diff options
Diffstat (limited to 'kernel')
155 files changed, 6287 insertions, 2695 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index e0852dc333ac..3de8fd11873b 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -101,7 +101,7 @@ config UNINLINE_SPIN_UNLOCK # unlock and unlock_irq functions are inlined when: # - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y # or -# - DEBUG_SPINLOCK=n and PREEMPT=n +# - DEBUG_SPINLOCK=n and PREEMPTION=n # # unlock_bh and unlock_irqrestore functions are inlined when: # - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y @@ -139,7 +139,7 @@ config INLINE_SPIN_UNLOCK_BH config INLINE_SPIN_UNLOCK_IRQ def_bool y - depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ + depends on !PREEMPTION || ARCH_INLINE_SPIN_UNLOCK_IRQ config INLINE_SPIN_UNLOCK_IRQRESTORE def_bool y @@ -168,7 +168,7 @@ config INLINE_READ_LOCK_IRQSAVE config INLINE_READ_UNLOCK def_bool y - depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK + depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK config INLINE_READ_UNLOCK_BH def_bool y @@ -176,7 +176,7 @@ config INLINE_READ_UNLOCK_BH config INLINE_READ_UNLOCK_IRQ def_bool y - depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ + depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK_IRQ config INLINE_READ_UNLOCK_IRQRESTORE def_bool y @@ -205,7 +205,7 @@ config INLINE_WRITE_LOCK_IRQSAVE config INLINE_WRITE_UNLOCK def_bool y - depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK + depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK config INLINE_WRITE_UNLOCK_BH def_bool y @@ -213,7 +213,7 @@ config INLINE_WRITE_UNLOCK_BH config INLINE_WRITE_UNLOCK_IRQ def_bool y - depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ + depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK_IRQ config INLINE_WRITE_UNLOCK_IRQRESTORE def_bool y diff --git a/kernel/Makefile b/kernel/Makefile index f2cc0d118a0b..4cb4130ced32 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -27,6 +27,7 @@ KCOV_INSTRUMENT_softirq.o := n # and produce insane amounts of uninteresting coverage. KCOV_INSTRUMENT_module.o := n KCOV_INSTRUMENT_extable.o := n +KCOV_INSTRUMENT_stacktrace.o := n # Don't self-instrument. KCOV_INSTRUMENT_kcov.o := n KASAN_SANITIZE_kcov.o := n diff --git a/kernel/acct.c b/kernel/acct.c index 81f9831a7859..11ff4a596d6b 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -416,6 +416,7 @@ static void fill_ac(acct_t *ac) { struct pacct_struct *pacct = ¤t->signal->pacct; u64 elapsed, run_time; + time64_t btime; struct tty_struct *tty; /* @@ -448,7 +449,8 @@ static void fill_ac(acct_t *ac) } #endif do_div(elapsed, AHZ); - ac->ac_btime = get_seconds() - elapsed; + btime = ktime_get_real_seconds() - elapsed; + ac->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); #if ACCT_VERSION==2 ac->ac_ahz = AHZ; #endif diff --git a/kernel/audit.c b/kernel/audit.c index 8e09f0f55b4b..9ddfe2aa6671 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -102,12 +102,13 @@ struct audit_net { * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ -static struct auditd_connection { +struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; -} *auditd_conn = NULL; +}; +static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records @@ -1100,13 +1101,11 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature audit_log_end(ab); } -static int audit_set_feature(struct sk_buff *skb) +static int audit_set_feature(struct audit_features *uaf) { - struct audit_features *uaf; int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); - uaf = nlmsg_data(nlmsg_hdr(skb)); /* if there is ever a version 2 we should handle that here */ @@ -1174,6 +1173,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { u32 seq; void *data; + int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; @@ -1187,6 +1187,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); + data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { @@ -1210,7 +1211,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) @@ -1314,7 +1315,9 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; break; case AUDIT_SET_FEATURE: - err = audit_set_feature(skb); + if (data_len < sizeof(struct audit_features)) + return -EINVAL; + err = audit_set_feature(data); if (err) return err; break; @@ -1326,6 +1329,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + char *str = data; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); @@ -1333,26 +1338,24 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) break; } audit_log_user_recv_msg(&ab, msg_type); - if (msg_type != AUDIT_USER_TTY) + if (msg_type != AUDIT_USER_TTY) { + /* ensure NULL termination */ + str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, - (char *)data); - else { - int size; - + str); + } else { audit_log_format(ab, " data="); - size = nlmsg_len(nlh); - if (size > 0 && - ((unsigned char *)data)[size - 1] == '\0') - size--; - audit_log_n_untrustedstring(ab, data, size); + if (data_len > 0 && str[data_len - 1] == '\0') + data_len--; + audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: - if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) + if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, @@ -1364,7 +1367,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_end(ab); return -EPERM; } - err = audit_rule_change(msg_type, seq, data, nlmsg_len(nlh)); + err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); @@ -1379,7 +1382,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; - size_t msglen = nlmsg_len(nlh); + size_t msglen = data_len; char *old, *new; err = -EINVAL; @@ -1455,7 +1458,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ - memcpy(&s, data, min_t(size_t, sizeof(s), nlmsg_len(nlh))); + memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index b0126e9c0743..026e34da4ace 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -456,6 +456,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; + u32 f_val; err = -EINVAL; @@ -464,12 +465,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, goto exit_free; f->type = data->fields[i]; - f->val = data->values[i]; + f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ - if ((f->type == AUDIT_LOGINUID) && (f->val == AUDIT_UID_UNSET)) { + if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; - f->val = 0; + f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } @@ -485,7 +486,7 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: - f->uid = make_kuid(current_user_ns(), f->val); + f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; @@ -494,11 +495,12 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: - f->gid = make_kgid(current_user_ns(), f->val); + f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: + f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: @@ -511,11 +513,13 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } + entry->rule.buflen += f_val; + f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule); /* Keep currently invalid fields around in case they @@ -524,68 +528,71 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; - } - if (err) { - kfree(str); + } else if (err) goto exit_free; - } else - f->lsm_str = str; break; case AUDIT_WATCH: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - - err = audit_to_watch(&entry->rule, str, f->val, f->op); + } + err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } + entry->rule.buflen += f_val; break; case AUDIT_DIR: - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; - + } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; + entry->rule.buflen += f_val; break; case AUDIT_INODE: + f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: - if (entry->rule.filterkey || f->val > AUDIT_MAX_KEY_LEN) + if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); - if (IS_ERR(str)) + str = audit_unpack_string(&bufp, &remain, f_val); + if (IS_ERR(str)) { + err = PTR_ERR(str); goto exit_free; - entry->rule.buflen += f->val; + } + entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: - if (entry->rule.exe || f->val > PATH_MAX) + if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; - str = audit_unpack_string(&bufp, &remain, f->val); + str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } - entry->rule.buflen += f->val; - - audit_mark = audit_alloc_mark(&entry->rule, str, f->val); + audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } + entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; + default: + f->val = f_val; + break; } } diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 3f671bf617e8..046ce5d98033 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o +obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o @@ -26,3 +27,6 @@ endif ifeq ($(CONFIG_SYSFS),y) obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o endif +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o +endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f0d19bbb9211..95d77770353c 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -503,6 +503,8 @@ const struct bpf_map_ops array_map_ops = { .map_mmap = array_map_mmap, .map_seq_show_elem = array_map_seq_show_elem, .map_check_btf = array_map_check_btf, + .map_lookup_batch = generic_map_lookup_batch, + .map_update_batch = generic_map_update_batch, }; const struct bpf_map_ops percpu_array_map_ops = { diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c new file mode 100644 index 000000000000..042f95534f86 --- /dev/null +++ b/kernel/bpf/bpf_struct_ops.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2019 Facebook */ + +#include <linux/bpf.h> +#include <linux/bpf_verifier.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <linux/slab.h> +#include <linux/numa.h> +#include <linux/seq_file.h> +#include <linux/refcount.h> +#include <linux/mutex.h> + +enum bpf_struct_ops_state { + BPF_STRUCT_OPS_STATE_INIT, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE, +}; + +#define BPF_STRUCT_OPS_COMMON_VALUE \ + refcount_t refcnt; \ + enum bpf_struct_ops_state state + +struct bpf_struct_ops_value { + BPF_STRUCT_OPS_COMMON_VALUE; + char data[0] ____cacheline_aligned_in_smp; +}; + +struct bpf_struct_ops_map { + struct bpf_map map; + const struct bpf_struct_ops *st_ops; + /* protect map_update */ + struct mutex lock; + /* progs has all the bpf_prog that is populated + * to the func ptr of the kernel's struct + * (in kvalue.data). + */ + struct bpf_prog **progs; + /* image is a page that has all the trampolines + * that stores the func args before calling the bpf_prog. + * A PAGE_SIZE "image" is enough to store all trampoline for + * "progs[]". + */ + void *image; + /* uvalue->data stores the kernel struct + * (e.g. tcp_congestion_ops) that is more useful + * to userspace than the kvalue. For example, + * the bpf_prog's id is stored instead of the kernel + * address of a func ptr. + */ + struct bpf_struct_ops_value *uvalue; + /* kvalue.data stores the actual kernel's struct + * (e.g. tcp_congestion_ops) that will be + * registered to the kernel subsystem. + */ + struct bpf_struct_ops_value kvalue; +}; + +#define VALUE_PREFIX "bpf_struct_ops_" +#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) + +/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is + * the map's value exposed to the userspace and its btf-type-id is + * stored at the map->btf_vmlinux_value_type_id. + * + */ +#define BPF_STRUCT_OPS_TYPE(_name) \ +extern struct bpf_struct_ops bpf_##_name; \ + \ +struct bpf_struct_ops_##_name { \ + BPF_STRUCT_OPS_COMMON_VALUE; \ + struct _name data ____cacheline_aligned_in_smp; \ +}; +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + +enum { +#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + __NR_BPF_STRUCT_OPS_TYPE, +}; + +static struct bpf_struct_ops * const bpf_struct_ops[] = { +#define BPF_STRUCT_OPS_TYPE(_name) \ + [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE +}; + +const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { +}; + +const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +}; + +static const struct btf_type *module_type; + +void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +{ + s32 type_id, value_id, module_id; + const struct btf_member *member; + struct bpf_struct_ops *st_ops; + const struct btf_type *t; + char value_name[128]; + const char *mname; + u32 i, j; + + /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ +#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); +#include "bpf_struct_ops_types.h" +#undef BPF_STRUCT_OPS_TYPE + + module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); + if (module_id < 0) { + pr_warn("Cannot find struct module in btf_vmlinux\n"); + return; + } + module_type = btf_type_by_id(btf, module_id); + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + st_ops = bpf_struct_ops[i]; + + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + continue; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); + + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in btf_vmlinux\n", + value_name); + continue; + } + + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in btf_vmlinux\n", + st_ops->name); + continue; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + continue; + } + + for_each_member(j, t, member) { + const struct btf_type *func_proto; + + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", + st_ops->name); + break; + } + + if (btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + break; + } + + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (func_proto && + btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[j])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + break; + } + } + + if (j == btf_type_vlen(t)) { + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + } else { + st_ops->type_id = type_id; + st_ops->type = t; + st_ops->value_id = value_id; + st_ops->value_type = btf_type_by_id(btf, + value_id); + } + } + } +} + +extern struct btf *btf_vmlinux; + +static const struct bpf_struct_ops * +bpf_struct_ops_find_value(u32 value_id) +{ + unsigned int i; + + if (!value_id || !btf_vmlinux) + return NULL; + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + if (bpf_struct_ops[i]->value_id == value_id) + return bpf_struct_ops[i]; + } + + return NULL; +} + +const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) +{ + unsigned int i; + + if (!type_id || !btf_vmlinux) + return NULL; + + for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { + if (bpf_struct_ops[i]->type_id == type_id) + return bpf_struct_ops[i]; + } + + return NULL; +} + +static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + if (key && *(u32 *)key == 0) + return -ENOENT; + + *(u32 *)next_key = 0; + return 0; +} + +int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, + void *value) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + struct bpf_struct_ops_value *uvalue, *kvalue; + enum bpf_struct_ops_state state; + + if (unlikely(*(u32 *)key != 0)) + return -ENOENT; + + kvalue = &st_map->kvalue; + /* Pair with smp_store_release() during map_update */ + state = smp_load_acquire(&kvalue->state); + if (state == BPF_STRUCT_OPS_STATE_INIT) { + memset(value, 0, map->value_size); + return 0; + } + + /* No lock is needed. state and refcnt do not need + * to be updated together under atomic context. + */ + uvalue = (struct bpf_struct_ops_value *)value; + memcpy(uvalue, st_map->uvalue, map->value_size); + uvalue->state = state; + refcount_set(&uvalue->refcnt, refcount_read(&kvalue->refcnt)); + + return 0; +} + +static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) +{ + const struct btf_type *t = st_map->st_ops->type; + u32 i; + + for (i = 0; i < btf_type_vlen(t); i++) { + if (st_map->progs[i]) { + bpf_prog_put(st_map->progs[i]); + st_map->progs[i] = NULL; + } + } +} + +static int check_zero_holes(const struct btf_type *t, void *data) +{ + const struct btf_member *member; + u32 i, moff, msize, prev_mend = 0; + const struct btf_type *mtype; + + for_each_member(i, t, member) { + moff = btf_member_bit_offset(t, member) / 8; + if (moff > prev_mend && + memchr_inv(data + prev_mend, 0, moff - prev_mend)) + return -EINVAL; + + mtype = btf_type_by_id(btf_vmlinux, member->type); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, + NULL, NULL); + if (IS_ERR(mtype)) + return PTR_ERR(mtype); + prev_mend = moff + msize; + } + + if (t->size > prev_mend && + memchr_inv(data + prev_mend, 0, t->size - prev_mend)) + return -EINVAL; + + return 0; +} + +static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + const struct bpf_struct_ops *st_ops = st_map->st_ops; + struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_member *member; + const struct btf_type *t = st_ops->type; + void *udata, *kdata; + int prog_fd, err = 0; + void *image; + u32 i; + + if (flags) + return -EINVAL; + + if (*(u32 *)key != 0) + return -E2BIG; + + err = check_zero_holes(st_ops->value_type, value); + if (err) + return err; + + uvalue = (struct bpf_struct_ops_value *)value; + err = check_zero_holes(t, uvalue->data); + if (err) + return err; + + if (uvalue->state || refcount_read(&uvalue->refcnt)) + return -EINVAL; + + uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; + kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue; + + mutex_lock(&st_map->lock); + + if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + err = -EBUSY; + goto unlock; + } + + memcpy(uvalue, value, map->value_size); + + udata = &uvalue->data; + kdata = &kvalue->data; + image = st_map->image; + + for_each_member(i, t, member) { + const struct btf_type *mtype, *ptype; + struct bpf_prog *prog; + u32 moff; + + moff = btf_member_bit_offset(t, member) / 8; + ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + if (ptype == module_type) { + if (*(void **)(udata + moff)) + goto reset_unlock; + *(void **)(kdata + moff) = BPF_MODULE_OWNER; + continue; + } + + err = st_ops->init_member(t, member, kdata, udata); + if (err < 0) + goto reset_unlock; + + /* The ->init_member() has handled this member */ + if (err > 0) + continue; + + /* If st_ops->init_member does not handle it, + * we will only handle func ptrs and zero-ed members + * here. Reject everything else. + */ + + /* All non func ptr member must be 0 */ + if (!ptype || !btf_type_is_func_proto(ptype)) { + u32 msize; + + mtype = btf_type_by_id(btf_vmlinux, member->type); + mtype = btf_resolve_size(btf_vmlinux, mtype, &msize, + NULL, NULL); + if (IS_ERR(mtype)) { + err = PTR_ERR(mtype); + goto reset_unlock; + } + + if (memchr_inv(udata + moff, 0, msize)) { + err = -EINVAL; + goto reset_unlock; + } + + continue; + } + + prog_fd = (int)(*(unsigned long *)(udata + moff)); + /* Similar check as the attr->attach_prog_fd */ + if (!prog_fd) + continue; + + prog = bpf_prog_get(prog_fd); + if (IS_ERR(prog)) { + err = PTR_ERR(prog); + goto reset_unlock; + } + st_map->progs[i] = prog; + + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || + prog->aux->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != i) { + err = -EINVAL; + goto reset_unlock; + } + + err = arch_prepare_bpf_trampoline(image, + st_map->image + PAGE_SIZE, + &st_ops->func_models[i], 0, + &prog, 1, NULL, 0, NULL); + if (err < 0) + goto reset_unlock; + + *(void **)(kdata + moff) = image; + image += err; + + /* put prog_id to udata */ + *(unsigned long *)(udata + moff) = prog->aux->id; + } + + refcount_set(&kvalue->refcnt, 1); + bpf_map_inc(map); + + set_memory_ro((long)st_map->image, 1); + set_memory_x((long)st_map->image, 1); + err = st_ops->reg(kdata); + if (likely(!err)) { + /* Pair with smp_load_acquire() during lookup_elem(). + * It ensures the above udata updates (e.g. prog->aux->id) + * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. + */ + smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + goto unlock; + } + + /* Error during st_ops->reg(). It is very unlikely since + * the above init_member() should have caught it earlier + * before reg(). The only possibility is if there was a race + * in registering the struct_ops (under the same name) to + * a sub-system through different struct_ops's maps. + */ + set_memory_nx((long)st_map->image, 1); + set_memory_rw((long)st_map->image, 1); + bpf_map_put(map); + +reset_unlock: + bpf_struct_ops_map_put_progs(st_map); + memset(uvalue, 0, map->value_size); + memset(kvalue, 0, map->value_size); +unlock: + mutex_unlock(&st_map->lock); + return err; +} + +static int bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) +{ + enum bpf_struct_ops_state prev_state; + struct bpf_struct_ops_map *st_map; + + st_map = (struct bpf_struct_ops_map *)map; + prev_state = cmpxchg(&st_map->kvalue.state, + BPF_STRUCT_OPS_STATE_INUSE, + BPF_STRUCT_OPS_STATE_TOBEFREE); + if (prev_state == BPF_STRUCT_OPS_STATE_INUSE) { + st_map->st_ops->unreg(&st_map->kvalue.data); + if (refcount_dec_and_test(&st_map->kvalue.refcnt)) + bpf_map_put(map); + } + + return 0; +} + +static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + int err; + + value = kmalloc(map->value_size, GFP_USER | __GFP_NOWARN); + if (!value) + return; + + err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); + if (!err) { + btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + value, m); + seq_puts(m, "\n"); + } + + kfree(value); +} + +static void bpf_struct_ops_map_free(struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + if (st_map->progs) + bpf_struct_ops_map_put_progs(st_map); + bpf_map_area_free(st_map->progs); + bpf_jit_free_exec(st_map->image); + bpf_map_area_free(st_map->uvalue); + bpf_map_area_free(st_map); +} + +static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) +{ + if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || + attr->map_flags || !attr->btf_vmlinux_value_type_id) + return -EINVAL; + return 0; +} + +static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) +{ + const struct bpf_struct_ops *st_ops; + size_t map_total_size, st_map_size; + struct bpf_struct_ops_map *st_map; + const struct btf_type *t, *vt; + struct bpf_map_memory mem; + struct bpf_map *map; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); + if (!st_ops) + return ERR_PTR(-ENOTSUPP); + + vt = st_ops->value_type; + if (attr->value_size != vt->size) + return ERR_PTR(-EINVAL); + + t = st_ops->type; + + st_map_size = sizeof(*st_map) + + /* kvalue stores the + * struct bpf_struct_ops_tcp_congestions_ops + */ + (vt->size - sizeof(struct bpf_struct_ops_value)); + map_total_size = st_map_size + + /* uvalue */ + sizeof(vt->size) + + /* struct bpf_progs **progs */ + btf_type_vlen(t) * sizeof(struct bpf_prog *); + err = bpf_map_charge_init(&mem, map_total_size); + if (err < 0) + return ERR_PTR(err); + + st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); + if (!st_map) { + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + st_map->st_ops = st_ops; + map = &st_map->map; + + st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->progs = + bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_prog *), + NUMA_NO_NODE); + st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!st_map->uvalue || !st_map->progs || !st_map->image) { + bpf_struct_ops_map_free(map); + bpf_map_charge_finish(&mem); + return ERR_PTR(-ENOMEM); + } + + mutex_init(&st_map->lock); + set_vm_flush_reset_perms(st_map->image); + bpf_map_init_from_attr(map, attr); + bpf_map_charge_move(&map->memory, &mem); + + return map; +} + +const struct bpf_map_ops bpf_struct_ops_map_ops = { + .map_alloc_check = bpf_struct_ops_map_alloc_check, + .map_alloc = bpf_struct_ops_map_alloc, + .map_free = bpf_struct_ops_map_free, + .map_get_next_key = bpf_struct_ops_map_get_next_key, + .map_lookup_elem = bpf_struct_ops_map_lookup_elem, + .map_delete_elem = bpf_struct_ops_map_delete_elem, + .map_update_elem = bpf_struct_ops_map_update_elem, + .map_seq_show_elem = bpf_struct_ops_map_seq_show_elem, +}; + +/* "const void *" because some subsystem is + * passing a const (e.g. const struct tcp_congestion_ops *) + */ +bool bpf_struct_ops_get(const void *kdata) +{ + struct bpf_struct_ops_value *kvalue; + + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + + return refcount_inc_not_zero(&kvalue->refcnt); +} + +void bpf_struct_ops_put(const void *kdata) +{ + struct bpf_struct_ops_value *kvalue; + + kvalue = container_of(kdata, struct bpf_struct_ops_value, data); + if (refcount_dec_and_test(&kvalue->refcnt)) { + struct bpf_struct_ops_map *st_map; + + st_map = container_of(kvalue, struct bpf_struct_ops_map, + kvalue); + bpf_map_put(&st_map->map); + } +} diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h new file mode 100644 index 000000000000..066d83ea1c99 --- /dev/null +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* internal file - do not include directly */ + +#ifdef CONFIG_BPF_JIT +#ifdef CONFIG_INET +#include <net/tcp.h> +BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) +#endif +#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ed2075884724..787140095e58 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -180,11 +180,6 @@ */ #define BTF_MAX_SIZE (16 * 1024 * 1024) -#define for_each_member(i, struct_type, member) \ - for (i = 0, member = btf_type_member(struct_type); \ - i < btf_type_vlen(struct_type); \ - i++, member++) - #define for_each_member_from(i, from, struct_type, member) \ for (i = from, member = btf_type_member(struct_type) + from; \ i < btf_type_vlen(struct_type); \ @@ -281,6 +276,11 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_DATASEC] = "DATASEC", }; +static const char *btf_type_str(const struct btf_type *t) +{ + return btf_kind_str[BTF_INFO_KIND(t->info)]; +} + struct btf_kind_operations { s32 (*check_meta)(struct btf_verifier_env *env, const struct btf_type *t, @@ -382,6 +382,65 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } +s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind) +{ + const struct btf_type *t; + const char *tname; + u32 i; + + for (i = 1; i <= btf->nr_types; i++) { + t = btf->types[i]; + if (BTF_INFO_KIND(t->info) != kind) + continue; + + tname = btf_name_by_offset(btf, t->name_off); + if (!strcmp(tname, name)) + return i; + } + + return -ENOENT; +} + +const struct btf_type *btf_type_skip_modifiers(const struct btf *btf, + u32 id, u32 *res_id) +{ + const struct btf_type *t = btf_type_by_id(btf, id); + + while (btf_type_is_modifier(t)) { + id = t->type; + t = btf_type_by_id(btf, t->type); + } + + if (res_id) + *res_id = id; + + return t; +} + +const struct btf_type *btf_type_resolve_ptr(const struct btf *btf, + u32 id, u32 *res_id) +{ + const struct btf_type *t; + + t = btf_type_skip_modifiers(btf, id, NULL); + if (!btf_type_is_ptr(t)) + return NULL; + + return btf_type_skip_modifiers(btf, t->type, res_id); +} + +const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, + u32 id, u32 *res_id) +{ + const struct btf_type *ptype; + + ptype = btf_type_resolve_ptr(btf, id, res_id); + if (ptype && btf_type_is_func_proto(ptype)) + return ptype; + + return NULL; +} + /* Types that act only as a source, not sink or intermediate * type when resolving. */ @@ -446,30 +505,6 @@ static const char *btf_int_encoding_str(u8 encoding) return "UNKN"; } -static u16 btf_type_vlen(const struct btf_type *t) -{ - return BTF_INFO_VLEN(t->info); -} - -static bool btf_type_kflag(const struct btf_type *t) -{ - return BTF_INFO_KFLAG(t->info); -} - -static u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) -{ - return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) - : member->offset; -} - -static u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) -{ - return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) - : 0; -} - static u32 btf_type_int(const struct btf_type *t) { return *(u32 *)(t + 1); @@ -480,11 +515,6 @@ static const struct btf_array *btf_type_array(const struct btf_type *t) return (const struct btf_array *)(t + 1); } -static const struct btf_member *btf_type_member(const struct btf_type *t) -{ - return (const struct btf_member *)(t + 1); -} - static const struct btf_enum *btf_type_enum(const struct btf_type *t) { return (const struct btf_enum *)(t + 1); @@ -1057,7 +1087,7 @@ static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) * *elem_type: same as return type ("struct X") * *total_nelems: 1 */ -static const struct btf_type * +const struct btf_type * btf_resolve_size(const struct btf *btf, const struct btf_type *type, u32 *type_size, const struct btf_type **elem_type, u32 *total_nelems) @@ -1111,8 +1141,10 @@ resolved: return ERR_PTR(-EINVAL); *type_size = nelems * size; - *total_nelems = nelems; - *elem_type = type; + if (total_nelems) + *total_nelems = nelems; + if (elem_type) + *elem_type = type; return array_type ? : type; } @@ -1826,7 +1858,10 @@ static void btf_modifier_seq_show(const struct btf *btf, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) { - t = btf_type_id_resolve(btf, &type_id); + if (btf->resolved_ids) + t = btf_type_id_resolve(btf, &type_id); + else + t = btf_type_skip_modifiers(btf, type_id, NULL); btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); } @@ -2621,8 +2656,8 @@ static s32 btf_func_check_meta(struct btf_verifier_env *env, return -EINVAL; } - if (btf_type_vlen(t)) { - btf_verifier_log_type(env, t, "vlen != 0"); + if (btf_type_vlen(t) > BTF_FUNC_GLOBAL) { + btf_verifier_log_type(env, t, "Invalid func linkage"); return -EINVAL; } @@ -3476,7 +3511,8 @@ static u8 bpf_ctx_convert_map[] = { static const struct btf_member * btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type) + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) { const struct btf_type *conv_struct; const struct btf_type *ctx_struct; @@ -3497,12 +3533,13 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - bpf_log(log, "BPF program ctx type is not a struct\n"); + if (log->level & BPF_LOG_LEVEL) + bpf_log(log, "arg#%d type is not a struct\n", arg); return NULL; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { - bpf_log(log, "BPF program ctx struct doesn't have a name\n"); + bpf_log(log, "arg#%d struct doesn't have a name\n", arg); return NULL; } /* prog_type is valid bpf program type. No need for bounds check. */ @@ -3535,11 +3572,12 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, struct btf *btf, static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *t, - enum bpf_prog_type prog_type) + enum bpf_prog_type prog_type, + int arg) { const struct btf_member *prog_ctx_type, *kern_ctx_type; - prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type); + prog_ctx_type = btf_get_prog_ctx_type(log, btf, t, prog_type, arg); if (!prog_ctx_type) return -ENOENT; kern_ctx_type = prog_ctx_type + 1; @@ -3605,6 +3643,8 @@ struct btf *btf_parse_vmlinux(void) goto errout; } + bpf_struct_ops_init(btf, log); + btf_verifier_env_free(env); refcount_set(&btf->refcnt, 1); return btf; @@ -3629,6 +3669,19 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) } } +static bool is_string_ptr(struct btf *btf, const struct btf_type *t) +{ + /* t comes in already as a pointer */ + t = btf_type_by_id(btf, t->type); + + /* allow const */ + if (BTF_INFO_KIND(t->info) == BTF_KIND_CONST) + t = btf_type_by_id(btf, t->type); + + /* char, signed char, unsigned char */ + return btf_type_is_int(t) && t->size == 1; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -3677,7 +3730,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t)) + if (btf_type_is_int(t) || btf_type_is_enum(t)) /* accessing a scalar */ return true; if (!btf_type_is_ptr(t)) { @@ -3695,12 +3748,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, */ return true; + if (is_string_ptr(btf, t)) + return true; + /* this is a pointer to another type */ info->reg_type = PTR_TO_BTF_ID; - info->btf_id = t->type; if (tgt_prog) { - ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type); + ret = btf_translate_to_vmlinux(log, btf, t, tgt_prog->type, arg); if (ret > 0) { info->btf_id = ret; return true; @@ -3708,10 +3763,14 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, return false; } } + + info->btf_id = t->type; t = btf_type_by_id(btf, t->type); /* skip modifiers */ - while (btf_type_is_modifier(t)) + while (btf_type_is_modifier(t)) { + info->btf_id = t->type; t = btf_type_by_id(btf, t->type); + } if (!btf_type_is_struct(t)) { bpf_log(log, "func '%s' arg%d type %s is not a struct\n", @@ -3737,23 +3796,57 @@ int btf_struct_access(struct bpf_verifier_log *log, again: tname = __btf_name_by_offset(btf_vmlinux, t->name_off); if (!btf_type_is_struct(t)) { - bpf_log(log, "Type '%s' is not a struct", tname); + bpf_log(log, "Type '%s' is not a struct\n", tname); return -EINVAL; } - for_each_member(i, t, member) { - if (btf_member_bitfield_size(t, member)) - /* bitfields are not supported yet */ - continue; + if (off + size > t->size) { + bpf_log(log, "access beyond struct %s at off %u size %u\n", + tname, off, size); + return -EACCES; + } + for_each_member(i, t, member) { /* offset of the field in bytes */ moff = btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; + + if (btf_member_bitfield_size(t, member)) { + u32 end_bit = btf_member_bit_offset(t, member) + + btf_member_bitfield_size(t, member); + + /* off <= moff instead of off == moff because clang + * does not generate a BTF member for anonymous + * bitfield like the ":16" here: + * struct { + * int :16; + * int x:8; + * }; + */ + if (off <= moff && + BITS_ROUNDUP_BYTES(end_bit) <= off + size) + return SCALAR_VALUE; + + /* off may be accessing a following member + * + * or + * + * Doing partial access at either end of this + * bitfield. Continue on this case also to + * treat it as not accessing this bitfield + * and eventually error out as field not + * found to keep it simple. + * It could be relaxed if there was a legit + * partial access case later. + */ + continue; + } + /* In case of "off" is pointing to holes of a struct */ if (off < moff) - continue; + break; /* type of the field */ mtype = btf_type_by_id(btf_vmlinux, member->type); @@ -3838,6 +3931,7 @@ again: if (btf_type_is_ptr(mtype)) { const struct btf_type *stype; + u32 id; if (msize != size || off != moff) { bpf_log(log, @@ -3846,12 +3940,9 @@ again: return -EACCES; } - stype = btf_type_by_id(btf_vmlinux, mtype->type); - /* skip modifiers */ - while (btf_type_is_modifier(stype)) - stype = btf_type_by_id(btf_vmlinux, stype->type); + stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); if (btf_type_is_struct(stype)) { - *next_btf_id = mtype->type; + *next_btf_id = id; return PTR_TO_BTF_ID; } } @@ -4043,11 +4134,158 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return 0; } -int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog) +/* Compare BTFs of two functions assuming only scalars and pointers to context. + * t1 points to BTF_KIND_FUNC in btf1 + * t2 points to BTF_KIND_FUNC in btf2 + * Returns: + * EINVAL - function prototype mismatch + * EFAULT - verifier bug + * 0 - 99% match. The last 1% is validated by the verifier. + */ +static int btf_check_func_type_match(struct bpf_verifier_log *log, + struct btf *btf1, const struct btf_type *t1, + struct btf *btf2, const struct btf_type *t2) +{ + const struct btf_param *args1, *args2; + const char *fn1, *fn2, *s1, *s2; + u32 nargs1, nargs2, i; + + fn1 = btf_name_by_offset(btf1, t1->name_off); + fn2 = btf_name_by_offset(btf2, t2->name_off); + + if (btf_func_linkage(t1) != BTF_FUNC_GLOBAL) { + bpf_log(log, "%s() is not a global function\n", fn1); + return -EINVAL; + } + if (btf_func_linkage(t2) != BTF_FUNC_GLOBAL) { + bpf_log(log, "%s() is not a global function\n", fn2); + return -EINVAL; + } + + t1 = btf_type_by_id(btf1, t1->type); + if (!t1 || !btf_type_is_func_proto(t1)) + return -EFAULT; + t2 = btf_type_by_id(btf2, t2->type); + if (!t2 || !btf_type_is_func_proto(t2)) + return -EFAULT; + + args1 = (const struct btf_param *)(t1 + 1); + nargs1 = btf_type_vlen(t1); + args2 = (const struct btf_param *)(t2 + 1); + nargs2 = btf_type_vlen(t2); + + if (nargs1 != nargs2) { + bpf_log(log, "%s() has %d args while %s() has %d args\n", + fn1, nargs1, fn2, nargs2); + return -EINVAL; + } + + t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); + t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); + if (t1->info != t2->info) { + bpf_log(log, + "Return type %s of %s() doesn't match type %s of %s()\n", + btf_type_str(t1), fn1, + btf_type_str(t2), fn2); + return -EINVAL; + } + + for (i = 0; i < nargs1; i++) { + t1 = btf_type_skip_modifiers(btf1, args1[i].type, NULL); + t2 = btf_type_skip_modifiers(btf2, args2[i].type, NULL); + + if (t1->info != t2->info) { + bpf_log(log, "arg%d in %s() is %s while %s() has %s\n", + i, fn1, btf_type_str(t1), + fn2, btf_type_str(t2)); + return -EINVAL; + } + if (btf_type_has_size(t1) && t1->size != t2->size) { + bpf_log(log, + "arg%d in %s() has size %d while %s() has %d\n", + i, fn1, t1->size, + fn2, t2->size); + return -EINVAL; + } + + /* global functions are validated with scalars and pointers + * to context only. And only global functions can be replaced. + * Hence type check only those types. + */ + if (btf_type_is_int(t1) || btf_type_is_enum(t1)) + continue; + if (!btf_type_is_ptr(t1)) { + bpf_log(log, + "arg%d in %s() has unrecognized type\n", + i, fn1); + return -EINVAL; + } + t1 = btf_type_skip_modifiers(btf1, t1->type, NULL); + t2 = btf_type_skip_modifiers(btf2, t2->type, NULL); + if (!btf_type_is_struct(t1)) { + bpf_log(log, + "arg%d in %s() is not a pointer to context\n", + i, fn1); + return -EINVAL; + } + if (!btf_type_is_struct(t2)) { + bpf_log(log, + "arg%d in %s() is not a pointer to context\n", + i, fn2); + return -EINVAL; + } + /* This is an optional check to make program writing easier. + * Compare names of structs and report an error to the user. + * btf_prepare_func_args() already checked that t2 struct + * is a context type. btf_prepare_func_args() will check + * later that t1 struct is a context type as well. + */ + s1 = btf_name_by_offset(btf1, t1->name_off); + s2 = btf_name_by_offset(btf2, t2->name_off); + if (strcmp(s1, s2)) { + bpf_log(log, + "arg%d %s(struct %s *) doesn't match %s(struct %s *)\n", + i, fn1, s1, fn2, s2); + return -EINVAL; + } + } + return 0; +} + +/* Compare BTFs of given program with BTF of target program */ +int btf_check_type_match(struct bpf_verifier_env *env, struct bpf_prog *prog, + struct btf *btf2, const struct btf_type *t2) +{ + struct btf *btf1 = prog->aux->btf; + const struct btf_type *t1; + u32 btf_id = 0; + + if (!prog->aux->func_info) { + bpf_log(&env->log, "Program extension requires BTF\n"); + return -EINVAL; + } + + btf_id = prog->aux->func_info[0].type_id; + if (!btf_id) + return -EFAULT; + + t1 = btf_type_by_id(btf1, btf_id); + if (!t1 || !btf_type_is_func(t1)) + return -EFAULT; + + return btf_check_func_type_match(&env->log, btf1, t1, btf2, t2); +} + +/* Compare BTF of a function with given bpf_reg_state. + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - there is a type mismatch or BTF is not available. + * 0 - BTF matches with what bpf_reg_state expects. + * Only PTR_TO_CTX and SCALAR_VALUE states are recognized. + */ +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *reg) { - struct bpf_verifier_state *st = env->cur_state; - struct bpf_func_state *func = st->frame[st->curframe]; - struct bpf_reg_state *reg = func->regs; struct bpf_verifier_log *log = &env->log; struct bpf_prog *prog = env->prog; struct btf *btf = prog->aux->btf; @@ -4057,27 +4295,30 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog) const char *tname; if (!prog->aux->func_info) - return 0; + return -EINVAL; btf_id = prog->aux->func_info[subprog].type_id; if (!btf_id) - return 0; + return -EFAULT; if (prog->aux->func_info_aux[subprog].unreliable) - return 0; + return -EINVAL; t = btf_type_by_id(btf, btf_id); if (!t || !btf_type_is_func(t)) { - bpf_log(log, "BTF of subprog %d doesn't point to KIND_FUNC\n", + /* These checks were already done by the verifier while loading + * struct bpf_func_info + */ + bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", subprog); - return -EINVAL; + return -EFAULT; } tname = btf_name_by_offset(btf, t->name_off); t = btf_type_by_id(btf, t->type); if (!t || !btf_type_is_func_proto(t)) { - bpf_log(log, "Invalid type of func %s\n", tname); - return -EINVAL; + bpf_log(log, "Invalid BTF of func %s\n", tname); + return -EFAULT; } args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); @@ -4103,25 +4344,130 @@ int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog) bpf_log(log, "R%d is not a pointer\n", i + 1); goto out; } - /* If program is passing PTR_TO_CTX into subprogram - * check that BTF type matches. + /* If function expects ctx type in BTF check that caller + * is passing PTR_TO_CTX. */ - if (reg[i + 1].type == PTR_TO_CTX && - !btf_get_prog_ctx_type(log, btf, t, prog->type)) - goto out; - /* All other pointers are ok */ - continue; + if (btf_get_prog_ctx_type(log, btf, t, prog->type, i)) { + if (reg[i + 1].type != PTR_TO_CTX) { + bpf_log(log, + "arg#%d expected pointer to ctx, but got %s\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)]); + goto out; + } + if (check_ctx_reg(env, ®[i + 1], i + 1)) + goto out; + continue; + } } - bpf_log(log, "Unrecognized argument type %s\n", - btf_kind_str[BTF_INFO_KIND(t->info)]); + bpf_log(log, "Unrecognized arg#%d type %s\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)]); goto out; } return 0; out: - /* LLVM optimizations can remove arguments from static functions. */ - bpf_log(log, - "Type info disagrees with actual arguments due to compiler optimizations\n"); + /* Compiler optimizations can remove arguments from static functions + * or mismatched type can be passed into a global function. + * In such cases mark the function as unreliable from BTF point of view. + */ prog->aux->func_info_aux[subprog].unreliable = true; + return -EINVAL; +} + +/* Convert BTF of a function into bpf_reg_state if possible + * Returns: + * EFAULT - there is a verifier bug. Abort verification. + * EINVAL - cannot convert BTF. + * 0 - Successfully converted BTF into bpf_reg_state + * (either PTR_TO_CTX or SCALAR_VALUE). + */ +int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, + struct bpf_reg_state *reg) +{ + struct bpf_verifier_log *log = &env->log; + struct bpf_prog *prog = env->prog; + enum bpf_prog_type prog_type = prog->type; + struct btf *btf = prog->aux->btf; + const struct btf_param *args; + const struct btf_type *t; + u32 i, nargs, btf_id; + const char *tname; + + if (!prog->aux->func_info || + prog->aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL) { + bpf_log(log, "Verifier bug\n"); + return -EFAULT; + } + + btf_id = prog->aux->func_info[subprog].type_id; + if (!btf_id) { + bpf_log(log, "Global functions need valid BTF\n"); + return -EFAULT; + } + + t = btf_type_by_id(btf, btf_id); + if (!t || !btf_type_is_func(t)) { + /* These checks were already done by the verifier while loading + * struct bpf_func_info + */ + bpf_log(log, "BTF of func#%d doesn't point to KIND_FUNC\n", + subprog); + return -EFAULT; + } + tname = btf_name_by_offset(btf, t->name_off); + + if (log->level & BPF_LOG_LEVEL) + bpf_log(log, "Validating %s() func#%d...\n", + tname, subprog); + + if (prog->aux->func_info_aux[subprog].unreliable) { + bpf_log(log, "Verifier bug in function %s()\n", tname); + return -EFAULT; + } + if (prog_type == BPF_PROG_TYPE_EXT) + prog_type = prog->aux->linked_prog->type; + + t = btf_type_by_id(btf, t->type); + if (!t || !btf_type_is_func_proto(t)) { + bpf_log(log, "Invalid type of function %s()\n", tname); + return -EFAULT; + } + args = (const struct btf_param *)(t + 1); + nargs = btf_type_vlen(t); + if (nargs > 5) { + bpf_log(log, "Global function %s() with %d > 5 args. Buggy compiler.\n", + tname, nargs); + return -EINVAL; + } + /* check that function returns int */ + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (!btf_type_is_int(t) && !btf_type_is_enum(t)) { + bpf_log(log, + "Global function %s() doesn't return scalar. Only those are supported.\n", + tname); + return -EINVAL; + } + /* Convert BTF function arguments into verifier types. + * Only PTR_TO_CTX and SCALAR are supported atm. + */ + for (i = 0; i < nargs; i++) { + t = btf_type_by_id(btf, args[i].type); + while (btf_type_is_modifier(t)) + t = btf_type_by_id(btf, t->type); + if (btf_type_is_int(t) || btf_type_is_enum(t)) { + reg[i + 1].type = SCALAR_VALUE; + continue; + } + if (btf_type_is_ptr(t) && + btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + reg[i + 1].type = PTR_TO_CTX; + continue; + } + bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", + i, btf_kind_str[BTF_INFO_KIND(t->info)], tname); + return -EINVAL; + } return 0; } diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 9e43b72eb619..9a500fadbef5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -106,8 +106,7 @@ static u32 prog_list_length(struct list_head *head) * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, - enum bpf_attach_type type, - u32 new_flags) + enum bpf_attach_type type) { struct cgroup *p; @@ -290,31 +289,34 @@ cleanup: * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach + * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * * Must be called with cgroup_mutex held. */ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_prog *replace_prog, enum bpf_attach_type type, u32 flags) { + u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE], *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {NULL}; + struct bpf_prog_list *pl, *replace_pl = NULL; enum bpf_cgroup_storage_type stype; - struct bpf_prog_list *pl; - bool pl_was_allocated; int err; - if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || + ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; - if (!hierarchy_allows_attach(cgrp, type, flags)) + if (!hierarchy_allows_attach(cgrp, type)) return -EPERM; - if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + if (!list_empty(progs) && cgrp->bpf.flags[type] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none @@ -324,6 +326,21 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) { + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + if (pl->prog == replace_prog) + replace_pl = pl; + } + if ((flags & BPF_F_REPLACE) && !replace_pl) + /* prog to replace not found for cgroup */ + return -ENOENT; + } else if (!list_empty(progs)) { + replace_pl = list_first_entry(progs, typeof(*pl), node); + } + for_each_cgroup_storage_type(stype) { storage[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storage[stype])) { @@ -334,53 +351,28 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, } } - if (flags & BPF_F_ALLOW_MULTI) { - list_for_each_entry(pl, progs, node) { - if (pl->prog == prog) { - /* disallow attaching the same prog twice */ - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -EINVAL; - } + if (replace_pl) { + pl = replace_pl; + old_prog = pl->prog; + for_each_cgroup_storage_type(stype) { + old_storage[stype] = pl->storage[stype]; + bpf_cgroup_storage_unlink(old_storage[stype]); } - + } else { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); return -ENOMEM; } - - pl_was_allocated = true; - pl->prog = prog; - 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) { - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -ENOMEM; - } - pl_was_allocated = true; - list_add_tail(&pl->node, progs); - } else { - pl = list_first_entry(progs, typeof(*pl), node); - old_prog = pl->prog; - 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; - for_each_cgroup_storage_type(stype) - pl->storage[stype] = storage[stype]; } - cgrp->bpf.flags[type] = flags; + pl->prog = prog; + for_each_cgroup_storage_type(stype) + pl->storage[stype] = storage[stype]; + + cgrp->bpf.flags[type] = saved_flags; err = update_effective_progs(cgrp, type); if (err) @@ -408,7 +400,7 @@ cleanup: pl->storage[stype] = old_storage[stype]; bpf_cgroup_storage_link(old_storage[stype], cgrp, type); } - if (pl_was_allocated) { + if (!replace_pl) { list_del(&pl->node); kfree(pl); } @@ -546,6 +538,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { + struct bpf_prog *replace_prog = NULL; struct cgroup *cgrp; int ret; @@ -553,8 +546,20 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, if (IS_ERR(cgrp)) return PTR_ERR(cgrp); - ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + if ((attr->attach_flags & BPF_F_ALLOW_MULTI) && + (attr->attach_flags & BPF_F_REPLACE)) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype); + if (IS_ERR(replace_prog)) { + cgroup_put(cgrp); + return PTR_ERR(replace_prog); + } + } + + ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type, attr->attach_flags); + + if (replace_prog) + bpf_prog_put(replace_prog); cgroup_put(cgrp); return ret; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index af6b738cf435..973a20d49749 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -222,8 +222,6 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, u32 pages, delta; int ret; - BUG_ON(fp_old == NULL); - size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) @@ -520,9 +518,9 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) #ifdef CONFIG_BPF_JIT /* All BPF JIT sysctl knobs here. */ -int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON); +int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); +int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; -int bpf_jit_kallsyms __read_mostly; long bpf_jit_limit __read_mostly; static __always_inline void @@ -2139,6 +2137,7 @@ 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_spin_lock_proto __weak; const struct bpf_func_proto bpf_spin_unlock_proto __weak; +const struct bpf_func_proto bpf_jiffies64_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; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index ef49e17ae47c..70f71b154fa5 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -72,17 +72,18 @@ struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ struct bpf_cpu_map_entry **cpu_map; - struct list_head __percpu *flush_list; }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx); +static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list); + +static int bq_flush_to_queue(struct xdp_bulk_queue *bq); static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { struct bpf_cpu_map *cmap; int err = -ENOMEM; - int ret, cpu; u64 cost; + int ret; if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -106,7 +107,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - cost += sizeof(struct list_head) * num_possible_cpus(); /* Notice returns -EPERM on if map size is larger than memlock limit */ ret = bpf_map_charge_init(&cmap->map.memory, cost); @@ -115,23 +115,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) goto free_cmap; } - cmap->flush_list = alloc_percpu(struct list_head); - if (!cmap->flush_list) - goto free_charge; - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(cmap->flush_list, cpu)); - /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), cmap->map.numa_node); if (!cmap->cpu_map) - goto free_percpu; + goto free_charge; return &cmap->map; -free_percpu: - free_percpu(cmap->flush_list); free_charge: bpf_map_charge_finish(&cmap->map.memory); free_cmap: @@ -399,22 +390,14 @@ free_rcu: static void __cpu_map_entry_free(struct rcu_head *rcu) { struct bpf_cpu_map_entry *rcpu; - int cpu; /* This cpu_map_entry have been disconnected from map and one - * RCU graze-period have elapsed. Thus, XDP cannot queue any + * RCU grace-period have elapsed. Thus, XDP cannot queue any * new packets and cannot change/set flush_needed that can * find this entry. */ rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); - /* Flush remaining packets in percpu bulkq */ - for_each_online_cpu(cpu) { - struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); - - /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(bq, false); - } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ put_cpu_map_entry(rcpu); @@ -436,7 +419,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) * percpu bulkq to queue. Due to caller map_delete_elem() disable * preemption, cannot call kthread_stop() to make sure queue is empty. * Instead a work_queue is started for stopping kthread, - * cpu_map_kthread_stop, which waits for an RCU graze period before + * cpu_map_kthread_stop, which waits for an RCU grace period before * stopping kthread, emptying the queue. */ static void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, @@ -507,7 +490,6 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, static void cpu_map_free(struct bpf_map *map) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - int cpu; u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, @@ -522,18 +504,6 @@ static void cpu_map_free(struct bpf_map *map) bpf_clear_redirect_map(map); synchronize_rcu(); - /* To ensure all pending flush operations have completed wait for flush - * list be empty on _all_ cpus. Because the above synchronize_rcu() - * ensures the map is disconnected from the program we can assume no new - * items will be added to the list. - */ - for_each_online_cpu(cpu) { - struct list_head *flush_list = per_cpu_ptr(cmap->flush_list, cpu); - - while (!list_empty(flush_list)) - cond_resched(); - } - /* For cpu_map the remote CPUs can still be using the entries * (struct bpf_cpu_map_entry). */ @@ -544,10 +514,9 @@ static void cpu_map_free(struct bpf_map *map) if (!rcpu) continue; - /* bq flush and cleanup happens after RCU graze-period */ + /* bq flush and cleanup happens after RCU grace-period */ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ } - free_percpu(cmap->flush_list); bpf_map_area_free(cmap->cpu_map); kfree(cmap); } @@ -599,7 +568,7 @@ const struct bpf_map_ops cpu_map_ops = { .map_check_btf = map_check_no_btf, }; -static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) +static int bq_flush_to_queue(struct xdp_bulk_queue *bq) { struct bpf_cpu_map_entry *rcpu = bq->obj; unsigned int processed = 0, drops = 0; @@ -620,10 +589,7 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - if (likely(in_napi_ctx)) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); + xdp_return_frame_rx_napi(xdpf); } processed++; } @@ -642,11 +608,11 @@ static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) */ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct list_head *flush_list = this_cpu_ptr(rcpu->cmap->flush_list); + struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(bq, true); + bq_flush_to_queue(bq); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver @@ -681,16 +647,26 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, return 0; } -void __cpu_map_flush(struct bpf_map *map) +void __cpu_map_flush(void) { - struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - struct list_head *flush_list = this_cpu_ptr(cmap->flush_list); + struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list); struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { - bq_flush_to_queue(bq, true); + bq_flush_to_queue(bq); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(bq->obj->kthread); } } + +static int __init cpu_map_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu)); + return 0; +} + +subsys_initcall(cpu_map_init); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 3d3d61b5985b..58bdca5d978a 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -53,13 +53,11 @@ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) #define DEV_MAP_BULK_SIZE 16 -struct bpf_dtab_netdev; - -struct xdp_bulk_queue { +struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; struct list_head flush_node; + struct net_device *dev; struct net_device *dev_rx; - struct bpf_dtab_netdev *obj; unsigned int count; }; @@ -67,15 +65,13 @@ struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ struct hlist_node index_hlist; struct bpf_dtab *dtab; - struct xdp_bulk_queue __percpu *bulkq; struct rcu_head rcu; - unsigned int idx; /* keep track of map index for tracepoint */ + unsigned int idx; }; struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev **netdev_map; /* DEVMAP type only */ - struct list_head __percpu *flush_list; struct list_head list; /* these are only used for DEVMAP_HASH type maps */ @@ -85,6 +81,7 @@ struct bpf_dtab { u32 n_buckets; }; +static DEFINE_PER_CPU(struct list_head, dev_flush_list); static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); @@ -109,8 +106,8 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { - int err, cpu; - u64 cost; + u64 cost = 0; + int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -125,9 +122,6 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) bpf_map_init_from_attr(&dtab->map, attr); - /* make sure page count doesn't overflow */ - cost = (u64) sizeof(struct list_head) * num_possible_cpus(); - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); @@ -143,17 +137,10 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (err) return -EINVAL; - dtab->flush_list = alloc_percpu(struct list_head); - if (!dtab->flush_list) - goto free_charge; - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu)); - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets); if (!dtab->dev_index_head) - goto free_percpu; + goto free_charge; spin_lock_init(&dtab->index_lock); } else { @@ -161,13 +148,11 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_percpu; + goto free_charge; } return 0; -free_percpu: - free_percpu(dtab->flush_list); free_charge: bpf_map_charge_finish(&dtab->map.memory); return -ENOMEM; @@ -201,14 +186,16 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - int i, cpu; + int i; /* 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. The rcu critical section only guarantees - * no further reads against netdev_map. It does __not__ ensure pending - * flush operations (if any) are complete. + * disconnected from events. The following synchronize_rcu() guarantees + * both rcu read critical sections complete and waits for + * preempt-disable regions (NAPI being the relevant context here) so we + * are certain there will be no further reads against the netdev_map and + * all flush operations are complete. Flush operations can only be done + * from NAPI context for this reason. */ spin_lock(&dev_map_lock); @@ -221,18 +208,6 @@ static void dev_map_free(struct bpf_map *map) /* Make sure prior __dev_map_entry_free() have completed. */ rcu_barrier(); - /* To ensure all pending flush operations have completed wait for flush - * list to empty on _all_ cpus. - * Because the above synchronize_rcu() ensures the map is disconnected - * from the program we can assume no new items will be added. - */ - for_each_online_cpu(cpu) { - struct list_head *flush_list = per_cpu_ptr(dtab->flush_list, cpu); - - while (!list_empty(flush_list)) - cond_resched(); - } - if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { for (i = 0; i < dtab->n_buckets; i++) { struct bpf_dtab_netdev *dev; @@ -243,7 +218,6 @@ static void dev_map_free(struct bpf_map *map) hlist_for_each_entry_safe(dev, next, head, index_hlist) { hlist_del_rcu(&dev->index_hlist); - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -258,7 +232,6 @@ static void dev_map_free(struct bpf_map *map) if (!dev) continue; - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -266,7 +239,6 @@ static void dev_map_free(struct bpf_map *map) bpf_map_area_free(dtab->netdev_map); } - free_percpu(dtab->flush_list); kfree(dtab); } @@ -293,7 +265,8 @@ struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) struct hlist_head *head = dev_map_index_hash(dtab, key); struct bpf_dtab_netdev *dev; - hlist_for_each_entry_rcu(dev, head, index_hlist) + hlist_for_each_entry_rcu(dev, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) if (dev->idx == key) return dev; @@ -345,11 +318,9 @@ static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, return -ENOENT; } -static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, - bool in_napi_ctx) +static int bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) { - struct bpf_dtab_netdev *obj = bq->obj; - struct net_device *dev = obj->dev; + struct net_device *dev = bq->dev; int sent = 0, drops = 0, err = 0; int i; @@ -372,8 +343,7 @@ static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, out: bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->idx, - sent, drops, bq->dev_rx, dev, err); + trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, drops, err); bq->dev_rx = NULL; __list_del_clearprev(&bq->flush_node); return 0; @@ -384,33 +354,29 @@ error: for (i = 0; i < bq->count; i++) { struct xdp_frame *xdpf = bq->q[i]; - /* RX path under NAPI protection, can return frames faster */ - if (likely(in_napi_ctx)) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); + xdp_return_frame_rx_napi(xdpf); drops++; } goto out; } -/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled +/* __dev_flush is called from xdp_do_flush() which _must_ be signaled * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the * net device can be torn down. On devmap tear down we ensure the flush list * is empty before completing to ensure all flush operations have completed. + * When drivers update the bpf program they may need to ensure any flush ops + * are also complete. Using synchronize_rcu or call_rcu will suffice for this + * because both wait for napi context to exit. */ -void __dev_map_flush(struct bpf_map *map) +void __dev_flush(void) { - struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct list_head *flush_list = this_cpu_ptr(dtab->flush_list); - struct xdp_bulk_queue *bq, *tmp; + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct xdp_dev_bulk_queue *bq, *tmp; - rcu_read_lock(); list_for_each_entry_safe(bq, tmp, flush_list, flush_node) - bq_xmit_all(bq, XDP_XMIT_FLUSH, true); - rcu_read_unlock(); + bq_xmit_all(bq, XDP_XMIT_FLUSH); } /* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or @@ -432,15 +398,14 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, +static int bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) - { - struct list_head *flush_list = this_cpu_ptr(obj->dtab->flush_list); - struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + struct list_head *flush_list = this_cpu_ptr(&dev_flush_list); + struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(bq, 0, true); + bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -457,10 +422,9 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, return 0; } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, - struct net_device *dev_rx) +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) { - struct net_device *dev = dst->dev; struct xdp_frame *xdpf; int err; @@ -475,7 +439,21 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, if (unlikely(!xdpf)) return -EOVERFLOW; - return bq_enqueue(dst, xdpf, dev_rx); + return bq_enqueue(dev, xdpf, dev_rx); +} + +int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + return __xdp_enqueue(dev, xdp, dev_rx); +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + + return __xdp_enqueue(dev, xdp, dev_rx); } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, @@ -509,28 +487,11 @@ static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) return dev ? &dev->ifindex : NULL; } -static void dev_map_flush_old(struct bpf_dtab_netdev *dev) -{ - if (dev->dev->netdev_ops->ndo_xdp_xmit) { - struct xdp_bulk_queue *bq; - int cpu; - - rcu_read_lock(); - for_each_online_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(bq, XDP_XMIT_FLUSH, false); - } - rcu_read_unlock(); - } -} - static void __dev_map_entry_free(struct rcu_head *rcu) { struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); - dev_map_flush_old(dev); - free_percpu(dev->bulkq); dev_put(dev->dev); kfree(dev); } @@ -545,12 +506,11 @@ static int dev_map_delete_elem(struct bpf_map *map, void *key) return -EINVAL; /* Use call_rcu() here to ensure any rcu critical sections have - * completed, but this does not guarantee a flush has happened - * yet. Because driver side rcu_read_lock/unlock only protects the - * running XDP program. However, for pending flush operations the - * dev and ctx are stored in another per cpu map. And additionally, - * the driver tear down ensures all soft irqs are complete before - * removing the net device in the case of dev_put equals zero. + * completed as well as any flush operations because call_rcu + * will wait for preempt-disable region to complete, NAPI in this + * context. And additionally, the driver tear down ensures all + * soft irqs are complete before removing the net device in the + * case of dev_put equals zero. */ old_dev = xchg(&dtab->netdev_map[k], NULL); if (old_dev) @@ -585,30 +545,15 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, u32 ifindex, unsigned int idx) { - gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev; - struct xdp_bulk_queue *bq; - int cpu; - dev = kmalloc_node(sizeof(*dev), gfp, dtab->map.numa_node); + dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, + dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return ERR_PTR(-ENOMEM); - } - - for_each_possible_cpu(cpu) { - bq = per_cpu_ptr(dev->bulkq, cpu); - bq->obj = dev; - } - dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { - free_percpu(dev->bulkq); kfree(dev); return ERR_PTR(-EINVAL); } @@ -768,9 +713,23 @@ static int dev_map_notification(struct notifier_block *notifier, { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; - int i; + int i, cpu; switch (event) { + case NETDEV_REGISTER: + if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) + break; + + /* will be freed in free_netdev() */ + netdev->xdp_bulkq = + __alloc_percpu_gfp(sizeof(struct xdp_dev_bulk_queue), + sizeof(void *), GFP_ATOMIC); + if (!netdev->xdp_bulkq) + return NOTIFY_BAD; + + for_each_possible_cpu(cpu) + per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete @@ -810,10 +769,15 @@ static struct notifier_block dev_map_notifier = { static int __init dev_map_init(void) { + int cpu; + /* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */ BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu)); return 0; } diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c new file mode 100644 index 000000000000..b3e5b214fed8 --- /dev/null +++ b/kernel/bpf/dispatcher.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2019 Intel Corporation. */ + +#include <linux/hash.h> +#include <linux/bpf.h> +#include <linux/filter.h> + +/* The BPF dispatcher is a multiway branch code generator. The + * dispatcher is a mechanism to avoid the performance penalty of an + * indirect call, which is expensive when retpolines are enabled. A + * dispatch client registers a BPF program into the dispatcher, and if + * there is available room in the dispatcher a direct call to the BPF + * program will be generated. All calls to the BPF programs called via + * the dispatcher will then be a direct call, instead of an + * indirect. The dispatcher hijacks a trampoline function it via the + * __fentry__ of the trampoline. The trampoline function has the + * following signature: + * + * unsigned int trampoline(const void *ctx, const struct bpf_insn *insnsi, + * unsigned int (*bpf_func)(const void *, + * const struct bpf_insn *)); + */ + +static struct bpf_dispatcher_prog *bpf_dispatcher_find_prog( + struct bpf_dispatcher *d, struct bpf_prog *prog) +{ + int i; + + for (i = 0; i < BPF_DISPATCHER_MAX; i++) { + if (prog == d->progs[i].prog) + return &d->progs[i]; + } + return NULL; +} + +static struct bpf_dispatcher_prog *bpf_dispatcher_find_free( + struct bpf_dispatcher *d) +{ + return bpf_dispatcher_find_prog(d, NULL); +} + +static bool bpf_dispatcher_add_prog(struct bpf_dispatcher *d, + struct bpf_prog *prog) +{ + struct bpf_dispatcher_prog *entry; + + if (!prog) + return false; + + entry = bpf_dispatcher_find_prog(d, prog); + if (entry) { + refcount_inc(&entry->users); + return false; + } + + entry = bpf_dispatcher_find_free(d); + if (!entry) + return false; + + bpf_prog_inc(prog); + entry->prog = prog; + refcount_set(&entry->users, 1); + d->num_progs++; + return true; +} + +static bool bpf_dispatcher_remove_prog(struct bpf_dispatcher *d, + struct bpf_prog *prog) +{ + struct bpf_dispatcher_prog *entry; + + if (!prog) + return false; + + entry = bpf_dispatcher_find_prog(d, prog); + if (!entry) + return false; + + if (refcount_dec_and_test(&entry->users)) { + entry->prog = NULL; + bpf_prog_put(prog); + d->num_progs--; + return true; + } + return false; +} + +int __weak arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs) +{ + return -ENOTSUPP; +} + +static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image) +{ + s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0]; + int i; + + for (i = 0; i < BPF_DISPATCHER_MAX; i++) { + if (d->progs[i].prog) + *ipsp++ = (s64)(uintptr_t)d->progs[i].prog->bpf_func; + } + return arch_prepare_bpf_dispatcher(image, &ips[0], d->num_progs); +} + +static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) +{ + void *old, *new; + u32 noff; + int err; + + if (!prev_num_progs) { + old = NULL; + noff = 0; + } else { + old = d->image + d->image_off; + noff = d->image_off ^ (BPF_IMAGE_SIZE / 2); + } + + new = d->num_progs ? d->image + noff : NULL; + if (new) { + if (bpf_dispatcher_prepare(d, new)) + return; + } + + err = bpf_arch_text_poke(d->func, BPF_MOD_JUMP, old, new); + if (err || !new) + return; + + d->image_off = noff; +} + +void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, + struct bpf_prog *to) +{ + bool changed = false; + int prev_num_progs; + + if (from == to) + return; + + mutex_lock(&d->mutex); + if (!d->image) { + d->image = bpf_image_alloc(); + if (!d->image) + goto out; + } + + prev_num_progs = d->num_progs; + changed |= bpf_dispatcher_remove_prog(d, from); + changed |= bpf_dispatcher_add_prog(d, to); + + if (!changed) + goto out; + + bpf_dispatcher_update(d, prev_num_progs); +out: + mutex_unlock(&d->mutex); +} diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 22066a62c8c9..a1468e3f5af2 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -17,6 +17,16 @@ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) +#define BATCH_OPS(_name) \ + .map_lookup_batch = \ + _name##_map_lookup_batch, \ + .map_lookup_and_delete_batch = \ + _name##_map_lookup_and_delete_batch, \ + .map_update_batch = \ + generic_map_update_batch, \ + .map_delete_batch = \ + generic_map_delete_batch + struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; @@ -46,6 +56,7 @@ struct htab_elem { union { struct bpf_htab *htab; struct pcpu_freelist_node fnode; + struct htab_elem *batch_flink; }; }; }; @@ -116,6 +127,17 @@ free_elems: bpf_map_area_free(htab->elems); } +/* The LRU list has a lock (lru_lock). Each htab bucket has a lock + * (bucket_lock). If both locks need to be acquired together, the lock + * order is always lru_lock -> bucket_lock and this only happens in + * bpf_lru_list.c logic. For example, certain code path of + * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(), + * will acquire lru_lock first followed by acquiring bucket_lock. + * + * In hashtab.c, to avoid deadlock, lock acquisition of + * bucket_lock followed by lru_lock is not allowed. In such cases, + * bucket_lock needs to be released first before acquiring lru_lock. + */ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, u32 hash) { @@ -1232,6 +1254,292 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static int +__htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr, + bool do_delete, bool is_lru_map, + bool is_percpu) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + u32 bucket_cnt, total, key_size, value_size, roundup_key_size; + void *keys = NULL, *values = NULL, *value, *dst_key, *dst_val; + void __user *uvalues = u64_to_user_ptr(attr->batch.values); + void __user *ukeys = u64_to_user_ptr(attr->batch.keys); + void *ubatch = u64_to_user_ptr(attr->batch.in_batch); + u32 batch, max_count, size, bucket_size; + struct htab_elem *node_to_free = NULL; + u64 elem_map_flags, map_flags; + struct hlist_nulls_head *head; + struct hlist_nulls_node *n; + unsigned long flags = 0; + bool locked = false; + struct htab_elem *l; + struct bucket *b; + int ret = 0; + + elem_map_flags = attr->batch.elem_flags; + if ((elem_map_flags & ~BPF_F_LOCK) || + ((elem_map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return -EINVAL; + + map_flags = attr->batch.flags; + if (map_flags) + return -EINVAL; + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + batch = 0; + if (ubatch && copy_from_user(&batch, ubatch, sizeof(batch))) + return -EFAULT; + + if (batch >= htab->n_buckets) + return -ENOENT; + + key_size = htab->map.key_size; + roundup_key_size = round_up(htab->map.key_size, 8); + value_size = htab->map.value_size; + size = round_up(value_size, 8); + if (is_percpu) + value_size = size * num_possible_cpus(); + total = 0; + /* while experimenting with hash tables with sizes ranging from 10 to + * 1000, it was observed that a bucket can have upto 5 entries. + */ + bucket_size = 5; + +alloc: + /* We cannot do copy_from_user or copy_to_user inside + * the rcu_read_lock. Allocate enough space here. + */ + keys = kvmalloc(key_size * bucket_size, GFP_USER | __GFP_NOWARN); + values = kvmalloc(value_size * bucket_size, GFP_USER | __GFP_NOWARN); + if (!keys || !values) { + ret = -ENOMEM; + goto after_loop; + } + +again: + preempt_disable(); + this_cpu_inc(bpf_prog_active); + rcu_read_lock(); +again_nocopy: + dst_key = keys; + dst_val = values; + b = &htab->buckets[batch]; + head = &b->head; + /* do not grab the lock unless need it (bucket_cnt > 0). */ + if (locked) + raw_spin_lock_irqsave(&b->lock, flags); + + bucket_cnt = 0; + hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) + bucket_cnt++; + + if (bucket_cnt && !locked) { + locked = true; + goto again_nocopy; + } + + if (bucket_cnt > (max_count - total)) { + if (total == 0) + ret = -ENOSPC; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + goto after_loop; + } + + if (bucket_cnt > bucket_size) { + bucket_size = bucket_cnt; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ + raw_spin_unlock_irqrestore(&b->lock, flags); + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + kvfree(keys); + kvfree(values); + goto alloc; + } + + /* Next block is only safe to run if you have grabbed the lock */ + if (!locked) + goto next_batch; + + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { + memcpy(dst_key, l->key, key_size); + + if (is_percpu) { + int off = 0, cpu; + void __percpu *pptr; + + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + bpf_long_memcpy(dst_val + off, + per_cpu_ptr(pptr, cpu), size); + off += size; + } + } else { + value = l->key + roundup_key_size; + if (elem_map_flags & BPF_F_LOCK) + copy_map_value_locked(map, dst_val, value, + true); + else + copy_map_value(map, dst_val, value); + check_and_init_map_lock(map, dst_val); + } + if (do_delete) { + hlist_nulls_del_rcu(&l->hash_node); + + /* bpf_lru_push_free() will acquire lru_lock, which + * may cause deadlock. See comments in function + * prealloc_lru_pop(). Let us do bpf_lru_push_free() + * after releasing the bucket lock. + */ + if (is_lru_map) { + l->batch_flink = node_to_free; + node_to_free = l; + } else { + free_htab_elem(htab, l); + } + } + dst_key += key_size; + dst_val += value_size; + } + + raw_spin_unlock_irqrestore(&b->lock, flags); + locked = false; + + while (node_to_free) { + l = node_to_free; + node_to_free = node_to_free->batch_flink; + bpf_lru_push_free(&htab->lru, &l->lru_node); + } + +next_batch: + /* If we are not copying data, we can go to next bucket and avoid + * unlocking the rcu. + */ + if (!bucket_cnt && (batch + 1 < htab->n_buckets)) { + batch++; + goto again_nocopy; + } + + rcu_read_unlock(); + this_cpu_dec(bpf_prog_active); + preempt_enable(); + if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, + key_size * bucket_cnt) || + copy_to_user(uvalues + total * value_size, values, + value_size * bucket_cnt))) { + ret = -EFAULT; + goto after_loop; + } + + total += bucket_cnt; + batch++; + if (batch >= htab->n_buckets) { + ret = -ENOENT; + goto after_loop; + } + goto again; + +after_loop: + if (ret == -EFAULT) + goto out; + + /* copy # of entries and next batch */ + ubatch = u64_to_user_ptr(attr->batch.out_batch); + if (copy_to_user(ubatch, &batch, sizeof(batch)) || + put_user(total, &uattr->batch.count)) + ret = -EFAULT; + +out: + kvfree(keys); + kvfree(values); + return ret; +} + +static int +htab_percpu_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, true); +} + +static int +htab_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, true); +} + +static int +htab_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + false, false); +} + +static int +htab_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + false, false); +} + +static int +htab_lru_percpu_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, true); +} + +static int +htab_lru_percpu_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, true); +} + +static int +htab_lru_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, false, + true, false); +} + +static int +htab_lru_map_lookup_and_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return __htab_map_lookup_and_delete_batch(map, attr, uattr, true, + true, false); +} + const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1242,6 +1550,7 @@ const struct bpf_map_ops htab_map_ops = { .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab), }; const struct bpf_map_ops htab_lru_map_ops = { @@ -1255,6 +1564,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, + BATCH_OPS(htab_lru), }; /* Called from eBPF program */ @@ -1368,6 +1678,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .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, + BATCH_OPS(htab_percpu), }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1379,6 +1690,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .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, + BATCH_OPS(htab_lru_percpu), }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index cada974c9f4e..d8b7b110a1c5 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -11,6 +11,7 @@ #include <linux/uidgid.h> #include <linux/filter.h> #include <linux/ctype.h> +#include <linux/jiffies.h> #include "../../lib/kstrtox.h" @@ -312,6 +313,17 @@ void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, preempt_enable(); } +BPF_CALL_0(bpf_jiffies64) +{ + return get_jiffies_64(); +} + +const struct bpf_func_proto bpf_jiffies64_proto = { + .func = bpf_jiffies64, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index ecf42bec38c0..5e40e7fccc21 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -196,6 +196,7 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) void *key = map_iter(m)->key; void *prev_key; + (*pos)++; if (map_iter(m)->done) return NULL; @@ -208,8 +209,6 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) map_iter(m)->done = true; return NULL; } - - ++(*pos); return key; } @@ -380,7 +379,7 @@ static const struct inode_operations bpf_dir_iops = { .unlink = simple_unlink, }; -static int bpf_obj_do_pin(const struct filename *pathname, void *raw, +static int bpf_obj_do_pin(const char __user *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; @@ -389,7 +388,7 @@ static int bpf_obj_do_pin(const struct filename *pathname, void *raw, umode_t mode; int ret; - dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0); + dentry = user_path_create(AT_FDCWD, pathname, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -422,30 +421,22 @@ out: int bpf_obj_pin_user(u32 ufd, const char __user *pathname) { - struct filename *pname; enum bpf_type type; void *raw; int ret; - pname = getname(pathname); - if (IS_ERR(pname)) - return PTR_ERR(pname); - raw = bpf_fd_probe_obj(ufd, &type); - if (IS_ERR(raw)) { - ret = PTR_ERR(raw); - goto out; - } + if (IS_ERR(raw)) + return PTR_ERR(raw); - ret = bpf_obj_do_pin(pname, raw, type); + ret = bpf_obj_do_pin(pathname, raw, type); if (ret != 0) bpf_any_put(raw, type); -out: - putname(pname); + return ret; } -static void *bpf_obj_do_get(const struct filename *pathname, +static void *bpf_obj_do_get(const char __user *pathname, enum bpf_type *type, int flags) { struct inode *inode; @@ -453,7 +444,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, void *raw; int ret; - ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path); + ret = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); @@ -480,36 +471,27 @@ out: int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; - struct filename *pname; - int ret = -ENOENT; int f_flags; void *raw; + int ret; f_flags = bpf_get_file_flag(flags); if (f_flags < 0) return f_flags; - pname = getname(pathname); - if (IS_ERR(pname)) - return PTR_ERR(pname); - - raw = bpf_obj_do_get(pname, &type, f_flags); - if (IS_ERR(raw)) { - ret = PTR_ERR(raw); - goto out; - } + raw = bpf_obj_do_get(pathname, &type, f_flags); + if (IS_ERR(raw)) + return PTR_ERR(raw); if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else - goto out; + return -ENOENT; if (ret < 0) bpf_any_put(raw, type); -out: - putname(pname); return ret; } @@ -587,16 +569,11 @@ enum { OPT_MODE, }; -static const struct fs_parameter_spec bpf_param_specs[] = { +static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32oct ("mode", OPT_MODE), {} }; -static const struct fs_parameter_description bpf_fs_parameters = { - .name = "bpf", - .specs = bpf_param_specs, -}; - struct bpf_mount_opts { umode_t mode; }; @@ -607,7 +584,7 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) struct fs_parse_result result; int opt; - opt = fs_parse(fc, &bpf_fs_parameters, param, &result); + opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd @@ -683,7 +660,7 @@ static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, - .parameters = &bpf_fs_parameters, + .parameters = bpf_fs_parameters, .kill_sb = kill_litter_super, }; diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 5e9366b33f0f..b3c48d1533cb 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -22,7 +22,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) */ 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_PERCPU_CGROUP_STORAGE) { + inner_map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE || + inner_map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { fdput(f); return ERR_PTR(-ENOTSUPP); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 5b9da0954a27..bd09290e3648 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -302,14 +302,14 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct inode *ns_inode; struct path ns_path; char __user *uinsns; - void *res; + int res; u32 ulen; res = ns_get_path_cb(&ns_path, bpf_prog_offload_info_fill_ns, &args); - if (IS_ERR(res)) { + if (res) { if (!info->ifindex) return -ENODEV; - return PTR_ERR(res); + return res; } down_read(&bpf_devs_lock); @@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, ulen = info->jited_prog_len; info->jited_prog_len = aux->offload->jited_len; - if (info->jited_prog_len & ulen) { + if (info->jited_prog_len && ulen) { uinsns = u64_to_user_ptr(info->jited_prog_insns); ulen = min_t(u32, info->jited_prog_len, ulen); if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) { @@ -526,13 +526,13 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) }; struct inode *ns_inode; struct path ns_path; - void *res; + int res; res = ns_get_path_cb(&ns_path, bpf_map_offload_info_fill_ns, &args); - if (IS_ERR(res)) { + if (res) { if (!info->ifindex) return -ENODEV; - return PTR_ERR(res); + return res; } ns_inode = ns_path.dentry->d_inode; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index e3461ec59570..a91ad518c050 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,7 @@ #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> +#include <linux/audit.h> #include <uapi/linux/btf.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -128,6 +129,152 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static u32 bpf_map_value_size(struct bpf_map *map) +{ + 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_CGROUP_STORAGE) + return round_up(map->value_size, 8) * num_possible_cpus(); + else if (IS_FD_MAP(map)) + return sizeof(u32); + else + return map->value_size; +} + +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(); +} + +static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, + void *value, __u64 flags) +{ + int err; + + /* Need to create a kthread, thus must support schedule */ + if (bpf_map_is_dev_bound(map)) { + return bpf_map_offload_update_elem(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_SOCKHASH || + map->map_type == BPF_MAP_TYPE_SOCKMAP || + map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + return map->ops->map_update_elem(map, key, value, flags); + } else if (IS_FD_PROG_ARRAY(map)) { + return bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + } + + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from + * inside bpf map update or delete otherwise deadlocks are possible + */ + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + err = bpf_percpu_hash_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { + err = bpf_percpu_array_update(map, key, value, flags); + } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { + err = bpf_percpu_cgroup_storage_update(map, key, value, + flags); + } else if (IS_FD_ARRAY(map)) { + rcu_read_lock(); + err = bpf_fd_array_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { + rcu_read_lock(); + err = bpf_fd_htab_map_update_elem(map, f.file, key, value, + flags); + rcu_read_unlock(); + } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { + /* rcu_read_lock() is not needed */ + err = bpf_fd_reuseport_array_update_elem(map, key, value, + 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, flags); + } else { + rcu_read_lock(); + err = map->ops->map_update_elem(map, key, value, flags); + rcu_read_unlock(); + } + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + +static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, + __u64 flags) +{ + void *ptr; + int err; + + if (bpf_map_is_dev_bound(map)) + return bpf_map_offload_lookup_elem(map, key, value); + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + 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) || IS_FD_PROG_ARRAY(map)) { + err = bpf_fd_array_map_lookup_elem(map, key, value); + } else if (IS_FD_HASH(map)) { + 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 if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + /* struct_ops map requires directly updating "value" */ + err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); + } else { + rcu_read_lock(); + if (map->ops->map_lookup_elem_sys_only) + ptr = map->ops->map_lookup_elem_sys_only(map, key); + else + ptr = map->ops->map_lookup_elem(map, key); + if (IS_ERR(ptr)) { + err = PTR_ERR(ptr); + } else if (!ptr) { + err = -ENOENT; + } else { + err = 0; + if (flags & BPF_F_LOCK) + /* lock 'ptr' and copy everything but lock */ + copy_map_value_locked(map, value, ptr, true); + else + copy_map_value(map, value, ptr); + /* mask lock, since value wasn't zero inited */ + check_and_init_map_lock(map, value); + } + rcu_read_unlock(); + } + + this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + + return err; +} + static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -627,7 +774,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -641,6 +788,14 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + if (attr->btf_vmlinux_value_type_id) { + if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || + attr->btf_key_type_id || attr->btf_value_type_id) + return -EINVAL; + } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { + return -EINVAL; + } + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -663,32 +818,35 @@ static int map_create(union bpf_attr *attr) atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); - if (attr->btf_key_type_id || attr->btf_value_type_id) { + map->spin_lock_off = -EINVAL; + if (attr->btf_key_type_id || attr->btf_value_type_id || + /* Even the map's value is a kernel's struct, + * the bpf_prog.o must have BTF to begin with + * to figure out the corresponding kernel's + * counter part. Thus, attr->btf_fd has + * to be valid also. + */ + attr->btf_vmlinux_value_type_id) { struct btf *btf; - if (!attr->btf_value_type_id) { - err = -EINVAL; - goto free_map; - } - btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } + map->btf = btf; - err = map_check_btf(map, btf, attr->btf_key_type_id, - attr->btf_value_type_id); - if (err) { - btf_put(btf); - goto free_map; + if (attr->btf_value_type_id) { + err = map_check_btf(map, btf, attr->btf_key_type_id, + attr->btf_value_type_id); + if (err) + goto free_map; } - map->btf = btf; map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; - } else { - map->spin_lock_off = -EINVAL; + map->btf_vmlinux_value_type_id = + attr->btf_vmlinux_value_type_id; } err = security_bpf_map_alloc(map); @@ -815,7 +973,7 @@ static int map_lookup_elem(union bpf_attr *attr) void __user *uvalue = u64_to_user_ptr(attr->value); int ufd = attr->map_fd; struct bpf_map *map; - void *key, *value, *ptr; + void *key, *value; u32 value_size; struct fd f; int err; @@ -847,72 +1005,14 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - 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_CGROUP_STORAGE) - value_size = round_up(map->value_size, 8) * num_possible_cpus(); - else if (IS_FD_MAP(map)) - value_size = sizeof(u32); - else - value_size = map->value_size; + value_size = bpf_map_value_size(map); err = -ENOMEM; value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_lookup_elem(map, key, value); - goto done; - } - - preempt_disable(); - this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - 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) || IS_FD_PROG_ARRAY(map)) { - err = bpf_fd_array_map_lookup_elem(map, key, value); - } else if (IS_FD_HASH(map)) { - 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(); - if (map->ops->map_lookup_elem_sys_only) - ptr = map->ops->map_lookup_elem_sys_only(map, key); - else - ptr = map->ops->map_lookup_elem(map, key); - if (IS_ERR(ptr)) { - err = PTR_ERR(ptr); - } else if (!ptr) { - err = -ENOENT; - } else { - err = 0; - if (attr->flags & BPF_F_LOCK) - /* lock 'ptr' and copy everything but lock */ - copy_map_value_locked(map, value, ptr, true); - else - copy_map_value(map, value, ptr); - /* mask lock, since value wasn't zero inited */ - check_and_init_map_lock(map, value); - } - rcu_read_unlock(); - } - this_cpu_dec(bpf_prog_active); - preempt_enable(); - -done: + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -931,16 +1031,6 @@ 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 @@ -996,60 +1086,8 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; - /* Need to create a kthread, thus must support schedule */ - if (bpf_map_is_dev_bound(map)) { - err = bpf_map_offload_update_elem(map, key, value, attr->flags); - goto out; - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || - map->map_type == BPF_MAP_TYPE_SOCKHASH || - map->map_type == BPF_MAP_TYPE_SOCKMAP) { - err = map->ops->map_update_elem(map, key, value, attr->flags); - goto out; - } else if (IS_FD_PROG_ARRAY(map)) { - err = bpf_fd_array_map_update_elem(map, f.file, key, value, - attr->flags); - goto out; - } + err = bpf_map_update_value(map, f, key, value, attr->flags); - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); - if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - 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, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { - rcu_read_lock(); - err = bpf_fd_htab_map_update_elem(map, f.file, key, value, - attr->flags); - rcu_read_unlock(); - } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { - /* 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); - rcu_read_unlock(); - } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); - maybe_wait_bpf_programs(map); -out: free_value: kfree(value); free_key: @@ -1091,7 +1129,9 @@ static int map_delete_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; - } else if (IS_FD_PROG_ARRAY(map)) { + } else if (IS_FD_PROG_ARRAY(map) || + map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } @@ -1178,6 +1218,220 @@ err_put: return err; } +int generic_map_delete_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 cp, max_count; + int err = 0; + void *key; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + max_count = attr->batch.count; + if (!max_count) + return 0; + + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!key) + return -ENOMEM; + + for (cp = 0; cp < max_count; cp++) { + err = -EFAULT; + if (copy_from_user(key, keys + cp * map->key_size, + map->key_size)) + break; + + if (bpf_map_is_dev_bound(map)) { + err = bpf_map_offload_delete_elem(map, key); + break; + } + + preempt_disable(); + __this_cpu_inc(bpf_prog_active); + rcu_read_lock(); + err = map->ops->map_delete_elem(map, key); + rcu_read_unlock(); + __this_cpu_dec(bpf_prog_active); + preempt_enable(); + maybe_wait_bpf_programs(map); + if (err) + break; + } + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + + kfree(key); + return err; +} + +int generic_map_update_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + u32 value_size, cp, max_count; + int ufd = attr->map_fd; + void *key, *value; + struct fd f; + int err = 0; + + f = fdget(ufd); + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + return -EINVAL; + } + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + key = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!key) + return -ENOMEM; + + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) { + kfree(key); + return -ENOMEM; + } + + for (cp = 0; cp < max_count; cp++) { + err = -EFAULT; + if (copy_from_user(key, keys + cp * map->key_size, + map->key_size) || + copy_from_user(value, values + cp * value_size, value_size)) + break; + + err = bpf_map_update_value(map, f, key, value, + attr->batch.elem_flags); + + if (err) + break; + } + + if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) + err = -EFAULT; + + kfree(value); + kfree(key); + return err; +} + +#define MAP_LOOKUP_RETRIES 3 + +int generic_map_lookup_batch(struct bpf_map *map, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); + void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); + void __user *values = u64_to_user_ptr(attr->batch.values); + void __user *keys = u64_to_user_ptr(attr->batch.keys); + void *buf, *buf_prevkey, *prev_key, *key, *value; + int err, retry = MAP_LOOKUP_RETRIES; + u32 value_size, cp, max_count; + + if (attr->batch.elem_flags & ~BPF_F_LOCK) + return -EINVAL; + + if ((attr->batch.elem_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) + return -EINVAL; + + value_size = bpf_map_value_size(map); + + max_count = attr->batch.count; + if (!max_count) + return 0; + + if (put_user(0, &uattr->batch.count)) + return -EFAULT; + + buf_prevkey = kmalloc(map->key_size, GFP_USER | __GFP_NOWARN); + if (!buf_prevkey) + return -ENOMEM; + + buf = kmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); + if (!buf) { + kvfree(buf_prevkey); + return -ENOMEM; + } + + err = -EFAULT; + prev_key = NULL; + if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) + goto free_buf; + key = buf; + value = key + map->key_size; + if (ubatch) + prev_key = buf_prevkey; + + for (cp = 0; cp < max_count;) { + rcu_read_lock(); + err = map->ops->map_get_next_key(map, prev_key, key); + rcu_read_unlock(); + if (err) + break; + err = bpf_map_copy_value(map, key, value, + attr->batch.elem_flags); + + if (err == -ENOENT) { + if (retry) { + retry--; + continue; + } + err = -EINTR; + break; + } + + if (err) + goto free_buf; + + if (copy_to_user(keys + cp * map->key_size, key, + map->key_size)) { + err = -EFAULT; + goto free_buf; + } + if (copy_to_user(values + cp * value_size, value, value_size)) { + err = -EFAULT; + goto free_buf; + } + + if (!prev_key) + prev_key = buf_prevkey; + + swap(prev_key, key); + retry = MAP_LOOKUP_RETRIES; + cp++; + } + + if (err == -EFAULT) + goto free_buf; + + if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || + (cp && copy_to_user(uobatch, prev_key, map->key_size)))) + err = -EFAULT; + +free_buf: + kfree(buf_prevkey); + kfree(buf); + return err; +} + #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value static int map_lookup_and_delete_elem(union bpf_attr *attr) @@ -1306,6 +1560,36 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) return 0; } +enum bpf_audit { + BPF_AUDIT_LOAD, + BPF_AUDIT_UNLOAD, + BPF_AUDIT_MAX, +}; + +static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { + [BPF_AUDIT_LOAD] = "LOAD", + [BPF_AUDIT_UNLOAD] = "UNLOAD", +}; + +static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) +{ + struct audit_context *ctx = NULL; + struct audit_buffer *ab; + + if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) + return; + if (audit_enabled == AUDIT_OFF) + return; + if (op == BPF_AUDIT_LOAD) + ctx = audit_context(); + ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); + if (unlikely(!ab)) + return; + audit_log_format(ab, "prog-id=%u op=%s", + prog->aux->id, bpf_audit_str[op]); + audit_log_end(ab); +} + int __bpf_prog_charge(struct user_struct *user, u32 pages) { unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; @@ -1421,6 +1705,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic64_dec_and_test(&prog->aux->refcnt)) { perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); __bpf_prog_put_noref(prog, true); @@ -1640,17 +1925,24 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, u32 btf_id, u32 prog_fd) { - switch (prog_type) { - case BPF_PROG_TYPE_TRACING: + if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; - break; - default: - if (btf_id || prog_fd) + + switch (prog_type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_EXT: + break; + default: return -EINVAL; - break; + } } + if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + prog_type != BPF_PROG_TYPE_EXT) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { @@ -1691,6 +1983,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_EXT: + if (expected_attach_type) + return -EINVAL; + /* fallthrough */ default: return 0; } @@ -1830,6 +2126,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); + bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) @@ -1892,7 +2189,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog) int tr_fd, err; if (prog->expected_attach_type != BPF_TRACE_FENTRY && - prog->expected_attach_type != BPF_TRACE_FEXIT) { + prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } @@ -1959,12 +2257,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_EXT && prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { err = -EINVAL; goto out_put_prog; } - if (prog->type == BPF_PROG_TYPE_TRACING) { + if (prog->type == BPF_PROG_TYPE_TRACING || + prog->type == BPF_PROG_TYPE_EXT) { if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. @@ -2040,10 +2340,10 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, } } -#define BPF_PROG_ATTACH_LAST_FIELD attach_flags +#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd #define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) static int bpf_prog_attach(const union bpf_attr *attr) { @@ -2305,17 +2605,12 @@ static int bpf_obj_get_next_id(const union bpf_attr *attr, #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id -static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; - u32 id = attr->prog_id; - int fd; - if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) - return -EINVAL; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + if (!id) + return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); @@ -2324,7 +2619,22 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); + return prog; +} + +static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) +{ + struct bpf_prog *prog; + u32 id = attr->prog_id; + int fd; + + if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); @@ -2774,6 +3084,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } + info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_info_fill(&info, map); @@ -2986,6 +3297,61 @@ out: return err; } +#define BPF_MAP_BATCH_LAST_FIELD batch.flags + +#define BPF_DO_BATCH(fn) \ + do { \ + if (!fn) { \ + err = -ENOTSUPP; \ + goto err_put; \ + } \ + err = fn(map, attr, uattr); \ + } while (0) + +static int bpf_map_do_batch(const union bpf_attr *attr, + union bpf_attr __user *uattr, + int cmd) +{ + struct bpf_map *map; + int err, ufd; + struct fd f; + + if (CHECK_ATTR(BPF_MAP_BATCH)) + return -EINVAL; + + ufd = attr->batch.map_fd; + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if ((cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && + !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + + if (cmd != BPF_MAP_LOOKUP_BATCH && + !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + if (cmd == BPF_MAP_LOOKUP_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_batch); + else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) + BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch); + else if (cmd == BPF_MAP_UPDATE_BATCH) + BPF_DO_BATCH(map->ops->map_update_batch); + else + BPF_DO_BATCH(map->ops->map_delete_batch); + +err_put: + fdput(f); + return err; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -3083,6 +3449,19 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; + case BPF_MAP_LOOKUP_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_LOOKUP_BATCH); + break; + case BPF_MAP_LOOKUP_AND_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, + BPF_MAP_LOOKUP_AND_DELETE_BATCH); + break; + case BPF_MAP_UPDATE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_UPDATE_BATCH); + break; + case BPF_MAP_DELETE_BATCH: + err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index ca52b9642943..d4f335a9a899 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -44,14 +44,19 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } -struct tnum tnum_arshift(struct tnum a, u8 min_shift) +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ - return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); + if (insn_bitness == 32) + return TNUM((u32)(((s32)a.value) >> min_shift), + (u32)(((s32)a.mask) >> min_shift)); + else + return TNUM((s64)a.value >> min_shift, + (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 23b0d5cfd47e..6b264a92064b 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -4,16 +4,98 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ftrace.h> +#include <linux/rbtree_latch.h> + +/* dummy _ops. The verifier will operate on target program's ops. */ +const struct bpf_verifier_ops bpf_extension_verifier_ops = { +}; +const struct bpf_prog_ops bpf_extension_prog_ops = { +}; /* btf_vmlinux has ~22k attachable functions. 1k htab is enough. */ #define TRAMPOLINE_HASH_BITS 10 #define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; +static struct latch_tree_root image_tree __cacheline_aligned; -/* serializes access to trampoline_table */ +/* serializes access to trampoline_table and image_tree */ static DEFINE_MUTEX(trampoline_mutex); +static void *bpf_jit_alloc_exec_page(void) +{ + void *image; + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return NULL; + + set_vm_flush_reset_perms(image); + /* Keep image as writeable. The alternative is to keep flipping ro/rw + * everytime new program is attached or detached. + */ + set_memory_x((long)image, 1); + return image; +} + +static __always_inline bool image_tree_less(struct latch_tree_node *a, + struct latch_tree_node *b) +{ + struct bpf_image *ia = container_of(a, struct bpf_image, tnode); + struct bpf_image *ib = container_of(b, struct bpf_image, tnode); + + return ia < ib; +} + +static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n) +{ + void *image = container_of(n, struct bpf_image, tnode); + + if (addr < image) + return -1; + if (addr >= image + PAGE_SIZE) + return 1; + + return 0; +} + +static const struct latch_tree_ops image_tree_ops = { + .less = image_tree_less, + .comp = image_tree_comp, +}; + +static void *__bpf_image_alloc(bool lock) +{ + struct bpf_image *image; + + image = bpf_jit_alloc_exec_page(); + if (!image) + return NULL; + + if (lock) + mutex_lock(&trampoline_mutex); + latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops); + if (lock) + mutex_unlock(&trampoline_mutex); + return image->data; +} + +void *bpf_image_alloc(void) +{ + return __bpf_image_alloc(true); +} + +bool is_bpf_image_address(unsigned long addr) +{ + bool ret; + + rcu_read_lock(); + ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL; + rcu_read_unlock(); + + return ret; +} + struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { struct bpf_trampoline *tr; @@ -34,7 +116,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) goto out; /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = bpf_jit_alloc_exec(PAGE_SIZE); + image = __bpf_image_alloc(false); if (!image) { kfree(tr); tr = NULL; @@ -48,12 +130,6 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) mutex_init(&tr->mutex); for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); - - set_vm_flush_reset_perms(image); - /* Keep image as writeable. The alternative is to keep flipping ro/rw - * everytime new program is attached or detached. - */ - set_memory_x((long)image, 1); tr->image = image; out: mutex_unlock(&trampoline_mutex); @@ -115,14 +191,14 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) } /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into PAGE_SIZE / 2 + * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 */ #define BPF_MAX_TRAMP_PROGS 40 static int bpf_trampoline_update(struct bpf_trampoline *tr) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2; struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; @@ -150,11 +226,20 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) if (fexit_cnt) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; - err = arch_prepare_bpf_trampoline(new_image, &tr->func.model, flags, + /* Though the second half of trampoline page is unused a task could be + * preempted in the middle of the first half of trampoline and two + * updates to trampoline would change the code from underneath the + * preempted task. Hence wait for tasks to voluntarily schedule or go + * to userspace. + */ + synchronize_rcu_tasks(); + + err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, + &tr->func.model, flags, fentry, fentry_cnt, fexit, fexit_cnt, tr->func.addr); - if (err) + if (err < 0) goto out; if (tr->selector) @@ -175,8 +260,10 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) switch (t) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; - default: + case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; + default: + return BPF_TRAMP_REPLACE; } } @@ -185,12 +272,31 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog) enum bpf_tramp_prog_type kind; struct bpf_trampoline *tr; int err = 0; + int cnt; tr = prog->aux->trampoline; kind = bpf_attach_type_to_tramp(prog->expected_attach_type); mutex_lock(&tr->mutex); - if (tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT] - >= BPF_MAX_TRAMP_PROGS) { + if (tr->extension_prog) { + /* cannot attach fentry/fexit if extension prog is attached. + * cannot overwrite extension prog either. + */ + err = -EBUSY; + goto out; + } + cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + if (kind == BPF_TRAMP_REPLACE) { + /* Cannot attach extension if fentry/fexit are in use. */ + if (cnt) { + err = -EBUSY; + goto out; + } + tr->extension_prog = prog; + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, NULL, + prog->bpf_func); + goto out; + } + if (cnt >= BPF_MAX_TRAMP_PROGS) { err = -E2BIG; goto out; } @@ -221,15 +327,25 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog) tr = prog->aux->trampoline; kind = bpf_attach_type_to_tramp(prog->expected_attach_type); mutex_lock(&tr->mutex); + if (kind == BPF_TRAMP_REPLACE) { + WARN_ON_ONCE(!tr->extension_prog); + err = bpf_arch_text_poke(tr->func.addr, BPF_MOD_JUMP, + tr->extension_prog->bpf_func, NULL); + tr->extension_prog = NULL; + goto out; + } hlist_del(&prog->aux->tramp_hlist); tr->progs_cnt[kind]--; err = bpf_trampoline_update(prog->aux->trampoline); +out: mutex_unlock(&tr->mutex); return err; } void bpf_trampoline_put(struct bpf_trampoline *tr) { + struct bpf_image *image; + if (!tr) return; mutex_lock(&trampoline_mutex); @@ -240,7 +356,11 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) goto out; if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; - bpf_jit_free_exec(tr->image); + image = container_of(tr->image, struct bpf_image, data); + latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops); + /* wait for tasks to get out of trampoline before freeing it */ + synchronize_rcu_tasks(); + bpf_jit_free_exec(image); hlist_del(&tr->hlist); kfree(tr); out: @@ -286,7 +406,8 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) } int __weak -arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, +arch_prepare_bpf_trampoline(void *image, void *image_end, + const struct btf_func_model *m, u32 flags, struct bpf_prog **fentry_progs, int fentry_cnt, struct bpf_prog **fexit_progs, int fexit_cnt, void *orig_call) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ce85e7041f0c..1cc945daa9c8 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1122,10 +1122,6 @@ static void init_reg_state(struct bpf_verifier_env *env, regs[BPF_REG_FP].type = PTR_TO_STACK; mark_reg_known_zero(env, regs, BPF_REG_FP); regs[BPF_REG_FP].frameno = state->frameno; - - /* 1st arg to a function */ - regs[BPF_REG_1].type = PTR_TO_CTX; - mark_reg_known_zero(env, regs, BPF_REG_1); } #define BPF_MAIN_FUNC (-1) @@ -1916,6 +1912,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: + case PTR_TO_BTF_ID: return true; default: return false; @@ -2738,8 +2735,8 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -static int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +int check_ctx_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { /* Access to ctx or passing it to a helper is only allowed in * its original, unmodified form. @@ -2858,11 +2855,6 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, u32 btf_id; int ret; - if (atype != BPF_READ) { - verbose(env, "only read is supported\n"); - return -EACCES; - } - if (off < 0) { verbose(env, "R%d is ptr_%s invalid negative access: off=%d\n", @@ -2879,17 +2871,32 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); + if (env->ops->btf_struct_access) { + ret = env->ops->btf_struct_access(&env->log, t, off, size, + atype, &btf_id); + } else { + if (atype != BPF_READ) { + verbose(env, "only read is supported\n"); + return -EACCES; + } + + ret = btf_struct_access(&env->log, t, off, size, atype, + &btf_id); + } + if (ret < 0) return ret; - if (ret == SCALAR_VALUE) { - mark_reg_unknown(env, regs, value_regno); - return 0; + if (atype == BPF_READ) { + if (ret == SCALAR_VALUE) { + mark_reg_unknown(env, regs, value_regno); + return 0; + } + mark_reg_known_zero(env, regs, value_regno); + regs[value_regno].type = PTR_TO_BTF_ID; + regs[value_regno].btf_id = btf_id; } - mark_reg_known_zero(env, regs, value_regno); - regs[value_regno].type = PTR_TO_BTF_ID; - regs[value_regno].btf_id = btf_id; + return 0; } @@ -3945,12 +3952,26 @@ static int release_reference(struct bpf_verifier_env *env, return 0; } +static void clear_caller_saved_regs(struct bpf_verifier_env *env, + struct bpf_reg_state *regs) +{ + int i; + + /* after the call registers r0 - r5 were scratched */ + for (i = 0; i < CALLER_SAVED_REGS; i++) { + mark_reg_not_init(env, regs, caller_saved[i]); + check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + } +} + 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_info_aux *func_info_aux; struct bpf_func_state *caller, *callee; int i, err, subprog, target_insn; + bool is_global = false; if (state->curframe + 1 >= MAX_CALL_FRAMES) { verbose(env, "the call stack of %d frames is too deep\n", @@ -3973,6 +3994,32 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EFAULT; } + func_info_aux = env->prog->aux->func_info_aux; + if (func_info_aux) + is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL; + err = btf_check_func_arg_match(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + if (is_global) { + if (err) { + verbose(env, "Caller passes invalid args into func#%d\n", + subprog); + return err; + } else { + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, + "Func#%d is global and valid. Skipping.\n", + subprog); + clear_caller_saved_regs(env, caller->regs); + + /* All global functions return SCALAR_VALUE */ + mark_reg_unknown(env, caller->regs, BPF_REG_0); + + /* continue with next insn after call */ + return 0; + } + } + callee = kzalloc(sizeof(*callee), GFP_KERNEL); if (!callee) return -ENOMEM; @@ -3999,18 +4046,11 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* 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); - } + clear_caller_saved_regs(env, caller->regs); /* only increment it after check_reg_arg() finished */ state->curframe++; - if (btf_check_func_arg_match(env, subprog)) - return -EINVAL; - /* and go analyze first insn of the callee */ *insn_idx = target_insn; @@ -5049,9 +5089,16 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Upon reaching here, src_known is true and * umax_val is equal to umin_val. */ - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + if (insn_bitness == 32) { + dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); + dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); + } else { + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + } + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, + insn_bitness); /* blow away the dst_reg umin_value/umax_value and rely on * dst_reg var_off to refine the result. @@ -6353,8 +6400,30 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) static int check_return_code(struct bpf_verifier_env *env) { struct tnum enforce_attach_type_range = tnum_unknown; + const struct bpf_prog *prog = env->prog; struct bpf_reg_state *reg; struct tnum range = tnum_range(0, 1); + int err; + + /* The struct_ops func-ptr's return type could be "void" */ + if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS && + !prog->aux->attach_func_proto->type) + return 0; + + /* 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 + * of bpf_exit, which means that program wrote + * something into it earlier + */ + err = check_reg_arg(env, BPF_REG_0, SRC_OP); + if (err) + return err; + + if (is_pointer_value(env, BPF_REG_0)) { + verbose(env, "R0 leaks addr as return value\n"); + return -EACCES; + } switch (env->prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: @@ -6743,12 +6812,13 @@ static int check_btf_func(struct bpf_verifier_env *env, /* check type_id */ type = btf_type_by_id(btf, krecord[i].type_id); - if (!type || BTF_INFO_KIND(type->info) != BTF_KIND_FUNC) { + if (!type || !btf_type_is_func(type)) { verbose(env, "invalid type id %d in func info", krecord[i].type_id); ret = -EINVAL; goto err_free; } + info_aux[i].linkage = BTF_INFO_VLEN(type->info); prev_offset = krecord[i].insn_off; urecord += urec_size; } @@ -7728,35 +7798,13 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev) static int do_check(struct bpf_verifier_env *env) { - struct bpf_verifier_state *state; + struct bpf_verifier_state *state = env->cur_state; struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len; bool do_print_state = false; int prev_insn_idx = -1; - env->prev_linfo = NULL; - - state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); - if (!state) - return -ENOMEM; - state->curframe = 0; - state->speculative = false; - state->branches = 1; - state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); - if (!state->frame[0]) { - kfree(state); - return -ENOMEM; - } - env->cur_state = state; - init_func_state(env, state->frame[0], - BPF_MAIN_FUNC /* callsite */, - 0 /* frameno */, - 0 /* subprogno, zero == main subprog */); - - if (btf_check_func_arg_match(env, 0)) - return -EINVAL; - for (;;) { struct bpf_insn *insn; u8 class; @@ -7834,7 +7882,7 @@ static int do_check(struct bpf_verifier_env *env) } regs = cur_regs(env); - env->insn_aux_data[env->insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; prev_insn_idx = env->insn_idx; if (class == BPF_ALU || class == BPF_ALU64) { @@ -8020,21 +8068,6 @@ static int do_check(struct bpf_verifier_env *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 - * of bpf_exit, which means that program wrote - * something into it earlier - */ - err = check_reg_arg(env, BPF_REG_0, SRC_OP); - if (err) - return err; - - if (is_pointer_value(env, BPF_REG_0)) { - verbose(env, "R0 leaks addr as return value\n"); - return -EACCES; - } - err = check_return_code(env); if (err) return err; @@ -8069,7 +8102,7 @@ process_bpf_exit: return err; env->insn_idx++; - env->insn_aux_data[env->insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = env->pass_cnt; } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -8082,7 +8115,6 @@ process_bpf_exit: env->insn_idx++; } - env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -8142,6 +8174,11 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { + verbose(env, "bpf_struct_ops map cannot be used in prog\n"); + return -EINVAL; + } + return 0; } @@ -8354,7 +8391,7 @@ static int adjust_insn_aux_data(struct bpf_verifier_env *env, memcpy(new_data + off + cnt - 1, old_data + off, sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1)); for (i = off; i < off + cnt - 1; i++) { - new_data[i].seen = true; + new_data[i].seen = env->pass_cnt; new_data[i].zext_dst = insn_has_def32(env, insn + i); } env->insn_aux_data = new_data; @@ -8833,12 +8870,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) convert_ctx_access = bpf_xdp_sock_convert_ctx_access; break; case PTR_TO_BTF_ID: - if (type == BPF_WRITE) { + if (type == BPF_READ) { + insn->code = BPF_LDX | BPF_PROBE_MEM | + BPF_SIZE((insn)->code); + env->prog->aux->num_exentries++; + } else if (env->prog->type != BPF_PROG_TYPE_STRUCT_OPS) { verbose(env, "Writes through BTF pointers are not allowed\n"); return -EINVAL; } - insn->code = BPF_LDX | BPF_PROBE_MEM | BPF_SIZE((insn)->code); - env->prog->aux->num_exentries++; continue; default: continue; @@ -9418,6 +9457,30 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) goto patch_call_imm; } + if (prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_jiffies64) { + struct bpf_insn ld_jiffies_addr[2] = { + BPF_LD_IMM64(BPF_REG_0, + (unsigned long)&jiffies), + }; + + insn_buf[0] = ld_jiffies_addr[0]; + insn_buf[1] = ld_jiffies_addr[1]; + insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, + BPF_REG_0, 0); + cnt = 3; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, + cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed @@ -9464,6 +9527,7 @@ static void free_states(struct bpf_verifier_env *env) kfree(sl); sl = sln; } + env->free_list = NULL; if (!env->explored_states) return; @@ -9477,11 +9541,164 @@ static void free_states(struct bpf_verifier_env *env) kfree(sl); sl = sln; } + env->explored_states[i] = NULL; } +} - kvfree(env->explored_states); +/* The verifier is using insn_aux_data[] to store temporary data during + * verification and to store information for passes that run after the + * verification like dead code sanitization. do_check_common() for subprogram N + * may analyze many other subprograms. sanitize_insn_aux_data() clears all + * temporary data after do_check_common() finds that subprogram N cannot be + * verified independently. pass_cnt counts the number of times + * do_check_common() was run and insn->aux->seen tells the pass number + * insn_aux_data was touched. These variables are compared to clear temporary + * data from failed pass. For testing and experiments do_check_common() can be + * run multiple times even when prior attempt to verify is unsuccessful. + */ +static void sanitize_insn_aux_data(struct bpf_verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + struct bpf_insn_aux_data *aux; + int i, class; + + for (i = 0; i < env->prog->len; i++) { + class = BPF_CLASS(insn[i].code); + if (class != BPF_LDX && class != BPF_STX) + continue; + aux = &env->insn_aux_data[i]; + if (aux->seen != env->pass_cnt) + continue; + memset(aux, 0, offsetof(typeof(*aux), orig_idx)); + } +} + +static int do_check_common(struct bpf_verifier_env *env, int subprog) +{ + struct bpf_verifier_state *state; + struct bpf_reg_state *regs; + int ret, i; + + env->prev_linfo = NULL; + env->pass_cnt++; + + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); + if (!state) + return -ENOMEM; + state->curframe = 0; + state->speculative = false; + state->branches = 1; + state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); + if (!state->frame[0]) { + kfree(state); + return -ENOMEM; + } + env->cur_state = state; + init_func_state(env, state->frame[0], + BPF_MAIN_FUNC /* callsite */, + 0 /* frameno */, + subprog); + + regs = state->frame[state->curframe]->regs; + if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { + ret = btf_prepare_func_args(env, subprog, regs); + if (ret) + goto out; + for (i = BPF_REG_1; i <= BPF_REG_5; i++) { + if (regs[i].type == PTR_TO_CTX) + mark_reg_known_zero(env, regs, i); + else if (regs[i].type == SCALAR_VALUE) + mark_reg_unknown(env, regs, i); + } + } else { + /* 1st arg to a function */ + regs[BPF_REG_1].type = PTR_TO_CTX; + mark_reg_known_zero(env, regs, BPF_REG_1); + ret = btf_check_func_arg_match(env, subprog, regs); + if (ret == -EFAULT) + /* unlikely verifier bug. abort. + * ret == 0 and ret < 0 are sadly acceptable for + * main() function due to backward compatibility. + * Like socket filter program may be written as: + * int bpf_prog(struct pt_regs *ctx) + * and never dereference that ctx in the program. + * 'struct pt_regs' is a type mismatch for socket + * filter that should be using 'struct __sk_buff'. + */ + goto out; + } + + ret = do_check(env); +out: + /* check for NULL is necessary, since cur_state can be freed inside + * do_check() under memory pressure. + */ + if (env->cur_state) { + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + } + while (!pop_stack(env, NULL, NULL)); + free_states(env); + if (ret) + /* clean aux data in case subprog was rejected */ + sanitize_insn_aux_data(env); + return ret; } +/* Verify all global functions in a BPF program one by one based on their BTF. + * All global functions must pass verification. Otherwise the whole program is rejected. + * Consider: + * int bar(int); + * int foo(int f) + * { + * return bar(f); + * } + * int bar(int b) + * { + * ... + * } + * foo() will be verified first for R1=any_scalar_value. During verification it + * will be assumed that bar() already verified successfully and call to bar() + * from foo() will be checked for type match only. Later bar() will be verified + * independently to check that it's safe for R1=any_scalar_value. + */ +static int do_check_subprogs(struct bpf_verifier_env *env) +{ + struct bpf_prog_aux *aux = env->prog->aux; + int i, ret; + + if (!aux->func_info) + return 0; + + for (i = 1; i < env->subprog_cnt; i++) { + if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL) + continue; + env->insn_idx = env->subprog_info[i].start; + WARN_ON_ONCE(env->insn_idx == 0); + ret = do_check_common(env, i); + if (ret) { + return ret; + } else if (env->log.level & BPF_LOG_LEVEL) { + verbose(env, + "Func#%d is safe for any args that match its prototype\n", + i); + } + } + return 0; +} + +static int do_check_main(struct bpf_verifier_env *env) +{ + int ret; + + env->insn_idx = 0; + ret = do_check_common(env, 0); + if (!ret) + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; + return ret; +} + + static void print_verification_stats(struct bpf_verifier_env *env) { int i; @@ -9506,9 +9723,62 @@ static void print_verification_stats(struct bpf_verifier_env *env) env->peak_states, env->longest_mark_read_walk); } +static int check_struct_ops_btf_id(struct bpf_verifier_env *env) +{ + const struct btf_type *t, *func_proto; + const struct bpf_struct_ops *st_ops; + const struct btf_member *member; + struct bpf_prog *prog = env->prog; + u32 btf_id, member_idx; + const char *mname; + + btf_id = prog->aux->attach_btf_id; + st_ops = bpf_struct_ops_find(btf_id); + if (!st_ops) { + verbose(env, "attach_btf_id %u is not a supported struct\n", + btf_id); + return -ENOTSUPP; + } + + t = st_ops->type; + member_idx = prog->expected_attach_type; + if (member_idx >= btf_type_vlen(t)) { + verbose(env, "attach to invalid member idx %u of struct %s\n", + member_idx, st_ops->name); + return -EINVAL; + } + + member = &btf_type_member(t)[member_idx]; + mname = btf_name_by_offset(btf_vmlinux, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + NULL); + if (!func_proto) { + verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", + mname, member_idx, st_ops->name); + return -EINVAL; + } + + if (st_ops->check_member) { + int err = st_ops->check_member(t, member); + + if (err) { + verbose(env, "attach to unsupported member %s of struct %s\n", + mname, st_ops->name); + return err; + } + } + + prog->aux->attach_func_proto = func_proto; + prog->aux->attach_func_name = mname; + env->ops = st_ops->verifier_ops; + + return 0; +} + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + bool prog_extension = prog->type == BPF_PROG_TYPE_EXT; struct bpf_prog *tgt_prog = prog->aux->linked_prog; u32 btf_id = prog->aux->attach_btf_id; const char prefix[] = "btf_trace_"; @@ -9521,7 +9791,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) long addr; u64 key; - if (prog->type != BPF_PROG_TYPE_TRACING) + if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) + return check_struct_ops_btf_id(env); + + if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension) return 0; if (!btf_id) { @@ -9557,8 +9830,59 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } conservative = aux->func_info_aux[subprog].unreliable; + if (prog_extension) { + if (conservative) { + verbose(env, + "Cannot replace static functions\n"); + return -EINVAL; + } + if (!prog->jit_requested) { + verbose(env, + "Extension programs should be JITed\n"); + return -EINVAL; + } + env->ops = bpf_verifier_ops[tgt_prog->type]; + } + if (!tgt_prog->jited) { + verbose(env, "Can attach to only JITed progs\n"); + return -EINVAL; + } + if (tgt_prog->type == prog->type) { + /* Cannot fentry/fexit another fentry/fexit program. + * Cannot attach program extension to another extension. + * It's ok to attach fentry/fexit to extension program. + */ + verbose(env, "Cannot recursively attach\n"); + return -EINVAL; + } + if (tgt_prog->type == BPF_PROG_TYPE_TRACING && + prog_extension && + (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY || + tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) { + /* Program extensions can extend all program types + * except fentry/fexit. The reason is the following. + * The fentry/fexit programs are used for performance + * analysis, stats and can be attached to any program + * type except themselves. When extension program is + * replacing XDP function it is necessary to allow + * performance analysis of all functions. Both original + * XDP program and its program extension. Hence + * attaching fentry/fexit to BPF_PROG_TYPE_EXT is + * allowed. If extending of fentry/fexit was allowed it + * would be possible to create long call chain + * fentry->extension->fentry->extension beyond + * reasonable stack size. Hence extending fentry is not + * allowed. + */ + verbose(env, "Cannot extend fentry/fexit\n"); + return -EINVAL; + } key = ((u64)aux->id) << 32 | btf_id; } else { + if (prog_extension) { + verbose(env, "Cannot replace kernel functions\n"); + return -EINVAL; + } key = btf_id; } @@ -9596,6 +9920,10 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) prog->aux->attach_func_proto = t; prog->aux->attach_btf_trace = true; return 0; + default: + if (!prog_extension) + return -EINVAL; + /* fallthrough */ case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: if (!btf_type_is_func(t)) { @@ -9603,6 +9931,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) btf_id); return -EINVAL; } + if (prog_extension && + btf_check_type_match(env, prog, btf, t)) + return -EINVAL; t = btf_type_by_id(btf, t->type); if (!btf_type_is_func_proto(t)) return -EINVAL; @@ -9626,18 +9957,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (ret < 0) goto out; if (tgt_prog) { - if (!tgt_prog->jited) { - /* for now */ - verbose(env, "Can trace only JITed BPF progs\n"); - ret = -EINVAL; - goto out; - } - if (tgt_prog->type == BPF_PROG_TYPE_TRACING) { - /* prevent cycles */ - verbose(env, "Cannot recursively attach\n"); - ret = -EINVAL; - goto out; - } if (subprog == 0) addr = (long) tgt_prog->bpf_func; else @@ -9659,8 +9978,6 @@ out: if (ret) bpf_trampoline_put(tr); return ret; - default: - return -EINVAL; } } @@ -9730,10 +10047,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, goto skip_full_check; } - ret = check_attach_btf_id(env); - if (ret) - goto skip_full_check; - env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; @@ -9770,22 +10083,22 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, if (ret < 0) goto skip_full_check; + ret = check_attach_btf_id(env); + if (ret) + goto skip_full_check; + ret = check_cfg(env); if (ret < 0) goto skip_full_check; - ret = do_check(env); - if (env->cur_state) { - free_verifier_state(env->cur_state, true); - env->cur_state = NULL; - } + ret = do_check_subprogs(env); + ret = ret ?: do_check_main(env); 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); + kvfree(env->explored_states); if (ret == 0) ret = check_max_stack_depth(env); diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index 90c4fce1c981..2cc5c8f4c800 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -72,9 +72,9 @@ static void xsk_map_sock_delete(struct xdp_sock *xs, static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { struct bpf_map_memory mem; - int cpu, err, numa_node; + int err, numa_node; struct xsk_map *m; - u64 cost, size; + u64 size; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -86,9 +86,8 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) numa_node = bpf_map_attr_numa_node(attr); size = struct_size(m, xsk_map, attr->max_entries); - cost = size + array_size(sizeof(*m->flush_list), num_possible_cpus()); - err = bpf_map_charge_init(&mem, cost); + err = bpf_map_charge_init(&mem, size); if (err < 0) return ERR_PTR(err); @@ -102,16 +101,6 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) bpf_map_charge_move(&m->map.memory, &mem); spin_lock_init(&m->lock); - m->flush_list = alloc_percpu(struct list_head); - if (!m->flush_list) { - bpf_map_charge_finish(&m->map.memory); - bpf_map_area_free(m); - return ERR_PTR(-ENOMEM); - } - - for_each_possible_cpu(cpu) - INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); - return &m->map; } @@ -121,7 +110,6 @@ static void xsk_map_free(struct bpf_map *map) bpf_clear_redirect_map(map); synchronize_net(); - free_percpu(m->flush_list); bpf_map_area_free(m); } diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 90d1710fef6c..bfbeabc17a9d 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -7,7 +7,7 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> -#include <linux/fs_context.h> +#include <linux/fs_parser.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; @@ -265,7 +265,7 @@ extern const struct proc_ns_operations cgroupns_operations; */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; -extern const struct fs_parameter_description cgroup1_fs_parameters; +extern const struct fs_parameter_spec cgroup1_fs_parameters[]; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 09f3a413f6f8..f2d7cea86ffe 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -18,8 +18,6 @@ #include <trace/events/cgroup.h> -#define cg_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) - /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls @@ -473,6 +471,7 @@ static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) */ p++; if (p >= end) { + (*pos)++; return NULL; } else { *pos = *p; @@ -784,7 +783,7 @@ void cgroup1_release_agent(struct work_struct *work) pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!pathbuf || !agentbuf) + if (!pathbuf || !agentbuf || !strlen(agentbuf)) goto out; spin_lock_irq(&css_set_lock); @@ -887,7 +886,7 @@ enum cgroup1_param { Opt_xattr, }; -static const struct fs_parameter_spec cgroup1_param_specs[] = { +const struct fs_parameter_spec cgroup1_fs_parameters[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), @@ -899,11 +898,6 @@ static const struct fs_parameter_spec cgroup1_param_specs[] = { {} }; -const struct fs_parameter_description cgroup1_fs_parameters = { - .name = "cgroup1", - .specs = cgroup1_param_specs, -}; - int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); @@ -911,7 +905,7 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) struct fs_parse_result result; int opt, i; - opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result); + opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { fc->source = param->string; @@ -924,7 +918,7 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->subsys_mask |= (1 << i); return 0; } - return cg_invalf(fc, "cgroup1: Unknown subsys name '%s'", param->key); + return invalfc(fc, "Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; @@ -952,7 +946,7 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) - return cg_invalf(fc, "cgroup1: release_agent respecified"); + return invalfc(fc, "release_agent respecified"); ctx->release_agent = param->string; param->string = NULL; break; @@ -962,9 +956,9 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) return -ENOENT; /* Can't specify an empty name */ if (!param->size) - return cg_invalf(fc, "cgroup1: Empty name"); + return invalfc(fc, "Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) - return cg_invalf(fc, "cgroup1: Name too long"); + return invalfc(fc, "Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; @@ -972,11 +966,11 @@ int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; - return cg_invalf(fc, "cgroup1: Invalid name"); + return invalfc(fc, "Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) - return cg_invalf(fc, "cgroup1: name respecified"); + return invalfc(fc, "name respecified"); ctx->name = param->string; param->string = NULL; break; @@ -1011,7 +1005,7 @@ static int check_cgroupfs_options(struct fs_context *fc) if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) - return cg_invalf(fc, "cgroup1: subsys name conflicts with all"); + return invalfc(fc, "subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } @@ -1021,7 +1015,7 @@ static int check_cgroupfs_options(struct fs_context *fc) * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) - return cg_invalf(fc, "cgroup1: Need name or subsystem set"); + return invalfc(fc, "Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility @@ -1029,11 +1023,11 @@ static int check_cgroupfs_options(struct fs_context *fc) * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) - return cg_invalf(fc, "cgroup1: noprefix used incorrectly"); + return invalfc(fc, "noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) - return cg_invalf(fc, "cgroup1: none used incorrectly"); + return invalfc(fc, "none used incorrectly"); return 0; } @@ -1063,7 +1057,7 @@ int cgroup1_reconfigure(struct fs_context *fc) /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { - cg_invalf(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", + errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; @@ -1180,7 +1174,7 @@ static int cgroup1_root_to_use(struct fs_context *fc) * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) - return cg_invalf(fc, "cgroup1: No subsys list or none specified"); + return invalfc(fc, "No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 735af8f15f95..7a39dc882095 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1816,24 +1816,19 @@ enum cgroup2_param { nr__cgroup2_params }; -static const struct fs_parameter_spec cgroup2_param_specs[] = { +static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("memory_localevents", Opt_memory_localevents), {} }; -static const struct fs_parameter_description cgroup2_fs_parameters = { - .name = "cgroup2", - .specs = cgroup2_param_specs, -}; - static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; - opt = fs_parse(fc, &cgroup2_fs_parameters, param, &result); + opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; @@ -2156,7 +2151,7 @@ static void cgroup_kill_sb(struct super_block *sb) struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, - .parameters = &cgroup1_fs_parameters, + .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; @@ -2164,7 +2159,7 @@ struct file_system_type cgroup_fs_type = { static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, - .parameters = &cgroup2_fs_parameters, + .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; @@ -3055,8 +3050,6 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); - WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); - if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; @@ -3066,6 +3059,8 @@ static int cgroup_apply_control_enable(struct cgroup *cgrp) return PTR_ERR(css); } + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + if (css_visible(css)) { ret = css_populate_dir(css); if (ret) @@ -3101,11 +3096,11 @@ static void cgroup_apply_control_disable(struct cgroup *cgrp) for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); - WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); - if (!css) continue; + WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); + if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); @@ -3392,7 +3387,8 @@ static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, if (strcmp(strstrip(buf), "threaded")) return -EINVAL; - cgrp = cgroup_kn_lock_live(of->kn, false); + /* drain dying csses before we re-apply (threaded) subtree control */ + cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; @@ -3546,21 +3542,21 @@ static int cpu_stat_show(struct seq_file *seq, void *v) static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; - struct psi_group *psi = cgroup_id(cgrp) == 1 ? &psi_system : &cgrp->psi; + struct psi_group *psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; return psi_show(seq, psi, PSI_CPU); } @@ -4404,12 +4400,16 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it) } } while (!css_set_populated(cset) && list_empty(&cset->dying_tasks)); - if (!list_empty(&cset->tasks)) + if (!list_empty(&cset->tasks)) { it->task_pos = cset->tasks.next; - else if (!list_empty(&cset->mg_tasks)) + it->cur_tasks_head = &cset->tasks; + } else if (!list_empty(&cset->mg_tasks)) { it->task_pos = cset->mg_tasks.next; - else + it->cur_tasks_head = &cset->mg_tasks; + } else { it->task_pos = cset->dying_tasks.next; + it->cur_tasks_head = &cset->dying_tasks; + } it->tasks_head = &cset->tasks; it->mg_tasks_head = &cset->mg_tasks; @@ -4467,10 +4467,14 @@ repeat: else it->task_pos = it->task_pos->next; - if (it->task_pos == it->tasks_head) + if (it->task_pos == it->tasks_head) { it->task_pos = it->mg_tasks_head->next; - if (it->task_pos == it->mg_tasks_head) + it->cur_tasks_head = it->mg_tasks_head; + } + if (it->task_pos == it->mg_tasks_head) { it->task_pos = it->dying_tasks_head->next; + it->cur_tasks_head = it->dying_tasks_head; + } if (it->task_pos == it->dying_tasks_head) css_task_iter_advance_css_set(it); } else { @@ -4489,11 +4493,12 @@ repeat: goto repeat; /* and dying leaders w/o live member threads */ - if (!atomic_read(&task->signal->live)) + if (it->cur_tasks_head == it->dying_tasks_head && + !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ - if (task->flags & PF_EXITING) + if (it->cur_tasks_head == it->dying_tasks_head) goto repeat; } } @@ -4599,6 +4604,9 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) struct kernfs_open_file *of = s->private; struct css_task_iter *it = of->priv; + if (pos) + (*pos)++; + return css_task_iter_next(it); } @@ -4614,7 +4622,7 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, * from position 0, so we can simply keep iterating on !0 *pos. */ if (!it) { - if (WARN_ON_ONCE((*pos)++)) + if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); it = kzalloc(sizeof(*it), GFP_KERNEL); @@ -4622,10 +4630,11 @@ static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, return ERR_PTR(-ENOMEM); of->priv = it; css_task_iter_start(&cgrp->self, iter_flags, it); - } else if (!(*pos)++) { + } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); - } + } else + return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } @@ -5931,11 +5940,14 @@ void cgroup_post_fork(struct task_struct *child) spin_lock_irq(&css_set_lock); - WARN_ON_ONCE(!list_empty(&child->cg_list)); - cset = task_css_set(current); /* current is @child's parent */ - get_css_set(cset); - cset->nr_tasks++; - css_set_move_task(child, NULL, cset, false); + /* init tasks are special, only link regular threads */ + if (likely(child->pid)) { + WARN_ON_ONCE(!list_empty(&child->cg_list)); + cset = task_css_set(current); /* current is @child's parent */ + get_css_set(cset); + cset->nr_tasks++; + css_set_move_task(child, NULL, cset, false); + } /* * If the cgroup has to be frozen, the new task has too. Let's set @@ -6288,12 +6300,13 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #ifdef CONFIG_CGROUP_BPF int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags) + struct bpf_prog *replace_prog, enum bpf_attach_type type, + u32 flags) { int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags); mutex_unlock(&cgroup_mutex); return ret; } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index b48b22d4deb6..6f87352f8219 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -33,7 +33,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) return; /* - * Paired with the one in cgroup_rstat_cpu_pop_upated(). Either we + * Paired with the one in cgroup_rstat_cpu_pop_updated(). Either we * see NULL updated_next or they see our updated stat. */ smp_mb(); diff --git a/kernel/compat.c b/kernel/compat.c index 95005f849c68..843dd17e6078 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -26,70 +26,6 @@ #include <linux/uaccess.h> -static int __compat_get_timeval(struct timeval *tv, const struct old_timeval32 __user *ctv) -{ - return (!access_ok(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 old_timeval32 __user *ctv) -{ - return (!access_ok(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 old_timespec32 __user *cts) -{ - return (!access_ok(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 old_timespec32 __user *cts) -{ - return (!access_ok(cts, sizeof(*cts)) || - __put_user(ts->tv_sec, &cts->tv_sec) || - __put_user(ts->tv_nsec, &cts->tv_nsec)) ? -EFAULT : 0; -} - -int compat_get_timeval(struct timeval *tv, const void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(tv, utv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_get_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_get_timeval); - -int compat_put_timeval(const struct timeval *tv, void __user *utv) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(utv, tv, sizeof(*tv)) ? -EFAULT : 0; - else - return __compat_put_timeval(tv, utv); -} -EXPORT_SYMBOL_GPL(compat_put_timeval); - -int compat_get_timespec(struct timespec *ts, const void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_from_user(ts, uts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_get_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_get_timespec); - -int compat_put_timespec(const struct timespec *ts, void __user *uts) -{ - if (COMPAT_USE_64BIT_TIME) - return copy_to_user(uts, ts, sizeof(*ts)) ? -EFAULT : 0; - else - return __compat_put_timespec(ts, uts); -} -EXPORT_SYMBOL_GPL(compat_put_timespec); - #ifdef __ARCH_WANT_SYS_SIGPROCMASK /* diff --git a/kernel/configs.c b/kernel/configs.c index c09ea4c995e1..a28c79c5f713 100644 --- a/kernel/configs.c +++ b/kernel/configs.c @@ -47,10 +47,9 @@ ikconfig_read_current(struct file *file, char __user *buf, &kernel_config_data); } -static const struct file_operations ikconfig_file_ops = { - .owner = THIS_MODULE, - .read = ikconfig_read_current, - .llseek = default_llseek, +static const struct proc_ops config_gz_proc_ops = { + .proc_read = ikconfig_read_current, + .proc_lseek = default_llseek, }; static int __init ikconfig_init(void) @@ -59,7 +58,7 @@ static int __init ikconfig_init(void) /* create the current config file */ entry = proc_create("config.gz", S_IFREG | S_IRUGO, NULL, - &ikconfig_file_ops); + &config_gz_proc_ops); if (!entry) return -ENOMEM; diff --git a/kernel/cpu.c b/kernel/cpu.c index a59cc980adad..9c706af713fb 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -525,8 +525,7 @@ static int bringup_wait_for_ap(unsigned int cpu) if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; - /* Unpark the stopper thread and the hotplug thread of the target cpu */ - stop_machine_unpark(cpu); + /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* @@ -1089,8 +1088,8 @@ void notify_cpu_starting(unsigned int cpu) /* * Called from the idle task. Wake up the controlling task which brings the - * stopper and the hotplug thread of the upcoming CPU up and then delegates - * the rest of the online bringup to the hotplug thread. + * hotplug thread of the upcoming CPU up and then delegates the rest of the + * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { @@ -1100,6 +1099,12 @@ void cpuhp_online_idle(enum cpuhp_state state) if (state != CPUHP_AP_ONLINE_IDLE) return; + /* + * Unpart the stopper thread before we start the idle loop (and start + * scheduling); this ensures the stopper task is always available. + */ + stop_machine_unpark(smp_processor_id()); + st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } @@ -1909,6 +1914,78 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) } EXPORT_SYMBOL(__cpuhp_remove_state); +#ifdef CONFIG_HOTPLUG_SMT +static void cpuhp_offline_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = true; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); +} + +static void cpuhp_online_cpu_device(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); + + dev->offline = false; + /* Tell user space about the state change */ + kobject_uevent(&dev->kobj, KOBJ_ONLINE); +} + +int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + for_each_online_cpu(cpu) { + if (topology_is_primary_thread(cpu)) + continue; + ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); + if (ret) + break; + /* + * As this needs to hold the cpu maps lock it's impossible + * to call device_offline() because that ends up calling + * cpu_down() which takes cpu maps lock. cpu maps lock + * needs to be held as this might race against in kernel + * abusers of the hotplug machinery (thermal management). + * + * So nothing would update device:offline state. That would + * leave the sysfs entry stale and prevent onlining after + * smt control has been changed to 'off' again. This is + * called under the sysfs hotplug lock, so it is properly + * serialized against the regular offline usage. + */ + cpuhp_offline_cpu_device(cpu); + } + if (!ret) + cpu_smt_control = ctrlval; + cpu_maps_update_done(); + return ret; +} + +int cpuhp_smt_enable(void) +{ + int cpu, ret = 0; + + cpu_maps_update_begin(); + cpu_smt_control = CPU_SMT_ENABLED; + for_each_present_cpu(cpu) { + /* Skip online CPUs and CPUs on offline nodes */ + if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) + continue; + ret = _cpu_up(cpu, 0, CPUHP_ONLINE); + if (ret) + break; + /* See comment in cpuhp_smt_disable() */ + cpuhp_online_cpu_device(cpu); + } + cpu_maps_update_done(); + return ret; +} +#endif + #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t show_cpuhp_state(struct device *dev, struct device_attribute *attr, char *buf) @@ -2063,77 +2140,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static void cpuhp_offline_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = true; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); -} - -static void cpuhp_online_cpu_device(unsigned int cpu) -{ - struct device *dev = get_cpu_device(cpu); - - dev->offline = false; - /* Tell user space about the state change */ - kobject_uevent(&dev->kobj, KOBJ_ONLINE); -} - -int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - for_each_online_cpu(cpu) { - if (topology_is_primary_thread(cpu)) - continue; - ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); - if (ret) - break; - /* - * As this needs to hold the cpu maps lock it's impossible - * to call device_offline() because that ends up calling - * cpu_down() which takes cpu maps lock. cpu maps lock - * needs to be held as this might race against in kernel - * abusers of the hotplug machinery (thermal management). - * - * So nothing would update device:offline state. That would - * leave the sysfs entry stale and prevent onlining after - * smt control has been changed to 'off' again. This is - * called under the sysfs hotplug lock, so it is properly - * serialized against the regular offline usage. - */ - cpuhp_offline_cpu_device(cpu); - } - if (!ret) - cpu_smt_control = ctrlval; - cpu_maps_update_done(); - return ret; -} - -int cpuhp_smt_enable(void) -{ - int cpu, ret = 0; - - cpu_maps_update_begin(); - cpu_smt_control = CPU_SMT_ENABLED; - for_each_present_cpu(cpu) { - /* Skip online CPUs and CPUs on offline nodes */ - if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) - continue; - ret = _cpu_up(cpu, 0, CPUHP_ONLINE); - if (ret) - break; - /* See comment in cpuhp_smt_disable() */ - cpuhp_online_cpu_device(cpu); - } - cpu_maps_update_done(); - return ret; -} - - static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) diff --git a/kernel/cred.c b/kernel/cred.c index 9ed51b70ed80..809a985b1793 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -175,8 +175,8 @@ void exit_creds(struct task_struct *tsk) put_cred(cred); #ifdef CONFIG_KEYS_REQUEST_CACHE - key_put(current->cached_requested_key); - current->cached_requested_key = NULL; + key_put(tsk->cached_requested_key); + tsk->cached_requested_key = NULL; #endif } diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 62c301ad0773..d7ebb2c79cb8 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -412,7 +412,6 @@ static int kdb_bc(int argc, const char **argv) * assume that the breakpoint number is desired. */ if (addr < KDB_MAXBPT) { - bp = &kdb_breakpoints[addr]; lowbp = highbp = addr; highbp++; } else { diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 4af48ac53625..3de0cc780c16 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -119,7 +119,6 @@ kdb_bt_cpu(unsigned long cpu) return; } - kdb_set_current_task(kdb_tsk); kdb_bt1(kdb_tsk, ~0UL, false); } @@ -166,10 +165,8 @@ kdb_bt(int argc, const char **argv) if (diag) return diag; p = find_task_by_pid_ns(pid, &init_pid_ns); - if (p) { - kdb_set_current_task(p); + if (p) return kdb_bt1(p, ~0UL, false); - } kdb_printf("No process with pid == %ld found\n", pid); return 0; } else if (strcmp(argv[0], "btt") == 0) { @@ -178,11 +175,9 @@ kdb_bt(int argc, const char **argv) diag = kdbgetularg((char *)argv[1], &addr); if (diag) return diag; - kdb_set_current_task((struct task_struct *)addr); return kdb_bt1((struct task_struct *)addr, ~0UL, false); } else if (strcmp(argv[0], "btc") == 0) { unsigned long cpu = ~0; - struct task_struct *save_current_task = kdb_current_task; if (argc > 1) return KDB_ARGCOUNT; if (argc == 1) { @@ -204,7 +199,6 @@ kdb_bt(int argc, const char **argv) kdb_bt_cpu(cpu); touch_nmi_watchdog(); } - kdb_set_current_task(save_current_task); } return 0; } else { diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 8bcdded5d61f..924bc9298a42 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -553,7 +553,7 @@ int vkdb_printf(enum kdb_msgsrc src, const char *fmt, va_list ap) int this_cpu, old_cpu; char *cp, *cp2, *cphold = NULL, replaced_byte = ' '; char *moreprompt = "more> "; - struct console *c = console_drivers; + struct console *c; unsigned long uninitialized_var(flags); /* Serialize kdb_printf if multiple cpus try to write at once. @@ -698,10 +698,9 @@ kdb_printit: cp2++; } } - while (c) { + for_each_console(c) { c->write(c, cp, retlen - (cp - kdb_buffer)); touch_nmi_watchdog(); - c = c->next; } } if (logging) { @@ -752,7 +751,6 @@ kdb_printit: moreprompt = "more> "; kdb_input_flush(); - c = console_drivers; if (dbg_io_ops && !dbg_io_ops->is_console) { len = strlen(moreprompt); @@ -762,10 +760,9 @@ kdb_printit: cp++; } } - while (c) { + for_each_console(c) { c->write(c, moreprompt, strlen(moreprompt)); touch_nmi_watchdog(); - c = c->next; } if (logging) diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 4567fe998c30..ba12e9f4661e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -73,7 +73,6 @@ int kdb_nextline = 1; int kdb_state; /* General KDB state */ struct task_struct *kdb_current_task; -EXPORT_SYMBOL(kdb_current_task); struct pt_regs *kdb_current_regs; const char *kdb_diemsg; @@ -1139,7 +1138,7 @@ static void kdb_dumpregs(struct pt_regs *regs) console_loglevel = old_lvl; } -void kdb_set_current_task(struct task_struct *p) +static void kdb_set_current_task(struct task_struct *p) { kdb_current_task = p; diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 55d052061ef9..2e296e4a234c 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -240,8 +240,8 @@ extern void *debug_kmalloc(size_t size, gfp_t flags); extern void debug_kfree(void *); extern void debug_kusage(void); -extern void kdb_set_current_task(struct task_struct *); extern struct task_struct *kdb_current_task; +extern struct pt_regs *kdb_current_regs; #ifdef CONFIG_KDB_KEYBOARD extern void kdb_kbd_cleanup_state(void); diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index daa4e6eefdde..8bc6f2d670f9 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -302,9 +302,16 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); phys_addr_t mask = align - 1; unsigned long node = rmem->fdt_node; + bool default_cma = of_get_flat_dt_prop(node, "linux,cma-default", NULL); struct cma *cma; int err; + if (size_cmdline != -1 && default_cma) { + pr_info("Reserved memory: bypass %s node, using cmdline CMA params instead\n", + rmem->name); + return -EBUSY; + } + if (!of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; @@ -322,7 +329,7 @@ static int __init rmem_cma_setup(struct reserved_mem *rmem) /* Architecture specific contiguous memory fixup. */ dma_contiguous_early_fixup(rmem->base, rmem->size); - if (of_get_flat_dt_prop(node, "linux,cma-default", NULL)) + if (default_cma) dma_contiguous_set_default(cma); rmem->ops = &rmem_cma_ops; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 6af7ae83c4ad..ac7956c38f69 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -23,18 +23,6 @@ */ unsigned int zone_dma_bits __ro_after_init = 24; -static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size) -{ - if (!dev->dma_mask) { - dev_err_once(dev, "DMA map on device without dma_mask\n"); - } else if (*dev->dma_mask >= DMA_BIT_MASK(32) || dev->bus_dma_limit) { - dev_err_once(dev, - "overflow %pad+%zu of DMA mask %llx bus limit %llx\n", - &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); - } - WARN_ON_ONCE(1); -} - static inline dma_addr_t phys_to_dma_direct(struct device *dev, phys_addr_t phys) { @@ -357,13 +345,6 @@ void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl, EXPORT_SYMBOL(dma_direct_unmap_sg); #endif -static inline bool dma_direct_possible(struct device *dev, dma_addr_t dma_addr, - size_t size) -{ - return swiotlb_force != SWIOTLB_FORCE && - dma_capable(dev, dma_addr, size, true); -} - 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) @@ -371,9 +352,16 @@ dma_addr_t dma_direct_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; dma_addr_t dma_addr = phys_to_dma(dev, phys); - if (unlikely(!dma_direct_possible(dev, dma_addr, size)) && - !swiotlb_map(dev, &phys, &dma_addr, size, dir, attrs)) { - report_addr(dev, dma_addr, size); + if (unlikely(swiotlb_force == SWIOTLB_FORCE)) + return swiotlb_map(dev, phys, size, dir, attrs); + + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + if (swiotlb_force != SWIOTLB_NO_FORCE) + return swiotlb_map(dev, phys, size, dir, attrs); + + dev_WARN_ONCE(dev, 1, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } @@ -411,7 +399,10 @@ dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr, dma_addr_t dma_addr = paddr; if (unlikely(!dma_capable(dev, dma_addr, size, false))) { - report_addr(dev, dma_addr, size); + dev_err_once(dev, + "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + WARN_ON_ONCE(1); return DMA_MAPPING_ERROR; } @@ -472,28 +463,26 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma, } #endif /* CONFIG_MMU */ -/* - * 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) { - u64 min_mask; + u64 min_mask = (max_pfn - 1) << PAGE_SHIFT; - if (IS_ENABLED(CONFIG_ZONE_DMA)) - min_mask = DMA_BIT_MASK(zone_dma_bits); - else - min_mask = DMA_BIT_MASK(32); - - min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT); + /* + * 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 >= DMA_BIT_MASK(32)) + return 1; /* * This check needs to be against the actual bit mask value, so * use __phys_to_dma() here so that the SME encryption mask isn't * part of the check. */ + if (IS_ENABLED(CONFIG_ZONE_DMA)) + min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits)); return mask >= __phys_to_dma(dev, min_mask); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 9280d6f8271e..c19379fabd20 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -22,6 +22,7 @@ #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> @@ -656,35 +657,38 @@ void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr, } /* - * Create a swiotlb mapping for the buffer at @phys, and in case of DMAing + * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing * to the device copy the data into it as well. */ -bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr, - size_t size, enum dma_data_direction dir, unsigned long attrs) +dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, + enum dma_data_direction dir, unsigned long attrs) { - trace_swiotlb_bounced(dev, *dma_addr, size, swiotlb_force); + phys_addr_t swiotlb_addr; + dma_addr_t dma_addr; - if (unlikely(swiotlb_force == SWIOTLB_NO_FORCE)) { - dev_warn_ratelimited(dev, - "Cannot do DMA to address %pa\n", phys); - return false; - } + trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, + swiotlb_force); - /* 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, size, dir, attrs); - if (*phys == (phys_addr_t)DMA_MAPPING_ERROR) - return false; + swiotlb_addr = swiotlb_tbl_map_single(dev, + __phys_to_dma(dev, io_tlb_start), + paddr, size, size, dir, attrs); + if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) + return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ - *dma_addr = __phys_to_dma(dev, *phys); - if (unlikely(!dma_capable(dev, *dma_addr, size, true))) { - swiotlb_tbl_unmap_single(dev, *phys, size, size, dir, + dma_addr = __phys_to_dma(dev, swiotlb_addr); + if (unlikely(!dma_capable(dev, dma_addr, size, true))) { + swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC); - return false; + dev_WARN_ONCE(dev, 1, + "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", + &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); + return DMA_MAPPING_ERROR; } - return true; + if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + arch_sync_dma_for_device(swiotlb_addr, size, dir); + return dma_addr; } size_t swiotlb_max_mapping_size(struct device *dev) diff --git a/kernel/events/core.c b/kernel/events/core.c index 455451d24b4a..e453589da97c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -951,9 +951,9 @@ list_update_cgroup_event(struct perf_event *event, /* * Because cgroup events are always per-cpu events, - * this will always be called from the right CPU. + * @ctx == &cpuctx->ctx. */ - cpuctx = __get_cpu_context(ctx); + cpuctx = container_of(ctx, struct perf_cpu_context, ctx); /* * Since setting cpuctx->cgrp is conditional on the current @cgrp @@ -979,7 +979,8 @@ list_update_cgroup_event(struct perf_event *event, cpuctx_entry = &cpuctx->cgrp_cpuctx_entry; if (add) - list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list)); + list_add(cpuctx_entry, + per_cpu_ptr(&cgrp_cpuctx_list, event->cpu)); else list_del(cpuctx_entry); } @@ -5916,7 +5917,15 @@ accounting: */ user_lock_limit *= num_online_cpus(); - user_locked = atomic_long_read(&user->locked_vm) + user_extra; + user_locked = atomic_long_read(&user->locked_vm); + + /* + * sysctl_perf_event_mlock may have changed, so that + * user->locked_vm > user_lock_limit + */ + if (user_locked > user_lock_limit) + user_locked = user_lock_limit; + user_locked += user_extra; if (user_locked > user_lock_limit) { /* @@ -7495,7 +7504,7 @@ static void perf_fill_ns_link_info(struct perf_ns_link_info *ns_link_info, { struct path ns_path; struct inode *ns_inode; - void *error; + int error; error = ns_get_path(&ns_path, task, ns_ops); if (!error) { @@ -11465,8 +11474,10 @@ SYSCALL_DEFINE5(perf_event_open, } } - if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) + if (perf_need_aux_event(event) && !perf_get_aux_event(event, group_leader)) { + err = -EINVAL; goto err_locked; + } /* * Must be under the same ctx::mutex as perf_install_in_context(), diff --git a/kernel/exit.c b/kernel/exit.c index 2833ffb0c211..0b81b26a872a 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -619,8 +619,8 @@ static void forget_original_parent(struct task_struct *father, reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { - t->real_parent = reaper; - BUG_ON((!t->ptrace) != (t->parent == father)); + RCU_INIT_POINTER(t->real_parent, reaper); + BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) diff --git a/kernel/extable.c b/kernel/extable.c index f6920a11e28a..a0024f27d3a1 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -131,8 +131,9 @@ int kernel_text_address(unsigned long addr) * triggers a stack trace, or a WARN() that happens during * coming back from idle, or cpu on or offlining. * - * is_module_text_address() as well as the kprobe slots - * and is_bpf_text_address() require RCU to be watching. + * is_module_text_address() as well as the kprobe slots, + * is_bpf_text_address() and is_bpf_image_address require + * RCU to be watching. */ no_rcu = !rcu_is_watching(); @@ -148,6 +149,8 @@ int kernel_text_address(unsigned long addr) goto out; if (is_bpf_text_address(addr)) goto out; + if (is_bpf_image_address(addr)) + goto out; ret = 0; out: if (no_rcu) diff --git a/kernel/fork.c b/kernel/fork.c index 080809560072..86425305cd4a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -692,7 +692,7 @@ void __mmdrop(struct mm_struct *mm) WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); - mmu_notifier_mm_destroy(mm); + mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); free_mm(mm); @@ -1025,7 +1025,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_aio(mm); mm_init_owner(mm, p); RCU_INIT_POINTER(mm->exe_file, NULL); - mmu_notifier_mm_init(mm); + mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; @@ -1508,7 +1508,7 @@ static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); - rcu_assign_pointer(tsk->sighand, sig); + RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; @@ -1832,6 +1832,7 @@ static __latent_entropy struct task_struct *copy_process( struct multiprocess_signals delayed; struct file *pidfile = NULL; u64 clone_flags = args->flags; + struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different @@ -1874,8 +1875,16 @@ static __latent_entropy struct task_struct *copy_process( */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || - (task_active_pid_ns(current) != - current->nsproxy->pid_ns_for_children)) + (task_active_pid_ns(current) != nsp->pid_ns_for_children)) + return ERR_PTR(-EINVAL); + } + + /* + * If the new process will be in a different time namespace + * do not allow it to share VM or a thread group with the forking task. + */ + if (clone_flags & (CLONE_THREAD | CLONE_VM)) { + if (nsp->time_ns != nsp->time_ns_for_children) return ERR_PTR(-EINVAL); } @@ -2821,7 +2830,8 @@ static int check_unshare_flags(unsigned long unshare_flags) if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| - CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP)) + CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| + CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing diff --git a/kernel/futex.c b/kernel/futex.c index 03c518e9747e..0cf84c8664f2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1178,6 +1178,7 @@ out_error: /** * wait_for_owner_exiting - Block until the owner has exited + * @ret: owner's current futex lock status * @exiting: Pointer to the exiting task * * Caller must hold a refcount on @exiting. diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig index 060e8e726755..3941a9c48f83 100644 --- a/kernel/gcov/Kconfig +++ b/kernel/gcov/Kconfig @@ -4,7 +4,7 @@ menu "GCOV-based kernel profiling" config GCOV_KERNEL bool "Enable gcov-based kernel profiling" depends on DEBUG_FS - select CONSTRUCTORS + select CONSTRUCTORS if !UML default n ---help--- This option enables gcov-based code profiling (e.g. for code coverage diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 6c7ca2e983a5..02236b13b359 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/ratelimit.h> #include <linux/irq.h> +#include <linux/sched/isolation.h> #include "internals.h" @@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void) } } +static bool hk_should_isolate(struct irq_data *data, unsigned int cpu) +{ + const struct cpumask *hk_mask; + + if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) + return false; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask)) + return false; + + return cpumask_test_cpu(cpu, hk_mask); +} + static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) { struct irq_data *data = irq_desc_get_irq_data(desc); @@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu) /* * If the interrupt can only be directed to a single target * CPU then it is already assigned to a CPU in the affinity - * mask. No point in trying to move it around. + * mask. No point in trying to move it around unless the + * isolation mechanism requests to move it to an upcoming + * housekeeping CPU. */ - if (!irqd_is_single_target(data)) + if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu)) irq_set_affinity_locked(data, affinity, false); } diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index c1eccd4f6520..a949bd39e343 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -114,6 +114,7 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), BIT_MASK_DESCR(IRQD_CAN_RESERVE), + BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK), BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 3924fbe829d4..c9d8eb7f5c02 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -128,8 +128,6 @@ static inline void unregister_handler_proc(unsigned int irq, extern bool irq_can_set_affinity_usr(unsigned int irq); -extern int irq_select_affinity_usr(unsigned int irq); - extern void irq_set_thread_affinity(struct irq_desc *desc); extern int irq_do_set_affinity(struct irq_data *data, diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 5b8fdd659e54..98a5f10d1900 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -891,6 +891,7 @@ __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) + __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index dd822fd8a7d5..7527e5ef6fe5 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -987,6 +987,23 @@ const struct irq_domain_ops irq_domain_simple_ops = { EXPORT_SYMBOL_GPL(irq_domain_simple_ops); /** + * irq_domain_translate_onecell() - Generic translate for direct one cell + * bindings + */ +int irq_domain_translate_onecell(struct irq_domain *d, + struct irq_fwspec *fwspec, + unsigned long *out_hwirq, + unsigned int *out_type) +{ + if (WARN_ON(fwspec->param_count < 1)) + return -EINVAL; + *out_hwirq = fwspec->param[0]; + *out_type = IRQ_TYPE_NONE; + return 0; +} +EXPORT_SYMBOL_GPL(irq_domain_translate_onecell); + +/** * irq_domain_translate_twocell() - Generic translate for direct two cell * bindings * @@ -1459,6 +1476,7 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg) if (rv) { /* Restore the original irq_data. */ *root_irq_data = *child_irq_data; + kfree(child_irq_data); goto error; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1753486b440c..7eee98c38f25 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/sched/rt.h> #include <linux/sched/task.h> +#include <linux/sched/isolation.h> #include <uapi/linux/sched/types.h> #include <linux/task_work.h> @@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, if (!chip || !chip->irq_set_affinity) return -EINVAL; - ret = chip->irq_set_affinity(data, mask, force); + /* + * If this is a managed interrupt and housekeeping is enabled on + * it check whether the requested affinity mask intersects with + * a housekeeping CPU. If so, then remove the isolated CPUs from + * the mask and just keep the housekeeping CPU(s). This prevents + * the affinity setter from routing the interrupt to an isolated + * CPU to avoid that I/O submitted from a housekeeping CPU causes + * interrupts on an isolated one. + * + * If the masks do not intersect or include online CPU(s) then + * keep the requested mask. The isolated target CPUs are only + * receiving interrupts when the I/O operation was submitted + * directly from them. + * + * If all housekeeping CPUs in the affinity mask are offline, the + * interrupt will be migrated by the CPU hotplug code once a + * housekeeping CPU which belongs to the affinity mask comes + * online. + */ + if (irqd_affinity_is_managed(data) && + housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) { + const struct cpumask *hk_mask, *prog_mask; + + static DEFINE_RAW_SPINLOCK(tmp_mask_lock); + static struct cpumask tmp_mask; + + hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ); + + raw_spin_lock(&tmp_mask_lock); + cpumask_and(&tmp_mask, mask, hk_mask); + if (!cpumask_intersects(&tmp_mask, cpu_online_mask)) + prog_mask = mask; + else + prog_mask = &tmp_mask; + ret = chip->irq_set_affinity(data, prog_mask, force); + raw_spin_unlock(&tmp_mask_lock); + } else { + ret = chip->irq_set_affinity(data, mask, force); + } switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: @@ -442,23 +481,9 @@ int irq_setup_affinity(struct irq_desc *desc) { return irq_select_affinity(irq_desc_get_irq(desc)); } -#endif - -/* - * Called when a bogus affinity is set via /proc/irq - */ -int irq_select_affinity_usr(unsigned int irq) -{ - struct irq_desc *desc = irq_to_desc(irq); - unsigned long flags; - int ret; +#endif /* CONFIG_AUTO_IRQ_AFFINITY */ +#endif /* CONFIG_SMP */ - raw_spin_lock_irqsave(&desc->lock, flags); - ret = irq_setup_affinity(desc); - raw_spin_unlock_irqrestore(&desc->lock, flags); - return ret; -} -#endif /** * irq_set_vcpu_affinity - Set vcpu affinity for the interrupt @@ -692,6 +717,13 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on) * * Wakeup mode lets this IRQ wake the system from sleep * states like "suspend to RAM". + * + * Note: irq enable/disable state is completely orthogonal + * to the enable/disable state of irq wake. An irq can be + * disabled with disable_irq() and still wake the system as + * long as the irq has wake enabled. If this does not hold, + * then the underlying irq chip and the related driver need + * to be investigated. */ int irq_set_irq_wake(unsigned int irq, unsigned int on) { @@ -1500,8 +1532,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) * has. The type flags are unreliable as the * underlying chip implementation can override them. */ - pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n", - irq); + pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n", + new->name, irq); ret = -EINVAL; goto out_unlock; } diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index ad26fbcfbfc8..eb95f6106a1e 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -453,8 +453,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, continue; irq_data = irq_domain_get_irq_data(domain, desc->irq); - if (!can_reserve) + if (!can_reserve) { irqd_clr_can_reserve(irq_data); + if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) + irqd_set_msi_nomask_quirk(irq_data); + } ret = irq_domain_activate_irq(irq_data, can_reserve); if (ret) goto cleanup; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index cfc4f088a0e7..32c071d7bc03 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -111,6 +111,28 @@ static int irq_affinity_list_proc_show(struct seq_file *m, void *v) return show_irq_affinity(AFFINITY_LIST, m); } +#ifndef CONFIG_AUTO_IRQ_AFFINITY +static inline int irq_select_affinity_usr(unsigned int irq) +{ + /* + * If the interrupt is started up already then this fails. The + * interrupt is assigned to an online CPU already. There is no + * point to move it around randomly. Tell user space that the + * selected mask is bogus. + * + * If not then any change to the affinity is pointless because the + * startup code invokes irq_setup_affinity() which will select + * a online CPU anyway. + */ + return -EINVAL; +} +#else +/* ALPHA magic affinity auto selector. Keep it for historical reasons. */ +static inline int irq_select_affinity_usr(unsigned int irq) +{ + return irq_select_affinity(irq); +} +#endif static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) @@ -176,20 +198,20 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); } -static const struct file_operations irq_affinity_proc_fops = { - .open = irq_affinity_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = irq_affinity_proc_write, +static const struct proc_ops irq_affinity_proc_ops = { + .proc_open = irq_affinity_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = irq_affinity_proc_write, }; -static const struct file_operations irq_affinity_list_proc_fops = { - .open = irq_affinity_list_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = irq_affinity_list_proc_write, +static const struct proc_ops irq_affinity_list_proc_ops = { + .proc_open = irq_affinity_list_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = irq_affinity_list_proc_write, }; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK @@ -246,12 +268,12 @@ static int default_affinity_open(struct inode *inode, struct file *file) return single_open(file, default_affinity_show, PDE_DATA(inode)); } -static const struct file_operations default_affinity_proc_fops = { - .open = default_affinity_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = default_affinity_write, +static const struct proc_ops default_affinity_proc_ops = { + .proc_open = default_affinity_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = default_affinity_write, }; static int irq_node_proc_show(struct seq_file *m, void *v) @@ -342,7 +364,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ proc_create_data("smp_affinity", 0644, desc->dir, - &irq_affinity_proc_fops, irqp); + &irq_affinity_proc_ops, irqp); /* create /proc/irq/<irq>/affinity_hint */ proc_create_single_data("affinity_hint", 0444, desc->dir, @@ -350,7 +372,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) /* create /proc/irq/<irq>/smp_affinity_list */ proc_create_data("smp_affinity_list", 0644, desc->dir, - &irq_affinity_list_proc_fops, irqp); + &irq_affinity_list_proc_ops, irqp); proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show, irqp); @@ -401,7 +423,7 @@ static void register_default_affinity_proc(void) { #ifdef CONFIG_SMP proc_create("irq/default_smp_affinity", 0644, NULL, - &default_affinity_proc_fops); + &default_affinity_proc_ops); #endif } diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index 2ed97a7c9b2a..f865e5f4d382 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -34,6 +34,7 @@ static atomic_t irq_poll_active; * true and let the handler run. */ bool irq_wait_for_poll(struct irq_desc *desc) + __must_hold(&desc->lock) { if (WARN_ONCE(irq_poll_cpu == smp_processor_id(), "irq poll in progress on cpu %d for irq %d\n", diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 136ce049c4ad..a9b3f660dee7 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -44,7 +44,7 @@ __attribute__((weak, section(".rodata"))); extern const unsigned long kallsyms_relative_base __attribute__((weak, section(".rodata"))); -extern const u8 kallsyms_token_table[] __weak; +extern const char kallsyms_token_table[] __weak; extern const u16 kallsyms_token_index[] __weak; extern const unsigned int kallsyms_markers[] __weak; @@ -58,7 +58,8 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, char *result, size_t maxlen) { int len, skipped_first = 0; - const u8 *tptr, *data; + const char *tptr; + const u8 *data; /* Get the compressed symbol length from the first symbol byte. */ data = &kallsyms_names[off]; @@ -698,16 +699,16 @@ const char *kdb_walk_kallsyms(loff_t *pos) } #endif /* CONFIG_KGDB_KDB */ -static const struct file_operations kallsyms_operations = { - .open = kallsyms_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release_private, +static const struct proc_ops kallsyms_proc_ops = { + .proc_open = kallsyms_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release_private, }; static int __init kallsyms_init(void) { - proc_create("kallsyms", 0444, NULL, &kallsyms_operations); + proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops); return 0; } device_initcall(kallsyms_init); diff --git a/kernel/kexec.c b/kernel/kexec.c index bc933c0db9bf..f977786fe498 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -159,6 +159,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* Install the new kernel and uninstall the old */ image = xchg(dest_image, image); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 15d70a90b50d..c19c0dad1ebe 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -589,6 +589,12 @@ static void kimage_free_extra_pages(struct kimage *image) kimage_free_page_list(&image->unusable_pages); } + +int __weak machine_kexec_post_load(struct kimage *image) +{ + return 0; +} + void kimage_terminate(struct kimage *image) { if (*image->entry != 0) @@ -1171,7 +1177,7 @@ int kernel_kexec(void) * CPU hotplug again; so re-enable it here. */ cpu_hotplug_enable(); - pr_emerg("Starting new kernel\n"); + pr_notice("Starting new kernel\n"); machine_shutdown(); } diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index a2df93948665..faa74d5f6941 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -441,6 +441,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, kimage_terminate(image); + ret = machine_kexec_post_load(image); + if (ret) + goto out; + /* * Free up any temporary buffers allocated which are not needed * after image has been loaded diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 48aaf2ac0d0d..39d30ccf8d87 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -13,6 +13,8 @@ void kimage_terminate(struct kimage *image); int kimage_is_destination_range(struct kimage *image, unsigned long start, unsigned long end); +int machine_kexec_post_load(struct kimage *image); + extern struct mutex kexec_mutex; #ifdef CONFIG_KEXEC_FILE diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 53534aa258a6..2625c241ac00 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -510,6 +510,8 @@ static void do_unoptimize_kprobes(void) arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { + /* Switching from detour code to origin */ + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -610,6 +612,18 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } +static bool optprobe_queued_unopt(struct optimized_kprobe *op) +{ + struct optimized_kprobe *_op; + + list_for_each_entry(_op, &unoptimizing_list, list) { + if (op == _op) + return true; + } + + return false; +} + /* Optimize kprobe if p is ready to be optimized */ static void optimize_kprobe(struct kprobe *p) { @@ -631,17 +645,21 @@ static void optimize_kprobe(struct kprobe *p) return; /* Check if it is already optimized. */ - if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) + if (op->kp.flags & KPROBE_FLAG_OPTIMIZED) { + if (optprobe_queued_unopt(op)) { + /* This is under unoptimizing. Just dequeue the probe */ + list_del_init(&op->list); + } return; + } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; - if (!list_empty(&op->list)) - /* This is under unoptimizing. Just dequeue the probe */ - list_del_init(&op->list); - else { - list_add(&op->list, &optimizing_list); - kick_kprobe_optimizer(); - } + /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ + if (WARN_ON_ONCE(!list_empty(&op->list))) + return; + + list_add(&op->list, &optimizing_list); + kick_kprobe_optimizer(); } /* Short cut to direct unoptimizing */ @@ -649,6 +667,7 @@ static void force_unoptimize_kprobe(struct optimized_kprobe *op) { lockdep_assert_cpus_held(); arch_unoptimize_kprobe(op); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); } @@ -662,31 +681,33 @@ static void unoptimize_kprobe(struct kprobe *p, bool force) return; /* This is not an optprobe nor optimized */ op = container_of(p, struct optimized_kprobe, kp); - if (!kprobe_optimized(p)) { - /* Unoptimized or unoptimizing case */ - if (force && !list_empty(&op->list)) { - /* - * Only if this is unoptimizing kprobe and forced, - * forcibly unoptimize it. (No need to unoptimize - * unoptimized kprobe again :) - */ - list_del_init(&op->list); - force_unoptimize_kprobe(op); - } + if (!kprobe_optimized(p)) return; - } - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (!list_empty(&op->list)) { - /* Dequeue from the optimization queue */ - list_del_init(&op->list); + if (optprobe_queued_unopt(op)) { + /* Queued in unoptimizing queue */ + if (force) { + /* + * Forcibly unoptimize the kprobe here, and queue it + * in the freeing list for release afterwards. + */ + force_unoptimize_kprobe(op); + list_move(&op->list, &freeing_list); + } + } else { + /* Dequeue from the optimizing queue */ + list_del_init(&op->list); + op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + } return; } + /* Optimized kprobe case */ - if (force) + if (force) { /* Forcibly update the code: this is a special case */ force_unoptimize_kprobe(op); - else { + } else { list_add(&op->list, &unoptimizing_list); kick_kprobe_optimizer(); } diff --git a/kernel/latencytop.c b/kernel/latencytop.c index e3acead004e6..8d1c15832e55 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -255,17 +255,17 @@ static int lstats_open(struct inode *inode, struct file *filp) return single_open(filp, lstats_show, NULL); } -static const struct file_operations lstats_fops = { - .open = lstats_open, - .read = seq_read, - .write = lstats_write, - .llseek = seq_lseek, - .release = single_release, +static const struct proc_ops lstats_proc_ops = { + .proc_open = lstats_open, + .proc_read = seq_read, + .proc_write = lstats_write, + .proc_lseek = seq_lseek, + .proc_release = single_release, }; static int __init init_lstats_procfs(void) { - proc_create("latency_stats", 0644, NULL, &lstats_fops); + proc_create("latency_stats", 0644, NULL, &lstats_proc_ops); return 0; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 32282e7112d3..32406ef0d6a2 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -482,7 +482,7 @@ static struct lock_trace *save_trace(void) struct lock_trace *trace, *t2; struct hlist_head *hash_head; u32 hash; - unsigned int max_entries; + int max_entries; BUILD_BUG_ON_NOT_POWER_OF_2(STACK_TRACE_HASH_SIZE); BUILD_BUG_ON(LOCK_TRACE_SIZE_IN_LONGS >= MAX_STACK_TRACE_ENTRIES); @@ -490,10 +490,8 @@ static struct lock_trace *save_trace(void) trace = (struct lock_trace *)(stack_trace + nr_stack_trace_entries); max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries - LOCK_TRACE_SIZE_IN_LONGS; - trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); - if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES - - LOCK_TRACE_SIZE_IN_LONGS - 1) { + if (max_entries <= 0) { if (!debug_locks_off_graph_unlock()) return NULL; @@ -502,6 +500,7 @@ static struct lock_trace *save_trace(void) return NULL; } + trace->nr_entries = stack_trace_save(trace->entries, max_entries, 3); hash = jhash(trace->entries, trace->nr_entries * sizeof(trace->entries[0]), 0); diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index dadb7b7fba37..231684cfc5ae 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -286,9 +286,9 @@ static int lockdep_stats_show(struct seq_file *m, void *v) seq_printf(m, " stack-trace entries: %11lu [max: %lu]\n", nr_stack_trace_entries, MAX_STACK_TRACE_ENTRIES); #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) - seq_printf(m, " number of stack traces: %llu\n", + seq_printf(m, " number of stack traces: %11llu\n", lockdep_stack_trace_count()); - seq_printf(m, " number of stack hash chains: %llu\n", + seq_printf(m, " number of stack hash chains: %11llu\n", lockdep_stack_hash_count()); #endif seq_printf(m, " combined max dependencies: %11u\n", @@ -643,12 +643,12 @@ static int lock_stat_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations proc_lock_stat_operations = { - .open = lock_stat_open, - .write = lock_stat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = lock_stat_release, +static const struct proc_ops lock_stat_proc_ops = { + .proc_open = lock_stat_open, + .proc_write = lock_stat_write, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = lock_stat_release, }; #endif /* CONFIG_LOCK_STAT */ @@ -660,8 +660,7 @@ static int __init lockdep_proc_init(void) #endif proc_create_single("lockdep_stats", S_IRUSR, NULL, lockdep_stats_show); #ifdef CONFIG_LOCK_STAT - proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, - &proc_lock_stat_operations); + proc_create("lock_stat", S_IRUSR | S_IWUSR, NULL, &lock_stat_proc_ops); #endif return 0; diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 6ef600aa0f47..1f7734949ac8 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -134,20 +134,17 @@ bool osq_lock(struct optimistic_spin_queue *lock) * cmpxchg in an attempt to undo our queueing. */ - while (!READ_ONCE(node->locked)) { - /* - * If we need to reschedule bail... so we can block. - * Use vcpu_is_preempted() to avoid waiting for a preempted - * lock holder: - */ - if (need_resched() || vcpu_is_preempted(node_cpu(node->prev))) - goto unqueue; - - cpu_relax(); - } - return true; + /* + * Wait to acquire the lock or cancelation. Note that need_resched() + * will come with an IPI, which will wake smp_cond_load_relaxed() if it + * is implemented with a monitor-wait. vcpu_is_preempted() relies on + * polling, be careful. + */ + if (smp_cond_load_relaxed(&node->locked, VAL || need_resched() || + vcpu_is_preempted(node_cpu(node->prev)))) + return true; -unqueue: + /* unqueue */ /* * Step - A -- stabilize @prev * diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 2473f10c6956..b9515fcc9b29 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -31,14 +31,15 @@ /* * The basic principle of a queue-based spinlock can best be understood * by studying a classic queue-based spinlock implementation called the - * MCS lock. The paper below provides a good description for this kind - * of lock. + * MCS lock. A copy of the original MCS lock paper ("Algorithms for Scalable + * Synchronization on Shared-Memory Multiprocessors by Mellor-Crummey and + * Scott") is available at * - * http://www.cise.ufl.edu/tr/DOC/REP-1992-71.pdf + * https://bugzilla.kernel.org/show_bug.cgi?id=206115 * - * This queued spinlock implementation is based on the MCS lock, however to make - * it fit the 4 bytes we assume spinlock_t to be, and preserve its existing - * API, we must modify it somehow. + * This queued spinlock implementation is based on the MCS lock, however to + * make it fit the 4 bytes we assume spinlock_t to be, and preserve its + * existing API, we must modify it somehow. * * In particular; where the traditional MCS lock consists of a tail pointer * (8 bytes) and needs the next pointer (another 8 bytes) of its own node to diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 44e68761f432..0d9b6be9ecc8 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1226,8 +1226,8 @@ wait: * In this case, we attempt to acquire the lock again * without sleeping. */ - if ((wstate == WRITER_HANDOFF) && - (rwsem_spin_on_owner(sem, 0) == OWNER_NULL)) + if (wstate == WRITER_HANDOFF && + rwsem_spin_on_owner(sem, RWSEM_NONSPINNABLE) == OWNER_NULL) goto trylock_again; /* Block until there are no active lockers. */ diff --git a/kernel/module.c b/kernel/module.c index b56f3224b161..33569a01d6e1 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -214,7 +214,8 @@ static struct module *mod_find(unsigned long addr) { struct module *mod; - list_for_each_entry_rcu(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list, + lockdep_is_held(&module_mutex)) { if (within_module(addr, mod)) return mod; } @@ -448,7 +449,8 @@ bool each_symbol_section(bool (*fn)(const struct symsearch *arr, if (each_symbol_in_section(arr, ARRAY_SIZE(arr), NULL, fn, data)) return true; - list_for_each_entry_rcu(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list, + lockdep_is_held(&module_mutex)) { struct symsearch arr[] = { { mod->syms, mod->syms + mod->num_syms, mod->crcs, NOT_GPL_ONLY, false }, @@ -616,7 +618,8 @@ static struct module *find_module_all(const char *name, size_t len, module_assert_mutex_or_preempt(); - list_for_each_entry_rcu(mod, &modules, list) { + list_for_each_entry_rcu(mod, &modules, list, + lockdep_is_held(&module_mutex)) { if (!even_unformed && mod->state == MODULE_STATE_UNFORMED) continue; if (strlen(mod->name) == len && !memcmp(mod->name, name, len)) @@ -1781,6 +1784,8 @@ static int module_add_modinfo_attrs(struct module *mod) error_out: if (i > 0) module_remove_modinfo_attrs(mod, --i); + else + kfree(mod->modinfo_attrs); return error; } @@ -2031,49 +2036,6 @@ static void module_enable_nx(const struct module *mod) frob_writable_data(&mod->init_layout, set_memory_nx); } -/* Iterate through all modules and set each module's text as RW */ -void set_all_modules_text_rw(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - if (mod->state == MODULE_STATE_UNFORMED) - continue; - - frob_text(&mod->core_layout, set_memory_rw); - frob_text(&mod->init_layout, set_memory_rw); - } - mutex_unlock(&module_mutex); -} - -/* Iterate through all modules and set each module's text as RO */ -void set_all_modules_text_ro(void) -{ - struct module *mod; - - if (!rodata_enabled) - return; - - mutex_lock(&module_mutex); - list_for_each_entry_rcu(mod, &modules, list) { - /* - * Ignore going modules since it's possible that ro - * protection has already been disabled, otherwise we'll - * run into protection faults at module deallocation. - */ - if (mod->state == MODULE_STATE_UNFORMED || - mod->state == MODULE_STATE_GOING) - continue; - - frob_text(&mod->core_layout, set_memory_ro); - frob_text(&mod->init_layout, set_memory_ro); - } - mutex_unlock(&module_mutex); -} #else /* !CONFIG_STRICT_MODULE_RWX */ static void module_enable_nx(const struct module *mod) { } #endif /* CONFIG_STRICT_MODULE_RWX */ @@ -2877,7 +2839,7 @@ static int module_sig_check(struct load_info *info, int flags) reason = "Loading of module with unavailable key"; decide: if (is_module_sig_enforced()) { - pr_notice("%s is rejected\n", reason); + pr_notice("%s: %s is rejected\n", info->name, reason); return -EKEYREJECTED; } @@ -3054,9 +3016,7 @@ static int setup_load_info(struct load_info *info, int flags) /* Try to find a name early so we can log errors with a module name */ info->index.info = find_sec(info, ".modinfo"); - if (!info->index.info) - info->name = "(missing .modinfo section)"; - else + if (info->index.info) info->name = get_modinfo(info, "name"); /* Find internal symbols and strings. */ @@ -3071,14 +3031,15 @@ static int setup_load_info(struct load_info *info, int flags) } if (info->index.sym == 0) { - pr_warn("%s: module has no symbols (stripped?)\n", info->name); + pr_warn("%s: module has no symbols (stripped?)\n", + info->name ?: "(missing .modinfo section or name field)"); return -ENOEXEC; } info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); if (!info->index.mod) { pr_warn("%s: No module found in object\n", - info->name ?: "(missing .modinfo name field)"); + info->name ?: "(missing .modinfo section or name field)"); return -ENOEXEC; } /* This is temporary: point mod into copy of data. */ @@ -4393,16 +4354,16 @@ static int modules_open(struct inode *inode, struct file *file) return err; } -static const struct file_operations proc_modules_operations = { - .open = modules_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops modules_proc_ops = { + .proc_open = modules_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; static int __init proc_modules_init(void) { - proc_create("modules", 0, NULL, &proc_modules_operations); + proc_create("modules", 0, NULL, &modules_proc_ops); return 0; } module_init(proc_modules_init); diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index c815f58e6bc0..ed9882108cd2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -18,6 +18,7 @@ #include <linux/pid_namespace.h> #include <net/net_namespace.h> #include <linux/ipc_namespace.h> +#include <linux/time_namespace.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/syscalls.h> @@ -40,6 +41,10 @@ struct nsproxy init_nsproxy = { #ifdef CONFIG_CGROUPS .cgroup_ns = &init_cgroup_ns, #endif +#ifdef CONFIG_TIME_NS + .time_ns = &init_time_ns, + .time_ns_for_children = &init_time_ns, +#endif }; static inline struct nsproxy *create_nsproxy(void) @@ -106,8 +111,18 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_net; } + new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns, + tsk->nsproxy->time_ns_for_children); + if (IS_ERR(new_nsp->time_ns_for_children)) { + err = PTR_ERR(new_nsp->time_ns_for_children); + goto out_time; + } + new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns); + return new_nsp; +out_time: + put_net(new_nsp->net_ns); out_net: put_cgroup_ns(new_nsp->cgroup_ns); out_cgroup: @@ -136,15 +151,16 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) struct nsproxy *old_ns = tsk->nsproxy; struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); struct nsproxy *new_ns; + int ret; if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWPID | CLONE_NEWNET | - CLONE_NEWCGROUP)))) { - get_nsproxy(old_ns); - return 0; - } - - if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + CLONE_NEWCGROUP | CLONE_NEWTIME)))) { + if (likely(old_ns->time_ns_for_children == old_ns->time_ns)) { + get_nsproxy(old_ns); + return 0; + } + } else if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; /* @@ -162,6 +178,12 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) if (IS_ERR(new_ns)) return PTR_ERR(new_ns); + ret = timens_on_fork(new_ns, tsk); + if (ret) { + free_nsproxy(new_ns); + return ret; + } + tsk->nsproxy = new_ns; return 0; } @@ -176,6 +198,10 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns_for_children) put_pid_ns(ns->pid_ns_for_children); + if (ns->time_ns) + put_time_ns(ns->time_ns); + if (ns->time_ns_for_children) + put_time_ns(ns->time_ns_for_children); put_cgroup_ns(ns->cgroup_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); @@ -192,7 +218,8 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP))) + CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP | + CLONE_NEWTIME))) return 0; user_ns = new_cred ? new_cred->user_ns : current_user_ns(); diff --git a/kernel/padata.c b/kernel/padata.c index c3fec1413295..72777c10bb9c 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -2,7 +2,7 @@ /* * padata.c - generic interface to process data streams in parallel * - * See Documentation/padata.txt for an api documentation. + * See Documentation/core-api/padata.rst for more information. * * Copyright (C) 2008, 2009 secunet Security Networks AG * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com> @@ -35,6 +35,8 @@ #define MAX_OBJ_NUM 1000 +static void padata_free_pd(struct parallel_data *pd); + static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { int cpu, target_cpu; @@ -87,7 +89,7 @@ static void padata_parallel_worker(struct work_struct *parallel_work) /** * padata_do_parallel - padata parallelization function * - * @pinst: padata instance + * @ps: padatashell * @padata: object to be parallelized * @cb_cpu: pointer to the CPU that the serialization callback function should * run on. If it's not in the serial cpumask of @pinst @@ -97,17 +99,20 @@ static void padata_parallel_worker(struct work_struct *parallel_work) * The parallelization callback function will run with BHs off. * Note: Every object which is parallelized by padata_do_parallel * must be seen by padata_do_serial. + * + * Return: 0 on success or else negative error code. */ -int padata_do_parallel(struct padata_instance *pinst, +int padata_do_parallel(struct padata_shell *ps, struct padata_priv *padata, int *cb_cpu) { + struct padata_instance *pinst = ps->pinst; int i, cpu, cpu_index, target_cpu, err; struct padata_parallel_queue *queue; struct parallel_data *pd; rcu_read_lock_bh(); - pd = rcu_dereference_bh(pinst->pd); + pd = rcu_dereference_bh(ps->pd); err = -EINVAL; if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID) @@ -160,14 +165,12 @@ EXPORT_SYMBOL(padata_do_parallel); /* * padata_find_next - Find the next object that needs serialization. * - * Return values are: - * - * A pointer to the control struct of the next object that needs - * serialization, if present in one of the percpu reorder queues. - * - * NULL, if the next object that needs serialization will - * be parallel processed by another cpu and is not yet present in - * the cpu's reorder queue. + * Return: + * * A pointer to the control struct of the next object that needs + * serialization, if present in one of the percpu reorder queues. + * * NULL, if the next object that needs serialization will + * be parallel processed by another cpu and is not yet present in + * the cpu's reorder queue. */ static struct padata_priv *padata_find_next(struct parallel_data *pd, bool remove_object) @@ -199,7 +202,6 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd, if (remove_object) { list_del_init(&padata->list); - atomic_dec(&pd->reorder_objects); ++pd->processed; pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu, -1, false); } @@ -210,10 +212,10 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd, static void padata_reorder(struct parallel_data *pd) { + struct padata_instance *pinst = pd->ps->pinst; int cb_cpu; struct padata_priv *padata; struct padata_serial_queue *squeue; - struct padata_instance *pinst = pd->pinst; struct padata_parallel_queue *next_queue; /* @@ -283,6 +285,7 @@ static void padata_serial_worker(struct work_struct *serial_work) struct padata_serial_queue *squeue; struct parallel_data *pd; LIST_HEAD(local_list); + int cnt; local_bh_disable(); squeue = container_of(serial_work, struct padata_serial_queue, work); @@ -292,6 +295,8 @@ static void padata_serial_worker(struct work_struct *serial_work) list_replace_init(&squeue->serial.list, &local_list); spin_unlock(&squeue->serial.lock); + cnt = 0; + while (!list_empty(&local_list)) { struct padata_priv *padata; @@ -301,9 +306,12 @@ static void padata_serial_worker(struct work_struct *serial_work) list_del_init(&padata->list); padata->serial(padata); - atomic_dec(&pd->refcnt); + cnt++; } local_bh_enable(); + + if (atomic_sub_and_test(cnt, &pd->refcnt)) + padata_free_pd(pd); } /** @@ -327,7 +335,6 @@ void padata_do_serial(struct padata_priv *padata) if (cur->seq_nr < padata->seq_nr) break; list_add(&padata->list, &cur->list); - atomic_inc(&pd->reorder_objects); spin_unlock(&pqueue->reorder.lock); /* @@ -341,36 +348,39 @@ void padata_do_serial(struct padata_priv *padata) } EXPORT_SYMBOL(padata_do_serial); -static int padata_setup_cpumasks(struct parallel_data *pd, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask) +static int padata_setup_cpumasks(struct padata_instance *pinst) { struct workqueue_attrs *attrs; + int err; + + attrs = alloc_workqueue_attrs(); + if (!attrs) + return -ENOMEM; + + /* Restrict parallel_wq workers to pd->cpumask.pcpu. */ + cpumask_copy(attrs->cpumask, pinst->cpumask.pcpu); + err = apply_workqueue_attrs(pinst->parallel_wq, attrs); + free_workqueue_attrs(attrs); + + return err; +} + +static int pd_setup_cpumasks(struct parallel_data *pd, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) +{ int err = -ENOMEM; if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) goto out; - cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_online_mask); - if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) goto free_pcpu_mask; - cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_online_mask); - attrs = alloc_workqueue_attrs(); - if (!attrs) - goto free_cbcpu_mask; - - /* Restrict parallel_wq workers to pd->cpumask.pcpu. */ - cpumask_copy(attrs->cpumask, pd->cpumask.pcpu); - err = apply_workqueue_attrs(pd->pinst->parallel_wq, attrs); - free_workqueue_attrs(attrs); - if (err < 0) - goto free_cbcpu_mask; + cpumask_copy(pd->cpumask.pcpu, pcpumask); + cpumask_copy(pd->cpumask.cbcpu, cbcpumask); return 0; -free_cbcpu_mask: - free_cpumask_var(pd->cpumask.cbcpu); free_pcpu_mask: free_cpumask_var(pd->cpumask.pcpu); out: @@ -414,12 +424,16 @@ static void padata_init_pqueues(struct parallel_data *pd) } /* Allocate and initialize the internal cpumask dependend resources. */ -static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, - const struct cpumask *pcpumask, - const struct cpumask *cbcpumask) +static struct parallel_data *padata_alloc_pd(struct padata_shell *ps) { + struct padata_instance *pinst = ps->pinst; + const struct cpumask *cbcpumask; + const struct cpumask *pcpumask; struct parallel_data *pd; + cbcpumask = pinst->rcpumask.cbcpu; + pcpumask = pinst->rcpumask.pcpu; + pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL); if (!pd) goto err; @@ -432,15 +446,14 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, if (!pd->squeue) goto err_free_pqueue; - pd->pinst = pinst; - if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0) + pd->ps = ps; + if (pd_setup_cpumasks(pd, pcpumask, cbcpumask)) goto err_free_squeue; padata_init_pqueues(pd); padata_init_squeues(pd); atomic_set(&pd->seq_nr, -1); - atomic_set(&pd->reorder_objects, 0); - atomic_set(&pd->refcnt, 0); + atomic_set(&pd->refcnt, 1); spin_lock_init(&pd->lock); pd->cpu = cpumask_first(pd->cpumask.pcpu); INIT_WORK(&pd->reorder_work, invoke_padata_reorder); @@ -466,29 +479,6 @@ static void padata_free_pd(struct parallel_data *pd) kfree(pd); } -/* Flush all objects out of the padata queues. */ -static void padata_flush_queues(struct parallel_data *pd) -{ - int cpu; - struct padata_parallel_queue *pqueue; - struct padata_serial_queue *squeue; - - for_each_cpu(cpu, pd->cpumask.pcpu) { - pqueue = per_cpu_ptr(pd->pqueue, cpu); - flush_work(&pqueue->work); - } - - if (atomic_read(&pd->reorder_objects)) - padata_reorder(pd); - - for_each_cpu(cpu, pd->cpumask.cbcpu) { - squeue = per_cpu_ptr(pd->squeue, cpu); - flush_work(&squeue->work); - } - - BUG_ON(atomic_read(&pd->refcnt) != 0); -} - static void __padata_start(struct padata_instance *pinst) { pinst->flags |= PADATA_INIT; @@ -502,72 +492,52 @@ static void __padata_stop(struct padata_instance *pinst) pinst->flags &= ~PADATA_INIT; synchronize_rcu(); - - get_online_cpus(); - padata_flush_queues(pinst->pd); - put_online_cpus(); } /* Replace the internal control structure with a new one. */ -static void padata_replace(struct padata_instance *pinst, - struct parallel_data *pd_new) +static int padata_replace_one(struct padata_shell *ps) +{ + struct parallel_data *pd_new; + + pd_new = padata_alloc_pd(ps); + if (!pd_new) + return -ENOMEM; + + ps->opd = rcu_dereference_protected(ps->pd, 1); + rcu_assign_pointer(ps->pd, pd_new); + + return 0; +} + +static int padata_replace(struct padata_instance *pinst) { - struct parallel_data *pd_old = pinst->pd; - int notification_mask = 0; + struct padata_shell *ps; + int err; pinst->flags |= PADATA_RESET; - rcu_assign_pointer(pinst->pd, pd_new); + cpumask_and(pinst->rcpumask.pcpu, pinst->cpumask.pcpu, + cpu_online_mask); - synchronize_rcu(); + cpumask_and(pinst->rcpumask.cbcpu, pinst->cpumask.cbcpu, + cpu_online_mask); - if (!cpumask_equal(pd_old->cpumask.pcpu, pd_new->cpumask.pcpu)) - notification_mask |= PADATA_CPU_PARALLEL; - if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu)) - notification_mask |= PADATA_CPU_SERIAL; + list_for_each_entry(ps, &pinst->pslist, list) { + err = padata_replace_one(ps); + if (err) + break; + } - padata_flush_queues(pd_old); - padata_free_pd(pd_old); + synchronize_rcu(); - if (notification_mask) - blocking_notifier_call_chain(&pinst->cpumask_change_notifier, - notification_mask, - &pd_new->cpumask); + list_for_each_entry_continue_reverse(ps, &pinst->pslist, list) + if (atomic_dec_and_test(&ps->opd->refcnt)) + padata_free_pd(ps->opd); pinst->flags &= ~PADATA_RESET; -} - -/** - * padata_register_cpumask_notifier - Registers a notifier that will be called - * if either pcpu or cbcpu or both cpumasks change. - * - * @pinst: A poineter to padata instance - * @nblock: A pointer to notifier block. - */ -int padata_register_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock) -{ - return blocking_notifier_chain_register(&pinst->cpumask_change_notifier, - nblock); -} -EXPORT_SYMBOL(padata_register_cpumask_notifier); -/** - * padata_unregister_cpumask_notifier - Unregisters cpumask notifier - * registered earlier using padata_register_cpumask_notifier - * - * @pinst: A pointer to data instance. - * @nlock: A pointer to notifier block. - */ -int padata_unregister_cpumask_notifier(struct padata_instance *pinst, - struct notifier_block *nblock) -{ - return blocking_notifier_chain_unregister( - &pinst->cpumask_change_notifier, - nblock); + return err; } -EXPORT_SYMBOL(padata_unregister_cpumask_notifier); - /* If cpumask contains no active cpu, we mark the instance as invalid. */ static bool padata_validate_cpumask(struct padata_instance *pinst, @@ -587,7 +557,7 @@ static int __padata_set_cpumasks(struct padata_instance *pinst, cpumask_var_t cbcpumask) { int valid; - struct parallel_data *pd; + int err; valid = padata_validate_cpumask(pinst, pcpumask); if (!valid) { @@ -600,29 +570,26 @@ static int __padata_set_cpumasks(struct padata_instance *pinst, __padata_stop(pinst); out_replace: - pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); - if (!pd) - return -ENOMEM; - cpumask_copy(pinst->cpumask.pcpu, pcpumask); cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); - padata_replace(pinst, pd); + err = padata_setup_cpumasks(pinst) ?: padata_replace(pinst); if (valid) __padata_start(pinst); - return 0; + return err; } /** - * padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value - * equivalent to @cpumask. - * + * padata_set_cpumask - Sets specified by @cpumask_type cpumask to the value + * equivalent to @cpumask. * @pinst: padata instance * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding * to parallel and serial cpumasks respectively. * @cpumask: the cpumask to use + * + * Return: 0 on success or negative error code */ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask) @@ -630,8 +597,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, struct cpumask *serial_mask, *parallel_mask; int err = -EINVAL; - mutex_lock(&pinst->lock); get_online_cpus(); + mutex_lock(&pinst->lock); switch (cpumask_type) { case PADATA_CPU_PARALLEL: @@ -649,8 +616,8 @@ int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, err = __padata_set_cpumasks(pinst, parallel_mask, serial_mask); out: - put_online_cpus(); mutex_unlock(&pinst->lock); + put_online_cpus(); return err; } @@ -660,6 +627,8 @@ EXPORT_SYMBOL(padata_set_cpumask); * padata_start - start the parallel processing * * @pinst: padata instance to start + * + * Return: 0 on success or negative error code */ int padata_start(struct padata_instance *pinst) { @@ -695,82 +664,33 @@ EXPORT_SYMBOL(padata_stop); static int __padata_add_cpu(struct padata_instance *pinst, int cpu) { - struct parallel_data *pd; + int err = 0; if (cpumask_test_cpu(cpu, cpu_online_mask)) { - pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, - pinst->cpumask.cbcpu); - if (!pd) - return -ENOMEM; - - padata_replace(pinst, pd); + err = padata_replace(pinst); if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) __padata_start(pinst); } - return 0; + return err; } static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) { - struct parallel_data *pd = NULL; - - if (cpumask_test_cpu(cpu, cpu_online_mask)) { + int err = 0; + if (!cpumask_test_cpu(cpu, cpu_online_mask)) { if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) __padata_stop(pinst); - pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, - pinst->cpumask.cbcpu); - if (!pd) - return -ENOMEM; - - padata_replace(pinst, pd); - - cpumask_clear_cpu(cpu, pd->cpumask.cbcpu); - cpumask_clear_cpu(cpu, pd->cpumask.pcpu); + err = padata_replace(pinst); } - return 0; -} - - /** - * padata_remove_cpu - remove a cpu from the one or both(serial and parallel) - * padata cpumasks. - * - * @pinst: padata instance - * @cpu: cpu to remove - * @mask: bitmask specifying from which cpumask @cpu should be removed - * The @mask may be any combination of the following flags: - * PADATA_CPU_SERIAL - serial cpumask - * PADATA_CPU_PARALLEL - parallel cpumask - */ -int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask) -{ - int err; - - if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL))) - return -EINVAL; - - mutex_lock(&pinst->lock); - - get_online_cpus(); - if (mask & PADATA_CPU_SERIAL) - cpumask_clear_cpu(cpu, pinst->cpumask.cbcpu); - if (mask & PADATA_CPU_PARALLEL) - cpumask_clear_cpu(cpu, pinst->cpumask.pcpu); - - err = __padata_remove_cpu(pinst, cpu); - put_online_cpus(); - - mutex_unlock(&pinst->lock); - return err; } -EXPORT_SYMBOL(padata_remove_cpu); static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu) { @@ -793,7 +713,7 @@ static int padata_cpu_online(unsigned int cpu, struct hlist_node *node) return ret; } -static int padata_cpu_prep_down(unsigned int cpu, struct hlist_node *node) +static int padata_cpu_dead(unsigned int cpu, struct hlist_node *node) { struct padata_instance *pinst; int ret; @@ -814,11 +734,15 @@ static enum cpuhp_state hp_online; static void __padata_free(struct padata_instance *pinst) { #ifdef CONFIG_HOTPLUG_CPU + cpuhp_state_remove_instance_nocalls(CPUHP_PADATA_DEAD, &pinst->node); cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node); #endif + WARN_ON(!list_empty(&pinst->pslist)); + padata_stop(pinst); - padata_free_pd(pinst->pd); + free_cpumask_var(pinst->rcpumask.cbcpu); + free_cpumask_var(pinst->rcpumask.pcpu); free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); destroy_workqueue(pinst->serial_wq); @@ -959,13 +883,14 @@ static struct kobj_type padata_attr_type = { * @name: used to identify the instance * @pcpumask: cpumask that will be used for padata parallelization * @cbcpumask: cpumask that will be used for padata serialization + * + * Return: new instance on success, NULL on error */ static struct padata_instance *padata_alloc(const char *name, const struct cpumask *pcpumask, const struct cpumask *cbcpumask) { struct padata_instance *pinst; - struct parallel_data *pd = NULL; pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL); if (!pinst) @@ -993,29 +918,40 @@ static struct padata_instance *padata_alloc(const char *name, !padata_validate_cpumask(pinst, cbcpumask)) goto err_free_masks; - pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); - if (!pd) + if (!alloc_cpumask_var(&pinst->rcpumask.pcpu, GFP_KERNEL)) goto err_free_masks; + if (!alloc_cpumask_var(&pinst->rcpumask.cbcpu, GFP_KERNEL)) + goto err_free_rcpumask_pcpu; - rcu_assign_pointer(pinst->pd, pd); + INIT_LIST_HEAD(&pinst->pslist); cpumask_copy(pinst->cpumask.pcpu, pcpumask); cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); + cpumask_and(pinst->rcpumask.pcpu, pcpumask, cpu_online_mask); + cpumask_and(pinst->rcpumask.cbcpu, cbcpumask, cpu_online_mask); + + if (padata_setup_cpumasks(pinst)) + goto err_free_rcpumask_cbcpu; pinst->flags = 0; - BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier); kobject_init(&pinst->kobj, &padata_attr_type); mutex_init(&pinst->lock); #ifdef CONFIG_HOTPLUG_CPU cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node); + cpuhp_state_add_instance_nocalls_cpuslocked(CPUHP_PADATA_DEAD, + &pinst->node); #endif put_online_cpus(); return pinst; +err_free_rcpumask_cbcpu: + free_cpumask_var(pinst->rcpumask.cbcpu); +err_free_rcpumask_pcpu: + free_cpumask_var(pinst->rcpumask.pcpu); err_free_masks: free_cpumask_var(pinst->cpumask.pcpu); free_cpumask_var(pinst->cpumask.cbcpu); @@ -1036,6 +972,8 @@ err: * parallel workers. * * @name: used to identify the instance + * + * Return: new instance on success, NULL on error */ struct padata_instance *padata_alloc_possible(const char *name) { @@ -1046,7 +984,7 @@ EXPORT_SYMBOL(padata_alloc_possible); /** * padata_free - free a padata instance * - * @padata_inst: padata instance to free + * @pinst: padata instance to free */ void padata_free(struct padata_instance *pinst) { @@ -1054,6 +992,63 @@ void padata_free(struct padata_instance *pinst) } EXPORT_SYMBOL(padata_free); +/** + * padata_alloc_shell - Allocate and initialize padata shell. + * + * @pinst: Parent padata_instance object. + * + * Return: new shell on success, NULL on error + */ +struct padata_shell *padata_alloc_shell(struct padata_instance *pinst) +{ + struct parallel_data *pd; + struct padata_shell *ps; + + ps = kzalloc(sizeof(*ps), GFP_KERNEL); + if (!ps) + goto out; + + ps->pinst = pinst; + + get_online_cpus(); + pd = padata_alloc_pd(ps); + put_online_cpus(); + + if (!pd) + goto out_free_ps; + + mutex_lock(&pinst->lock); + RCU_INIT_POINTER(ps->pd, pd); + list_add(&ps->list, &pinst->pslist); + mutex_unlock(&pinst->lock); + + return ps; + +out_free_ps: + kfree(ps); +out: + return NULL; +} +EXPORT_SYMBOL(padata_alloc_shell); + +/** + * padata_free_shell - free a padata shell + * + * @ps: padata shell to free + */ +void padata_free_shell(struct padata_shell *ps) +{ + struct padata_instance *pinst = ps->pinst; + + mutex_lock(&pinst->lock); + list_del(&ps->list); + padata_free_pd(rcu_dereference_protected(ps->pd, 1)); + mutex_unlock(&pinst->lock); + + kfree(ps); +} +EXPORT_SYMBOL(padata_free_shell); + #ifdef CONFIG_HOTPLUG_CPU static __init int padata_driver_init(void) @@ -1061,17 +1056,24 @@ static __init int padata_driver_init(void) int ret; ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online", - padata_cpu_online, - padata_cpu_prep_down); + padata_cpu_online, NULL); if (ret < 0) return ret; hp_online = ret; + + ret = cpuhp_setup_state_multi(CPUHP_PADATA_DEAD, "padata:dead", + NULL, padata_cpu_dead); + if (ret < 0) { + cpuhp_remove_multi_state(hp_online); + return ret; + } return 0; } module_init(padata_driver_init); static __exit void padata_driver_exit(void) { + cpuhp_remove_multi_state(CPUHP_PADATA_DEAD); cpuhp_remove_multi_state(hp_online); } module_exit(padata_driver_exit); diff --git a/kernel/pid.c b/kernel/pid.c index 2278e249141d..0f4ecb57214c 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -578,3 +578,93 @@ void __init pid_idr_init(void) init_pid_ns.pid_cachep = KMEM_CACHE(pid, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } + +static struct file *__pidfd_fget(struct task_struct *task, int fd) +{ + struct file *file; + int ret; + + ret = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (ret) + return ERR_PTR(ret); + + if (ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS)) + file = fget_task(task, fd); + else + file = ERR_PTR(-EPERM); + + mutex_unlock(&task->signal->cred_guard_mutex); + + return file ?: ERR_PTR(-EBADF); +} + +static int pidfd_getfd(struct pid *pid, int fd) +{ + struct task_struct *task; + struct file *file; + int ret; + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return -ESRCH; + + file = __pidfd_fget(task, fd); + put_task_struct(task); + if (IS_ERR(file)) + return PTR_ERR(file); + + ret = security_file_receive(file); + if (ret) { + fput(file); + return ret; + } + + ret = get_unused_fd_flags(O_CLOEXEC); + if (ret < 0) + fput(file); + else + fd_install(ret, file); + + return ret; +} + +/** + * sys_pidfd_getfd() - Get a file descriptor from another process + * + * @pidfd: the pidfd file descriptor of the process + * @fd: the file descriptor number to get + * @flags: flags on how to get the fd (reserved) + * + * This syscall gets a copy of a file descriptor from another process + * based on the pidfd, and file descriptor number. It requires that + * the calling process has the ability to ptrace the process represented + * by the pidfd. The process which is having its file descriptor copied + * is otherwise unaffected. + * + * Return: On success, a cloexec file descriptor is returned. + * On error, a negative errno number will be returned. + */ +SYSCALL_DEFINE3(pidfd_getfd, int, pidfd, int, fd, + unsigned int, flags) +{ + struct pid *pid; + struct fd f; + int ret; + + /* flags is currently unused - make sure it's unset */ + if (flags) + return -EINVAL; + + f = fdget(pidfd); + if (!f.file) + return -EBADF; + + pid = pidfd_pid(f.file); + if (IS_ERR(pid)) + ret = PTR_ERR(pid); + else + ret = pidfd_getfd(pid, fd); + + fdput(f); + return ret; +} diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index d3667b4075c1..7cbfbeacd68a 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -27,7 +27,10 @@ config SUSPEND_SKIP_SYNC Skip the kernel sys_sync() before freezing user processes. Some systems prefer not to pay this cost on every invocation of suspend, or they are content with invoking sync() from - user-space before invoking suspend. Say Y if that's your case. + user-space before invoking suspend. There's a run-time switch + at '/sys/power/sync_on_suspend' to configure this behaviour. + This setting changes the default for the run-tim switch. Say Y + to change the default to disable the kernel sys_sync(). config HIBERNATE_CALLBACKS bool diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 3c0a5a8170b0..6dbeedb7354c 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -9,7 +9,7 @@ * Copyright (C) 2012 Bojan Smojver <bojan@rexursive.com> */ -#define pr_fmt(fmt) "PM: " fmt +#define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/export.h> #include <linux/suspend.h> @@ -106,7 +106,7 @@ EXPORT_SYMBOL(system_entering_hibernation); #ifdef CONFIG_PM_DEBUG static void hibernation_debug_sleep(void) { - pr_info("hibernation debug: Waiting for 5 seconds.\n"); + pr_info("debug: Waiting for 5 seconds.\n"); mdelay(5000); } @@ -277,7 +277,7 @@ static int create_image(int platform_mode) error = dpm_suspend_end(PMSG_FREEZE); if (error) { - pr_err("Some devices failed to power down, aborting hibernation\n"); + pr_err("Some devices failed to power down, aborting\n"); return error; } @@ -295,7 +295,7 @@ static int create_image(int platform_mode) error = syscore_suspend(); if (error) { - pr_err("Some system devices failed to power down, aborting hibernation\n"); + pr_err("Some system devices failed to power down, aborting\n"); goto Enable_irqs; } @@ -310,7 +310,7 @@ static int create_image(int platform_mode) restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) - pr_err("Error %d creating hibernation image\n", error); + pr_err("Error %d creating image\n", error); if (!in_suspend) { events_check_enabled = false; @@ -680,7 +680,7 @@ static int load_image_and_restore(void) if (!error) hibernation_restore(flags & SF_PLATFORM_MODE); - pr_err("Failed to load hibernation image, recovering.\n"); + pr_err("Failed to load image, recovering.\n"); swsusp_free(); free_basic_memory_bitmaps(); Unlock: @@ -743,7 +743,7 @@ int hibernate(void) else flags |= SF_CRC32_MODE; - pm_pr_dbg("Writing image.\n"); + pm_pr_dbg("Writing hibernation image.\n"); error = swsusp_write(flags); swsusp_free(); if (!error) { @@ -755,7 +755,7 @@ int hibernate(void) in_suspend = 0; pm_restore_gfp_mask(); } else { - pm_pr_dbg("Image restored successfully.\n"); + pm_pr_dbg("Hibernation image restored successfully.\n"); } Free_bitmaps: @@ -894,7 +894,7 @@ static int software_resume(void) goto Close_Finish; } - pm_pr_dbg("Preparing processes for restore.\n"); + pm_pr_dbg("Preparing processes for hibernation restore.\n"); error = freeze_processes(); if (error) goto Close_Finish; @@ -903,7 +903,7 @@ static int software_resume(void) Finish: __pm_notifier_call_chain(PM_POST_RESTORE, nr_calls, NULL); pm_restore_console(); - pr_info("resume from hibernation failed (%d)\n", error); + pr_info("resume failed (%d)\n", error); atomic_inc(&snapshot_device_available); /* For success case, the suspend path will release the lock */ Unlock: @@ -1068,7 +1068,8 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, lock_system_sleep(); swsusp_resume_device = res; unlock_system_sleep(); - pm_pr_dbg("Configured resume from disk to %u\n", swsusp_resume_device); + pm_pr_dbg("Configured hibernation resume from disk to %u\n", + swsusp_resume_device); noresume = 0; software_resume(); return n; diff --git a/kernel/power/main.c b/kernel/power/main.c index e26de7af520b..69b7a8aeca3b 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -190,6 +190,38 @@ static ssize_t mem_sleep_store(struct kobject *kobj, struct kobj_attribute *attr } power_attr(mem_sleep); + +/* + * sync_on_suspend: invoke ksys_sync_helper() before suspend. + * + * show() returns whether ksys_sync_helper() is invoked before suspend. + * store() accepts 0 or 1. 0 disables ksys_sync_helper() and 1 enables it. + */ +bool sync_on_suspend_enabled = !IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC); + +static ssize_t sync_on_suspend_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sprintf(buf, "%d\n", sync_on_suspend_enabled); +} + +static ssize_t sync_on_suspend_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (kstrtoul(buf, 10, &val)) + return -EINVAL; + + if (val > 1) + return -EINVAL; + + sync_on_suspend_enabled = !!val; + return n; +} + +power_attr(sync_on_suspend); #endif /* CONFIG_SUSPEND */ #ifdef CONFIG_PM_SLEEP_DEBUG @@ -855,6 +887,7 @@ static struct attribute * g[] = { &wakeup_count_attr.attr, #ifdef CONFIG_SUSPEND &mem_sleep_attr.attr, + &sync_on_suspend_attr.attr, #endif #ifdef CONFIG_PM_AUTOSLEEP &autosleep_attr.attr, diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 26b9168321e7..d82b7b88d616 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -8,7 +8,7 @@ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> */ -#define pr_fmt(fmt) "PM: " fmt +#define pr_fmt(fmt) "PM: hibernation: " fmt #include <linux/version.h> #include <linux/module.h> @@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void) void clear_free_pages(void) { -#ifdef CONFIG_PAGE_POISONING_ZERO struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; - memory_bm_position_reset(bm); - pfn = memory_bm_next_pfn(bm); - while (pfn != BM_END_OF_MAP) { - if (pfn_valid(pfn)) - clear_highpage(pfn_to_page(pfn)); - + if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) { + memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (pfn_valid(pfn)) + clear_highpage(pfn_to_page(pfn)); + + pfn = memory_bm_next_pfn(bm); + } + memory_bm_position_reset(bm); + pr_info("free pages cleared after restore\n"); } - memory_bm_position_reset(bm); - pr_info("free pages cleared after restore\n"); -#endif /* PAGE_POISONING_ZERO */ } /** @@ -1566,9 +1566,7 @@ static unsigned long preallocate_image_highmem(unsigned long nr_pages) */ static unsigned long __fraction(u64 x, u64 multiplier, u64 base) { - x *= multiplier; - do_div(x, base); - return (unsigned long)x; + return div64_u64(x * multiplier, base); } static unsigned long preallocate_highmem_fraction(unsigned long nr_pages, @@ -1683,7 +1681,7 @@ static unsigned long minimum_image_size(unsigned long saveable) * hibernation for allocations made while saving the image and for device * drivers, in case they need to allocate memory from their hibernation * callbacks (these two numbers are given by PAGES_FOR_IO (which is a rough - * estimate) and reserverd_size divided by PAGE_SIZE (which is tunable through + * estimate) and reserved_size divided by PAGE_SIZE (which is tunable through * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * @@ -1705,16 +1703,20 @@ int hibernate_preallocate_memory(void) ktime_t start, stop; int error; - pr_info("Preallocating image memory... "); + pr_info("Preallocating image memory\n"); start = ktime_get(); error = memory_bm_create(&orig_bm, GFP_IMAGE, PG_ANY); - if (error) + if (error) { + pr_err("Cannot allocate original bitmap\n"); goto err_out; + } error = memory_bm_create(©_bm, GFP_IMAGE, PG_ANY); - if (error) + if (error) { + pr_err("Cannot allocate copy bitmap\n"); goto err_out; + } alloc_normal = 0; alloc_highmem = 0; @@ -1804,8 +1806,11 @@ int hibernate_preallocate_memory(void) alloc -= pages; pages += pages_highmem; pages_highmem = preallocate_image_highmem(alloc); - if (pages_highmem < alloc) + if (pages_highmem < alloc) { + pr_err("Image allocation is %lu pages short\n", + alloc - pages_highmem); goto err_out; + } pages += pages_highmem; /* * size is the desired number of saveable pages to leave in @@ -1836,13 +1841,12 @@ int hibernate_preallocate_memory(void) out: stop = ktime_get(); - pr_cont("done (allocated %lu pages)\n", pages); + pr_info("Allocated %lu pages for snapshot\n", pages); swsusp_show_speed(start, stop, pages, "Allocated"); return 0; err_out: - pr_cont("\n"); swsusp_free(); return -ENOMEM; } @@ -1976,7 +1980,7 @@ asmlinkage __visible int swsusp_save(void) { unsigned int nr_pages, nr_highmem; - pr_info("Creating hibernation image:\n"); + pr_info("Creating image:\n"); drain_local_pages(NULL); nr_pages = count_data_pages(); @@ -2010,7 +2014,7 @@ asmlinkage __visible int swsusp_save(void) nr_copy_pages = nr_pages; nr_meta_pages = DIV_ROUND_UP(nr_pages * sizeof(long), PAGE_SIZE); - pr_info("Hibernation image created (%d pages copied)\n", nr_pages); + pr_info("Image created (%d pages copied)\n", nr_pages); return 0; } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index f3b7239f1892..8b1bb5ee7e5d 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -131,11 +131,12 @@ static void s2idle_loop(void) * to avoid them upfront. */ for (;;) { - if (s2idle_ops && s2idle_ops->wake) - s2idle_ops->wake(); - - if (pm_wakeup_pending()) + if (s2idle_ops && s2idle_ops->wake) { + if (s2idle_ops->wake()) + break; + } else if (pm_wakeup_pending()) { break; + } pm_wakeup_clear(false); @@ -564,7 +565,7 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_TO_IDLE) s2idle_begin(); - if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) { + if (sync_on_suspend_enabled) { trace_suspend_resume(TPS("sync_filesystems"), 0, true); ksys_sync_helper(); trace_suspend_resume(TPS("sync_filesystems"), 0, false); diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c index 60564b58de07..e1ed58adb69e 100644 --- a/kernel/power/suspend_test.c +++ b/kernel/power/suspend_test.c @@ -70,7 +70,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state) static char info_test[] __initdata = KERN_INFO "PM: test RTC wakeup from '%s' suspend\n"; - unsigned long now; + time64_t now; struct rtc_wkalrm alm; int status; @@ -81,10 +81,10 @@ repeat: printk(err_readtime, dev_name(&rtc->dev), status); return; } - rtc_tm_to_time(&alm.time, &now); + now = rtc_tm_to_time64(&alm.time); memset(&alm, 0, sizeof alm); - rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); + rtc_time64_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time); alm.enabled = true; status = rtc_set_alarm(rtc, &alm); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 1ef6f75d92f1..fada22dc4ab6 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -2770,8 +2770,6 @@ void register_console(struct console *newcon) * for us. */ logbuf_lock_irqsave(flags); - console_seq = syslog_seq; - console_idx = syslog_idx; /* * We're about to replay the log buffer. Only do this to the * just-registered console to avoid excessive message spam to @@ -2783,6 +2781,8 @@ void register_console(struct console *newcon) */ exclusive_console = newcon; exclusive_console_stop_seq = console_seq; + console_seq = syslog_seq; + console_idx = syslog_idx; logbuf_unlock_irqrestore(flags); } console_unlock(); diff --git a/kernel/profile.c b/kernel/profile.c index 4b144b02ca5d..6f69a4195d56 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -442,18 +442,18 @@ static ssize_t prof_cpu_mask_proc_write(struct file *file, return err; } -static const struct file_operations prof_cpu_mask_proc_fops = { - .open = prof_cpu_mask_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = prof_cpu_mask_proc_write, +static const struct proc_ops prof_cpu_mask_proc_ops = { + .proc_open = prof_cpu_mask_proc_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_write = prof_cpu_mask_proc_write, }; void create_prof_cpu_mask(void) { /* create /proc/irq/prof_cpu_mask */ - proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_fops); + proc_create("irq/prof_cpu_mask", 0600, NULL, &prof_cpu_mask_proc_ops); } /* @@ -517,10 +517,10 @@ static ssize_t write_profile(struct file *file, const char __user *buf, return count; } -static const struct file_operations proc_profile_operations = { - .read = read_profile, - .write = write_profile, - .llseek = default_llseek, +static const struct proc_ops profile_proc_ops = { + .proc_read = read_profile, + .proc_write = write_profile, + .proc_lseek = default_llseek, }; int __ref create_proc_profile(void) @@ -548,7 +548,7 @@ int __ref create_proc_profile(void) err = 0; #endif entry = proc_create("profile", S_IWUSR | S_IRUGO, - NULL, &proc_profile_operations); + NULL, &profile_proc_ops); if (!entry) goto err_state_onl; proc_set_size(entry, (1 + prof_len) * sizeof(atomic_t)); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index cb9ddcc08119..43d6179508d6 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -264,12 +264,17 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) return ret; } -static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) +static bool ptrace_has_cap(const struct cred *cred, struct user_namespace *ns, + unsigned int mode) { + int ret; + if (mode & PTRACE_MODE_NOAUDIT) - return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NOAUDIT); else - return has_ns_capability(current, ns, CAP_SYS_PTRACE); + ret = security_capable(cred, ns, CAP_SYS_PTRACE, CAP_OPT_NONE); + + return ret == 0; } /* Returns 0 on success, -errno on denial. */ @@ -321,7 +326,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) gid_eq(caller_gid, tcred->sgid) && gid_eq(caller_gid, tcred->gid)) goto ok; - if (ptrace_has_cap(tcred->user_ns, mode)) + if (ptrace_has_cap(cred, tcred->user_ns, mode)) goto ok; rcu_read_unlock(); return -EPERM; @@ -340,7 +345,7 @@ ok: mm = task->mm; if (mm && ((get_dumpable(mm) != SUID_DUMP_USER) && - !ptrace_has_cap(mm->user_ns, mode))) + !ptrace_has_cap(cred, mm->user_ns, mode))) return -EPERM; return security_ptrace_access_check(task, mode); diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index 7644eda17d62..1cc940fef17c 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -7,7 +7,7 @@ menu "RCU Subsystem" config TREE_RCU bool - default y if !PREEMPTION && SMP + default y if SMP help This option selects the RCU implementation that is designed for very large SMP system with hundreds or @@ -17,6 +17,7 @@ config TREE_RCU config PREEMPT_RCU bool default y if PREEMPTION + select TREE_RCU help This option selects the RCU implementation that is designed for very large SMP systems with hundreds or @@ -78,7 +79,7 @@ config TASKS_RCU user-mode execution as quiescent states. config RCU_STALL_COMMON - def_bool ( TREE_RCU || PREEMPT_RCU ) + def_bool TREE_RCU help This option enables RCU CPU stall code that is common between the TINY and TREE variants of RCU. The purpose is to allow @@ -86,13 +87,13 @@ config RCU_STALL_COMMON making these warnings mandatory for the tree variants. config RCU_NEED_SEGCBLIST - def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU ) + def_bool ( TREE_RCU || TREE_SRCU ) config RCU_FANOUT int "Tree-based hierarchical RCU fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + depends on TREE_RCU && RCU_EXPERT default 64 if 64BIT default 32 if !64BIT help @@ -112,7 +113,7 @@ config RCU_FANOUT_LEAF int "Tree-based hierarchical RCU leaf-level fanout value" range 2 64 if 64BIT range 2 32 if !64BIT - depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT + depends on TREE_RCU && RCU_EXPERT default 16 help This option controls the leaf-level fanout of hierarchical @@ -187,7 +188,7 @@ config RCU_BOOST_DELAY config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" - depends on TREE_RCU || PREEMPT_RCU + depends on TREE_RCU depends on RCU_EXPERT || NO_HZ_FULL default n help @@ -200,8 +201,8 @@ config RCU_NOCB_CPU 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 + the "p" for RCU-preempt (PREEMPTION kernels) and "s" for RCU-sched + (!PREEMPTION 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/Makefile b/kernel/rcu/Makefile index 020e8b6a644b..82d5fba48b2f 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -9,6 +9,5 @@ obj-$(CONFIG_TINY_SRCU) += srcutiny.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o obj-$(CONFIG_RCU_PERF_TEST) += rcuperf.o obj-$(CONFIG_TREE_RCU) += tree.o -obj-$(CONFIG_PREEMPT_RCU) += tree.o obj-$(CONFIG_TINY_RCU) += tiny.o obj-$(CONFIG_RCU_NEED_SEGCBLIST) += rcu_segcblist.o diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index ab504fbc76ca..05f936ed167a 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -198,33 +198,6 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -void kfree(const void *); - -/* - * Reclaim the specified callback, either by invoking it (non-lazy case) - * or freeing it directly (lazy case). Return true if lazy, false otherwise. - */ -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); - if (__is_kfree_rcu_offset(offset)) { - trace_rcu_invoke_kfree_callback(rn, head, offset); - kfree((void *)head - offset); - rcu_lock_release(&rcu_callback_map); - return true; - } else { - trace_rcu_invoke_callback(rn, head); - f = head->func; - WRITE_ONCE(head->func, (rcu_callback_t)0L); - f(head); - rcu_lock_release(&rcu_callback_map); - return false; - } -} - #ifdef CONFIG_RCU_STALL_COMMON extern int rcu_cpu_stall_ftrace_dump; @@ -281,7 +254,7 @@ void rcu_test_sync_prims(void); */ extern void resched_cpu(int cpu); -#if defined(SRCU) || !defined(TINY_RCU) +#if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) #include <linux/rcu_node_tree.h> @@ -418,7 +391,7 @@ do { \ #define raw_lockdep_assert_held_rcu_node(p) \ lockdep_assert_held(&ACCESS_PRIVATE(p, lock)) -#endif /* #if defined(SRCU) || !defined(TINY_RCU) */ +#endif /* #if defined(CONFIG_SRCU) || !defined(CONFIG_TINY_RCU) */ #ifdef CONFIG_SRCU void srcu_init(void); @@ -454,7 +427,7 @@ enum rcutorture_type { INVALID_RCU_FLAVOR }; -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, unsigned long *gp_seq); void do_trace_rcu_torture_read(const char *rcutorturename, diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index cbc87b804db9..5f4fd3b8777c 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -20,14 +20,10 @@ void rcu_cblist_init(struct rcu_cblist *rclp) rclp->head = NULL; rclp->tail = &rclp->head; rclp->len = 0; - rclp->len_lazy = 0; } /* * Enqueue an rcu_head structure onto the specified callback list. - * This function assumes that the callback is non-lazy because it - * is intended for use by no-CBs CPUs, which do not distinguish - * between lazy and non-lazy RCU callbacks. */ void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp) { @@ -54,7 +50,6 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, else drclp->tail = &drclp->head; drclp->len = srclp->len; - drclp->len_lazy = srclp->len_lazy; if (!rhp) { rcu_cblist_init(srclp); } else { @@ -62,16 +57,12 @@ void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, srclp->head = rhp; srclp->tail = &rhp->next; WRITE_ONCE(srclp->len, 1); - srclp->len_lazy = 0; } } /* * Dequeue the oldest rcu_head structure from the specified callback - * list. This function assumes that the callback is non-lazy, but - * the caller can later invoke rcu_cblist_dequeued_lazy() if it - * finds otherwise (and if it cares about laziness). This allows - * different users to have different ways of determining laziness. + * list. */ struct rcu_head *rcu_cblist_dequeue(struct rcu_cblist *rclp) { @@ -161,7 +152,6 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp) for (i = 0; i < RCU_CBLIST_NSEGS; i++) rsclp->tails[i] = &rsclp->head; rcu_segcblist_set_len(rsclp, 0); - rsclp->len_lazy = 0; rsclp->enabled = 1; } @@ -173,7 +163,6 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) { WARN_ON_ONCE(!rcu_segcblist_empty(rsclp)); WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp)); - WARN_ON_ONCE(rcu_segcblist_n_lazy_cbs(rsclp)); rsclp->enabled = 0; } @@ -253,11 +242,9 @@ bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp) * absolutely not OK for it to ever miss posting a callback. */ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy) + struct rcu_head *rhp) { rcu_segcblist_inc_len(rsclp); - if (lazy) - rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is enqueued. */ rhp->next = NULL; WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp); @@ -275,15 +262,13 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, * period. You have been warned. */ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy) + struct rcu_head *rhp) { int i; if (rcu_segcblist_n_cbs(rsclp) == 0) return false; rcu_segcblist_inc_len(rsclp); - if (lazy) - rsclp->len_lazy++; smp_mb(); /* Ensure counts are updated before callback is entrained. */ rhp->next = NULL; for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--) @@ -307,8 +292,6 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { - rclp->len_lazy += rsclp->len_lazy; - rsclp->len_lazy = 0; rclp->len = rcu_segcblist_xchg_len(rsclp, 0); } @@ -361,9 +344,7 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp, void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { - rsclp->len_lazy += rclp->len_lazy; rcu_segcblist_add_len(rsclp, rclp->len); - rclp->len_lazy = 0; rclp->len = 0; } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 815c2fdd3fcc..5c293afc07b8 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -15,15 +15,6 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp) return READ_ONCE(rclp->len); } -/* - * Account for the fact that a previously dequeued callback turned out - * to be marked as lazy. - */ -static inline void rcu_cblist_dequeued_lazy(struct rcu_cblist *rclp) -{ - rclp->len_lazy--; -} - void rcu_cblist_init(struct rcu_cblist *rclp); void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp); void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, @@ -59,18 +50,6 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) #endif } -/* Return number of lazy callbacks in segmented callback list. */ -static inline long rcu_segcblist_n_lazy_cbs(struct rcu_segcblist *rsclp) -{ - return rsclp->len_lazy; -} - -/* Return number of lazy callbacks in segmented callback list. */ -static inline long rcu_segcblist_n_nonlazy_cbs(struct rcu_segcblist *rsclp) -{ - return rcu_segcblist_n_cbs(rsclp) - rsclp->len_lazy; -} - /* * Is the specified rcu_segcblist enabled, for example, not corresponding * to an offline CPU? @@ -106,9 +85,9 @@ struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp); bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp); void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy); + struct rcu_head *rhp); bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, - struct rcu_head *rhp, bool lazy); + struct rcu_head *rhp); void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index 5f884d560384..da94b89cd531 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -86,6 +86,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN, "Shutdown at end of performance tests."); torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable"); +torture_param(int, kfree_rcu_test, 0, "Do we run a kfree_rcu() perf test?"); static char *perf_type = "rcu"; module_param(perf_type, charp, 0444); @@ -105,8 +106,8 @@ static atomic_t n_rcu_perf_writer_finished; static wait_queue_head_t shutdown_wq; static u64 t_rcu_perf_writer_started; static u64 t_rcu_perf_writer_finished; -static unsigned long b_rcu_perf_writer_started; -static unsigned long b_rcu_perf_writer_finished; +static unsigned long b_rcu_gp_test_started; +static unsigned long b_rcu_gp_test_finished; static DEFINE_PER_CPU(atomic_t, n_async_inflight); #define MAX_MEAS 10000 @@ -378,10 +379,10 @@ rcu_perf_writer(void *arg) if (atomic_inc_return(&n_rcu_perf_writer_started) >= nrealwriters) { t_rcu_perf_writer_started = t; if (gp_exp) { - b_rcu_perf_writer_started = + b_rcu_gp_test_started = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_started = cur_ops->get_gp_seq(); + b_rcu_gp_test_started = cur_ops->get_gp_seq(); } } @@ -429,10 +430,10 @@ retry: PERFOUT_STRING("Test complete"); t_rcu_perf_writer_finished = t; if (gp_exp) { - b_rcu_perf_writer_finished = + b_rcu_gp_test_finished = cur_ops->exp_completed() / 2; } else { - b_rcu_perf_writer_finished = + b_rcu_gp_test_finished = cur_ops->get_gp_seq(); } if (shutdown) { @@ -515,8 +516,8 @@ rcu_perf_cleanup(void) t_rcu_perf_writer_finished - t_rcu_perf_writer_started, ngps, - rcuperf_seq_diff(b_rcu_perf_writer_finished, - b_rcu_perf_writer_started)); + rcuperf_seq_diff(b_rcu_gp_test_finished, + b_rcu_gp_test_started)); for (i = 0; i < nrealwriters; i++) { if (!writer_durations) break; @@ -584,6 +585,159 @@ rcu_perf_shutdown(void *arg) return -EINVAL; } +/* + * kfree_rcu() performance tests: Start a kfree_rcu() loop on all CPUs for number + * of iterations and measure total time and number of GP for all iterations to complete. + */ + +torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu()."); +torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration."); +torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees."); + +static struct task_struct **kfree_reader_tasks; +static int kfree_nrealthreads; +static atomic_t n_kfree_perf_thread_started; +static atomic_t n_kfree_perf_thread_ended; + +struct kfree_obj { + char kfree_obj[8]; + struct rcu_head rh; +}; + +static int +kfree_perf_thread(void *arg) +{ + int i, loop = 0; + long me = (long)arg; + struct kfree_obj *alloc_ptr; + u64 start_time, end_time; + + VERBOSE_PERFOUT_STRING("kfree_perf_thread task started"); + set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)); + set_user_nice(current, MAX_NICE); + + start_time = ktime_get_mono_fast_ns(); + + if (atomic_inc_return(&n_kfree_perf_thread_started) >= kfree_nrealthreads) { + if (gp_exp) + b_rcu_gp_test_started = cur_ops->exp_completed() / 2; + else + b_rcu_gp_test_started = cur_ops->get_gp_seq(); + } + + do { + for (i = 0; i < kfree_alloc_num; i++) { + alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL); + if (!alloc_ptr) + return -ENOMEM; + + kfree_rcu(alloc_ptr, rh); + } + + cond_resched(); + } while (!torture_must_stop() && ++loop < kfree_loops); + + if (atomic_inc_return(&n_kfree_perf_thread_ended) >= kfree_nrealthreads) { + end_time = ktime_get_mono_fast_ns(); + + if (gp_exp) + b_rcu_gp_test_finished = cur_ops->exp_completed() / 2; + else + b_rcu_gp_test_finished = cur_ops->get_gp_seq(); + + pr_alert("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n", + (unsigned long long)(end_time - start_time), kfree_loops, + rcuperf_seq_diff(b_rcu_gp_test_finished, b_rcu_gp_test_started)); + if (shutdown) { + smp_mb(); /* Assign before wake. */ + wake_up(&shutdown_wq); + } + } + + torture_kthread_stopping("kfree_perf_thread"); + return 0; +} + +static void +kfree_perf_cleanup(void) +{ + int i; + + if (torture_cleanup_begin()) + return; + + if (kfree_reader_tasks) { + for (i = 0; i < kfree_nrealthreads; i++) + torture_stop_kthread(kfree_perf_thread, + kfree_reader_tasks[i]); + kfree(kfree_reader_tasks); + } + + torture_cleanup_end(); +} + +/* + * shutdown kthread. Just waits to be awakened, then shuts down system. + */ +static int +kfree_perf_shutdown(void *arg) +{ + do { + wait_event(shutdown_wq, + atomic_read(&n_kfree_perf_thread_ended) >= + kfree_nrealthreads); + } while (atomic_read(&n_kfree_perf_thread_ended) < kfree_nrealthreads); + + smp_mb(); /* Wake before output. */ + + kfree_perf_cleanup(); + kernel_power_off(); + return -EINVAL; +} + +static int __init +kfree_perf_init(void) +{ + long i; + int firsterr = 0; + + kfree_nrealthreads = compute_real(kfree_nthreads); + /* Start up the kthreads. */ + if (shutdown) { + init_waitqueue_head(&shutdown_wq); + firsterr = torture_create_kthread(kfree_perf_shutdown, NULL, + shutdown_task); + if (firsterr) + goto unwind; + schedule_timeout_uninterruptible(1); + } + + kfree_reader_tasks = kcalloc(kfree_nrealthreads, sizeof(kfree_reader_tasks[0]), + GFP_KERNEL); + if (kfree_reader_tasks == NULL) { + firsterr = -ENOMEM; + goto unwind; + } + + for (i = 0; i < kfree_nrealthreads; i++) { + firsterr = torture_create_kthread(kfree_perf_thread, (void *)i, + kfree_reader_tasks[i]); + if (firsterr) + goto unwind; + } + + while (atomic_read(&n_kfree_perf_thread_started) < kfree_nrealthreads) + schedule_timeout_uninterruptible(1); + + torture_init_end(); + return 0; + +unwind: + torture_init_end(); + kfree_perf_cleanup(); + return firsterr; +} + static int __init rcu_perf_init(void) { @@ -616,6 +770,9 @@ rcu_perf_init(void) if (cur_ops->init) cur_ops->init(); + if (kfree_rcu_test) + return kfree_perf_init(); + nrealwriters = compute_real(nwriters); nrealreaders = compute_real(nreaders); atomic_set(&n_rcu_perf_reader_started, 0); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index dee043feb71f..1aeecc165b21 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1661,43 +1661,52 @@ static void rcu_torture_fwd_prog_cb(struct rcu_head *rhp) struct rcu_fwd_cb { struct rcu_head rh; struct rcu_fwd_cb *rfc_next; + struct rcu_fwd *rfc_rfp; int rfc_gps; }; -static DEFINE_SPINLOCK(rcu_fwd_lock); -static struct rcu_fwd_cb *rcu_fwd_cb_head; -static struct rcu_fwd_cb **rcu_fwd_cb_tail = &rcu_fwd_cb_head; -static long n_launders_cb; -static unsigned long rcu_fwd_startat; -static bool rcu_fwd_emergency_stop; + #define MAX_FWD_CB_JIFFIES (8 * HZ) /* Maximum CB test duration. */ #define MIN_FWD_CB_LAUNDERS 3 /* This many CB invocations to count. */ #define MIN_FWD_CBS_LAUNDERED 100 /* Number of counted CBs. */ #define FWD_CBS_HIST_DIV 10 /* Histogram buckets/second. */ +#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)) + struct rcu_launder_hist { long n_launders; unsigned long launder_gp_seq; }; -#define N_LAUNDERS_HIST (2 * MAX_FWD_CB_JIFFIES / (HZ / FWD_CBS_HIST_DIV)) -static struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST]; -static unsigned long rcu_launder_gp_seq_start; -static void rcu_torture_fwd_cb_hist(void) +struct rcu_fwd { + spinlock_t rcu_fwd_lock; + struct rcu_fwd_cb *rcu_fwd_cb_head; + struct rcu_fwd_cb **rcu_fwd_cb_tail; + long n_launders_cb; + unsigned long rcu_fwd_startat; + struct rcu_launder_hist n_launders_hist[N_LAUNDERS_HIST]; + unsigned long rcu_launder_gp_seq_start; +}; + +struct rcu_fwd *rcu_fwds; +bool rcu_fwd_emergency_stop; + +static void rcu_torture_fwd_cb_hist(struct rcu_fwd *rfp) { unsigned long gps; unsigned long gps_old; int i; int j; - for (i = ARRAY_SIZE(n_launders_hist) - 1; i > 0; i--) - if (n_launders_hist[i].n_launders > 0) + for (i = ARRAY_SIZE(rfp->n_launders_hist) - 1; i > 0; i--) + if (rfp->n_launders_hist[i].n_launders > 0) break; pr_alert("%s: Callback-invocation histogram (duration %lu jiffies):", - __func__, jiffies - rcu_fwd_startat); - gps_old = rcu_launder_gp_seq_start; + __func__, jiffies - rfp->rcu_fwd_startat); + gps_old = rfp->rcu_launder_gp_seq_start; for (j = 0; j <= i; j++) { - gps = n_launders_hist[j].launder_gp_seq; + gps = rfp->n_launders_hist[j].launder_gp_seq; pr_cont(" %ds/%d: %ld:%ld", - j + 1, FWD_CBS_HIST_DIV, n_launders_hist[j].n_launders, + j + 1, FWD_CBS_HIST_DIV, + rfp->n_launders_hist[j].n_launders, rcutorture_seq_diff(gps, gps_old)); gps_old = gps; } @@ -1711,26 +1720,27 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp) int i; struct rcu_fwd_cb *rfcp = container_of(rhp, struct rcu_fwd_cb, rh); struct rcu_fwd_cb **rfcpp; + struct rcu_fwd *rfp = rfcp->rfc_rfp; rfcp->rfc_next = NULL; rfcp->rfc_gps++; - spin_lock_irqsave(&rcu_fwd_lock, flags); - rfcpp = rcu_fwd_cb_tail; - rcu_fwd_cb_tail = &rfcp->rfc_next; + spin_lock_irqsave(&rfp->rcu_fwd_lock, flags); + rfcpp = rfp->rcu_fwd_cb_tail; + rfp->rcu_fwd_cb_tail = &rfcp->rfc_next; WRITE_ONCE(*rfcpp, rfcp); - WRITE_ONCE(n_launders_cb, n_launders_cb + 1); - i = ((jiffies - rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV)); - if (i >= ARRAY_SIZE(n_launders_hist)) - i = ARRAY_SIZE(n_launders_hist) - 1; - n_launders_hist[i].n_launders++; - n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq(); - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1); + i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV)); + if (i >= ARRAY_SIZE(rfp->n_launders_hist)) + i = ARRAY_SIZE(rfp->n_launders_hist) - 1; + rfp->n_launders_hist[i].n_launders++; + rfp->n_launders_hist[i].launder_gp_seq = cur_ops->get_gp_seq(); + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); } // Give the scheduler a chance, even on nohz_full CPUs. static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) { - if (IS_ENABLED(CONFIG_PREEMPT) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { + if (IS_ENABLED(CONFIG_PREEMPTION) && IS_ENABLED(CONFIG_NO_HZ_FULL)) { // Real call_rcu() floods hit userspace, so emulate that. if (need_resched() || (iter & 0xfff)) schedule(); @@ -1744,23 +1754,23 @@ static void rcu_torture_fwd_prog_cond_resched(unsigned long iter) * Free all callbacks on the rcu_fwd_cb_head list, either because the * test is over or because we hit an OOM event. */ -static unsigned long rcu_torture_fwd_prog_cbfree(void) +static unsigned long rcu_torture_fwd_prog_cbfree(struct rcu_fwd *rfp) { unsigned long flags; unsigned long freed = 0; struct rcu_fwd_cb *rfcp; for (;;) { - spin_lock_irqsave(&rcu_fwd_lock, flags); - rfcp = rcu_fwd_cb_head; + spin_lock_irqsave(&rfp->rcu_fwd_lock, flags); + rfcp = rfp->rcu_fwd_cb_head; if (!rfcp) { - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); break; } - rcu_fwd_cb_head = rfcp->rfc_next; - if (!rcu_fwd_cb_head) - rcu_fwd_cb_tail = &rcu_fwd_cb_head; - spin_unlock_irqrestore(&rcu_fwd_lock, flags); + rfp->rcu_fwd_cb_head = rfcp->rfc_next; + if (!rfp->rcu_fwd_cb_head) + rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head; + spin_unlock_irqrestore(&rfp->rcu_fwd_lock, flags); kfree(rfcp); freed++; rcu_torture_fwd_prog_cond_resched(freed); @@ -1774,7 +1784,8 @@ static unsigned long rcu_torture_fwd_prog_cbfree(void) } /* Carry out need_resched()/cond_resched() forward-progress testing. */ -static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) +static void rcu_torture_fwd_prog_nr(struct rcu_fwd *rfp, + int *tested, int *tested_tries) { unsigned long cver; unsigned long dur; @@ -1804,8 +1815,8 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) sd = cur_ops->stall_dur() + 1; sd4 = (sd + fwd_progress_div - 1) / fwd_progress_div; dur = sd4 + torture_random(&trs) % (sd - sd4); - WRITE_ONCE(rcu_fwd_startat, jiffies); - stopat = rcu_fwd_startat + dur; + WRITE_ONCE(rfp->rcu_fwd_startat, jiffies); + stopat = rfp->rcu_fwd_startat + dur; while (time_before(jiffies, stopat) && !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { @@ -1840,7 +1851,7 @@ static void rcu_torture_fwd_prog_nr(int *tested, int *tested_tries) } /* Carry out call_rcu() forward-progress testing. */ -static void rcu_torture_fwd_prog_cr(void) +static void rcu_torture_fwd_prog_cr(struct rcu_fwd *rfp) { unsigned long cver; unsigned long flags; @@ -1864,23 +1875,23 @@ static void rcu_torture_fwd_prog_cr(void) /* Loop continuously posting RCU callbacks. */ WRITE_ONCE(rcu_fwd_cb_nodelay, true); cur_ops->sync(); /* Later readers see above write. */ - WRITE_ONCE(rcu_fwd_startat, jiffies); - stopat = rcu_fwd_startat + MAX_FWD_CB_JIFFIES; + WRITE_ONCE(rfp->rcu_fwd_startat, jiffies); + stopat = rfp->rcu_fwd_startat + MAX_FWD_CB_JIFFIES; n_launders = 0; - n_launders_cb = 0; + rfp->n_launders_cb = 0; // Hoist initialization for multi-kthread n_launders_sa = 0; n_max_cbs = 0; n_max_gps = 0; - for (i = 0; i < ARRAY_SIZE(n_launders_hist); i++) - n_launders_hist[i].n_launders = 0; + for (i = 0; i < ARRAY_SIZE(rfp->n_launders_hist); i++) + rfp->n_launders_hist[i].n_launders = 0; cver = READ_ONCE(rcu_torture_current_version); gps = cur_ops->get_gp_seq(); - rcu_launder_gp_seq_start = gps; + rfp->rcu_launder_gp_seq_start = gps; tick_dep_set_task(current, TICK_DEP_BIT_RCU); while (time_before(jiffies, stopat) && !shutdown_time_arrived() && !READ_ONCE(rcu_fwd_emergency_stop) && !torture_must_stop()) { - rfcp = READ_ONCE(rcu_fwd_cb_head); + rfcp = READ_ONCE(rfp->rcu_fwd_cb_head); rfcpn = NULL; if (rfcp) rfcpn = READ_ONCE(rfcp->rfc_next); @@ -1888,7 +1899,7 @@ static void rcu_torture_fwd_prog_cr(void) if (rfcp->rfc_gps >= MIN_FWD_CB_LAUNDERS && ++n_max_gps >= MIN_FWD_CBS_LAUNDERED) break; - rcu_fwd_cb_head = rfcpn; + rfp->rcu_fwd_cb_head = rfcpn; n_launders++; n_launders_sa++; } else { @@ -1900,6 +1911,7 @@ static void rcu_torture_fwd_prog_cr(void) n_max_cbs++; n_launders_sa = 0; rfcp->rfc_gps = 0; + rfcp->rfc_rfp = rfp; } cur_ops->call(&rfcp->rh, rcu_torture_fwd_cb_cr); rcu_torture_fwd_prog_cond_resched(n_launders + n_max_cbs); @@ -1910,22 +1922,22 @@ static void rcu_torture_fwd_prog_cr(void) } } stoppedat = jiffies; - n_launders_cb_snap = READ_ONCE(n_launders_cb); + n_launders_cb_snap = READ_ONCE(rfp->n_launders_cb); cver = READ_ONCE(rcu_torture_current_version) - cver; gps = rcutorture_seq_diff(cur_ops->get_gp_seq(), gps); cur_ops->cb_barrier(); /* Wait for callbacks to be invoked. */ - (void)rcu_torture_fwd_prog_cbfree(); + (void)rcu_torture_fwd_prog_cbfree(rfp); if (!torture_must_stop() && !READ_ONCE(rcu_fwd_emergency_stop) && !shutdown_time_arrived()) { WARN_ON(n_max_gps < MIN_FWD_CBS_LAUNDERED); pr_alert("%s Duration %lu barrier: %lu pending %ld n_launders: %ld n_launders_sa: %ld n_max_gps: %ld n_max_cbs: %ld cver %ld gps %ld\n", __func__, - stoppedat - rcu_fwd_startat, jiffies - stoppedat, + stoppedat - rfp->rcu_fwd_startat, jiffies - stoppedat, n_launders + n_max_cbs - n_launders_cb_snap, n_launders, n_launders_sa, n_max_gps, n_max_cbs, cver, gps); - rcu_torture_fwd_cb_hist(); + rcu_torture_fwd_cb_hist(rfp); } schedule_timeout_uninterruptible(HZ); /* Let CBs drain. */ tick_dep_clear_task(current, TICK_DEP_BIT_RCU); @@ -1940,20 +1952,22 @@ static void rcu_torture_fwd_prog_cr(void) static int rcutorture_oom_notify(struct notifier_block *self, unsigned long notused, void *nfreed) { + struct rcu_fwd *rfp = rcu_fwds; + WARN(1, "%s invoked upon OOM during forward-progress testing.\n", __func__); - rcu_torture_fwd_cb_hist(); - rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2); + rcu_torture_fwd_cb_hist(rfp); + rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rfp->rcu_fwd_startat)) / 2); WRITE_ONCE(rcu_fwd_emergency_stop, true); smp_mb(); /* Emergency stop before free and wait to avoid hangs. */ pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); rcu_barrier(); pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); rcu_barrier(); pr_info("%s: Freed %lu RCU callbacks.\n", - __func__, rcu_torture_fwd_prog_cbfree()); + __func__, rcu_torture_fwd_prog_cbfree(rfp)); smp_mb(); /* Frees before return to avoid redoing OOM. */ (*(unsigned long *)nfreed)++; /* Forward progress CBs freed! */ pr_info("%s returning after OOM processing.\n", __func__); @@ -1967,6 +1981,7 @@ static struct notifier_block rcutorture_oom_nb = { /* Carry out grace-period forward-progress testing. */ static int rcu_torture_fwd_prog(void *args) { + struct rcu_fwd *rfp = args; int tested = 0; int tested_tries = 0; @@ -1978,8 +1993,8 @@ static int rcu_torture_fwd_prog(void *args) schedule_timeout_interruptible(fwd_progress_holdoff * HZ); WRITE_ONCE(rcu_fwd_emergency_stop, false); register_oom_notifier(&rcutorture_oom_nb); - rcu_torture_fwd_prog_nr(&tested, &tested_tries); - rcu_torture_fwd_prog_cr(); + rcu_torture_fwd_prog_nr(rfp, &tested, &tested_tries); + rcu_torture_fwd_prog_cr(rfp); unregister_oom_notifier(&rcutorture_oom_nb); /* Avoid slow periods, better to test when busy. */ @@ -1995,6 +2010,8 @@ static int rcu_torture_fwd_prog(void *args) /* If forward-progress checking is requested and feasible, spawn the thread. */ static int __init rcu_torture_fwd_prog_init(void) { + struct rcu_fwd *rfp; + if (!fwd_progress) return 0; /* Not requested, so don't do it. */ if (!cur_ops->stall_dur || cur_ops->stall_dur() <= 0 || @@ -2013,8 +2030,12 @@ static int __init rcu_torture_fwd_prog_init(void) 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); + rfp = kzalloc(sizeof(*rfp), GFP_KERNEL); + if (!rfp) + return -ENOMEM; + spin_lock_init(&rfp->rcu_fwd_lock); + rfp->rcu_fwd_cb_tail = &rfp->rcu_fwd_cb_head; + return torture_create_kthread(rcu_torture_fwd_prog, rfp, fwd_prog_task); } /* Callback function for RCU barrier testing. */ diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 44d6606b8325..6208c1dae5c9 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -103,7 +103,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); /* * Workqueue handler to drive one grace period and invoke any callbacks - * that become ready as a result. Single-CPU and !PREEMPT operation + * that become ready as a result. Single-CPU and !PREEMPTION operation * means that we get away with murder on synchronization. ;-) */ void srcu_drive_gp(struct work_struct *wp) diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 5dffade2d7cd..657e6a7d1c03 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -530,7 +530,7 @@ static void srcu_gp_end(struct srcu_struct *ssp) idx = rcu_seq_state(ssp->srcu_gp_seq); WARN_ON_ONCE(idx != SRCU_STATE_SCAN2); cbdelay = srcu_get_delay(ssp); - ssp->srcu_last_gp_end = ktime_get_mono_fast_ns(); + WRITE_ONCE(ssp->srcu_last_gp_end, ktime_get_mono_fast_ns()); rcu_seq_end(&ssp->srcu_gp_seq); gpseq = rcu_seq_current(&ssp->srcu_gp_seq); if (ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, gpseq)) @@ -762,6 +762,7 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) unsigned long flags; struct srcu_data *sdp; unsigned long t; + unsigned long tlast; /* If the local srcu_data structure has callbacks, not idle. */ local_irq_save(flags); @@ -780,9 +781,9 @@ static bool srcu_might_be_idle(struct srcu_struct *ssp) /* First, see if enough time has passed since the last GP. */ t = ktime_get_mono_fast_ns(); + tlast = READ_ONCE(ssp->srcu_last_gp_end); if (exp_holdoff == 0 || - time_in_range_open(t, ssp->srcu_last_gp_end, - ssp->srcu_last_gp_end + exp_holdoff)) + time_in_range_open(t, tlast, tlast + exp_holdoff)) return false; /* Too soon after last GP. */ /* Next, check for probable idleness. */ @@ -853,7 +854,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp, local_irq_save(flags); sdp = this_cpu_ptr(ssp->sda); spin_lock_rcu_node(sdp); - rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); + rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_gp_seq)); s = rcu_seq_snap(&ssp->srcu_gp_seq); @@ -1052,7 +1053,7 @@ void srcu_barrier(struct srcu_struct *ssp) sdp->srcu_barrier_head.func = srcu_barrier_cb; debug_rcu_head_queue(&sdp->srcu_barrier_head); if (!rcu_segcblist_entrain(&sdp->srcu_cblist, - &sdp->srcu_barrier_head, 0)) { + &sdp->srcu_barrier_head)) { debug_rcu_head_unqueue(&sdp->srcu_barrier_head); atomic_dec(&ssp->srcu_barrier_cpu_cnt); } diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 477b4eb44af5..dd572ce7c747 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -22,6 +22,7 @@ #include <linux/time.h> #include <linux/cpu.h> #include <linux/prefetch.h> +#include <linux/slab.h> #include "rcu.h" @@ -73,6 +74,31 @@ void rcu_sched_clock_irq(int user) } } +/* + * Reclaim the specified callback, either by invoking it for non-kfree cases or + * freeing it directly (for kfree). Return true if kfreeing, false otherwise. + */ +static inline bool rcu_reclaim_tiny(struct rcu_head *head) +{ + rcu_callback_t f; + unsigned long offset = (unsigned long)head->func; + + rcu_lock_acquire(&rcu_callback_map); + if (__is_kfree_rcu_offset(offset)) { + trace_rcu_invoke_kfree_callback("", head, offset); + kfree((void *)head - offset); + rcu_lock_release(&rcu_callback_map); + return true; + } + + trace_rcu_invoke_callback("", head); + f = head->func; + WRITE_ONCE(head->func, (rcu_callback_t)0L); + f(head); + rcu_lock_release(&rcu_callback_map); + return false; +} + /* Invoke the RCU callbacks whose grace period has elapsed. */ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) { @@ -100,7 +126,7 @@ static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused prefetch(next); debug_rcu_head_unqueue(list); local_bh_disable(); - __rcu_reclaim("", list); + rcu_reclaim_tiny(list); local_bh_enable(); list = next; } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1694a6b57ad8..d91c9156fab2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -43,7 +43,6 @@ #include <uapi/linux/sched/types.h> #include <linux/prefetch.h> #include <linux/delay.h> -#include <linux/stop_machine.h> #include <linux/random.h> #include <linux/trace_events.h> #include <linux/suspend.h> @@ -55,6 +54,7 @@ #include <linux/oom.h> #include <linux/smpboot.h> #include <linux/jiffies.h> +#include <linux/slab.h> #include <linux/sched/isolation.h> #include <linux/sched/clock.h> #include "../time/tick-internal.h" @@ -84,7 +84,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), }; -struct rcu_state rcu_state = { +static struct rcu_state rcu_state = { .level = { &rcu_state.node[0] }, .gp_state = RCU_GP_IDLE, .gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, @@ -188,7 +188,7 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); * held, but the bit corresponding to the current CPU will be stable * in most contexts. */ -unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) { return READ_ONCE(rnp->qsmaskinitnext); } @@ -294,7 +294,7 @@ static void rcu_dynticks_eqs_online(void) * * No ordering, as we are sampling CPU-local information. */ -bool rcu_dynticks_curr_cpu_in_eqs(void) +static bool rcu_dynticks_curr_cpu_in_eqs(void) { struct rcu_data *rdp = this_cpu_ptr(&rcu_data); @@ -305,7 +305,7 @@ bool rcu_dynticks_curr_cpu_in_eqs(void) * 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_data *rdp) +static int rcu_dynticks_snap(struct rcu_data *rdp) { int snap = atomic_add_return(0, &rdp->dynticks); @@ -529,16 +529,6 @@ static struct rcu_node *rcu_get_root(void) } /* - * Convert a ->gp_state value to a character string. - */ -static const char *gp_state_getname(short gs) -{ - if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) - return "???"; - return gp_state_names[gs]; -} - -/* * Send along grace-period-related data for rcutorture diagnostics. */ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags, @@ -577,7 +567,7 @@ static void rcu_eqs_enter(bool user) } lockdep_assert_irqs_disabled(); - trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, rdp->dynticks); + trace_rcu_dyntick(TPS("Start"), rdp->dynticks_nesting, 0, atomic_read(&rdp->dynticks)); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); rdp = this_cpu_ptr(&rcu_data); do_nocb_deferred_wakeup(rdp); @@ -650,14 +640,15 @@ static __always_inline void rcu_nmi_exit_common(bool irq) * leave it in non-RCU-idle state. */ if (rdp->dynticks_nmi_nesting != 1) { - trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, rdp->dynticks); + trace_rcu_dyntick(TPS("--="), rdp->dynticks_nmi_nesting, rdp->dynticks_nmi_nesting - 2, + atomic_read(&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"), rdp->dynticks_nmi_nesting, 0, rdp->dynticks); + trace_rcu_dyntick(TPS("Startirq"), rdp->dynticks_nmi_nesting, 0, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, 0); /* Avoid store tearing. */ if (irq) @@ -744,7 +735,7 @@ static void rcu_eqs_exit(bool user) rcu_dynticks_task_exit(); rcu_dynticks_eqs_exit(); rcu_cleanup_after_idle(); - trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, rdp->dynticks); + trace_rcu_dyntick(TPS("End"), rdp->dynticks_nesting, 1, atomic_read(&rdp->dynticks)); WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !user && !is_idle_task(current)); WRITE_ONCE(rdp->dynticks_nesting, 1); WARN_ON_ONCE(rdp->dynticks_nmi_nesting); @@ -800,8 +791,8 @@ void rcu_user_exit(void) */ static __always_inline void rcu_nmi_enter_common(bool irq) { - struct rcu_data *rdp = this_cpu_ptr(&rcu_data); long incby = 2; + struct rcu_data *rdp = this_cpu_ptr(&rcu_data); /* Complain about underflow. */ WARN_ON_ONCE(rdp->dynticks_nmi_nesting < 0); @@ -828,12 +819,17 @@ static __always_inline void rcu_nmi_enter_common(bool irq) } else if (tick_nohz_full_cpu(rdp->cpu) && rdp->dynticks_nmi_nesting == DYNTICK_IRQ_NONIDLE && READ_ONCE(rdp->rcu_urgent_qs) && !rdp->rcu_forced_tick) { - rdp->rcu_forced_tick = true; - tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); + raw_spin_lock_rcu_node(rdp->mynode); + // Recheck under lock. + if (rdp->rcu_urgent_qs && !rdp->rcu_forced_tick) { + rdp->rcu_forced_tick = true; + tick_dep_set_cpu(rdp->cpu, TICK_DEP_BIT_RCU); + } + raw_spin_unlock_rcu_node(rdp->mynode); } trace_rcu_dyntick(incby == 1 ? TPS("Endirq") : TPS("++="), rdp->dynticks_nmi_nesting, - rdp->dynticks_nmi_nesting + incby, rdp->dynticks); + rdp->dynticks_nmi_nesting + incby, atomic_read(&rdp->dynticks)); WRITE_ONCE(rdp->dynticks_nmi_nesting, /* Prevent store tearing. */ rdp->dynticks_nmi_nesting + incby); barrier(); @@ -898,6 +894,7 @@ void rcu_irq_enter_irqson(void) */ static void rcu_disable_urgency_upon_qs(struct rcu_data *rdp) { + raw_lockdep_assert_held_rcu_node(rdp->mynode); WRITE_ONCE(rdp->rcu_urgent_qs, false); WRITE_ONCE(rdp->rcu_need_heavy_qs, false); if (tick_nohz_full_cpu(rdp->cpu) && rdp->rcu_forced_tick) { @@ -1934,7 +1931,7 @@ rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags) struct rcu_node *rnp_p; raw_lockdep_assert_held_rcu_node(rnp); - if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPTION)) || + if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_RCU)) || WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) || rnp->qsmask != 0) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); @@ -2146,7 +2143,6 @@ static void rcu_do_batch(struct rcu_data *rdp) /* If no callbacks are ready, just return. */ if (!rcu_segcblist_ready_cbs(&rdp->cblist)) { 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(rcu_state.name, 0, !rcu_segcblist_empty(&rdp->cblist), @@ -2168,7 +2164,6 @@ static void rcu_do_batch(struct rcu_data *rdp) if (unlikely(bl > 100)) tlimit = local_clock() + rcu_resched_ns; 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); if (offloaded) @@ -2179,9 +2174,19 @@ static void rcu_do_batch(struct rcu_data *rdp) tick_dep_set_task(current, TICK_DEP_BIT_RCU); rhp = rcu_cblist_dequeue(&rcl); for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) { + rcu_callback_t f; + debug_rcu_head_unqueue(rhp); - if (__rcu_reclaim(rcu_state.name, rhp)) - rcu_cblist_dequeued_lazy(&rcl); + + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_callback(rcu_state.name, rhp); + + f = rhp->func; + WRITE_ONCE(rhp->func, (rcu_callback_t)0L); + f(rhp); + + rcu_lock_release(&rcu_callback_map); + /* * Stop only if limit reached and CPU has something to do. * Note: The rcl structure counts down from zero. @@ -2294,7 +2299,7 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) mask = 0; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->qsmask == 0) { - if (!IS_ENABLED(CONFIG_PREEMPTION) || + if (!IS_ENABLED(CONFIG_PREEMPT_RCU) || rcu_preempt_blocked_readers_cgp(rnp)) { /* * No point in scanning bits because they @@ -2308,14 +2313,11 @@ static void force_qs_rnp(int (*f)(struct rcu_data *rdp)) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); continue; } - for_each_leaf_node_possible_cpu(rnp, cpu) { - unsigned long bit = leaf_node_cpu_bit(rnp, cpu); - if ((rnp->qsmask & bit) != 0) { - rdp = per_cpu_ptr(&rcu_data, cpu); - if (f(rdp)) { - mask |= bit; - rcu_disable_urgency_upon_qs(rdp); - } + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->qsmask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (f(rdp)) { + mask |= rdp->grpmask; + rcu_disable_urgency_upon_qs(rdp); } } if (mask != 0) { @@ -2474,8 +2476,8 @@ static void rcu_cpu_kthread(unsigned int cpu) char work, *workp = this_cpu_ptr(&rcu_data.rcu_cpu_has_work); int spincnt; + trace_rcu_utilization(TPS("Start CPU kthread@rcu_run")); for (spincnt = 0; spincnt < 10; spincnt++) { - trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); local_bh_disable(); *statusp = RCU_KTHREAD_RUNNING; local_irq_disable(); @@ -2583,7 +2585,7 @@ static void rcu_leak_callback(struct rcu_head *rhp) * is expected to specify a CPU. */ static void -__call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) +__call_rcu(struct rcu_head *head, rcu_callback_t func) { unsigned long flags; struct rcu_data *rdp; @@ -2618,18 +2620,17 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); } + if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags)) return; // Enqueued onto ->nocb_bypass, so just leave. /* If we get here, rcu_nocb_try_bypass() acquired ->nocb_lock. */ - rcu_segcblist_enqueue(&rdp->cblist, head, lazy); + rcu_segcblist_enqueue(&rdp->cblist, head); if (__is_kfree_rcu_offset((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(rcu_state.name, head, - rcu_segcblist_n_lazy_cbs(&rdp->cblist), rcu_segcblist_n_cbs(&rdp->cblist)); /* Go handle any RCU core processing required. */ @@ -2679,28 +2680,230 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, bool lazy) */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, 0); + __call_rcu(head, func); } EXPORT_SYMBOL_GPL(call_rcu); + +/* Maximum number of jiffies to wait before draining a batch. */ +#define KFREE_DRAIN_JIFFIES (HZ / 50) +#define KFREE_N_BATCHES 2 + +/** + * struct kfree_rcu_cpu_work - single batch of kfree_rcu() requests + * @rcu_work: Let queue_rcu_work() invoke workqueue handler after grace period + * @head_free: List of kfree_rcu() objects waiting for a grace period + * @krcp: Pointer to @kfree_rcu_cpu structure + */ + +struct kfree_rcu_cpu_work { + struct rcu_work rcu_work; + struct rcu_head *head_free; + struct kfree_rcu_cpu *krcp; +}; + +/** + * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period + * @head: List of kfree_rcu() objects not yet waiting for a grace period + * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period + * @lock: Synchronize access to this structure + * @monitor_work: Promote @head to @head_free after KFREE_DRAIN_JIFFIES + * @monitor_todo: Tracks whether a @monitor_work delayed work is pending + * @initialized: The @lock and @rcu_work fields have been initialized + * + * This is a per-CPU structure. The reason that it is not included in + * the rcu_data structure is to permit this code to be extracted from + * the RCU files. Such extraction could allow further optimization of + * the interactions with the slab allocators. + */ +struct kfree_rcu_cpu { + struct rcu_head *head; + struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; + spinlock_t lock; + struct delayed_work monitor_work; + bool monitor_todo; + bool initialized; +}; + +static DEFINE_PER_CPU(struct kfree_rcu_cpu, krc); + +/* + * This function is invoked in workqueue context after a grace period. + * It frees all the objects queued on ->head_free. + */ +static void kfree_rcu_work(struct work_struct *work) +{ + unsigned long flags; + struct rcu_head *head, *next; + struct kfree_rcu_cpu *krcp; + struct kfree_rcu_cpu_work *krwp; + + krwp = container_of(to_rcu_work(work), + struct kfree_rcu_cpu_work, rcu_work); + krcp = krwp->krcp; + spin_lock_irqsave(&krcp->lock, flags); + head = krwp->head_free; + krwp->head_free = NULL; + spin_unlock_irqrestore(&krcp->lock, flags); + + // List "head" is now private, so traverse locklessly. + for (; head; head = next) { + unsigned long offset = (unsigned long)head->func; + + next = head->next; + // Potentially optimize with kfree_bulk in future. + debug_rcu_head_unqueue(head); + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset); + + if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) { + /* Could be optimized with kfree_bulk() in future. */ + kfree((void *)head - offset); + } + + rcu_lock_release(&rcu_callback_map); + cond_resched_tasks_rcu_qs(); + } +} + /* - * Queue an RCU callback for lazy invocation after a grace period. - * This will likely be later named something like "call_rcu_lazy()", - * but this change will require some way of tagging the lazy RCU - * callbacks in the list of pending callbacks. Until then, this - * function may only be called from __kfree_rcu(). + * Schedule the kfree batch RCU work to run in workqueue context after a GP. + * + * This function is invoked by kfree_rcu_monitor() when the KFREE_DRAIN_JIFFIES + * timeout has been reached. + */ +static inline bool queue_kfree_rcu_work(struct kfree_rcu_cpu *krcp) +{ + int i; + struct kfree_rcu_cpu_work *krwp = NULL; + + lockdep_assert_held(&krcp->lock); + for (i = 0; i < KFREE_N_BATCHES; i++) + if (!krcp->krw_arr[i].head_free) { + krwp = &(krcp->krw_arr[i]); + break; + } + + // If a previous RCU batch is in progress, we cannot immediately + // queue another one, so return false to tell caller to retry. + if (!krwp) + return false; + + krwp->head_free = krcp->head; + krcp->head = NULL; + INIT_RCU_WORK(&krwp->rcu_work, kfree_rcu_work); + queue_rcu_work(system_wq, &krwp->rcu_work); + return true; +} + +static inline void kfree_rcu_drain_unlock(struct kfree_rcu_cpu *krcp, + unsigned long flags) +{ + // Attempt to start a new batch. + krcp->monitor_todo = false; + if (queue_kfree_rcu_work(krcp)) { + // Success! Our job is done here. + spin_unlock_irqrestore(&krcp->lock, flags); + return; + } + + // Previous RCU batch still in progress, try again later. + krcp->monitor_todo = true; + schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); + spin_unlock_irqrestore(&krcp->lock, flags); +} + +/* + * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. + * It invokes kfree_rcu_drain_unlock() to attempt to start another batch. + */ +static void kfree_rcu_monitor(struct work_struct *work) +{ + unsigned long flags; + struct kfree_rcu_cpu *krcp = container_of(work, struct kfree_rcu_cpu, + monitor_work.work); + + spin_lock_irqsave(&krcp->lock, flags); + if (krcp->monitor_todo) + kfree_rcu_drain_unlock(krcp, flags); + else + spin_unlock_irqrestore(&krcp->lock, flags); +} + +/* + * Queue a request for lazy invocation of kfree() after a grace period. + * + * Each kfree_call_rcu() request is added to a batch. The batch will be drained + * every KFREE_DRAIN_JIFFIES number of jiffies. All the objects in the batch + * will be kfree'd in workqueue context. This allows us to: + * + * 1. Batch requests together to reduce the number of grace periods during + * heavy kfree_rcu() load. + * + * 2. It makes it possible to use kfree_bulk() on a large number of + * kfree_rcu() requests thus reducing cache misses and the per-object + * overhead of kfree(). */ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu(head, func, 1); + unsigned long flags; + struct kfree_rcu_cpu *krcp; + + local_irq_save(flags); // For safely calling this_cpu_ptr(). + krcp = this_cpu_ptr(&krc); + if (krcp->initialized) + spin_lock(&krcp->lock); + + // Queue the object but don't yet schedule the batch. + if (debug_rcu_head_queue(head)) { + // Probable double kfree_rcu(), just leak. + WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n", + __func__, head); + goto unlock_return; + } + head->func = func; + head->next = krcp->head; + krcp->head = head; + + // Set timer to drain after KFREE_DRAIN_JIFFIES. + if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING && + !krcp->monitor_todo) { + krcp->monitor_todo = true; + schedule_delayed_work(&krcp->monitor_work, KFREE_DRAIN_JIFFIES); + } + +unlock_return: + if (krcp->initialized) + spin_unlock(&krcp->lock); + local_irq_restore(flags); } EXPORT_SYMBOL_GPL(kfree_call_rcu); +void __init kfree_rcu_scheduler_running(void) +{ + int cpu; + unsigned long flags; + + for_each_online_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + spin_lock_irqsave(&krcp->lock, flags); + if (!krcp->head || krcp->monitor_todo) { + spin_unlock_irqrestore(&krcp->lock, flags); + continue; + } + krcp->monitor_todo = true; + schedule_delayed_work_on(cpu, &krcp->monitor_work, + KFREE_DRAIN_JIFFIES); + spin_unlock_irqrestore(&krcp->lock, flags); + } +} + /* * During early boot, any blocking grace-period wait automatically - * implies a grace period. Later on, this is never the case for PREEMPT. + * implies a grace period. Later on, this is never the case for PREEMPTION. * - * Howevr, because a context switch is a grace period for !PREEMPT, any + * Howevr, because a context switch is a grace period for !PREEMPTION, 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 @@ -2896,7 +3099,7 @@ static void rcu_barrier_func(void *unused) debug_rcu_head_queue(&rdp->barrier_head); rcu_nocb_lock(rdp); WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); - if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head, 0)) { + if (rcu_segcblist_entrain(&rdp->cblist, &rdp->barrier_head)) { atomic_inc(&rcu_state.barrier_cpu_count); } else { debug_rcu_head_unqueue(&rdp->barrier_head); @@ -3557,12 +3760,29 @@ static void __init rcu_dump_rcu_node_tree(void) struct workqueue_struct *rcu_gp_wq; struct workqueue_struct *rcu_par_gp_wq; +static void __init kfree_rcu_batch_init(void) +{ + int cpu; + int i; + + for_each_possible_cpu(cpu) { + struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); + + spin_lock_init(&krcp->lock); + for (i = 0; i < KFREE_N_BATCHES; i++) + krcp->krw_arr[i].krcp = krcp; + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); + krcp->initialized = true; + } +} + void __init rcu_init(void) { int cpu; rcu_early_boot_tests(); + kfree_rcu_batch_init(); rcu_bootup_announce(); rcu_init_geometry(); rcu_init_one(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 055c31781d3a..0c87e4c161c2 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -16,7 +16,6 @@ #include <linux/cpumask.h> #include <linux/seqlock.h> #include <linux/swait.h> -#include <linux/stop_machine.h> #include <linux/rcu_node_tree.h> #include "rcu_segcblist.h" @@ -182,8 +181,8 @@ struct rcu_data { bool rcu_need_heavy_qs; /* GP old, so heavy quiescent state! */ bool rcu_urgent_qs; /* GP old need light quiescent state. */ bool rcu_forced_tick; /* Forced tick to provide QS. */ + bool rcu_forced_tick_exp; /* ... provide QS to expedited GP. */ #ifdef CONFIG_RCU_FAST_NO_HZ - bool all_lazy; /* All CPU's CBs lazy at idle start? */ 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. */ @@ -368,18 +367,6 @@ struct rcu_state { #define RCU_GP_CLEANUP 7 /* Grace-period cleanup started. */ #define RCU_GP_CLEANED 8 /* Grace-period cleanup complete. */ -static const char * const gp_state_names[] = { - "RCU_GP_IDLE", - "RCU_GP_WAIT_GPS", - "RCU_GP_DONE_GPS", - "RCU_GP_ONOFF", - "RCU_GP_INIT", - "RCU_GP_WAIT_FQS", - "RCU_GP_DOING_FQS", - "RCU_GP_CLEANUP", - "RCU_GP_CLEANED", -}; - /* * In order to export the rcu_state name to the tracing tools, it * needs to be added in the __tracepoint_string section. @@ -403,8 +390,6 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name; #define RCU_NAME rcu_name #endif /* #else #ifdef CONFIG_TRACING */ -int rcu_dynticks_snap(struct rcu_data *rdp); - /* Forward declarations for tree_plugin.h */ static void rcu_bootup_announce(void); static void rcu_qs(void); @@ -415,7 +400,6 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp); static int rcu_print_task_exp_stall(struct rcu_node *rnp); static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp); static void rcu_flavor_sched_clock_irq(int user); -void call_rcu(struct rcu_head *head, rcu_callback_t func); 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); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index d632cd019597..dcbd75791f39 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -21,7 +21,7 @@ static void rcu_exp_gp_seq_start(void) } /* - * Return then value that expedited-grace-period counter will have + * Return the value that the expedited-grace-period counter will have * at the end of the current grace period. */ static __maybe_unused unsigned long rcu_exp_gp_seq_endval(void) @@ -39,7 +39,9 @@ static void rcu_exp_gp_seq_end(void) } /* - * Take a snapshot of the expedited-grace-period counter. + * Take a snapshot of the expedited-grace-period counter, which is the + * earliest value that will indicate that a full grace period has + * elapsed since the current time. */ static unsigned long rcu_exp_gp_seq_snap(void) { @@ -134,7 +136,7 @@ static void __maybe_unused sync_exp_reset_tree(void) rcu_for_each_node_breadth_first(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); WARN_ON_ONCE(rnp->expmask); - rnp->expmask = rnp->expmaskinit; + WRITE_ONCE(rnp->expmask, rnp->expmaskinit); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -143,31 +145,26 @@ static void __maybe_unused sync_exp_reset_tree(void) * Return non-zero if there is no RCU expedited grace period in progress * for the specified rcu_node structure, in other words, if all CPUs and * tasks covered by the specified rcu_node structure have done their bit - * for the current expedited grace period. Works only for preemptible - * RCU -- other RCU implementation use other means. - * - * Caller must hold the specificed rcu_node structure's ->lock + * for the current expedited grace period. */ -static bool sync_rcu_preempt_exp_done(struct rcu_node *rnp) +static bool sync_rcu_exp_done(struct rcu_node *rnp) { raw_lockdep_assert_held_rcu_node(rnp); - return rnp->exp_tasks == NULL && READ_ONCE(rnp->expmask) == 0; } /* - * Like sync_rcu_preempt_exp_done(), but this function assumes the caller - * doesn't hold the rcu_node's ->lock, and will acquire and release the lock - * itself + * Like sync_rcu_exp_done(), but where the caller does not hold the + * rcu_node's ->lock. */ -static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) +static bool sync_rcu_exp_done_unlocked(struct rcu_node *rnp) { unsigned long flags; bool ret; raw_spin_lock_irqsave_rcu_node(rnp, flags); - ret = sync_rcu_preempt_exp_done(rnp); + ret = sync_rcu_exp_done(rnp); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return ret; @@ -181,8 +178,6 @@ static bool sync_rcu_preempt_exp_done_unlocked(struct rcu_node *rnp) * which the task was queued or to one of that rcu_node structure's ancestors, * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) - * - * Caller must hold the specified rcu_node structure's ->lock. */ static void __rcu_report_exp_rnp(struct rcu_node *rnp, bool wake, unsigned long flags) @@ -190,8 +185,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, { unsigned long mask; + raw_lockdep_assert_held_rcu_node(rnp); for (;;) { - if (!sync_rcu_preempt_exp_done(rnp)) { + if (!sync_rcu_exp_done(rnp)) { if (!rnp->expmask) rcu_initiate_boost(rnp, flags); else @@ -211,7 +207,7 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, rnp = rnp->parent; raw_spin_lock_rcu_node(rnp); /* irqs already disabled */ WARN_ON_ONCE(!(rnp->expmask & mask)); - rnp->expmask &= ~mask; + WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask); } } @@ -234,14 +230,23 @@ static void __maybe_unused rcu_report_exp_rnp(struct rcu_node *rnp, bool wake) static void rcu_report_exp_cpu_mult(struct rcu_node *rnp, unsigned long mask, bool wake) { + int cpu; unsigned long flags; + struct rcu_data *rdp; raw_spin_lock_irqsave_rcu_node(rnp, flags); if (!(rnp->expmask & mask)) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); return; } - rnp->expmask &= ~mask; + WRITE_ONCE(rnp->expmask, rnp->expmask & ~mask); + for_each_leaf_node_cpu_mask(rnp, cpu, mask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (!IS_ENABLED(CONFIG_NO_HZ_FULL) || !rdp->rcu_forced_tick_exp) + continue; + rdp->rcu_forced_tick_exp = false; + tick_dep_clear_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + } __rcu_report_exp_rnp(rnp, wake, flags); /* Releases rnp->lock. */ } @@ -345,8 +350,8 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) /* Each pass checks a CPU for identity, offline, and idle. */ 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(&rcu_data, cpu); + unsigned long mask = rdp->grpmask; int snap; if (raw_smp_processor_id() == cpu || @@ -372,12 +377,10 @@ static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); /* 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); + for_each_leaf_node_cpu_mask(rnp, cpu, mask_ofl_ipi) { struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + unsigned long mask = rdp->grpmask; - if (!(mask_ofl_ipi & mask)) - continue; retry_ipi: if (rcu_dynticks_in_eqs_since(rdp, rdp->exp_dynticks_snap)) { mask_ofl_test |= mask; @@ -389,10 +392,10 @@ retry_ipi: } ret = smp_call_function_single(cpu, rcu_exp_handler, NULL, 0); put_cpu(); - if (!ret) { - mask_ofl_ipi &= ~mask; + /* The CPU will report the QS in response to the IPI. */ + if (!ret) continue; - } + /* Failed, raced with CPU hotplug operation. */ raw_spin_lock_irqsave_rcu_node(rnp, flags); if ((rnp->qsmaskinitnext & mask) && @@ -403,13 +406,12 @@ retry_ipi: schedule_timeout_uninterruptible(1); goto retry_ipi; } - /* CPU really is offline, so we can ignore it. */ - if (!(rnp->expmask & mask)) - mask_ofl_ipi &= ~mask; + /* CPU really is offline, so we must report its QS. */ + if (rnp->expmask & mask) + mask_ofl_test |= mask; raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } /* Report quiescent states for those that went offline. */ - mask_ofl_test |= mask_ofl_ipi; if (mask_ofl_test) rcu_report_exp_cpu_mult(rnp, mask_ofl_test, false); } @@ -456,29 +458,61 @@ static void sync_rcu_exp_select_cpus(void) flush_work(&rnp->rew.rew_work); } -static void synchronize_sched_expedited_wait(void) +/* + * Wait for the expedited grace period to elapse, within time limit. + * If the time limit is exceeded without the grace period elapsing, + * return false, otherwise return true. + */ +static bool synchronize_rcu_expedited_wait_once(long tlimit) +{ + int t; + struct rcu_node *rnp_root = rcu_get_root(); + + t = swait_event_timeout_exclusive(rcu_state.expedited_wq, + sync_rcu_exp_done_unlocked(rnp_root), + tlimit); + // Workqueues should not be signaled. + if (t > 0 || sync_rcu_exp_done_unlocked(rnp_root)) + return true; + WARN_ON(t < 0); /* workqueues should not be signaled. */ + return false; +} + +/* + * Wait for the expedited grace period to elapse, issuing any needed + * RCU CPU stall warnings along the way. + */ +static void synchronize_rcu_expedited_wait(void) { int cpu; unsigned long jiffies_stall; unsigned long jiffies_start; unsigned long mask; int ndetected; + struct rcu_data *rdp; struct rcu_node *rnp; struct rcu_node *rnp_root = rcu_get_root(); - int ret; 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; + if (IS_ENABLED(CONFIG_NO_HZ_FULL)) { + if (synchronize_rcu_expedited_wait_once(1)) + return; + rcu_for_each_leaf_node(rnp) { + for_each_leaf_node_cpu_mask(rnp, cpu, rnp->expmask) { + rdp = per_cpu_ptr(&rcu_data, cpu); + if (rdp->rcu_forced_tick_exp) + continue; + rdp->rcu_forced_tick_exp = true; + tick_dep_set_cpu(cpu, TICK_DEP_BIT_RCU_EXP); + } + } + } for (;;) { - ret = swait_event_timeout_exclusive( - 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)) + if (synchronize_rcu_expedited_wait_once(jiffies_stall)) return; - WARN_ON(ret < 0); /* workqueues should not be signaled. */ if (rcu_cpu_stall_suppress) continue; panic_on_rcu_stall(); @@ -491,7 +525,7 @@ static void synchronize_sched_expedited_wait(void) struct rcu_data *rdp; mask = leaf_node_cpu_bit(rnp, cpu); - if (!(rnp->expmask & mask)) + if (!(READ_ONCE(rnp->expmask) & mask)) continue; ndetected++; rdp = per_cpu_ptr(&rcu_data, cpu); @@ -503,17 +537,18 @@ static void synchronize_sched_expedited_wait(void) } pr_cont(" } %lu jiffies s: %lu root: %#lx/%c\n", jiffies - jiffies_start, rcu_state.expedited_sequence, - rnp_root->expmask, ".T"[!!rnp_root->exp_tasks]); + READ_ONCE(rnp_root->expmask), + ".T"[!!rnp_root->exp_tasks]); if (ndetected) { pr_err("blocking rcu_node structures:"); rcu_for_each_node_breadth_first(rnp) { if (rnp == rnp_root) continue; /* printed unconditionally */ - if (sync_rcu_preempt_exp_done_unlocked(rnp)) + if (sync_rcu_exp_done_unlocked(rnp)) continue; pr_cont(" l=%u:%d-%d:%#lx/%c", rnp->level, rnp->grplo, rnp->grphi, - rnp->expmask, + READ_ONCE(rnp->expmask), ".T"[!!rnp->exp_tasks]); } pr_cont("\n"); @@ -521,7 +556,7 @@ static void synchronize_sched_expedited_wait(void) 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)) + if (!(READ_ONCE(rnp->expmask) & mask)) continue; dump_cpu_task(cpu); } @@ -540,15 +575,14 @@ static void rcu_exp_wait_wake(unsigned long s) { struct rcu_node *rnp; - synchronize_sched_expedited_wait(); - rcu_exp_gp_seq_end(); - trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); + synchronize_rcu_expedited_wait(); - /* - * Switch over to wakeup mode, allowing the next GP, but -only- the - * next GP, to proceed. - */ + // Switch over to wakeup mode, allowing the next GP to proceed. + // End the previous grace period only after acquiring the mutex + // to ensure that only one GP runs concurrently with wakeups. mutex_lock(&rcu_state.exp_wake_mutex); + rcu_exp_gp_seq_end(); + trace_rcu_exp_grace_period(rcu_state.name, s, TPS("end")); rcu_for_each_node_breadth_first(rnp) { if (ULONG_CMP_LT(READ_ONCE(rnp->exp_seq_rq), s)) { @@ -559,7 +593,7 @@ static void rcu_exp_wait_wake(unsigned long s) spin_unlock(&rnp->exp_lock); } smp_mb(); /* All above changes before wakeup. */ - wake_up_all(&rnp->exp_wq[rcu_seq_ctr(rcu_state.expedited_sequence) & 0x3]); + wake_up_all(&rnp->exp_wq[rcu_seq_ctr(s) & 0x3]); } trace_rcu_exp_grace_period(rcu_state.name, s, TPS("endwake")); mutex_unlock(&rcu_state.exp_wake_mutex); @@ -610,7 +644,7 @@ static void rcu_exp_handler(void *unused) * critical section. If also enabled or idle, immediately * report the quiescent state, otherwise defer. */ - if (!t->rcu_read_lock_nesting) { + if (!rcu_preempt_depth()) { if (!(preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK)) || rcu_dynticks_curr_cpu_in_eqs()) { rcu_report_exp_rdp(rdp); @@ -634,7 +668,7 @@ static void rcu_exp_handler(void *unused) * 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) { + if (rcu_preempt_depth() > 0) { raw_spin_lock_irqsave_rcu_node(rnp, flags); if (rnp->expmask & rdp->grpmask) { rdp->exp_deferred_qs = true; @@ -670,7 +704,7 @@ static void rcu_exp_handler(void *unused) } } -/* PREEMPT=y, so no PREEMPT=n expedited grace period to clean up after. */ +/* PREEMPTION=y, so no PREEMPTION=n expedited grace period to clean up after. */ static void sync_sched_exp_online_cleanup(int cpu) { } @@ -785,7 +819,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) * implementations, it is still unfriendly to real-time workloads, so is * thus not recommended for any sort of common-case code. In fact, if * you are using synchronize_rcu_expedited() in a loop, please restructure - * your code to batch your updates, and then Use a single synchronize_rcu() + * 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(). diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index fa08d55f7040..c6ea81cd4189 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -220,7 +220,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp) * blocked tasks. */ if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) { - rnp->gp_tasks = &t->rcu_node_entry; + WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq); } if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD)) @@ -290,8 +290,8 @@ void rcu_note_context_switch(bool preempt) 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 && + WARN_ON_ONCE(!preempt && rcu_preempt_depth() > 0); + if (rcu_preempt_depth() > 0 && !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ @@ -340,7 +340,7 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); */ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) { - return rnp->gp_tasks != NULL; + return READ_ONCE(rnp->gp_tasks) != NULL; } /* Bias and limit values for ->rcu_read_lock_nesting. */ @@ -348,6 +348,21 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) #define RCU_NEST_NMAX (-INT_MAX / 2) #define RCU_NEST_PMAX (INT_MAX / 2) +static void rcu_preempt_read_enter(void) +{ + current->rcu_read_lock_nesting++; +} + +static void rcu_preempt_read_exit(void) +{ + current->rcu_read_lock_nesting--; +} + +static void rcu_preempt_depth_set(int val) +{ + current->rcu_read_lock_nesting = val; +} + /* * Preemptible RCU implementation for rcu_read_lock(). * Just increment ->rcu_read_lock_nesting, shared state will be updated @@ -355,9 +370,9 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp) */ void __rcu_read_lock(void) { - current->rcu_read_lock_nesting++; + rcu_preempt_read_enter(); if (IS_ENABLED(CONFIG_PROVE_LOCKING)) - WARN_ON_ONCE(current->rcu_read_lock_nesting > RCU_NEST_PMAX); + WARN_ON_ONCE(rcu_preempt_depth() > RCU_NEST_PMAX); barrier(); /* critical section after entry code. */ } EXPORT_SYMBOL_GPL(__rcu_read_lock); @@ -373,19 +388,19 @@ void __rcu_read_unlock(void) { struct task_struct *t = current; - if (t->rcu_read_lock_nesting != 1) { - --t->rcu_read_lock_nesting; + if (rcu_preempt_depth() != 1) { + rcu_preempt_read_exit(); } else { barrier(); /* critical section before exit code. */ - t->rcu_read_lock_nesting = -RCU_NEST_BIAS; + rcu_preempt_depth_set(-RCU_NEST_BIAS); barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(READ_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; + rcu_preempt_depth_set(0); } if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { - int rrln = t->rcu_read_lock_nesting; + int rrln = rcu_preempt_depth(); WARN_ON_ONCE(rrln < 0 && rrln > RCU_NEST_NMAX); } @@ -444,15 +459,9 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) local_irq_restore(flags); return; } - t->rcu_read_unlock_special.b.deferred_qs = false; - if (special.b.need_qs) { + t->rcu_read_unlock_special.s = 0; + if (special.b.need_qs) rcu_qs(); - t->rcu_read_unlock_special.b.need_qs = false; - if (!t->rcu_read_unlock_special.s && !rdp->exp_deferred_qs) { - local_irq_restore(flags); - return; - } - } /* * Respond to a request by an expedited grace period for a @@ -460,17 +469,11 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * tasks are handled when removing the task from the * blocked-tasks list below. */ - if (rdp->exp_deferred_qs) { + if (rdp->exp_deferred_qs) rcu_report_exp_rdp(rdp); - if (!t->rcu_read_unlock_special.s) { - 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; /* * Remove this task from the list it blocked on. The task @@ -485,7 +488,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) empty_norm = !rcu_preempt_blocked_readers_cgp(rnp); WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq && (!empty_norm || rnp->qsmask)); - empty_exp = sync_rcu_preempt_exp_done(rnp); + empty_exp = sync_rcu_exp_done(rnp); smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */ np = rcu_next_node_entry(t, rnp); list_del_init(&t->rcu_node_entry); @@ -493,7 +496,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) trace_rcu_unlock_preempted_task(TPS("rcu_preempt"), rnp->gp_seq, t->pid); if (&t->rcu_node_entry == rnp->gp_tasks) - rnp->gp_tasks = np; + WRITE_ONCE(rnp->gp_tasks, np); if (&t->rcu_node_entry == rnp->exp_tasks) rnp->exp_tasks = np; if (IS_ENABLED(CONFIG_RCU_BOOST)) { @@ -509,7 +512,7 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags) * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, * so we must take a snapshot of the expedited state. */ - empty_exp_now = sync_rcu_preempt_exp_done(rnp); + empty_exp_now = sync_rcu_exp_done(rnp); if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report(TPS("preempt_rcu"), rnp->gp_seq, @@ -551,7 +554,7 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) { return (__this_cpu_read(rcu_data.exp_deferred_qs) || READ_ONCE(t->rcu_read_unlock_special.s)) && - t->rcu_read_lock_nesting <= 0; + rcu_preempt_depth() <= 0; } /* @@ -564,16 +567,16 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t) static void rcu_preempt_deferred_qs(struct task_struct *t) { unsigned long flags; - bool couldrecurse = t->rcu_read_lock_nesting >= 0; + bool couldrecurse = rcu_preempt_depth() >= 0; if (!rcu_preempt_need_deferred_qs(t)) return; if (couldrecurse) - t->rcu_read_lock_nesting -= RCU_NEST_BIAS; + rcu_preempt_depth_set(rcu_preempt_depth() - RCU_NEST_BIAS); local_irq_save(flags); rcu_preempt_deferred_qs_irqrestore(t, flags); if (couldrecurse) - t->rcu_read_lock_nesting += RCU_NEST_BIAS; + rcu_preempt_depth_set(rcu_preempt_depth() + RCU_NEST_BIAS); } /* @@ -610,9 +613,8 @@ static void rcu_read_unlock_special(struct task_struct *t) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - t->rcu_read_unlock_special.b.exp_hint = false; exp = (t->rcu_blocked_node && t->rcu_blocked_node->exp_tasks) || - (rdp->grpmask & rnp->expmask) || + (rdp->grpmask & READ_ONCE(rnp->expmask)) || tick_nohz_full_cpu(rdp->cpu); // Need to defer quiescent state until everything is enabled. if (irqs_were_disabled && use_softirq && @@ -640,7 +642,6 @@ static void rcu_read_unlock_special(struct task_struct *t) local_irq_restore(flags); return; } - WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, false); rcu_preempt_deferred_qs_irqrestore(t, flags); } @@ -648,8 +649,7 @@ static void rcu_read_unlock_special(struct task_struct *t) * Check that the list of blocked tasks for the newly completed grace * period is in fact empty. It is a serious bug to complete a grace * period that still has RCU readers blocked! This function must be - * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock - * must be held by the caller. + * invoked -before- updating this rnp's ->gp_seq. * * Also, if there are blocked tasks on the list, they automatically * block the newly created grace period, so set up ->gp_tasks accordingly. @@ -659,11 +659,12 @@ 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"); + raw_lockdep_assert_held_rcu_node(rnp); if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp))) dump_blkd_tasks(rnp, 10); if (rcu_preempt_has_tasks(rnp) && (rnp->qsmaskinit || rnp->wait_blkd_tasks)) { - rnp->gp_tasks = rnp->blkd_tasks.next; + WRITE_ONCE(rnp->gp_tasks, rnp->blkd_tasks.next); t = container_of(rnp->gp_tasks, struct task_struct, rcu_node_entry); trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"), @@ -686,7 +687,7 @@ static void rcu_flavor_sched_clock_irq(int user) if (user || rcu_is_cpu_rrupt_from_idle()) { rcu_note_voluntary_context_switch(current); } - if (t->rcu_read_lock_nesting > 0 || + if (rcu_preempt_depth() > 0 || (preempt_count() & (PREEMPT_MASK | SOFTIRQ_MASK))) { /* No QS, force context switch if deferred. */ if (rcu_preempt_need_deferred_qs(t)) { @@ -696,13 +697,13 @@ static void rcu_flavor_sched_clock_irq(int user) } else if (rcu_preempt_need_deferred_qs(t)) { rcu_preempt_deferred_qs(t); /* Report deferred QS. */ return; - } else if (!t->rcu_read_lock_nesting) { + } else if (!rcu_preempt_depth()) { 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 && + if (rcu_preempt_depth() > 0 && __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 && @@ -723,11 +724,11 @@ void exit_rcu(void) struct task_struct *t = current; if (unlikely(!list_empty(¤t->rcu_node_entry))) { - t->rcu_read_lock_nesting = 1; + rcu_preempt_depth_set(1); barrier(); WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true); - } else if (unlikely(t->rcu_read_lock_nesting)) { - t->rcu_read_lock_nesting = 1; + } else if (unlikely(rcu_preempt_depth())) { + rcu_preempt_depth_set(1); } else { return; } @@ -757,7 +758,8 @@ dump_blkd_tasks(struct rcu_node *rnp, int ncheck) pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n", __func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext); pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n", - __func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks); + __func__, READ_ONCE(rnp->gp_tasks), rnp->boost_tasks, + rnp->exp_tasks); pr_info("%s: ->blkd_tasks", __func__); i = 0; list_for_each(lhp, &rnp->blkd_tasks) { @@ -788,7 +790,7 @@ static void __init rcu_bootup_announce(void) } /* - * Note a quiescent state for PREEMPT=n. Because we do not need to know + * Note a quiescent state for PREEMPTION=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. @@ -838,7 +840,7 @@ void rcu_all_qs(void) EXPORT_SYMBOL_GPL(rcu_all_qs); /* - * Note a PREEMPT=n context switch. The caller must have disabled interrupts. + * Note a PREEMPTION=n context switch. The caller must have disabled interrupts. */ void rcu_note_context_switch(bool preempt) { @@ -1262,10 +1264,9 @@ static void rcu_prepare_for_idle(void) /* * This code is invoked when a CPU goes idle, at which point we want * to have the CPU do everything required for RCU so that it can enter - * the energy-efficient dyntick-idle mode. This is handled by a - * state machine implemented by rcu_prepare_for_idle() below. + * the energy-efficient dyntick-idle mode. * - * The following three proprocessor symbols control this state machine: + * The following preprocessor symbol controls this: * * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted * to sleep in dyntick-idle mode with RCU callbacks pending. This @@ -1274,21 +1275,15 @@ static void rcu_prepare_for_idle(void) * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your * system. And if you are -that- concerned about energy efficiency, * just power the system down and be done with it! - * RCU_IDLE_LAZY_GP_DELAY gives the number of jiffies that a CPU is - * permitted to sleep in dyntick-idle mode with only lazy RCU - * callbacks pending. Setting this too high can OOM your system. * - * The values below work well in practice. If future workloads require + * The value below works well in practice. If future workloads require * adjustment, they can be converted into kernel config parameters, though * making the state machine smarter might be a better option. */ #define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ -#define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ static int rcu_idle_gp_delay = RCU_IDLE_GP_DELAY; module_param(rcu_idle_gp_delay, int, 0644); -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 on the current CPU, but only if it has been @@ -1327,8 +1322,7 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) /* * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready * to invoke. If the CPU has callbacks, try to advance them. Tell the - * caller to set the timeout based on whether or not there are non-lazy - * callbacks. + * caller about what to set the timeout. * * The caller must have disabled interrupts. */ @@ -1354,25 +1348,18 @@ int rcu_needs_cpu(u64 basemono, u64 *nextevt) } rdp->last_accelerate = jiffies; - /* Request timer delay depending on laziness, and round. */ - rdp->all_lazy = !rcu_segcblist_n_nonlazy_cbs(&rdp->cblist); - if (rdp->all_lazy) { - dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies; - } else { - dj = round_up(rcu_idle_gp_delay + jiffies, - rcu_idle_gp_delay) - jiffies; - } + /* Request timer and round. */ + dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; + *nextevt = basemono + dj * TICK_NSEC; return 0; } /* - * Prepare a CPU for idle from an RCU perspective. The first major task - * is to sense whether nohz mode has been enabled or disabled via sysfs. - * The second major task is to check to see if a non-lazy callback has - * arrived at a CPU that previously had only lazy callbacks. The third - * major task is to accelerate (that is, assign grace-period numbers to) - * any recently arrived callbacks. + * Prepare a CPU for idle from an RCU perspective. The first major task is to + * sense whether nohz mode has been enabled or disabled via sysfs. The second + * major task is to accelerate (that is, assign grace-period numbers to) any + * recently arrived callbacks. * * The caller must have disabled interrupts. */ @@ -1399,17 +1386,6 @@ static void rcu_prepare_for_idle(void) return; /* - * If a non-lazy callback arrived at a CPU having only lazy - * callbacks, invoke RCU core for the side-effect of recalculating - * idle duration on re-entry to idle. - */ - if (rdp->all_lazy && rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)) { - rdp->all_lazy = false; - invoke_rcu_core(); - return; - } - - /* * If we have not yet accelerated this jiffy, accelerate all * callbacks on this CPU. */ @@ -2321,6 +2297,8 @@ static void __init rcu_organize_nocb_kthreads(void) { int cpu; bool firsttime = true; + bool gotnocbs = false; + bool gotnocbscbs = true; int ls = rcu_nocb_gp_stride; int nl = 0; /* Next GP kthread. */ struct rcu_data *rdp; @@ -2343,21 +2321,31 @@ static void __init rcu_organize_nocb_kthreads(void) rdp = per_cpu_ptr(&rcu_data, cpu); if (rdp->cpu >= nl) { /* New GP kthread, set up for CBs & next GP. */ + gotnocbs = true; nl = DIV_ROUND_UP(rdp->cpu + 1, ls) * ls; rdp->nocb_gp_rdp = rdp; rdp_gp = rdp; - if (!firsttime && dump_tree) - pr_cont("\n"); - firsttime = false; - pr_alert("%s: No-CB GP kthread CPU %d:", __func__, cpu); + if (dump_tree) { + if (!firsttime) + pr_cont("%s\n", gotnocbscbs + ? "" : " (self only)"); + gotnocbscbs = false; + firsttime = false; + pr_alert("%s: No-CB GP kthread CPU %d:", + __func__, cpu); + } } else { /* Another CB kthread, link to previous GP kthread. */ + gotnocbscbs = true; rdp->nocb_gp_rdp = rdp_gp; rdp_prev->nocb_next_cb_rdp = rdp; - pr_alert(" %d", cpu); + if (dump_tree) + pr_cont(" %d", cpu); } rdp_prev = rdp; } + if (gotnocbs && dump_tree) + pr_cont("%s\n", gotnocbscbs ? "" : " (self only)"); } /* diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index c0b8c458d8a6..55f9b84790d3 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -163,7 +163,7 @@ static void rcu_iw_handler(struct irq_work *iwp) // // Printing RCU CPU stall warnings -#ifdef CONFIG_PREEMPTION +#ifdef CONFIG_PREEMPT_RCU /* * Dump detailed information for all tasks blocking the current RCU @@ -215,7 +215,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) return ndetected; } -#else /* #ifdef CONFIG_PREEMPTION */ +#else /* #ifdef CONFIG_PREEMPT_RCU */ /* * Because preemptible RCU does not exist, we never have to check for @@ -233,7 +233,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp) { return 0; } -#endif /* #else #ifdef CONFIG_PREEMPTION */ +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* * Dump stacks of all tasks running on stalled CPUs. First try using @@ -263,11 +263,9 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { struct rcu_data *rdp = &per_cpu(rcu_data, cpu); - sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c", + sprintf(cp, "last_accelerate: %04lx/%04lx dyntick_enabled: %d", rdp->last_accelerate & 0xffff, jiffies & 0xffff, - ".l"[rdp->all_lazy], - ".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)], - ".D"[!!rdp->tick_nohz_enabled_snap]); + !!rdp->tick_nohz_enabled_snap); } #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ @@ -279,6 +277,28 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ +static const char * const gp_state_names[] = { + [RCU_GP_IDLE] = "RCU_GP_IDLE", + [RCU_GP_WAIT_GPS] = "RCU_GP_WAIT_GPS", + [RCU_GP_DONE_GPS] = "RCU_GP_DONE_GPS", + [RCU_GP_ONOFF] = "RCU_GP_ONOFF", + [RCU_GP_INIT] = "RCU_GP_INIT", + [RCU_GP_WAIT_FQS] = "RCU_GP_WAIT_FQS", + [RCU_GP_DOING_FQS] = "RCU_GP_DOING_FQS", + [RCU_GP_CLEANUP] = "RCU_GP_CLEANUP", + [RCU_GP_CLEANED] = "RCU_GP_CLEANED", +}; + +/* + * Convert a ->gp_state value to a character string. + */ +static const char *gp_state_getname(short gs) +{ + if (gs < 0 || gs >= ARRAY_SIZE(gp_state_names)) + return "???"; + return gp_state_names[gs]; +} + /* * Print out diagnostic information for the specified stalled CPU. * diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 1861103662db..6c4b862f57d6 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -40,6 +40,7 @@ #include <linux/rcupdate_wait.h> #include <linux/sched/isolation.h> #include <linux/kprobes.h> +#include <linux/slab.h> #define CREATE_TRACE_POINTS @@ -51,9 +52,7 @@ #define MODULE_PARAM_PREFIX "rcupdate." #ifndef CONFIG_TINY_RCU -extern int rcu_expedited; /* from sysctl */ module_param(rcu_expedited, int, 0); -extern int rcu_normal; /* from sysctl */ module_param(rcu_normal, int, 0); static int rcu_normal_after_boot; module_param(rcu_normal_after_boot, int, 0); @@ -218,6 +217,7 @@ static int __init rcu_set_runtime_mode(void) { rcu_test_sync_prims(); rcu_scheduler_active = RCU_SCHEDULER_RUNNING; + kfree_rcu_scheduler_running(); rcu_test_sync_prims(); return 0; } @@ -435,7 +435,7 @@ struct debug_obj_descr rcuhead_debug_descr = { EXPORT_SYMBOL_GPL(rcuhead_debug_descr); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_RCU_TRACE) void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, unsigned long c) @@ -853,14 +853,22 @@ static void test_callback(struct rcu_head *r) DEFINE_STATIC_SRCU(early_srcu); +struct early_boot_kfree_rcu { + struct rcu_head rh; +}; + static void early_boot_test_call_rcu(void) { static struct rcu_head head; static struct rcu_head shead; + struct early_boot_kfree_rcu *rhp; call_rcu(&head, test_callback); if (IS_ENABLED(CONFIG_SRCU)) call_srcu(&early_srcu, &shead, test_callback); + rhp = kmalloc(sizeof(*rhp), GFP_KERNEL); + if (!WARN_ON_ONCE(!rhp)) + kfree_rcu(rhp, rh); } void rcu_early_boot_tests(void) diff --git a/kernel/rseq.c b/kernel/rseq.c index 27c48eb7de40..a4f86a9d6937 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -310,6 +310,8 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int ret; if (flags & RSEQ_FLAG_UNREGISTER) { + if (flags & ~RSEQ_FLAG_UNREGISTER) + return -EINVAL; /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index 1152259a4ca0..12bca64dff73 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -370,7 +370,7 @@ u64 sched_clock_cpu(int cpu) if (sched_clock_stable()) return sched_clock() + __sched_clock_offset; - if (!static_branch_unlikely(&sched_clock_running)) + if (!static_branch_likely(&sched_clock_running)) return sched_clock(); preempt_disable_notrace(); @@ -393,7 +393,7 @@ void sched_clock_tick(void) if (sched_clock_stable()) return; - if (!static_branch_unlikely(&sched_clock_running)) + if (!static_branch_likely(&sched_clock_running)) return; lockdep_assert_irqs_disabled(); @@ -460,7 +460,7 @@ void __init sched_clock_init(void) u64 sched_clock_cpu(int cpu) { - if (!static_branch_unlikely(&sched_clock_running)) + if (!static_branch_likely(&sched_clock_running)) return 0; return sched_clock(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 90e4b00ace89..1a9983da4408 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -552,27 +552,32 @@ void resched_cpu(int cpu) */ int get_nohz_timer_target(void) { - int i, cpu = smp_processor_id(); + int i, cpu = smp_processor_id(), default_cpu = -1; struct sched_domain *sd; - if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) - return cpu; + if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) { + if (!idle_cpu(cpu)) + return cpu; + default_cpu = cpu; + } rcu_read_lock(); for_each_domain(cpu, sd) { - for_each_cpu(i, sched_domain_span(sd)) { + for_each_cpu_and(i, sched_domain_span(sd), + housekeeping_cpumask(HK_FLAG_TIMER)) { if (cpu == i) continue; - if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) { + if (!idle_cpu(i)) { cpu = i; goto unlock; } } } - if (!housekeeping_cpu(cpu, HK_FLAG_TIMER)) - cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + if (default_cpu == -1) + default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + cpu = default_cpu; unlock: rcu_read_unlock(); return cpu; @@ -919,17 +924,17 @@ uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id) return uc_req; } -unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) +unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) { struct uclamp_se uc_eff; /* Task currently refcounted: use back-annotated (effective) value */ if (p->uclamp[clamp_id].active) - return p->uclamp[clamp_id].value; + return (unsigned long)p->uclamp[clamp_id].value; uc_eff = uclamp_eff_get(p, clamp_id); - return uc_eff.value; + return (unsigned long)uc_eff.value; } /* @@ -1253,7 +1258,8 @@ static void __init init_uclamp(void) mutex_init(&uclamp_mutex); for_each_possible_cpu(cpu) { - memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); + memset(&cpu_rq(cpu)->uclamp, 0, + sizeof(struct uclamp_rq)*UCLAMP_CNT); cpu_rq(cpu)->uclamp_flags = 0; } @@ -1441,17 +1447,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP -static inline bool is_per_cpu_kthread(struct task_struct *p) -{ - if (!(p->flags & PF_KTHREAD)) - return false; - - if (p->nr_cpus_allowed != 1) - return false; - - return true; -} - /* * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_rq(). @@ -3668,28 +3663,32 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu)) + if (!tick_nohz_tick_stopped_cpu(cpu)) goto out_requeue; rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr) || cpu_is_offline(cpu)) + if (cpu_is_offline(cpu)) goto out_unlock; + curr = rq->curr; update_rq_clock(rq); - delta = rq_clock_task(rq) - curr->se.exec_start; - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + if (!is_idle_task(curr)) { + /* + * Make sure the next tick runs within a reasonable + * amount of time. + */ + delta = rq_clock_task(rq) - curr->se.exec_start; + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + } curr->sched_class->task_tick(rq, curr, 0); + calc_load_nohz_remote(rq); out_unlock: rq_unlock_irq(rq, &rf); - out_requeue: + /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough @@ -4504,7 +4503,7 @@ static inline int rt_effective_prio(struct task_struct *p, int prio) void set_user_nice(struct task_struct *p, long nice) { bool queued, running; - int old_prio, delta; + int old_prio; struct rq_flags rf; struct rq *rq; @@ -4538,19 +4537,18 @@ void set_user_nice(struct task_struct *p, long nice) set_load_weight(p, true); old_prio = p->prio; p->prio = effective_prio(p); - delta = p->prio - old_prio; - if (queued) { + if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - /* - * If the task increased its priority or is running and - * lowered its priority, then reschedule its CPU: - */ - if (delta < 0 || (delta > 0 && task_running(rq, p))) - resched_curr(rq); - } if (running) set_next_task(rq, p); + + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + p->sched_class->prio_changed(rq, p, old_prio); + out_unlock: task_rq_unlock(rq, p, &rf); } @@ -7063,8 +7061,15 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, queue_flags); - if (running) + if (running) { set_next_task(rq, tsk); + /* + * After changing group, the running task may have joined a + * throttled one but it's still the running task. Trigger a + * resched to make sure that task can still run. + */ + resched_curr(rq); + } task_rq_unlock(rq, tsk, &rf); } @@ -7100,6 +7105,12 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) if (parent) sched_online_group(tg, parent); + +#ifdef CONFIG_UCLAMP_TASK_GROUP + /* Propagate the effective uclamp value for the new group */ + cpu_util_update_eff(css); +#endif + return 0; } @@ -7254,7 +7265,7 @@ capacity_from_percent(char *buf) &req.percent); if (req.ret) return req; - if (req.percent > UCLAMP_PERCENT_SCALE) { + if ((u64)req.percent > UCLAMP_PERCENT_SCALE) { req.ret = -ERANGE; return req; } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 9b8916fd00a2..7fbaee24c824 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -238,7 +238,7 @@ unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, */ util = util_cfs + cpu_util_rt(rq); if (type == FREQUENCY_UTIL) - util = uclamp_util_with(rq, util, p); + util = uclamp_rq_util_with(rq, util, p); dl_util = cpu_util_dl(rq); diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index b7abca987d94..1a2719e1350a 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -46,6 +46,8 @@ static int convert_prio(int prio) * @cp: The cpupri context * @p: The task * @lowest_mask: A mask to fill in with selected CPUs (or NULL) + * @fitness_fn: A pointer to a function to do custom checks whether the CPU + * fits a specific criteria so that we only return those CPUs. * * Note: This function returns the recommended CPUs as calculated during the * current invocation. By the time the call returns, the CPUs may have in @@ -57,7 +59,8 @@ static int convert_prio(int prio) * Return: (int)bool - CPUs were found */ int cpupri_find(struct cpupri *cp, struct task_struct *p, - struct cpumask *lowest_mask) + struct cpumask *lowest_mask, + bool (*fitness_fn)(struct task_struct *p, int cpu)) { int idx = 0; int task_pri = convert_prio(p->prio); @@ -98,6 +101,8 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, continue; if (lowest_mask) { + int cpu; + cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); /* @@ -108,7 +113,23 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, * condition, simply act as though we never hit this * priority level and continue on. */ - if (cpumask_any(lowest_mask) >= nr_cpu_ids) + if (cpumask_empty(lowest_mask)) + continue; + + if (!fitness_fn) + return 1; + + /* Ensure the capacity of the CPUs fit the task */ + for_each_cpu(cpu, lowest_mask) { + if (!fitness_fn(p, cpu)) + cpumask_clear_cpu(cpu, lowest_mask); + } + + /* + * If no CPU at the current priority can fit the task + * continue looking + */ + if (cpumask_empty(lowest_mask)) continue; } diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h index 7dc20a3232e7..32dd520db11f 100644 --- a/kernel/sched/cpupri.h +++ b/kernel/sched/cpupri.h @@ -18,7 +18,9 @@ struct cpupri { }; #ifdef CONFIG_SMP -int cpupri_find(struct cpupri *cp, struct task_struct *p, struct cpumask *lowest_mask); +int cpupri_find(struct cpupri *cp, struct task_struct *p, + struct cpumask *lowest_mask, + bool (*fitness_fn)(struct task_struct *p, int cpu)); void cpupri_set(struct cpupri *cp, int cpu, int pri); int cpupri_init(struct cpupri *cp); void cpupri_cleanup(struct cpupri *cp); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index d43318a489f2..cff3e656566d 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -355,7 +355,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) * softirq as those do not count in task exec_runtime any more. */ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq, int ticks) + int ticks) { u64 other, cputime = TICK_NSEC * ticks; @@ -381,7 +381,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, account_system_index_time(p, cputime, CPUTIME_SOFTIRQ); } else if (user_tick) { account_user_time(p, cputime); - } else if (p == rq->idle) { + } else if (p == this_rq()->idle) { account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ account_guest_time(p, cputime); @@ -392,14 +392,12 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, static void irqtime_account_idle_ticks(int ticks) { - struct rq *rq = this_rq(); - - irqtime_account_process_tick(current, 0, rq, ticks); + irqtime_account_process_tick(current, 0, ticks); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ static inline void irqtime_account_idle_ticks(int ticks) { } static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq, int nr_ticks) { } + int nr_ticks) { } #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ /* @@ -473,13 +471,12 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) void account_process_tick(struct task_struct *p, int user_tick) { u64 cputime, steal; - struct rq *rq = this_rq(); if (vtime_accounting_enabled_this_cpu()) return; if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq, 1); + irqtime_account_process_tick(p, user_tick, 1); return; } @@ -493,7 +490,7 @@ void account_process_tick(struct task_struct *p, int user_tick) if (user_tick) account_user_time(p, cputime); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + else if ((p != this_rq()->idle) || (irq_count() != HARDIRQ_OFFSET)) account_system_time(p, HARDIRQ_OFFSET, cputime); else account_idle_time(cputime); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index f7e4579e746c..879d3ccf3806 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -751,9 +751,16 @@ void sysrq_sched_debug_show(void) int cpu; sched_debug_header(NULL); - for_each_online_cpu(cpu) + for_each_online_cpu(cpu) { + /* + * Need to reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI or stop_machine. + */ + touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); print_cpu(NULL, cpu); - + } } /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ba749f579714..c1217bfe5e81 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -801,7 +801,7 @@ void post_init_entity_util_avg(struct task_struct *p) * For !fair tasks do: * update_cfs_rq_load_avg(now, cfs_rq); - attach_entity_load_avg(cfs_rq, se, 0); + attach_entity_load_avg(cfs_rq, se); switched_from_fair(rq, p); * * such that the next switched_to_fair() has the @@ -3114,7 +3114,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) { struct rq *rq = rq_of(cfs_rq); - if (&rq->cfs == cfs_rq || (flags & SCHED_CPUFREQ_MIGRATION)) { + if (&rq->cfs == cfs_rq) { /* * There are a few boundary cases this might miss but it should * get called often enough that that should (hopefully) not be @@ -3366,16 +3366,17 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf runnable_load_sum = (s64)se_runnable(se) * runnable_sum; runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX); - delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum; - delta_avg = runnable_load_avg - se->avg.runnable_load_avg; - - se->avg.runnable_load_sum = runnable_sum; - se->avg.runnable_load_avg = runnable_load_avg; if (se->on_rq) { + delta_sum = runnable_load_sum - + se_weight(se) * se->avg.runnable_load_sum; + delta_avg = runnable_load_avg - se->avg.runnable_load_avg; add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg); add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum); } + + se->avg.runnable_load_sum = runnable_sum; + se->avg.runnable_load_avg = runnable_load_avg; } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3515,12 +3516,11 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) * attach_entity_load_avg - attach this entity to its cfs_rq load avg * @cfs_rq: cfs_rq to attach to * @se: sched_entity to attach - * @flags: migration hints * * Must call update_cfs_rq_load_avg() before this, since we rely on * cfs_rq->avg.last_update_time being current. */ -static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib; @@ -3556,7 +3556,7 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s add_tg_cfs_propagate(cfs_rq, se->avg.load_sum); - cfs_rq_util_change(cfs_rq, flags); + cfs_rq_util_change(cfs_rq, 0); trace_pelt_cfs_tp(cfs_rq); } @@ -3614,7 +3614,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s * * IOW we're enqueueing a task on a new CPU. */ - attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION); + attach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, 0); } else if (decayed) { @@ -3711,6 +3711,20 @@ static inline unsigned long task_util_est(struct task_struct *p) return max(task_util(p), _task_util_est(p)); } +#ifdef CONFIG_UCLAMP_TASK +static inline unsigned long uclamp_task_util(struct task_struct *p) +{ + return clamp(task_util_est(p), + uclamp_eff_value(p, UCLAMP_MIN), + uclamp_eff_value(p, UCLAMP_MAX)); +} +#else +static inline unsigned long uclamp_task_util(struct task_struct *p) +{ + return task_util_est(p); +} +#endif + static inline void util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) { @@ -3822,7 +3836,7 @@ done: static inline int task_fits_capacity(struct task_struct *p, long capacity) { - return fits_capacity(task_util_est(p), capacity); + return fits_capacity(uclamp_task_util(p), capacity); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -3857,7 +3871,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s static inline void remove_entity_load_avg(struct sched_entity *se) {} static inline void -attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) {} +attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} @@ -5196,6 +5210,20 @@ static inline void update_overutilized_status(struct rq *rq) static inline void update_overutilized_status(struct rq *rq) { } #endif +/* Runqueue only has SCHED_IDLE tasks enqueued */ +static int sched_idle_rq(struct rq *rq) +{ + return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + rq->nr_running); +} + +#ifdef CONFIG_SMP +static int sched_idle_cpu(int cpu) +{ + return sched_idle_rq(cpu_rq(cpu)); +} +#endif + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -5310,6 +5338,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct sched_entity *se = &p->se; int task_sleep = flags & DEQUEUE_SLEEP; int idle_h_nr_running = task_has_idle_policy(p); + bool was_sched_idle = sched_idle_rq(rq); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); @@ -5356,6 +5385,10 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!se) sub_nr_running(rq, 1); + /* balance early to pull high priority tasks */ + if (unlikely(!was_sched_idle && sched_idle_rq(rq))) + rq->next_balance = jiffies; + util_est_dequeue(&rq->cfs, p, task_sleep); hrtick_update(rq); } @@ -5378,15 +5411,6 @@ static struct { #endif /* CONFIG_NO_HZ_COMMON */ -/* CPU only has SCHED_IDLE tasks enqueued */ -static int sched_idle_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && - rq->nr_running); -} - static unsigned long cpu_load(struct rq *rq) { return cfs_rq_load_avg(&rq->cfs); @@ -5588,7 +5612,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this unsigned int min_exit_latency = UINT_MAX; u64 latest_idle_timestamp = 0; int least_loaded_cpu = this_cpu; - int shallowest_idle_cpu = -1, si_cpu = -1; + int shallowest_idle_cpu = -1; int i; /* Check if we have any choice: */ @@ -5597,6 +5621,9 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this /* Traverse only the allowed CPUs */ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { + if (sched_idle_cpu(i)) + return i; + if (available_idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5619,12 +5646,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this latest_idle_timestamp = rq->idle_stamp; shallowest_idle_cpu = i; } - } else if (shallowest_idle_cpu == -1 && si_cpu == -1) { - if (sched_idle_cpu(i)) { - si_cpu = i; - continue; - } - + } else if (shallowest_idle_cpu == -1) { load = cpu_load(cpu_rq(i)); if (load < min_load) { min_load = load; @@ -5633,11 +5655,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this } } - if (shallowest_idle_cpu != -1) - return shallowest_idle_cpu; - if (si_cpu != -1) - return si_cpu; - return least_loaded_cpu; + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; } static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, @@ -5790,7 +5808,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int */ static int select_idle_smt(struct task_struct *p, int target) { - int cpu, si_cpu = -1; + int cpu; if (!static_branch_likely(&sched_smt_present)) return -1; @@ -5798,13 +5816,11 @@ static int select_idle_smt(struct task_struct *p, int target) for_each_cpu(cpu, cpu_smt_mask(target)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; - if (available_idle_cpu(cpu)) + if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; - if (si_cpu == -1 && sched_idle_cpu(cpu)) - si_cpu = cpu; } - return si_cpu; + return -1; } #else /* CONFIG_SCHED_SMT */ @@ -5828,12 +5844,13 @@ static inline int select_idle_smt(struct task_struct *p, int target) */ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); struct sched_domain *this_sd; u64 avg_cost, avg_idle; u64 time, cost; s64 delta; int this = smp_processor_id(); - int cpu, nr = INT_MAX, si_cpu = -1; + int cpu, nr = INT_MAX; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -5859,15 +5876,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t time = cpu_clock(this); - for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + for_each_cpu_wrap(cpu, cpus, target) { if (!--nr) - return si_cpu; - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) - continue; - if (available_idle_cpu(cpu)) + return -1; + if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) break; - if (si_cpu == -1 && sched_idle_cpu(cpu)) - si_cpu = cpu; } time = cpu_clock(this) - time; @@ -5896,6 +5911,20 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) (available_idle_cpu(prev) || sched_idle_cpu(prev))) return prev; + /* + * Allow a per-cpu kthread to stack with the wakee if the + * kworker thread and the tasks previous CPUs are the same. + * The assumption is that the wakee queued work for the + * per-cpu kthread that is now complete and the wakeup is + * essentially a sync wakeup. An obvious example of this + * pattern is IO completions. + */ + if (is_per_cpu_kthread(current) && + prev == smp_processor_id() && + this_rq()->nr_running <= 1) { + return prev; + } + /* Check a recently used CPU as a potential idle candidate: */ recent_used_cpu = p->recent_used_cpu; if (recent_used_cpu != prev && @@ -6268,9 +6297,18 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; - /* Skip CPUs that will be overutilized. */ util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); + spare_cap = cpu_cap - util; + + /* + * Skip CPUs that cannot satisfy the capacity request. + * IOW, placing the task there would make the CPU + * overutilized. Take uclamp into account to see how + * much capacity we can get out of the CPU; this is + * aligned with schedutil_cpu_util(). + */ + util = uclamp_rq_util_with(cpu_rq(cpu), util, p); if (!fits_capacity(util, cpu_cap)) continue; @@ -6285,7 +6323,6 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * Find the CPU with the maximum spare capacity in * the performance domain */ - spare_cap = cpu_cap - util; if (spare_cap > max_spare_cap) { max_spare_cap = spare_cap; max_spare_cap_cpu = cpu; @@ -7780,29 +7817,11 @@ void update_group_capacity(struct sched_domain *sd, int cpu) */ for_each_cpu(cpu, sched_group_span(sdg)) { - struct sched_group_capacity *sgc; - struct rq *rq = cpu_rq(cpu); + unsigned long cpu_cap = capacity_of(cpu); - /* - * build_sched_domains() -> init_sched_groups_capacity() - * gets here before we've attached the domains to the - * runqueues. - * - * Use capacity_of(), which is set irrespective of domains - * in update_cpu_capacity(). - * - * This avoids capacity from being 0 and - * causing divide-by-zero issues on boot. - */ - if (unlikely(!rq->sd)) { - capacity += capacity_of(cpu); - } else { - sgc = rq->sd->groups->sgc; - capacity += sgc->capacity; - } - - min_capacity = min(capacity, min_capacity); - max_capacity = max(capacity, max_capacity); + capacity += cpu_cap; + min_capacity = min(cpu_cap, min_capacity); + max_capacity = max(cpu_cap, max_capacity); } } else { /* @@ -8168,14 +8187,18 @@ static bool update_sd_pick_busiest(struct lb_env *env, case group_has_spare: /* - * Select not overloaded group with lowest number of - * idle cpus. We could also compare the spare capacity - * which is more stable but it can end up that the - * group has less spare capacity but finally more idle + * Select not overloaded group with lowest number of idle cpus + * and highest number of running tasks. We could also compare + * the spare capacity which is more stable but it can end up + * that the group has less spare capacity but finally more idle * CPUs which means less opportunity to pull tasks. */ - if (sgs->idle_cpus >= busiest->idle_cpus) + if (sgs->idle_cpus > busiest->idle_cpus) return false; + else if ((sgs->idle_cpus == busiest->idle_cpus) && + (sgs->sum_nr_running <= busiest->sum_nr_running)) + return false; + break; } @@ -8314,6 +8337,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, sgs->group_capacity = group->sgc->capacity; + sgs->group_weight = group->group_weight; + sgs->group_type = group_classify(sd->imbalance_pct, group, sgs); /* @@ -8648,10 +8673,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * Try to use spare capacity of local group without overloading it or * emptying busiest. - * XXX Spreading tasks across NUMA nodes is not always the best policy - * and special care should be taken for SD_NUMA domain level before - * spreading the tasks. For now, load_balance() fully relies on - * NUMA_BALANCING and fbq_classify_group/rq to override the decision. */ if (local->group_type == group_has_spare) { if (busiest->group_type > group_fully_busy) { @@ -8691,16 +8712,37 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s env->migration_type = migrate_task; lsub_positive(&nr_diff, local->sum_nr_running); env->imbalance = nr_diff >> 1; - return; - } + } else { - /* - * If there is no overload, we just want to even the number of - * idle cpus. - */ - env->migration_type = migrate_task; - env->imbalance = max_t(long, 0, (local->idle_cpus - + /* + * If there is no overload, we just want to even the number of + * idle cpus. + */ + env->migration_type = migrate_task; + env->imbalance = max_t(long, 0, (local->idle_cpus - busiest->idle_cpus) >> 1); + } + + /* Consider allowing a small imbalance between NUMA groups */ + if (env->sd->flags & SD_NUMA) { + unsigned int imbalance_min; + + /* + * Compute an allowed imbalance based on a simple + * pair of communicating tasks that should remain + * local and ignore them. + * + * NOTE: Generally this would have been based on + * the domain size and this was evaluated. However, + * the benefit is similar across a range of workloads + * and machines but scaling by the domain size adds + * the risk that lower domains have to be rebalanced. + */ + imbalance_min = 2; + if (busiest->sum_nr_running <= imbalance_min) + env->imbalance = 0; + } + return; } @@ -9529,6 +9571,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) { int continue_balancing = 1; int cpu = rq->cpu; + int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); unsigned long interval; struct sched_domain *sd; /* Earliest time when we have to do rebalance again */ @@ -9565,7 +9608,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) break; } - interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + interval = get_sd_balance_interval(sd, busy); need_serialize = sd->flags & SD_SERIALIZE; if (need_serialize) { @@ -9581,9 +9624,10 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) * state even if we migrated tasks. Update it. */ idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; + busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); } sd->last_balance = jiffies; - interval = get_sd_balance_interval(sd, idle != CPU_IDLE); + interval = get_sd_balance_interval(sd, busy); } if (need_serialize) spin_unlock(&balancing); @@ -10333,6 +10377,9 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) if (!task_on_rq_queued(p)) return; + if (rq->cfs.nr_running == 1) + return; + /* * Reschedule if we are currently running on this runqueue and * our priority decreased, or if we are not currently running on @@ -10423,7 +10470,7 @@ static void attach_entity_cfs_rq(struct sched_entity *se) /* Synchronize entity with its cfs_rq */ update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD); - attach_entity_load_avg(cfs_rq, se, 0); + attach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, false); propagate_entity_cfs_rq(se); } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index ffa959e91227..b743bf38f08f 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -158,7 +158,7 @@ static void cpuidle_idle_call(void) /* * Suspend-to-idle ("s2idle") is a system state in which all user space * has been frozen, all I/O devices have been suspended and the only - * activity happens here and in iterrupts (if any). In that case bypass + * activity happens here and in interrupts (if any). In that case bypass * the cpuidle governor and go stratight for the deepest idle state * available. Possibly also suspend the local tick and the entire * timekeeping to prevent timer interrupts from kicking us out of idle diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 9fcb2a695a41..008d6ac2342b 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str) continue; } + if (!strncmp(str, "managed_irq,", 12)) { + str += 12; + flags |= HK_FLAG_MANAGED_IRQ; + continue; + } + pr_warn("isolcpus: Error, unknown flag\n"); return 0; } diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 28a516575c18..de22da666ac7 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void) return calc_load_idx & 1; } -void calc_load_nohz_start(void) +static void calc_load_nohz_fold(struct rq *rq) { - struct rq *this_rq = this_rq(); long delta; - /* - * We're going into NO_HZ mode, if there's any pending delta, fold it - * into the pending NO_HZ delta. - */ - delta = calc_load_fold_active(this_rq, 0); + delta = calc_load_fold_active(rq, 0); if (delta) { int idx = calc_load_write_idx(); @@ -248,6 +243,24 @@ void calc_load_nohz_start(void) } } +void calc_load_nohz_start(void) +{ + /* + * We're going into NO_HZ mode, if there's any pending delta, fold it + * into the pending NO_HZ delta. + */ + calc_load_nohz_fold(this_rq()); +} + +/* + * Keep track of the load for NOHZ_FULL, must be called between + * calc_load_nohz_{start,stop}(). + */ +void calc_load_nohz_remote(struct rq *rq) +{ + calc_load_nohz_fold(rq); +} + void calc_load_nohz_stop(void) { struct rq *this_rq = this_rq(); @@ -268,7 +281,7 @@ void calc_load_nohz_stop(void) this_rq->calc_load_update += LOAD_FREQ; } -static long calc_load_nohz_fold(void) +static long calc_load_nohz_read(void) { int idx = calc_load_read_idx(); long delta = 0; @@ -323,7 +336,7 @@ static void calc_global_nohz(void) } #else /* !CONFIG_NO_HZ_COMMON */ -static inline long calc_load_nohz_fold(void) { return 0; } +static inline long calc_load_nohz_read(void) { return 0; } static inline void calc_global_nohz(void) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks) /* * Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs. */ - delta = calc_load_nohz_fold(); + delta = calc_load_nohz_read(); if (delta) atomic_long_add(delta, &calc_load_tasks); diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index a96db50d40e0..bd006b79b360 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -129,8 +129,20 @@ accumulate_sum(u64 delta, struct sched_avg *sa, * Step 2 */ delta %= 1024; - contrib = __accumulate_pelt_segments(periods, - 1024 - sa->period_contrib, delta); + if (load) { + /* + * This relies on the: + * + * if (!load) + * runnable = running = 0; + * + * clause from ___update_load_sum(); this results in + * the below usage of @contrib to dissapear entirely, + * so no point in calculating it. + */ + contrib = __accumulate_pelt_segments(periods, + 1024 - sa->period_contrib, delta); + } } sa->period_contrib = delta; @@ -205,7 +217,9 @@ ___update_load_sum(u64 now, struct sched_avg *sa, * This means that weight will be 0 but not running for a sched_entity * but also for a cfs_rq if the latter becomes idle. As an example, * this happens during idle_balance() which calls - * update_blocked_averages() + * update_blocked_averages(). + * + * Also see the comment in accumulate_sum(). */ if (!load) runnable = running = 0; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ce8f6748678a..028520702717 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1199,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; + if (!nbytes) + return -EINVAL; + buf_size = min(nbytes, sizeof(buf)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; @@ -1251,39 +1254,41 @@ static int psi_fop_release(struct inode *inode, struct file *file) return single_release(inode, file); } -static const struct file_operations psi_io_fops = { - .open = psi_io_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_io_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_io_proc_ops = { + .proc_open = psi_io_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_io_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, }; -static const struct file_operations psi_memory_fops = { - .open = psi_memory_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_memory_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_memory_proc_ops = { + .proc_open = psi_memory_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_memory_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_release, }; -static const struct file_operations psi_cpu_fops = { - .open = psi_cpu_open, - .read = seq_read, - .llseek = seq_lseek, - .write = psi_cpu_write, - .poll = psi_fop_poll, - .release = psi_fop_release, +static const struct proc_ops psi_cpu_proc_ops = { + .proc_open = psi_cpu_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_write = psi_cpu_write, + .proc_poll = psi_fop_poll, + .proc_release = psi_fop_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); + if (psi_enable) { + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_proc_ops); + proc_create("pressure/memory", 0, NULL, &psi_memory_proc_ops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_proc_ops); + } return 0; } module_init(psi_proc_init); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e591d40fd645..4043abe45459 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -437,6 +437,45 @@ static inline int on_rt_rq(struct sched_rt_entity *rt_se) return rt_se->on_rq; } +#ifdef CONFIG_UCLAMP_TASK +/* + * Verify the fitness of task @p to run on @cpu taking into account the uclamp + * settings. + * + * This check is only important for heterogeneous systems where uclamp_min value + * is higher than the capacity of a @cpu. For non-heterogeneous system this + * function will always return true. + * + * The function will return true if the capacity of the @cpu is >= the + * uclamp_min and false otherwise. + * + * Note that uclamp_min will be clamped to uclamp_max if uclamp_min + * > uclamp_max. + */ +static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu) +{ + unsigned int min_cap; + unsigned int max_cap; + unsigned int cpu_cap; + + /* Only heterogeneous systems can benefit from this check */ + if (!static_branch_unlikely(&sched_asym_cpucapacity)) + return true; + + min_cap = uclamp_eff_value(p, UCLAMP_MIN); + max_cap = uclamp_eff_value(p, UCLAMP_MAX); + + cpu_cap = capacity_orig_of(cpu); + + return cpu_cap >= min(min_cap, max_cap); +} +#else +static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu) +{ + return true; +} +#endif + #ifdef CONFIG_RT_GROUP_SCHED static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) @@ -1391,6 +1430,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) { struct task_struct *curr; struct rq *rq; + bool test; /* For anything but wake ups, just return the task_cpu */ if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK) @@ -1422,10 +1462,16 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) * * This test is optimistic, if we get it wrong the load-balancer * will have to sort it out. + * + * We take into account the capacity of the CPU to ensure it fits the + * requirement of the task - which is only important on heterogeneous + * systems like big.LITTLE. */ - if (curr && unlikely(rt_task(curr)) && - (curr->nr_cpus_allowed < 2 || - curr->prio <= p->prio)) { + test = curr && + unlikely(rt_task(curr)) && + (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio); + + if (test || !rt_task_fits_capacity(p, cpu)) { int target = find_lowest_rq(p); /* @@ -1449,15 +1495,15 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * let's hope p can move out. */ if (rq->curr->nr_cpus_allowed == 1 || - !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) + !cpupri_find(&rq->rd->cpupri, rq->curr, NULL, NULL)) return; /* * p is migratable, so let's not schedule it and * see if it is pushed or pulled somewhere else. */ - if (p->nr_cpus_allowed != 1 - && cpupri_find(&rq->rd->cpupri, p, NULL)) + if (p->nr_cpus_allowed != 1 && + cpupri_find(&rq->rd->cpupri, p, NULL, NULL)) return; /* @@ -1601,7 +1647,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, p->cpus_ptr)) + cpumask_test_cpu(cpu, p->cpus_ptr) && + rt_task_fits_capacity(p, cpu)) return 1; return 0; @@ -1643,7 +1690,8 @@ static int find_lowest_rq(struct task_struct *task) if (task->nr_cpus_allowed == 1) return -1; /* No other targets possible */ - if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) + if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask, + rt_task_fits_capacity)) return -1; /* No targets found */ /* @@ -2147,12 +2195,14 @@ skip: */ static void task_woken_rt(struct rq *rq, struct task_struct *p) { - if (!task_running(rq, p) && - !test_tsk_need_resched(rq->curr) && - p->nr_cpus_allowed > 1 && - (dl_task(rq->curr) || rt_task(rq->curr)) && - (rq->curr->nr_cpus_allowed < 2 || - rq->curr->prio <= p->prio)) + bool need_to_push = !task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + p->nr_cpus_allowed > 1 && + (dl_task(rq->curr) || rt_task(rq->curr)) && + (rq->curr->nr_cpus_allowed < 2 || + rq->curr->prio <= p->prio); + + if (need_to_push || !rt_task_fits_capacity(p, cpu_of(rq))) push_rt_tasks(rq); } @@ -2224,7 +2274,10 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) + bool need_to_push = rq->rt.overloaded || + !rt_task_fits_capacity(p, cpu_of(rq)); + + if (p->nr_cpus_allowed > 1 && need_to_push) rt_queue_push_tasks(rq); #endif /* CONFIG_SMP */ if (p->prio < rq->curr->prio && cpu_online(cpu_of(rq))) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 280a3c735935..9ea647835fd6 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -896,7 +896,7 @@ struct rq { */ unsigned long nr_uninterruptible; - struct task_struct *curr; + struct task_struct __rcu *curr; struct task_struct *idle; struct task_struct *stop; unsigned long next_balance; @@ -2300,14 +2300,14 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ #ifdef CONFIG_UCLAMP_TASK -unsigned int uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); +unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); static __always_inline -unsigned int uclamp_util_with(struct rq *rq, unsigned int util, - struct task_struct *p) +unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, + struct task_struct *p) { - unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); - unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); + unsigned long min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); + unsigned long max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); if (p) { min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN)); @@ -2324,18 +2324,10 @@ unsigned int uclamp_util_with(struct rq *rq, unsigned int util, return clamp(util, min_util, max_util); } - -static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) -{ - return uclamp_util_with(rq, util, NULL); -} #else /* CONFIG_UCLAMP_TASK */ -static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, - struct task_struct *p) -{ - return util; -} -static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) +static inline +unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util, + struct task_struct *p) { return util; } @@ -2487,3 +2479,16 @@ static inline void membarrier_switch_mm(struct rq *rq, { } #endif + +#ifdef CONFIG_SMP +static inline bool is_per_cpu_kthread(struct task_struct *p) +{ + if (!(p->flags & PF_KTHREAD)) + return false; + + if (p->nr_cpus_allowed != 1) + return false; + + return true; +} +#endif diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 6ec1e595b1d4..dfb64c08a407 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1880,6 +1880,42 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve } /* + * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for + * any two given CPUs at this (non-NUMA) topology level. + */ +static bool topology_span_sane(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, int cpu) +{ + int i; + + /* NUMA levels are allowed to overlap */ + if (tl->flags & SDTL_OVERLAP) + return true; + + /* + * Non-NUMA levels cannot partially overlap - they must be either + * completely equal or completely disjoint. Otherwise we can end up + * breaking the sched_group lists - i.e. a later get_group() pass + * breaks the linking done for an earlier span. + */ + for_each_cpu(i, cpu_map) { + if (i == cpu) + continue; + /* + * We should 'and' all those masks with 'cpu_map' to exactly + * match the topology we're about to build, but that can only + * remove CPUs, which only lessens our ability to detect + * overlaps + */ + if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) && + cpumask_intersects(tl->mask(cpu), tl->mask(i))) + return false; + } + + return true; +} + +/* * Find the sched_domain_topology_level where all CPU capacities are visible * for all CPUs. */ @@ -1975,6 +2011,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att has_asym = true; } + if (WARN_ON(!topology_span_sane(tl, cpu_map, i))) + goto error; + sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i); if (tl == sched_domain_topology) diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index 45eba18a2898..02ce292b9bc0 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -179,6 +179,7 @@ void init_wait_var_entry(struct wait_bit_queue_entry *wbq_entry, void *var, int .bit_nr = -1, }, .wq_entry = { + .flags = flags, .private = current, .func = var_wake_function, .entry = LIST_HEAD_INIT(wbq_entry->wq_entry.entry), diff --git a/kernel/signal.c b/kernel/signal.c index bcd46f547db3..5b2396350dd1 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -413,27 +413,32 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimi { struct sigqueue *q = NULL; struct user_struct *user; + int sigpending; /* * Protect access to @t credentials. This can go away when all * callers hold rcu read lock. + * + * NOTE! A pending signal will hold on to the user refcount, + * and we get/put the refcount only when the sigpending count + * changes from/to zero. */ rcu_read_lock(); - user = get_uid(__task_cred(t)->user); - atomic_inc(&user->sigpending); + user = __task_cred(t)->user; + sigpending = atomic_inc_return(&user->sigpending); + if (sigpending == 1) + get_uid(user); rcu_read_unlock(); - if (override_rlimit || - atomic_read(&user->sigpending) <= - task_rlimit(t, RLIMIT_SIGPENDING)) { + if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) { q = kmem_cache_alloc(sigqueue_cachep, flags); } else { print_dropped_signal(sig); } if (unlikely(q == NULL)) { - atomic_dec(&user->sigpending); - free_uid(user); + if (atomic_dec_and_test(&user->sigpending)) + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; @@ -447,8 +452,8 @@ static void __sigqueue_free(struct sigqueue *q) { if (q->flags & SIGQUEUE_PREALLOC) return; - atomic_dec(&q->user->sigpending); - free_uid(q->user); + if (atomic_dec_and_test(&q->user->sigpending)) + free_uid(q->user); kmem_cache_free(sigqueue_cachep, q); } @@ -1383,7 +1388,7 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk, * must see ->sighand == NULL. */ spin_lock_irqsave(&sighand->siglock, *flags); - if (likely(sighand == tsk->sighand)) + if (likely(sighand == rcu_access_pointer(tsk->sighand))) break; spin_unlock_irqrestore(&sighand->siglock, *flags); } diff --git a/kernel/smp.c b/kernel/smp.c index 7dbcb402c2fc..d0ada39eb4d4 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -395,22 +395,9 @@ call: } EXPORT_SYMBOL_GPL(smp_call_function_any); -/** - * smp_call_function_many(): Run a function on a set of other CPUs. - * @mask: The set of cpus to run on (only runs on online subset). - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @wait: If true, wait (atomically) until function has completed - * on other CPUs. - * - * If @wait is true, then returns once @func has returned. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. Preemption - * must be disabled when calling this function. - */ -void smp_call_function_many(const struct cpumask *mask, - smp_call_func_t func, void *info, bool wait) +static void smp_call_function_many_cond(const struct cpumask *mask, + smp_call_func_t func, void *info, + bool wait, smp_cond_func_t cond_func) { struct call_function_data *cfd; int cpu, next_cpu, this_cpu = smp_processor_id(); @@ -448,7 +435,8 @@ void smp_call_function_many(const struct cpumask *mask, /* Fastpath: do that cpu by itself. */ if (next_cpu >= nr_cpu_ids) { - smp_call_function_single(cpu, func, info, wait); + if (!cond_func || cond_func(cpu, info)) + smp_call_function_single(cpu, func, info, wait); return; } @@ -465,6 +453,9 @@ void smp_call_function_many(const struct cpumask *mask, for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); + if (cond_func && !cond_func(cpu, info)) + continue; + csd_lock(csd); if (wait) csd->flags |= CSD_FLAG_SYNCHRONOUS; @@ -486,6 +477,26 @@ void smp_call_function_many(const struct cpumask *mask, } } } + +/** + * smp_call_function_many(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on (only runs on online subset). + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed + * on other CPUs. + * + * If @wait is true, then returns once @func has returned. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. Preemption + * must be disabled when calling this function. + */ +void smp_call_function_many(const struct cpumask *mask, + smp_call_func_t func, void *info, bool wait) +{ + smp_call_function_many_cond(mask, func, info, wait, NULL); +} EXPORT_SYMBOL(smp_call_function_many); /** @@ -668,11 +679,6 @@ EXPORT_SYMBOL(on_each_cpu_mask); * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. - * @gfp_flags: GFP flags to use when allocating the cpumask - * used internally by the function. - * - * The function might sleep if the GFP flags indicates a non - * atomic allocation is allowed. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. @@ -680,46 +686,27 @@ 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_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) +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, const struct cpumask *mask) { - cpumask_var_t cpus; - int cpu, ret; - - might_sleep_if(gfpflags_allow_blocking(gfp_flags)); - - if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) { - preempt_disable(); - for_each_cpu(cpu, mask) - if (cond_func(cpu, info)) - __cpumask_set_cpu(cpu, cpus); - on_each_cpu_mask(cpus, func, info, wait); - preempt_enable(); - free_cpumask_var(cpus); - } else { - /* - * No free cpumask, bother. No matter, we'll - * just have to IPI them one by one. - */ - preempt_disable(); - for_each_cpu(cpu, mask) - if (cond_func(cpu, info)) { - ret = smp_call_function_single(cpu, func, - info, wait); - WARN_ON_ONCE(ret); - } - preempt_enable(); + int cpu = get_cpu(); + + smp_call_function_many_cond(mask, func, info, wait, cond_func); + if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) { + unsigned long flags; + + local_irq_save(flags); + func(info); + local_irq_restore(flags); } + put_cpu(); } 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) +void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait) { - on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, - cpu_online_mask); + on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask); } EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 1fe34a9fabc2..865bb0228ab6 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -442,7 +442,7 @@ static int __stop_cpus(const struct cpumask *cpumask, * @cpumask were offline; otherwise, 0 if all executions of @fn * returned 0, any non zero return value if any returned non zero. */ -int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) +static int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) { int ret; @@ -453,36 +453,6 @@ int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) return ret; } -/** - * try_stop_cpus - try to stop multiple cpus - * @cpumask: cpus to stop - * @fn: function to execute - * @arg: argument to @fn - * - * Identical to stop_cpus() except that it fails with -EAGAIN if - * someone else is already using the facility. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * -EAGAIN if someone else is already stopping cpus, -ENOENT if - * @fn(@arg) was not executed at all because all cpus in @cpumask were - * offline; otherwise, 0 if all executions of @fn returned 0, any non - * zero return value if any returned non zero. - */ -int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg) -{ - int ret; - - /* static works are used, process one request at a time */ - if (!mutex_trylock(&stop_cpus_mutex)) - return -EAGAIN; - ret = __stop_cpus(cpumask, fn, arg); - mutex_unlock(&stop_cpus_mutex); - return ret; -} - static int cpu_stop_should_run(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); diff --git a/kernel/sys.c b/kernel/sys.c index a9331f101883..f9bc5c303e3f 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2261,6 +2261,8 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, return -EINVAL; } +#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LESS_THROTTLE) + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2488,6 +2490,29 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = GET_TAGGED_ADDR_CTRL(); break; + case PR_SET_IO_FLUSHER: + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + if (arg3 || arg4 || arg5) + return -EINVAL; + + if (arg2 == 1) + current->flags |= PR_IO_FLUSHER; + else if (!arg2) + current->flags &= ~PR_IO_FLUSHER; + else + return -EINVAL; + break; + case PR_GET_IO_FLUSHER: + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + error = (current->flags & PR_IO_FLUSHER) == PR_IO_FLUSHER; + break; default: error = -EINVAL; break; diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c index 2a63241a8453..ccb78509f1a8 100644 --- a/kernel/sysctl-test.c +++ b/kernel/sysctl-test.c @@ -389,4 +389,6 @@ static struct kunit_suite sysctl_test_suite = { .test_cases = sysctl_test_cases, }; -kunit_test_suite(sysctl_test_suite); +kunit_test_suites(&sysctl_test_suite); + +MODULE_LICENSE("GPL v2"); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 70665934d53e..ad5b88a53c5a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -805,15 +805,6 @@ static struct ctl_table kern_table[] = { .extra2 = &maxolduid, }, #ifdef CONFIG_S390 -#ifdef CONFIG_MATHEMU - { - .procname = "ieee_emulation_warnings", - .data = &sysctl_ieee_emulation_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif { .procname = "userprocess_debug", .data = &show_unhandled_signals, @@ -1268,7 +1259,7 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_do_static_key, }, #endif -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) { .procname = "panic_on_rcu_stall", .data = &sysctl_panic_on_rcu_stall, diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 1867044800bb..c8f00168afe8 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -19,3 +19,4 @@ obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o +obj-$(CONFIG_TIME_NS) += namespace.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 451f9d05ccfe..2ffb466af77e 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -26,6 +26,7 @@ #include <linux/freezer.h> #include <linux/compat.h> #include <linux/module.h> +#include <linux/time_namespace.h> #include "posix-timers.h" @@ -36,13 +37,15 @@ * struct alarm_base - Alarm timer bases * @lock: Lock for syncrhonized access to the base * @timerqueue: Timerqueue head managing the list of events - * @gettime: Function to read the time correlating to the base + * @get_ktime: Function to read the time correlating to the base + * @get_timespec: Function to read the namespace time correlating to the base * @base_clockid: clockid for the base */ static struct alarm_base { spinlock_t lock; struct timerqueue_head timerqueue; - ktime_t (*gettime)(void); + ktime_t (*get_ktime)(void); + void (*get_timespec)(struct timespec64 *tp); clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; @@ -55,8 +58,6 @@ static DEFINE_SPINLOCK(freezer_delta_lock); #endif #ifdef CONFIG_RTC_CLASS -static struct wakeup_source *ws; - /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; @@ -66,8 +67,6 @@ static DEFINE_SPINLOCK(rtcdev_lock); * alarmtimer_get_rtcdev - Return selected rtcdevice * * This function returns the rtc device to use for wakealarms. - * If one has not already been chosen, it checks to see if a - * functional rtc device is available. */ struct rtc_device *alarmtimer_get_rtcdev(void) { @@ -87,7 +86,8 @@ static int alarmtimer_rtc_add_device(struct device *dev, { unsigned long flags; struct rtc_device *rtc = to_rtc_device(dev); - struct wakeup_source *__ws; + struct platform_device *pdev; + int ret = 0; if (rtcdev) return -EBUSY; @@ -97,26 +97,31 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (!device_may_wakeup(rtc->dev.parent)) return -1; - __ws = wakeup_source_register(dev, "alarmtimer"); + pdev = platform_device_register_data(dev, "alarmtimer", + PLATFORM_DEVID_AUTO, NULL, 0); + if (!IS_ERR(pdev)) + device_init_wakeup(&pdev->dev, true); spin_lock_irqsave(&rtcdev_lock, flags); - if (!rtcdev) { + if (!IS_ERR(pdev) && !rtcdev) { if (!try_module_get(rtc->owner)) { - spin_unlock_irqrestore(&rtcdev_lock, flags); - return -1; + ret = -1; + goto unlock; } rtcdev = rtc; /* hold a reference so it doesn't go away */ get_device(dev); - ws = __ws; - __ws = NULL; + pdev = NULL; + } else { + ret = -1; } +unlock: spin_unlock_irqrestore(&rtcdev_lock, flags); - wakeup_source_unregister(__ws); + platform_device_unregister(pdev); - return 0; + return ret; } static inline void alarmtimer_rtc_timer_init(void) @@ -138,11 +143,6 @@ static void alarmtimer_rtc_interface_remove(void) class_interface_unregister(&alarmtimer_rtc_interface); } #else -struct rtc_device *alarmtimer_get_rtcdev(void) -{ - return NULL; -} -#define rtcdev (NULL) static inline int alarmtimer_rtc_interface_setup(void) { return 0; } static inline void alarmtimer_rtc_interface_remove(void) { } static inline void alarmtimer_rtc_timer_init(void) { } @@ -207,7 +207,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) spin_unlock_irqrestore(&base->lock, flags); if (alarm->function) - restart = alarm->function(alarm, base->gettime()); + restart = alarm->function(alarm, base->get_ktime()); spin_lock_irqsave(&base->lock, flags); if (restart != ALARMTIMER_NORESTART) { @@ -217,7 +217,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_fired(alarm, base->gettime()); + trace_alarmtimer_fired(alarm, base->get_ktime()); return ret; } @@ -225,7 +225,7 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) ktime_t alarm_expires_remaining(const struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; - return ktime_sub(alarm->node.expires, base->gettime()); + return ktime_sub(alarm->node.expires, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_expires_remaining); @@ -270,7 +270,7 @@ static int alarmtimer_suspend(struct device *dev) spin_unlock_irqrestore(&base->lock, flags); if (!next) continue; - delta = ktime_sub(next->expires, base->gettime()); + delta = ktime_sub(next->expires, base->get_ktime()); if (!min || (delta < min)) { expires = next->expires; min = delta; @@ -281,7 +281,7 @@ static int alarmtimer_suspend(struct device *dev) return 0; if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { - __pm_wakeup_event(ws, 2 * MSEC_PER_SEC); + pm_wakeup_event(dev, 2 * MSEC_PER_SEC); return -EBUSY; } @@ -296,7 +296,7 @@ static int alarmtimer_suspend(struct device *dev) /* Set alarm, if in the past reject suspend briefly to handle */ ret = rtc_timer_start(rtc, &rtctimer, now, 0); if (ret < 0) - __pm_wakeup_event(ws, MSEC_PER_SEC); + pm_wakeup_event(dev, MSEC_PER_SEC); return ret; } @@ -364,7 +364,7 @@ void alarm_start(struct alarm *alarm, ktime_t start) hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_start(alarm, base->gettime()); + trace_alarmtimer_start(alarm, base->get_ktime()); } EXPORT_SYMBOL_GPL(alarm_start); @@ -377,7 +377,7 @@ void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; - start = ktime_add_safe(start, base->gettime()); + start = ktime_add_safe(start, base->get_ktime()); alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); @@ -414,7 +414,7 @@ int alarm_try_to_cancel(struct alarm *alarm) alarmtimer_dequeue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); - trace_alarmtimer_cancel(alarm, base->gettime()); + trace_alarmtimer_cancel(alarm, base->get_ktime()); return ret; } EXPORT_SYMBOL_GPL(alarm_try_to_cancel); @@ -474,7 +474,7 @@ u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) { struct alarm_base *base = &alarm_bases[alarm->type]; - return alarm_forward(alarm, base->gettime(), interval); + return alarm_forward(alarm, base->get_ktime(), interval); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -500,7 +500,7 @@ static void alarmtimer_freezerset(ktime_t absexp, enum alarmtimer_type type) return; } - delta = ktime_sub(absexp, base->gettime()); + delta = ktime_sub(absexp, base->get_ktime()); spin_lock_irqsave(&freezer_delta_lock, flags); if (!freezer_delta || (delta < freezer_delta)) { @@ -632,7 +632,7 @@ static void alarm_timer_arm(struct k_itimer *timr, ktime_t expires, struct alarm_base *base = &alarm_bases[alarm->type]; if (!absolute) - expires = ktime_add_safe(expires, base->gettime()); + expires = ktime_add_safe(expires, base->get_ktime()); if (sigev_none) alarm->node.expires = expires; else @@ -657,24 +657,41 @@ static int alarm_clock_getres(const clockid_t which_clock, struct timespec64 *tp } /** - * alarm_clock_get - posix clock_get interface + * alarm_clock_get_timespec - posix clock_get_timespec interface * @which_clock: clockid * @tp: timespec to fill. * - * Provides the underlying alarm base time. + * Provides the underlying alarm base time in a tasks time namespace. */ -static int alarm_clock_get(clockid_t which_clock, struct timespec64 *tp) +static int alarm_clock_get_timespec(clockid_t which_clock, struct timespec64 *tp) { struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; if (!alarmtimer_get_rtcdev()) return -EINVAL; - *tp = ktime_to_timespec64(base->gettime()); + base->get_timespec(tp); + return 0; } /** + * alarm_clock_get_ktime - posix clock_get_ktime interface + * @which_clock: clockid + * + * Provides the underlying alarm base time in the root namespace. + */ +static ktime_t alarm_clock_get_ktime(clockid_t which_clock) +{ + struct alarm_base *base = &alarm_bases[clock2alarm(which_clock)]; + + if (!alarmtimer_get_rtcdev()) + return -EINVAL; + + return base->get_ktime(); +} + +/** * alarm_timer_create - posix timer_create interface * @new_timer: k_itimer pointer to manage * @@ -747,7 +764,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, struct timespec64 rmt; ktime_t rem; - rem = ktime_sub(absexp, alarm_bases[type].gettime()); + rem = ktime_sub(absexp, alarm_bases[type].get_ktime()); if (rem <= 0) return 0; @@ -816,9 +833,11 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, exp = timespec64_to_ktime(*tsreq); /* Convert (if necessary) to absolute time */ if (flags != TIMER_ABSTIME) { - ktime_t now = alarm_bases[type].gettime(); + ktime_t now = alarm_bases[type].get_ktime(); exp = ktime_add_safe(now, exp); + } else { + exp = timens_ktime_to_host(which_clock, exp); } ret = alarmtimer_do_nsleep(&alarm, exp, type); @@ -837,7 +856,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags, const struct k_clock alarm_clock = { .clock_getres = alarm_clock_getres, - .clock_get = alarm_clock_get, + .clock_get_ktime = alarm_clock_get_ktime, + .clock_get_timespec = alarm_clock_get_timespec, .timer_create = alarm_timer_create, .timer_set = common_timer_set, .timer_del = common_timer_del, @@ -866,6 +886,12 @@ static struct platform_driver alarmtimer_driver = { } }; +static void get_boottime_timespec(struct timespec64 *tp) +{ + ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); +} + /** * alarmtimer_init - Initialize alarm timer code * @@ -874,17 +900,18 @@ static struct platform_driver alarmtimer_driver = { */ static int __init alarmtimer_init(void) { - struct platform_device *pdev; - int error = 0; + int error; int i; alarmtimer_rtc_timer_init(); /* Initialize alarm bases */ alarm_bases[ALARM_REALTIME].base_clockid = CLOCK_REALTIME; - alarm_bases[ALARM_REALTIME].gettime = &ktime_get_real; + alarm_bases[ALARM_REALTIME].get_ktime = &ktime_get_real; + alarm_bases[ALARM_REALTIME].get_timespec = ktime_get_real_ts64, alarm_bases[ALARM_BOOTTIME].base_clockid = CLOCK_BOOTTIME; - alarm_bases[ALARM_BOOTTIME].gettime = &ktime_get_boottime; + alarm_bases[ALARM_BOOTTIME].get_ktime = &ktime_get_boottime; + alarm_bases[ALARM_BOOTTIME].get_timespec = get_boottime_timespec; for (i = 0; i < ALARM_NUMTYPE; i++) { timerqueue_init_head(&alarm_bases[i].timerqueue); spin_lock_init(&alarm_bases[i].lock); @@ -898,15 +925,7 @@ static int __init alarmtimer_init(void) if (error) goto out_if; - pdev = platform_device_register_simple("alarmtimer", -1, NULL, 0); - if (IS_ERR(pdev)) { - error = PTR_ERR(pdev); - goto out_drv; - } return 0; - -out_drv: - platform_driver_unregister(&alarmtimer_driver); out_if: alarmtimer_rtc_interface_remove(); return error; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index fff5f64981c6..428beb69426a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -293,8 +293,15 @@ static void clocksource_watchdog(struct timer_list *unused) next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); if (next_cpu >= nr_cpu_ids) next_cpu = cpumask_first(cpu_online_mask); - watchdog_timer.expires += WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, next_cpu); + + /* + * Arm timer if not already pending: could race with concurrent + * pair clocksource_stop_watchdog() clocksource_start_watchdog(). + */ + if (!timer_pending(&watchdog_timer)) { + watchdog_timer.expires += WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, next_cpu); + } out: spin_unlock(&watchdog_lock); } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 8de90ea31280..3a609e7344f3 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1477,7 +1477,7 @@ EXPORT_SYMBOL_GPL(hrtimer_active); static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, - unsigned long flags) + unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); int restart; @@ -1910,8 +1910,8 @@ static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) return ret; } -long hrtimer_nanosleep(const struct timespec64 *rqtp, - const enum hrtimer_mode mode, const clockid_t clockid) +long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, + const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; @@ -1923,7 +1923,7 @@ long hrtimer_nanosleep(const struct timespec64 *rqtp, slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); - hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); + hrtimer_set_expires_range_ns(&t.timer, rqtp, slack); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; @@ -1958,7 +1958,8 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; - return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, + CLOCK_MONOTONIC); } #endif @@ -1978,7 +1979,8 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; - return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC); + return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, + CLOCK_MONOTONIC); } #endif diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 9e59c9ea92aa..ca4e6d57d68b 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -97,20 +97,20 @@ static int do_getitimer(int which, struct itimerspec64 *value) return 0; } -static int put_itimerval(struct itimerval __user *o, +static int put_itimerval(struct __kernel_old_itimerval __user *o, const struct itimerspec64 *i) { - struct itimerval v; + struct __kernel_old_itimerval v; v.it_interval.tv_sec = i->it_interval.tv_sec; v.it_interval.tv_usec = i->it_interval.tv_nsec / NSEC_PER_USEC; v.it_value.tv_sec = i->it_value.tv_sec; v.it_value.tv_usec = i->it_value.tv_nsec / NSEC_PER_USEC; - return copy_to_user(o, &v, sizeof(struct itimerval)) ? -EFAULT : 0; + return copy_to_user(o, &v, sizeof(struct __kernel_old_itimerval)) ? -EFAULT : 0; } -SYSCALL_DEFINE2(getitimer, int, which, struct itimerval __user *, value) +SYSCALL_DEFINE2(getitimer, int, which, struct __kernel_old_itimerval __user *, value) { struct itimerspec64 get_buffer; int error = do_getitimer(which, &get_buffer); @@ -314,11 +314,11 @@ SYSCALL_DEFINE1(alarm, unsigned int, seconds) #endif -static int get_itimerval(struct itimerspec64 *o, const struct itimerval __user *i) +static int get_itimerval(struct itimerspec64 *o, const struct __kernel_old_itimerval __user *i) { - struct itimerval v; + struct __kernel_old_itimerval v; - if (copy_from_user(&v, i, sizeof(struct itimerval))) + if (copy_from_user(&v, i, sizeof(struct __kernel_old_itimerval))) return -EFAULT; /* Validate the timevals in value. */ @@ -333,8 +333,8 @@ static int get_itimerval(struct itimerspec64 *o, const struct itimerval __user * return 0; } -SYSCALL_DEFINE3(setitimer, int, which, struct itimerval __user *, value, - struct itimerval __user *, ovalue) +SYSCALL_DEFINE3(setitimer, int, which, struct __kernel_old_itimerval __user *, value, + struct __kernel_old_itimerval __user *, ovalue) { struct itimerspec64 set_buffer, get_buffer; int error; diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c new file mode 100644 index 000000000000..12858507d75a --- /dev/null +++ b/kernel/time/namespace.c @@ -0,0 +1,468 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Author: Andrei Vagin <avagin@openvz.org> + * Author: Dmitry Safonov <dima@arista.com> + */ + +#include <linux/time_namespace.h> +#include <linux/user_namespace.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/seq_file.h> +#include <linux/proc_ns.h> +#include <linux/export.h> +#include <linux/time.h> +#include <linux/slab.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/mm.h> + +#include <vdso/datapage.h> + +ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, + struct timens_offsets *ns_offsets) +{ + ktime_t offset; + + switch (clockid) { + case CLOCK_MONOTONIC: + offset = timespec64_to_ktime(ns_offsets->monotonic); + break; + case CLOCK_BOOTTIME: + case CLOCK_BOOTTIME_ALARM: + offset = timespec64_to_ktime(ns_offsets->boottime); + break; + default: + return tim; + } + + /* + * Check that @tim value is in [offset, KTIME_MAX + offset] + * and subtract offset. + */ + if (tim < offset) { + /* + * User can specify @tim *absolute* value - if it's lesser than + * the time namespace's offset - it's already expired. + */ + tim = 0; + } else { + tim = ktime_sub(tim, offset); + if (unlikely(tim > KTIME_MAX)) + tim = KTIME_MAX; + } + + return tim; +} + +static struct ucounts *inc_time_namespaces(struct user_namespace *ns) +{ + return inc_ucount(ns, current_euid(), UCOUNT_TIME_NAMESPACES); +} + +static void dec_time_namespaces(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_TIME_NAMESPACES); +} + +/** + * clone_time_ns - Clone a time namespace + * @user_ns: User namespace which owns a new namespace. + * @old_ns: Namespace to clone + * + * Clone @old_ns and set the clone refcount to 1 + * + * Return: The new namespace or ERR_PTR. + */ +static struct time_namespace *clone_time_ns(struct user_namespace *user_ns, + struct time_namespace *old_ns) +{ + struct time_namespace *ns; + struct ucounts *ucounts; + int err; + + err = -ENOSPC; + ucounts = inc_time_namespaces(user_ns); + if (!ucounts) + goto fail; + + err = -ENOMEM; + ns = kmalloc(sizeof(*ns), GFP_KERNEL); + if (!ns) + goto fail_dec; + + kref_init(&ns->kref); + + ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO); + if (!ns->vvar_page) + goto fail_free; + + err = ns_alloc_inum(&ns->ns); + if (err) + goto fail_free_page; + + ns->ucounts = ucounts; + ns->ns.ops = &timens_operations; + ns->user_ns = get_user_ns(user_ns); + ns->offsets = old_ns->offsets; + ns->frozen_offsets = false; + return ns; + +fail_free_page: + __free_page(ns->vvar_page); +fail_free: + kfree(ns); +fail_dec: + dec_time_namespaces(ucounts); +fail: + return ERR_PTR(err); +} + +/** + * copy_time_ns - Create timens_for_children from @old_ns + * @flags: Cloning flags + * @user_ns: User namespace which owns a new namespace. + * @old_ns: Namespace to clone + * + * If CLONE_NEWTIME specified in @flags, creates a new timens_for_children; + * adds a refcounter to @old_ns otherwise. + * + * Return: timens_for_children namespace or ERR_PTR. + */ +struct time_namespace *copy_time_ns(unsigned long flags, + struct user_namespace *user_ns, struct time_namespace *old_ns) +{ + if (!(flags & CLONE_NEWTIME)) + return get_time_ns(old_ns); + + return clone_time_ns(user_ns, old_ns); +} + +static struct timens_offset offset_from_ts(struct timespec64 off) +{ + struct timens_offset ret; + + ret.sec = off.tv_sec; + ret.nsec = off.tv_nsec; + + return ret; +} + +/* + * A time namespace VVAR page has the same layout as the VVAR page which + * contains the system wide VDSO data. + * + * For a normal task the VVAR pages are installed in the normal ordering: + * VVAR + * PVCLOCK + * HVCLOCK + * TIMENS <- Not really required + * + * Now for a timens task the pages are installed in the following order: + * TIMENS + * PVCLOCK + * HVCLOCK + * VVAR + * + * The check for vdso_data->clock_mode is in the unlikely path of + * the seq begin magic. So for the non-timens case most of the time + * 'seq' is even, so the branch is not taken. + * + * If 'seq' is odd, i.e. a concurrent update is in progress, the extra check + * for vdso_data->clock_mode is a non-issue. The task is spin waiting for the + * update to finish and for 'seq' to become even anyway. + * + * Timens page has vdso_data->clock_mode set to VCLOCK_TIMENS which enforces + * the time namespace handling path. + */ +static void timens_setup_vdso_data(struct vdso_data *vdata, + struct time_namespace *ns) +{ + struct timens_offset *offset = vdata->offset; + struct timens_offset monotonic = offset_from_ts(ns->offsets.monotonic); + struct timens_offset boottime = offset_from_ts(ns->offsets.boottime); + + vdata->seq = 1; + vdata->clock_mode = VCLOCK_TIMENS; + offset[CLOCK_MONOTONIC] = monotonic; + offset[CLOCK_MONOTONIC_RAW] = monotonic; + offset[CLOCK_MONOTONIC_COARSE] = monotonic; + offset[CLOCK_BOOTTIME] = boottime; + offset[CLOCK_BOOTTIME_ALARM] = boottime; +} + +/* + * Protects possibly multiple offsets writers racing each other + * and tasks entering the namespace. + */ +static DEFINE_MUTEX(offset_lock); + +static void timens_set_vvar_page(struct task_struct *task, + struct time_namespace *ns) +{ + struct vdso_data *vdata; + unsigned int i; + + if (ns == &init_time_ns) + return; + + /* Fast-path, taken by every task in namespace except the first. */ + if (likely(ns->frozen_offsets)) + return; + + mutex_lock(&offset_lock); + /* Nothing to-do: vvar_page has been already initialized. */ + if (ns->frozen_offsets) + goto out; + + ns->frozen_offsets = true; + vdata = arch_get_vdso_data(page_address(ns->vvar_page)); + + for (i = 0; i < CS_BASES; i++) + timens_setup_vdso_data(&vdata[i], ns); + +out: + mutex_unlock(&offset_lock); +} + +void free_time_ns(struct kref *kref) +{ + struct time_namespace *ns; + + ns = container_of(kref, struct time_namespace, kref); + dec_time_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + __free_page(ns->vvar_page); + kfree(ns); +} + +static struct time_namespace *to_time_ns(struct ns_common *ns) +{ + return container_of(ns, struct time_namespace, ns); +} + +static struct ns_common *timens_get(struct task_struct *task) +{ + struct time_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->time_ns; + get_time_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static struct ns_common *timens_for_children_get(struct task_struct *task) +{ + struct time_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->time_ns_for_children; + get_time_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void timens_put(struct ns_common *ns) +{ + put_time_ns(to_time_ns(ns)); +} + +static int timens_install(struct nsproxy *nsproxy, struct ns_common *new) +{ + struct time_namespace *ns = to_time_ns(new); + int err; + + if (!current_is_single_threaded()) + return -EUSERS; + + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return -EPERM; + + timens_set_vvar_page(current, ns); + + err = vdso_join_timens(current, ns); + if (err) + return err; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns); + nsproxy->time_ns = ns; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns_for_children); + nsproxy->time_ns_for_children = ns; + return 0; +} + +int timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) +{ + struct ns_common *nsc = &nsproxy->time_ns_for_children->ns; + struct time_namespace *ns = to_time_ns(nsc); + int err; + + /* create_new_namespaces() already incremented the ref counter */ + if (nsproxy->time_ns == nsproxy->time_ns_for_children) + return 0; + + timens_set_vvar_page(tsk, ns); + + err = vdso_join_timens(tsk, ns); + if (err) + return err; + + get_time_ns(ns); + put_time_ns(nsproxy->time_ns); + nsproxy->time_ns = ns; + + return 0; +} + +static struct user_namespace *timens_owner(struct ns_common *ns) +{ + return to_time_ns(ns)->user_ns; +} + +static void show_offset(struct seq_file *m, int clockid, struct timespec64 *ts) +{ + seq_printf(m, "%d %lld %ld\n", clockid, ts->tv_sec, ts->tv_nsec); +} + +void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m) +{ + struct ns_common *ns; + struct time_namespace *time_ns; + + ns = timens_for_children_get(p); + if (!ns) + return; + time_ns = to_time_ns(ns); + + show_offset(m, CLOCK_MONOTONIC, &time_ns->offsets.monotonic); + show_offset(m, CLOCK_BOOTTIME, &time_ns->offsets.boottime); + put_time_ns(time_ns); +} + +int proc_timens_set_offset(struct file *file, struct task_struct *p, + struct proc_timens_offset *offsets, int noffsets) +{ + struct ns_common *ns; + struct time_namespace *time_ns; + struct timespec64 tp; + int i, err; + + ns = timens_for_children_get(p); + if (!ns) + return -ESRCH; + time_ns = to_time_ns(ns); + + if (!file_ns_capable(file, time_ns->user_ns, CAP_SYS_TIME)) { + put_time_ns(time_ns); + return -EPERM; + } + + for (i = 0; i < noffsets; i++) { + struct proc_timens_offset *off = &offsets[i]; + + switch (off->clockid) { + case CLOCK_MONOTONIC: + ktime_get_ts64(&tp); + break; + case CLOCK_BOOTTIME: + ktime_get_boottime_ts64(&tp); + break; + default: + err = -EINVAL; + goto out; + } + + err = -ERANGE; + + if (off->val.tv_sec > KTIME_SEC_MAX || + off->val.tv_sec < -KTIME_SEC_MAX) + goto out; + + tp = timespec64_add(tp, off->val); + /* + * KTIME_SEC_MAX is divided by 2 to be sure that KTIME_MAX is + * still unreachable. + */ + if (tp.tv_sec < 0 || tp.tv_sec > KTIME_SEC_MAX / 2) + goto out; + } + + mutex_lock(&offset_lock); + if (time_ns->frozen_offsets) { + err = -EACCES; + goto out_unlock; + } + + err = 0; + /* Don't report errors after this line */ + for (i = 0; i < noffsets; i++) { + struct proc_timens_offset *off = &offsets[i]; + struct timespec64 *offset = NULL; + + switch (off->clockid) { + case CLOCK_MONOTONIC: + offset = &time_ns->offsets.monotonic; + break; + case CLOCK_BOOTTIME: + offset = &time_ns->offsets.boottime; + break; + } + + *offset = off->val; + } + +out_unlock: + mutex_unlock(&offset_lock); +out: + put_time_ns(time_ns); + + return err; +} + +const struct proc_ns_operations timens_operations = { + .name = "time", + .type = CLONE_NEWTIME, + .get = timens_get, + .put = timens_put, + .install = timens_install, + .owner = timens_owner, +}; + +const struct proc_ns_operations timens_for_children_operations = { + .name = "time_for_children", + .type = CLONE_NEWTIME, + .get = timens_for_children_get, + .put = timens_put, + .install = timens_install, + .owner = timens_owner, +}; + +struct time_namespace init_time_ns = { + .kref = KREF_INIT(3), + .user_ns = &init_user_ns, + .ns.inum = PROC_TIME_INIT_INO, + .ns.ops = &timens_operations, + .frozen_offsets = true, +}; + +static int __init time_ns_init(void) +{ + return 0; +} +subsys_initcall(time_ns_init); diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 200fb2d3be99..77c0c2370b6d 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -310,8 +310,8 @@ out: } const struct k_clock clock_posix_dynamic = { - .clock_getres = pc_clock_getres, - .clock_set = pc_clock_settime, - .clock_get = pc_clock_gettime, - .clock_adj = pc_clock_adjtime, + .clock_getres = pc_clock_getres, + .clock_set = pc_clock_settime, + .clock_get_timespec = pc_clock_gettime, + .clock_adj = pc_clock_adjtime, }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 42d512fcfda2..8ff6da77a01f 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1391,26 +1391,26 @@ static int thread_cpu_timer_create(struct k_itimer *timer) } const struct k_clock clock_posix_cpu = { - .clock_getres = posix_cpu_clock_getres, - .clock_set = posix_cpu_clock_set, - .clock_get = posix_cpu_clock_get, - .timer_create = posix_cpu_timer_create, - .nsleep = posix_cpu_nsleep, - .timer_set = posix_cpu_timer_set, - .timer_del = posix_cpu_timer_del, - .timer_get = posix_cpu_timer_get, - .timer_rearm = posix_cpu_timer_rearm, + .clock_getres = posix_cpu_clock_getres, + .clock_set = posix_cpu_clock_set, + .clock_get_timespec = posix_cpu_clock_get, + .timer_create = posix_cpu_timer_create, + .nsleep = posix_cpu_nsleep, + .timer_set = posix_cpu_timer_set, + .timer_del = posix_cpu_timer_del, + .timer_get = posix_cpu_timer_get, + .timer_rearm = posix_cpu_timer_rearm, }; const struct k_clock clock_process = { - .clock_getres = process_cpu_clock_getres, - .clock_get = process_cpu_clock_get, - .timer_create = process_cpu_timer_create, - .nsleep = process_cpu_nsleep, + .clock_getres = process_cpu_clock_getres, + .clock_get_timespec = process_cpu_clock_get, + .timer_create = process_cpu_timer_create, + .nsleep = process_cpu_nsleep, }; const struct k_clock clock_thread = { - .clock_getres = thread_cpu_clock_getres, - .clock_get = thread_cpu_clock_get, - .timer_create = thread_cpu_timer_create, + .clock_getres = thread_cpu_clock_getres, + .clock_get_timespec = thread_cpu_clock_get, + .timer_create = thread_cpu_timer_create, }; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 67df65f887ac..fcb3b21d8bdc 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -14,6 +14,7 @@ #include <linux/ktime.h> #include <linux/timekeeping.h> #include <linux/posix-timers.h> +#include <linux/time_namespace.h> #include <linux/compat.h> #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER @@ -77,9 +78,11 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) break; case CLOCK_MONOTONIC: ktime_get_ts64(tp); + timens_add_monotonic(tp); break; case CLOCK_BOOTTIME: ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); break; default: return -EINVAL; @@ -126,6 +129,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, struct __kernel_timespec __user *, rmtp) { struct timespec64 t; + ktime_t texp; switch (which_clock) { case CLOCK_REALTIME: @@ -144,13 +148,19 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, rmtp = NULL; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; - return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? + texp = timespec64_to_ktime(t); + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } #ifdef CONFIG_COMPAT COMPAT_SYS_NI(timer_create); +#endif + +#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA) COMPAT_SYS_NI(getitimer); COMPAT_SYS_NI(setitimer); #endif @@ -212,6 +222,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, struct old_timespec32 __user *, rmtp) { struct timespec64 t; + ktime_t texp; switch (which_clock) { case CLOCK_REALTIME: @@ -230,7 +241,10 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, rmtp = NULL; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; - return hrtimer_nanosleep(&t, flags & TIMER_ABSTIME ? + texp = timespec64_to_ktime(t); + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0ec5b7a1d769..ff0eb30de346 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -30,6 +30,7 @@ #include <linux/hashtable.h> #include <linux/compat.h> #include <linux/nospec.h> +#include <linux/time_namespace.h> #include "timekeeping.h" #include "posix-timers.h" @@ -165,12 +166,17 @@ static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) } /* Get clock_realtime */ -static int posix_clock_realtime_get(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_real_ts64(tp); return 0; } +static ktime_t posix_get_realtime_ktime(clockid_t which_clock) +{ + return ktime_get_real(); +} + /* Set clock_realtime */ static int posix_clock_realtime_set(const clockid_t which_clock, const struct timespec64 *tp) @@ -187,18 +193,25 @@ static int posix_clock_realtime_adj(const clockid_t which_clock, /* * Get monotonic time for posix timers */ -static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_monotonic_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_ts64(tp); + timens_add_monotonic(tp); return 0; } +static ktime_t posix_get_monotonic_ktime(clockid_t which_clock) +{ + return ktime_get(); +} + /* * Get monotonic-raw time for posix timers */ static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp) { ktime_get_raw_ts64(tp); + timens_add_monotonic(tp); return 0; } @@ -213,6 +226,7 @@ static int posix_get_monotonic_coarse(clockid_t which_clock, struct timespec64 *tp) { ktime_get_coarse_ts64(tp); + timens_add_monotonic(tp); return 0; } @@ -222,18 +236,29 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime_timespec(const clockid_t which_clock, struct timespec64 *tp) { ktime_get_boottime_ts64(tp); + timens_add_boottime(tp); return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static ktime_t posix_get_boottime_ktime(const clockid_t which_clock) +{ + return ktime_get_boottime(); +} + +static int posix_get_tai_timespec(clockid_t which_clock, struct timespec64 *tp) { ktime_get_clocktai_ts64(tp); return 0; } +static ktime_t posix_get_tai_ktime(clockid_t which_clock) +{ + return ktime_get_clocktai(); +} + static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) { tp->tv_sec = 0; @@ -645,7 +670,6 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) { const struct k_clock *kc = timr->kclock; ktime_t now, remaining, iv; - struct timespec64 ts64; bool sig_none; sig_none = timr->it_sigev_notify == SIGEV_NONE; @@ -663,12 +687,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) return; } - /* - * The timespec64 based conversion is suboptimal, but it's not - * worth to implement yet another callback. - */ - kc->clock_get(timr->it_clock, &ts64); - now = timespec64_to_ktime(ts64); + now = kc->clock_get_ktime(timr->it_clock); /* * When a requeue is pending or this is a SIGEV_NONE timer move the @@ -781,7 +800,7 @@ static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, * Posix magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they become CLOCK_MONOTONIC based under the * hood. See hrtimer_init(). Update timr->kclock, so the generic - * functions which use timr->kclock->clock_get() work. + * functions which use timr->kclock->clock_get_*() work. * * Note: it_clock stays unmodified, because the next timer_set() might * use ABSTIME, so it needs to switch back. @@ -866,6 +885,8 @@ int common_timer_set(struct k_itimer *timr, int flags, timr->it_interval = timespec64_to_ktime(new_setting->it_interval); expires = timespec64_to_ktime(new_setting->it_value); + if (flags & TIMER_ABSTIME) + expires = timens_ktime_to_host(timr->it_clock, expires); sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); @@ -1067,7 +1088,7 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, if (!kc) return -EINVAL; - error = kc->clock_get(which_clock, &kernel_tp); + error = kc->clock_get_timespec(which_clock, &kernel_tp); if (!error && put_timespec64(&kernel_tp, tp)) error = -EFAULT; @@ -1149,7 +1170,7 @@ SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, if (!kc) return -EINVAL; - err = kc->clock_get(which_clock, &ts); + err = kc->clock_get_timespec(which_clock, &ts); if (!err && put_old_timespec32(&ts, tp)) err = -EFAULT; @@ -1200,7 +1221,22 @@ SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, static int common_nsleep(const clockid_t which_clock, int flags, const struct timespec64 *rqtp) { - return hrtimer_nanosleep(rqtp, flags & TIMER_ABSTIME ? + ktime_t texp = timespec64_to_ktime(*rqtp); + + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? + HRTIMER_MODE_ABS : HRTIMER_MODE_REL, + which_clock); +} + +static int common_nsleep_timens(const clockid_t which_clock, int flags, + const struct timespec64 *rqtp) +{ + ktime_t texp = timespec64_to_ktime(*rqtp); + + if (flags & TIMER_ABSTIME) + texp = timens_ktime_to_host(which_clock, texp); + + return hrtimer_nanosleep(texp, flags & TIMER_ABSTIME ? HRTIMER_MODE_ABS : HRTIMER_MODE_REL, which_clock); } @@ -1261,7 +1297,8 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, static const struct k_clock clock_realtime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_clock_realtime_get, + .clock_get_timespec = posix_get_realtime_timespec, + .clock_get_ktime = posix_get_realtime_ktime, .clock_set = posix_clock_realtime_set, .clock_adj = posix_clock_realtime_adj, .nsleep = common_nsleep, @@ -1279,8 +1316,9 @@ static const struct k_clock clock_realtime = { static const struct k_clock clock_monotonic = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_ktime_get_ts, - .nsleep = common_nsleep, + .clock_get_timespec = posix_get_monotonic_timespec, + .clock_get_ktime = posix_get_monotonic_ktime, + .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, @@ -1295,22 +1333,23 @@ static const struct k_clock clock_monotonic = { static const struct k_clock clock_monotonic_raw = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_raw, + .clock_get_timespec = posix_get_monotonic_raw, }; static const struct k_clock clock_realtime_coarse = { .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_realtime_coarse, + .clock_get_timespec = posix_get_realtime_coarse, }; static const struct k_clock clock_monotonic_coarse = { .clock_getres = posix_get_coarse_res, - .clock_get = posix_get_monotonic_coarse, + .clock_get_timespec = posix_get_monotonic_coarse, }; static const struct k_clock clock_tai = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_tai, + .clock_get_ktime = posix_get_tai_ktime, + .clock_get_timespec = posix_get_tai_timespec, .nsleep = common_nsleep, .timer_create = common_timer_create, .timer_set = common_timer_set, @@ -1326,8 +1365,9 @@ static const struct k_clock clock_tai = { static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_boottime, - .nsleep = common_nsleep, + .clock_get_ktime = posix_get_boottime_ktime, + .clock_get_timespec = posix_get_boottime_timespec, + .nsleep = common_nsleep_timens, .timer_create = common_timer_create, .timer_set = common_timer_set, .timer_get = common_timer_get, diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 897c29e162b9..f32a2ebba9b8 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -6,8 +6,11 @@ struct k_clock { struct timespec64 *tp); int (*clock_set)(const clockid_t which_clock, const struct timespec64 *tp); - int (*clock_get)(const clockid_t which_clock, - struct timespec64 *tp); + /* Returns the clock value in the current time namespace. */ + int (*clock_get_timespec)(const clockid_t which_clock, + struct timespec64 *tp); + /* Returns the clock value in the root time namespace. */ + ktime_t (*clock_get_ktime)(const clockid_t which_clock); int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx); int (*timer_create)(struct k_itimer *timer); int (*nsleep)(const clockid_t which_clock, int flags, diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index dbd69052eaa6..e4332e3e2d56 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -169,14 +169,15 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) { u64 res, wrap, new_mask, new_epoch, cyc, ns; u32 new_mult, new_shift; - unsigned long r; + unsigned long r, flags; char r_unit; struct clock_read_data rd; if (cd.rate > rate) return; - WARN_ON(!irqs_disabled()); + /* Cannot register a sched_clock with interrupts on */ + local_irq_save(flags); /* Calculate the mult/shift to convert counter ticks to ns. */ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600); @@ -233,6 +234,8 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate) if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) enable_sched_clock_irqtime(); + local_irq_restore(flags); + pr_debug("Registered %pS as sched_clock source\n", read); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 59225b484e4e..7e5d3524e924 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/hrtimer.h> #include <linux/interrupt.h> +#include <linux/nmi.h> #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> @@ -558,6 +559,7 @@ void tick_unfreeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); } else { + touch_softlockup_watchdog(); tick_resume_local(); } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 8b192e67aabc..a792d21cac64 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -58,8 +58,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* * Do a quick check without holding jiffies_lock: + * The READ_ONCE() pairs with two updates done later in this function. */ - delta = ktime_sub(now, last_jiffies_update); + delta = ktime_sub(now, READ_ONCE(last_jiffies_update)); if (delta < tick_period) return; @@ -70,8 +71,9 @@ static void tick_do_update_jiffies64(ktime_t now) if (delta >= tick_period) { delta = ktime_sub(delta, tick_period); - last_jiffies_update = ktime_add(last_jiffies_update, - tick_period); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add(last_jiffies_update, tick_period)); /* Slow path for long timeouts */ if (unlikely(delta >= tick_period)) { @@ -79,8 +81,10 @@ static void tick_do_update_jiffies64(ktime_t now) ticks = ktime_divns(delta, incr); - last_jiffies_update = ktime_add_ns(last_jiffies_update, - incr * ticks); + /* Pairs with the lockless read in this function. */ + WRITE_ONCE(last_jiffies_update, + ktime_add_ns(last_jiffies_update, + incr * ticks)); } do_timer(++ticks); diff --git a/kernel/time/time.c b/kernel/time/time.c index 704ccd9451b0..3985b2b32d08 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -449,49 +449,6 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0, } EXPORT_SYMBOL(mktime64); -/** - * ns_to_timespec - Convert nanoseconds to timespec - * @nsec: the nanoseconds value to be converted - * - * Returns the timespec representation of the nsec parameter. - */ -struct timespec ns_to_timespec(const s64 nsec) -{ - struct timespec ts; - s32 rem; - - if (!nsec) - return (struct timespec) {0, 0}; - - ts.tv_sec = div_s64_rem(nsec, NSEC_PER_SEC, &rem); - if (unlikely(rem < 0)) { - ts.tv_sec--; - rem += NSEC_PER_SEC; - } - ts.tv_nsec = rem; - - return ts; -} -EXPORT_SYMBOL(ns_to_timespec); - -/** - * ns_to_timeval - Convert nanoseconds to timeval - * @nsec: the nanoseconds value to be converted - * - * Returns the timeval representation of the nsec parameter. - */ -struct timeval ns_to_timeval(const s64 nsec) -{ - struct timespec ts = ns_to_timespec(nsec); - struct timeval tv; - - tv.tv_sec = ts.tv_sec; - tv.tv_usec = (suseconds_t) ts.tv_nsec / 1000; - - return tv; -} -EXPORT_SYMBOL(ns_to_timeval); - struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec) { struct timespec64 ts = ns_to_timespec64(nsec); @@ -626,10 +583,12 @@ EXPORT_SYMBOL(__usecs_to_jiffies); * The >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC) converts the scaled nsec * value to a scaled second value. */ -static unsigned long -__timespec64_to_jiffies(u64 sec, long nsec) + +unsigned long +timespec64_to_jiffies(const struct timespec64 *value) { - nsec = nsec + TICK_NSEC - 1; + u64 sec = value->tv_sec; + long nsec = value->tv_nsec + TICK_NSEC - 1; if (sec >= MAX_SEC_IN_JIFFIES){ sec = MAX_SEC_IN_JIFFIES; @@ -640,18 +599,6 @@ __timespec64_to_jiffies(u64 sec, long nsec) (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } - -static unsigned long -__timespec_to_jiffies(unsigned long sec, long nsec) -{ - return __timespec64_to_jiffies((u64)sec, nsec); -} - -unsigned long -timespec64_to_jiffies(const struct timespec64 *value) -{ - return __timespec64_to_jiffies(value->tv_sec, value->tv_nsec); -} EXPORT_SYMBOL(timespec64_to_jiffies); void @@ -669,44 +616,6 @@ jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) EXPORT_SYMBOL(jiffies_to_timespec64); /* - * We could use a similar algorithm to timespec_to_jiffies (with a - * different multiplier for usec instead of nsec). But this has a - * problem with rounding: we can't exactly add TICK_NSEC - 1 to the - * usec value, since it's not necessarily integral. - * - * We could instead round in the intermediate scaled representation - * (i.e. in units of 1/2^(large scale) jiffies) but that's also - * perilous: the scaling introduces a small positive error, which - * combined with a division-rounding-upward (i.e. adding 2^(scale) - 1 - * units to the intermediate before shifting) leads to accidental - * overflow and overestimates. - * - * At the cost of one additional multiplication by a constant, just - * use the timespec implementation. - */ -unsigned long -timeval_to_jiffies(const struct timeval *value) -{ - return __timespec_to_jiffies(value->tv_sec, - value->tv_usec * NSEC_PER_USEC); -} -EXPORT_SYMBOL(timeval_to_jiffies); - -void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value) -{ - /* - * Convert jiffies to nanoseconds and separate with - * one divide. - */ - u32 rem; - - value->tv_sec = div_u64_rem((u64)jiffies * TICK_NSEC, - NSEC_PER_SEC, &rem); - value->tv_usec = rem / NSEC_PER_USEC; -} -EXPORT_SYMBOL(jiffies_to_timeval); - -/* * Convert jiffies/jiffies_64 to clock_t and back. */ clock_t jiffies_to_clock_t(unsigned long x) diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 5ee0f7709410..9577c89179cd 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -28,11 +28,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdata[CS_RAW].mult = tk->tkr_raw.mult; vdata[CS_RAW].shift = tk->tkr_raw.shift; - /* CLOCK_REALTIME */ - vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; - vdso_ts->sec = tk->xtime_sec; - vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - /* CLOCK_MONOTONIC */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; @@ -70,12 +65,6 @@ static inline void update_vdso_data(struct vdso_data *vdata, vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; - - /* - * Read without the seqlock held by clock_getres(). - * Note: No need to have a second copy. - */ - WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); } void update_vsyscall(struct timekeeper *tk) @@ -84,20 +73,17 @@ void update_vsyscall(struct timekeeper *tk) struct vdso_timestamp *vdso_ts; u64 nsec; - if (__arch_update_vdso_data()) { - /* - * Some architectures might want to skip the update of the - * data page. - */ - return; - } - /* copy vsyscall data */ vdso_write_begin(vdata); vdata[CS_HRES_COARSE].clock_mode = __arch_get_clock_mode(tk); vdata[CS_RAW].clock_mode = __arch_get_clock_mode(tk); + /* CLOCK_REALTIME also required for time() */ + vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; + vdso_ts->sec = tk->xtime_sec; + vdso_ts->nsec = tk->tkr_mono.xtime_nsec; + /* CLOCK_REALTIME_COARSE */ vdso_ts = &vdata[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; @@ -110,7 +96,18 @@ void update_vsyscall(struct timekeeper *tk) nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); - update_vdso_data(vdata, tk); + /* + * Read without the seqlock held by clock_getres(). + * Note: No need to have a second copy. + */ + WRITE_ONCE(vdata[CS_HRES_COARSE].hrtimer_res, hrtimer_resolution); + + /* + * Architectures can opt out of updating the high resolution part + * of the VDSO. + */ + if (__arch_update_vdso_data()) + update_vdso_data(vdata, tk); __arch_update_vsyscall(vdata, tk); diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 0735ae8545d8..ca39dc3230cb 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -335,6 +335,7 @@ static void put_probe_ref(void) static void blk_trace_cleanup(struct blk_trace *bt) { + synchronize_rcu(); blk_trace_free(bt); put_probe_ref(); } @@ -629,8 +630,10 @@ static int compat_blk_trace_setup(struct request_queue *q, char *name, static int __blk_trace_startstop(struct request_queue *q, int start) { int ret; - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (bt == NULL) return -EINVAL; @@ -740,8 +743,8 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) void blk_trace_shutdown(struct request_queue *q) { mutex_lock(&q->blk_trace_mutex); - - if (q->blk_trace) { + if (rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex))) { __blk_trace_startstop(q, 0); __blk_trace_remove(q); } @@ -752,8 +755,10 @@ void blk_trace_shutdown(struct request_queue *q) #ifdef CONFIG_BLK_CGROUP static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + /* We don't use the 'bt' value here except as an optimization... */ + bt = rcu_dereference_protected(q->blk_trace, 1); if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return 0; @@ -796,10 +801,14 @@ blk_trace_request_get_cgid(struct request_queue *q, struct request *rq) static void blk_add_trace_rq(struct request *rq, int error, unsigned int nr_bytes, u32 what, u64 cgid) { - struct blk_trace *bt = rq->q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(rq->q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } if (blk_rq_is_passthrough(rq)) what |= BLK_TC_ACT(BLK_TC_PC); @@ -808,6 +817,7 @@ static void blk_add_trace_rq(struct request *rq, int error, __blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq), rq->cmd_flags, what, error, 0, NULL, cgid); + rcu_read_unlock(); } static void blk_add_trace_rq_insert(void *ignore, @@ -853,14 +863,19 @@ static void blk_add_trace_rq_complete(void *ignore, struct request *rq, static void blk_add_trace_bio(struct request_queue *q, struct bio *bio, u32 what, int error) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, what, error, 0, NULL, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } static void blk_add_trace_bio_bounce(void *ignore, @@ -905,11 +920,14 @@ static void blk_add_trace_getrq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } @@ -921,27 +939,35 @@ static void blk_add_trace_sleeprq(void *ignore, if (bio) blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0); else { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ, 0, 0, NULL, 0); + rcu_read_unlock(); } } static void blk_add_trace_plug(void *ignore, struct request_queue *q) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) __blk_add_trace(bt, 0, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL, 0); + rcu_read_unlock(); } static void blk_add_trace_unplug(void *ignore, struct request_queue *q, unsigned int depth, bool explicit) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(depth); u32 what; @@ -953,14 +979,17 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q, __blk_add_trace(bt, 0, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu, 0); } + rcu_read_unlock(); } static void blk_add_trace_split(void *ignore, struct request_queue *q, struct bio *bio, unsigned int pdu) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); if (bt) { __be64 rpdu = cpu_to_be64(pdu); @@ -969,6 +998,7 @@ static void blk_add_trace_split(void *ignore, BLK_TA_SPLIT, bio->bi_status, sizeof(rpdu), &rpdu, blk_trace_bio_get_cgid(q, bio)); } + rcu_read_unlock(); } /** @@ -988,11 +1018,15 @@ static void blk_add_trace_bio_remap(void *ignore, struct request_queue *q, struct bio *bio, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(bio_dev(bio)); @@ -1001,6 +1035,7 @@ static void blk_add_trace_bio_remap(void *ignore, __blk_add_trace(bt, bio->bi_iter.bi_sector, bio->bi_iter.bi_size, bio_op(bio), bio->bi_opf, BLK_TA_REMAP, bio->bi_status, sizeof(r), &r, blk_trace_bio_get_cgid(q, bio)); + rcu_read_unlock(); } /** @@ -1021,11 +1056,15 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, sector_t from) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; struct blk_io_trace_remap r; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } r.device_from = cpu_to_be32(dev); r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); @@ -1034,6 +1073,7 @@ static void blk_add_trace_rq_remap(void *ignore, __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), rq_data_dir(rq), 0, BLK_TA_REMAP, 0, sizeof(r), &r, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } /** @@ -1051,14 +1091,19 @@ void blk_add_driver_data(struct request_queue *q, struct request *rq, void *data, size_t len) { - struct blk_trace *bt = q->blk_trace; + struct blk_trace *bt; - if (likely(!bt)) + rcu_read_lock(); + bt = rcu_dereference(q->blk_trace); + if (likely(!bt)) { + rcu_read_unlock(); return; + } __blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0, BLK_TA_DRV_DATA, 0, len, data, blk_trace_request_get_cgid(q, rq)); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(blk_add_driver_data); @@ -1597,6 +1642,7 @@ static int blk_trace_remove_queue(struct request_queue *q) return -EINVAL; put_probe_ref(); + synchronize_rcu(); blk_trace_free(bt); return 0; } @@ -1758,6 +1804,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, struct hd_struct *p = dev_to_part(dev); struct request_queue *q; struct block_device *bdev; + struct blk_trace *bt; ssize_t ret = -ENXIO; bdev = bdget(part_devt(p)); @@ -1770,21 +1817,23 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - ret = sprintf(buf, "%u\n", !!q->blk_trace); + ret = sprintf(buf, "%u\n", !!bt); goto out_unlock_bdev; } - if (q->blk_trace == NULL) + if (bt == NULL) ret = sprintf(buf, "disabled\n"); else if (attr == &dev_attr_act_mask) - ret = blk_trace_mask2str(buf, q->blk_trace->act_mask); + ret = blk_trace_mask2str(buf, bt->act_mask); else if (attr == &dev_attr_pid) - ret = sprintf(buf, "%u\n", q->blk_trace->pid); + ret = sprintf(buf, "%u\n", bt->pid); else if (attr == &dev_attr_start_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->start_lba); + ret = sprintf(buf, "%llu\n", bt->start_lba); else if (attr == &dev_attr_end_lba) - ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); + ret = sprintf(buf, "%llu\n", bt->end_lba); out_unlock_bdev: mutex_unlock(&q->blk_trace_mutex); @@ -1801,6 +1850,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, struct block_device *bdev; struct request_queue *q; struct hd_struct *p; + struct blk_trace *bt; u64 value; ssize_t ret = -EINVAL; @@ -1831,8 +1881,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, mutex_lock(&q->blk_trace_mutex); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); if (attr == &dev_attr_enable) { - if (!!value == !!q->blk_trace) { + if (!!value == !!bt) { ret = 0; goto out_unlock_bdev; } @@ -1844,18 +1896,21 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } ret = 0; - if (q->blk_trace == NULL) + if (bt == NULL) { ret = blk_trace_setup_queue(q, bdev); + bt = rcu_dereference_protected(q->blk_trace, + lockdep_is_held(&q->blk_trace_mutex)); + } if (ret == 0) { if (attr == &dev_attr_act_mask) - q->blk_trace->act_mask = value; + bt->act_mask = value; else if (attr == &dev_attr_pid) - q->blk_trace->pid = value; + bt->pid = value; else if (attr == &dev_attr_start_lba) - q->blk_trace->start_lba = value; + bt->start_lba = value; else if (attr == &dev_attr_end_lba) - q->blk_trace->end_lba = value; + bt->end_lba = value; } out_unlock_bdev: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index e5ef4ae9edb5..19e793aa441a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -703,6 +703,7 @@ struct send_signal_irq_work { struct irq_work irq_work; struct task_struct *task; u32 sig; + enum pid_type type; }; static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); @@ -712,10 +713,10 @@ static void do_bpf_send_signal(struct irq_work *entry) struct send_signal_irq_work *work; work = container_of(entry, struct send_signal_irq_work, irq_work); - group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID); + group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); } -BPF_CALL_1(bpf_send_signal, u32, sig) +static int bpf_send_signal_common(u32 sig, enum pid_type type) { struct send_signal_irq_work *work = NULL; @@ -748,11 +749,17 @@ BPF_CALL_1(bpf_send_signal, u32, sig) */ work->task = current; work->sig = sig; + work->type = type; irq_work_queue(&work->irq_work); return 0; } - return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID); + return group_send_sig_info(sig, SEND_SIG_PRIV, current, type); +} + +BPF_CALL_1(bpf_send_signal, u32, sig) +{ + return bpf_send_signal_common(sig, PIDTYPE_TGID); } static const struct bpf_func_proto bpf_send_signal_proto = { @@ -762,6 +769,18 @@ static const struct bpf_func_proto bpf_send_signal_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_1(bpf_send_signal_thread, u32, sig) +{ + return bpf_send_signal_common(sig, PIDTYPE_PID); +} + +static const struct bpf_func_proto bpf_send_signal_thread_proto = { + .func = bpf_send_signal_thread, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -822,6 +841,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; + case BPF_FUNC_send_signal_thread: + return &bpf_send_signal_thread_proto; default: return NULL; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a89c562ffb8f..6b11e4e2150c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8570,7 +8570,7 @@ static struct trace_array *trace_array_create(const char *name) ret = event_trace_add_tracer(tr->dir, tr); if (ret) { - tracefs_remove_recursive(tr->dir); + tracefs_remove(tr->dir); goto out_free_tr; } @@ -8681,7 +8681,7 @@ static int __remove_instance(struct trace_array *tr) event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); - tracefs_remove_recursive(tr->dir); + tracefs_remove(tr->dir); free_trace_buffers(tr); for (i = 0; i < tr->nr_topts; i++) { @@ -9485,6 +9485,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3c75d29bd861..99372dd7d168 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -52,6 +52,9 @@ enum trace_type { #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_struct #define __field_struct(type, item) __field(type, item) @@ -71,26 +74,22 @@ enum trace_type { #define F_STRUCT(args...) args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct struct_name { \ struct trace_entry ent; \ tstruct \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter) +#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print, \ - filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) __packed +#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed #include "trace_entries.h" @@ -1964,17 +1963,15 @@ extern void tracing_log_err(struct trace_array *tr, #define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str)) #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct trace_event_call \ __aligned(4) event_##call; #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #undef FTRACE_ENTRY_PACKED -#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index 78c146efb862..f22746f3c132 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -61,15 +61,13 @@ FTRACE_ENTRY_REG(function, ftrace_entry, TRACE_FN, F_STRUCT( - __field( unsigned long, ip ) - __field( unsigned long, parent_ip ) + __field_fn( unsigned long, ip ) + __field_fn( unsigned long, parent_ip ) ), F_printk(" %ps <-- %ps", (void *)__entry->ip, (void *)__entry->parent_ip), - FILTER_TRACE_FN, - perf_ftrace_event_register ); @@ -84,9 +82,7 @@ FTRACE_ENTRY_PACKED(funcgraph_entry, ftrace_graph_ent_entry, __field_desc( int, graph_ent, depth ) ), - F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth), - - FILTER_OTHER + F_printk("--> %ps (%d)", (void *)__entry->func, __entry->depth) ); /* Function return entry */ @@ -97,18 +93,16 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry, F_STRUCT( __field_struct( struct ftrace_graph_ret, ret ) __field_desc( unsigned long, ret, func ) + __field_desc( unsigned long, ret, overrun ) __field_desc( unsigned long long, ret, calltime) __field_desc( unsigned long long, ret, rettime ) - __field_desc( unsigned long, ret, overrun ) __field_desc( int, ret, depth ) ), F_printk("<-- %ps (%d) (start: %llx end: %llx) over: %d", (void *)__entry->func, __entry->depth, __entry->calltime, __entry->rettime, - __entry->depth), - - FILTER_OTHER + __entry->depth) ); /* @@ -137,9 +131,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry, F_printk("%u:%u:%u ==> %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -157,9 +149,7 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry, F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]", __entry->prev_pid, __entry->prev_prio, __entry->prev_state, __entry->next_pid, __entry->next_prio, __entry->next_state, - __entry->next_cpu), - - FILTER_OTHER + __entry->next_cpu) ); /* @@ -183,9 +173,7 @@ FTRACE_ENTRY(kernel_stack, stack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); FTRACE_ENTRY(user_stack, userstack_entry, @@ -203,9 +191,7 @@ FTRACE_ENTRY(user_stack, userstack_entry, (void *)__entry->caller[0], (void *)__entry->caller[1], (void *)__entry->caller[2], (void *)__entry->caller[3], (void *)__entry->caller[4], (void *)__entry->caller[5], - (void *)__entry->caller[6], (void *)__entry->caller[7]), - - FILTER_OTHER + (void *)__entry->caller[6], (void *)__entry->caller[7]) ); /* @@ -222,9 +208,7 @@ FTRACE_ENTRY(bprint, bprint_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->fmt), - - FILTER_OTHER + (void *)__entry->ip, __entry->fmt) ); FTRACE_ENTRY_REG(print, print_entry, @@ -239,8 +223,6 @@ FTRACE_ENTRY_REG(print, print_entry, F_printk("%ps: %s", (void *)__entry->ip, __entry->buf), - FILTER_OTHER, - ftrace_event_register ); @@ -254,9 +236,7 @@ FTRACE_ENTRY(raw_data, raw_data_entry, ), F_printk("id:%04x %08x", - __entry->id, (int)__entry->buf[0]), - - FILTER_OTHER + __entry->id, (int)__entry->buf[0]) ); FTRACE_ENTRY(bputs, bputs_entry, @@ -269,9 +249,7 @@ FTRACE_ENTRY(bputs, bputs_entry, ), F_printk("%ps: %s", - (void *)__entry->ip, __entry->str), - - FILTER_OTHER + (void *)__entry->ip, __entry->str) ); FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, @@ -283,16 +261,14 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw, __field_desc( resource_size_t, rw, phys ) __field_desc( unsigned long, rw, value ) __field_desc( unsigned long, rw, pc ) - __field_desc( int, rw, map_id ) + __field_desc( int, rw, map_id ) __field_desc( unsigned char, rw, opcode ) __field_desc( unsigned char, rw, width ) ), F_printk("%lx %lx %lx %d %x %x", (unsigned long)__entry->phys, __entry->value, __entry->pc, - __entry->map_id, __entry->opcode, __entry->width), - - FILTER_OTHER + __entry->map_id, __entry->opcode, __entry->width) ); FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, @@ -304,15 +280,13 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map, __field_desc( resource_size_t, map, phys ) __field_desc( unsigned long, map, virt ) __field_desc( unsigned long, map, len ) - __field_desc( int, map, map_id ) + __field_desc( int, map, map_id ) __field_desc( unsigned char, map, opcode ) ), F_printk("%lx %lx %lx %d %x", (unsigned long)__entry->phys, __entry->virt, __entry->len, - __entry->map_id, __entry->opcode), - - FILTER_OTHER + __entry->map_id, __entry->opcode) ); @@ -334,9 +308,7 @@ FTRACE_ENTRY(branch, trace_branch, F_printk("%u:%s:%s (%u)%s", __entry->line, __entry->func, __entry->file, __entry->correct, - __entry->constant ? " CONSTANT" : ""), - - FILTER_OTHER + __entry->constant ? " CONSTANT" : "") ); @@ -362,7 +334,5 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __entry->duration, __entry->outer_duration, __entry->nmi_total_ts, - __entry->nmi_count), - - FILTER_OTHER + __entry->nmi_count) ); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index da62472b1297..f38234ecea18 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -24,6 +24,7 @@ #include <linux/delay.h> #include <trace/events/sched.h> +#include <trace/syscall.h> #include <asm/setup.h> @@ -698,7 +699,7 @@ static void remove_subsystem(struct trace_subsystem_dir *dir) return; if (!--dir->nr_events) { - tracefs_remove_recursive(dir->entry); + tracefs_remove(dir->entry); list_del(&dir->list); __put_system_dir(dir); } @@ -717,7 +718,7 @@ static void remove_event_file_dir(struct trace_event_file *file) } spin_unlock(&dir->d_lock); - tracefs_remove_recursive(dir); + tracefs_remove(dir); } list_del(&file->list); @@ -2018,7 +2019,24 @@ event_create_dir(struct dentry *parent, struct trace_event_file *file) */ head = trace_get_fields(call); if (list_empty(head)) { - ret = call->class->define_fields(call); + struct trace_event_fields *field = call->class->fields_array; + unsigned int offset = sizeof(struct trace_entry); + + for (; field->type; field++) { + if (field->type == TRACE_FUNCTION_TYPE) { + ret = field->define_fields(call); + break; + } + + offset = ALIGN(offset, field->align); + ret = trace_define_field(call, field->type, field->name, + offset, field->size, + field->is_signed, field->filter_type); + if (ret) + break; + + offset += field->size; + } if (ret < 0) { pr_warn("Could not initialize trace point events/%s\n", name); @@ -3150,7 +3168,7 @@ int event_trace_del_tracer(struct trace_array *tr) down_write(&trace_event_sem); __trace_remove_event_dirs(tr); - tracefs_remove_recursive(tr->event_dir); + tracefs_remove(tr->event_dir); up_write(&trace_event_sem); tr->event_dir = NULL; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9d87aa1f0b79..5f6834a2bf41 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -121,6 +121,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1192,6 +1193,12 @@ static struct synth_event *find_synth_event(const char *name) return NULL; } +static struct trace_event_fields synth_event_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = synth_event_define_fields }, + {} +}; + static int register_synth_event(struct synth_event *event) { struct trace_event_call *call = &event->call; @@ -1213,7 +1220,7 @@ static int register_synth_event(struct synth_event *event) INIT_LIST_HEAD(&call->class->fields); call->event.funcs = &synth_event_funcs; - call->class->define_fields = synth_event_define_fields; + call->class->fields_array = synth_event_fields_array; ret = register_trace_event(&call->event); if (!ret) { @@ -3299,8 +3306,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -3342,6 +3357,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -3553,6 +3570,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 2e6d2e9741cc..77ce5a3b6773 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -29,10 +29,8 @@ static int ftrace_event_register(struct trace_event_call *call, * function and thus become accesible via perf. */ #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \ - filter, regfn) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) /* not needed for this file */ #undef __field_struct @@ -41,6 +39,9 @@ static int ftrace_event_register(struct trace_event_call *call, #undef __field #define __field(type, item) type item; +#undef __field_fn +#define __field_fn(type, item) type item; + #undef __field_desc #define __field_desc(type, container, item) type item; @@ -60,7 +61,7 @@ static int ftrace_event_register(struct trace_event_call *call, #define F_printk(fmt, args...) fmt, args #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ struct ____ftrace_##name { \ tstruct \ }; \ @@ -73,76 +74,46 @@ static void __always_unused ____ftrace_check_##name(void) \ } #undef FTRACE_ENTRY_DUP -#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \ - FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \ - filter) +#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \ + FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) #include "trace_entries.h" +#undef __field_ext +#define __field_ext(_type, _item, _filter_type) { \ + .type = #_type, .name = #_item, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = _filter_type }, + #undef __field -#define __field(type, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field(_type, _item) __field_ext(_type, _item, FILTER_OTHER) + +#undef __field_fn +#define __field_fn(_type, _item) __field_ext(_type, _item, FILTER_TRACE_FN) #undef __field_desc -#define __field_desc(type, container, item) \ - ret = trace_define_field(event_call, #type, #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __field_desc(_type, _container, _item) __field_ext(_type, _item, FILTER_OTHER) #undef __array -#define __array(type, item, len) \ - do { \ - char *type_str = #type"["__stringify(len)"]"; \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, type_str, #item, \ - offsetof(typeof(field), item), \ - sizeof(field.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; \ - } while (0); +#define __array(_type, _item, _len) { \ + .type = #_type"["__stringify(_len)"]", .name = #_item, \ + .size = sizeof(_type[_len]), .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef __array_desc -#define __array_desc(type, container, item, len) \ - BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \ - ret = trace_define_field(event_call, #type "[" #len "]", #item, \ - offsetof(typeof(field), \ - container.item), \ - sizeof(field.container.item), \ - is_signed_type(type), filter_type); \ - if (ret) \ - return ret; +#define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) #undef __dynamic_array -#define __dynamic_array(type, item) \ - ret = trace_define_field(event_call, #type "[]", #item, \ - offsetof(typeof(field), item), \ - 0, is_signed_type(type), filter_type);\ - if (ret) \ - return ret; +#define __dynamic_array(_type, _item) { \ + .type = #_type "[]", .name = #_item, \ + .size = 0, .align = __alignof__(_type), \ + is_signed_type(_type), .filter_type = FILTER_OTHER }, #undef FTRACE_ENTRY -#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \ -static int __init \ -ftrace_define_fields_##name(struct trace_event_call *event_call) \ -{ \ - struct struct_name field; \ - int ret; \ - int filter_type = filter; \ - \ - tstruct; \ - \ - return ret; \ -} +#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \ +static struct trace_event_fields ftrace_event_fields_##name[] = { \ + tstruct \ + {} }; #include "trace_entries.h" @@ -152,6 +123,9 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #undef __field #define __field(type, item) +#undef __field_fn +#define __field_fn(type, item) + #undef __field_desc #define __field_desc(type, container, item) @@ -168,12 +142,10 @@ ftrace_define_fields_##name(struct trace_event_call *event_call) \ #define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args) #undef FTRACE_ENTRY_REG -#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\ - regfn) \ - \ +#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, regfn) \ static struct trace_event_class __refdata event_class_ftrace_##call = { \ .system = __stringify(TRACE_SYSTEM), \ - .define_fields = ftrace_define_fields_##call, \ + .fields_array = ftrace_event_fields_##call, \ .fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\ .reg = regfn, \ }; \ @@ -191,9 +163,9 @@ static struct trace_event_call __used \ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call; #undef FTRACE_ENTRY -#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \ +#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \ FTRACE_ENTRY_REG(call, struct_name, etype, \ - PARAMS(tstruct), PARAMS(print), filter, NULL) + PARAMS(tstruct), PARAMS(print), NULL) bool ftrace_event_is_function(struct trace_event_call *call) { diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index b44446bf0872..a48808c43249 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -556,7 +556,7 @@ static int init_tracefs(void) return 0; err: - tracefs_remove_recursive(top_dir); + tracefs_remove(top_dir); return -ENOMEM; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 21bafd48f2ac..362cca52f5de 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -289,7 +289,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, false); if (ret < 0) goto error; @@ -1714,16 +1714,28 @@ static struct trace_event_functions kprobe_funcs = { .trace = print_kprobe_event }; +static struct trace_event_fields kretprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kretprobe_event_define_fields }, + {} +}; + +static struct trace_event_fields kprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = kprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_kprobe *tk) { struct trace_event_call *call = trace_probe_event_call(&tk->tp); if (trace_kprobe_is_return(tk)) { call->event.funcs = &kretprobe_funcs; - call->class->define_fields = kretprobe_event_define_fields; + call->class->fields_array = kretprobe_fields_array; } else { call->event.funcs = &kprobe_funcs; - call->class->define_fields = kprobe_event_define_fields; + call->class->fields_array = kprobe_fields_array; } call->flags = TRACE_EVENT_FL_KPROBE; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 905b10af5d5c..ab8b6436d53f 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -876,7 +876,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, for (i = 0; i < tp->nr_args; i++) { parg = tp->args + i; if (parg->count) { - if (strcmp(parg->type->name, "string") == 0) + if ((strcmp(parg->type->name, "string") == 0) || + (strcmp(parg->type->name, "ustring") == 0)) fmt = ", __get_str(%s[%d])"; else fmt = ", REC->%s[%d]"; @@ -884,7 +885,8 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, pos += snprintf(buf + pos, LEN_OR_ZERO, fmt, parg->name, j); } else { - if (strcmp(parg->type->name, "string") == 0) + if ((strcmp(parg->type->name, "string") == 0) || + (strcmp(parg->type->name, "ustring") == 0)) fmt = ", __get_str(%s)"; else fmt = ", REC->%s"; @@ -984,15 +986,19 @@ void trace_probe_cleanup(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, bool alloc_filter) { struct trace_event_call *call; + size_t size = sizeof(struct trace_probe_event); int ret = 0; if (!event || !group) return -EINVAL; - tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL); + if (alloc_filter) + size += sizeof(struct trace_uprobe_filter); + + tp->event = kzalloc(size, GFP_KERNEL); if (!tp->event) return -ENOMEM; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4ee703728aec..a0ff9e200ef6 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -223,6 +223,12 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* Event call and class holder */ struct trace_probe_event { unsigned int flags; /* For TP_FLAG_* */ @@ -230,6 +236,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + struct trace_uprobe_filter filter[0]; }; struct trace_probe { @@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, bool alloc_filter); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 837ad4818bb4..d85a2f0f316b 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -203,11 +203,10 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, field, name) \ - sizeof(type) != sizeof(trace.field) ? \ - __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), field), \ - sizeof(trace.field), is_signed_type(type) +#define SYSCALL_FIELD(_type, _name) { \ + .type = #_type, .name = #_name, \ + .size = sizeof(_type), .align = __alignof__(_type), \ + .is_signed = is_signed_type(_type), .filter_type = FILTER_OTHER } static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -274,42 +273,23 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) { struct syscall_trace_enter trace; struct syscall_metadata *meta = call->data; - int ret; - int i; int offset = offsetof(typeof(trace), args); - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; + int ret = 0; + int i; for (i = 0; i < meta->nb_args; i++) { ret = trace_define_field(call, meta->types[i], meta->args[i], offset, sizeof(unsigned long), 0, FILTER_OTHER); + if (ret) + break; offset += sizeof(unsigned long); } return ret; } -static int __init syscall_exit_define_fields(struct trace_event_call *call) -{ - struct syscall_trace_exit trace; - int ret; - - ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), - FILTER_OTHER); - if (ret) - return ret; - - ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), - FILTER_OTHER); - - return ret; -} - static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id) { struct trace_array *tr = data; @@ -507,6 +487,13 @@ static int __init init_syscall_trace(struct trace_event_call *call) return id; } +static struct trace_event_fields __refdata syscall_enter_fields_array[] = { + SYSCALL_FIELD(int, __syscall_nr), + { .type = TRACE_FUNCTION_TYPE, + .define_fields = syscall_enter_define_fields }, + {} +}; + struct trace_event_functions enter_syscall_print_funcs = { .trace = print_syscall_enter, }; @@ -518,7 +505,7 @@ struct trace_event_functions exit_syscall_print_funcs = { struct trace_event_class __refdata event_class_syscall_enter = { .system = "syscalls", .reg = syscall_enter_register, - .define_fields = syscall_enter_define_fields, + .fields_array = syscall_enter_fields_array, .get_fields = syscall_get_enter_fields, .raw_init = init_syscall_trace, }; @@ -526,7 +513,11 @@ struct trace_event_class __refdata event_class_syscall_enter = { struct trace_event_class __refdata event_class_syscall_exit = { .system = "syscalls", .reg = syscall_exit_register, - .define_fields = syscall_exit_define_fields, + .fields_array = (struct trace_event_fields[]){ + SYSCALL_FIELD(int, __syscall_nr), + SYSCALL_FIELD(long, ret), + {} + }, .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields), .raw_init = init_syscall_trace, }; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 6c75d94f5c2f..18d16f3ef980 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -34,12 +34,6 @@ struct uprobe_trace_entry_head { #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) -struct trace_uprobe_filter { - rwlock_t rwlock; - int nr_systemwide; - struct list_head perf_events; -}; - static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); @@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; @@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: @@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp) struct trace_probe *pos; struct trace_uprobe *tu; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } @@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call, } tu = container_of(tp, struct trace_uprobe, tp); - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; @@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - err = 0; - if (!done) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); - } - return err; + return done; } -static int uprobe_perf_multi_call(struct trace_event_call *call, - struct perf_event *event, - int (*op)(struct trace_uprobe *tu, struct perf_event *event)) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; @@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call, if (WARN_ON_ONCE(!tp)) return -ENODEV; + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); - ret = op(tu, event); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; +} + static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_multi_call(event, data, uprobe_perf_open); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_multi_call(event, data, uprobe_perf_close); + return uprobe_perf_close(event, data); #endif default: @@ -1507,12 +1528,17 @@ static struct trace_event_functions uprobe_funcs = { .trace = print_uprobe_event }; +static struct trace_event_fields uprobe_fields_array[] = { + { .type = TRACE_FUNCTION_TYPE, + .define_fields = uprobe_event_define_fields }, + {} +}; + static inline void init_trace_event_call(struct trace_uprobe *tu) { struct trace_event_call *call = trace_probe_event_call(&tu->tp); - call->event.funcs = &uprobe_funcs; - call->class->define_fields = uprobe_event_define_fields; + call->class->fields_array = uprobe_fields_array; call->flags = TRACE_EVENT_FL_UPROBE | TRACE_EVENT_FL_CAP_ANY; call->class->reg = trace_uprobe_register; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 7be3e7530841..257ffb993ea2 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -24,6 +24,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, const struct cred *tcred; u64 utime, stime, utimescaled, stimescaled; u64 delta; + time64_t btime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); @@ -32,9 +33,11 @@ void bacct_add_tsk(struct user_namespace *user_ns, /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); stats->ac_etime = delta; - /* Convert to seconds for btime */ - do_div(delta, USEC_PER_SEC); - stats->ac_btime = get_seconds() - delta; + /* Convert to seconds for btime (note y2106 limit) */ + btime = ktime_get_real_seconds() - div_u64(delta, USEC_PER_SEC); + stats->ac_btime = clamp_t(time64_t, btime, 0, U32_MAX); + stats->ac_btime64 = btime; + if (thread_group_leader(tsk)) { stats->ac_exitcode = tsk->exit_code; if (tsk->flags & PF_FORKNOEXEC) diff --git a/kernel/up.c b/kernel/up.c index 862b460ab97a..c6f323dcd45b 100644 --- a/kernel/up.c +++ b/kernel/up.c @@ -14,7 +14,8 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info, { unsigned long flags; - WARN_ON(cpu != 0); + if (cpu != 0) + return -ENXIO; local_irq_save(flags); func(info); @@ -68,9 +69,8 @@ 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_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) +void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait, const struct cpumask *mask) { unsigned long flags; @@ -84,11 +84,10 @@ void on_each_cpu_cond_mask(bool (*cond_func)(int cpu, void *info), } 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) +void on_each_cpu_cond(smp_cond_func_t cond_func, smp_call_func_t func, + void *info, bool wait) { - on_each_cpu_cond_mask(cond_func, func, info, wait, gfp_flags, NULL); + on_each_cpu_cond_mask(cond_func, func, info, wait, NULL); } EXPORT_SYMBOL(on_each_cpu_cond); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f41334ef0971..b6b1f54a7837 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -161,6 +161,8 @@ static void lockup_detector_update_enable(void) #ifdef CONFIG_SOFTLOCKUP_DETECTOR +#define SOFTLOCKUP_RESET ULONG_MAX + /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; @@ -173,8 +175,6 @@ static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); -static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); -static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; @@ -274,7 +274,7 @@ notrace void touch_softlockup_watchdog_sched(void) * Preemption can be enabled. It doesn't matter which CPU's timestamp * gets zeroed here, so use the raw_ operation. */ - raw_cpu_write(watchdog_touch_ts, 0); + raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } notrace void touch_softlockup_watchdog(void) @@ -298,14 +298,14 @@ void touch_all_softlockup_watchdogs(void) * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) - per_cpu(watchdog_touch_ts, cpu) = 0; + per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; wq_watchdog_touch(-1); } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); - __this_cpu_write(watchdog_touch_ts, 0); + __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } static int is_softlockup(unsigned long touch_ts) @@ -350,8 +350,6 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); */ static int softlockup_fn(void *data) { - __this_cpu_write(soft_lockup_hrtimer_cnt, - __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); complete(this_cpu_ptr(&softlockup_completion)); @@ -383,7 +381,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); - if (touch_ts == 0) { + if (touch_ts == SOFTLOCKUP_RESET) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically @@ -416,22 +414,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; /* only warn once */ - if (__this_cpu_read(soft_watchdog_warn) == true) { - /* - * When multiple processes are causing softlockups the - * softlockup detector only warns on the first one - * because the code relies on a full quiet cycle to - * re-arm. The second process prevents the quiet cycle - * and never gets reported. Use task pointers to detect - * this. - */ - if (__this_cpu_read(softlockup_task_ptr_saved) != - current) { - __this_cpu_write(soft_watchdog_warn, false); - __touch_watchdog(); - } + if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; - } if (softlockup_all_cpu_backtrace) { /* Prevent multiple soft-lockup reports if one cpu is already @@ -447,7 +431,6 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); - __this_cpu_write(softlockup_task_ptr_saved, current); print_modules(); print_irqtrace_events(current); if (regs) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index cfc923558e04..4e01c448b4b4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1411,14 +1411,16 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, return; rcu_read_lock(); retry: - if (req_cpu == WORK_CPU_UNBOUND) - cpu = wq_select_unbound_cpu(raw_smp_processor_id()); - /* pwq which will be used unless @work is executing elsewhere */ - if (!(wq->flags & WQ_UNBOUND)) - pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); - else + if (wq->flags & WQ_UNBOUND) { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = wq_select_unbound_cpu(raw_smp_processor_id()); pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + } else { + if (req_cpu == WORK_CPU_UNBOUND) + cpu = raw_smp_processor_id(); + pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); + } /* * If @work was previously on a different pool, it might still be @@ -2266,7 +2268,7 @@ __acquires(&pool->lock) * While we must be careful to not use "work" after this, the trace * point will only record its address. */ - trace_workqueue_execute_end(work); + trace_workqueue_execute_end(work, worker->current_func); lock_map_release(&lockdep_map); lock_map_release(&pwq->wq->lockdep_map); @@ -2280,7 +2282,7 @@ __acquires(&pool->lock) } /* - * The following prevents a kworker from hogging CPU on !PREEMPT + * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in |