (!IS_ENABLED(CONFIG_PREEMPT) || rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they @@ -2705,13 +2545,13 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) for_each_leaf_node_possible_cpu(rnp, cpu) { unsigned long bit = leaf_node_cpu_bit(rnp, cpu); if ((rnp->qsmask & bit) != 0) { - if (f(per_cpu_ptr(rsp->rda, cpu))) + if (f(per_cpu_ptr(&rcu_data, cpu))) mask |= bit; } } if (mask != 0) { /* Idle/offline CPUs, report (releases rnp->lock). */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); } else { /* Nothing to do here, so just drop the lock. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2723,7 +2563,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp)) * Force quiescent states on reluctant CPUs, and also detect which * CPUs are in dyntick-idle mode. */ -static void force_quiescent_state(struct rcu_state *rsp) +static void force_quiescent_state(void) { unsigned long flags; bool ret; @@ -2731,9 +2571,9 @@ static void force_quiescent_state(struct rcu_state *rsp) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = __this_cpu_read(rsp->rda->mynode); + rnp = __this_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { - ret = (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || + ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); if (rnp_old != NULL) raw_spin_unlock(&rnp_old->fqslock); @@ -2741,18 +2581,19 @@ static void force_quiescent_state(struct rcu_state *rsp) return; rnp_old = rnp; } - /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ + /* rnp_old == rcu_get_root(), rnp == NULL. */ /* Reached the root of the rcu_node tree, acquire lock. */ raw_spin_lock_irqsave_rcu_node(rnp_old, flags); raw_spin_unlock(&rnp_old->fqslock); - if (READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + if (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) { raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); return; /* Someone beat us to it. */ } - WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); + WRITE_ONCE(rcu_state.gp_flags, + READ_ONCE(rcu_state.gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); } /* @@ -2760,30 +2601,29 @@ static void force_quiescent_state(struct rcu_state *rsp) * RCU to come out of its idle mode. */ static void -rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, - struct rcu_data *rdp) +rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp) { const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ; unsigned long flags; unsigned long j; - struct rcu_node *rnp_root = rcu_get_root(rsp); + struct rcu_node *rnp_root = rcu_get_root(); static atomic_t warned = ATOMIC_INIT(0); - if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) || + if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() || ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed)) return; j = jiffies; /* Expensive access, and in common case don't get here. */ - if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || - time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || atomic_read(&warned)) return; raw_spin_lock_irqsave_rcu_node(rnp, flags); j = jiffies; - if (rcu_gp_in_progress(rsp) || + if (rcu_gp_in_progress() || ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || - time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) || - time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) || + time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) || + time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) || atomic_read(&warned)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; @@ -2793,21 +2633,21 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, if (rnp_root != rnp) raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ j = jiffies; - if (rcu_gp_in_progress(rsp) || + if (rcu_gp_in_progress() || ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) || - time_before(j, rsp->gp_req_activity + gpssdelay) || - time_before(j, rsp->gp_activity + gpssdelay) || + time_before(j, rcu_state.gp_req_activity + gpssdelay) || + time_before(j, rcu_state.gp_activity + gpssdelay) || atomic_xchg(&warned, 1)) { raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n", - __func__, (long)READ_ONCE(rsp->gp_seq), + __func__, (long)READ_ONCE(rcu_state.gp_seq), (long)READ_ONCE(rnp_root->gp_seq_needed), - j - rsp->gp_req_activity, j - rsp->gp_activity, - rsp->gp_flags, rsp->gp_state, rsp->name, - rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL); + j - rcu_state.gp_req_activity, j - rcu_state.gp_activity, + rcu_state.gp_flags, rcu_state.gp_state, rcu_state.name, + rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL); WARN_ON(1); if (rnp_root != rnp) raw_spin_unlock_rcu_node(rnp_root); @@ -2815,69 +2655,65 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp, } /* - * This does the RCU core processing work for the specified rcu_state - * and rcu_data structures. This may be called only from the CPU to - * whom the rdp belongs. + * This does the RCU core processing work for the specified rcu_data + * structures. This may be called only from the CPU to whom the rdp + * belongs. */ -static void -__rcu_process_callbacks(struct rcu_state *rsp) +static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { unsigned long flags; - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; + if (cpu_is_offline(smp_processor_id())) + return; + trace_rcu_utilization(TPS("Start RCU core")); WARN_ON_ONCE(!rdp->beenonline); + /* Report any deferred quiescent states if preemption enabled. */ + if (!(preempt_count() & PREEMPT_MASK)) { + rcu_preempt_deferred_qs(current); + } else if (rcu_preempt_need_deferred_qs(current)) { + set_tsk_need_resched(current); + set_preempt_need_resched(); + } + /* Update RCU state based on any recent quiescent states. */ - rcu_check_quiescent_state(rsp, rdp); + rcu_check_quiescent_state(rdp); /* No grace period and unregistered callbacks? */ - if (!rcu_gp_in_progress(rsp) && + if (!rcu_gp_in_progress() && rcu_segcblist_is_enabled(&rdp->cblist)) { local_irq_save(flags); if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) - rcu_accelerate_cbs_unlocked(rsp, rnp, rdp); + rcu_accelerate_cbs_unlocked(rnp, rdp); local_irq_restore(flags); } - rcu_check_gp_start_stall(rsp, rnp, rdp); + rcu_check_gp_start_stall(rnp, rdp); /* If there are callbacks ready, invoke them. */ if (rcu_segcblist_ready_cbs(&rdp->cblist)) - invoke_rcu_callbacks(rsp, rdp); + invoke_rcu_callbacks(rdp); /* Do any needed deferred wakeups of rcuo kthreads. */ do_nocb_deferred_wakeup(rdp); -} - -/* - * Do RCU core processing for the current CPU. - */ -static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) -{ - struct rcu_state *rsp; - - if (cpu_is_offline(smp_processor_id())) - return; - trace_rcu_utilization(TPS("Start RCU core")); - for_each_rcu_flavor(rsp) - __rcu_process_callbacks(rsp); trace_rcu_utilization(TPS("End RCU core")); } /* - * Schedule RCU callback invocation. If the specified type of RCU - * does not support RCU priority boosting, just do a direct call, - * otherwise wake up the per-CPU kernel kthread. Note that because we - * are running on the current CPU with softirqs disabled, the - * rcu_cpu_kthread_task cannot disappear out from under us. + * Schedule RCU callback invocation. If the running implementation of RCU + * does not support RCU priority boosting, just do a direct call, otherwise + * wake up the per-CPU kernel kthread. Note that because we are running + * on the current CPU with softirqs disabled, the rcu_cpu_kthread_task + * cannot disappear out from under us. */ -static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp) +static void invoke_rcu_callbacks(struct rcu_data *rdp) { if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) return; - if (likely(!rsp->boost)) { - rcu_do_batch(rsp, rdp); + if (likely(!rcu_state.boost)) { + rcu_do_batch(rdp); return; } invoke_rcu_callbacks_kthread(); @@ -2892,8 +2728,8 @@ static void invoke_rcu_core(void) /* * Handle any core-RCU processing required by a call_rcu() invocation. */ -static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, - struct rcu_head *head, unsigned long flags) +static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head, + unsigned long flags) { /* * If called from an extended quiescent state, invoke the RCU @@ -2917,18 +2753,18 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, rdp->qlen_last_fqs_check + qhimark)) { /* Are we ignoring a completed grace period? */ - note_gp_changes(rsp, rdp); + note_gp_changes(rdp); /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp); + if (!rcu_gp_in_progress()) { + rcu_accelerate_cbs_unlocked(rdp->mynode, rdp); } else { /* Give the grace period a kick. */ rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && + if (rcu_state.n_force_qs == rdp->n_force_qs_snap && rcu_segcblist_first_pend_cb(&rdp->cblist) != head) - force_quiescent_state(rsp); - rdp->n_force_qs_snap = rsp->n_force_qs; + force_quiescent_state(); + rdp->n_force_qs_snap = rcu_state.n_force_qs; rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); } } @@ -2944,12 +2780,11 @@ static void rcu_leak_callback(struct rcu_head *rhp) /* * Helper function for call_rcu() and friends. The cpu argument will * normally be -1, indicating "currently running CPU". It may specify - * a CPU only if that CPU is a no-CBs CPU. Currently, only _rcu_barrier() + * a CPU only if that CPU is a no-CBs CPU. Currently, only rcu_barrier() * is expected to specify a CPU. */ static void -__call_rcu(struct rcu_head *head, rcu_callback_t func, - struct rcu_state *rsp, int cpu, bool lazy) +__call_rcu(struct rcu_head *head, rcu_callback_t func, int cpu, bool lazy) { unsigned long flags; struct rcu_data *rdp; @@ -2971,14 +2806,14 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, head->func = func; head->next = NULL; local_irq_save(flags); - rdp = this_cpu_ptr(rsp->rda); + rdp = this_cpu_ptr(&rcu_data); /* Add the callback to our list. */ if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist)) || cpu != -1) { int offline; if (cpu != -1) - rdp = per_cpu_ptr(rsp->rda, cpu); + rdp = per_cpu_ptr(&rcu_data, cpu); if (likely(rdp->mynode)) { /* Post-boot, so this should be for a no-CBs CPU. */ offline = !__call_rcu_nocb(rdp, head, lazy, flags); @@ -3001,72 +2836,60 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, rcu_idle_count_callbacks_posted(); if (__is_kfree_rcu_offset((unsigned long)func)) - trace_rcu_kfree_callback(rsp->name, head, (unsigned long)func, + trace_rcu_kfree_callback(rcu_state.name, head, + (unsigned long)func, rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist)); else - trace_rcu_callback(rsp->name, head, + trace_rcu_callback(rcu_state.name, head, rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist)); /* Go handle any RCU core processing required. */ - __call_rcu_core(rsp, rdp, head, flags); + __call_rcu_core(rdp, head, flags); local_irq_restore(flags); } /** - * call_rcu_sched() - Queue an RCU for invocation after sched 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 currently executing RCU - * read-side critical sections have completed. call_rcu_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by: - * - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR - * - anything that disables preemption. - * - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_sched(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func, &rcu_sched_state, -1, 0); -} -EXPORT_SYMBOL_GPL(call_rcu_sched); - -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * 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 currently executing RCU - * read-side critical sections have completed. call_rcu_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by: - * - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -void call_rcu_bh(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func, &rcu_bh_state, -1, 0); -} -EXPORT_SYMBOL_GPL(call_rcu_bh); + * 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, 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). + */ +void call_rcu(struct rcu_head *head, rcu_callback_t func) +{ + __call_rcu(head, func, -1, 0); +} +EXPORT_SYMBOL_GPL(call_rcu); /* * Queue an RCU callback for lazy invocation after a grace period. @@ -3075,110 +2898,12 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * callbacks in the list of pending callbacks. Until then, this * function may only be called from __kfree_rcu(). */ -void kfree_call_rcu(struct rcu_head *head, - rcu_callback_t func) +void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, rcu_state_p, -1, 1); + __call_rcu(head, func, -1, 1); } EXPORT_SYMBOL_GPL(kfree_call_rcu); -/* - * Because a context switch is a grace period for RCU-sched and RCU-bh, - * any blocking grace-period wait automatically implies a grace period - * if there is only one CPU online at any point time during execution - * of either synchronize_sched() or synchronize_rcu_bh(). It is OK to - * occasionally incorrectly indicate that there are multiple CPUs online - * when there was in fact only one the whole time, as this just adds - * some overhead: RCU still operates correctly. - */ -static int rcu_blocking_is_gp(void) -{ - int ret; - - might_sleep(); /* Check for RCU read-side critical section. */ - preempt_disable(); - ret = num_online_cpus() <= 1; - preempt_enable(); - return ret; -} - -/** - * synchronize_sched - wait until an rcu-sched grace period has elapsed. - * - * Control will return to the caller some time after a full rcu-sched - * grace period has elapsed, in other words after all currently executing - * rcu-sched read-side critical sections have completed. These read-side - * critical sections are delimited by rcu_read_lock_sched() and - * rcu_read_unlock_sched(), and may be nested. Note that preempt_disable(), - * local_irq_disable(), and so on may be used in place of - * rcu_read_lock_sched(). - * - * This means that all preempt_disable code sequences, including NMI and - * non-threaded hardware-interrupt handlers, in progress on entry will - * have completed before this primitive returns. However, this does not - * guarantee that softirq handlers will have completed, since in some - * kernels, these handlers can run in process context, and can block. - * - * Note that this guarantee implies further memory-ordering guarantees. - * On systems with more than one CPU, when synchronize_sched() returns, - * each CPU is guaranteed to have executed a full memory barrier since the - * end of its last RCU-sched read-side critical section whose beginning - * preceded the call to synchronize_sched(). In addition, each CPU having - * an RCU read-side critical section that extends beyond the return from - * synchronize_sched() is guaranteed to have executed a full memory barrier - * after the beginning of synchronize_sched() and 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 synchronize_sched(), which returned - * to its caller on CPU B, then both CPU A and CPU B are guaranteed - * to have executed a full memory barrier during the execution of - * synchronize_sched() -- even if CPU A and CPU B are the same CPU (but - * again only if the system has more than one CPU). - */ -void synchronize_sched(void) -{ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || - lock_is_held(&rcu_lock_map) || - lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_sched() in RCU-sched read-side critical section"); - if (rcu_blocking_is_gp()) - return; - if (rcu_gp_is_expedited()) - synchronize_sched_expedited(); - else - wait_rcu_gp(call_rcu_sched); -} -EXPORT_SYMBOL_GPL(synchronize_sched); - -/** - * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. - * - * Control will return to the caller some time after a full rcu_bh grace - * period has elapsed, in other words after all currently executing rcu_bh - * read-side critical sections have completed. RCU read-side critical - * sections are delimited by rcu_read_lock_bh() and rcu_read_unlock_bh(), - * and may be nested. - * - * See the description of synchronize_sched() for more detailed information - * on memory ordering guarantees. - */ -void synchronize_rcu_bh(void) -{ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || - lock_is_held(&rcu_lock_map) || - lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); - if (rcu_blocking_is_gp()) - return; - if (rcu_gp_is_expedited()) - synchronize_rcu_bh_expedited(); - else - wait_rcu_gp(call_rcu_bh); -} -EXPORT_SYMBOL_GPL(synchronize_rcu_bh); - /** * get_state_synchronize_rcu - Snapshot current RCU state * @@ -3193,7 +2918,7 @@ unsigned long get_state_synchronize_rcu(void) * before the load from ->gp_seq. */ smp_mb(); /* ^^^ */ - return rcu_seq_snap(&rcu_state_p->gp_seq); + return rcu_seq_snap(&rcu_state.gp_seq); } EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); @@ -3213,70 +2938,30 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu); */ void cond_synchronize_rcu(unsigned long oldstate) { - if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate)) + if (!rcu_seq_done(&rcu_state.gp_seq, oldstate)) synchronize_rcu(); else smp_mb(); /* Ensure GP ends before subsequent accesses. */ } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); -/** - * get_state_synchronize_sched - Snapshot current RCU-sched state - * - * Returns a cookie that is used by a later call to cond_synchronize_sched() - * to determine whether or not a full grace period has elapsed in the - * meantime. - */ -unsigned long get_state_synchronize_sched(void) -{ - /* - * Any prior manipulation of RCU-protected data must happen - * before the load from ->gp_seq. - */ - smp_mb(); /* ^^^ */ - return rcu_seq_snap(&rcu_sched_state.gp_seq); -} -EXPORT_SYMBOL_GPL(get_state_synchronize_sched); - -/** - * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period - * - * @oldstate: return value from earlier call to get_state_synchronize_sched() - * - * If a full RCU-sched grace period has elapsed since the earlier call to - * get_state_synchronize_sched(), just return. Otherwise, invoke - * synchronize_sched() to wait for a full grace period. - * - * Yes, this function does not take counter wrap into account. But - * counter wrap is harmless. If the counter wraps, we have waited for - * more than 2 billion grace periods (and way more on a 64-bit system!), - * so waiting for one additional grace period should be just fine. - */ -void cond_synchronize_sched(unsigned long oldstate) -{ - if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate)) - synchronize_sched(); - else - smp_mb(); /* Ensure GP ends before subsequent accesses. */ -} -EXPORT_SYMBOL_GPL(cond_synchronize_sched); - /* - * Check to see if there is any immediate RCU-related work to be done - * by the current CPU, for the specified type of RCU, returning 1 if so. - * The checks are in order of increasing expense: checks that can be - * carried out against CPU-local state are performed first. However, - * we must check for CPU stalls first, else we might not get a chance. + * Check to see if there is any immediate RCU-related work to be done by + * the current CPU, returning 1 if so and zero otherwise. The checks are + * in order of increasing expense: checks that can be carried out against + * CPU-local state are performed first. However, we must check for CPU + * stalls first, else we might not get a chance. */ -static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) +static int rcu_pending(void) { + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; /* Check for CPU stalls, if enabled. */ - check_cpu_stall(rsp, rdp); + check_cpu_stall(rdp); /* Is this CPU a NO_HZ_FULL CPU that should ignore RCU? */ - if (rcu_nohz_full_cpu(rsp)) + if (rcu_nohz_full_cpu()) return 0; /* Is the RCU core waiting for a quiescent state from this CPU? */ @@ -3288,7 +2973,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) return 1; /* Has RCU gone idle with this CPU needing another grace period? */ - if (!rcu_gp_in_progress(rsp) && + if (!rcu_gp_in_progress() && rcu_segcblist_is_enabled(&rdp->cblist) && !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) return 1; @@ -3307,21 +2992,6 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) } /* - * Check to see if there is any immediate RCU-related work to be done - * by the current CPU, returning 1 if so. This function is part of the - * RCU implementation; it is -not- an exported member of the RCU API. - */ -static int rcu_pending(void) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - if (__rcu_pending(rsp, this_cpu_ptr(rsp->rda))) - return 1; - return 0; -} - -/* * Return true if the specified CPU has any callback. If all_lazy is * non-NULL, store an indication of whether all callbacks are lazy. * (If there are no callbacks, all of them are deemed to be lazy.) @@ -3331,17 +3001,12 @@ static bool rcu_cpu_has_callbacks(bool *all_lazy) bool al = true; bool hc = false; struct rcu_data *rdp; - struct rcu_state *rsp; - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - if (rcu_segcblist_empty(&rdp->cblist)) - continue; + rdp = this_cpu_ptr(&rcu_data); + if (!rcu_segcblist_empty(&rdp->cblist)) { hc = true; - if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist) || !all_lazy) { + if (rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) al = false; - break; - } } if (all_lazy) *all_lazy = al; @@ -3349,81 +3014,80 @@ static bool rcu_cpu_has_callbacks(bool *all_lazy) } /* - * Helper function for _rcu_barrier() tracing. If tracing is disabled, + * Helper function for rcu_barrier() tracing. If tracing is disabled, * the compiler is expected to optimize this away. */ -static void _rcu_barrier_trace(struct rcu_state *rsp, const char *s, - int cpu, unsigned long done) +static void rcu_barrier_trace(const char *s, int cpu, unsigned long done) { - trace_rcu_barrier(rsp->name, s, cpu, - atomic_read(&rsp->barrier_cpu_count), done); + trace_rcu_barrier(rcu_state.name, s, cpu, + atomic_read(&rcu_state.barrier_cpu_count), done); } /* - * RCU callback function for _rcu_barrier(). If we are last, wake - * up the task executing _rcu_barrier(). + * RCU callback function for rcu_barrier(). If we are last, wake + * up the task executing rcu_barrier(). */ static void rcu_barrier_callback(struct rcu_head *rhp) { - struct rcu_data *rdp = container_of(rhp, struct rcu_data, barrier_head); - struct rcu_state *rsp = rdp->rsp; - - if (atomic_dec_and_test(&rsp->barrier_cpu_count)) { - _rcu_barrier_trace(rsp, TPS("LastCB"), -1, - rsp->barrier_sequence); - complete(&rsp->barrier_completion); + if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) { + rcu_barrier_trace(TPS("LastCB"), -1, + rcu_state.barrier_sequence); + complete(&rcu_state.barrier_completion); } else { - _rcu_barrier_trace(rsp, TPS("CB"), -1, rsp->barrier_sequence); + rcu_barrier_trace(TPS("CB"), -1, rcu_state.barrier_sequence); } } /* * Called with preemption disabled, and from cross-cpu IRQ context. */ -static void rcu_barrier_func(void *type) +static void rcu_barrier_func(void *unused) { - struct rcu_state *rsp = type; - struct rcu_data *rdp = raw_cpu_ptr(rsp->rda); + struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); - _rcu_barrier_trace(rsp, TPS("IRQ"), -1, rsp->barrier_sequence); + rcu_barrier_trace(TPS("IRQ"), -1, rcu_state.barrier_sequence); rdp->barrier_head.func = rcu_barrier_callback; debug_rcu_head_queue(&rdp->barrier_head); if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { - atomic_inc(&rsp->barrier_cpu_count); + atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); - _rcu_barrier_trace(rsp, TPS("IRQNQ"), -1, - rsp->barrier_sequence); + rcu_barrier_trace(TPS("IRQNQ"), -1, + rcu_state.barrier_sequence); } } -/* - * Orchestrate the specified type of RCU barrier, waiting for all - * RCU callbacks of the specified type to complete. +/** + * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. + * + * Note that this primitive does not necessarily wait for an RCU grace period + * to complete. For example, if there are no RCU callbacks queued anywhere + * in the system, then rcu_barrier() is within its rights to return + * immediately, without waiting for anything, much less an RCU grace period. */ -static void _rcu_barrier(struct rcu_state *rsp) +void rcu_barrier(void) { int cpu; struct rcu_data *rdp; - unsigned long s = rcu_seq_snap(&rsp->barrier_sequence); + unsigned long s = rcu_seq_snap(&rcu_state.barrier_sequence); - _rcu_barrier_trace(rsp, TPS("Begin"), -1, s); + rcu_barrier_trace(TPS("Begin"), -1, s); /* Take mutex to serialize concurrent rcu_barrier() requests. */ - mutex_lock(&rsp->barrier_mutex); + mutex_lock(&rcu_state.barrier_mutex); /* Did someone else do our work for us? */ - if (rcu_seq_done(&rsp->barrier_sequence, s)) { - _rcu_barrier_trace(rsp, TPS("EarlyExit"), -1, - rsp->barrier_sequence); + if (rcu_seq_done(&rcu_state.barrier_sequence, s)) { + rcu_barrier_trace(TPS("EarlyExit"), -1, + rcu_state.barrier_sequence); smp_mb(); /* caller's subsequent code after above check. */ - mutex_unlock(&rsp->barrier_mutex); + mutex_unlock(&rcu_state.barrier_mutex); return; } /* Mark the start of the barrier operation. */ - rcu_seq_start(&rsp->barrier_sequence); - _rcu_barrier_trace(rsp, TPS("Inc1"), -1, rsp->barrier_sequence); + rcu_seq_start(&rcu_state.barrier_sequence); + rcu_barrier_trace(TPS("Inc1"), -1, rcu_state.barrier_sequence); /* * Initialize the count to one rather than to zero in order to @@ -3431,8 +3095,8 @@ static void _rcu_barrier(struct rcu_state *rsp) * (or preemption of this task). Exclude CPU-hotplug operations * to ensure that no offline CPU has callbacks queued. */ - init_completion(&rsp->barrier_completion); - atomic_set(&rsp->barrier_cpu_count, 1); + init_completion(&rcu_state.barrier_completion); + atomic_set(&rcu_state.barrier_cpu_count, 1); get_online_cpus(); /* @@ -3443,26 +3107,26 @@ static void _rcu_barrier(struct rcu_state *rsp) for_each_possible_cpu(cpu) { if (!cpu_online(cpu) && !rcu_is_nocb_cpu(cpu)) continue; - rdp = per_cpu_ptr(rsp->rda, cpu); + rdp = per_cpu_ptr(&rcu_data, cpu); if (rcu_is_nocb_cpu(cpu)) { - if (!rcu_nocb_cpu_needs_barrier(rsp, cpu)) { - _rcu_barrier_trace(rsp, TPS("OfflineNoCB"), cpu, - rsp->barrier_sequence); + if (!rcu_nocb_cpu_needs_barrier(cpu)) { + rcu_barrier_trace(TPS("OfflineNoCB"), cpu, + rcu_state.barrier_sequence); } else { - _rcu_barrier_trace(rsp, TPS("OnlineNoCB"), cpu, - rsp->barrier_sequence); + rcu_barrier_trace(TPS("OnlineNoCB"), cpu, + rcu_state.barrier_sequence); smp_mb__before_atomic(); - atomic_inc(&rsp->barrier_cpu_count); + atomic_inc(&rcu_state.barrier_cpu_count); __call_rcu(&rdp->barrier_head, - rcu_barrier_callback, rsp, cpu, 0); + rcu_barrier_callback, cpu, 0); } } else if (rcu_segcblist_n_cbs(&rdp->cblist)) { - _rcu_barrier_trace(rsp, TPS("OnlineQ"), cpu, - rsp->barrier_sequence); - smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); + rcu_barrier_trace(TPS("OnlineQ"), cpu, + rcu_state.barrier_sequence); + smp_call_function_single(cpu, rcu_barrier_func, NULL, 1); } else { - _rcu_barrier_trace(rsp, TPS("OnlineNQ"), cpu, - rsp->barrier_sequence); + rcu_barrier_trace(TPS("OnlineNQ"), cpu, + rcu_state.barrier_sequence); } } put_online_cpus(); @@ -3471,37 +3135,20 @@ static void _rcu_barrier(struct rcu_state *rsp) * Now that we have an rcu_barrier_callback() callback on each * CPU, and thus each counted, remove the initial count. */ - if (atomic_dec_and_test(&rsp->barrier_cpu_count)) - complete(&rsp->barrier_completion); + if (atomic_dec_and_test(&rcu_state.barrier_cpu_count)) + complete(&rcu_state.barrier_completion); /* Wait for all rcu_barrier_callback() callbacks to be invoked. */ - wait_for_completion(&rsp->barrier_completion); + wait_for_completion(&rcu_state.barrier_completion); /* Mark the end of the barrier operation. */ - _rcu_barrier_trace(rsp, TPS("Inc2"), -1, rsp->barrier_sequence); - rcu_seq_end(&rsp->barrier_sequence); + rcu_barrier_trace(TPS("Inc2"), -1, rcu_state.barrier_sequence); + rcu_seq_end(&rcu_state.barrier_sequence); /* Other rcu_barrier() invocations can now safely proceed. */ - mutex_unlock(&rsp->barrier_mutex); -} - -/** - * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. - */ -void rcu_barrier_bh(void) -{ - _rcu_barrier(&rcu_bh_state); -} -EXPORT_SYMBOL_GPL(rcu_barrier_bh); - -/** - * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. - */ -void rcu_barrier_sched(void) -{ - _rcu_barrier(&rcu_sched_state); + mutex_unlock(&rcu_state.barrier_mutex); } -EXPORT_SYMBOL_GPL(rcu_barrier_sched); +EXPORT_SYMBOL_GPL(rcu_barrier); /* * Propagate ->qsinitmask bits up the rcu_node tree to account for the @@ -3535,46 +3182,46 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) * Do boot-time initialization of a CPU's per-CPU RCU data. */ static void __init -rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) +rcu_boot_init_percpu_data(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); /* Set up local state, ensuring consistent view of global state. */ rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu); - rdp->dynticks = &per_cpu(rcu_dynticks, cpu); - WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1); - WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks))); - rdp->rcu_ofl_gp_seq = rsp->gp_seq; + WARN_ON_ONCE(rdp->dynticks_nesting != 1); + WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp))); + rdp->rcu_ofl_gp_seq = rcu_state.gp_seq; rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED; - rdp->rcu_onl_gp_seq = rsp->gp_seq; + rdp->rcu_onl_gp_seq = rcu_state.gp_seq; rdp->rcu_onl_gp_flags = RCU_GP_CLEANED; rdp->cpu = cpu; - rdp->rsp = rsp; rcu_boot_init_nocb_percpu_data(rdp); } /* - * Initialize a CPU's per-CPU RCU data. Note that only one online or + * Invoked early in the CPU-online process, when pretty much all services + * are available. The incoming CPU is not present. + * + * Initializes a CPU's per-CPU RCU data. Note that only one online or * offline event can be happening at a given time. Note also that we can * accept some slop in the rsp->gp_seq access due to the fact that this * CPU cannot possibly have any RCU callbacks in flight yet. */ -static void -rcu_init_percpu_data(int cpu, struct rcu_state *rsp) +int rcutree_prepare_cpu(unsigned int cpu) { unsigned long flags; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct rcu_node *rnp = rcu_get_root(); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave_rcu_node(rnp, flags); rdp->qlen_last_fqs_check = 0; - rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->n_force_qs_snap = rcu_state.n_force_qs; rdp->blimit = blimit; if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */ !init_nocb_callback_list(rdp)) rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ - rdp->dynticks->dynticks_nesting = 1; /* CPU not up, no tearing. */ + rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */ rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -3589,25 +3236,11 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->gp_seq = rnp->gp_seq; rdp->gp_seq_needed = rnp->gp_seq; rdp->cpu_no_qs.b.norm = true; - rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu); rdp->core_needs_qs = false; rdp->rcu_iw_pending = false; rdp->rcu_iw_gp_seq = rnp->gp_seq - 1; - trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl")); + trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); -} - -/* - * Invoked early in the CPU-online process, when pretty much all - * services are available. The incoming CPU is not present. - */ -int rcutree_prepare_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - rcu_init_percpu_data(cpu, rsp); - rcu_prepare_kthreads(cpu); rcu_spawn_all_nocb_kthreads(cpu); @@ -3619,7 +3252,7 @@ int rcutree_prepare_cpu(unsigned int cpu) */ static void rcutree_affinity_setting(unsigned int cpu, int outgoing) { - struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); rcu_boost_kthread_setaffinity(rdp->mynode, outgoing); } @@ -3633,15 +3266,12 @@ int rcutree_online_cpu(unsigned int cpu) unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; - for_each_rcu_flavor(rsp) { - rdp = per_cpu_ptr(rsp->rda, cpu); - rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rnp->ffmask |= rdp->grpmask; - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask |= rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (IS_ENABLED(CONFIG_TREE_SRCU)) srcu_online_cpu(cpu); if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) @@ -3660,15 +3290,12 @@ int rcutree_offline_cpu(unsigned int cpu) unsigned long flags; struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; - for_each_rcu_flavor(rsp) { - rdp = per_cpu_ptr(rsp->rda, cpu); - rnp = rdp->mynode; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rnp->ffmask &= ~rdp->grpmask; - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->ffmask &= ~rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); rcutree_affinity_setting(cpu, cpu); if (IS_ENABLED(CONFIG_TREE_SRCU)) @@ -3676,32 +3303,6 @@ int rcutree_offline_cpu(unsigned int cpu) return 0; } -/* - * Near the end of the offline process. We do only tracing here. - */ -int rcutree_dying_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_cpu(rsp); - return 0; -} - -/* - * The outgoing CPU is gone and we are running elsewhere. - */ -int rcutree_dead_cpu(unsigned int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) { - rcu_cleanup_dead_cpu(cpu, rsp); - do_nocb_deferred_wakeup(per_cpu_ptr(rsp->rda, cpu)); - } - return 0; -} - static DEFINE_PER_CPU(int, rcu_cpu_started); /* @@ -3723,137 +3324,113 @@ void rcu_cpu_starting(unsigned int cpu) unsigned long oldmask; struct rcu_data *rdp; struct rcu_node *rnp; - struct rcu_state *rsp; if (per_cpu(rcu_cpu_started, cpu)) return; per_cpu(rcu_cpu_started, cpu) = 1; - for_each_rcu_flavor(rsp) { - rdp = per_cpu_ptr(rsp->rda, cpu); - rnp = rdp->mynode; - mask = rdp->grpmask; - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rnp->qsmaskinitnext |= mask; - oldmask = rnp->expmaskinitnext; - rnp->expmaskinitnext |= mask; - oldmask ^= rnp->expmaskinitnext; - nbits = bitmap_weight(&oldmask, BITS_PER_LONG); - /* Allow lockless access for expedited grace periods. */ - smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */ - rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ - rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq); - rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags); - if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ - /* Report QS -after- changing ->qsmaskinitnext! */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); - } else { - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - } + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + mask = rdp->grpmask; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rnp->qsmaskinitnext |= mask; + oldmask = rnp->expmaskinitnext; + rnp->expmaskinitnext |= mask; + oldmask ^= rnp->expmaskinitnext; + nbits = bitmap_weight(&oldmask, BITS_PER_LONG); + /* Allow lockless access for expedited grace periods. */ + smp_store_release(&rcu_state.ncpus, rcu_state.ncpus + nbits); /* ^^^ */ + rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */ + rdp->rcu_onl_gp_seq = READ_ONCE(rcu_state.gp_seq); + rdp->rcu_onl_gp_flags = READ_ONCE(rcu_state.gp_flags); + if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */ + /* Report QS -after- changing ->qsmaskinitnext! */ + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); + } else { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } #ifdef CONFIG_HOTPLUG_CPU /* - * The CPU is exiting the idle loop into the arch_cpu_idle_dead() - * function. We now remove it from the rcu_node tree's ->qsmaskinitnext - * bit masks. + * The outgoing function has no further need of RCU, so remove it from + * the rcu_node tree's ->qsmaskinitnext bit masks. + * + * Note that this function is special in that it is invoked directly + * from the outgoing CPU rather than from the cpuhp_step mechanism. + * This is because this function must be invoked at a precise location. */ -static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp) +void rcu_report_dead(unsigned int cpu) { unsigned long flags; unsigned long mask; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + /* QS for any half-done expedited grace period. */ + preempt_disable(); + rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); + preempt_enable(); + rcu_preempt_deferred_qs(current); + /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; - spin_lock(&rsp->ofl_lock); + raw_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(rsp->gp_seq); - rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags); + rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); + rdp->rcu_ofl_gp_flags = READ_ONCE(rcu_state.gp_flags); if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */ /* Report quiescent state -before- changing ->qsmaskinitnext! */ - rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags); + rcu_report_qs_rnp(mask, rnp, rnp->gp_seq, flags); raw_spin_lock_irqsave_rcu_node(rnp, flags); } rnp->qsmaskinitnext &= ~mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - spin_unlock(&rsp->ofl_lock); -} - -/* - * The outgoing function has no further need of RCU, so remove it from - * the list of CPUs that RCU must track. - * - * Note that this function is special in that it is invoked directly - * from the outgoing CPU rather than from the cpuhp_step mechanism. - * This is because this function must be invoked at a precise location. - */ -void rcu_report_dead(unsigned int cpu) -{ - struct rcu_state *rsp; - - /* QS for any half-done expedited RCU-sched GP. */ - preempt_disable(); - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(rcu_sched_state.rda), true); - preempt_enable(); - for_each_rcu_flavor(rsp) - rcu_cleanup_dying_idle_cpu(cpu, rsp); + raw_spin_unlock(&rcu_state.ofl_lock); per_cpu(rcu_cpu_started, cpu) = 0; } -/* Migrate the dead CPU's callbacks to the current CPU. */ -static void rcu_migrate_callbacks(int cpu, struct rcu_state *rsp) +/* + * The outgoing CPU has just passed through the dying-idle state, and we + * are being invoked from the CPU that was IPIed to continue the offline + * operation. Migrate the outgoing CPU's callbacks to the current CPU. + */ +void rcutree_migrate_callbacks(int cpu) { unsigned long flags; struct rcu_data *my_rdp; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_node *rnp_root = rcu_get_root(rdp->rsp); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct rcu_node *rnp_root = rcu_get_root(); bool needwake; if (rcu_is_nocb_cpu(cpu) || rcu_segcblist_empty(&rdp->cblist)) return; /* No callbacks to migrate. */ local_irq_save(flags); - my_rdp = this_cpu_ptr(rsp->rda); + my_rdp = this_cpu_ptr(&rcu_data); if (rcu_nocb_adopt_orphan_cbs(my_rdp, rdp, flags)) { local_irq_restore(flags); return; } raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */ /* Leverage recent GPs and set GP for new callbacks. */ - needwake = rcu_advance_cbs(rsp, rnp_root, rdp) || - rcu_advance_cbs(rsp, rnp_root, my_rdp); + needwake = rcu_advance_cbs(rnp_root, rdp) || + rcu_advance_cbs(rnp_root, my_rdp); rcu_segcblist_merge(&my_rdp->cblist, &rdp->cblist); WARN_ON_ONCE(rcu_segcblist_empty(&my_rdp->cblist) != !rcu_segcblist_n_cbs(&my_rdp->cblist)); raw_spin_unlock_irqrestore_rcu_node(rnp_root, flags); if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); WARN_ONCE(rcu_segcblist_n_cbs(&rdp->cblist) != 0 || !rcu_segcblist_empty(&rdp->cblist), "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, 1stCB=%p\n", cpu, rcu_segcblist_n_cbs(&rdp->cblist), rcu_segcblist_first_cb(&rdp->cblist)); } - -/* - * The outgoing CPU has just passed through the dying-idle state, - * and we are being invoked from the CPU that was IPIed to continue the - * offline operation. We need to migrate the outgoing CPU's callbacks. - */ -void rcutree_migrate_callbacks(int cpu) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - rcu_migrate_callbacks(cpu, rsp); -} #endif /* @@ -3881,14 +3458,13 @@ static int rcu_pm_notify(struct notifier_block *self, } /* - * Spawn the kthreads that handle each RCU flavor's grace periods. + * Spawn the kthreads that handle RCU's grace periods. */ static int __init rcu_spawn_gp_kthread(void) { unsigned long flags; int kthread_prio_in = kthread_prio; struct rcu_node *rnp; - struct rcu_state *rsp; struct sched_param sp; struct task_struct *t; @@ -3908,19 +3484,17 @@ static int __init rcu_spawn_gp_kthread(void) kthread_prio, kthread_prio_in); rcu_scheduler_fully_active = 1; - for_each_rcu_flavor(rsp) { - t = kthread_create(rcu_gp_kthread, rsp, "%s", rsp->name); - BUG_ON(IS_ERR(t)); - rnp = rcu_get_root(rsp); - raw_spin_lock_irqsave_rcu_node(rnp, flags); - rsp->gp_kthread = t; - if (kthread_prio) { - sp.sched_priority = kthread_prio; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - } - raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - wake_up_process(t); + t = kthread_create(rcu_gp_kthread, NULL, "%s", rcu_state.name); + BUG_ON(IS_ERR(t)); + rnp = rcu_get_root(); + raw_spin_lock_irqsave_rcu_node(rnp, flags); + rcu_state.gp_kthread = t; + if (kthread_prio) { + sp.sched_priority = kthread_prio; + sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + wake_up_process(t); rcu_spawn_nocb_kthreads(); rcu_spawn_boost_kthreads(); return 0; @@ -3947,9 +3521,9 @@ void rcu_scheduler_starting(void) } /* - * Helper function for rcu_init() that initializes one rcu_state structure. + * Helper function for rcu_init() that initializes the rcu_state structure. */ -static void __init rcu_init_one(struct rcu_state *rsp) +static void __init rcu_init_one(void) { static const char * const buf[] = RCU_NODE_NAME_INIT; static const char * const fqs[] = RCU_FQS_NAME_INIT; @@ -3971,14 +3545,15 @@ static void __init rcu_init_one(struct rcu_state *rsp) /* Initialize the level-tracking arrays. */ for (i = 1; i < rcu_num_lvls; i++) - rsp->level[i] = rsp->level[i - 1] + num_rcu_lvl[i - 1]; + rcu_state.level[i] = + rcu_state.level[i - 1] + num_rcu_lvl[i - 1]; rcu_init_levelspread(levelspread, num_rcu_lvl); /* Initialize the elements themselves, starting from the leaves. */ for (i = rcu_num_lvls - 1; i >= 0; i--) { cpustride *= levelspread[i]; - rnp = rsp->level[i]; + rnp = rcu_state.level[i]; for (j = 0; j < num_rcu_lvl[i]; j++, rnp++) { raw_spin_lock_init(&ACCESS_PRIVATE(rnp, lock)); lockdep_set_class_and_name(&ACCESS_PRIVATE(rnp, lock), @@ -3986,9 +3561,9 @@ static void __init rcu_init_one(struct rcu_state *rsp) raw_spin_lock_init(&rnp->fqslock); lockdep_set_class_and_name(&rnp->fqslock, &rcu_fqs_class[i], fqs[i]); - rnp->gp_seq = rsp->gp_seq; - rnp->gp_seq_needed = rsp->gp_seq; - rnp->completedqs = rsp->gp_seq; + rnp->gp_seq = rcu_state.gp_seq; + rnp->gp_seq_needed = rcu_state.gp_seq; + rnp->completedqs = rcu_state.gp_seq; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -4001,8 +3576,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) rnp->parent = NULL; } else { rnp->grpnum = j % levelspread[i - 1]; - rnp->grpmask = 1UL << rnp->grpnum; - rnp->parent = rsp->level[i - 1] + + rnp->grpmask = BIT(rnp->grpnum); + rnp->parent = rcu_state.level[i - 1] + j / levelspread[i - 1]; } rnp->level = i; @@ -4016,16 +3591,15 @@ static void __init rcu_init_one(struct rcu_state *rsp) } } - init_swait_queue_head(&rsp->gp_wq); - init_swait_queue_head(&rsp->expedited_wq); - rnp = rcu_first_leaf_node(rsp); + init_swait_queue_head(&rcu_state.gp_wq); + init_swait_queue_head(&rcu_state.expedited_wq); + rnp = rcu_first_leaf_node(); for_each_possible_cpu(i) { while (i > rnp->grphi) rnp++; - per_cpu_ptr(rsp->rda, i)->mynode = rnp; - rcu_boot_init_percpu_data(i, rsp); + per_cpu_ptr(&rcu_data, i)->mynode = rnp; + rcu_boot_init_percpu_data(i); } - list_add(&rsp->flavors, &rcu_struct_flavors); } /* @@ -4051,6 +3625,8 @@ static void __init rcu_init_geometry(void) jiffies_till_first_fqs = d; if (jiffies_till_next_fqs == ULONG_MAX) jiffies_till_next_fqs = d; + if (jiffies_till_sched_qs == ULONG_MAX) + adjust_jiffies_till_sched_qs(); /* If the compile-time values are accurate, just leave. */ if (rcu_fanout_leaf == RCU_FANOUT_LEAF && @@ -4109,16 +3685,16 @@ static void __init rcu_init_geometry(void) /* * Dump out the structure of the rcu_node combining tree associated - * with the rcu_state structure referenced by rsp. + * with the rcu_state structure. */ -static void __init rcu_dump_rcu_node_tree(struct rcu_state *rsp) +static void __init rcu_dump_rcu_node_tree(void) { int level = 0; struct rcu_node *rnp; pr_info("rcu_node tree layout dump\n"); pr_info(" "); - rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_for_each_node_breadth_first(rnp) { if (rnp->level != level) { pr_cont("\n"); pr_info(" "); @@ -4140,11 +3716,9 @@ void __init rcu_init(void) rcu_bootup_announce(); rcu_init_geometry(); - rcu_init_one(&rcu_bh_state); - rcu_init_one(&rcu_sched_state); + rcu_init_one(); if (dump_tree) - rcu_dump_rcu_node_tree(&rcu_sched_state); - __rcu_init_preempt(); + rcu_dump_rcu_node_tree(); open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); /* @@ -4164,6 +3738,7 @@ void __init rcu_init(void) WARN_ON(!rcu_gp_wq); rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_par_gp_wq); + srcu_init(); } #include "tree_exp.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4e74df768c57..703e19ff532d 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -34,34 +34,9 @@ #include "rcu_segcblist.h" -/* - * Dynticks per-CPU state. - */ -struct rcu_dynticks { - long dynticks_nesting; /* Track process nesting level. */ - long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ - atomic_t dynticks; /* Even value for idle, else odd. */ - bool rcu_need_heavy_qs; /* GP old, need heavy quiescent state. */ - unsigned long rcu_qs_ctr; /* Light universal quiescent state ctr. */ - bool rcu_urgent_qs; /* GP old need light quiescent state. */ -#ifdef CONFIG_RCU_FAST_NO_HZ - bool all_lazy; /* Are all CPU's CBs lazy? */ - unsigned long nonlazy_posted; - /* # times non-lazy CBs posted to CPU. */ - unsigned long nonlazy_posted_snap; - /* idle-period nonlazy_posted snapshot. */ - unsigned long last_accelerate; - /* Last jiffy CBs were accelerated. */ - unsigned long last_advance_all; - /* Last jiffy CBs were all advanced. */ - int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ -#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ -}; - /* Communicate arguments to a workqueue handler. */ struct rcu_exp_work { smp_call_func_t rew_func; - struct rcu_state *rew_rsp; unsigned long rew_s; struct work_struct rew_work; }; @@ -170,7 +145,7 @@ struct rcu_node { * are indexed relative to this interval rather than the global CPU ID space. * This generates the bit for a CPU in node-local masks. */ -#define leaf_node_cpu_bit(rnp, cpu) (1UL << ((cpu) - (rnp)->grplo)) +#define leaf_node_cpu_bit(rnp, cpu) (BIT((cpu) - (rnp)->grplo)) /* * Union to allow "aggregate OR" operation on the need for a quiescent @@ -189,12 +164,11 @@ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ unsigned long gp_seq; /* Track rsp->rcu_gp_seq counter. */ unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed ctr. */ - unsigned long rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */ - /* for rcu_all_qs() invocations. */ union rcu_noqs cpu_no_qs; /* No QSes yet for this CPU. */ bool core_needs_qs; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ bool gpwrap; /* Possible ->gp_seq wrap. */ + bool deferred_qs; /* This CPU awaiting a deferred QS? */ struct rcu_node *mynode; /* This CPU's leaf of hierarchy */ unsigned long grpmask; /* Mask to apply to leaf qsmask. */ unsigned long ticks_this_gp; /* The number of scheduling-clock */ @@ -213,23 +187,27 @@ struct rcu_data { long blimit; /* Upper limit on a processed batch */ /* 3) dynticks interface. */ - struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ int dynticks_snap; /* Per-GP tracking for dynticks. */ - - /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ - unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ - unsigned long cond_resched_completed; - /* Grace period that needs help */ - /* from cond_resched(). */ - - /* 5) _rcu_barrier(), OOM callbacks, and expediting. */ - struct rcu_head barrier_head; + long dynticks_nesting; /* Track process nesting level. */ + long dynticks_nmi_nesting; /* Track irq/NMI nesting level. */ + atomic_t dynticks; /* Even value for idle, else odd. */ + bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */ + bool rcu_urgent_qs; /* GP old need light quiescent state. */ #ifdef CONFIG_RCU_FAST_NO_HZ - struct rcu_head oom_head; + bool all_lazy; /* Are all CPU's CBs lazy? */ + unsigned long nonlazy_posted; /* # times non-lazy CB posted to CPU. */ + unsigned long nonlazy_posted_snap; + /* Nonlazy_posted snapshot. */ + unsigned long last_accelerate; /* Last jiffy CBs were accelerated. */ + unsigned long last_advance_all; /* Last jiffy CBs were all advanced. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ + + /* 4) rcu_barrier(), OOM callbacks, and expediting. */ + struct rcu_head barrier_head; int exp_dynticks_snap; /* Double-check need for IPI. */ - /* 6) Callback offloading. */ + /* 5) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU struct rcu_head *nocb_head; /* CBs waiting for kthread. */ struct rcu_head **nocb_tail; @@ -256,7 +234,7 @@ struct rcu_data { /* Leader CPU takes GP-end wakeups. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ - /* 7) Diagnostic data, including RCU CPU stall warnings. */ + /* 6) Diagnostic data, including RCU CPU stall warnings. */ unsigned int softirq_snap; /* Snapshot of softirq activity. */ /* ->rcu_iw* fields protected by leaf rcu_node ->lock. */ struct irq_work rcu_iw; /* Check for non-irq activity. */ @@ -266,9 +244,9 @@ struct rcu_data { short rcu_ofl_gp_flags; /* ->gp_flags at last offline. */ unsigned long rcu_onl_gp_seq; /* ->gp_seq at last online. */ short rcu_onl_gp_flags; /* ->gp_flags at last online. */ + unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ int cpu; - struct rcu_state *rsp; }; /* Values for nocb_defer_wakeup field in struct rcu_data. */ @@ -314,8 +292,6 @@ struct rcu_state { struct rcu_node *level[RCU_NUM_LVLS + 1]; /* Hierarchy levels (+1 to */ /* shut bogus gcc warning) */ - struct rcu_data __percpu *rda; /* pointer of percu rcu_data. */ - call_rcu_func_t call; /* call_rcu() flavor. */ int ncpus; /* # CPUs seen so far. */ /* The following fields are guarded by the root rcu_node's lock. */ @@ -334,7 +310,7 @@ struct rcu_state { atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ unsigned long barrier_sequence; /* ++ at start and end of */ - /* _rcu_barrier(). */ + /* rcu_barrier(). */ /* End of fields guarded by barrier_mutex. */ struct mutex exp_mutex; /* Serialize expedited GP. */ @@ -366,9 +342,8 @@ struct rcu_state { /* jiffies. */ const char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ - struct list_head flavors; /* List of RCU flavors. */ - spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; + raw_spinlock_t ofl_lock ____cacheline_internodealigned_in_smp; /* Synchronize offline with */ /* GP pre-initialization. */ }; @@ -388,7 +363,6 @@ struct rcu_state { #define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ -#ifndef RCU_TREE_NONCORE static const char * const gp_state_names[] = { "RCU_GP_IDLE", "RCU_GP_WAIT_GPS", @@ -400,13 +374,29 @@ static const char * const gp_state_names[] = { "RCU_GP_CLEANUP", "RCU_GP_CLEANED", }; -#endif /* #ifndef RCU_TREE_NONCORE */ - -extern struct list_head rcu_struct_flavors; -/* Sequence through rcu_state structures for each RCU flavor. */ -#define for_each_rcu_flavor(rsp) \ - list_for_each_entry((rsp), &rcu_struct_flavors, flavors) +/* + * In order to export the rcu_state name to the tracing tools, it + * needs to be added in the __tracepoint_string section. + * This requires defining a separate variable tp_<sname>_varname + * that points to the string being used, and this will allow + * the tracing userspace tools to be able to decipher the string + * address to the matching string. + */ +#ifdef CONFIG_PREEMPT_RCU +#define RCU_ABBR 'p' +#define RCU_NAME_RAW "rcu_preempt" +#else /* #ifdef CONFIG_PREEMPT_RCU */ +#define RCU_ABBR 's' +#define RCU_NAME_RAW "rcu_sched" +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#ifndef CONFIG_TRACING +#define RCU_NAME RCU_NAME_RAW +#else /* #ifdef CONFIG_TRACING */ +static char rcu_name[] = RCU_NAME_RAW; +static const char *tp_rcu_varname __used __tracepoint_string = rcu_name; +#define RCU_NAME rcu_name +#endif /* #else #ifdef CONFIG_TRACING */ /* * RCU implementation internal declarations: @@ -419,7 +409,7 @@ extern struct rcu_state rcu_bh_state; extern struct rcu_state rcu_preempt_state; #endif /* #ifdef CONFIG_PREEMPT_RCU */ -int rcu_dynticks_snap(struct rcu_dynticks *rdtp); +int rcu_dynticks_snap(struct rcu_data *rdp); #ifdef CONFIG_RCU_BOOST DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); @@ -428,45 +418,37 @@ DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DECLARE_PER_CPU(char, rcu_cpu_has_work); #endif /* #ifdef CONFIG_RCU_BOOST */ -#ifndef RCU_TREE_NONCORE - /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); -static void rcu_preempt_note_context_switch(bool preempt); +static void rcu_qs(void); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static bool rcu_preempt_has_tasks(struct rcu_node *rnp); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_print_detail_task_stall(struct rcu_state *rsp); +static void rcu_print_detail_task_stall(void); static int rcu_print_task_stall(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); -static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, - struct rcu_node *rnp); -static void rcu_preempt_check_callbacks(void); +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); +static void rcu_flavor_check_callbacks(int user); void call_rcu(struct rcu_head *head, rcu_callback_t func); -static void __init __rcu_init_preempt(void); -static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, - int ncheck); +static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); -#ifdef CONFIG_RCU_BOOST -static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp); -#endif /* #ifdef CONFIG_RCU_BOOST */ static void __init rcu_spawn_boost_kthreads(void); static void rcu_prepare_kthreads(int cpu); static void rcu_cleanup_after_idle(void); static void rcu_prepare_for_idle(void); static void rcu_idle_count_callbacks_posted(void); static bool rcu_preempt_has_tasks(struct rcu_node *rnp); +static bool rcu_preempt_need_deferred_qs(struct task_struct *t); +static void rcu_preempt_deferred_qs(struct task_struct *t); static void print_cpu_stall_info_begin(void); -static void print_cpu_stall_info(struct rcu_state *rsp, int cpu); +static void print_cpu_stall_info(int cpu); static void print_cpu_stall_info_end(void); static void zero_cpu_stall_ticks(struct rcu_data *rdp); -static void increment_cpu_stall_ticks(void); -static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); +static bool rcu_nocb_cpu_needs_barrier(int cpu); static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); @@ -481,11 +463,11 @@ static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); static void rcu_spawn_all_nocb_kthreads(int cpu); static void __init rcu_spawn_nocb_kthreads(void); #ifdef CONFIG_RCU_NOCB_CPU -static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp); +static void __init rcu_organize_nocb_kthreads(void); #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ static bool init_nocb_callback_list(struct rcu_data *rdp); static void rcu_bind_gp_kthread(void); -static bool rcu_nohz_full_cpu(struct rcu_state *rsp); +static bool rcu_nohz_full_cpu(void); static void rcu_dynticks_task_enter(void); static void rcu_dynticks_task_exit(void); @@ -496,5 +478,3 @@ void srcu_offline_cpu(unsigned int cpu); void srcu_online_cpu(unsigned int cpu) { } void srcu_offline_cpu(unsigned int cpu) { } #endif /* #else #ifdef CONFIG_SRCU */ - -#endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 0b2c2ad69629..8d18c1014e2b 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -25,39 +25,39 @@ /* * Record the start of an expedited grace period. */ -static void rcu_exp_gp_seq_start(struct rcu_state *rsp) +static void rcu_exp_gp_seq_start(void) { - rcu_seq_start(&rsp->expedited_sequence); + rcu_seq_start(&rcu_state.expedited_sequence); } /* * Return then value that expedited-grace-period counter will have * at the end of the current grace period. */ -static __maybe_unused unsigned long rcu_exp_gp_seq_endval(struct rcu_state *rsp) +static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void) { - return rcu_seq_endval(&rsp->expedited_sequence); + return rcu_seq_endval(&rcu_state.expedited_sequence); } /* * Record the end of an expedited grace period. */ -static void rcu_exp_gp_seq_end(struct rcu_state *rsp) +static void rcu_exp_gp_seq_end(void) { - rcu_seq_end(&rsp->expedited_sequence); + rcu_seq_end(&rcu_state.expedited_sequence); smp_mb(); /* Ensure that consecutive grace periods serialize. */ } /* * Take a snapshot of the expedited-grace-period counter. */ -static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) +static unsigned long rcu_exp_gp_seq_snap(void) { unsigned long s; smp_mb(); /* Caller's modifications seen first by other CPUs. */ - s = rcu_seq_snap(&rsp->expedited_sequence); - trace_rcu_exp_grace_period(rsp->name, s, TPS("snap")); + s = rcu_seq_snap(&rcu_state.expedited_sequence); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("snap")); return s; } @@ -66,9 +66,9 @@ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp) * if a full expedited grace period has elapsed since that snapshot * was taken. */ -static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) +static bool rcu_exp_gp_seq_done(unsigned long s) { - return rcu_seq_done(&rsp->expedited_sequence, s); + return rcu_seq_done(&rcu_state.expedited_sequence, s); } /* @@ -78,26 +78,26 @@ static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s) * ever been online. This means that this function normally takes its * no-work-to-do fastpath. */ -static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) +static void sync_exp_reset_tree_hotplug(void) { bool done; unsigned long flags; unsigned long mask; unsigned long oldmask; - int ncpus = smp_load_acquire(&rsp->ncpus); /* Order against locking. */ + int ncpus = smp_load_acquire(&rcu_state.ncpus); /* Order vs. locking. */ struct rcu_node *rnp; struct rcu_node *rnp_up; /* If no new CPUs onlined since last time, nothing to do. */ - if (likely(ncpus == rsp->ncpus_snap)) + if (likely(ncpus == rcu_state.ncpus_snap)) return; - rsp->ncpus_snap = ncpus; + rcu_state.ncpus_snap = ncpus; /* * Each pass through the following loop propagates newly onlined * CPUs for the current rcu_node structure up the rcu_node tree. */ - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmaskinit == rnp->expmaskinitnext) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -135,13 +135,13 @@ static void sync_exp_reset_tree_hotplug(struct rcu_state *rsp) * Reset the ->expmask values in the rcu_node tree in preparation for * a new expedited grace period. */ -static void __maybe_unused sync_exp_reset_tree(struct rcu_state *rsp) +static void __maybe_unused sync_exp_reset_tree(void) { unsigned long flags; struct rcu_node *rnp; - sync_exp_reset_tree_hotplug(rsp); - rcu_for_each_node_breadth_first(rsp, rnp) { + sync_exp_reset_tree_hotplug(); + rcu_for_each_node_breadth_first(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); rnp->expmask = rnp->expmaskinit; @@ -194,7 +194,7 @@ static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) * * Caller must hold the specified rcu_node structure's ->lock. */ -static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, +static void __rcu_report_exp_rnp(struct rcu_node *rnp, bool wake, unsigned long flags) __releases(rnp->lock) { @@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - swake_up_one(&rsp->expedited_wq); + swake_up_one(&rcu_state.expedited_wq); } break; } @@ -229,20 +229,19 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, * Report expedited quiescent state for specified node. This is a * lock-acquisition wrapper function for __rcu_report_exp_rnp(). */ -static void __maybe_unused rcu_report_exp_rnp(struct rcu_state *rsp, - struct rcu_node *rnp, bool wake) +static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake) { unsigned long flags; raw_spin_lock_irqsave_rcu_node(rnp, flags); - __rcu_report_exp_rnp(rsp, rnp, wake, flags); + __rcu_report_exp_rnp(rnp, wake, flags); } /* * Report expedited quiescent state for multiple CPUs, all covered by the * specified leaf rcu_node structure. */ -static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, +static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, unsigned long mask, bool wake) { unsigned long flags; @@ -253,23 +252,23 @@ static void rcu_report_exp_cpu_mult(struct rcu_state *rsp, struct rcu_node *rnp, return; } rnp->expmask &= ~mask; - __rcu_report_exp_rnp(rsp, rnp, wake, flags); /* Releases rnp->lock. */ + __rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */ } /* * Report expedited quiescent state for specified rcu_data (CPU). */ -static void rcu_report_exp_rdp(struct rcu_state *rsp, struct rcu_data *rdp, - bool wake) +static void rcu_report_exp_rdp(struct rcu_data *rdp) { - rcu_report_exp_cpu_mult(rsp, rdp->mynode, rdp->grpmask, wake); + WRITE_ONCE(rdp->deferred_qs, false); + rcu_report_exp_cpu_mult(rdp->mynode, rdp->grpmask, true); } -/* Common code for synchronize_{rcu,sched}_expedited() work-done checking. */ -static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s) +/* Common code for work-done checking. */ +static bool sync_exp_work_done(unsigned long s) { - if (rcu_exp_gp_seq_done(rsp, s)) { - trace_rcu_exp_grace_period(rsp->name, s, TPS("done")); + if (rcu_exp_gp_seq_done(s)) { + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("done")); /* Ensure test happens before caller kfree(). */ smp_mb__before_atomic(); /* ^^^ */ return true; @@ -284,28 +283,28 @@ static bool sync_exp_work_done(struct rcu_state *rsp, unsigned long s) * with the mutex held, indicating that the caller must actually do the * expedited grace period. */ -static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) +static bool exp_funnel_lock(unsigned long s) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id()); struct rcu_node *rnp = rdp->mynode; - struct rcu_node *rnp_root = rcu_get_root(rsp); + struct rcu_node *rnp_root = rcu_get_root(); /* Low-contention fastpath. */ if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s) && (rnp == rnp_root || ULONG_CMP_LT(READ_ONCE(rnp_root->exp_seq_rq), s)) && - mutex_trylock(&rsp->exp_mutex)) + mutex_trylock(&rcu_state.exp_mutex)) goto fastpath; /* * Each pass through the following loop works its way up * the rcu_node tree, returning if others have done the work or - * otherwise falls through to acquire rsp->exp_mutex. The mapping + * otherwise falls through to acquire ->exp_mutex. The mapping * from CPU to rcu_node structure can be inexact, as it is just * promoting locality and is not strictly needed for correctness. */ for (; rnp != NULL; rnp = rnp->parent) { - if (sync_exp_work_done(rsp, s)) + if (sync_exp_work_done(s)) return true; /* Work not done, either wait here or go up. */ @@ -314,68 +313,29 @@ static bool exp_funnel_lock(struct rcu_state *rsp, unsigned long s) /* Someone else doing GP, so wait for them. */ spin_unlock(&rnp->exp_lock); - trace_rcu_exp_funnel_lock(rsp->name, rnp->level, + trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level, rnp->grplo, rnp->grphi, TPS("wait")); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], - sync_exp_work_done(rsp, s)); + sync_exp_work_done(s)); return true; } rnp->exp_seq_rq = s; /* Followers can wait on us. */ spin_unlock(&rnp->exp_lock); - trace_rcu_exp_funnel_lock(rsp->name, rnp->level, rnp->grplo, - rnp->grphi, TPS("nxtlvl")); + trace_rcu_exp_funnel_lock(rcu_state.name, rnp->level, + rnp->grplo, rnp->grphi, TPS("nxtlvl")); } - mutex_lock(&rsp->exp_mutex); + mutex_lock(&rcu_state.exp_mutex); fastpath: - if (sync_exp_work_done(rsp, s)) { - mutex_unlock(&rsp->exp_mutex); + if (sync_exp_work_done(s)) { + mutex_unlock(&rcu_state.exp_mutex); return true; } - rcu_exp_gp_seq_start(rsp); - trace_rcu_exp_grace_period(rsp->name, s, TPS("start")); + rcu_exp_gp_seq_start(); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("start")); return false; } -/* Invoked on each online non-idle CPU for expedited quiescent state. */ -static void sync_sched_exp_handler(void *data) -{ - struct rcu_data *rdp; - struct rcu_node *rnp; - struct rcu_state *rsp = data; - - rdp = this_cpu_ptr(rsp->rda); - rnp = rdp->mynode; - if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || - __this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) - return; - if (rcu_is_cpu_rrupt_from_idle()) { - rcu_report_exp_rdp(&rcu_sched_state, - this_cpu_ptr(&rcu_sched_data), true); - return; - } - __this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, true); - /* Store .exp before .rcu_urgent_qs. */ - smp_store_release(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs), true); - resched_cpu(smp_processor_id()); -} - -/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */ -static void sync_sched_exp_online_cleanup(int cpu) -{ - struct rcu_data *rdp; - int ret; - struct rcu_node *rnp; - struct rcu_state *rsp = &rcu_sched_state; - - rdp = per_cpu_ptr(rsp->rda, cpu); - rnp = rdp->mynode; - if (!(READ_ONCE(rnp->expmask) & rdp->grpmask)) - return; - ret = smp_call_function_single(cpu, sync_sched_exp_handler, rsp, 0); - WARN_ON_ONCE(ret); -} - /* * Select the CPUs within the specified rcu_node that the upcoming * expedited grace period needs to wait for. @@ -391,7 +351,6 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) struct rcu_exp_work *rewp = container_of(wp, struct rcu_exp_work, rew_work); struct rcu_node *rnp = container_of(rewp, struct rcu_node, rew); - struct rcu_state *rsp = rewp->rew_rsp; func = rewp->rew_func; raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -400,15 +359,14 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) mask_ofl_test = 0; for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { unsigned long mask = leaf_node_cpu_bit(rnp, cpu); - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = per_cpu_ptr(&rcu_dynticks, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); int snap; if (raw_smp_processor_id() == cpu || !(rnp->qsmaskinitnext & mask)) { mask_ofl_test |= mask; } else { - snap = rcu_dynticks_snap(rdtp); + snap = rcu_dynticks_snap(rdp); if (rcu_dynticks_in_eqs(snap)) mask_ofl_test |= mask; else @@ -429,17 +387,16 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) /* IPI the remaining CPUs for expedited quiescent state. */ for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { unsigned long mask = leaf_node_cpu_bit(rnp, cpu); - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); if (!(mask_ofl_ipi & mask)) continue; retry_ipi: - if (rcu_dynticks_in_eqs_since(rdp->dynticks, - rdp->exp_dynticks_snap)) { + if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) { mask_ofl_test |= mask; continue; } - ret = smp_call_function_single(cpu, func, rsp, 0); + ret = smp_call_function_single(cpu, func, NULL, 0); if (!ret) { mask_ofl_ipi &= ~mask; continue; @@ -450,7 +407,7 @@ retry_ipi: (rnp->expmask & mask)) { /* Online, so delay for a bit and try again. */ raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("selectofl")); + trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("selectofl")); schedule_timeout_uninterruptible(1); goto retry_ipi; } @@ -462,33 +419,31 @@ retry_ipi: /* Report quiescent states for those that went offline. */ mask_ofl_test |= mask_ofl_ipi; if (mask_ofl_test) - rcu_report_exp_cpu_mult(rsp, rnp, mask_ofl_test, false); + rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); } /* * Select the nodes that the upcoming expedited grace period needs * to wait for. */ -static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, - smp_call_func_t func) +static void sync_rcu_exp_select_cpus(smp_call_func_t func) { int cpu; struct rcu_node *rnp; - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset")); - sync_exp_reset_tree(rsp); - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("select")); + trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("reset")); + sync_exp_reset_tree(); + trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("select")); /* Schedule work for each leaf rcu_node structure. */ - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ rnp->rew.rew_func = func; - rnp->rew.rew_rsp = rsp; if (!READ_ONCE(rcu_par_gp_wq) || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || - rcu_is_last_leaf_node(rsp, rnp)) { + rcu_is_last_leaf_node(rnp)) { /* No workqueues yet or last leaf, do direct call. */ sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work); continue; @@ -505,12 +460,12 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp, } /* Wait for workqueue jobs (if any) to complete. */ - rcu_for_each_leaf_node(rsp, rnp) + rcu_for_each_leaf_node(rnp) if (rnp->exp_need_flush) flush_work(&rnp->rew.rew_work); } -static void synchronize_sched_expedited_wait(struct rcu_state *rsp) +static void synchronize_sched_expedited_wait(void) { int cpu; unsigned long jiffies_stall; @@ -518,16 +473,16 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) unsigned long mask; int ndetected; struct rcu_node *rnp; - struct rcu_node *rnp_root = rcu_get_root(rsp); + struct rcu_node *rnp_root = rcu_get_root(); int ret; - trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("startwait")); + trace_rcu_exp_grace_period(rcu_state.name, rcu_exp_gp_seq_endval(), TPS("startwait")); jiffies_stall = rcu_jiffies_till_stall_check(); jiffies_start = jiffies; for (;;) { ret = swait_event_timeout_exclusive( - rsp->expedited_wq, + rcu_state.expedited_wq, sync_rcu_preempt_exp_done_unlocked(rnp_root), jiffies_stall); if (ret > 0 || sync_rcu_preempt_exp_done_unlocked(rnp_root)) @@ -537,9 +492,9 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) continue; panic_on_rcu_stall(); pr_err("INFO: %s detected expedited stalls on CPUs/tasks: {", - rsp->name); + rcu_state.name); ndetected = 0; - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { ndetected += rcu_print_task_exp_stall(rnp); for_each_leaf_node_possible_cpu(rnp, cpu) { struct rcu_data *rdp; @@ -548,7 +503,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) if (!(rnp->expmask & mask)) continue; ndetected++; - rdp = per_cpu_ptr(rsp->rda, cpu); + rdp = per_cpu_ptr(&rcu_data, cpu); pr_cont(" %d-%c%c%c", cpu, "O."[!!cpu_online(cpu)], "o."[!!(rdp->grpmask & rnp->expmaskinit)], @@ -556,11 +511,11 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } } pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", - jiffies - jiffies_start, rsp->expedited_sequence, + jiffies - jiffies_start, rcu_state.expedited_sequence, rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); if (ndetected) { pr_err("blocking rcu_node structures:"); - rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_for_each_node_breadth_first(rnp) { if (rnp == rnp_root) continue; /* printed unconditionally */ if (sync_rcu_preempt_exp_done_unlocked(rnp)) @@ -572,7 +527,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) } pr_cont("\n"); } - rcu_for_each_leaf_node(rsp, rnp) { + rcu_for_each_leaf_node(rnp) { for_each_leaf_node_possible_cpu(rnp, cpu) { mask = leaf_node_cpu_bit(rnp, cpu); if (!(rnp->expmask & mask)) @@ -590,21 +545,21 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) * grace period. Also update all the ->exp_seq_rq counters as needed * in order to avoid counter-wrap problems. */ -static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s) +static void rcu_exp_wait_wake(unsigned long s) { struct rcu_node *rnp; - synchronize_sched_expedited_wait(rsp); - rcu_exp_gp_seq_end(rsp); - trace_rcu_exp_grace_period(rsp->name, s, TPS("end")); + synchronize_sched_expedited_wait(); + rcu_exp_gp_seq_end(); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); /* * Switch over to wakeup mode, allowing the next GP, but -only- the * next GP, to proceed. */ - mutex_lock(&rsp->exp_wake_mutex); + mutex_lock(&rcu_state.exp_wake_mutex); - rcu_for_each_node_breadth_first(rsp, rnp) { + rcu_for_each_node_breadth_first(rnp) { if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) { spin_lock(&rnp->exp_lock); /* Recheck, avoid hang in case someone just arrived. */ @@ -613,24 +568,23 @@ static void rcu_exp_wait_wake(struct rcu_state *rsp, unsigned long s) spin_unlock(&rnp->exp_lock); } smp_mb(); /* All above changes before wakeup. */ - wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rsp->expedited_sequence) & 0x3]); + wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]); } - trace_rcu_exp_grace_period(rsp->name, s, TPS("endwake")); - mutex_unlock(&rsp->exp_wake_mutex); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake")); + mutex_unlock(&rcu_state.exp_wake_mutex); } /* * 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) +static void rcu_exp_sel_wait_wake(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); + sync_rcu_exp_select_cpus(func); /* Wait and clean up, including waking everyone. */ - rcu_exp_wait_wake(rsp, s); + rcu_exp_wait_wake(s); } /* @@ -641,15 +595,14 @@ static void wait_rcu_exp_gp(struct work_struct *wp) struct rcu_exp_work *rewp; rewp = container_of(wp, struct rcu_exp_work, rew_work); - rcu_exp_sel_wait_wake(rewp->rew_rsp, rewp->rew_func, rewp->rew_s); + rcu_exp_sel_wait_wake(rewp->rew_func, rewp->rew_s); } /* - * Given an rcu_state pointer and a smp_call_function() handler, kick - * off the specified flavor of expedited grace period. + * Given a smp_call_function() handler, kick off the specified + * implementation of expedited grace period. */ -static void _synchronize_rcu_expedited(struct rcu_state *rsp, - smp_call_func_t func) +static void _synchronize_rcu_expedited(smp_call_func_t func) { struct rcu_data *rdp; struct rcu_exp_work rew; @@ -658,71 +611,37 @@ static void _synchronize_rcu_expedited(struct rcu_state *rsp, /* If expedited grace periods are prohibited, fall back to normal. */ if (rcu_gp_is_normal()) { - wait_rcu_gp(rsp->call); + wait_rcu_gp(call_rcu); return; } /* Take a snapshot of the sequence number. */ - s = rcu_exp_gp_seq_snap(rsp); - if (exp_funnel_lock(rsp, s)) + s = rcu_exp_gp_seq_snap(); + if (exp_funnel_lock(s)) return; /* Someone else did our work for us. */ /* 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); + rcu_exp_sel_wait_wake(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); queue_work(rcu_gp_wq, &rew.rew_work); } /* Wait for expedited grace period to complete. */ - rdp = per_cpu_ptr(rsp->rda, raw_smp_processor_id()); - rnp = rcu_get_root(rsp); + rdp = per_cpu_ptr(&rcu_data, raw_smp_processor_id()); + rnp = rcu_get_root(); wait_event(rnp->exp_wq[rcu_seq_ctr(s) & 0x3], - sync_exp_work_done(rsp, s)); + sync_exp_work_done(s)); smp_mb(); /* Workqueue actions happen before return. */ /* Let the next expedited grace period start. */ - mutex_unlock(&rsp->exp_mutex); -} - -/** - * synchronize_sched_expedited - Brute-force RCU-sched grace period - * - * Wait for an RCU-sched grace period to elapse, but use a "big hammer" - * approach to force the grace period to end quickly. This consumes - * significant time on all CPUs and is unfriendly to real-time workloads, - * so is thus not recommended for any sort of common-case code. In fact, - * if you are using synchronize_sched_expedited() in a loop, please - * restructure your code to batch your updates, and then use a single - * synchronize_sched() instead. - * - * This implementation can be thought of as an application of sequence - * locking to expedited grace periods, but using the sequence counter to - * determine when someone else has already done the work instead of for - * retrying readers. - */ -void synchronize_sched_expedited(void) -{ - struct rcu_state *rsp = &rcu_sched_state; - - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || - lock_is_held(&rcu_lock_map) || - lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_sched_expedited() in RCU read-side critical section"); - - /* If only one CPU, this is automatically a grace period. */ - if (rcu_blocking_is_gp()) - return; - - _synchronize_rcu_expedited(rsp, sync_sched_exp_handler); + mutex_unlock(&rcu_state.exp_mutex); } -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #ifdef CONFIG_PREEMPT_RCU @@ -733,34 +652,78 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited); * ->expmask fields in the rcu_node tree. Otherwise, immediately * report the quiescent state. */ -static void sync_rcu_exp_handler(void *info) +static void sync_rcu_exp_handler(void *unused) { - struct rcu_data *rdp; - struct rcu_state *rsp = info; + unsigned long flags; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); + struct rcu_node *rnp = rdp->mynode; struct task_struct *t = current; /* - * Within an RCU read-side critical section, request that the next - * rcu_read_unlock() report. Unless this RCU read-side critical - * section has already blocked, in which case it is already set - * up for the expedited grace period to wait on it. + * First, the common case of not being in an RCU read-side + * critical section. If also enabled or idle, immediately + * report the quiescent state, otherwise defer. */ - if (t->rcu_read_lock_nesting > 0 && - !t->rcu_read_unlock_special.b.blocked) { - t->rcu_read_unlock_special.b.exp_need_qs = true; + if (!t->rcu_read_lock_nesting) { + if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || + rcu_dynticks_curr_cpu_in_eqs()) { + rcu_report_exp_rdp(rdp); + } else { + rdp->deferred_qs = true; + set_tsk_need_resched(t); + set_preempt_need_resched(); + } return; } /* - * We are either exiting an RCU read-side critical section (negative - * values of t->rcu_read_lock_nesting) or are not in one at all - * (zero value of t->rcu_read_lock_nesting). Or we are in an RCU - * read-side critical section that blocked before this expedited - * grace period started. Either way, we can immediately report - * the quiescent state. + * Second, the less-common case of being in an RCU read-side + * critical section. In this case we can count on a future + * rcu_read_unlock(). However, this rcu_read_unlock() might + * execute on some other CPU, but in that case there will be + * a future context switch. Either way, if the expedited + * grace period is still waiting on this CPU, set ->deferred_qs + * so that the eventual quiescent state will be reported. + * Note that there is a large group of race conditions that + * can have caused this quiescent state to already have been + * reported, so we really do need to check ->expmask. + */ + if (t->rcu_read_lock_nesting > 0) { + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (rnp->expmask & rdp->grpmask) + rdp->deferred_qs = true; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + + /* + * The final and least likely case is where the interrupted + * code was just about to or just finished exiting the RCU-preempt + * read-side critical section, and no, we can't tell which. + * So either way, set ->deferred_qs to flag later code that + * a quiescent state is required. + * + * If the CPU is fully enabled (or if some buggy RCU-preempt + * read-side critical section is being used from idle), just + * invoke rcu_preempt_defer_qs() to immediately report the + * quiescent state. We cannot use rcu_read_unlock_special() + * because we are in an interrupt handler, which will cause that + * function to take an early exit without doing anything. + * + * Otherwise, force a context switch after the CPU enables everything. */ - rdp = this_cpu_ptr(rsp->rda); - rcu_report_exp_rdp(rsp, rdp, true); + rdp->deferred_qs = true; + if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || + WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs())) { + rcu_preempt_deferred_qs(t); + } else { + set_tsk_need_resched(t); + set_preempt_need_resched(); + } +} + +/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */ +static void sync_sched_exp_online_cleanup(int cpu) +{ } /** @@ -780,11 +743,11 @@ static void sync_rcu_exp_handler(void *info) * you are using synchronize_rcu_expedited() in a loop, please restructure * your code to batch your updates, and then Use a single synchronize_rcu() * instead. + * + * This has the same semantics as (but is more brutal than) synchronize_rcu(). */ void synchronize_rcu_expedited(void) { - struct rcu_state *rsp = rcu_state_p; - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || lock_is_held(&rcu_lock_map) || lock_is_held(&rcu_sched_lock_map), @@ -792,19 +755,82 @@ void synchronize_rcu_expedited(void) if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) return; - _synchronize_rcu_expedited(rsp, sync_rcu_exp_handler); + _synchronize_rcu_expedited(sync_rcu_exp_handler); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); #else /* #ifdef CONFIG_PREEMPT_RCU */ +/* Invoked on each online non-idle CPU for expedited quiescent state. */ +static void sync_sched_exp_handler(void *unused) +{ + struct rcu_data *rdp; + struct rcu_node *rnp; + + rdp = this_cpu_ptr(&rcu_data); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask) || + __this_cpu_read(rcu_data.cpu_no_qs.b.exp)) + return; + if (rcu_is_cpu_rrupt_from_idle()) { + rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); + return; + } + __this_cpu_write(rcu_data.cpu_no_qs.b.exp, true); + /* Store .exp before .rcu_urgent_qs. */ + smp_store_release(this_cpu_ptr(&rcu_data.rcu_urgent_qs), true); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + +/* Send IPI for expedited cleanup if needed at end of CPU-hotplug operation. */ +static void sync_sched_exp_online_cleanup(int cpu) +{ + struct rcu_data *rdp; + int ret; + struct rcu_node *rnp; + + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + if (!(READ_ONCE(rnp->expmask) & rdp->grpmask)) + return; + ret = smp_call_function_single(cpu, sync_sched_exp_handler, NULL, 0); + WARN_ON_ONCE(ret); +} + /* - * Wait for an rcu-preempt grace period, but make it happen quickly. - * But because preemptible RCU does not exist, map to rcu-sched. + * Because a context switch is a grace period for !PREEMPT, any + * blocking grace-period wait automatically implies a grace period if + * there is only one CPU online at any point time during execution of + * either synchronize_rcu() or synchronize_rcu_expedited(). It is OK to + * occasionally incorrectly indicate that there are multiple CPUs online + * when there was in fact only one the whole time, as this just adds some + * overhead: RCU still operates correctly. */ +static int rcu_blocking_is_gp(void) +{ + int ret; + + might_sleep(); /* Check for RCU read-side critical section. */ + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; +} + +/* PREEMPT=n implementation of synchronize_rcu_expedited(). */ void synchronize_rcu_expedited(void) { - synchronize_sched_expedited(); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_expedited() in RCU read-side critical section"); + + /* If only one CPU, this is automatically a grace period. */ + if (rcu_blocking_is_gp()) + return; + + _synchronize_rcu_expedited(sync_sched_exp_handler); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a97c20ea9bce..05915e536336 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -38,8 +38,7 @@ #include "../locking/rtmutex_common.h" /* - * Control variables for per-CPU and per-rcu_node kthreads. These - * handle all flavors of RCU. + * Control variables for per-CPU and per-rcu_node kthreads. */ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); @@ -106,6 +105,8 @@ static void __init rcu_bootup_announce_oddness(void) pr_info("\tBoot-time adjustment of first FQS scan delay to %ld jiffies.\n", jiffies_till_first_fqs); if (jiffies_till_next_fqs != ULONG_MAX) pr_info("\tBoot-time adjustment of subsequent FQS scan delay to %ld jiffies.\n", jiffies_till_next_fqs); + if (jiffies_till_sched_qs != ULONG_MAX) + pr_info("\tBoot-time adjustment of scheduler-enlistment delay to %ld jiffies.\n", jiffies_till_sched_qs); if (rcu_kick_kthreads) pr_info("\tKick kthreads if too-long grace period.\n"); if (IS_ENABLED(CONFIG_DEBUG_OBJECTS_RCU_HEAD)) @@ -123,12 +124,7 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_PREEMPT_RCU -RCU_STATE_INITIALIZER(rcu_preempt, 'p', call_rcu); -static struct rcu_state *const rcu_state_p = &rcu_preempt_state; -static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data; - -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, - bool wake); +static void rcu_report_exp_rnp(struct rcu_node *rnp, bool wake); static void rcu_read_unlock_special(struct task_struct *t); /* @@ -284,13 +280,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * no need to check for a subsequent expedited GP. (Though we are * still in a quiescent state in any case.) */ - if (blkd_state & RCU_EXP_BLKD && - t->rcu_read_unlock_special.b.exp_need_qs) { - t->rcu_read_unlock_special.b.exp_need_qs = false; - rcu_report_exp_rdp(rdp->rsp, rdp, true); - } else { - WARN_ON_ONCE(t->rcu_read_unlock_special.b.exp_need_qs); - } + if (blkd_state & RCU_EXP_BLKD && rdp->deferred_qs) + rcu_report_exp_rdp(rdp); + else + WARN_ON_ONCE(rdp->deferred_qs); } /* @@ -306,15 +299,15 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * * Callers to this function must disable preemption. */ -static void rcu_preempt_qs(void) +static void rcu_qs(void) { - RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n"); - if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_qs() invoked with preemption enabled!!!\n"); + if (__this_cpu_read(rcu_data.cpu_no_qs.s)) { trace_rcu_grace_period(TPS("rcu_preempt"), - __this_cpu_read(rcu_data_p->gp_seq), + __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); - __this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false); - barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ + __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); + barrier(); /* Coordinate with rcu_flavor_check_callbacks(). */ current->rcu_read_unlock_special.b.need_qs = false; } } @@ -332,19 +325,20 @@ static void rcu_preempt_qs(void) * * Caller must disable interrupts. */ -static void rcu_preempt_note_context_switch(bool preempt) +void rcu_note_context_switch(bool preempt) { struct task_struct *t = current; - struct rcu_data *rdp; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; + barrier(); /* Avoid RCU read-side critical sections leaking down. */ + trace_rcu_utilization(TPS("Start context switch")); lockdep_assert_irqs_disabled(); WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); if (t->rcu_read_lock_nesting > 0 && !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ - rdp = this_cpu_ptr(rcu_state_p->rda); rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); t->rcu_read_unlock_special.b.blocked = true; @@ -357,7 +351,7 @@ static void rcu_preempt_note_context_switch(bool preempt) */ WARN_ON_ONCE((rdp->grpmask & rcu_rnp_online_cpus(rnp)) == 0); WARN_ON_ONCE(!list_empty(&t->rcu_node_entry)); - trace_rcu_preempt_task(rdp->rsp->name, + trace_rcu_preempt_task(rcu_state.name, t->pid, (rnp->qsmask & rdp->grpmask) ? rnp->gp_seq @@ -371,6 +365,9 @@ static void rcu_preempt_note_context_switch(bool preempt) * behalf of preempted instance of __rcu_read_unlock(). */ rcu_read_unlock_special(t); + rcu_preempt_deferred_qs(t); + } else { + rcu_preempt_deferred_qs(t); } /* @@ -382,8 +379,13 @@ static void rcu_preempt_note_context_switch(bool preempt) * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ - rcu_preempt_qs(); + rcu_qs(); + if (rdp->deferred_qs) + rcu_report_exp_rdp(rdp); + trace_rcu_utilization(TPS("End context switch")); + barrier(); /* Avoid RCU read-side critical sections leaking up. */ } +EXPORT_SYMBOL_GPL(rcu_note_context_switch); /* * Check for preempted RCU readers blocking the current grace period @@ -464,74 +466,56 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) } /* - * Handle special cases during rcu_read_unlock(), such as needing to - * notify RCU core processing or task having blocked during the RCU - * read-side critical section. + * Report deferred quiescent states. The deferral time can + * be quite short, for example, in the case of the call from + * rcu_read_unlock_special(). */ -static void rcu_read_unlock_special(struct task_struct *t) +static void +rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) { bool empty_exp; bool empty_norm; bool empty_exp_now; - unsigned long flags; struct list_head *np; bool drop_boost_mutex = false; struct rcu_data *rdp; struct rcu_node *rnp; union rcu_special special; - /* NMI handlers cannot block and cannot safely manipulate state. */ - if (in_nmi()) - return; - - local_irq_save(flags); - /* * If RCU core is waiting for this CPU to exit its critical section, * report the fact that it has exited. Because irqs are disabled, * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; + rdp = this_cpu_ptr(&rcu_data); + if (!special.s && !rdp->deferred_qs) { + local_irq_restore(flags); + return; + } if (special.b.need_qs) { - rcu_preempt_qs(); + rcu_qs(); t->rcu_read_unlock_special.b.need_qs = false; - if (!t->rcu_read_unlock_special.s) { + if (!t->rcu_read_unlock_special.s && !rdp->deferred_qs) { local_irq_restore(flags); return; } } /* - * Respond to a request for an expedited grace period, but only if - * we were not preempted, meaning that we were running on the same - * CPU throughout. If we were preempted, the exp_need_qs flag - * would have been cleared at the time of the first preemption, - * and the quiescent state would be reported when we were dequeued. + * Respond to a request by an expedited grace period for a + * quiescent state from this CPU. Note that requests from + * tasks are handled when removing the task from the + * blocked-tasks list below. */ - if (special.b.exp_need_qs) { - WARN_ON_ONCE(special.b.blocked); - t->rcu_read_unlock_special.b.exp_need_qs = false; - rdp = this_cpu_ptr(rcu_state_p->rda); - rcu_report_exp_rdp(rcu_state_p, rdp, true); + if (rdp->deferred_qs) { + rcu_report_exp_rdp(rdp); if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } } - /* Hardware IRQ handlers cannot block, complain if they get here. */ - if (in_irq() || in_serving_softirq()) { - lockdep_rcu_suspicious(__FILE__, __LINE__, - "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); - pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", - t->rcu_read_unlock_special.s, - t->rcu_read_unlock_special.b.blocked, - t->rcu_read_unlock_special.b.exp_need_qs, - t->rcu_read_unlock_special.b.need_qs); - local_irq_restore(flags); - return; - } - /* Clean up if blocked during RCU read-side critical section. */ if (special.b.blocked) { t->rcu_read_unlock_special.b.blocked = false; @@ -582,7 +566,7 @@ static void rcu_read_unlock_special(struct task_struct *t) rnp->grplo, rnp->grphi, !!rnp->gp_tasks); - rcu_report_unblock_qs_rnp(rcu_state_p, rnp, flags); + rcu_report_unblock_qs_rnp(rnp, flags); } else { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } @@ -596,13 +580,79 @@ static void rcu_read_unlock_special(struct task_struct *t) * then we need to report up the rcu_node hierarchy. */ if (!empty_exp && empty_exp_now) - rcu_report_exp_rnp(rcu_state_p, rnp, true); + rcu_report_exp_rnp(rnp, true); } else { local_irq_restore(flags); } } /* + * Is a deferred quiescent-state pending, and are we also not in + * an RCU read-side critical section? It is the caller's responsibility + * to ensure it is otherwise safe to report any deferred quiescent + * states. The reason for this is that it is safe to report a + * quiescent state during context switch even though preemption + * is disabled. This function cannot be expected to understand these + * nuances, so the caller must handle them. + */ +static bool rcu_preempt_need_deferred_qs(struct task_struct *t) +{ + return (this_cpu_ptr(&rcu_data)->deferred_qs || + READ_ONCE(t->rcu_read_unlock_special.s)) && + t->rcu_read_lock_nesting <= 0; +} + +/* + * Report a deferred quiescent state if needed and safe to do so. + * As with rcu_preempt_need_deferred_qs(), "safe" involves only + * not being in an RCU read-side critical section. The caller must + * evaluate safety in terms of interrupt, softirq, and preemption + * disabling. + */ +static void rcu_preempt_deferred_qs(struct task_struct *t) +{ + unsigned long flags; + bool couldrecurse = t->rcu_read_lock_nesting >= 0; + + if (!rcu_preempt_need_deferred_qs(t)) + return; + if (couldrecurse) + t->rcu_read_lock_nesting -= INT_MIN; + local_irq_save(flags); + rcu_preempt_deferred_qs_irqrestore(t, flags); + if (couldrecurse) + t->rcu_read_lock_nesting += INT_MIN; +} + +/* + * Handle special cases during rcu_read_unlock(), such as needing to + * notify RCU core processing or task having blocked during the RCU + * read-side critical section. + */ +static void rcu_read_unlock_special(struct task_struct *t) +{ + unsigned long flags; + bool preempt_bh_were_disabled = + !!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)); + bool irqs_were_disabled; + + /* NMI handlers cannot block and cannot safely manipulate state. */ + if (in_nmi()) + return; + + local_irq_save(flags); + irqs_were_disabled = irqs_disabled_flags(flags); + if ((preempt_bh_were_disabled || irqs_were_disabled) && + t->rcu_read_unlock_special.b.blocked) { + /* Need to defer quiescent state until everything is enabled. */ + raise_softirq_irqoff(RCU_SOFTIRQ); + local_irq_restore(flags); + return; + } + rcu_preempt_deferred_qs_irqrestore(t, flags); +} + +/* * Dump detailed information for all tasks blocking the current RCU * grace period on the specified rcu_node structure. */ @@ -633,12 +683,12 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) * Dump detailed information for all tasks blocking the current RCU * grace period. */ -static void rcu_print_detail_task_stall(struct rcu_state *rsp) +static void rcu_print_detail_task_stall(void) { - struct rcu_node *rnp = rcu_get_root(rsp); + struct rcu_node *rnp = rcu_get_root(); rcu_print_detail_task_stall_rnp(rnp); - rcu_for_each_leaf_node(rsp, rnp) + rcu_for_each_leaf_node(rnp) rcu_print_detail_task_stall_rnp(rnp); } @@ -706,14 +756,13 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. */ -static void -rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { struct task_struct *t; RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n"); if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) - dump_blkd_tasks(rsp, rnp, 10); + dump_blkd_tasks(rnp, 10); if (rcu_preempt_has_tasks(rnp) && (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { rnp->gp_tasks = rnp->blkd_tasks.next; @@ -732,62 +781,38 @@ rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) * * Caller must disable hard irqs. */ -static void rcu_preempt_check_callbacks(void) +static void rcu_flavor_check_callbacks(int user) { - struct rcu_state *rsp = &rcu_preempt_state; struct task_struct *t = current; - if (t->rcu_read_lock_nesting == 0) { - rcu_preempt_qs(); + if (user || rcu_is_cpu_rrupt_from_idle()) { + rcu_note_voluntary_context_switch(current); + } + if (t->rcu_read_lock_nesting > 0 || + (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) { + /* No QS, force context switch if deferred. */ + if (rcu_preempt_need_deferred_qs(t)) { + set_tsk_need_resched(t); + set_preempt_need_resched(); + } + } else if (rcu_preempt_need_deferred_qs(t)) { + rcu_preempt_deferred_qs(t); /* Report deferred QS. */ + return; + } else if (!t->rcu_read_lock_nesting) { + rcu_qs(); /* Report immediate QS. */ return; } + + /* If GP is oldish, ask for help from rcu_read_unlock_special(). */ if (t->rcu_read_lock_nesting > 0 && - __this_cpu_read(rcu_data_p->core_needs_qs) && - __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) && + __this_cpu_read(rcu_data.core_needs_qs) && + __this_cpu_read(rcu_data.cpu_no_qs.b.norm) && !t->rcu_read_unlock_special.b.need_qs && - time_after(jiffies, rsp->gp_start + HZ)) + time_after(jiffies, rcu_state.gp_start + HZ)) t->rcu_read_unlock_special.b.need_qs = true; } /** - * 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. - * - * 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). - */ -void call_rcu(struct rcu_head *head, rcu_callback_t func) -{ - __call_rcu(head, func, rcu_state_p, -1, 0); -} -EXPORT_SYMBOL_GPL(call_rcu); - -/** * synchronize_rcu - wait until a grace period has elapsed. * * Control will return to the caller some time after a full grace @@ -797,14 +822,28 @@ EXPORT_SYMBOL_GPL(call_rcu); * concurrently with new RCU read-side critical sections that began while * synchronize_rcu() was waiting. RCU read-side critical sections are * delimited by rcu_read_lock() and rcu_read_unlock(), and may be nested. + * In addition, 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 this guarantee implies further memory-ordering guarantees. + * On systems with more than one CPU, when synchronize_rcu() returns, + * 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 synchronize_rcu(). In addition, each CPU having + * an RCU read-side critical section that extends beyond the return from + * synchronize_rcu() is guaranteed to have executed a full memory barrier + * after the beginning of synchronize_rcu() and 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. * - * See the description of synchronize_sched() for more detailed - * information on memory-ordering guarantees. However, please note - * that -only- the memory-ordering guarantees apply. For example, - * synchronize_rcu() is -not- guaranteed to wait on things like code - * protected by preempt_disable(), instead, synchronize_rcu() is -only- - * guaranteed to wait on RCU read-side critical sections, that is, sections - * of code protected by rcu_read_lock(). + * Furthermore, if CPU A invoked synchronize_rcu(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_rcu() -- even if CPU A and CPU B are the same CPU (but + * again only if the system has more than one CPU). */ void synchronize_rcu(void) { @@ -821,28 +860,6 @@ void synchronize_rcu(void) } EXPORT_SYMBOL_GPL(synchronize_rcu); -/** - * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. - * - * Note that this primitive does not necessarily wait for an RCU grace period - * to complete. For example, if there are no RCU callbacks queued anywhere - * in the system, then rcu_barrier() is within its rights to return - * immediately, without waiting for anything, much less an RCU grace period. - */ -void rcu_barrier(void) -{ - _rcu_barrier(rcu_state_p); -} -EXPORT_SYMBOL_GPL(rcu_barrier); - -/* - * Initialize preemptible RCU's state structures. - */ -static void __init __rcu_init_preempt(void) -{ - rcu_init_one(rcu_state_p); -} - /* * Check for a task exiting while in a preemptible-RCU read-side * critical section, clean up if so. No need to issue warnings, @@ -859,6 +876,7 @@ void exit_rcu(void) barrier(); t->rcu_read_unlock_special.b.blocked = true; __rcu_read_unlock(); + rcu_preempt_deferred_qs(current); } /* @@ -866,7 +884,7 @@ void exit_rcu(void) * specified number of elements. */ static void -dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +dump_blkd_tasks(struct rcu_node *rnp, int ncheck) { int cpu; int i; @@ -893,7 +911,7 @@ dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) } pr_cont("\n"); for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) { - rdp = per_cpu_ptr(rsp->rda, 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], @@ -904,8 +922,6 @@ dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) #else /* #ifdef CONFIG_PREEMPT_RCU */ -static struct rcu_state *const rcu_state_p = &rcu_sched_state; - /* * Tell them what RCU they are running. */ @@ -916,14 +932,85 @@ static void __init rcu_bootup_announce(void) } /* - * Because preemptible RCU does not exist, we never have to check for - * CPUs being in quiescent states. + * Note a quiescent state for PREEMPT=n. Because we do not need to know + * how many quiescent states passed, just if there was at least one since + * the start of the grace period, this just sets a flag. The caller must + * have disabled preemption. */ -static void rcu_preempt_note_context_switch(bool preempt) +static void rcu_qs(void) { + RCU_LOCKDEP_WARN(preemptible(), "rcu_qs() invoked with preemption enabled!!!"); + if (!__this_cpu_read(rcu_data.cpu_no_qs.s)) + return; + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_data.gp_seq), TPS("cpuqs")); + __this_cpu_write(rcu_data.cpu_no_qs.b.norm, false); + if (!__this_cpu_read(rcu_data.cpu_no_qs.b.exp)) + return; + __this_cpu_write(rcu_data.cpu_no_qs.b.exp, false); + rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); } /* + * Register an urgently needed quiescent state. If there is an + * emergency, invoke rcu_momentary_dyntick_idle() to do a heavy-weight + * dyntick-idle quiescent state visible to other CPUs, which will in + * some cases serve for expedited as well as normal grace periods. + * Either way, register a lightweight quiescent state. + * + * The barrier() calls are redundant in the common case when this is + * called externally, but just in case this is called from within this + * file. + * + */ +void rcu_all_qs(void) +{ + unsigned long flags; + + if (!raw_cpu_read(rcu_data.rcu_urgent_qs)) + return; + preempt_disable(); + /* Load rcu_urgent_qs before other flags. */ + if (!smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) { + preempt_enable(); + return; + } + this_cpu_write(rcu_data.rcu_urgent_qs, false); + barrier(); /* Avoid RCU read-side critical sections leaking down. */ + if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) { + local_irq_save(flags); + rcu_momentary_dyntick_idle(); + local_irq_restore(flags); + } + rcu_qs(); + barrier(); /* Avoid RCU read-side critical sections leaking up. */ + preempt_enable(); +} +EXPORT_SYMBOL_GPL(rcu_all_qs); + +/* + * Note a PREEMPT=n context switch. The caller must have disabled interrupts. + */ +void rcu_note_context_switch(bool preempt) +{ + barrier(); /* Avoid RCU read-side critical sections leaking down. */ + trace_rcu_utilization(TPS("Start context switch")); + rcu_qs(); + /* Load rcu_urgent_qs before other flags. */ + if (!smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) + goto out; + this_cpu_write(rcu_data.rcu_urgent_qs, false); + if (unlikely(raw_cpu_read(rcu_data.rcu_need_heavy_qs))) + rcu_momentary_dyntick_idle(); + if (!preempt) + rcu_tasks_qs(current); +out: + trace_rcu_utilization(TPS("End context switch")); + barrier(); /* Avoid RCU read-side critical sections leaking up. */ +} +EXPORT_SYMBOL_GPL(rcu_note_context_switch); + +/* * Because preemptible RCU does not exist, there are never any preempted * RCU readers. */ @@ -941,10 +1028,20 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp) } /* + * Because there is no preemptible RCU, there can be no deferred quiescent + * states. + */ +static bool rcu_preempt_need_deferred_qs(struct task_struct *t) +{ + return false; +} +static void rcu_preempt_deferred_qs(struct task_struct *t) { } + +/* * Because preemptible RCU does not exist, we never have to check for * tasks blocked within RCU read-side critical sections. */ -static void rcu_print_detail_task_stall(struct rcu_state *rsp) +static void rcu_print_detail_task_stall(void) { } @@ -972,36 +1069,54 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * so there is no need to check for blocked tasks. So check only for * bogus qsmask values. */ -static void -rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp) { WARN_ON_ONCE(rnp->qsmask); } /* - * Because preemptible RCU does not exist, it never has any callbacks - * to check. + * Check to see if this CPU is in a non-context-switch quiescent state + * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). + * Also schedule RCU core processing. + * + * This function must be called from hardirq context. It is normally + * invoked from the scheduling-clock interrupt. */ -static void rcu_preempt_check_callbacks(void) +static void rcu_flavor_check_callbacks(int user) { -} + if (user || rcu_is_cpu_rrupt_from_idle()) { -/* - * Because preemptible RCU does not exist, rcu_barrier() is just - * another name for rcu_barrier_sched(). - */ -void rcu_barrier(void) -{ - rcu_barrier_sched(); + /* + * Get here if this CPU took its interrupt from user + * mode or from the idle loop, and if this is not a + * nested interrupt. In this case, the CPU is in + * a quiescent state, so note it. + * + * No memory barrier is required here because rcu_qs() + * references only CPU-local variables that other CPUs + * neither access nor modify, at least not while the + * corresponding CPU is online. + */ + + rcu_qs(); + } } -EXPORT_SYMBOL_GPL(rcu_barrier); -/* - * Because preemptible RCU does not exist, it need not be initialized. - */ -static void __init __rcu_init_preempt(void) +/* PREEMPT=n implementation of synchronize_rcu(). */ +void synchronize_rcu(void) { + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); + if (rcu_blocking_is_gp()) + return; + if (rcu_gp_is_expedited()) + synchronize_rcu_expedited(); + else + wait_rcu_gp(call_rcu); } +EXPORT_SYMBOL_GPL(synchronize_rcu); /* * Because preemptible RCU does not exist, tasks cannot possibly exit @@ -1015,7 +1130,7 @@ void exit_rcu(void) * Dump the guaranteed-empty blocked-tasks state. Trust but verify. */ static void -dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck) +dump_blkd_tasks(struct rcu_node *rnp, int ncheck) { WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks)); } @@ -1212,21 +1327,20 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * already exist. We only create this kthread for preemptible RCU. * Returns zero if all is well, a negated errno otherwise. */ -static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) +static int rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { - int rnp_index = rnp - &rsp->node[0]; + int rnp_index = rnp - rcu_get_root(); unsigned long flags; struct sched_param sp; struct task_struct *t; - if (rcu_state_p != rsp) + if (!IS_ENABLED(CONFIG_PREEMPT_RCU)) return 0; if (!rcu_scheduler_fully_active || rcu_rnp_online_cpus(rnp) == 0) return 0; - rsp->boost = 1; + rcu_state.boost = 1; if (rnp->boost_kthread_task != NULL) return 0; t = kthread_create(rcu_boost_kthread, (void *)rnp, @@ -1244,9 +1358,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, static void rcu_kthread_do_work(void) { - rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); - rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); - rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); + rcu_do_batch(this_cpu_ptr(&rcu_data)); } static void rcu_cpu_kthread_setup(unsigned int cpu) @@ -1268,9 +1380,9 @@ static int rcu_cpu_kthread_should_run(unsigned int cpu) } /* - * Per-CPU kernel thread that invokes RCU callbacks. This replaces the - * RCU softirq used in flavors and configurations of RCU that do not - * support RCU priority boosting. + * Per-CPU kernel thread that invokes RCU callbacks. This replaces + * the RCU softirq used in configurations of RCU that do not support RCU + * priority boosting. */ static void rcu_cpu_kthread(unsigned int cpu) { @@ -1353,18 +1465,18 @@ static void __init rcu_spawn_boost_kthreads(void) for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); - rcu_for_each_leaf_node(rcu_state_p, rnp) - (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + rcu_for_each_leaf_node(rnp) + (void)rcu_spawn_one_boost_kthread(rnp); } static void rcu_prepare_kthreads(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rcu_state_p->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ if (rcu_scheduler_fully_active) - (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + (void)rcu_spawn_one_boost_kthread(rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1411,8 +1523,8 @@ static void rcu_prepare_kthreads(int cpu) * 1 if so. This function is part of the RCU implementation; it is -not- * an exported member of the RCU API. * - * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs - * any flavor of RCU. + * Because we not have RCU_FAST_NO_HZ, just check whether or not this + * CPU has RCU callbacks queued. */ int rcu_needs_cpu(u64 basemono, u64 *nextevt) { @@ -1478,41 +1590,36 @@ static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY; module_param(rcu_idle_lazy_gp_delay, int, 0644); /* - * Try to advance callbacks for all flavors of RCU on the current CPU, but - * only if it has been awhile since the last time we did so. Afterwards, - * if there are any callbacks ready for immediate invocation, return true. + * Try to advance callbacks on the current CPU, but only if it has been + * awhile since the last time we did so. Afterwards, if there are any + * callbacks ready for immediate invocation, return true. */ static bool __maybe_unused rcu_try_advance_all_cbs(void) { bool cbs_ready = false; - struct rcu_data *rdp; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; - struct rcu_state *rsp; /* Exit early if we advanced recently. */ - if (jiffies == rdtp->last_advance_all) + if (jiffies == rdp->last_advance_all) return false; - rdtp->last_advance_all = jiffies; + rdp->last_advance_all = jiffies; - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - rnp = rdp->mynode; + rnp = rdp->mynode; - /* - * Don't bother checking unless a grace period has - * completed since we last checked and there are - * callbacks not yet ready to invoke. - */ - if ((rcu_seq_completed_gp(rdp->gp_seq, - rcu_seq_current(&rnp->gp_seq)) || - unlikely(READ_ONCE(rdp->gpwrap))) && - rcu_segcblist_pend_cbs(&rdp->cblist)) - note_gp_changes(rsp, rdp); - - if (rcu_segcblist_ready_cbs(&rdp->cblist)) - cbs_ready = true; - } + /* + * Don't bother checking unless a grace period has + * completed since we last checked and there are + * callbacks not yet ready to invoke. + */ + if ((rcu_seq_completed_gp(rdp->gp_seq, + rcu_seq_current(&rnp->gp_seq)) || + unlikely(READ_ONCE(rdp->gpwrap))) && + rcu_segcblist_pend_cbs(&rdp->cblist)) + note_gp_changes(rdp); + + if (rcu_segcblist_ready_cbs(&rdp->cblist)) + cbs_ready = true; return cbs_ready; } @@ -1526,16 +1633,16 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) */ int rcu_needs_cpu(u64 basemono, u64 *nextevt) { - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); unsigned long dj; lockdep_assert_irqs_disabled(); /* Snapshot to detect later posting of non-lazy callback. */ - rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; + rdp->nonlazy_posted_snap = rdp->nonlazy_posted; /* If no callbacks, RCU doesn't need the CPU. */ - if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) { + if (!rcu_cpu_has_callbacks(&rdp->all_lazy)) { *nextevt = KTIME_MAX; return 0; } @@ -1546,10 +1653,10 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) invoke_rcu_core(); return 1; } - rdtp->last_accelerate = jiffies; + rdp->last_accelerate = jiffies; /* Request timer delay depending on laziness, and round. */ - if (!rdtp->all_lazy) { + if (!rdp->all_lazy) { dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; } else { @@ -1572,10 +1679,8 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) static void rcu_prepare_for_idle(void) { bool needwake; - struct rcu_data *rdp; - struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp; - struct rcu_state *rsp; int tne; lockdep_assert_irqs_disabled(); @@ -1584,10 +1689,10 @@ static void rcu_prepare_for_idle(void) /* Handle nohz enablement switches conservatively. */ tne = READ_ONCE(tick_nohz_active); - if (tne != rdtp->tick_nohz_enabled_snap) { + if (tne != rdp->tick_nohz_enabled_snap) { if (rcu_cpu_has_callbacks(NULL)) invoke_rcu_core(); /* force nohz to see update. */ - rdtp->tick_nohz_enabled_snap = tne; + rdp->tick_nohz_enabled_snap = tne; return; } if (!tne) @@ -1598,10 +1703,10 @@ static void rcu_prepare_for_idle(void) * callbacks, invoke RCU core for the side-effect of recalculating * idle duration on re-entry to idle. */ - if (rdtp->all_lazy && - rdtp->nonlazy_posted != rdtp->nonlazy_posted_snap) { - rdtp->all_lazy = false; - rdtp->nonlazy_posted_snap = rdtp->nonlazy_posted; + if (rdp->all_lazy && + rdp->nonlazy_posted != rdp->nonlazy_posted_snap) { + rdp->all_lazy = false; + rdp->nonlazy_posted_snap = rdp->nonlazy_posted; invoke_rcu_core(); return; } @@ -1610,19 +1715,16 @@ static void rcu_prepare_for_idle(void) * If we have not yet accelerated this jiffy, accelerate all * callbacks on this CPU. */ - if (rdtp->last_accelerate == jiffies) + if (rdp->last_accelerate == jiffies) return; - rdtp->last_accelerate = jiffies; - for_each_rcu_flavor(rsp) { - rdp = this_cpu_ptr(rsp->rda); - if (!rcu_segcblist_pend_cbs(&rdp->cblist)) - continue; + rdp->last_accelerate = jiffies; + if (rcu_segcblist_pend_cbs(&rdp->cblist)) { rnp = rdp->mynode; raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - needwake = rcu_accelerate_cbs(rsp, rnp, rdp); + needwake = rcu_accelerate_cbs(rnp, rdp); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ if (needwake) - rcu_gp_kthread_wake(rsp); + rcu_gp_kthread_wake(); } } @@ -1650,104 +1752,23 @@ static void rcu_cleanup_after_idle(void) */ static void rcu_idle_count_callbacks_posted(void) { - __this_cpu_add(rcu_dynticks.nonlazy_posted, 1); -} - -/* - * Data for flushing lazy RCU callbacks at OOM time. - */ -static atomic_t oom_callback_count; -static DECLARE_WAIT_QUEUE_HEAD(oom_callback_wq); - -/* - * RCU OOM callback -- decrement the outstanding count and deliver the - * wake-up if we are the last one. - */ -static void rcu_oom_callback(struct rcu_head *rhp) -{ - if (atomic_dec_and_test(&oom_callback_count)) - wake_up(&oom_callback_wq); -} - -/* - * Post an rcu_oom_notify callback on the current CPU if it has at - * least one lazy callback. This will unnecessarily post callbacks - * to CPUs that already have a non-lazy callback at the end of their - * callback list, but this is an infrequent operation, so accept some - * extra overhead to keep things simple. - */ -static void rcu_oom_notify_cpu(void *unused) -{ - struct rcu_state *rsp; - struct rcu_data *rdp; - - for_each_rcu_flavor(rsp) { - rdp = raw_cpu_ptr(rsp->rda); - if (rcu_segcblist_n_lazy_cbs(&rdp->cblist)) { - atomic_inc(&oom_callback_count); - rsp->call(&rdp->oom_head, rcu_oom_callback); - } - } -} - -/* - * If low on memory, ensure that each CPU has a non-lazy callback. - * This will wake up CPUs that have only lazy callbacks, in turn - * ensuring that they free up the corresponding memory in a timely manner. - * Because an uncertain amount of memory will be freed in some uncertain - * timeframe, we do not claim to have freed anything. - */ -static int rcu_oom_notify(struct notifier_block *self, - unsigned long notused, void *nfreed) -{ - int cpu; - - /* Wait for callbacks from earlier instance to complete. */ - wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0); - smp_mb(); /* Ensure callback reuse happens after callback invocation. */ - - /* - * Prevent premature wakeup: ensure that all increments happen - * before there is a chance of the counter reaching zero. - */ - atomic_set(&oom_callback_count, 1); - - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); - cond_resched_tasks_rcu_qs(); - } - - /* Unconditionally decrement: no need to wake ourselves up. */ - atomic_dec(&oom_callback_count); - - return NOTIFY_OK; + __this_cpu_add(rcu_data.nonlazy_posted, 1); } -static struct notifier_block rcu_oom_nb = { - .notifier_call = rcu_oom_notify -}; - -static int __init rcu_register_oom_notifier(void) -{ - register_oom_notifier(&rcu_oom_nb); - return 0; -} -early_initcall(rcu_register_oom_notifier); - #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ #ifdef CONFIG_RCU_FAST_NO_HZ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { - struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); - unsigned long nlpd = rdtp->nonlazy_posted - rdtp->nonlazy_posted_snap; + struct rcu_data *rdp = &per_cpu(rcu_data, cpu); + unsigned long nlpd = rdp->nonlazy_posted - rdp->nonlazy_posted_snap; sprintf(cp, "last_accelerate: %04lx/%04lx, nonlazy_posted: %ld, %c%c", - rdtp->last_accelerate & 0xffff, jiffies & 0xffff, + rdp->last_accelerate & 0xffff, jiffies & 0xffff, ulong2long(nlpd), - rdtp->all_lazy ? 'L' : '.', - rdtp->tick_nohz_enabled_snap ? '.' : 'D'); + rdp->all_lazy ? 'L' : '.', + rdp->tick_nohz_enabled_snap ? '.' : 'D'); } #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ @@ -1768,21 +1789,19 @@ static void print_cpu_stall_info_begin(void) /* * Print out diagnostic information for the specified stalled CPU. * - * If the specified CPU is aware of the current RCU grace period - * (flavor specified by rsp), then print the number of scheduling - * clock interrupts the CPU has taken during the time that it has - * been aware. Otherwise, print the number of RCU grace periods - * that this CPU is ignorant of, for example, "1" if the CPU was - * aware of the previous grace period. + * If the specified CPU is aware of the current RCU grace period, then + * print the number of scheduling clock interrupts the CPU has taken + * during the time that it has been aware. Otherwise, print the number + * of RCU grace periods that this CPU is ignorant of, for example, "1" + * if the CPU was aware of the previous grace period. * * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info. */ -static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) +static void print_cpu_stall_info(int cpu) { unsigned long delta; char fast_no_hz[72]; - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); - struct rcu_dynticks *rdtp = rdp->dynticks; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); char *ticks_title; unsigned long ticks_value; @@ -1792,7 +1811,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) */ touch_nmi_watchdog(); - ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq); + ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq); if (ticks_value) { ticks_title = "GPs behind"; } else { @@ -1810,10 +1829,10 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu) rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' : "!."[!delta], ticks_value, ticks_title, - rcu_dynticks_snap(rdtp) & 0xfff, - rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting, + rcu_dynticks_snap(rdp) & 0xfff, + rdp->dynticks_nesting, rdp->dynticks_nmi_nesting, rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu), - READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart, + READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, fast_no_hz); } @@ -1823,20 +1842,12 @@ static void print_cpu_stall_info_end(void) pr_err("\t"); } -/* Zero ->ticks_this_gp for all flavors of RCU. */ +/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */ static void zero_cpu_stall_ticks(struct rcu_data *rdp) { rdp->ticks_this_gp = 0; rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id()); -} - -/* Increment ->ticks_this_gp for all flavors of RCU. */ -static void increment_cpu_stall_ticks(void) -{ - struct rcu_state *rsp; - - for_each_rcu_flavor(rsp) - raw_cpu_inc(rsp->rda->ticks_this_gp); + WRITE_ONCE(rdp->last_fqs_resched, jiffies); } #ifdef CONFIG_RCU_NOCB_CPU @@ -1958,17 +1969,17 @@ static void wake_nocb_leader_defer(struct rcu_data *rdp, int waketype, if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) mod_timer(&rdp->nocb_timer, jiffies + 1); WRITE_ONCE(rdp->nocb_defer_wakeup, waketype); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, reason); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, reason); raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); } /* - * Does the specified CPU need an RCU callback for the specified flavor + * Does the specified CPU need an RCU callback for this invocation * of rcu_barrier()? */ -static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +static bool rcu_nocb_cpu_needs_barrier(int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); unsigned long ret; #ifdef CONFIG_PROVE_RCU struct rcu_head *rhp; @@ -1979,7 +1990,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) * There needs to be a barrier before this function is called, * but associated with a prior determination that no more * callbacks would be posted. In the worst case, the first - * barrier in _rcu_barrier() suffices (but the caller cannot + * barrier in rcu_barrier() suffices (but the caller cannot * necessarily rely on this, not a substitute for the caller * getting the concurrency design right!). There must also be * a barrier between the following load an posting of a callback @@ -2037,7 +2048,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, /* If we are not being polled and there is a kthread, awaken it ... */ t = READ_ONCE(rdp->nocb_kthread); if (rcu_nocb_poll || !t) { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNotPoll")); return; } @@ -2046,7 +2057,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, if (!irqs_disabled_flags(flags)) { /* ... if queue was empty ... */ wake_nocb_leader(rdp, false); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeEmpty")); } else { wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE, @@ -2057,7 +2068,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, /* ... or if many callbacks queued. */ if (!irqs_disabled_flags(flags)) { wake_nocb_leader(rdp, true); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeOvf")); } else { wake_nocb_leader_defer(rdp, RCU_NOCB_WAKE_FORCE, @@ -2065,7 +2076,7 @@ static void __call_rcu_nocb_enqueue(struct rcu_data *rdp, } rdp->qlen_last_fqs_check = LONG_MAX / 2; } else { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WakeNot")); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); } return; } @@ -2087,12 +2098,12 @@ static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, return false; __call_rcu_nocb_enqueue(rdp, rhp, &rhp->next, 1, lazy, flags); if (__is_kfree_rcu_offset((unsigned long)rhp->func)) - trace_rcu_kfree_callback(rdp->rsp->name, rhp, + trace_rcu_kfree_callback(rcu_state.name, rhp, (unsigned long)rhp->func, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); else - trace_rcu_callback(rdp->rsp->name, rhp, + trace_rcu_callback(rcu_state.name, rhp, -atomic_long_read(&rdp->nocb_q_count_lazy), -atomic_long_read(&rdp->nocb_q_count)); @@ -2142,7 +2153,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) struct rcu_node *rnp = rdp->mynode; local_irq_save(flags); - c = rcu_seq_snap(&rdp->rsp->gp_seq); + c = rcu_seq_snap(&rcu_state.gp_seq); if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { local_irq_restore(flags); } else { @@ -2150,7 +2161,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) needwake = rcu_start_this_gp(rnp, rdp, c); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (needwake) - rcu_gp_kthread_wake(rdp->rsp); + rcu_gp_kthread_wake(); } /* @@ -2187,7 +2198,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { - trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep")); + trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, TPS("Sleep")); swait_event_interruptible_exclusive(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags); @@ -2197,7 +2208,7 @@ wait_again: raw_spin_unlock_irqrestore(&my_rdp->nocb_lock, flags); } else if (firsttime) { firsttime = false; /* Don't drown trace log with "Poll"! */ - trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Poll")); + trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, TPS("Poll")); } /* @@ -2224,7 +2235,7 @@ wait_again: if (rcu_nocb_poll) { schedule_timeout_interruptible(1); } else { - trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, my_rdp->cpu, TPS("WokeEmpty")); } goto wait_again; @@ -2269,7 +2280,7 @@ wait_again: static void nocb_follower_wait(struct rcu_data *rdp) { for (;;) { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep")); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FollowerSleep")); swait_event_interruptible_exclusive(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); if (smp_load_acquire(&rdp->nocb_follower_head)) { @@ -2277,7 +2288,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) return; } WARN_ON(signal_pending(current)); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WokeEmpty")); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); } } @@ -2312,10 +2323,10 @@ static int rcu_nocb_kthread(void *arg) rdp->nocb_follower_tail = &rdp->nocb_follower_head; raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); BUG_ON(!list); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("WokeNonEmpty")); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeNonEmpty")); /* Each pass through the following loop invokes a callback. */ - trace_rcu_batch_start(rdp->rsp->name, + trace_rcu_batch_start(rcu_state.name, atomic_long_read(&rdp->nocb_q_count_lazy), atomic_long_read(&rdp->nocb_q_count), -1); c = cl = 0; @@ -2323,23 +2334,23 @@ static int rcu_nocb_kthread(void *arg) next = list->next; /* Wait for enqueuing to complete, if needed. */ while (next == NULL && &list->next != tail) { - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WaitQueue")); schedule_timeout_interruptible(1); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeQueue")); next = list->next; } debug_rcu_head_unqueue(list); local_bh_disable(); - if (__rcu_reclaim(rdp->rsp->name, list)) + if (__rcu_reclaim(rcu_state.name, list)) cl++; c++; local_bh_enable(); cond_resched_tasks_rcu_qs(); list = next; } - trace_rcu_batch_end(rdp->rsp->name, c, !!list, 0, 0, 1); + trace_rcu_batch_end(rcu_state.name, c, !!list, 0, 0, 1); smp_mb__before_atomic(); /* _add after CB invocation. */ atomic_long_add(-c, &rdp->nocb_q_count); atomic_long_add(-cl, &rdp->nocb_q_count_lazy); @@ -2367,7 +2378,7 @@ static void do_nocb_deferred_wakeup_common(struct rcu_data *rdp) ndw = READ_ONCE(rdp->nocb_defer_wakeup); WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); __wake_nocb_leader(rdp, ndw == RCU_NOCB_WAKE_FORCE, flags); - trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("DeferredWake")); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DeferredWake")); } /* Do a deferred wakeup of rcu_nocb_kthread() from a timer handler. */ @@ -2393,7 +2404,6 @@ void __init rcu_init_nohz(void) { int cpu; bool need_rcu_nocb_mask = false; - struct rcu_state *rsp; #if defined(CONFIG_NO_HZ_FULL) if (tick_nohz_full_running && cpumask_weight(tick_nohz_full_mask)) @@ -2427,11 +2437,9 @@ void __init rcu_init_nohz(void) if (rcu_nocb_poll) pr_info("\tPoll for callbacks from no-CBs CPUs.\n"); - for_each_rcu_flavor(rsp) { - for_each_cpu(cpu, rcu_nocb_mask) - init_nocb_callback_list(per_cpu_ptr(rsp->rda, cpu)); - rcu_organize_nocb_kthreads(rsp); - } + for_each_cpu(cpu, rcu_nocb_mask) + init_nocb_callback_list(per_cpu_ptr(&rcu_data, cpu)); + rcu_organize_nocb_kthreads(); } /* Initialize per-rcu_data variables for no-CBs CPUs. */ @@ -2446,16 +2454,15 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) /* * If the specified CPU is a no-CBs CPU that does not already have its - * rcuo kthread for the specified RCU flavor, spawn it. If the CPUs are - * brought online out of order, this can require re-organizing the - * leader-follower relationships. + * rcuo kthread, spawn it. If the CPUs are brought online out of order, + * this can require re-organizing the leader-follower relationships. */ -static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) +static void rcu_spawn_one_nocb_kthread(int cpu) { struct rcu_data *rdp; struct rcu_data *rdp_last; struct rcu_data *rdp_old_leader; - struct rcu_data *rdp_spawn = per_cpu_ptr(rsp->rda, cpu); + struct rcu_data *rdp_spawn = per_cpu_ptr(&rcu_data, cpu); struct task_struct *t; /* @@ -2485,9 +2492,9 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) rdp_spawn->nocb_next_follower = rdp_old_leader; } - /* Spawn the kthread for this CPU and RCU flavor. */ + /* Spawn the kthread for this CPU. */ t = kthread_run(rcu_nocb_kthread, rdp_spawn, - "rcuo%c/%d", rsp->abbr, cpu); + "rcuo%c/%d", rcu_state.abbr, cpu); BUG_ON(IS_ERR(t)); WRITE_ONCE(rdp_spawn->nocb_kthread, t); } @@ -2498,11 +2505,8 @@ static void rcu_spawn_one_nocb_kthread(struct rcu_state *rsp, int cpu) */ static void rcu_spawn_all_nocb_kthreads(int cpu) { - struct rcu_state *rsp; - if (rcu_scheduler_fully_active) - for_each_rcu_flavor(rsp) - rcu_spawn_one_nocb_kthread(rsp, cpu); + rcu_spawn_one_nocb_kthread(cpu); } /* @@ -2526,7 +2530,7 @@ module_param(rcu_nocb_leader_stride, int, 0444); /* * Initialize leader-follower relationships for all no-CBs CPU. */ -static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) +static void __init rcu_organize_nocb_kthreads(void) { int cpu; int ls = rcu_nocb_leader_stride; @@ -2548,7 +2552,7 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp) * we will spawn the needed set of rcu_nocb_kthread() kthreads. */ for_each_cpu(cpu, rcu_nocb_mask) { - rdp = per_cpu_ptr(rsp->rda, cpu); + rdp = per_cpu_ptr(&rcu_data, cpu); if (rdp->cpu >= nl) { /* New leader, set up for followers & next leader. */ nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; @@ -2585,7 +2589,7 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) #else /* #ifdef CONFIG_RCU_NOCB_CPU */ -static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) +static bool rcu_nocb_cpu_needs_barrier(int cpu) { WARN_ON_ONCE(1); /* Should be dead code. */ return false; @@ -2654,12 +2658,12 @@ static bool init_nocb_callback_list(struct rcu_data *rdp) * This code relies on the fact that all NO_HZ_FULL CPUs are also * CONFIG_RCU_NOCB_CPU CPUs. */ -static bool rcu_nohz_full_cpu(struct rcu_state *rsp) +static bool rcu_nohz_full_cpu(void) { #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_cpu(smp_processor_id()) && - (!rcu_gp_in_progress(rsp) || - ULONG_CMP_LT(jiffies, READ_ONCE(rsp->gp_start) + HZ))) + (!rcu_gp_in_progress() || + ULONG_CMP_LT(jiffies, READ_ONCE(rcu_state.gp_start) + HZ))) return true; #endif /* #ifdef CONFIG_NO_HZ_FULL */ return false; diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 39cb23d22109..f203b94f6b5b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -203,11 +203,7 @@ 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(); } #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) @@ -298,7 +294,7 @@ EXPORT_SYMBOL_GPL(rcu_read_lock_held); * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. * - * Note that rcu_read_lock() is disallowed if the CPU is either idle or + * Note that rcu_read_lock_bh() is disallowed if the CPU is either idle or * offline from an RCU perspective, so check for those as well. */ int rcu_read_lock_bh_held(void) @@ -336,7 +332,7 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, int i; int j; - /* Initialize and register callbacks for each flavor specified. */ + /* Initialize and register callbacks for each crcu_array element. */ for (i = 0; i < n; i++) { if (checktiny && (crcu_array[i] == call_rcu || @@ -472,6 +468,7 @@ int rcu_jiffies_till_stall_check(void) } return till_stall_check * HZ + RCU_STALL_DELAY_DELTA; } +EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check); void rcu_sysrq_start(void) { @@ -701,19 +698,19 @@ static int __noreturn rcu_tasks_kthread(void *arg) /* * Wait for all pre-existing t->on_rq and t->nvcsw - * transitions to complete. Invoking synchronize_sched() + * transitions to complete. Invoking synchronize_rcu() * suffices because all these transitions occur with - * interrupts disabled. Without this synchronize_sched(), + * interrupts disabled. Without this synchronize_rcu(), * a read-side critical section that started before the * grace period might be incorrectly seen as having started * after the grace period. * - * This synchronize_sched() also dispenses with the + * This synchronize_rcu() also dispenses with the * need for a memory barrier on the first store to * ->rcu_tasks_holdout, as it forces the store to happen * after the beginning of the grace period. */ - synchronize_sched(); + synchronize_rcu(); /* * There were callbacks, so we need to wait for an @@ -740,7 +737,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) * This does only part of the job, ensuring that all * tasks that were previously exiting reach the point * where they have disabled preemption, allowing the - * later synchronize_sched() to finish the job. + * later synchronize_rcu() to finish the job. */ synchronize_srcu(&tasks_rcu_exit_srcu); @@ -790,20 +787,20 @@ static int __noreturn rcu_tasks_kthread(void *arg) * cause their RCU-tasks read-side critical sections to * extend past the end of the grace period. However, * because these ->nvcsw updates are carried out with - * interrupts disabled, we can use synchronize_sched() + * interrupts disabled, we can use synchronize_rcu() * to force the needed ordering on all such CPUs. * - * This synchronize_sched() also confines all + * This synchronize_rcu() also confines all * ->rcu_tasks_holdout accesses to be within the grace * period, avoiding the need for memory barriers for * ->rcu_tasks_holdout accesses. * - * In addition, this synchronize_sched() waits for exiting + * In addition, this synchronize_rcu() waits for exiting * tasks to complete their final preempt_disable() region * of execution, cleaning up after the synchronize_srcu() * above. */ - synchronize_sched(); + synchronize_rcu(); /* Invoke the callbacks. */ while (list) { @@ -870,15 +867,10 @@ static void __init rcu_tasks_bootup_oddness(void) #ifdef CONFIG_PROVE_RCU /* - * Early boot self test parameters, one for each flavor + * Early boot self test parameters. */ static bool rcu_self_test; -static bool rcu_self_test_bh; -static bool rcu_self_test_sched; - module_param(rcu_self_test, bool, 0444); -module_param(rcu_self_test_bh, bool, 0444); -module_param(rcu_self_test_sched, bool, 0444); static int rcu_self_test_counter; @@ -888,25 +880,16 @@ static void test_callback(struct rcu_head *r) pr_info("RCU test callback executed %d\n", rcu_self_test_counter); } +DEFINE_STATIC_SRCU(early_srcu); + static void early_boot_test_call_rcu(void) { static struct rcu_head head; + static struct rcu_head shead; call_rcu(&head, test_callback); -} - -static void early_boot_test_call_rcu_bh(void) -{ - static struct rcu_head head; - - call_rcu_bh(&head, test_callback); -} - -static void early_boot_test_call_rcu_sched(void) -{ - static struct rcu_head head; - - call_rcu_sched(&head, test_callback); + if (IS_ENABLED(CONFIG_SRCU)) + call_srcu(&early_srcu, &shead, test_callback); } void rcu_early_boot_tests(void) @@ -915,10 +898,6 @@ void rcu_early_boot_tests(void) if (rcu_self_test) early_boot_test_call_rcu(); - if (rcu_self_test_bh) - early_boot_test_call_rcu_bh(); - if (rcu_self_test_sched) - early_boot_test_call_rcu_sched(); rcu_test_sync_prims(); } @@ -930,16 +909,11 @@ static int rcu_verify_early_boot_tests(void) if (rcu_self_test) { early_boot_test_counter++; rcu_barrier(); + if (IS_ENABLED(CONFIG_SRCU)) { + early_boot_test_counter++; + srcu_barrier(&early_srcu); + } } - if (rcu_self_test_bh) { - early_boot_test_counter++; - rcu_barrier_bh(); - } - if (rcu_self_test_sched) { - early_boot_test_counter++; - rcu_barrier_sched(); - } - if (rcu_self_test_counter != early_boot_test_counter) { WARN_ON(1); ret = -1; diff --git a/kernel/reboot.c b/kernel/reboot.c index 8fb44dec9ad7..e1b79b6a2735 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -49,6 +49,7 @@ int reboot_force; */ void (*pm_power_off_prepare)(void); +EXPORT_SYMBOL_GPL(pm_power_off_prepare); /** * emergency_restart - reboot the system diff --git a/kernel/resource.c b/kernel/resource.c index 30e1bc68503b..b3a3a1fc499e 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -318,33 +318,34 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); -/* - * Finds the lowest iomem resource existing within [res->start.res->end). - * The caller must specify res->start, res->end, res->flags, and optionally - * desc. If found, returns 0, res is overwritten, if not found, returns -1. - * This function walks the whole tree and not just first level children until - * and unless first_level_children_only is true. +/** + * Finds the lowest iomem resource that covers part of [start..end]. The + * caller must specify start, end, flags, and desc (which may be + * IORES_DESC_NONE). + * + * If a resource is found, returns 0 and *res is overwritten with the part + * of the resource that's within [start..end]; if none is found, returns + * -1. + * + * This function walks the whole tree and not just first level children + * unless @first_lvl is true. */ -static int find_next_iomem_res(struct resource *res, unsigned long desc, - bool first_level_children_only) +static int find_next_iomem_res(resource_size_t start, resource_size_t end, + unsigned long flags, unsigned long desc, + bool first_lvl, struct resource *res) { - resource_size_t start, end; struct resource *p; - bool sibling_only = false; - BUG_ON(!res); - - start = res->start; - end = res->end; - BUG_ON(start >= end); + if (!res) + return -EINVAL; - if (first_level_children_only) - sibling_only = true; + if (start >= end) + return -EINVAL; read_lock(&resource_lock); - for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { - if ((p->flags & res->flags) != res->flags) + for (p = iomem_resource.child; p; p = next_resource(p, first_lvl)) { + if ((p->flags & flags) != flags) continue; if ((desc != IORES_DESC_NONE) && (desc != p->desc)) continue; @@ -352,45 +353,43 @@ static int find_next_iomem_res(struct resource *res, unsigned long desc, p = NULL; break; } - if ((p->end >= start) && (p->start < end)) + if ((p->end >= start) && (p->start <= end)) break; } read_unlock(&resource_lock); if (!p) return -1; + /* copy data */ - if (res->start < p->start) - res->start = p->start; - if (res->end > p->end) - res->end = p->end; + res->start = max(start, p->start); + res->end = min(end, p->end); res->flags = p->flags; res->desc = p->desc; return 0; } -static int __walk_iomem_res_desc(struct resource *res, unsigned long desc, - bool first_level_children_only, - void *arg, +static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, + unsigned long flags, unsigned long desc, + bool first_lvl, void *arg, int (*func)(struct resource *, void *)) { - u64 orig_end = res->end; + struct resource res; int ret = -1; - while ((res->start < res->end) && - !find_next_iomem_res(res, desc, first_level_children_only)) { - ret = (*func)(res, arg); + while (start < end && + !find_next_iomem_res(start, end, flags, desc, first_lvl, &res)) { + ret = (*func)(&res, arg); if (ret) break; - res->start = res->end + 1; - res->end = orig_end; + start = res.end + 1; } return ret; } -/* +/** * Walks through iomem resources and calls func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and @@ -407,13 +406,7 @@ static int __walk_iomem_res_desc(struct resource *res, unsigned long desc, int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { - struct resource res; - - res.start = start; - res.end = end; - res.flags = flags; - - return __walk_iomem_res_desc(&res, desc, false, arg, func); + return __walk_iomem_res_desc(start, end, flags, desc, false, arg, func); } EXPORT_SYMBOL_GPL(walk_iomem_res_desc); @@ -425,15 +418,11 @@ EXPORT_SYMBOL_GPL(walk_iomem_res_desc); * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, - int (*func)(struct resource *, void *)) + int (*func)(struct resource *, void *)) { - struct resource res; + unsigned long flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - res.start = start; - res.end = end; - res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - - return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true, + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true, arg, func); } @@ -444,13 +433,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, int walk_mem_res(u64 start, u64 end, void *arg, int (*func)(struct resource *, void *)) { - struct resource res; - - res.start = start; - res.end = end; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; - return __walk_iomem_res_desc(&res, IORES_DESC_NONE, true, + return __walk_iomem_res_desc(start, end, flags, IORES_DESC_NONE, true, arg, func); } @@ -462,27 +447,27 @@ int walk_mem_res(u64 start, u64 end, void *arg, * It is to be used only for System RAM. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, - void *arg, int (*func)(unsigned long, unsigned long, void *)) + void *arg, int (*func)(unsigned long, unsigned long, void *)) { + resource_size_t start, end; + unsigned long flags; struct resource res; unsigned long pfn, end_pfn; - u64 orig_end; int ret = -1; - res.start = (u64) start_pfn << PAGE_SHIFT; - res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; - res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - orig_end = res.end; - while ((res.start < res.end) && - (find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) { + start = (u64) start_pfn << PAGE_SHIFT; + end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; + flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + while (start < end && + !find_next_iomem_res(start, end, flags, IORES_DESC_NONE, + true, &res)) { pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) ret = (*func)(pfn, end_pfn - pfn, arg); if (ret) break; - res.start = res.end + 1; - res.end = orig_end; + start = res.end + 1; } return ret; } @@ -658,8 +643,8 @@ static int find_resource(struct resource *root, struct resource *new, * @constraint: the size and alignment constraints to be met. */ static int reallocate_resource(struct resource *root, struct resource *old, - resource_size_t newsize, - struct resource_constraint *constraint) + resource_size_t newsize, + struct resource_constraint *constraint) { int err=0; struct resource new = *old; @@ -972,7 +957,7 @@ skip: * Existing children of the resource are assumed to be immutable. */ int adjust_resource(struct resource *res, resource_size_t start, - resource_size_t size) + resource_size_t size) { int result; @@ -983,9 +968,9 @@ int adjust_resource(struct resource *res, resource_size_t start, } EXPORT_SYMBOL(adjust_resource); -static void __init __reserve_region_with_split(struct resource *root, - resource_size_t start, resource_size_t end, - const char *name) +static void __init +__reserve_region_with_split(struct resource *root, resource_size_t start, + resource_size_t end, const char *name) { struct resource *parent = root; struct resource *conflict; @@ -1044,9 +1029,9 @@ static void __init __reserve_region_with_split(struct resource *root, } -void __init reserve_region_with_split(struct resource *root, - resource_size_t start, resource_size_t end, - const char *name) +void __init +reserve_region_with_split(struct resource *root, resource_size_t start, + resource_size_t end, const char *name) { int abort = 0; @@ -1172,7 +1157,7 @@ EXPORT_SYMBOL(__request_region); * The described resource region must match a currently busy region. */ void __release_region(struct resource *parent, resource_size_t start, - resource_size_t n) + resource_size_t n) { struct resource **p; resource_size_t end; @@ -1234,7 +1219,7 @@ EXPORT_SYMBOL(__release_region); * simplicity. Enhance this logic when necessary. */ int release_mem_region_adjustable(struct resource *parent, - resource_size_t start, resource_size_t size) + resource_size_t start, resource_size_t size) { struct resource **p; struct resource *res; @@ -1410,9 +1395,9 @@ static int devm_region_match(struct device *dev, void *res, void *match_data) this->start == match->start && this->n == match->n; } -struct resource * __devm_request_region(struct device *dev, - struct resource *parent, resource_size_t start, - resource_size_t n, const char *name) +struct resource * +__devm_request_region(struct device *dev, struct resource *parent, + resource_size_t start, resource_size_t n, const char *name) { struct region_devres *dr = NULL; struct resource *res; diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c38..21fb5a5662b5 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 625bc9897f62..f12225f26b70 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -135,9 +135,8 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) * In theory, the compile should just see 0 here, and optimize out the call * to sched_rt_avg_update. But I don't trust it... */ -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - s64 steal = 0, irq_delta = 0; -#endif + s64 __maybe_unused steal = 0, irq_delta = 0; + #ifdef CONFIG_IRQ_TIME_ACCOUNTING irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; @@ -177,7 +176,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; -#ifdef HAVE_SCHED_AVG_IRQ +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) update_irq_load_avg(rq, irq_delta + steal); #endif @@ -701,6 +700,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) if (idle_policy(p->policy)) { load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; + p->se.runnable_weight = load->weight; return; } @@ -713,6 +713,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) } else { load->weight = scale_load(sched_prio_to_weight[prio]); load->inv_weight = sched_prio_to_wmult[prio]; + p->se.runnable_weight = load->weight; } } @@ -721,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -732,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -1167,7 +1172,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (task_cpu(p) != new_cpu) { if (p->sched_class->migrate_task_rq) - p->sched_class->migrate_task_rq(p); + p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; rseq_migrate(p); perf_event_task_migrate(p); @@ -2036,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -2875,6 +2881,18 @@ unsigned long long nr_context_switches(void) } /* + * Consumers of these two interfaces, like for example the cpuidle menu + * governor, are using nonsensical data. Preferring shallow idle state selection + * for a CPU that has IO-wait which might not even end up running the task when + * it does become runnable. + */ + +unsigned long nr_iowait_cpu(int cpu) +{ + return atomic_read(&cpu_rq(cpu)->nr_iowait); +} + +/* * IO-wait accounting, and how its mostly bollocks (on SMP). * * The idea behind IO-wait account is to account the idle time that we could @@ -2909,31 +2927,11 @@ unsigned long nr_iowait(void) unsigned long i, sum = 0; for_each_possible_cpu(i) - sum += atomic_read(&cpu_rq(i)->nr_iowait); + sum += nr_iowait_cpu(i); return sum; } -/* - * Consumers of these two interfaces, like for example the cpufreq menu - * governor are using nonsensical data. Boosting frequency for a CPU that has - * IO-wait which might not even end up running the task when it does become - * runnable. - */ - -unsigned long nr_iowait_cpu(int cpu) -{ - struct rq *this = cpu_rq(cpu); - return atomic_read(&this->nr_iowait); -} - -void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) -{ - struct rq *rq = this_rq(); - *nr_waiters = atomic_read(&rq->nr_iowait); - *load = rq->load.weight; -} - #ifdef CONFIG_SMP /* @@ -3050,6 +3048,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -4932,9 +4931,7 @@ static void do_sched_yield(void) struct rq_flags rf; struct rq *rq; - local_irq_disable(); - rq = this_rq(); - rq_lock(rq, &rf); + rq = this_rq_lock_irq(&rf); schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); @@ -5243,7 +5240,7 @@ out_unlock: * an error code. */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct timespec __user *, interval) + struct __kernel_timespec __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); @@ -5254,16 +5251,16 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, return retval; } -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, compat_pid_t, pid, - struct compat_timespec __user *, interval) + struct old_timespec32 __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); if (retval == 0) - retval = compat_put_timespec64(&t, interval); + retval = put_old_timespec32(&t, interval); return retval; } #endif @@ -6068,6 +6065,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 997ea7b839fa..91e4202b0634 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1607,7 +1607,7 @@ out: return cpu; } -static void migrate_task_rq_dl(struct task_struct *p) +static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused) { struct rq *rq; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f808ddf2a868..ee271bb661cc 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -693,6 +693,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); static unsigned long task_h_load(struct task_struct *p); +static unsigned long capacity_of(int cpu); /* Give new sched_entity start runnable values to heavy its load in infant time */ void init_entity_runnable_average(struct sched_entity *se) @@ -1392,6 +1393,17 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int last_cpupid, this_cpupid; this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + + /* + * Allow first faults or private faults to migrate immediately early in + * the lifetime of a task. The magic number 4 is based on waiting for + * two full passes of the "multi-stage node selection" test that is + * executed below. + */ + if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) + return true; /* * Multi-stage node selection is used in conjunction with a periodic @@ -1410,7 +1422,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * This quadric squishes small probabilities, making it less likely we * act on an unlikely task<->page relation. */ - last_cpupid = page_cpupid_xchg_last(page, this_cpupid); if (!cpupid_pid_unset(last_cpupid) && cpupid_to_nid(last_cpupid) != dst_nid) return false; @@ -1446,7 +1457,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, static unsigned long weighted_cpuload(struct rq *rq); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long capacity_of(int cpu); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -1454,8 +1464,6 @@ struct numa_stats { /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; - - unsigned int nr_running; }; /* @@ -1463,36 +1471,16 @@ struct numa_stats { */ static void update_numa_stats(struct numa_stats *ns, int nid) { - int smt, cpu, cpus = 0; - unsigned long capacity; + int cpu; memset(ns, 0, sizeof(*ns)); for_each_cpu(cpu, cpumask_of_node(nid)) { struct rq *rq = cpu_rq(cpu); - ns->nr_running += rq->nr_running; ns->load += weighted_cpuload(rq); ns->compute_capacity += capacity_of(cpu); - - cpus++; } - /* - * If we raced with hotplug and there are no CPUs left in our mask - * the @ns structure is NULL'ed and task_numa_compare() will - * not find this node attractive. - * - * We'll detect a huge imbalance and bail there. - */ - if (!cpus) - return; - - /* smt := ceil(cpus / capacity), assumes: 1 < smt_power < 2 */ - smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity); - capacity = cpus / smt; /* cores */ - - capacity = min_t(unsigned, capacity, - DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE)); } struct task_numa_env { @@ -1514,6 +1502,21 @@ struct task_numa_env { static void task_numa_assign(struct task_numa_env *env, struct task_struct *p, long imp) { + struct rq *rq = cpu_rq(env->dst_cpu); + + /* Bail out if run-queue part of active NUMA balance. */ + if (xchg(&rq->numa_migrate_on, 1)) + return; + + /* + * Clear previous best_cpu/rq numa-migrate flag, since task now + * found a better CPU to move/swap. + */ + if (env->best_cpu != -1) { + rq = cpu_rq(env->best_cpu); + WRITE_ONCE(rq->numa_migrate_on, 0); + } + if (env->best_task) put_task_struct(env->best_task); if (p) @@ -1553,6 +1556,13 @@ static bool load_too_imbalanced(long src_load, long dst_load, } /* + * Maximum NUMA importance can be 1998 (2*999); + * SMALLIMP @ 30 would be close to 1998/64. + * Used to deter task migration. + */ +#define SMALLIMP 30 + +/* * This checks if the overall compute and NUMA accesses of the system would * be improved if the source tasks was migrated to the target dst_cpu taking * into account that it might be best if task running on the dst_cpu should @@ -1569,6 +1579,9 @@ static void task_numa_compare(struct task_numa_env *env, long moveimp = imp; int dist = env->dist; + if (READ_ONCE(dst_rq->numa_migrate_on)) + return; + rcu_read_lock(); cur = task_rcu_dereference(&dst_rq->curr); if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur))) @@ -1582,7 +1595,7 @@ static void task_numa_compare(struct task_numa_env *env, goto unlock; if (!cur) { - if (maymove || imp > env->best_imp) + if (maymove && moveimp >= env->best_imp) goto assign; else goto unlock; @@ -1625,16 +1638,22 @@ static void task_numa_compare(struct task_numa_env *env, task_weight(cur, env->dst_nid, dist); } - if (imp <= env->best_imp) - goto unlock; - if (maymove && moveimp > imp && moveimp > env->best_imp) { - imp = moveimp - 1; + imp = moveimp; cur = NULL; goto assign; } /* + * If the NUMA importance is less than SMALLIMP, + * task migration might only result in ping pong + * of tasks and also hurt performance due to cache + * misses. + */ + if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2) + goto unlock; + + /* * In the overloaded case, try and keep the load balanced. */ load = task_h_load(env->p) - task_h_load(cur); @@ -1710,6 +1729,7 @@ static int task_numa_migrate(struct task_struct *p) .best_cpu = -1, }; struct sched_domain *sd; + struct rq *best_rq; unsigned long taskweight, groupweight; int nid, ret, dist; long taskimp, groupimp; @@ -1805,20 +1825,17 @@ static int task_numa_migrate(struct task_struct *p) if (env.best_cpu == -1) return -EAGAIN; - /* - * Reset the scan period if the task is being rescheduled on an - * alternative node to recheck if the tasks is now properly placed. - */ - p->numa_scan_period = task_scan_start(p); - + best_rq = cpu_rq(env.best_cpu); if (env.best_task == NULL) { ret = migrate_task_to(p, env.best_cpu); + WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); return ret; } ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); @@ -2596,6 +2613,39 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) } } +static void update_scan_period(struct task_struct *p, int new_cpu) +{ + int src_nid = cpu_to_node(task_cpu(p)); + int dst_nid = cpu_to_node(new_cpu); + + if (!static_branch_likely(&sched_numa_balancing)) + return; + + if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING)) + return; + + if (src_nid == dst_nid) + return; + + /* + * Allow resets if faults have been trapped before one scan + * has completed. This is most likely due to a new task that + * is pulled cross-node due to wakeups or load balancing. + */ + if (p->numa_scan_seq) { + /* + * Avoid scan adjustments if moving to the preferred + * node or if the task was not previously running on + * the preferred node. + */ + if (dst_nid == p->numa_preferred_nid || + (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + return; + } + + p->numa_scan_period = task_scan_start(p); +} + #else static void task_tick_numa(struct rq *rq, struct task_struct *curr) { @@ -2609,6 +2659,10 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) { } +static inline void update_scan_period(struct task_struct *p, int new_cpu) +{ +} + #endif /* CONFIG_NUMA_BALANCING */ static void @@ -3647,6 +3701,29 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) WRITE_ONCE(p->se.avg.util_est, ue); } +static inline int task_fits_capacity(struct task_struct *p, long capacity) +{ + return capacity * 1024 > task_util_est(p) * capacity_margin; +} + +static inline void update_misfit_status(struct task_struct *p, struct rq *rq) +{ + if (!static_branch_unlikely(&sched_asym_cpucapacity)) + return; + + if (!p) { + rq->misfit_task_load = 0; + return; + } + + if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) { + rq->misfit_task_load = 0; + return; + } + + rq->misfit_task_load = task_h_load(p); +} + #else /* CONFIG_SMP */ #define UPDATE_TG 0x0 @@ -3676,6 +3753,7 @@ util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {} static inline void util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) {} +static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {} #endif /* CONFIG_SMP */ @@ -3925,7 +4003,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * put back on, and if we advance min_vruntime, we'll be placed back * further than we started -- ie. we'll be penalized. */ - if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) update_min_vruntime(cfs_rq); } @@ -4400,9 +4478,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) /* * Add to the _head_ of the list, so that an already-started - * distribute_cfs_runtime will not see us + * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is + * not running add to the tail so that later runqueues don't get starved. */ - list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + if (cfs_b->distribute_running) + list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + else + list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); /* * If we're the first throttled task, make sure the bandwidth @@ -4546,14 +4628,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) * in us over-using our runtime if it is all used during this loop, but * only by limited amounts in that extreme case. */ - while (throttled && cfs_b->runtime > 0) { + while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { runtime = cfs_b->runtime; + cfs_b->distribute_running = 1; raw_spin_unlock(&cfs_b->lock); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime, runtime_expires); raw_spin_lock(&cfs_b->lock); + cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); cfs_b->runtime -= min(runtime, cfs_b->runtime); @@ -4664,6 +4748,11 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* confirm we're still not at a refresh boundary */ raw_spin_lock(&cfs_b->lock); + if (cfs_b->distribute_running) { + raw_spin_unlock(&cfs_b->lock); + return; + } + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { raw_spin_unlock(&cfs_b->lock); return; @@ -4673,6 +4762,9 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) runtime = cfs_b->runtime; expires = cfs_b->runtime_expires; + if (runtime) + cfs_b->distribute_running = 1; + raw_spin_unlock(&cfs_b->lock); if (!runtime) @@ -4683,6 +4775,7 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) raw_spin_lock(&cfs_b->lock); if (expires == cfs_b->runtime_expires) cfs_b->runtime -= min(runtime, cfs_b->runtime); + cfs_b->distribute_running = 0; raw_spin_unlock(&cfs_b->lock); } @@ -4791,6 +4884,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period_timer.function = sched_cfs_period_timer; hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; + cfs_b->distribute_running = 0; } static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) @@ -6188,6 +6282,9 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) { long min_cap, max_cap; + if (!static_branch_unlikely(&sched_asym_cpucapacity)) + return 0; + min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu)); max_cap = cpu_rq(cpu)->rd->max_cpu_capacity; @@ -6198,7 +6295,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) /* Bring task utilization in sync with prev_cpu */ sync_entity_load_avg(&p->se); - return min_cap * 1024 < task_util(p) * capacity_margin; + return !task_fits_capacity(p, min_cap); } /* @@ -6275,7 +6372,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se); * cfs_rq_of(p) references at time of call are still valid and identify the * previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held. */ -static void migrate_task_rq_fair(struct task_struct *p) +static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) { /* * As blocked tasks retain absolute vruntime the migration needs to @@ -6328,6 +6425,8 @@ static void migrate_task_rq_fair(struct task_struct *p) /* We have migrated, no longer consider this task hot */ p->se.exec_start = 0; + + update_scan_period(p, new_cpu); } static void task_dead_fair(struct task_struct *p) @@ -6615,9 +6714,12 @@ done: __maybe_unused; if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); + update_misfit_status(p, rq); + return p; idle: + update_misfit_status(NULL, rq); new_tasks = idle_balance(rq, rf); /* @@ -6823,6 +6925,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10; enum fbq_type { regular, remote, all }; +enum group_type { + group_other = 0, + group_misfit_task, + group_imbalanced, + group_overloaded, +}; + #define LBF_ALL_PINNED 0x01 #define LBF_NEED_BREAK 0x02 #define LBF_DST_PINNED 0x04 @@ -6853,6 +6962,7 @@ struct lb_env { unsigned int loop_max; enum fbq_type fbq_type; + enum group_type src_grp_type; struct list_head tasks; }; @@ -7233,7 +7343,7 @@ static inline bool others_have_blocked(struct rq *rq) if (READ_ONCE(rq->avg_dl.util_avg)) return true; -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ if (READ_ONCE(rq->avg_irq.util_avg)) return true; #endif @@ -7396,12 +7506,6 @@ static unsigned long task_h_load(struct task_struct *p) /********** Helpers for find_busiest_group ************************/ -enum group_type { - group_other = 0, - group_imbalanced, - group_overloaded, -}; - /* * sg_lb_stats - stats of a sched_group required for load_balancing */ @@ -7417,6 +7521,7 @@ struct sg_lb_stats { unsigned int group_weight; enum group_type group_type; int group_no_capacity; + unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -7525,13 +7630,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) cpu_rq(cpu)->cpu_capacity = capacity; sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; + sdg->sgc->max_capacity = capacity; } void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long capacity, min_capacity; + unsigned long capacity, min_capacity, max_capacity; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); @@ -7545,6 +7651,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) capacity = 0; min_capacity = ULONG_MAX; + max_capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -7575,6 +7682,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) } min_capacity = min(capacity, min_capacity); + max_capacity = max(capacity, max_capacity); } } else { /* @@ -7588,12 +7696,14 @@ void update_group_capacity(struct sched_domain *sd, int cpu) capacity += sgc->capacity; min_capacity = min(sgc->min_capacity, min_capacity); + max_capacity = max(sgc->max_capacity, max_capacity); group = group->next; } while (group != child->groups); } sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = min_capacity; + sdg->sgc->max_capacity = max_capacity; } /* @@ -7689,16 +7799,27 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) } /* - * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller + * group_smaller_min_cpu_capacity: Returns true if sched_group sg has smaller * per-CPU capacity than sched_group ref. */ static inline bool -group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { return sg->sgc->min_capacity * capacity_margin < ref->sgc->min_capacity * 1024; } +/* + * group_smaller_max_cpu_capacity: Returns true if sched_group sg has smaller + * per-CPU capacity_orig than sched_group ref. + */ +static inline bool +group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +{ + return sg->sgc->max_capacity * capacity_margin < + ref->sgc->max_capacity * 1024; +} + static inline enum group_type group_classify(struct sched_group *group, struct sg_lb_stats *sgs) @@ -7709,6 +7830,9 @@ group_type group_classify(struct sched_group *group, if (sg_imbalanced(group)) return group_imbalanced; + if (sgs->group_misfit_task_load) + return group_misfit_task; + return group_other; } @@ -7741,7 +7865,7 @@ static bool update_nohz_stats(struct rq *rq, bool force) * @load_idx: Load index of sched_domain of this_cpu for load calc. * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. - * @overload: Indicate more than one runnable task for any CPU. + * @overload: Indicate pullable load (e.g. >1 runnable task). */ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, @@ -7783,6 +7907,12 @@ static inline void update_sg_lb_stats(struct lb_env *env, */ if (!nr_running && idle_cpu(i)) sgs->idle_cpus++; + + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + sgs->group_misfit_task_load < rq->misfit_task_load) { + sgs->group_misfit_task_load = rq->misfit_task_load; + *overload = 1; + } } /* Adjust by relative CPU capacity of the group */ @@ -7818,6 +7948,17 @@ static bool update_sd_pick_busiest(struct lb_env *env, { struct sg_lb_stats *busiest = &sds->busiest_stat; + /* + * Don't try to pull misfit tasks we can't help. + * We can use max_capacity here as reduction in capacity on some + * CPUs in the group should either be possible to resolve + * internally or be covered by avg_load imbalance (eventually). + */ + if (sgs->group_type == group_misfit_task && + (!group_smaller_max_cpu_capacity(sg, sds->local) || + !group_has_capacity(env, &sds->local_stat))) + return false; + if (sgs->group_type > busiest->group_type) return true; @@ -7837,7 +7978,14 @@ static bool update_sd_pick_busiest(struct lb_env *env, * power/energy consequences are not considered. */ if (sgs->sum_nr_running <= sgs->group_weight && - group_smaller_cpu_capacity(sds->local, sg)) + group_smaller_min_cpu_capacity(sds->local, sg)) + return false; + + /* + * If we have more than one misfit sg go with the biggest misfit. + */ + if (sgs->group_type == group_misfit_task && + sgs->group_misfit_task_load < busiest->group_misfit_task_load) return false; asym_packing: @@ -7908,11 +8056,9 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; - int load_idx, prefer_sibling = 0; + int load_idx; bool overload = false; - - if (child && child->flags & SD_PREFER_SIBLING) - prefer_sibling = 1; + bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING; #ifdef CONFIG_NO_HZ_COMMON if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked)) @@ -7986,8 +8132,8 @@ next_group: if (!env->sd->parent) { /* update overload indicator if we are at root domain */ - if (env->dst_rq->rd->overload != overload) - env->dst_rq->rd->overload = overload; + if (READ_ONCE(env->dst_rq->rd->overload) != overload) + WRITE_ONCE(env->dst_rq->rd->overload, overload); } } @@ -8137,8 +8283,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * factors in sg capacity and sgs with smaller group_type are * skipped when updating the busiest sg: */ - if (busiest->avg_load <= sds->avg_load || - local->avg_load >= sds->avg_load) { + if (busiest->group_type != group_misfit_task && + (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load)) { env->imbalance = 0; return fix_small_imbalance(env, sds); } @@ -8172,6 +8319,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s (sds->avg_load - local->avg_load) * local->group_capacity ) / SCHED_CAPACITY_SCALE; + /* Boost imbalance to allow misfit task to be balanced. */ + if (busiest->group_type == group_misfit_task) { + env->imbalance = max_t(long, env->imbalance, + busiest->group_misfit_task_load); + } + /* * if *imbalance is less than the average load per runnable task * there is no guarantee that any tasks will be moved so we'll have @@ -8238,6 +8391,10 @@ static struct sched_group *find_busiest_group(struct lb_env *env) busiest->group_no_capacity) goto force_balance; + /* Misfit tasks should be dealt with regardless of the avg load */ + if (busiest->group_type == group_misfit_task) + goto force_balance; + /* * If the local group is busier than the selected busiest group * don't try and pull any tasks. @@ -8275,6 +8432,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) force_balance: /* Looks like there is an imbalance. Compute it */ + env->src_grp_type = busiest->group_type; calculate_imbalance(env, &sds); return env->imbalance ? sds.busiest : NULL; @@ -8322,8 +8480,32 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (rt > env->fbq_type) continue; + /* + * For ASYM_CPUCAPACITY domains with misfit tasks we simply + * seek the "biggest" misfit task. + */ + if (env->src_grp_type == group_misfit_task) { + if (rq->misfit_task_load > busiest_load) { + busiest_load = rq->misfit_task_load; + busiest = rq; + } + + continue; + } + capacity = capacity_of(i); + /* + * For ASYM_CPUCAPACITY domains, don't pick a CPU that could + * eventually lead to active_balancing high->low capacity. + * Higher per-CPU capacity is considered better than balancing + * average load. + */ + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + capacity_of(env->dst_cpu) < capacity && + rq->nr_running == 1) + continue; + wl = weighted_cpuload(rq); /* @@ -8391,6 +8573,9 @@ static int need_active_balance(struct lb_env *env) return 1; } + if (env->src_grp_type == group_misfit_task) + return 1; + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } @@ -9033,7 +9218,7 @@ static void nohz_balancer_kick(struct rq *rq) if (time_before(now, nohz.next_balance)) goto out; - if (rq->nr_running >= 2) { + if (rq->nr_running >= 2 || rq->misfit_task_load) { flags = NOHZ_KICK_MASK; goto out; } @@ -9402,7 +9587,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) rq_unpin_lock(this_rq, rf); if (this_rq->avg_idle < sysctl_sched_migration_cost || - !this_rq->rd->overload) { + !READ_ONCE(this_rq->rd->overload)) { rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); @@ -9564,6 +9749,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + + update_misfit_status(curr, rq); } /* diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 85ae8488039c..858589b83377 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -39,7 +39,7 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) -SCHED_FEAT(LB_BIAS, true) +SCHED_FEAT(LB_BIAS, false) /* * Decrement CPU capacity based on time not spent running tasks diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 16f84142f2f4..f5516bae0c1b 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -347,21 +347,6 @@ EXPORT_SYMBOL_GPL(play_idle); void cpu_startup_entry(enum cpuhp_state state) { - /* - * This #ifdef needs to die, but it's too late in the cycle to - * make this generic (ARM and SH have never invoked the canary - * init for the non boot CPUs!). Will be fixed in 3.11 - */ -#ifdef CONFIG_X86 - /* - * If we're the non-boot CPU, nothing set the stack canary up - * for us. The boot CPU already has it initialized but no harm - * in doing it again. This is a good place for updating it, as - * we wont ever return from this function (so the invalid - * canaries already on the stack wont ever trigger). - */ - boot_init_stack_canary(); -#endif arch_cpu_idle_prepare(); cpuhp_online_idle(state); while (1) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index a171c1258109..28a516575c18 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -91,19 +91,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } -/* - * a1 = a0 * e + a * (1 - e) +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. */ static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) { - unsigned long newload; + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; + return result; +} - return newload / FIXED_1; +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); } #ifdef CONFIG_NO_HZ_COMMON @@ -225,75 +279,6 @@ static long calc_load_nohz_fold(void) return delta; } -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-CPU ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 35475c0c5419..90fb5bc12ad4 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -269,9 +269,6 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) { - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); return 1; @@ -282,9 +279,6 @@ int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (entity_is_task(se)) - se->runnable_weight = se->load.weight; - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, cfs_rq->curr == se)) { @@ -358,7 +352,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) return 0; } -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ /* * irq: * diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index d2894db28955..7e56b489ff32 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -6,7 +6,7 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ int update_irq_load_avg(struct rq *rq, u64 running); #else static inline int diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..7cdecfc010af --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,759 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner <hannes@cmpxchg.org> + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include <linux/sched/loadavg.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/seqlock.h> +#include <linux/cgroup.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/psi.h> +#include "sched.h" + +static int psi_bug __read_mostly; + +bool psi_disabled __read_mostly; +core_param(psi_disabled, psi_disabled, bool, 0644); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (psi_disabled) + return; + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires > psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); + + if (!delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); +} + +static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + struct psi_group *group; + void *iter = NULL; + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + while ((group = iterate_groups(task, &iter))) + psi_group_change(group, cpu, clear, set); +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group *group; + void *iter = NULL; + + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (psi_disabled) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (psi_disabled) + return; + + cancel_delayed_work_sync(&cgroup->psi.clock_work); + free_percpu(cgroup->psi.pcpu); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +void cgroup_move_task(struct task_struct *task, struct css_set *to) +{ + bool move_psi = !psi_disabled; + unsigned int task_flags = 0; + struct rq_flags rf; + struct rq *rq; + + if (move_psi) { + rq = task_rq_lock(task, &rf); + + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + } + + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + + if (move_psi) { + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); + } +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) +{ + int full; + + if (psi_disabled) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + 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_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4a2e8cae63c4..618577fc9aa8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -54,9 +54,9 @@ #include <linux/proc_fs.h> #include <linux/prefetch.h> #include <linux/profile.h> +#include <linux/psi.h> #include <linux/rcupdate_wait.h> #include <linux/security.h> -#include <linux/stackprotector.h> #include <linux/stop_machine.h> #include <linux/suspend.h> #include <linux/swait.h> @@ -320,6 +320,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include <linux/cgroup.h> +#include <linux/psi.h> struct cfs_rq; struct rt_rq; @@ -346,6 +347,8 @@ struct cfs_bandwidth { int nr_periods; int nr_throttled; u64 throttled_time; + + bool distribute_running; #endif }; @@ -715,8 +718,12 @@ struct root_domain { cpumask_var_t span; cpumask_var_t online; - /* Indicate more than one runnable task for any CPU */ - bool overload; + /* + * Indicate pullable load on at least one CPU, e.g: + * - More than one runnable task + * - Running task is misfit + */ + int overload; /* * The bit corresponding to a CPU gets set here if such CPU has more @@ -783,6 +790,7 @@ struct rq { #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; + unsigned int numa_migrate_on; #endif #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; @@ -842,6 +850,8 @@ struct rq { unsigned char idle_balance; + unsigned long misfit_task_load; + /* For active balancing */ int active_balance; int push_cpu; @@ -855,8 +865,7 @@ struct rq { struct sched_avg avg_rt; struct sched_avg avg_dl; -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) -#define HAVE_SCHED_AVG_IRQ +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ struct sched_avg avg_irq; #endif u64 idle_stamp; @@ -950,6 +959,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +extern void update_rq_clock(struct rq *rq); + static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); @@ -1068,6 +1079,98 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) #endif } +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irqsave(&rq->lock, rf->flags); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock_irq(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irq(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_relock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_repin_lock(rq, rf); +} + +static inline void +rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irqrestore(&rq->lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irq(&rq->lock); +} + +static inline void +rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + rq_lock(rq, rf); + return rq; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, @@ -1185,6 +1288,7 @@ DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain *, sd_numa); DECLARE_PER_CPU(struct sched_domain *, sd_asym); +extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { atomic_t ref; @@ -1194,6 +1298,7 @@ struct sched_group_capacity { */ unsigned long capacity; unsigned long min_capacity; /* Min per-CPU capacity in group */ + unsigned long max_capacity; /* Max per-CPU capacity in group */ unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ @@ -1393,7 +1498,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features = 0; #undef SCHED_FEAT -#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) +#define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ @@ -1523,7 +1628,7 @@ struct sched_class { #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); - void (*migrate_task_rq)(struct task_struct *p); + void (*migrate_task_rq)(struct task_struct *p, int new_cpu); void (*task_woken)(struct rq *this_rq, struct task_struct *task); @@ -1693,8 +1798,8 @@ static inline void add_nr_running(struct rq *rq, unsigned count) if (prev_nr < 2 && rq->nr_running >= 2) { #ifdef CONFIG_SMP - if (!rq->rd->overload) - rq->rd->overload = true; + if (!READ_ONCE(rq->rd->overload)) + WRITE_ONCE(rq->rd->overload, 1); #endif } @@ -1708,8 +1813,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count) sched_update_tick_dependency(rq); } -extern void update_rq_clock(struct rq *rq); - extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); @@ -1774,86 +1877,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) #endif #endif -struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(rq->lock); - -struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(p->pi_lock) - __acquires(rq->lock); - -static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) - __releases(rq->lock) - __releases(p->pi_lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); -} - -static inline void -rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irqsave(&rq->lock, rf->flags); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock_irq(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irq(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_relock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_repin_lock(rq, rf); -} - -static inline void -rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irqrestore(&rq->lock, rf->flags); -} - -static inline void -rq_unlock_irq(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irq(&rq->lock); -} - -static inline void -rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - #ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT @@ -2214,7 +2237,7 @@ static inline unsigned long cpu_util_rt(struct rq *rq) } #endif -#ifdef HAVE_SCHED_AVG_IRQ +#ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) { return rq->avg_irq.util_avg; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8aea199a39b4..4904c4677000 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt # define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (psi_disabled) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (psi_disabled) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (psi_disabled) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (psi_disabled) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 505a41c42b96..9d74371e4aad 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -7,8 +7,8 @@ DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ -cpumask_var_t sched_domains_tmpmask; -cpumask_var_t sched_domains_tmpmask2; +static cpumask_var_t sched_domains_tmpmask; +static cpumask_var_t sched_domains_tmpmask2; #ifdef CONFIG_SCHED_DEBUG @@ -398,6 +398,7 @@ DEFINE_PER_CPU(int, sd_llc_id); DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DEFINE_PER_CPU(struct sched_domain *, sd_numa); DEFINE_PER_CPU(struct sched_domain *, sd_asym); +DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) { @@ -692,6 +693,7 @@ static void init_overlap_sched_group(struct sched_domain *sd, sg_span = sched_group_span(sg); sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + sg->sgc->max_capacity = SCHED_CAPACITY_SCALE; } static int @@ -851,6 +853,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd) sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg)); sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + sg->sgc->max_capacity = SCHED_CAPACITY_SCALE; return sg; } @@ -1061,7 +1064,6 @@ static struct cpumask ***sched_domains_numa_masks; * SD_SHARE_PKG_RESOURCES - describes shared caches * SD_NUMA - describes NUMA topologies * SD_SHARE_POWERDOMAIN - describes shared power domain - * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies * * Odd one out, which beside describing the topology has a quirk also * prescribes the desired behaviour that goes along with it: @@ -1073,13 +1075,12 @@ static struct cpumask ***sched_domains_numa_masks; SD_SHARE_PKG_RESOURCES | \ SD_NUMA | \ SD_ASYM_PACKING | \ - SD_ASYM_CPUCAPACITY | \ SD_SHARE_POWERDOMAIN) static struct sched_domain * sd_init(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, - struct sched_domain *child, int cpu) + struct sched_domain *child, int dflags, int cpu) { struct sd_data *sdd = &tl->data; struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); @@ -1100,6 +1101,9 @@ sd_init(struct sched_domain_topology_level *tl, "wrong sd_flags in topology description\n")) sd_flags &= ~TOPOLOGY_SD_FLAGS; + /* Apply detected topology flags */ + sd_flags |= dflags; + *sd = (struct sched_domain){ .min_interval = sd_weight, .max_interval = 2*sd_weight, @@ -1122,7 +1126,7 @@ sd_init(struct sched_domain_topology_level *tl, | 0*SD_SHARE_CPUCAPACITY | 0*SD_SHARE_PKG_RESOURCES | 0*SD_SERIALIZE - | 0*SD_PREFER_SIBLING + | 1*SD_PREFER_SIBLING | 0*SD_NUMA | sd_flags , @@ -1148,17 +1152,21 @@ sd_init(struct sched_domain_topology_level *tl, if (sd->flags & SD_ASYM_CPUCAPACITY) { struct sched_domain *t = sd; + /* + * Don't attempt to spread across CPUs of different capacities. + */ + if (sd->child) + sd->child->flags &= ~SD_PREFER_SIBLING; + for_each_lower_domain(t) t->flags |= SD_BALANCE_WAKE; } if (sd->flags & SD_SHARE_CPUCAPACITY) { - sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 110; sd->smt_gain = 1178; /* ~15% */ } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { - sd->flags |= SD_PREFER_SIBLING; sd->imbalance_pct = 117; sd->cache_nice_tries = 1; sd->busy_idx = 2; @@ -1169,6 +1177,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->busy_idx = 3; sd->idle_idx = 2; + sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { sd->flags &= ~(SD_BALANCE_EXEC | @@ -1178,7 +1187,6 @@ sd_init(struct sched_domain_topology_level *tl, #endif } else { - sd->flags |= SD_PREFER_SIBLING; sd->cache_nice_tries = 1; sd->busy_idx = 2; sd->idle_idx = 1; @@ -1604,9 +1612,9 @@ static void __sdt_free(const struct cpumask *cpu_map) static struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, struct sched_domain_attr *attr, - struct sched_domain *child, int cpu) + struct sched_domain *child, int dflags, int cpu) { - struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu); + struct sched_domain *sd = sd_init(tl, cpu_map, child, dflags, cpu); if (child) { sd->level = child->level + 1; @@ -1633,6 +1641,65 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve } /* + * Find the sched_domain_topology_level where all CPU capacities are visible + * for all CPUs. + */ +static struct sched_domain_topology_level +*asym_cpu_capacity_level(const struct cpumask *cpu_map) +{ + int i, j, asym_level = 0; + bool asym = false; + struct sched_domain_topology_level *tl, *asym_tl = NULL; + unsigned long cap; + + /* Is there any asymmetry? */ + cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map)); + + for_each_cpu(i, cpu_map) { + if (arch_scale_cpu_capacity(NULL, i) != cap) { + asym = true; + break; + } + } + + if (!asym) + return NULL; + + /* + * Examine topology from all CPU's point of views to detect the lowest + * sched_domain_topology_level where a highest capacity CPU is visible + * to everyone. + */ + for_each_cpu(i, cpu_map) { + unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i); + int tl_id = 0; + + for_each_sd_topology(tl) { + if (tl_id < asym_level) + goto next_level; + + for_each_cpu_and(j, tl->mask(i), cpu_map) { + unsigned long capacity; + + capacity = arch_scale_cpu_capacity(NULL, j); + + if (capacity <= max_capacity) + continue; + + max_capacity = capacity; + asym_level = tl_id; + asym_tl = tl; + } +next_level: + tl_id++; + } + } + + return asym_tl; +} + + +/* * Build sched domains for a given set of CPUs and attach the sched domains * to the individual CPUs */ @@ -1644,18 +1711,30 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att struct s_data d; struct rq *rq = NULL; int i, ret = -ENOMEM; + struct sched_domain_topology_level *tl_asym; + bool has_asym = false; alloc_state = __visit_domain_allocation_hell(&d, cpu_map); if (alloc_state != sa_rootdomain) goto error; + tl_asym = asym_cpu_capacity_level(cpu_map); + /* Set up domains for CPUs specified by the cpu_map: */ for_each_cpu(i, cpu_map) { struct sched_domain_topology_level *tl; sd = NULL; for_each_sd_topology(tl) { - sd = build_sched_domain(tl, cpu_map, attr, sd, i); + int dflags = 0; + + if (tl == tl_asym) { + dflags |= SD_ASYM_CPUCAPACITY; + has_asym = true; + } + + sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i); + if (tl == sched_domain_topology) *per_cpu_ptr(d.sd, i) = sd; if (tl->flags & SDTL_OVERLAP) @@ -1704,6 +1783,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att } rcu_read_unlock(); + if (has_asym) + static_branch_enable_cpuslocked(&sched_asym_cpucapacity); + if (rq && sched_debug_enabled) { pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n", cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index fd023ac24e10..f2ae2324c232 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -195,7 +195,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ - if (unlikely(WARN_ON(f == NULL))) + if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; if (!sd) { @@ -297,7 +297,7 @@ static inline pid_t seccomp_can_sync_threads(void) /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ - if (unlikely(WARN_ON(failed == 0))) + if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } @@ -522,7 +522,7 @@ void put_seccomp_filter(struct task_struct *tsk) __put_seccomp_filter(tsk->seccomp.filter); } -static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) +static void seccomp_init_siginfo(kernel_siginfo_t *info, int syscall, int reason) { clear_siginfo(info); info->si_signo = SIGSYS; @@ -542,7 +542,7 @@ static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) */ static void seccomp_send_sigsys(int syscall, int reason) { - struct siginfo info; + struct kernel_siginfo info; seccomp_init_siginfo(&info, syscall, reason); force_sig_info(SIGSYS, &info, current); } @@ -747,7 +747,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, /* Dump core only if this is the last remaining thread. */ if (action == SECCOMP_RET_KILL_PROCESS || get_nr_threads(current) == 1) { - siginfo_t info; + kernel_siginfo_t info; /* Show the original registers in the dump. */ syscall_rollback(current, task_pt_regs(current)); diff --git a/kernel/signal.c b/kernel/signal.c index 5843c541fda9..17565240b1c6 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -78,6 +78,10 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force) handler = sig_handler(t, sig); + /* SIGKILL and SIGSTOP may not be sent to the global init */ + if (unlikely(is_global_init(t) && sig_kernel_only(sig))) + return true; + if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) && handler == SIG_DFL && !(force && sig_kernel_only(sig))) return true; @@ -172,6 +176,7 @@ void recalc_sigpending(void) clear_thread_flag(TIF_SIGPENDING); } +EXPORT_SYMBOL(recalc_sigpending); void calculate_sigpending(void) { @@ -462,6 +467,7 @@ void flush_signals(struct task_struct *t) flush_sigqueue(&t->signal->shared_pending); spin_unlock_irqrestore(&t->sighand->siglock, flags); } +EXPORT_SYMBOL(flush_signals); #ifdef CONFIG_POSIX_TIMERS static void __flush_itimer_signals(struct sigpending *pending) @@ -543,7 +549,7 @@ bool unhandled_signal(struct task_struct *tsk, int sig) return !tsk->ptrace; } -static void collect_signal(int sig, struct sigpending *list, siginfo_t *info, +static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, bool *resched_timer) { struct sigqueue *q, *first = NULL; @@ -589,7 +595,7 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - siginfo_t *info, bool *resched_timer) + kernel_siginfo_t *info, bool *resched_timer) { int sig = next_signal(pending, mask); @@ -604,7 +610,7 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, * * All callers have to hold the siglock. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info) { bool resched_timer = false; int signr; @@ -680,6 +686,7 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) #endif return signr; } +EXPORT_SYMBOL_GPL(dequeue_signal); /* * Tell a process that it has a new active signal.. @@ -730,12 +737,12 @@ static void flush_sigqueue_mask(sigset_t *mask, struct sigpending *s) } } -static inline int is_si_special(const struct siginfo *info) +static inline int is_si_special(const struct kernel_siginfo *info) { - return info <= SEND_SIG_FORCED; + return info <= SEND_SIG_PRIV; } -static inline bool si_fromuser(const struct siginfo *info) +static inline bool si_fromuser(const struct kernel_siginfo *info) { return info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info)); @@ -760,7 +767,7 @@ static bool kill_ok_by_cred(struct task_struct *t) * Bad permissions for sending the signal * - the caller must hold the RCU read lock */ -static int check_kill_permission(int sig, struct siginfo *info, +static int check_kill_permission(int sig, struct kernel_siginfo *info, struct task_struct *t) { struct pid *sid; @@ -1003,7 +1010,7 @@ static inline bool legacy_queue(struct sigpending *signals, int sig) } #ifdef CONFIG_USER_NS -static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +static inline void userns_fixup_signal_uid(struct kernel_siginfo *info, struct task_struct *t) { if (current_user_ns() == task_cred_xxx(t, user_ns)) return; @@ -1017,13 +1024,13 @@ static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_str rcu_read_unlock(); } #else -static inline void userns_fixup_signal_uid(struct siginfo *info, struct task_struct *t) +static inline void userns_fixup_signal_uid(struct kernel_siginfo *info, struct task_struct *t) { return; } #endif -static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, +static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type, int from_ancestor_ns) { struct sigpending *pending; @@ -1035,7 +1042,7 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, - from_ancestor_ns || (info == SEND_SIG_FORCED))) + from_ancestor_ns || (info == SEND_SIG_PRIV))) goto ret; pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; @@ -1050,10 +1057,10 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t, result = TRACE_SIGNAL_DELIVERED; /* - * fast-pathed signals for kernel-internal things like SIGSTOP - * or SIGKILL. + * Skip useless siginfo allocation for SIGKILL SIGSTOP, + * and kernel threads. */ - if (info == SEND_SIG_FORCED) + if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) goto out_set; /* @@ -1143,7 +1150,7 @@ ret: return ret; } -static int send_signal(int sig, struct siginfo *info, struct task_struct *t, +static int send_signal(int sig, struct kernel_siginfo *info, struct task_struct *t, enum pid_type type) { int from_ancestor_ns = 0; @@ -1190,18 +1197,12 @@ static int __init setup_print_fatal_signals(char *str) __setup("print-fatal-signals=", setup_print_fatal_signals); int -__group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +__group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { return send_signal(sig, info, p, PIDTYPE_TGID); } -static int -specific_send_sig_info(int sig, struct siginfo *info, struct task_struct *t) -{ - return send_signal(sig, info, t, PIDTYPE_PID); -} - -int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, +int do_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) { unsigned long flags; @@ -1227,7 +1228,7 @@ int do_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * that is why we also clear SIGNAL_UNKILLABLE. */ int -force_sig_info(int sig, struct siginfo *info, struct task_struct *t) +force_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *t) { unsigned long int flags; int ret, blocked, ignored; @@ -1250,7 +1251,7 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) */ if (action->sa.sa_handler == SIG_DFL && !t->ptrace) t->signal->flags &= ~SIGNAL_UNKILLABLE; - ret = specific_send_sig_info(sig, info, t); + ret = send_signal(sig, info, t, PIDTYPE_PID); spin_unlock_irqrestore(&t->sighand->siglock, flags); return ret; @@ -1315,8 +1316,8 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, /* * send signal info to all the members of a group */ -int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, - enum pid_type type) +int group_send_sig_info(int sig, struct kernel_siginfo *info, + struct task_struct *p, enum pid_type type) { int ret; @@ -1335,7 +1336,7 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p, * control characters do (^C, ^Z etc) * - the caller must hold at least a readlock on tasklist_lock */ -int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) +int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; int retval, success; @@ -1350,7 +1351,7 @@ int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) return success ? 0 : retval; } -int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) +int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) { int error = -ESRCH; struct task_struct *p; @@ -1372,7 +1373,7 @@ int kill_pid_info(int sig, struct siginfo *info, struct pid *pid) } } -static int kill_proc_info(int sig, struct siginfo *info, pid_t pid) +static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; rcu_read_lock(); @@ -1393,7 +1394,7 @@ static inline bool kill_as_cred_perm(const struct cred *cred, } /* like kill_pid_info(), but doesn't use uid/euid of "current" */ -int kill_pid_info_as_cred(int sig, struct siginfo *info, struct pid *pid, +int kill_pid_info_as_cred(int sig, struct kernel_siginfo *info, struct pid *pid, const struct cred *cred) { int ret = -EINVAL; @@ -1437,7 +1438,7 @@ EXPORT_SYMBOL_GPL(kill_pid_info_as_cred); * is probably wrong. Should make it like BSD or SYSV. */ -static int kill_something_info(int sig, struct siginfo *info, pid_t pid) +static int kill_something_info(int sig, struct kernel_siginfo *info, pid_t pid) { int ret; @@ -1481,7 +1482,7 @@ static int kill_something_info(int sig, struct siginfo *info, pid_t pid) * These are for backward compatibility with the rest of the kernel source. */ -int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) +int send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p) { /* * Make sure legacy kernel users don't send in bad values @@ -1492,6 +1493,7 @@ int send_sig_info(int sig, struct siginfo *info, struct task_struct *p) return do_send_sig_info(sig, info, p, PIDTYPE_PID); } +EXPORT_SYMBOL(send_sig_info); #define __si_special(priv) \ ((priv) ? SEND_SIG_PRIV : SEND_SIG_NOINFO) @@ -1501,11 +1503,13 @@ send_sig(int sig, struct task_struct *p, int priv) { return send_sig_info(sig, __si_special(priv), p); } +EXPORT_SYMBOL(send_sig); void force_sig(int sig, struct task_struct *p) { force_sig_info(sig, SEND_SIG_PRIV, p); } +EXPORT_SYMBOL(force_sig); /* * When things go south during signal handling, we @@ -1529,7 +1533,7 @@ int force_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -1552,7 +1556,7 @@ int send_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -1572,7 +1576,7 @@ int send_sig_fault(int sig, int code, void __user *addr int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); @@ -1586,7 +1590,7 @@ int force_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct int send_sig_mceerr(int code, void __user *addr, short lsb, struct task_struct *t) { - struct siginfo info; + struct kernel_siginfo info; WARN_ON((code != BUS_MCEERR_AO) && (code != BUS_MCEERR_AR)); clear_siginfo(&info); @@ -1601,7 +1605,7 @@ EXPORT_SYMBOL(send_sig_mceerr); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; @@ -1616,7 +1620,7 @@ int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper) #ifdef SEGV_PKUERR int force_sig_pkuerr(void __user *addr, u32 pkey) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGSEGV; @@ -1633,7 +1637,7 @@ int force_sig_pkuerr(void __user *addr, u32 pkey) */ int force_sig_ptrace_errno_trap(int errno, void __user *addr) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = SIGTRAP; @@ -1762,7 +1766,7 @@ ret: */ bool do_notify_parent(struct task_struct *tsk, int sig) { - struct siginfo info; + struct kernel_siginfo info; unsigned long flags; struct sighand_struct *psig; bool autoreap = false; @@ -1867,7 +1871,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) static void do_notify_parent_cldstop(struct task_struct *tsk, bool for_ptracer, int why) { - struct siginfo info; + struct kernel_siginfo info; unsigned long flags; struct task_struct *parent; struct sighand_struct *sighand; @@ -1967,7 +1971,7 @@ static bool sigkill_pending(struct task_struct *tsk) * If we actually decide not to stop at all because the tracer * is gone, we keep current->exit_code unless clear_code. */ -static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) +static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t *info) __releases(¤t->sighand->siglock) __acquires(¤t->sighand->siglock) { @@ -2104,7 +2108,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) static void ptrace_do_notify(int signr, int exit_code, int why) { - siginfo_t info; + kernel_siginfo_t info; clear_siginfo(&info); info.si_signo = signr; @@ -2285,7 +2289,7 @@ static void do_jobctl_trap(void) } } -static int ptrace_signal(int signr, siginfo_t *info) +static int ptrace_signal(int signr, kernel_siginfo_t *info) { /* * We do not check sig_kernel_stop(signr) but set this marker @@ -2326,7 +2330,7 @@ static int ptrace_signal(int signr, siginfo_t *info) /* If the (new) signal is now blocked, requeue it. */ if (sigismember(¤t->blocked, signr)) { - specific_send_sig_info(signr, info, current); + send_signal(signr, info, current, PIDTYPE_PID); signr = 0; } @@ -2636,14 +2640,6 @@ out: } } -EXPORT_SYMBOL(recalc_sigpending); -EXPORT_SYMBOL_GPL(dequeue_signal); -EXPORT_SYMBOL(flush_signals); -EXPORT_SYMBOL(force_sig); -EXPORT_SYMBOL(send_sig); -EXPORT_SYMBOL(send_sig_info); -EXPORT_SYMBOL(sigprocmask); - /* * System call entry points. */ @@ -2737,6 +2733,7 @@ int sigprocmask(int how, sigset_t *set, sigset_t *oldset) __set_current_blocked(&newset); return 0; } +EXPORT_SYMBOL(sigprocmask); /** * sys_rt_sigprocmask - change the list of currently blocked signals @@ -2847,27 +2844,48 @@ COMPAT_SYSCALL_DEFINE2(rt_sigpending, compat_sigset_t __user *, uset, } #endif -enum siginfo_layout siginfo_layout(int sig, int si_code) +static const struct { + unsigned char limit, layout; +} sig_sicodes[] = { + [SIGILL] = { NSIGILL, SIL_FAULT }, + [SIGFPE] = { NSIGFPE, SIL_FAULT }, + [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, + [SIGBUS] = { NSIGBUS, SIL_FAULT }, + [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, +#if defined(SIGEMT) + [SIGEMT] = { NSIGEMT, SIL_FAULT }, +#endif + [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, + [SIGPOLL] = { NSIGPOLL, SIL_POLL }, + [SIGSYS] = { NSIGSYS, SIL_SYS }, +}; + +static bool known_siginfo_layout(unsigned sig, int si_code) +{ + if (si_code == SI_KERNEL) + return true; + else if ((si_code > SI_USER)) { + if (sig_specific_sicodes(sig)) { + if (si_code <= sig_sicodes[sig].limit) + return true; + } + else if (si_code <= NSIGPOLL) + return true; + } + else if (si_code >= SI_DETHREAD) + return true; + else if (si_code == SI_ASYNCNL) + return true; + return false; +} + +enum siginfo_layout siginfo_layout(unsigned sig, int si_code) { enum siginfo_layout layout = SIL_KILL; if ((si_code > SI_USER) && (si_code < SI_KERNEL)) { - static const struct { - unsigned char limit, layout; - } filter[] = { - [SIGILL] = { NSIGILL, SIL_FAULT }, - [SIGFPE] = { NSIGFPE, SIL_FAULT }, - [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, - [SIGBUS] = { NSIGBUS, SIL_FAULT }, - [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, -#if defined(SIGEMT) && defined(NSIGEMT) - [SIGEMT] = { NSIGEMT, SIL_FAULT }, -#endif - [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, - [SIGPOLL] = { NSIGPOLL, SIL_POLL }, - [SIGSYS] = { NSIGSYS, SIL_SYS }, - }; - if ((sig < ARRAY_SIZE(filter)) && (si_code <= filter[sig].limit)) { - layout = filter[sig].layout; + if ((sig < ARRAY_SIZE(sig_sicodes)) && + (si_code <= sig_sicodes[sig].limit)) { + layout = sig_sicodes[sig].layout; /* Handle the exceptions */ if ((sig == SIGBUS) && (si_code >= BUS_MCEERR_AR) && (si_code <= BUS_MCEERR_AO)) @@ -2892,22 +2910,69 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) return layout; } -int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from) +static inline char __user *si_expansion(const siginfo_t __user *info) +{ + return ((char __user *)info) + sizeof(struct kernel_siginfo); +} + +int copy_siginfo_to_user(siginfo_t __user *to, const kernel_siginfo_t *from) { - if (copy_to_user(to, from , sizeof(struct siginfo))) + char __user *expansion = si_expansion(to); + if (copy_to_user(to, from , sizeof(struct kernel_siginfo))) + return -EFAULT; + if (clear_user(expansion, SI_EXPANSION_SIZE)) return -EFAULT; return 0; } +static int post_copy_siginfo_from_user(kernel_siginfo_t *info, + const siginfo_t __user *from) +{ + if (unlikely(!known_siginfo_layout(info->si_signo, info->si_code))) { + char __user *expansion = si_expansion(from); + char buf[SI_EXPANSION_SIZE]; + int i; + /* + * An unknown si_code might need more than + * sizeof(struct kernel_siginfo) bytes. Verify all of the + * extra bytes are 0. This guarantees copy_siginfo_to_user + * will return this data to userspace exactly. + */ + if (copy_from_user(&buf, expansion, SI_EXPANSION_SIZE)) + return -EFAULT; + for (i = 0; i < SI_EXPANSION_SIZE; i++) { + if (buf[i] != 0) + return -E2BIG; + } + } + return 0; +} + +static int __copy_siginfo_from_user(int signo, kernel_siginfo_t *to, + const siginfo_t __user *from) +{ + if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) + return -EFAULT; + to->si_signo = signo; + return post_copy_siginfo_from_user(to, from); +} + +int copy_siginfo_from_user(kernel_siginfo_t *to, const siginfo_t __user *from) +{ + if (copy_from_user(to, from, sizeof(struct kernel_siginfo))) + return -EFAULT; + return post_copy_siginfo_from_user(to, from); +} + #ifdef CONFIG_COMPAT int copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct siginfo *from) + const struct kernel_siginfo *from) #if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION) { return __copy_siginfo_to_user32(to, from, in_x32_syscall()); } int __copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct siginfo *from, bool x32_ABI) + const struct kernel_siginfo *from, bool x32_ABI) #endif { struct compat_siginfo new; @@ -2991,88 +3056,106 @@ int __copy_siginfo_to_user32(struct compat_siginfo __user *to, return 0; } -int copy_siginfo_from_user32(struct siginfo *to, - const struct compat_siginfo __user *ufrom) +static int post_copy_siginfo_from_user32(kernel_siginfo_t *to, + const struct compat_siginfo *from) { - struct compat_siginfo from; - - if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) - return -EFAULT; - clear_siginfo(to); - to->si_signo = from.si_signo; - to->si_errno = from.si_errno; - to->si_code = from.si_code; - switch(siginfo_layout(from.si_signo, from.si_code)) { + to->si_signo = from->si_signo; + to->si_errno = from->si_errno; + to->si_code = from->si_code; + switch(siginfo_layout(from->si_signo, from->si_code)) { case SIL_KILL: - to->si_pid = from.si_pid; - to->si_uid = from.si_uid; + to->si_pid = from->si_pid; + to->si_uid = from->si_uid; break; case SIL_TIMER: - to->si_tid = from.si_tid; - to->si_overrun = from.si_overrun; - to->si_int = from.si_int; + to->si_tid = from->si_tid; + to->si_overrun = from->si_overrun; + to->si_int = from->si_int; break; case SIL_POLL: - to->si_band = from.si_band; - to->si_fd = from.si_fd; + to->si_band = from->si_band; + to->si_fd = from->si_fd; break; case SIL_FAULT: - to->si_addr = compat_ptr(from.si_addr); + to->si_addr = compat_ptr(from->si_addr); #ifdef __ARCH_SI_TRAPNO - to->si_trapno = from.si_trapno; + to->si_trapno = from->si_trapno; #endif break; case SIL_FAULT_MCEERR: - to->si_addr = compat_ptr(from.si_addr); + to->si_addr = compat_ptr(from->si_addr); #ifdef __ARCH_SI_TRAPNO - to->si_trapno = from.si_trapno; + to->si_trapno = from->si_trapno; #endif - to->si_addr_lsb = from.si_addr_lsb; + to->si_addr_lsb = from->si_addr_lsb; break; case SIL_FAULT_BNDERR: - to->si_addr = compat_ptr(from.si_addr); + to->si_addr = compat_ptr(from->si_addr); #ifdef __ARCH_SI_TRAPNO - to->si_trapno = from.si_trapno; + to->si_trapno = from->si_trapno; #endif - to->si_lower = compat_ptr(from.si_lower); - to->si_upper = compat_ptr(from.si_upper); + to->si_lower = compat_ptr(from->si_lower); + to->si_upper = compat_ptr(from->si_upper); break; case SIL_FAULT_PKUERR: - to->si_addr = compat_ptr(from.si_addr); + to->si_addr = compat_ptr(from->si_addr); #ifdef __ARCH_SI_TRAPNO - to->si_trapno = from.si_trapno; + to->si_trapno = from->si_trapno; #endif - to->si_pkey = from.si_pkey; + to->si_pkey = from->si_pkey; break; case SIL_CHLD: - to->si_pid = from.si_pid; - to->si_uid = from.si_uid; - to->si_status = from.si_status; + to->si_pid = from->si_pid; + to->si_uid = from->si_uid; + to->si_status = from->si_status; #ifdef CONFIG_X86_X32_ABI if (in_x32_syscall()) { - to->si_utime = from._sifields._sigchld_x32._utime; - to->si_stime = from._sifields._sigchld_x32._stime; + to->si_utime = from->_sifields._sigchld_x32._utime; + to->si_stime = from->_sifields._sigchld_x32._stime; } else #endif { - to->si_utime = from.si_utime; - to->si_stime = from.si_stime; + to->si_utime = from->si_utime; + to->si_stime = from->si_stime; } break; case SIL_RT: - to->si_pid = from.si_pid; - to->si_uid = from.si_uid; - to->si_int = from.si_int; + to->si_pid = from->si_pid; + to->si_uid = from->si_uid; + to->si_int = from->si_int; break; case SIL_SYS: - to->si_call_addr = compat_ptr(from.si_call_addr); - to->si_syscall = from.si_syscall; - to->si_arch = from.si_arch; + to->si_call_addr = compat_ptr(from->si_call_addr); + to->si_syscall = from->si_syscall; + to->si_arch = from->si_arch; break; } return 0; } + +static int __copy_siginfo_from_user32(int signo, struct kernel_siginfo *to, + const struct compat_siginfo __user *ufrom) +{ + struct compat_siginfo from; + + if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) + return -EFAULT; + + from.si_signo = signo; + return post_copy_siginfo_from_user32(to, &from); +} + +int copy_siginfo_from_user32(struct kernel_siginfo *to, + const struct compat_siginfo __user *ufrom) +{ + struct compat_siginfo from; + + if (copy_from_user(&from, ufrom, sizeof(struct compat_siginfo))) + return -EFAULT; + + return post_copy_siginfo_from_user32(to, &from); +} #endif /* CONFIG_COMPAT */ /** @@ -3081,8 +3164,8 @@ int copy_siginfo_from_user32(struct siginfo *to, * @info: if non-null, the signal's siginfo is returned here * @ts: upper bound on process time suspension */ -static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, - const struct timespec *ts) +static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, + const struct timespec64 *ts) { ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; @@ -3090,9 +3173,9 @@ static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, int sig, ret = 0; if (ts) { - if (!timespec_valid(ts)) + if (!timespec64_valid(ts)) return -EINVAL; - timeout = timespec_to_ktime(*ts); + timeout = timespec64_to_ktime(*ts); to = &timeout; } @@ -3140,12 +3223,13 @@ static int do_sigtimedwait(const sigset_t *which, siginfo_t *info, * @sigsetsize: size of sigset_t type */ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, - siginfo_t __user *, uinfo, const struct timespec __user *, uts, + siginfo_t __user *, uinfo, + const struct __kernel_timespec __user *, uts, size_t, sigsetsize) { sigset_t these; - struct timespec ts; - siginfo_t info; + struct timespec64 ts; + kernel_siginfo_t info; int ret; /* XXX: Don't preclude handling different sized sigset_t's. */ @@ -3156,7 +3240,7 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, return -EFAULT; if (uts) { - if (copy_from_user(&ts, uts, sizeof(ts))) + if (get_timespec64(&ts, uts)) return -EFAULT; } @@ -3173,11 +3257,11 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese, #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, struct compat_siginfo __user *, uinfo, - struct compat_timespec __user *, uts, compat_size_t, sigsetsize) + struct old_timespec32 __user *, uts, compat_size_t, sigsetsize) { sigset_t s; - struct timespec t; - siginfo_t info; + struct timespec64 t; + kernel_siginfo_t info; long ret; if (sigsetsize != sizeof(sigset_t)) @@ -3187,7 +3271,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, return -EFAULT; if (uts) { - if (compat_get_timespec(&t, uts)) + if (get_old_timespec32(&t, uts)) return -EFAULT; } @@ -3209,7 +3293,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, */ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -3222,7 +3306,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) } static int -do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) +do_send_specific(pid_t tgid, pid_t pid, int sig, struct kernel_siginfo *info) { struct task_struct *p; int error = -ESRCH; @@ -3253,7 +3337,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) static int do_tkill(pid_t tgid, pid_t pid, int sig) { - struct siginfo info; + struct kernel_siginfo info; clear_siginfo(&info); info.si_signo = sig; @@ -3300,7 +3384,7 @@ SYSCALL_DEFINE2(tkill, pid_t, pid, int, sig) return do_tkill(0, pid, sig); } -static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) +static int do_rt_sigqueueinfo(pid_t pid, int sig, kernel_siginfo_t *info) { /* Not even root can pretend to send signals from the kernel. * Nor can they impersonate a kill()/tgkill(), which adds source info. @@ -3309,8 +3393,6 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) (task_pid_vnr(current) != pid)) return -EPERM; - info->si_signo = sig; - /* POSIX.1b doesn't mention process groups. */ return kill_proc_info(sig, info, pid); } @@ -3324,9 +3406,10 @@ static int do_rt_sigqueueinfo(pid_t pid, int sig, siginfo_t *info) SYSCALL_DEFINE3(rt_sigqueueinfo, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { - siginfo_t info; - if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) - return -EFAULT; + kernel_siginfo_t info; + int ret = __copy_siginfo_from_user(sig, &info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_sigqueueinfo(pid, sig, &info); } @@ -3336,15 +3419,15 @@ COMPAT_SYSCALL_DEFINE3(rt_sigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; - int ret = copy_siginfo_from_user32(&info, uinfo); + kernel_siginfo_t info; + int ret = __copy_siginfo_from_user32(sig, &info, uinfo); if (unlikely(ret)) return ret; return do_rt_sigqueueinfo(pid, sig, &info); } #endif -static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) +static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, kernel_siginfo_t *info) { /* This is only valid for single tasks */ if (pid <= 0 || tgid <= 0) @@ -3357,19 +3440,16 @@ static int do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig, siginfo_t *info) (task_pid_vnr(current) != pid)) return -EPERM; - info->si_signo = sig; - return do_send_specific(tgid, pid, sig, info); } SYSCALL_DEFINE4(rt_tgsigqueueinfo, pid_t, tgid, pid_t, pid, int, sig, siginfo_t __user *, uinfo) { - siginfo_t info; - - if (copy_from_user(&info, uinfo, sizeof(siginfo_t))) - return -EFAULT; - + kernel_siginfo_t info; + int ret = __copy_siginfo_from_user(sig, &info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } @@ -3380,10 +3460,10 @@ COMPAT_SYSCALL_DEFINE4(rt_tgsigqueueinfo, int, sig, struct compat_siginfo __user *, uinfo) { - siginfo_t info; - - if (copy_siginfo_from_user32(&info, uinfo)) - return -EFAULT; + kernel_siginfo_t info; + int ret = __copy_siginfo_from_user32(sig, &info, uinfo); + if (unlikely(ret)) + return ret; return do_rt_tgsigqueueinfo(tgid, pid, sig, &info); } #endif @@ -3460,7 +3540,8 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) } static int -do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp) +do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, + size_t min_ss_size) { struct task_struct *t = current; @@ -3490,7 +3571,7 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp) ss_size = 0; ss_sp = NULL; } else { - if (unlikely(ss_size < MINSIGSTKSZ)) + if (unlikely(ss_size < min_ss_size)) return -ENOMEM; } @@ -3508,7 +3589,8 @@ SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) if (uss && copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL, - current_user_stack_pointer()); + current_user_stack_pointer(), + MINSIGSTKSZ); if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t))) err = -EFAULT; return err; @@ -3519,7 +3601,8 @@ int restore_altstack(const stack_t __user *uss) stack_t new; if (copy_from_user(&new, uss, sizeof(stack_t))) return -EFAULT; - (void)do_sigaltstack(&new, NULL, current_user_stack_pointer()); + (void)do_sigaltstack(&new, NULL, current_user_stack_pointer(), + MINSIGSTKSZ); /* squash all but EFAULT for now */ return 0; } @@ -3553,7 +3636,8 @@ static int do_compat_sigaltstack(const compat_stack_t __user *uss_ptr, uss.ss_size = uss32.ss_size; } ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, - compat_user_stack_pointer()); + compat_user_stack_pointer(), + COMPAT_MINSIGSTKSZ); if (ret >= 0 && uoss_ptr) { compat_stack_t old; memset(&old, 0, sizeof(old)); @@ -3962,13 +4046,57 @@ __weak const char *arch_vma_name(struct vm_area_struct *vma) return NULL; } -void __init signals_init(void) +static inline void siginfo_buildtime_checks(void) { - /* If this check fails, the __ARCH_SI_PREAMBLE_SIZE value is wrong! */ - BUILD_BUG_ON(__ARCH_SI_PREAMBLE_SIZE - != offsetof(struct siginfo, _sifields._pad)); BUILD_BUG_ON(sizeof(struct siginfo) != SI_MAX_SIZE); + /* Verify the offsets in the two siginfos match */ +#define CHECK_OFFSET(field) \ + BUILD_BUG_ON(offsetof(siginfo_t, field) != offsetof(kernel_siginfo_t, field)) + + /* kill */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + + /* timer */ + CHECK_OFFSET(si_tid); + CHECK_OFFSET(si_overrun); + CHECK_OFFSET(si_value); + + /* rt */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + CHECK_OFFSET(si_value); + + /* sigchld */ + CHECK_OFFSET(si_pid); + CHECK_OFFSET(si_uid); + CHECK_OFFSET(si_status); + CHECK_OFFSET(si_utime); + CHECK_OFFSET(si_stime); + + /* sigfault */ + CHECK_OFFSET(si_addr); + CHECK_OFFSET(si_addr_lsb); + CHECK_OFFSET(si_lower); + CHECK_OFFSET(si_upper); + CHECK_OFFSET(si_pkey); + + /* sigpoll */ + CHECK_OFFSET(si_band); + CHECK_OFFSET(si_fd); + + /* sigsys */ + CHECK_OFFSET(si_call_addr); + CHECK_OFFSET(si_syscall); + CHECK_OFFSET(si_arch); +#undef CHECK_OFFSET +} + +void __init signals_init(void) +{ + siginfo_buildtime_checks(); + sigqueue_cachep = KMEM_CACHE(sigqueue, SLAB_PANIC); } diff --git a/kernel/smp.c b/kernel/smp.c index d86eec5f51c1..163c451af42e 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -669,9 +669,9 @@ EXPORT_SYMBOL(on_each_cpu_mask); * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), +void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags) + gfp_t gfp_flags, const struct cpumask *mask) { cpumask_var_t cpus; int cpu, ret; @@ -680,9 +680,9 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { preempt_disable(); - for_each_online_cpu(cpu) + for_each_cpu(cpu, mask) if (cond_func(cpu, info)) - cpumask_set_cpu(cpu, cpus); + __cpumask_set_cpu(cpu, cpus); on_each_cpu_mask(cpus, func, info, wait); preempt_enable(); free_cpumask_var(cpus); @@ -692,7 +692,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), * just have to IPI them one by one. */ preempt_disable(); - for_each_online_cpu(cpu) + for_each_cpu(cpu, mask) if (cond_func(cpu, info)) { ret = smp_call_function_single(cpu, func, info, wait); @@ -701,6 +701,15 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), preempt_enable(); } } +EXPORT_SYMBOL(on_each_cpu_cond_mask); + +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, + cpu_online_mask); +} EXPORT_SYMBOL(on_each_cpu_cond); static void do_nothing(void *unused) diff --git a/kernel/softirq.c b/kernel/softirq.c index 6f584861d329..d28813306b2c 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -257,9 +257,9 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) int softirq_bit; /* - * Mask out PF_MEMALLOC s current task context is borrowed for the - * softirq. A softirq handled such as network RX might set PF_MEMALLOC - * again if the socket is related to swap + * Mask out PF_MEMALLOC as the current task context is borrowed for the + * softirq. A softirq handled, such as network RX, might set PF_MEMALLOC + * again if the socket is related to swapping. */ current->flags &= ~PF_MEMALLOC; @@ -301,7 +301,8 @@ restart: pending >>= softirq_bit; } - rcu_bh_qs(); + if (__this_cpu_read(ksoftirqd) == current) + rcu_softirq_qs(); local_irq_disable(); pending = local_softirq_pending(); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 78eabc41eaa6..58b981f4bb5d 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,6 +12,10 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool +# Architecture has extra clocksource init called from registration +config ARCH_CLOCKSOURCE_INIT + bool + # Clocksources require validation of the clocksource against the last # cycle update - x86/TSC misfeature config CLOCKSOURCE_VALIDATE_LAST_CYCLE diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 0e6e97a01942..ffe081623aec 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -937,6 +937,8 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { unsigned long flags; + clocksource_arch_init(cs); + /* Initialize mult/shift and max_idle_ns */ __clocksource_update_freq_scale(cs, scale, freq); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index e1a549c9e399..9cdd74bd2d27 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1660,7 +1660,7 @@ int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: - if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp)) + if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif @@ -1780,12 +1780,12 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) +COMPAT_SYSCALL_DEFINE2(nanosleep, struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 tu; - if (compat_get_timespec64(&tu, rqtp)) + if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 2c6847d5d69b..989ccf028bde 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -162,20 +162,20 @@ COMPAT_SYS_NI(setitimer); #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { struct timespec64 new_tp; if (which_clock != CLOCK_REALTIME) return -EINVAL; - if (compat_get_timespec64(&new_tp, tp)) + if (get_old_timespec32(&new_tp, tp)) return -EFAULT; return do_sys_settimeofday64(&new_tp, NULL); } COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { int ret; struct timespec64 kernel_tp; @@ -184,13 +184,13 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, if (ret) return ret; - if (compat_put_timespec64(&kernel_tp, tp)) + if (put_old_timespec32(&kernel_tp, tp)) return -EFAULT; return 0; } COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { struct timespec64 rtn_tp = { .tv_sec = 0, @@ -201,7 +201,7 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, case CLOCK_REALTIME: case CLOCK_MONOTONIC: case CLOCK_BOOTTIME: - if (compat_put_timespec64(&rtn_tp, tp)) + if (put_old_timespec32(&rtn_tp, tp)) return -EFAULT; return 0; default: @@ -210,8 +210,8 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, } COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 t; @@ -224,7 +224,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, return -EINVAL; } - if (compat_get_timespec64(&t, rqtp)) + if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) return -EINVAL; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 4b9127e95430..bd62b5eeb5a0 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -308,7 +308,7 @@ static void common_hrtimer_rearm(struct k_itimer *timr) * To protect against the timer going away while the interrupt is queued, * we require that the it_requeue_pending flag be set. */ -void posixtimer_rearm(struct siginfo *info) +void posixtimer_rearm(struct kernel_siginfo *info) { struct k_itimer *timr; unsigned long flags; @@ -755,13 +755,13 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct compat_itimerspec __user *, setting) + struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; int ret = do_timer_gettime(timer_id, &cur_setting); if (!ret) { - if (put_compat_itimerspec64(&cur_setting, setting)) + if (put_old_itimerspec32(&cur_setting, setting)) ret = -EFAULT; } return ret; @@ -928,8 +928,8 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - struct compat_itimerspec __user *, new, - struct compat_itimerspec __user *, old) + struct old_itimerspec32 __user *, new, + struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; @@ -937,12 +937,12 @@ COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, if (!new) return -EINVAL; - if (get_compat_itimerspec64(&new_spec, new)) + if (get_old_itimerspec32(&new_spec, new)) return -EFAULT; error = do_timer_settime(timer_id, flags, &new_spec, rtn); if (!error && old) { - if (put_compat_itimerspec64(&old_spec, old)) + if (put_old_itimerspec32(&old_spec, old)) error = -EFAULT; } return error; @@ -1115,7 +1115,7 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1123,14 +1123,14 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, if (!kc || !kc->clock_set) return -EINVAL; - if (compat_get_timespec64(&ts, tp)) + if (get_old_timespec32(&ts, tp)) return -EFAULT; return kc->clock_set(which_clock, &ts); } COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1141,7 +1141,7 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, err = kc->clock_get(which_clock, &ts); - if (!err && compat_put_timespec64(&ts, tp)) + if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; return err; @@ -1180,7 +1180,7 @@ COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct compat_timespec __user *, tp) + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1190,7 +1190,7 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, return -EINVAL; err = kc->clock_getres(which_clock, &ts); - if (!err && tp && compat_put_timespec64(&ts, tp)) + if (!err && tp && put_old_timespec32(&ts, tp)) return -EFAULT; return err; @@ -1237,8 +1237,8 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct compat_timespec __user *, rqtp, - struct compat_timespec __user *, rmtp) + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; @@ -1248,7 +1248,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, if (!kc->nsleep) return -EOPNOTSUPP; - if (compat_get_timespec64(&t, rqtp)) + if (get_old_timespec32(&t, rqtp)) return -EFAULT; if (!timespec64_valid(&t)) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index aa2094d5dd27..be0aac2b4300 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -400,8 +400,6 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) if (tick_broadcast_forced) break; cpumask_clear_cpu(cpu, tick_broadcast_on); - if (!tick_device_is_functional(dev)) - break; if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 5b33e2f5c0ed..69e673b88474 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -885,7 +885,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (need_resched()) return false; - if (unlikely(local_softirq_pending() && cpu_online(cpu))) { + if (unlikely(local_softirq_pending())) { static int ratelimit; if (ratelimit < 10 && diff --git a/kernel/time/time.c b/kernel/time/time.c index ccdb351277ee..e3a7f7fd3abc 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -104,12 +104,12 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_TIME -/* compat_time_t is a 32 bit "long" and needs to get converted. */ -COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) +/* old_time32_t is a 32 bit "long" and needs to get converted. */ +COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) { - compat_time_t i; + old_time32_t i; - i = (compat_time_t)ktime_get_real_seconds(); + i = (old_time32_t)ktime_get_real_seconds(); if (tloc) { if (put_user(i,tloc)) @@ -119,7 +119,7 @@ COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) return i; } -COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) +COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr) { struct timespec64 tv; int err; @@ -144,9 +144,11 @@ SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, struct timezone __user *, tz) { if (likely(tv != NULL)) { - struct timeval ktv; - do_gettimeofday(&ktv); - if (copy_to_user(tv, &ktv, sizeof(ktv))) + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + if (put_user(ts.tv_sec, &tv->tv_sec) || + put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (unlikely(tz != NULL)) { @@ -223,14 +225,15 @@ SYSCALL_DEFINE2(settimeofday, struct timeval __user *, tv, } #ifdef CONFIG_COMPAT -COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, +COMPAT_SYSCALL_DEFINE2(gettimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { if (tv) { - struct timeval ktv; + struct timespec64 ts; - do_gettimeofday(&ktv); - if (compat_put_timeval(&ktv, tv)) + ktime_get_real_ts64(&ts); + if (put_user(ts.tv_sec, &tv->tv_sec) || + put_user(ts.tv_nsec / 1000, &tv->tv_usec)) return -EFAULT; } if (tz) { @@ -241,7 +244,7 @@ COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, return 0; } -COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, +COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, struct timezone __user *, tz) { struct timespec64 new_ts; @@ -342,30 +345,6 @@ unsigned int jiffies_to_usecs(const unsigned long j) } EXPORT_SYMBOL(jiffies_to_usecs); -/** - * timespec_trunc - Truncate timespec to a granularity - * @t: Timespec - * @gran: Granularity in ns. - * - * Truncate a timespec to a granularity. Always rounds down. gran must - * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). - */ -struct timespec timespec_trunc(struct timespec t, unsigned gran) -{ - /* Avoid division in the common cases 1 ns and 1 s. */ - if (gran == 1) { - /* nothing */ - } else if (gran == NSEC_PER_SEC) { - t.tv_nsec = 0; - } else if (gran > 1 && gran < NSEC_PER_SEC) { - t.tv_nsec -= t.tv_nsec % gran; - } else { - WARN(1, "illegal file time granularity: %u", gran); - } - return t; -} -EXPORT_SYMBOL(timespec_trunc); - /* * mktime64 - Converts date to seconds. * Converts Gregorian date to seconds since 1970-01-01 00:00:00. @@ -884,10 +863,10 @@ int put_timespec64(const struct timespec64 *ts, } EXPORT_SYMBOL_GPL(put_timespec64); -int __compat_get_timespec64(struct timespec64 *ts64, - const struct compat_timespec __user *cts) +static int __get_old_timespec32(struct timespec64 *ts64, + const struct old_timespec32 __user *cts) { - struct compat_timespec ts; + struct old_timespec32 ts; int ret; ret = copy_from_user(&ts, cts, sizeof(ts)); @@ -900,33 +879,33 @@ int __compat_get_timespec64(struct timespec64 *ts64, return 0; } -int __compat_put_timespec64(const struct timespec64 *ts64, - struct compat_timespec __user *cts) +static int __put_old_timespec32(const struct timespec64 *ts64, + struct old_timespec32 __user *cts) { - struct compat_timespec ts = { + struct old_timespec32 ts = { .tv_sec = ts64->tv_sec, .tv_nsec = ts64->tv_nsec }; return copy_to_user(cts, &ts, sizeof(ts)) ? -EFAULT : 0; } -int compat_get_timespec64(struct timespec64 *ts, const void __user *uts) +int get_old_timespec32(struct timespec64 *ts, const void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; else - return __compat_get_timespec64(ts, uts); + return __get_old_timespec32(ts, uts); } -EXPORT_SYMBOL_GPL(compat_get_timespec64); +EXPORT_SYMBOL_GPL(get_old_timespec32); -int compat_put_timespec64(const struct timespec64 *ts, void __user *uts) +int put_old_timespec32(const struct timespec64 *ts, void __user *uts) { if (COMPAT_USE_64BIT_TIME) return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; else - return __compat_put_timespec64(ts, uts); + return __put_old_timespec32(ts, uts); } -EXPORT_SYMBOL_GPL(compat_put_timespec64); +EXPORT_SYMBOL_GPL(put_old_timespec32); int get_itimerspec64(struct itimerspec64 *it, const struct __kernel_itimerspec __user *uit) @@ -958,23 +937,23 @@ int put_itimerspec64(const struct itimerspec64 *it, } EXPORT_SYMBOL_GPL(put_itimerspec64); -int get_compat_itimerspec64(struct itimerspec64 *its, - const struct compat_itimerspec __user *uits) +int get_old_itimerspec32(struct itimerspec64 *its, + const struct old_itimerspec32 __user *uits) { - if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) || - __compat_get_timespec64(&its->it_value, &uits->it_value)) + if (__get_old_timespec32(&its->it_interval, &uits->it_interval) || + __get_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(get_compat_itimerspec64); +EXPORT_SYMBOL_GPL(get_old_itimerspec32); -int put_compat_itimerspec64(const struct itimerspec64 *its, - struct compat_itimerspec __user *uits) +int put_old_itimerspec32(const struct itimerspec64 *its, + struct old_itimerspec32 __user *uits) { - if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) || - __compat_put_timespec64(&its->it_value, &uits->it_value)) + if (__put_old_timespec32(&its->it_interval, &uits->it_interval) || + __put_old_timespec32(&its->it_value, &uits->it_value)) return -EFAULT; return 0; } -EXPORT_SYMBOL_GPL(put_compat_itimerspec64); +EXPORT_SYMBOL_GPL(put_old_itimerspec32); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f3b22f456fac..2d110c948805 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1212,22 +1212,6 @@ int get_device_system_crosststamp(int (*get_time_fn) EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** - * do_gettimeofday - Returns the time of day in a timeval - * @tv: pointer to the timeval to be set - * - * NOTE: Users should be converted to using getnstimeofday() - */ -void do_gettimeofday(struct timeval *tv) -{ - struct timespec64 now; - - getnstimeofday64(&now); - tv->tv_sec = now.tv_sec; - tv->tv_usec = now.tv_nsec/1000; -} -EXPORT_SYMBOL(do_gettimeofday); - -/** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * @@ -2174,14 +2158,6 @@ void getboottime64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(getboottime64); -unsigned long get_seconds(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - return tk->xtime_sec; -} -EXPORT_SYMBOL(get_seconds); - void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; diff --git a/kernel/torture.c b/kernel/torture.c index 1ac24a826589..17d91f5fba2a 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -573,7 +573,7 @@ static int stutter; * Block until the stutter interval ends. This must be called periodically * by all running kthreads that need to be subject to stuttering. */ -void stutter_wait(const char *title) +bool stutter_wait(const char *title) { int spt; @@ -590,6 +590,7 @@ void stutter_wait(const char *title) } torture_shutdown_absorb(title); } + return !!spt; } EXPORT_SYMBOL_GPL(stutter_wait); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2868d85f1fb1..fac0ddf8a8e2 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_css) + if (!bio->bi_blkg) return NULL; - return cgroup_get_kernfs_id(bio->bi_css->cgroup); + return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); } #else static union kernfs_node_id * diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index f704390db9fc..d8765c952fab 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -5,12 +5,12 @@ * Copyright (C) 2018 Joel Fernandes (Google) <joel@joelfernandes.org> */ +#include <linux/trace_clock.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kernel.h> #include <linux/kthread.h> -#include <linux/ktime.h> #include <linux/module.h> #include <linux/printk.h> #include <linux/string.h> @@ -25,13 +25,13 @@ MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt or irq (default ir static void busy_wait(ulong time) { - ktime_t start, end; - start = ktime_get(); + u64 start, end; + start = trace_clock_local(); do { - end = ktime_get(); + end = trace_clock_local(); if (kthread_should_stop()) break; - } while (ktime_to_ns(ktime_sub(end, start)) < (time * 1000)); + } while ((end - start) < (time * 1000)); } static int preemptirq_delay_run(void *data) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 85f6b01431c7..eb908ef2ecec 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -738,16 +738,30 @@ static void free_synth_field(struct synth_field *field) kfree(field); } -static struct synth_field *parse_synth_field(char *field_type, - char *field_name) +static struct synth_field *parse_synth_field(int argc, char **argv, + int *consumed) { struct synth_field *field; + const char *prefix = NULL; + char *field_type = argv[0], *field_name; int len, ret = 0; char *array; if (field_type[0] == ';') field_type++; + if (!strcmp(field_type, "unsigned")) { + if (argc < 3) + return ERR_PTR(-EINVAL); + prefix = "unsigned "; + field_type = argv[1]; + field_name = argv[2]; + *consumed = 3; + } else { + field_name = argv[1]; + *consumed = 2; + } + len = strlen(field_name); if (field_name[len - 1] == ';') field_name[len - 1] = '\0'; @@ -760,11 +774,15 @@ static struct synth_field *parse_synth_field(char *field_type, array = strchr(field_name, '['); if (array) len += strlen(array); + if (prefix) + len += strlen(prefix); field->type = kzalloc(len, GFP_KERNEL); if (!field->type) { ret = -ENOMEM; goto free; } + if (prefix) + strcat(field->type, prefix); strcat(field->type, field_type); if (array) { strcat(field->type, array); @@ -1009,7 +1027,7 @@ static int create_synth_event(int argc, char **argv) struct synth_field *field, *fields[SYNTH_FIELDS_MAX]; struct synth_event *event = NULL; bool delete_event = false; - int i, n_fields = 0, ret = 0; + int i, consumed = 0, n_fields = 0, ret = 0; char *name; mutex_lock(&synth_event_mutex); @@ -1045,8 +1063,10 @@ static int create_synth_event(int argc, char **argv) event = NULL; ret = -EEXIST; goto out; - } else if (delete_event) + } else if (delete_event) { + ret = -ENOENT; goto out; + } if (argc < 2) { ret = -EINVAL; @@ -1061,16 +1081,16 @@ static int create_synth_event(int argc, char **argv) goto err; } - field = parse_synth_field(argv[i], argv[i + 1]); + field = parse_synth_field(argc - i, &argv[i], &consumed); if (IS_ERR(field)) { ret = PTR_ERR(field); goto err; } - fields[n_fields] = field; - i++; n_fields++; + fields[n_fields++] = field; + i += consumed - 1; } - if (i < argc) { + if (i < argc && strcmp(argv[i], ";") != 0) { ret = -EINVAL; goto err; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index bf2c06ef9afc..a3be42304485 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -28,8 +28,8 @@ #include <linux/sched/task.h> #include <linux/static_key.h> -extern struct tracepoint * const __start___tracepoints_ptrs[]; -extern struct tracepoint * const __stop___tracepoints_ptrs[]; +extern tracepoint_ptr_t __start___tracepoints_ptrs[]; +extern tracepoint_ptr_t __stop___tracepoints_ptrs[]; DEFINE_SRCU(tracepoint_srcu); EXPORT_SYMBOL_GPL(tracepoint_srcu); @@ -371,25 +371,17 @@ int tracepoint_probe_unregister(struct tracepoint *tp, void *probe, void *data) } EXPORT_SYMBOL_GPL(tracepoint_probe_unregister); -static void for_each_tracepoint_range(struct tracepoint * const *begin, - struct tracepoint * const *end, +static void for_each_tracepoint_range( + tracepoint_ptr_t *begin, tracepoint_ptr_t *end, void (*fct)(struct tracepoint *tp, void *priv), void *priv) { + tracepoint_ptr_t *iter; + if (!begin) return; - - if (IS_ENABLED(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)) { - const int *iter; - - for (iter = (const int *)begin; iter < (const int *)end; iter++) - fct(offset_to_ptr(iter), priv); - } else { - struct tracepoint * const *iter; - - for (iter = begin; iter < end; iter++) - fct(*iter, priv); - } + for (iter = begin; iter < end; iter++) + fct(tracepoint_ptr_deref(iter), priv); } #ifdef CONFIG_MODULES diff --git a/kernel/umh.c b/kernel/umh.c index c449858946af..0baa672e023c 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -405,11 +405,19 @@ struct subprocess_info *call_usermodehelper_setup_file(struct file *file, void (*cleanup)(struct subprocess_info *info), void *data) { struct subprocess_info *sub_info; + struct umh_info *info = data; + const char *cmdline = (info->cmdline) ? info->cmdline : "usermodehelper"; sub_info = kzalloc(sizeof(struct subprocess_info), GFP_KERNEL); if (!sub_info) return NULL; + sub_info->argv = argv_split(GFP_KERNEL, cmdline, NULL); + if (!sub_info->argv) { + kfree(sub_info); + return NULL; + } + INIT_WORK(&sub_info->work, call_usermodehelper_exec_work); sub_info->path = "none"; sub_info->file = file; @@ -458,10 +466,11 @@ static int umh_pipe_setup(struct subprocess_info *info, struct cred *new) return 0; } -static void umh_save_pid(struct subprocess_info *info) +static void umh_clean_and_save_pid(struct subprocess_info *info) { struct umh_info *umh_info = info->data; + argv_free(info->argv); umh_info->pid = info->pid; } @@ -471,6 +480,9 @@ static void umh_save_pid(struct subprocess_info *info) * @len: length of the blob * @info: information about usermode process (shouldn't be NULL) * + * If info->cmdline is set it will be used as command line for the + * user process, else "usermodehelper" is used. + * * Returns either negative error or zero which indicates success * in executing a blob of bytes as a usermode process. In such * case 'struct umh_info *info' is populated with two pipes @@ -500,7 +512,7 @@ int fork_usermode_blob(void *data, size_t len, struct umh_info *info) err = -ENOMEM; sub_info = call_usermodehelper_setup_file(file, umh_pipe_setup, - umh_save_pid, info); + umh_clean_and_save_pid, info); if (!sub_info) goto out; diff --git a/kernel/up.c b/kernel/up.c index 42c46bf3e0a5..ff536f9cc8a2 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -68,9 +68,9 @@ EXPORT_SYMBOL(on_each_cpu_mask); * Preemption is disabled here to make sure the cond_func is called under the * same condtions in UP and SMP. */ -void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), - smp_call_func_t func, void *info, bool wait, - gfp_t gfp_flags) +void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags, const struct cpumask *mask) { unsigned long flags; @@ -82,6 +82,14 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), } preempt_enable(); } +EXPORT_SYMBOL(on_each_cpu_cond_mask); + +void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info), + smp_call_func_t func, void *info, bool wait, + gfp_t gfp_flags) +{ + on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, NULL); +} EXPORT_SYMBOL(on_each_cpu_cond); int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) |
