diff options
Diffstat (limited to 'kernel')
154 files changed, 7487 insertions, 3171 deletions
diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 547c88be8a28..addeed3df15d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -64,6 +64,7 @@ #include <uapi/linux/limits.h> #include <uapi/linux/netfilter/nf_tables.h> #include <uapi/linux/openat2.h> // struct open_how +#include <uapi/linux/fanotify.h> #include "audit.h" @@ -1294,15 +1295,11 @@ out: static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) { - int i; - if (cap_isclear(*cap)) { audit_log_format(ab, " %s=0", prefix); return; } - audit_log_format(ab, " %s=", prefix); - CAP_FOR_EACH_U32(i) - audit_log_format(ab, "%08x", cap->cap[CAP_LAST_U32 - i]); + audit_log_format(ab, " %s=%016llx", prefix, cap->val); } static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) @@ -2252,7 +2249,7 @@ static inline int audit_copy_fcaps(struct audit_names *name, if (!dentry) return 0; - rc = get_vfs_caps_from_disk(&init_user_ns, dentry, &caps); + rc = get_vfs_caps_from_disk(&nop_mnt_idmap, dentry, &caps); if (rc) return rc; @@ -2807,7 +2804,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm, ax->d.next = context->aux; context->aux = (void *)ax; - get_vfs_caps_from_disk(&init_user_ns, + get_vfs_caps_from_disk(&nop_mnt_idmap, bprm->file->f_path.dentry, &vcaps); ax->fcap.permitted = vcaps.permitted; @@ -2877,10 +2874,21 @@ void __audit_log_kern_module(char *name) context->type = AUDIT_KERN_MODULE; } -void __audit_fanotify(unsigned int response) +void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar) { - audit_log(audit_context(), GFP_KERNEL, - AUDIT_FANOTIFY, "resp=%u", response); + /* {subj,obj}_trust values are {0,1,2}: no,yes,unknown */ + switch (friar->hdr.type) { + case FAN_RESPONSE_INFO_NONE: + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, + "resp=%u fan_type=%u fan_info=0 subj_trust=2 obj_trust=2", + response, FAN_RESPONSE_INFO_NONE); + break; + case FAN_RESPONSE_INFO_AUDIT_RULE: + audit_log(audit_context(), GFP_KERNEL, AUDIT_FANOTIFY, + "resp=%u fan_type=%u fan_info=%X subj_trust=%u obj_trust=%u", + response, friar->hdr.type, friar->rule_number, + friar->subj_trust, friar->obj_trust); + } } void __audit_tk_injoffset(struct timespec64 offset) diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 3a12e6b400a2..02242614dcc7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o endif ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o +obj-$(CONFIG_BPF_SYSCALL) += cpumask.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif obj-$(CONFIG_BPF_PRELOAD) += preload/ diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b39a46e8fb08..35f4138a54dc 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -568,8 +568,8 @@ static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_att nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); + smap->buckets = bpf_map_kvcalloc(&smap->map, sizeof(*smap->buckets), + nbuckets, GFP_USER | __GFP_NOWARN); if (!smap->buckets) { bpf_map_area_free(smap); return ERR_PTR(-ENOMEM); @@ -580,8 +580,8 @@ static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_att raw_spin_lock_init(&smap->buckets[i].lock); } - smap->elem_size = - sizeof(struct bpf_local_storage_elem) + attr->value_size; + smap->elem_size = offsetof(struct bpf_local_storage_elem, + sdata.data[attr->value_size]); return smap; } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index a4a41ee3e80b..e14c822f8911 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks) */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_socket_sock_rcv_skb) BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7dd8af06413..73780748404c 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -337,6 +337,12 @@ const char *btf_type_str(const struct btf_type *t) #define BTF_SHOW_NAME_SIZE 80 /* + * The suffix of a type that indicates it cannot alias another type when + * comparing BTF IDs for kfunc invocations. + */ +#define NOCAST_ALIAS_SUFFIX "___init" + +/* * Common data to all BTF show operations. Private show functions can add * their own data to a structure containing a struct btf_show and consult it * in the show callback. See btf_type_show() below. @@ -1397,12 +1403,18 @@ __printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; - /* btf verifier prints all types it is processing via - * btf_verifier_log_type(..., fmt = NULL). - * Skip those prints for in-kernel BTF verification. - */ - if (log->level == BPF_LOG_KERNEL && !fmt) - return; + if (log->level == BPF_LOG_KERNEL) { + /* btf verifier prints all types it is processing via + * btf_verifier_log_type(..., fmt = NULL). + * Skip those prints for in-kernel BTF verification. + */ + if (!fmt) + return; + + /* Skip logging when loading module BTF with mismatches permitted */ + if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + return; + } __btf_verifier_log(log, "[%u] %s %s%s", env->log_type_id, @@ -1441,8 +1453,15 @@ static void btf_verifier_log_member(struct btf_verifier_env *env, if (!bpf_verifier_log_needed(log)) return; - if (log->level == BPF_LOG_KERNEL && !fmt) - return; + if (log->level == BPF_LOG_KERNEL) { + if (!fmt) + return; + + /* Skip logging when loading module BTF with mismatches permitted */ + if (env->btf->base_btf && IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + return; + } + /* The CHECK_META phase already did a btf dump. * * If member is logged again, it must hit an error in @@ -3228,7 +3247,7 @@ struct btf_field_info { struct { const char *node_name; u32 value_btf_id; - } list_head; + } graph_root; }; }; @@ -3305,12 +3324,14 @@ static const char *btf_find_decl_tag_value(const struct btf *btf, return NULL; } -static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, - const struct btf_type *t, int comp_idx, - u32 off, int sz, struct btf_field_info *info) +static int +btf_find_graph_root(const struct btf *btf, const struct btf_type *pt, + const struct btf_type *t, int comp_idx, u32 off, + int sz, struct btf_field_info *info, + enum btf_field_type head_type) { + const char *node_field_name; const char *value_type; - const char *list_node; s32 id; if (!__btf_type_is_struct(t)) @@ -3320,26 +3341,32 @@ static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); if (!value_type) return -EINVAL; - list_node = strstr(value_type, ":"); - if (!list_node) + node_field_name = strstr(value_type, ":"); + if (!node_field_name) return -EINVAL; - value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN); + value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __GFP_NOWARN); if (!value_type) return -ENOMEM; id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); kfree(value_type); if (id < 0) return id; - list_node++; - if (str_is_empty(list_node)) + node_field_name++; + if (str_is_empty(node_field_name)) return -EINVAL; - info->type = BPF_LIST_HEAD; + info->type = head_type; info->off = off; - info->list_head.value_btf_id = id; - info->list_head.node_name = list_node; + info->graph_root.value_btf_id = id; + info->graph_root.node_name = node_field_name; return BTF_FIELD_FOUND; } +#define field_mask_test_name(field_type, field_type_str) \ + if (field_mask & field_type && !strcmp(name, field_type_str)) { \ + type = field_type; \ + goto end; \ + } + static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, int *align, int *sz) { @@ -3363,18 +3390,11 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } - if (field_mask & BPF_LIST_HEAD) { - if (!strcmp(name, "bpf_list_head")) { - type = BPF_LIST_HEAD; - goto end; - } - } - if (field_mask & BPF_LIST_NODE) { - if (!strcmp(name, "bpf_list_node")) { - type = BPF_LIST_NODE; - goto end; - } - } + field_mask_test_name(BPF_LIST_HEAD, "bpf_list_head"); + field_mask_test_name(BPF_LIST_NODE, "bpf_list_node"); + field_mask_test_name(BPF_RB_ROOT, "bpf_rb_root"); + field_mask_test_name(BPF_RB_NODE, "bpf_rb_node"); + /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3387,6 +3407,8 @@ end: return type; } +#undef field_mask_test_name + static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t, u32 field_mask, struct btf_field_info *info, int info_cnt) @@ -3419,6 +3441,7 @@ static int btf_find_struct_field(const struct btf *btf, case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_LIST_NODE: + case BPF_RB_NODE: ret = btf_find_struct(btf, member_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3432,8 +3455,11 @@ static int btf_find_struct_field(const struct btf *btf, return ret; break; case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, t, member_type, i, off, sz, - idx < info_cnt ? &info[idx] : &tmp); + case BPF_RB_ROOT: + ret = btf_find_graph_root(btf, t, member_type, + i, off, sz, + idx < info_cnt ? &info[idx] : &tmp, + field_type); if (ret < 0) return ret; break; @@ -3480,6 +3506,7 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_LIST_NODE: + case BPF_RB_NODE: ret = btf_find_struct(btf, var_type, off, sz, field_type, idx < info_cnt ? &info[idx] : &tmp); if (ret < 0) @@ -3493,8 +3520,11 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, return ret; break; case BPF_LIST_HEAD: - ret = btf_find_list_head(btf, var, var_type, -1, off, sz, - idx < info_cnt ? &info[idx] : &tmp); + case BPF_RB_ROOT: + ret = btf_find_graph_root(btf, var, var_type, + -1, off, sz, + idx < info_cnt ? &info[idx] : &tmp, + field_type); if (ret < 0) return ret; break; @@ -3596,21 +3626,25 @@ end_btf: return ret; } -static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, - struct btf_field_info *info) +static int btf_parse_graph_root(const struct btf *btf, + struct btf_field *field, + struct btf_field_info *info, + const char *node_type_name, + size_t node_type_align) { const struct btf_type *t, *n = NULL; const struct btf_member *member; u32 offset; int i; - t = btf_type_by_id(btf, info->list_head.value_btf_id); + t = btf_type_by_id(btf, info->graph_root.value_btf_id); /* We've already checked that value_btf_id is a struct type. We * just need to figure out the offset of the list_node, and * verify its type. */ for_each_member(i, t, member) { - if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off))) + if (strcmp(info->graph_root.node_name, + __btf_name_by_offset(btf, member->name_off))) continue; /* Invalid BTF, two members with same name */ if (n) @@ -3618,24 +3652,38 @@ static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, n = btf_type_by_id(btf, member->type); if (!__btf_type_is_struct(n)) return -EINVAL; - if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off))) + if (strcmp(node_type_name, __btf_name_by_offset(btf, n->name_off))) return -EINVAL; offset = __btf_member_bit_offset(n, member); if (offset % 8) return -EINVAL; offset /= 8; - if (offset % __alignof__(struct bpf_list_node)) + if (offset % node_type_align) return -EINVAL; - field->list_head.btf = (struct btf *)btf; - field->list_head.value_btf_id = info->list_head.value_btf_id; - field->list_head.node_offset = offset; + field->graph_root.btf = (struct btf *)btf; + field->graph_root.value_btf_id = info->graph_root.value_btf_id; + field->graph_root.node_offset = offset; } if (!n) return -ENOENT; return 0; } +static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_list_node", + __alignof__(struct bpf_list_node)); +} + +static int btf_parse_rb_root(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + return btf_parse_graph_root(btf, field, info, "bpf_rb_node", + __alignof__(struct bpf_rb_node)); +} + struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { @@ -3698,7 +3746,13 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_RB_ROOT: + ret = btf_parse_rb_root(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; case BPF_LIST_NODE: + case BPF_RB_NODE: break; default: ret = -EFAULT; @@ -3707,8 +3761,33 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type rec->cnt++; } - /* bpf_list_head requires bpf_spin_lock */ - if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) { + /* bpf_{list_head, rb_node} require bpf_spin_lock */ + if ((btf_record_has_field(rec, BPF_LIST_HEAD) || + btf_record_has_field(rec, BPF_RB_ROOT)) && rec->spin_lock_off < 0) { + ret = -EINVAL; + goto end; + } + + /* need collection identity for non-owning refs before allowing this + * + * Consider a node type w/ both list and rb_node fields: + * struct node { + * struct bpf_list_node l; + * struct bpf_rb_node r; + * } + * + * Used like so: + * struct node *n = bpf_obj_new(....); + * bpf_list_push_front(&list_head, &n->l); + * bpf_rbtree_remove(&rb_root, &n->r); + * + * It should not be possible to rbtree_remove the node since it hasn't + * been added to a tree. But push_front converts n to a non-owning + * reference, and rbtree_remove accepts the non-owning reference to + * a type w/ bpf_rb_node field. + */ + if (btf_record_has_field(rec, BPF_LIST_NODE) && + btf_record_has_field(rec, BPF_RB_NODE)) { ret = -EINVAL; goto end; } @@ -3719,62 +3798,76 @@ end: return ERR_PTR(ret); } +#define GRAPH_ROOT_MASK (BPF_LIST_HEAD | BPF_RB_ROOT) +#define GRAPH_NODE_MASK (BPF_LIST_NODE | BPF_RB_NODE) + int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec) { int i; - /* There are two owning types, kptr_ref and bpf_list_head. The former - * only supports storing kernel types, which can never store references - * to program allocated local types, atleast not yet. Hence we only need - * to ensure that bpf_list_head ownership does not form cycles. + /* There are three types that signify ownership of some other type: + * kptr_ref, bpf_list_head, bpf_rb_root. + * kptr_ref only supports storing kernel types, which can't store + * references to program allocated local types. + * + * Hence we only need to ensure that bpf_{list_head,rb_root} ownership + * does not form cycles. */ - if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & BPF_LIST_HEAD)) + if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & GRAPH_ROOT_MASK)) return 0; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *meta; u32 btf_id; - if (!(rec->fields[i].type & BPF_LIST_HEAD)) + if (!(rec->fields[i].type & GRAPH_ROOT_MASK)) continue; - btf_id = rec->fields[i].list_head.value_btf_id; + btf_id = rec->fields[i].graph_root.value_btf_id; meta = btf_find_struct_meta(btf, btf_id); if (!meta) return -EFAULT; - rec->fields[i].list_head.value_rec = meta->record; + rec->fields[i].graph_root.value_rec = meta->record; - if (!(rec->field_mask & BPF_LIST_NODE)) + /* We need to set value_rec for all root types, but no need + * to check ownership cycle for a type unless it's also a + * node type. + */ + if (!(rec->field_mask & GRAPH_NODE_MASK)) continue; /* We need to ensure ownership acyclicity among all types. The * proper way to do it would be to topologically sort all BTF * IDs based on the ownership edges, since there can be multiple - * bpf_list_head in a type. Instead, we use the following - * reasoning: + * bpf_{list_head,rb_node} in a type. Instead, we use the + * following resaoning: * * - A type can only be owned by another type in user BTF if it - * has a bpf_list_node. + * has a bpf_{list,rb}_node. Let's call these node types. * - A type can only _own_ another type in user BTF if it has a - * bpf_list_head. + * bpf_{list_head,rb_root}. Let's call these root types. * - * We ensure that if a type has both bpf_list_head and - * bpf_list_node, its element types cannot be owning types. + * We ensure that if a type is both a root and node, its + * element types cannot be root types. * * To ensure acyclicity: * - * When A only has bpf_list_head, ownership chain can be: + * When A is an root type but not a node, its ownership + * chain can be: * A -> B -> C * Where: - * - B has both bpf_list_head and bpf_list_node. - * - C only has bpf_list_node. + * - A is an root, e.g. has bpf_rb_root. + * - B is both a root and node, e.g. has bpf_rb_node and + * bpf_list_head. + * - C is only an root, e.g. has bpf_list_node * - * When A has both bpf_list_head and bpf_list_node, some other - * type already owns it in the BTF domain, hence it can not own - * another owning type through any of the bpf_list_head edges. + * When A is both a root and node, some other type already + * owns it in the BTF domain, hence it can not own + * another root type through any of the ownership edges. * A -> B * Where: - * - B only has bpf_list_node. + * - A is both an root and node. + * - B is only an node. */ - if (meta->record->field_mask & BPF_LIST_HEAD) + if (meta->record->field_mask & GRAPH_ROOT_MASK) return -ELOOP; } return 0; @@ -4476,6 +4569,7 @@ static int btf_datasec_resolve(struct btf_verifier_env *env, struct btf *btf = env->btf; u16 i; + env->resolve_mode = RESOLVE_TBD; for_each_vsi_from(i, v->next_member, v->t, vsi) { u32 var_type_id = vsi->type, type_id, type_size = 0; const struct btf_type *var_type = btf_type_by_id(env->btf, @@ -5236,6 +5330,8 @@ static const char *alloc_obj_fields[] = { "bpf_spin_lock", "bpf_list_head", "bpf_list_node", + "bpf_rb_root", + "bpf_rb_node", }; static struct btf_struct_metas * @@ -5309,7 +5405,8 @@ btf_parse_struct_metas(struct bpf_verifier_log *log, struct btf *btf) type = &tab->types[tab->cnt]; type->btf_id = i; - record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE, t->size); + record = btf_parse_fields(btf, t, BPF_SPIN_LOCK | BPF_LIST_HEAD | BPF_LIST_NODE | + BPF_RB_ROOT | BPF_RB_NODE, t->size); /* The record cannot be unset, treat it as an error if so */ if (IS_ERR_OR_NULL(record)) { ret = PTR_ERR_OR_ZERO(record) ?: -EFAULT; @@ -5573,6 +5670,7 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, if (!ctx_struct) /* should not happen */ return NULL; +again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_struct->name_off); if (!ctx_tname) { /* should not happen */ @@ -5586,8 +5684,16 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * int socket_filter_bpf_prog(struct __sk_buff *skb) * { // no fields of skb are ever used } */ - if (strcmp(ctx_tname, tname)) - return NULL; + if (strcmp(ctx_tname, tname)) { + /* bpf_user_pt_regs_t is a typedef, so resolve it to + * underlying struct and check name again + */ + if (!btf_type_is_modifier(ctx_struct)) + return NULL; + while (btf_type_is_modifier(ctx_struct)) + ctx_struct = btf_type_by_id(btf_vmlinux, ctx_struct->type); + goto again; + } return ctx_type; } @@ -6433,6 +6539,18 @@ static int __get_type_size(struct btf *btf, u32 btf_id, return -EINVAL; } +static u8 __get_type_fmodel_flags(const struct btf_type *t) +{ + u8 flags = 0; + + if (__btf_type_is_struct(t)) + flags |= BTF_FMODEL_STRUCT_ARG; + if (btf_type_is_signed_int(t)) + flags |= BTF_FMODEL_SIGNED_ARG; + + return flags; +} + int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, @@ -6453,6 +6571,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->arg_flags[i] = 0; } m->ret_size = 8; + m->ret_flags = 0; m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } @@ -6472,6 +6591,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->ret_size = ret; + m->ret_flags = __get_type_fmodel_flags(t); for (i = 0; i < nargs; i++) { if (i == nargs - 1 && args[i].type == 0) { @@ -6496,7 +6616,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->arg_size[i] = ret; - m->arg_flags[i] = __btf_type_is_struct(t) ? BTF_FMODEL_STRUCT_ARG : 0; + m->arg_flags[i] = __get_type_fmodel_flags(t); } m->nr_args = nargs; return 0; @@ -7260,11 +7380,14 @@ static int btf_module_notify(struct notifier_block *nb, unsigned long op, } btf = btf_parse_module(mod->name, mod->btf_data, mod->btf_data_size); if (IS_ERR(btf)) { - pr_warn("failed to validate module [%s] BTF: %ld\n", - mod->name, PTR_ERR(btf)); kfree(btf_mod); - if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) + if (!IS_ENABLED(CONFIG_MODULE_ALLOW_BTF_MISMATCH)) { + pr_warn("failed to validate module [%s] BTF: %ld\n", + mod->name, PTR_ERR(btf)); err = PTR_ERR(btf); + } else { + pr_warn_once("Kernel module BTF mismatch detected, BTF debug info may be unavailable for some modules\n"); + } goto out; } err = btf_alloc_id(btf); @@ -7782,9 +7905,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); - return 0; end: - btf_free_dtor_kfunc_tab(btf); + if (ret) + btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } @@ -8210,3 +8333,119 @@ out: } return err; } + +bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, + const struct bpf_reg_state *reg, + int off) +{ + struct btf *btf = reg->btf; + const struct btf_type *walk_type, *safe_type; + const char *tname; + char safe_tname[64]; + long ret, safe_id; + const struct btf_member *member, *m_walk = NULL; + u32 i; + const char *walk_name; + + walk_type = btf_type_by_id(btf, reg->btf_id); + if (!walk_type) + return false; + + tname = btf_name_by_offset(btf, walk_type->name_off); + + ret = snprintf(safe_tname, sizeof(safe_tname), "%s__safe_fields", tname); + if (ret < 0) + return false; + + safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info)); + if (safe_id < 0) + return false; + + safe_type = btf_type_by_id(btf, safe_id); + if (!safe_type) + return false; + + for_each_member(i, walk_type, member) { + u32 moff; + + /* We're looking for the PTR_TO_BTF_ID member in the struct + * type we're walking which matches the specified offset. + * Below, we'll iterate over the fields in the safe variant of + * the struct and see if any of them has a matching type / + * name. + */ + moff = __btf_member_bit_offset(walk_type, member) / 8; + if (off == moff) { + m_walk = member; + break; + } + } + if (m_walk == NULL) + return false; + + walk_name = __btf_name_by_offset(btf, m_walk->name_off); + for_each_member(i, safe_type, member) { + const char *m_name = __btf_name_by_offset(btf, member->name_off); + + /* If we match on both type and name, the field is considered trusted. */ + if (m_walk->type == member->type && !strcmp(walk_name, m_name)) + return true; + } + + return false; +} + +bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, + const struct btf *reg_btf, u32 reg_id, + const struct btf *arg_btf, u32 arg_id) +{ + const char *reg_name, *arg_name, *search_needle; + const struct btf_type *reg_type, *arg_type; + int reg_len, arg_len, cmp_len; + size_t pattern_len = sizeof(NOCAST_ALIAS_SUFFIX) - sizeof(char); + + reg_type = btf_type_by_id(reg_btf, reg_id); + if (!reg_type) + return false; + + arg_type = btf_type_by_id(arg_btf, arg_id); + if (!arg_type) + return false; + + reg_name = btf_name_by_offset(reg_btf, reg_type->name_off); + arg_name = btf_name_by_offset(arg_btf, arg_type->name_off); + + reg_len = strlen(reg_name); + arg_len = strlen(arg_name); + + /* Exactly one of the two type names may be suffixed with ___init, so + * if the strings are the same size, they can't possibly be no-cast + * aliases of one another. If you have two of the same type names, e.g. + * they're both nf_conn___init, it would be improper to return true + * because they are _not_ no-cast aliases, they are the same type. + */ + if (reg_len == arg_len) + return false; + + /* Either of the two names must be the other name, suffixed with ___init. */ + if ((reg_len != arg_len + pattern_len) && + (arg_len != reg_len + pattern_len)) + return false; + + if (reg_len < arg_len) { + search_needle = strstr(arg_name, NOCAST_ALIAS_SUFFIX); + cmp_len = reg_len; + } else { + search_needle = strstr(reg_name, NOCAST_ALIAS_SUFFIX); + cmp_len = arg_len; + } + + if (!search_needle) + return false; + + /* ___init suffix must come at the end of the name */ + if (*(search_needle + pattern_len) != '\0') + return false; + + return !strncmp(reg_name, arg_name, cmp_len); +} diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ba3fff17e2f9..b297e9f60ca1 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -34,7 +34,9 @@ #include <linux/log2.h> #include <linux/bpf_verifier.h> #include <linux/nodemask.h> +#include <linux/nospec.h> #include <linux/bpf_mem_alloc.h> +#include <linux/memcontrol.h> #include <asm/barrier.h> #include <asm/unaligned.h> @@ -87,7 +89,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog_aux *aux; struct bpf_prog *fp; @@ -96,12 +98,12 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag if (fp == NULL) return NULL; - aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); + aux = kzalloc(sizeof(*aux), bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (aux == NULL) { vfree(fp); return NULL; } - fp->active = alloc_percpu_gfp(int, GFP_KERNEL_ACCOUNT | gfp_extra_flags); + fp->active = alloc_percpu_gfp(int, bpf_memcg_flags(GFP_KERNEL | gfp_extra_flags)); if (!fp->active) { vfree(fp); kfree(aux); @@ -126,7 +128,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *prog; int cpu; @@ -159,7 +161,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) prog->aux->jited_linfo = kvcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), - GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + bpf_memcg_flags(GFP_KERNEL | __GFP_NOWARN)); if (!prog->aux->jited_linfo) return -ENOMEM; @@ -234,7 +236,7 @@ void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog *fp; u32 pages; @@ -1910,9 +1912,7 @@ out: * reuse preexisting logic from Spectre v1 mitigation that * happens to produce the required code on x86 for v4 as well. */ -#ifdef CONFIG_X86 barrier_nospec(); -#endif CONT; #define LDST(SIZEOP, SIZE) \ STX_MEM_##SIZEOP: \ @@ -2096,6 +2096,14 @@ bool bpf_prog_map_compatible(struct bpf_map *map, if (fp->kprobe_override) return false; + /* XDP programs inserted into maps are not guaranteed to run on + * a particular netdev (and can run outside driver context entirely + * in the case of devmap and cpumap). Until device checks + * are implemented, prohibit adding dev-bound programs to program maps. + */ + if (bpf_prog_is_dev_bound(fp->aux)) + return false; + spin_lock(&map->owner.lock); if (!map->owner.type) { /* There's no owner yet where we could check for @@ -2182,7 +2190,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ - if (!bpf_prog_is_dev_bound(fp->aux)) { + if (!bpf_prog_is_offloaded(fp->aux)) { *err = bpf_prog_alloc_jited_linfo(fp); if (*err) return fp; @@ -2554,7 +2562,7 @@ static void bpf_prog_free_deferred(struct work_struct *work) bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) - bpf_prog_offload_destroy(aux->prog); + bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0b2d016f0bf..d2110c1f6fa6 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -361,7 +361,7 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c new file mode 100644 index 000000000000..52b981512a35 --- /dev/null +++ b/kernel/bpf/cpumask.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Meta, Inc */ +#include <linux/bpf.h> +#include <linux/bpf_mem_alloc.h> +#include <linux/btf.h> +#include <linux/btf_ids.h> +#include <linux/cpumask.h> + +/** + * struct bpf_cpumask - refcounted BPF cpumask wrapper structure + * @cpumask: The actual cpumask embedded in the struct. + * @usage: Object reference counter. When the refcount goes to 0, the + * memory is released back to the BPF allocator, which provides + * RCU safety. + * + * Note that we explicitly embed a cpumask_t rather than a cpumask_var_t. This + * is done to avoid confusing the verifier due to the typedef of cpumask_var_t + * changing depending on whether CONFIG_CPUMASK_OFFSTACK is defined or not. See + * the details in <linux/cpumask.h>. The consequence is that this structure is + * likely a bit larger than it needs to be when CONFIG_CPUMASK_OFFSTACK is + * defined due to embedding the whole NR_CPUS-size bitmap, but the extra memory + * overhead is minimal. For the more typical case of CONFIG_CPUMASK_OFFSTACK + * not being defined, the structure is the same size regardless. + */ +struct bpf_cpumask { + cpumask_t cpumask; + refcount_t usage; +}; + +static struct bpf_mem_alloc bpf_cpumask_ma; + +static bool cpu_valid(u32 cpu) +{ + return cpu < nr_cpu_ids; +} + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global kfuncs as their definitions will be in BTF"); + +/** + * bpf_cpumask_create() - Create a mutable BPF cpumask. + * + * Allocates a cpumask that can be queried, mutated, acquired, and released by + * a BPF program. The cpumask returned by this function must either be embedded + * in a map as a kptr, or freed with bpf_cpumask_release(). + * + * bpf_cpumask_create() allocates memory using the BPF memory allocator, and + * will not block. It may return NULL if no memory is available. + */ +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) +{ + struct bpf_cpumask *cpumask; + + /* cpumask must be the first element so struct bpf_cpumask be cast to struct cpumask. */ + BUILD_BUG_ON(offsetof(struct bpf_cpumask, cpumask) != 0); + + cpumask = bpf_mem_alloc(&bpf_cpumask_ma, sizeof(*cpumask)); + if (!cpumask) + return NULL; + + memset(cpumask, 0, sizeof(*cpumask)); + refcount_set(&cpumask->usage, 1); + + return cpumask; +} + +/** + * bpf_cpumask_acquire() - Acquire a reference to a BPF cpumask. + * @cpumask: The BPF cpumask being acquired. The cpumask must be a trusted + * pointer. + * + * Acquires a reference to a BPF cpumask. The cpumask returned by this function + * must either be embedded in a map as a kptr, or freed with + * bpf_cpumask_release(). + */ +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) +{ + refcount_inc(&cpumask->usage); + return cpumask; +} + +/** + * bpf_cpumask_kptr_get() - Attempt to acquire a reference to a BPF cpumask + * stored in a map. + * @cpumaskp: A pointer to a BPF cpumask map value. + * + * Attempts to acquire a reference to a BPF cpumask stored in a map value. The + * cpumask returned by this function must either be embedded in a map as a + * kptr, or freed with bpf_cpumask_release(). This function may return NULL if + * no BPF cpumask was found in the specified map value. + */ +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp) +{ + struct bpf_cpumask *cpumask; + + /* The BPF memory allocator frees memory backing its caches in an RCU + * callback. Thus, we can safely use RCU to ensure that the cpumask is + * safe to read. + */ + rcu_read_lock(); + + cpumask = READ_ONCE(*cpumaskp); + if (cpumask && !refcount_inc_not_zero(&cpumask->usage)) + cpumask = NULL; + + rcu_read_unlock(); + return cpumask; +} + +/** + * bpf_cpumask_release() - Release a previously acquired BPF cpumask. + * @cpumask: The cpumask being released. + * + * Releases a previously acquired reference to a BPF cpumask. When the final + * reference of the BPF cpumask has been released, it is subsequently freed in + * an RCU callback in the BPF memory allocator. + */ +__bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) +{ + if (!cpumask) + return; + + if (refcount_dec_and_test(&cpumask->usage)) { + migrate_disable(); + bpf_mem_free(&bpf_cpumask_ma, cpumask); + migrate_enable(); + } +} + +/** + * bpf_cpumask_first() - Get the index of the first nonzero bit in the cpumask. + * @cpumask: The cpumask being queried. + * + * Find the index of the first nonzero bit of the cpumask. A struct bpf_cpumask + * pointer may be safely passed to this function. + */ +__bpf_kfunc u32 bpf_cpumask_first(const struct cpumask *cpumask) +{ + return cpumask_first(cpumask); +} + +/** + * bpf_cpumask_first_zero() - Get the index of the first unset bit in the + * cpumask. + * @cpumask: The cpumask being queried. + * + * Find the index of the first unset bit of the cpumask. A struct bpf_cpumask + * pointer may be safely passed to this function. + */ +__bpf_kfunc u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) +{ + return cpumask_first_zero(cpumask); +} + +/** + * bpf_cpumask_set_cpu() - Set a bit for a CPU in a BPF cpumask. + * @cpu: The CPU to be set in the cpumask. + * @cpumask: The BPF cpumask in which a bit is being set. + */ +__bpf_kfunc void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return; + + cpumask_set_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_clear_cpu() - Clear a bit for a CPU in a BPF cpumask. + * @cpu: The CPU to be cleared from the cpumask. + * @cpumask: The BPF cpumask in which a bit is being cleared. + */ +__bpf_kfunc void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return; + + cpumask_clear_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_cpu() - Test whether a CPU is set in a cpumask. + * @cpu: The CPU being queried for. + * @cpumask: The cpumask being queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is an invalid cpu. + */ +__bpf_kfunc bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_and_set_cpu() - Atomically test and set a CPU in a BPF cpumask. + * @cpu: The CPU being set and queried for. + * @cpumask: The BPF cpumask being set and queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is invalid. + */ +__bpf_kfunc bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_and_set_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_test_and_clear_cpu() - Atomically test and clear a CPU in a BPF + * cpumask. + * @cpu: The CPU being cleared and queried for. + * @cpumask: The BPF cpumask being cleared and queried for containing a CPU. + * + * Return: + * * true - @cpu is set in the cpumask + * * false - @cpu was not set in the cpumask, or @cpu is invalid. + */ +__bpf_kfunc bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +{ + if (!cpu_valid(cpu)) + return false; + + return cpumask_test_and_clear_cpu(cpu, (struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_setall() - Set all of the bits in a BPF cpumask. + * @cpumask: The BPF cpumask having all of its bits set. + */ +__bpf_kfunc void bpf_cpumask_setall(struct bpf_cpumask *cpumask) +{ + cpumask_setall((struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_clear() - Clear all of the bits in a BPF cpumask. + * @cpumask: The BPF cpumask being cleared. + */ +__bpf_kfunc void bpf_cpumask_clear(struct bpf_cpumask *cpumask) +{ + cpumask_clear((struct cpumask *)cpumask); +} + +/** + * bpf_cpumask_and() - AND two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @dst has at least one bit set following the operation + * * false - @dst is empty following the operation + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_and(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + return cpumask_and((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_or() - OR two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc void bpf_cpumask_or(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + cpumask_or((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_xor() - XOR two cpumasks and store the result. + * @dst: The BPF cpumask where the result is being stored. + * @src1: The first input. + * @src2: The second input. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc void bpf_cpumask_xor(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) +{ + cpumask_xor((struct cpumask *)dst, src1, src2); +} + +/** + * bpf_cpumask_equal() - Check two cpumasks for equality. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @src1 and @src2 have the same bits set. + * * false - @src1 and @src2 differ in at least one bit. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_equal(src1, src2); +} + +/** + * bpf_cpumask_intersects() - Check two cpumasks for overlap. + * @src1: The first input. + * @src2: The second input. + * + * Return: + * * true - @src1 and @src2 have at least one of the same bits set. + * * false - @src1 and @src2 don't have any of the same bits set. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_intersects(src1, src2); +} + +/** + * bpf_cpumask_subset() - Check if a cpumask is a subset of another. + * @src1: The first cpumask being checked as a subset. + * @src2: The second cpumask being checked as a superset. + * + * Return: + * * true - All of the bits of @src1 are set in @src2. + * * false - At least one bit in @src1 is not set in @src2. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_subset(src1, src2); +} + +/** + * bpf_cpumask_empty() - Check if a cpumask is empty. + * @cpumask: The cpumask being checked. + * + * Return: + * * true - None of the bits in @cpumask are set. + * * false - At least one bit in @cpumask is set. + * + * A struct bpf_cpumask pointer may be safely passed to @cpumask. + */ +__bpf_kfunc bool bpf_cpumask_empty(const struct cpumask *cpumask) +{ + return cpumask_empty(cpumask); +} + +/** + * bpf_cpumask_full() - Check if a cpumask has all bits set. + * @cpumask: The cpumask being checked. + * + * Return: + * * true - All of the bits in @cpumask are set. + * * false - At least one bit in @cpumask is cleared. + * + * A struct bpf_cpumask pointer may be safely passed to @cpumask. + */ +__bpf_kfunc bool bpf_cpumask_full(const struct cpumask *cpumask) +{ + return cpumask_full(cpumask); +} + +/** + * bpf_cpumask_copy() - Copy the contents of a cpumask into a BPF cpumask. + * @dst: The BPF cpumask being copied into. + * @src: The cpumask being copied. + * + * A struct bpf_cpumask pointer may be safely passed to @src. + */ +__bpf_kfunc void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) +{ + cpumask_copy((struct cpumask *)dst, src); +} + +/** + * bpf_cpumask_any() - Return a random set CPU from a cpumask. + * @cpumask: The cpumask being queried. + * + * Return: + * * A random set bit within [0, num_cpus) if at least one bit is set. + * * >= num_cpus if no bit is set. + * + * A struct bpf_cpumask pointer may be safely passed to @src. + */ +__bpf_kfunc u32 bpf_cpumask_any(const struct cpumask *cpumask) +{ + return cpumask_any(cpumask); +} + +/** + * bpf_cpumask_any_and() - Return a random set CPU from the AND of two + * cpumasks. + * @src1: The first cpumask. + * @src2: The second cpumask. + * + * Return: + * * A random set bit within [0, num_cpus) if at least one bit is set. + * * >= num_cpus if no bit is set. + * + * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. + */ +__bpf_kfunc u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) +{ + return cpumask_any_and(src1, src2); +} + +__diag_pop(); + +BTF_SET8_START(cpumask_kfunc_btf_ids) +BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_cpumask_first, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_first_zero, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_set_cpu, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_clear_cpu, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_test_cpu, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_set_cpu, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_test_and_clear_cpu, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_setall, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_clear, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_and, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_or, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_xor, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_equal, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_intersects, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_subset, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_empty, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_full, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_any, KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_cpumask_any_and, KF_TRUSTED_ARGS) +BTF_SET8_END(cpumask_kfunc_btf_ids) + +static const struct btf_kfunc_id_set cpumask_kfunc_set = { + .owner = THIS_MODULE, + .set = &cpumask_kfunc_btf_ids, +}; + +BTF_ID_LIST(cpumask_dtor_ids) +BTF_ID(struct, bpf_cpumask) +BTF_ID(func, bpf_cpumask_release) + +static int __init cpumask_kfunc_init(void) +{ + int ret; + const struct btf_id_dtor_kfunc cpumask_dtors[] = { + { + .btf_id = cpumask_dtor_ids[0], + .kfunc_btf_id = cpumask_dtor_ids[1] + }, + }; + + ret = bpf_mem_alloc_init(&bpf_cpumask_ma, 0, false); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &cpumask_kfunc_set); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &cpumask_kfunc_set); + return ret ?: register_btf_id_dtor_kfuncs(cpumask_dtors, + ARRAY_SIZE(cpumask_dtors), + THIS_MODULE); +} + +late_initcall(cpumask_kfunc_init); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d01e4c55b376..2675fefc6cb6 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -474,7 +474,11 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, { int err; - if (!dev->netdev_ops->ndo_xdp_xmit) + if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return -EOPNOTSUPP; + + if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); @@ -532,8 +536,14 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { - if (!obj || - !obj->dev->netdev_ops->ndo_xdp_xmit) + if (!obj) + return false; + + if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return false; + + if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 5aa2b5525f79..5dfcb5ad0d06 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,7 +152,7 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab, { unsigned long flags; - hash = hash & HASHTAB_MAP_LOCK_MASK; + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); preempt_disable(); if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { @@ -171,7 +171,7 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab, struct bucket *b, u32 hash, unsigned long flags) { - hash = hash & HASHTAB_MAP_LOCK_MASK; + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); raw_spin_unlock_irqrestore(&b->raw_lock, flags); __this_cpu_dec(*(htab->map_locked[hash])); preempt_enable(); @@ -1004,8 +1004,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } - check_and_init_map_value(&htab->map, - l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); @@ -1592,6 +1590,7 @@ static int __htab_map_lookup_and_delete_elem(struct bpf_map *map, void *key, else copy_map_value(map, value, l->key + roundup_key_size); + /* Zeroing special fields in the temp buffer */ check_and_init_map_value(map, value); } @@ -1792,6 +1791,7 @@ again_nocopy: true); else copy_map_value(map, dst_val, value); + /* Zeroing special fields in the temp buffer */ check_and_init_map_value(map, dst_val); } if (do_delete) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index af30c6cbd65d..5b278a38ae58 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -756,19 +756,20 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype, /* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary * arguments representation. */ -#define MAX_BPRINTF_BUF_LEN 512 +#define MAX_BPRINTF_BIN_ARGS 512 /* Support executing three nested bprintf helper calls on a given CPU */ #define MAX_BPRINTF_NEST_LEVEL 3 struct bpf_bprintf_buffers { - char tmp_bufs[MAX_BPRINTF_NEST_LEVEL][MAX_BPRINTF_BUF_LEN]; + char bin_args[MAX_BPRINTF_BIN_ARGS]; + char buf[MAX_BPRINTF_BUF]; }; -static DEFINE_PER_CPU(struct bpf_bprintf_buffers, bpf_bprintf_bufs); + +static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs); static DEFINE_PER_CPU(int, bpf_bprintf_nest_level); -static int try_get_fmt_tmp_buf(char **tmp_buf) +static int try_get_buffers(struct bpf_bprintf_buffers **bufs) { - struct bpf_bprintf_buffers *bufs; int nest_level; preempt_disable(); @@ -778,18 +779,19 @@ static int try_get_fmt_tmp_buf(char **tmp_buf) preempt_enable(); return -EBUSY; } - bufs = this_cpu_ptr(&bpf_bprintf_bufs); - *tmp_buf = bufs->tmp_bufs[nest_level - 1]; + *bufs = this_cpu_ptr(&bpf_bprintf_bufs[nest_level - 1]); return 0; } -void bpf_bprintf_cleanup(void) +void bpf_bprintf_cleanup(struct bpf_bprintf_data *data) { - if (this_cpu_read(bpf_bprintf_nest_level)) { - this_cpu_dec(bpf_bprintf_nest_level); - preempt_enable(); - } + if (!data->bin_args && !data->buf) + return; + if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0)) + return; + this_cpu_dec(bpf_bprintf_nest_level); + preempt_enable(); } /* @@ -798,18 +800,20 @@ void bpf_bprintf_cleanup(void) * Returns a negative value if fmt is an invalid format string or 0 otherwise. * * This can be used in two ways: - * - Format string verification only: when bin_args is NULL + * - Format string verification only: when data->get_bin_args is false * - Arguments preparation: in addition to the above verification, it writes in - * bin_args a binary representation of arguments usable by bstr_printf where - * pointers from BPF have been sanitized. + * data->bin_args a binary representation of arguments usable by bstr_printf + * where pointers from BPF have been sanitized. * * In argument preparation mode, if 0 is returned, safe temporary buffers are * allocated and bpf_bprintf_cleanup should be called to free them after use. */ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, - u32 **bin_args, u32 num_args) + u32 num_args, struct bpf_bprintf_data *data) { + bool get_buffers = (data->get_bin_args && num_args) || data->get_buf; char *unsafe_ptr = NULL, *tmp_buf = NULL, *tmp_buf_end, *fmt_end; + struct bpf_bprintf_buffers *buffers = NULL; size_t sizeof_cur_arg, sizeof_cur_ip; int err, i, num_spec = 0; u64 cur_arg; @@ -820,14 +824,19 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, return -EINVAL; fmt_size = fmt_end - fmt; - if (bin_args) { - if (num_args && try_get_fmt_tmp_buf(&tmp_buf)) - return -EBUSY; + if (get_buffers && try_get_buffers(&buffers)) + return -EBUSY; - tmp_buf_end = tmp_buf + MAX_BPRINTF_BUF_LEN; - *bin_args = (u32 *)tmp_buf; + if (data->get_bin_args) { + if (num_args) + tmp_buf = buffers->bin_args; + tmp_buf_end = tmp_buf + MAX_BPRINTF_BIN_ARGS; + data->bin_args = (u32 *)tmp_buf; } + if (data->get_buf) + data->buf = buffers->buf; + for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { err = -EINVAL; @@ -1021,31 +1030,33 @@ nocopy_fmt: err = 0; out: if (err) - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(data); return err; } BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; /* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we * can safely give an unbounded size. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, args, num_args, &data); if (err < 0) return err; - err = bstr_printf(str, str_size, fmt, bin_args); + err = bstr_printf(str, str_size, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return err + 1; } @@ -1745,12 +1756,12 @@ unlock: while (head != orig_head) { void *obj = head; - obj -= field->list_head.node_offset; + obj -= field->graph_root.node_offset; head = head->next; /* The contained type can also have resources, including a * bpf_list_head which needs to be freed. */ - bpf_obj_free_fields(field->list_head.value_rec, obj); + bpf_obj_free_fields(field->graph_root.value_rec, obj); /* bpf_mem_free requires migrate_disable(), since we can be * called from map free path as well apart from BPF program (as * part of map ops doing bpf_obj_free_fields). @@ -1761,11 +1772,51 @@ unlock: } } +/* Like rbtree_postorder_for_each_entry_safe, but 'pos' and 'n' are + * 'rb_node *', so field name of rb_node within containing struct is not + * needed. + * + * Since bpf_rb_tree's node type has a corresponding struct btf_field with + * graph_root.node_offset, it's not necessary to know field name + * or type of node struct + */ +#define bpf_rbtree_postorder_for_each_entry_safe(pos, n, root) \ + for (pos = rb_first_postorder(root); \ + pos && ({ n = rb_next_postorder(pos); 1; }); \ + pos = n) + +void bpf_rb_root_free(const struct btf_field *field, void *rb_root, + struct bpf_spin_lock *spin_lock) +{ + struct rb_root_cached orig_root, *root = rb_root; + struct rb_node *pos, *n; + void *obj; + + BUILD_BUG_ON(sizeof(struct rb_root_cached) > sizeof(struct bpf_rb_root)); + BUILD_BUG_ON(__alignof__(struct rb_root_cached) > __alignof__(struct bpf_rb_root)); + + __bpf_spin_lock_irqsave(spin_lock); + orig_root = *root; + *root = RB_ROOT_CACHED; + __bpf_spin_unlock_irqrestore(spin_lock); + + bpf_rbtree_postorder_for_each_entry_safe(pos, n, &orig_root.rb_root) { + obj = pos; + obj -= field->graph_root.node_offset; + + bpf_obj_free_fields(field->graph_root.value_rec, obj); + + migrate_disable(); + bpf_mem_free(&bpf_global_ma, obj); + migrate_enable(); + } +} + __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); -void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; u64 size = local_type_id__k; @@ -1779,7 +1830,7 @@ void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) return p; } -void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) +__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; void *p = p__alloc; @@ -1800,12 +1851,12 @@ static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *hea tail ? list_add_tail(n, h) : list_add(n, h); } -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) { return __bpf_list_add(node, head, false); } -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) { return __bpf_list_add(node, head, true); } @@ -1823,23 +1874,73 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai return (struct bpf_list_node *)n; } -struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) { return __bpf_list_del(head, false); } -struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) { return __bpf_list_del(head, true); } +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, + struct bpf_rb_node *node) +{ + struct rb_root_cached *r = (struct rb_root_cached *)root; + struct rb_node *n = (struct rb_node *)node; + + rb_erase_cached(n, r); + RB_CLEAR_NODE(n); + return (struct bpf_rb_node *)n; +} + +/* Need to copy rbtree_add_cached's logic here because our 'less' is a BPF + * program + */ +static void __bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node, + void *less) +{ + struct rb_node **link = &((struct rb_root_cached *)root)->rb_root.rb_node; + bpf_callback_t cb = (bpf_callback_t)less; + struct rb_node *parent = NULL; + bool leftmost = true; + + while (*link) { + parent = *link; + if (cb((uintptr_t)node, (uintptr_t)parent, 0, 0, 0)) { + link = &parent->rb_left; + } else { + link = &parent->rb_right; + leftmost = false; + } + } + + rb_link_node((struct rb_node *)node, parent, link); + rb_insert_color_cached((struct rb_node *)node, + (struct rb_root_cached *)root, leftmost); +} + +__bpf_kfunc void bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node, + bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)) +{ + __bpf_rbtree_add(root, node, (void *)less); +} + +__bpf_kfunc struct bpf_rb_node *bpf_rbtree_first(struct bpf_rb_root *root) +{ + struct rb_root_cached *r = (struct rb_root_cached *)root; + + return (struct bpf_rb_node *)rb_first_cached(r); +} + /** * bpf_task_acquire - Acquire a reference to a task. A task acquired by this * kfunc which is not stored in a map as a kptr, must be released by calling * bpf_task_release(). * @p: The task on which a reference is being acquired. */ -struct task_struct *bpf_task_acquire(struct task_struct *p) +__bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p) { return get_task_struct(p); } @@ -1850,7 +1951,7 @@ struct task_struct *bpf_task_acquire(struct task_struct *p) * released by calling bpf_task_release(). * @p: The task on which a reference is being acquired. */ -struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) +__bpf_kfunc struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) { /* For the time being this function returns NULL, as it's not currently * possible to safely acquire a reference to a task with RCU protection @@ -1902,7 +2003,7 @@ struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) * be released by calling bpf_task_release(). * @pp: A pointer to a task kptr on which a reference is being acquired. */ -struct task_struct *bpf_task_kptr_get(struct task_struct **pp) +__bpf_kfunc struct task_struct *bpf_task_kptr_get(struct task_struct **pp) { /* We must return NULL here until we have clarity on how to properly * leverage RCU for ensuring a task's lifetime. See the comment above @@ -1915,7 +2016,7 @@ struct task_struct *bpf_task_kptr_get(struct task_struct **pp) * bpf_task_release - Release the reference acquired on a task. * @p: The task on which a reference is being released. */ -void bpf_task_release(struct task_struct *p) +__bpf_kfunc void bpf_task_release(struct task_struct *p) { if (!p) return; @@ -1930,7 +2031,7 @@ void bpf_task_release(struct task_struct *p) * calling bpf_cgroup_release(). * @cgrp: The cgroup on which a reference is being acquired. */ -struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) +__bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) { cgroup_get(cgrp); return cgrp; @@ -1942,7 +2043,7 @@ struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) * be released by calling bpf_cgroup_release(). * @cgrpp: A pointer to a cgroup kptr on which a reference is being acquired. */ -struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) +__bpf_kfunc struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) { struct cgroup *cgrp; @@ -1974,7 +2075,7 @@ struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) * drops to 0. * @cgrp: The cgroup on which a reference is being released. */ -void bpf_cgroup_release(struct cgroup *cgrp) +__bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) { if (!cgrp) return; @@ -1989,7 +2090,7 @@ void bpf_cgroup_release(struct cgroup *cgrp) * @cgrp: The cgroup for which we're performing a lookup. * @level: The level of ancestor to look up. */ -struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) +__bpf_kfunc struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) { struct cgroup *ancestor; @@ -2008,7 +2109,7 @@ struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) * stored in a map, or released with bpf_task_release(). * @pid: The pid of the task being looked up. */ -struct task_struct *bpf_task_from_pid(s32 pid) +__bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) { struct task_struct *p; @@ -2021,22 +2122,22 @@ struct task_struct *bpf_task_from_pid(s32 pid) return p; } -void *bpf_cast_to_kern_ctx(void *obj) +__bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; } -void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) +__bpf_kfunc void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) { return obj__ign; } -void bpf_rcu_read_lock(void) +__bpf_kfunc void bpf_rcu_read_lock(void) { rcu_read_lock(); } -void bpf_rcu_read_unlock(void) +__bpf_kfunc void bpf_rcu_read_unlock(void) { rcu_read_unlock(); } @@ -2057,6 +2158,10 @@ BTF_ID_FLAGS(func, bpf_task_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_task_acquire_not_zero, KF_ACQUIRE | KF_RCU | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_task_release, KF_RELEASE) +BTF_ID_FLAGS(func, bpf_rbtree_remove, KF_ACQUIRE) +BTF_ID_FLAGS(func, bpf_rbtree_add) +BTF_ID_FLAGS(func, bpf_rbtree_first, KF_RET_NULL) + #ifdef CONFIG_CGROUPS BTF_ID_FLAGS(func, bpf_cgroup_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_cgroup_kptr_get, KF_ACQUIRE | KF_KPTR_GET | KF_RET_NULL) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 4f841e16779e..9948b542a470 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -122,7 +122,7 @@ static struct inode *bpf_get_inode(struct super_block *sb, inode->i_mtime = inode->i_atime; inode->i_ctime = inode->i_atime; - inode_init_owner(&init_user_ns, inode, dir, mode); + inode_init_owner(&nop_mnt_idmap, inode, dir, mode); return inode; } @@ -152,7 +152,7 @@ static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, dir->i_ctime = dir->i_mtime; } -static int bpf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, +static int bpf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; @@ -382,7 +382,7 @@ bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) return simple_lookup(dir, dentry, flags); } -static int bpf_symlink(struct user_namespace *mnt_userns, struct inode *dir, +static int bpf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); @@ -559,7 +559,7 @@ int bpf_obj_get_user(const char __user *pathname, int flags) static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; - int ret = inode_permission(&init_user_ns, inode, MAY_READ); + int ret = inode_permission(&nop_mnt_idmap, inode, MAY_READ); if (ret) return ERR_PTR(ret); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index ebcc3dd0fa19..5fcdacbb8439 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size) if (size <= 192) return size_index[(size - 1) / 8] - 1; - return fls(size - 1) - 1; + return fls(size - 1) - 2; } #define NUM_CACHES 11 @@ -143,7 +143,7 @@ static void *__alloc(struct bpf_mem_cache *c, int node) return obj; } - return kmalloc_node(c->unit_size, flags, node); + return kmalloc_node(c->unit_size, flags | __GFP_ZERO, node); } static struct mem_cgroup *get_memcg(const struct bpf_mem_cache *c) @@ -395,7 +395,8 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) unit_size = size; #ifdef CONFIG_MEMCG_KMEM - objcg = get_obj_cgroup_from_current(); + if (memcg_bpf_enabled()) + objcg = get_obj_cgroup_from_current(); #endif for_each_possible_cpu(cpu) { c = per_cpu_ptr(pc, cpu); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 13e4efc971e6..0c85e06f7ea7 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -41,7 +41,7 @@ struct bpf_offload_dev { struct bpf_offload_netdev { struct rhash_head l; struct net_device *netdev; - struct bpf_offload_dev *offdev; + struct bpf_offload_dev *offdev; /* NULL when bound-only */ struct list_head progs; struct list_head maps; struct list_head offdev_netdevs; @@ -56,7 +56,6 @@ static const struct rhashtable_params offdevs_params = { }; static struct rhashtable offdevs; -static bool offdevs_inited; static int bpf_dev_offload_check(struct net_device *netdev) { @@ -72,58 +71,218 @@ bpf_offload_find_netdev(struct net_device *netdev) { lockdep_assert_held(&bpf_devs_lock); - if (!offdevs_inited) - return NULL; return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); } -int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev) { struct bpf_offload_netdev *ondev; - struct bpf_prog_offload *offload; int err; - if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS && - attr->prog_type != BPF_PROG_TYPE_XDP) - return -EINVAL; + ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); + if (!ondev) + return -ENOMEM; - if (attr->prog_flags) - return -EINVAL; + ondev->netdev = netdev; + ondev->offdev = offdev; + INIT_LIST_HEAD(&ondev->progs); + INIT_LIST_HEAD(&ondev->maps); + + err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); + if (err) { + netdev_warn(netdev, "failed to register for BPF offload\n"); + goto err_free; + } + + if (offdev) + list_add(&ondev->offdev_netdevs, &offdev->netdevs); + return 0; + +err_free: + kfree(ondev); + return err; +} + +static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_prog_offload *offload = prog->aux->offload; + + if (offload->dev_state) + offload->offdev->ops->destroy(prog); + + list_del_init(&offload->offloads); + kfree(offload); + prog->aux->offload = NULL; +} + +static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, + enum bpf_netdev_command cmd) +{ + struct netdev_bpf data = {}; + struct net_device *netdev; + + ASSERT_RTNL(); + + data.command = cmd; + data.offmap = offmap; + /* Caller must make sure netdev is valid */ + netdev = offmap->netdev; + + return netdev->netdev_ops->ndo_bpf(netdev, &data); +} + +static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) +{ + WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); + /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ + bpf_map_free_id(&offmap->map); + list_del_init(&offmap->offloads); + offmap->netdev = NULL; +} + +static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev) +{ + struct bpf_offload_netdev *ondev, *altdev = NULL; + struct bpf_offloaded_map *offmap, *mtmp; + struct bpf_prog_offload *offload, *ptmp; + + ASSERT_RTNL(); + + ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); + if (WARN_ON(!ondev)) + return; + + WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); + + /* Try to move the objects to another netdev of the device */ + if (offdev) { + list_del(&ondev->offdev_netdevs); + altdev = list_first_entry_or_null(&offdev->netdevs, + struct bpf_offload_netdev, + offdev_netdevs); + } + + if (altdev) { + list_for_each_entry(offload, &ondev->progs, offloads) + offload->netdev = altdev->netdev; + list_splice_init(&ondev->progs, &altdev->progs); + + list_for_each_entry(offmap, &ondev->maps, offloads) + offmap->netdev = altdev->netdev; + list_splice_init(&ondev->maps, &altdev->maps); + } else { + list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) + __bpf_prog_offload_destroy(offload->prog); + list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) + __bpf_map_offload_destroy(offmap); + } + + WARN_ON(!list_empty(&ondev->progs)); + WARN_ON(!list_empty(&ondev->maps)); + kfree(ondev); +} + +static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *netdev) +{ + struct bpf_offload_netdev *ondev; + struct bpf_prog_offload *offload; + int err; offload = kzalloc(sizeof(*offload), GFP_USER); if (!offload) return -ENOMEM; offload->prog = prog; + offload->netdev = netdev; - offload->netdev = dev_get_by_index(current->nsproxy->net_ns, - attr->prog_ifindex); - err = bpf_dev_offload_check(offload->netdev); - if (err) - goto err_maybe_put; - - down_write(&bpf_devs_lock); ondev = bpf_offload_find_netdev(offload->netdev); if (!ondev) { - err = -EINVAL; - goto err_unlock; + if (bpf_prog_is_offloaded(prog->aux)) { + err = -EINVAL; + goto err_free; + } + + /* When only binding to the device, explicitly + * create an entry in the hashtable. + */ + err = __bpf_offload_dev_netdev_register(NULL, offload->netdev); + if (err) + goto err_free; + ondev = bpf_offload_find_netdev(offload->netdev); } offload->offdev = ondev->offdev; prog->aux->offload = offload; list_add_tail(&offload->offloads, &ondev->progs); - dev_put(offload->netdev); - up_write(&bpf_devs_lock); return 0; -err_unlock: - up_write(&bpf_devs_lock); -err_maybe_put: - if (offload->netdev) - dev_put(offload->netdev); +err_free: kfree(offload); return err; } +int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) +{ + struct net_device *netdev; + int err; + + if (attr->prog_type != BPF_PROG_TYPE_SCHED_CLS && + attr->prog_type != BPF_PROG_TYPE_XDP) + return -EINVAL; + + if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY) + return -EINVAL; + + if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS && + attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY) + return -EINVAL; + + netdev = dev_get_by_index(current->nsproxy->net_ns, attr->prog_ifindex); + if (!netdev) + return -EINVAL; + + err = bpf_dev_offload_check(netdev); + if (err) + goto out; + + prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY); + + down_write(&bpf_devs_lock); + err = __bpf_prog_dev_bound_init(prog, netdev); + up_write(&bpf_devs_lock); + +out: + dev_put(netdev); + return err; +} + +int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) +{ + int err; + + if (!bpf_prog_is_dev_bound(old_prog->aux)) + return 0; + + if (bpf_prog_is_offloaded(old_prog->aux)) + return -EINVAL; + + new_prog->aux->dev_bound = old_prog->aux->dev_bound; + new_prog->aux->offload_requested = old_prog->aux->offload_requested; + + down_write(&bpf_devs_lock); + if (!old_prog->aux->offload) { + err = -EINVAL; + goto out; + } + + err = __bpf_prog_dev_bound_init(new_prog, old_prog->aux->offload->netdev); + +out: + up_write(&bpf_devs_lock); + return err; +} + int bpf_prog_offload_verifier_prep(struct bpf_prog *prog) { struct bpf_prog_offload *offload; @@ -209,27 +368,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) up_read(&bpf_devs_lock); } -static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +void bpf_prog_dev_bound_destroy(struct bpf_prog *prog) { - struct bpf_prog_offload *offload = prog->aux->offload; - - if (offload->dev_state) - offload->offdev->ops->destroy(prog); - - /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */ - bpf_prog_free_id(prog, true); - - list_del_init(&offload->offloads); - kfree(offload); - prog->aux->offload = NULL; -} + struct bpf_offload_netdev *ondev; + struct net_device *netdev; -void bpf_prog_offload_destroy(struct bpf_prog *prog) -{ + rtnl_lock(); down_write(&bpf_devs_lock); - if (prog->aux->offload) + if (prog->aux->offload) { + list_del_init(&prog->aux->offload->offloads); + + netdev = prog->aux->offload->netdev; __bpf_prog_offload_destroy(prog); + + ondev = bpf_offload_find_netdev(netdev); + if (!ondev->offdev && list_empty(&ondev->progs)) + __bpf_offload_dev_netdev_unregister(NULL, netdev); + } up_write(&bpf_devs_lock); + rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) @@ -343,22 +500,6 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, const struct bpf_prog_ops bpf_offload_prog_ops = { }; -static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, - enum bpf_netdev_command cmd) -{ - struct netdev_bpf data = {}; - struct net_device *netdev; - - ASSERT_RTNL(); - - data.command = cmd; - data.offmap = offmap; - /* Caller must make sure netdev is valid */ - netdev = offmap->netdev; - - return netdev->netdev_ops->ndo_bpf(netdev, &data); -} - struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { struct net *net = current->nsproxy->net_ns; @@ -408,15 +549,6 @@ err_unlock: return ERR_PTR(err); } -static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) -{ - WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); - /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ - bpf_map_free_id(&offmap->map, true); - list_del_init(&offmap->offloads); - offmap->netdev = NULL; -} - void bpf_map_offload_map_free(struct bpf_map *map) { struct bpf_offloaded_map *offmap = map_to_offmap(map); @@ -576,12 +708,28 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev) } EXPORT_SYMBOL_GPL(bpf_offload_dev_match); +bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) +{ + bool ret; + + if (bpf_prog_is_offloaded(lhs->aux) != bpf_prog_is_offloaded(rhs->aux)) + return false; + + down_read(&bpf_devs_lock); + ret = lhs->aux->offload && rhs->aux->offload && + lhs->aux->offload->netdev && + lhs->aux->offload->netdev == rhs->aux->offload->netdev; + up_read(&bpf_devs_lock); + + return ret; +} + bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) { struct bpf_offloaded_map *offmap; bool ret; - if (!bpf_map_is_dev_bound(map)) + if (!bpf_map_is_offloaded(map)) return bpf_map_offload_neutral(map); offmap = map_to_offmap(map); @@ -595,32 +743,11 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev; int err; - ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); - if (!ondev) - return -ENOMEM; - - ondev->netdev = netdev; - ondev->offdev = offdev; - INIT_LIST_HEAD(&ondev->progs); - INIT_LIST_HEAD(&ondev->maps); - down_write(&bpf_devs_lock); - err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); - if (err) { - netdev_warn(netdev, "failed to register for BPF offload\n"); - goto err_unlock_free; - } - - list_add(&ondev->offdev_netdevs, &offdev->netdevs); - up_write(&bpf_devs_lock); - return 0; - -err_unlock_free: + err = __bpf_offload_dev_netdev_register(offdev, netdev); up_write(&bpf_devs_lock); - kfree(ondev); return err; } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); @@ -628,43 +755,8 @@ EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev, *altdev; - struct bpf_offloaded_map *offmap, *mtmp; - struct bpf_prog_offload *offload, *ptmp; - - ASSERT_RTNL(); - down_write(&bpf_devs_lock); - ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); - if (WARN_ON(!ondev)) - goto unlock; - - WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); - list_del(&ondev->offdev_netdevs); - - /* Try to move the objects to another netdev of the device */ - altdev = list_first_entry_or_null(&offdev->netdevs, - struct bpf_offload_netdev, - offdev_netdevs); - if (altdev) { - list_for_each_entry(offload, &ondev->progs, offloads) - offload->netdev = altdev->netdev; - list_splice_init(&ondev->progs, &altdev->progs); - - list_for_each_entry(offmap, &ondev->maps, offloads) - offmap->netdev = altdev->netdev; - list_splice_init(&ondev->maps, &altdev->maps); - } else { - list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) - __bpf_prog_offload_destroy(offload->prog); - list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) - __bpf_map_offload_destroy(offmap); - } - - WARN_ON(!list_empty(&ondev->progs)); - WARN_ON(!list_empty(&ondev->maps)); - kfree(ondev); -unlock: + __bpf_offload_dev_netdev_unregister(offdev, netdev); up_write(&bpf_devs_lock); } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); @@ -673,18 +765,6 @@ struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) { struct bpf_offload_dev *offdev; - int err; - - down_write(&bpf_devs_lock); - if (!offdevs_inited) { - err = rhashtable_init(&offdevs, &offdevs_params); - if (err) { - up_write(&bpf_devs_lock); - return ERR_PTR(err); - } - offdevs_inited = true; - } - up_write(&bpf_devs_lock); offdev = kzalloc(sizeof(*offdev), GFP_KERNEL); if (!offdev) @@ -710,3 +790,67 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev) return offdev->priv; } EXPORT_SYMBOL_GPL(bpf_offload_dev_priv); + +void bpf_dev_bound_netdev_unregister(struct net_device *dev) +{ + struct bpf_offload_netdev *ondev; + + ASSERT_RTNL(); + + down_write(&bpf_devs_lock); + ondev = bpf_offload_find_netdev(dev); + if (ondev && !ondev->offdev) + __bpf_offload_dev_netdev_unregister(NULL, ondev->netdev); + up_write(&bpf_devs_lock); +} + +int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, + struct bpf_prog_aux *prog_aux) +{ + if (!bpf_prog_is_dev_bound(prog_aux)) { + bpf_log(log, "metadata kfuncs require device-bound program\n"); + return -EINVAL; + } + + if (bpf_prog_is_offloaded(prog_aux)) { + bpf_log(log, "metadata kfuncs can't be offloaded\n"); + return -EINVAL; + } + + return 0; +} + +void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) +{ + const struct xdp_metadata_ops *ops; + void *p = NULL; + + /* We don't hold bpf_devs_lock while resolving several + * kfuncs and can race with the unregister_netdevice(). + * We rely on bpf_dev_bound_match() check at attach + * to render this program unusable. + */ + down_read(&bpf_devs_lock); + if (!prog->aux->offload) + goto out; + + ops = prog->aux->offload->netdev->xdp_metadata_ops; + if (!ops) + goto out; + + if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_TIMESTAMP)) + p = ops->xmo_rx_timestamp; + else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH)) + p = ops->xmo_rx_hash; +out: + up_read(&bpf_devs_lock); + + return p; +} + +static int __init bpf_offload_init(void) +{ + return rhashtable_init(&offdevs, &offdevs_params); +} + +late_initcall(bpf_offload_init); diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c index 5106b5372f0c..b56f9f3314fd 100644 --- a/kernel/bpf/preload/bpf_preload_kern.c +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -3,7 +3,11 @@ #include <linux/init.h> #include <linux/module.h> #include "bpf_preload.h" -#include "iterators/iterators.lskel.h" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#include "iterators/iterators.lskel-little-endian.h" +#else +#include "iterators/iterators.lskel-big-endian.h" +#endif static struct bpf_link *maps_link, *progs_link; static struct iterators_bpf *skel; diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile index 6762b1260f2f..8937dc6bc8d0 100644 --- a/kernel/bpf/preload/iterators/Makefile +++ b/kernel/bpf/preload/iterators/Makefile @@ -35,20 +35,22 @@ endif .PHONY: all clean -all: iterators.lskel.h +all: iterators.lskel-little-endian.h + +big: iterators.lskel-big-endian.h clean: $(call msg,CLEAN) $(Q)rm -rf $(OUTPUT) iterators -iterators.lskel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) +iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL) $(call msg,GEN-SKEL,$@) $(Q)$(BPFTOOL) gen skeleton -L $< > $@ - -$(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) +$(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) $(call msg,BPF,$@) - $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + $(Q)mkdir -p $(@D) + $(Q)$(CLANG) -g -O2 -target bpf -m$* $(INCLUDES) \ -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ diff --git a/kernel/bpf/preload/iterators/README b/kernel/bpf/preload/iterators/README index 7fd6d39a9ad2..98e7c90ea012 100644 --- a/kernel/bpf/preload/iterators/README +++ b/kernel/bpf/preload/iterators/README @@ -1,4 +1,7 @@ WARNING: -If you change "iterators.bpf.c" do "make -j" in this directory to rebuild "iterators.skel.h". +If you change "iterators.bpf.c" do "make -j" in this directory to +rebuild "iterators.lskel-little-endian.h". Then, on a big-endian +machine, do "make -j big" in this directory to rebuild +"iterators.lskel-big-endian.h". Commit both resulting headers. Make sure to have clang 10 installed. See Documentation/bpf/bpf_devel_QA.rst diff --git a/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h new file mode 100644 index 000000000000..ebdc6c0cdb70 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h @@ -0,0 +1,419 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <bpf/skel_internal.h> + +struct iterators_bpf { + struct bpf_loader_ctx ctx; + struct { + struct bpf_map_desc rodata; + } maps; + struct { + struct bpf_prog_desc dump_bpf_map; + struct bpf_prog_desc dump_bpf_prog; + } progs; + struct { + int dump_bpf_map_fd; + int dump_bpf_prog_fd; + } links; +}; + +static inline int +iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_map.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_map_fd = fd; + return fd; +} + +static inline int +iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_prog.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_prog_fd = fd; + return fd; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *skel) +{ + int ret = 0; + + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); + return ret < 0 ? ret : 0; +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *skel) +{ + skel_closenz(skel->links.dump_bpf_map_fd); + skel_closenz(skel->links.dump_bpf_prog_fd); +} +static void +iterators_bpf__destroy(struct iterators_bpf *skel) +{ + if (!skel) + return; + iterators_bpf__detach(skel); + skel_closenz(skel->progs.dump_bpf_map.prog_fd); + skel_closenz(skel->progs.dump_bpf_prog.prog_fd); + skel_closenz(skel->maps.rodata.map_fd); + skel_free(skel); +} +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + struct iterators_bpf *skel; + + skel = skel_alloc(sizeof(*skel)); + if (!skel) + goto cleanup; + skel->ctx.sz = (void *)&skel->links - (void *)skel; + return skel; +cleanup: + iterators_bpf__destroy(skel); + return NULL; +} + +static inline int +iterators_bpf__load(struct iterators_bpf *skel) +{ + struct bpf_load_and_run_opts opts = {}; + int err; + + opts.ctx = (struct bpf_loader_ctx *)skel; + opts.data_sz = 6008; + opts.data = (void *)"\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x9f\x01\0\ +\0\0\0\x18\0\0\0\0\0\0\x04\x1c\0\0\x04\x1c\0\0\x05\x18\0\0\0\0\x02\0\0\0\0\0\0\ +\x02\0\0\0\x01\x04\0\0\x02\0\0\0\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\ +\0\x04\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x08\0\0\0\0\x02\0\0\0\0\0\0\x0d\0\0\0\ +\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\x01\0\0\0\0\0\0\x04\x01\ +\0\0\x20\0\0\0\x24\x0c\0\0\x01\0\0\0\x05\0\0\0\xc2\x04\0\0\x03\0\0\0\x18\0\0\0\ +\xd0\0\0\0\x09\0\0\0\0\0\0\0\xd4\0\0\0\x0b\0\0\0\x40\0\0\0\xdf\0\0\0\x0b\0\0\0\ +\x80\0\0\0\0\x02\0\0\0\0\0\0\x0a\0\0\0\xe7\x07\0\0\0\0\0\0\0\0\0\0\xf0\x08\0\0\ +\0\0\0\0\x0c\0\0\0\xf6\x01\0\0\0\0\0\0\x08\0\0\0\x40\0\0\x01\xb3\x04\0\0\x03\0\ +\0\0\x18\0\0\x01\xbb\0\0\0\x0e\0\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x01\ +\xc3\0\0\0\x0e\0\0\0\xa0\0\0\x01\xcf\x08\0\0\0\0\0\0\x0f\0\0\x01\xd5\x01\0\0\0\ +\0\0\0\x04\0\0\0\x20\0\0\x01\xe2\x01\0\0\0\0\0\0\x01\x01\0\0\x08\0\0\0\0\x03\0\ +\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\x01\xe7\x01\0\0\0\0\0\0\x04\0\0\ +\0\x20\0\0\0\0\x02\0\0\0\0\0\0\x14\0\0\x02\x4b\x04\0\0\x02\0\0\0\x10\0\0\0\x13\ +\0\0\0\x03\0\0\0\0\0\0\x02\x5e\0\0\0\x15\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x18\ +\0\0\0\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x13\0\0\x02\x63\x0c\0\0\x01\0\0\ +\0\x16\0\0\x02\xaf\x04\0\0\x01\0\0\0\x08\0\0\x02\xb8\0\0\0\x19\0\0\0\0\0\0\0\0\ +\x02\0\0\0\0\0\0\x1a\0\0\x03\x09\x04\0\0\x06\0\0\0\x38\0\0\x01\xbb\0\0\0\x0e\0\ +\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x03\x16\0\0\0\x1b\0\0\0\xc0\0\0\x03\ +\x27\0\0\0\x15\0\0\x01\0\0\0\x03\x30\0\0\0\x1d\0\0\x01\x40\0\0\x03\x3a\0\0\0\ +\x1e\0\0\x01\x80\0\0\0\0\x02\0\0\0\0\0\0\x1c\0\0\0\0\x0a\0\0\0\0\0\0\x10\0\0\0\ +\0\x02\0\0\0\0\0\0\x1f\0\0\0\0\x02\0\0\0\0\0\0\x20\0\0\x03\x84\x04\0\0\x02\0\0\ +\0\x08\0\0\x03\x92\0\0\0\x0e\0\0\0\0\0\0\x03\x9b\0\0\0\x0e\0\0\0\x20\0\0\x03\ +\x3a\x04\0\0\x03\0\0\0\x18\0\0\x03\xa5\0\0\0\x1b\0\0\0\0\0\0\x03\xad\0\0\0\x21\ +\0\0\0\x40\0\0\x03\xb3\0\0\0\x23\0\0\0\x80\0\0\0\0\x02\0\0\0\0\0\0\x22\0\0\0\0\ +\x02\0\0\0\0\0\0\x24\0\0\x03\xb7\x04\0\0\x01\0\0\0\x04\0\0\x03\xc2\0\0\0\x0e\0\ +\0\0\0\0\0\x04\x2b\x04\0\0\x01\0\0\0\x04\0\0\x04\x34\0\0\0\x0e\0\0\0\0\0\0\0\0\ +\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\x04\xaa\x0e\0\0\0\0\0\0\ +\x25\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\x04\ +\xbe\x0e\0\0\0\0\0\0\x27\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\ +\0\0\0\x20\0\0\x04\xd4\x0e\0\0\0\0\0\0\x29\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\ +\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\x04\xe9\x0e\0\0\0\0\0\0\x2b\0\0\0\0\0\0\0\0\ +\x03\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\x05\0\x0e\0\0\0\0\0\0\x2d\ +\0\0\0\x01\0\0\x05\x08\x0f\0\0\x04\0\0\0\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\ +\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\ +\0\x11\0\0\x05\x10\x0f\0\0\x01\0\0\0\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\x62\x70\ +\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\ +\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ +\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\ +\x30\0\x2f\x68\x6f\x6d\x65\x2f\x69\x69\x69\x2f\x6c\x69\x6e\x75\x78\x2d\x6b\x65\ +\x72\x6e\x65\x6c\x2d\x74\x6f\x6f\x6c\x63\x68\x61\x69\x6e\x2f\x73\x72\x63\x2f\ +\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\ +\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\ +\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\ +\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\ +\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\ +\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\ +\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\ +\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\ +\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\ +\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\ +\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\ +\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\ +\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\ +\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\ +\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\ +\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\ +\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\ +\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\ +\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\ +\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\ +\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\ +\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\ +\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\ +\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\ +\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\ +\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\ +\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\ +\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\ +\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\ +\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\ +\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\ +\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\ +\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\ +\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\ +\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\ +\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\ +\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\ +\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\ +\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\ +\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\ +\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\ +\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\ +\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\ +\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\ +\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\ +\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\ +\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\ +\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\ +\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\ +\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\ +\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\ +\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\ +\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\ +\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\ +\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\ +\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\ +\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\ +\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x09\x4c\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x62\0\0\0\ +\x01\0\0\0\x80\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\ +\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\0\0\0\0\0\0\0\0\0\0\x20\ +\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\ +\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\ +\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x21\0\0\0\0\0\0\x79\x62\0\0\ +\0\0\0\0\x79\x71\0\x08\0\0\0\0\x15\x70\0\x1a\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\ +\x10\0\x08\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xe8\xbf\x16\0\0\ +\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x30\0\0\0\0\0\x23\xb7\x50\0\0\ +\0\0\0\0\x85\0\0\0\0\0\0\x7e\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xe8\0\0\0\0\xb7\ +\x10\0\0\0\0\0\x04\xbf\x27\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\0\x7b\xa2\xff\xf0\0\0\ +\0\0\x61\x17\0\x14\0\0\0\0\x7b\xa1\xff\xf8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\ +\0\0\xff\xff\xff\xe8\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x23\ +\xb7\x30\0\0\0\0\0\x0e\xb7\x50\0\0\0\0\0\x18\x85\0\0\0\0\0\0\x7e\xb7\0\0\0\0\0\ +\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x9a\0\x01\x3c\ +\x1e\0\0\0\x01\0\0\0\x42\0\0\0\x9a\0\x01\x3c\x24\0\0\0\x02\0\0\0\x42\0\0\x01\ +\x0d\0\x01\x44\x1d\0\0\0\x03\0\0\0\x42\0\0\x01\x2e\0\x01\x4c\x06\0\0\0\x04\0\0\ +\0\x42\0\0\x01\x3d\0\x01\x40\x1d\0\0\0\x05\0\0\0\x42\0\0\x01\x62\0\x01\x58\x06\ +\0\0\0\x07\0\0\0\x42\0\0\x01\x75\0\x01\x5c\x03\0\0\0\x0e\0\0\0\x42\0\0\x01\xfb\ +\0\x01\x64\x02\0\0\0\x1e\0\0\0\x42\0\0\x02\x49\0\x01\x6c\x01\0\0\0\0\0\0\0\x02\ +\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\ +\0\x01\x09\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\x01\x39\0\0\0\0\0\0\0\x70\0\0\0\x0d\ +\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\x01\x09\0\0\0\0\0\0\0\xa0\0\0\0\x0d\ +\0\0\x01\x39\0\0\0\0\0\0\0\x1a\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\ +\x6d\x61\x70\0\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\ +\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\ +\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x21\0\0\ +\0\0\0\0\x79\x62\0\0\0\0\0\0\x79\x11\0\x08\0\0\0\0\x15\x10\0\x3b\0\0\0\0\x79\ +\x71\0\0\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\x10\0\x08\0\0\0\0\xbf\x4a\0\0\0\0\0\ +\0\x07\x40\0\0\xff\xff\xff\xd0\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x31\xb7\x30\0\0\0\0\0\x20\xb7\x50\0\0\0\0\0\0\x85\0\0\0\0\0\0\x7e\x7b\ +\xa6\xff\xc8\0\0\0\0\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xd0\0\0\0\0\xb7\x30\0\0\0\ +\0\0\x04\xbf\x97\0\0\0\0\0\0\x0f\x93\0\0\0\0\0\0\x79\x17\0\x28\0\0\0\0\x79\x87\ +\0\x30\0\0\0\0\x15\x80\0\x18\0\0\0\0\xb7\x20\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\ +\x61\x11\0\x04\0\0\0\0\x79\x38\0\x08\0\0\0\0\x67\x10\0\0\0\0\0\x03\x0f\x31\0\0\ +\0\0\0\0\x79\x68\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf8\ +\xb7\x20\0\0\0\0\0\x08\x85\0\0\0\0\0\0\x71\xb7\x10\0\0\0\0\0\0\x79\x3a\xff\xf8\ +\0\0\0\0\x0f\x31\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf4\ +\xb7\x20\0\0\0\0\0\x04\x85\0\0\0\0\0\0\x71\xb7\x30\0\0\0\0\0\x04\x61\x1a\xff\ +\xf4\0\0\0\0\x61\x28\0\x10\0\0\0\0\x3d\x12\0\x02\0\0\0\0\x0f\x61\0\0\0\0\0\0\ +\xbf\x96\0\0\0\0\0\0\x7b\xa9\xff\xd8\0\0\0\0\x79\x17\0\x18\0\0\0\0\x7b\xa1\xff\ +\xe0\0\0\0\0\x79\x17\0\x20\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x13\0\0\0\0\0\0\x7b\ +\xa1\xff\xe8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xd0\x79\x1a\ +\xff\xc8\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x51\xb7\x30\0\0\0\0\0\x11\ +\xb7\x50\0\0\0\0\0\x20\x85\0\0\0\0\0\0\x7e\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x9a\0\x01\x80\x1e\0\0\0\x01\0\0\0\ +\x42\0\0\0\x9a\0\x01\x80\x24\0\0\0\x02\0\0\0\x42\0\0\x02\x7f\0\x01\x88\x1f\0\0\ +\0\x03\0\0\0\x42\0\0\x02\xa3\0\x01\x94\x06\0\0\0\x04\0\0\0\x42\0\0\x02\xbc\0\ +\x01\xa0\x0e\0\0\0\x05\0\0\0\x42\0\0\x01\x3d\0\x01\x84\x1d\0\0\0\x06\0\0\0\x42\ +\0\0\x01\x62\0\x01\xa4\x06\0\0\0\x08\0\0\0\x42\0\0\x02\xce\0\x01\xa8\x03\0\0\0\ +\x10\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x17\0\0\0\x42\0\0\x03\x79\0\x01\ +\x04\x06\0\0\0\x1a\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x1b\0\0\0\x42\0\0\ +\x03\xca\0\x01\x10\x0f\0\0\0\x1c\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x2d\0\0\0\x1e\ +\0\0\0\x42\0\0\x04\x16\0\x01\x0c\x0d\0\0\0\x20\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\ +\x02\0\0\0\x21\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x02\0\0\0\x24\0\0\0\x42\0\0\x04\ +\x3d\0\x01\x18\x0d\0\0\0\x27\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x28\0\0\ +\0\x42\0\0\x04\x3d\0\x01\x18\x0d\0\0\0\x2b\0\0\0\x42\0\0\x04\x3d\0\x01\x18\x0d\ +\0\0\0\x2c\0\0\0\x42\0\0\x04\x6b\0\x01\x1c\x1b\0\0\0\x2d\0\0\0\x42\0\0\x04\x6b\ +\0\x01\x1c\x06\0\0\0\x2e\0\0\0\x42\0\0\x04\x8e\0\x01\x24\x0d\0\0\0\x30\0\0\0\ +\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x3f\0\0\0\x42\0\0\x02\x49\0\x01\xc0\x01\0\ +\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\ +\x10\0\0\0\x14\0\0\x01\x09\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\ +\x28\0\0\0\x08\0\0\x01\x39\0\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\ +\x90\0\0\0\x1a\0\0\x01\x09\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\x03\x71\0\0\0\0\0\0\ +\0\xb0\0\0\0\x1a\0\0\x03\x75\0\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\x03\xa3\0\0\0\0\0\ +\0\0\xd8\0\0\0\x20\0\0\x01\x09\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\ +\0\x01\x18\0\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\x01\x50\0\0\0\x1a\0\0\x01\x09\0\0\0\ +\0\0\0\x01\x60\0\0\0\x20\0\0\x04\x65\0\0\0\0\0\0\x01\x88\0\0\0\x1a\0\0\x01\x39\ +\0\0\0\0\0\0\x01\x98\0\0\0\x1a\0\0\x04\xa6\0\0\0\0\0\0\x01\xa0\0\0\0\x18\0\0\0\ +\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\ +\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\x12\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\ +\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0"; + opts.insns_sz = 2216; + opts.insns = (void *)"\ +\xbf\x61\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\x78\xb7\x20\0\ +\0\0\0\0\x88\xb7\x30\0\0\0\0\0\0\x85\0\0\0\0\0\0\x71\x05\0\0\x14\0\0\0\0\x61\ +\x1a\xff\x78\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x7c\ +\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x80\0\0\0\0\xd5\ +\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x84\0\0\0\0\xd5\x10\0\x01\0\ +\0\0\0\x85\0\0\0\0\0\0\xa8\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\ +\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xbf\x07\0\0\ +\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0e\x68\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\ +\0\0\0\x0e\x64\x63\x10\0\0\0\0\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0e\x58\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x05\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0e\x50\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x12\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0e\x50\xb7\x30\0\0\0\0\0\x1c\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\xd4\0\0\0\0\x63\xa7\xff\x78\0\0\0\0\ +\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xa0\x63\x10\0\0\0\ +\0\0\0\x61\x06\0\x1c\0\0\0\0\x15\0\0\x03\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0e\x7c\x63\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\ +\0\0\x0e\x70\xb7\x30\0\0\0\0\0\x48\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\ +\x70\xff\xc3\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x17\0\0\0\0\0\0\ +\x79\x36\0\x20\0\0\0\0\x15\x30\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x0e\xb8\xb7\x20\0\0\0\0\0\x62\x61\x06\0\x04\0\0\0\0\x45\0\0\x02\0\0\0\x01\x85\ +\0\0\0\0\0\0\x94\x05\0\0\x01\0\0\0\0\x85\0\0\0\0\0\0\x71\x18\x26\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x28\x63\ +\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x20\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0f\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xb8\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x38\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x02\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x28\xb7\x30\0\0\0\0\0\x20\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x9f\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x48\x63\x10\ +\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\x16\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x48\xb7\ +\x30\0\0\0\0\0\x04\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x92\0\0\ +\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x50\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x11\x70\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x58\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x11\x68\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x10\x58\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xb0\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\x60\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xc0\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\xf0\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x11\xe0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xd8\x7b\x10\0\0\0\0\0\0\x61\x06\0\x08\0\0\ +\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x78\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\ +\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x7c\x63\x10\0\0\0\0\0\0\x79\x06\0\ +\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x80\x7b\x10\0\0\0\0\0\0\x61\ +\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xa8\x63\x10\0\0\0\0\0\ +\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xf0\xb7\x20\0\0\0\0\0\x11\xb7\x30\0\0\0\ +\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\0\0\0\0\0\0\xc5\x70\ +\xff\x5c\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x11\x60\x63\x07\0\x6c\0\0\0\0\ +\x77\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\xb7\x10\0\0\0\0\0\x05\x18\x26\0\0\ +\0\0\0\0\0\0\0\0\0\0\x11\x60\xb7\x30\0\0\0\0\0\x8c\x85\0\0\0\0\0\0\xa6\xbf\x70\ +\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x11\xd0\x61\x10\0\0\0\0\0\0\xd5\ +\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xc5\x70\xff\x4a\0\0\ +\0\0\x63\xa7\xff\x80\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x12\x08\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x16\xe0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x12\x10\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd8\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x18\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x20\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x20\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x15\ +\xb0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x50\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x48\x7b\x10\0\0\0\0\ +\0\0\x61\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xe8\x63\x10\0\0\ +\0\0\0\0\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xec\x63\x10\ +\0\0\0\0\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xf0\x7b\ +\x10\0\0\0\0\0\0\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\ +\x18\x63\x10\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x60\xb7\x20\0\0\0\ +\0\0\x12\xb7\x30\0\0\0\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\ +\0\0\0\0\0\0\xc5\x70\xff\x13\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd0\ +\x63\x07\0\x6c\0\0\0\0\x77\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\xb7\x10\0\0\ +\0\0\0\x05\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd0\xb7\x30\0\0\0\0\0\x8c\x85\0\ +\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x17\x40\x61\ +\x10\0\0\0\0\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\ +\xc5\x70\xff\x01\0\0\0\0\x63\xa7\xff\x84\0\0\0\0\x61\x1a\xff\x78\0\0\0\0\xd5\ +\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x0a\xff\x80\0\0\ +\0\0\x63\x60\0\x28\0\0\0\0\x61\x0a\xff\x84\0\0\0\0\x63\x60\0\x2c\0\0\0\0\x18\ +\x16\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\0\0\x63\x60\0\x18\0\0\0\0\xb7\ +\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0"; + err = bpf_load_and_run(&opts); + if (err < 0) + return err; + return 0; +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *skel; + + skel = iterators_bpf__open(); + if (!skel) + return NULL; + if (iterators_bpf__load(skel)) { + iterators_bpf__destroy(skel); + return NULL; + } + return skel; +} + +__attribute__((unused)) static void +iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused))) +{ +#ifdef __cplusplus +#define _Static_assert static_assert +#endif +#ifdef __cplusplus +#undef _Static_assert +#endif +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/preload/iterators/iterators.lskel.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h index 70f236a82fe1..70f236a82fe1 100644 --- a/kernel/bpf/preload/iterators/iterators.lskel.h +++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 80f4b4d88aaf..8732e0aadf36 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -269,7 +269,7 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; } else { - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -290,7 +290,7 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma */ return -EPERM; } else { - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 64131f88c553..adc83cb82f37 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -181,7 +181,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, int err; /* Need to create a kthread, thus must support schedule */ - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(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_STRUCT_OPS) { @@ -238,7 +238,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, void *ptr; int err; - if (bpf_map_is_dev_bound(map)) + if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); @@ -309,7 +309,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; + gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; @@ -390,7 +390,7 @@ static int bpf_map_alloc_id(struct bpf_map *map) return id > 0 ? 0 : id; } -void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; @@ -402,18 +402,12 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) if (!map->id) return; - if (do_idr_lock) - spin_lock_irqsave(&map_idr_lock, flags); - else - __acquire(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; - if (do_idr_lock) - spin_unlock_irqrestore(&map_idr_lock, flags); - else - __release(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG_KMEM @@ -424,7 +418,8 @@ static void bpf_map_save_memcg(struct bpf_map *map) * So we have to check map->objcg for being NULL each time it's * being used. */ - map->objcg = get_obj_cgroup_from_current(); + if (memcg_bpf_enabled()) + map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) @@ -470,6 +465,21 @@ void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) return ptr; } +void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, + gfp_t flags) +{ + struct mem_cgroup *memcg, *old_memcg; + void *ptr; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); + ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); + + return ptr; +} + void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { @@ -527,9 +537,6 @@ void btf_record_free(struct btf_record *rec) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: if (rec->fields[i].kptr.module) @@ -538,7 +545,11 @@ void btf_record_free(struct btf_record *rec) break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to release for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + /* Nothing to release */ break; default: WARN_ON_ONCE(1); @@ -571,9 +582,6 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { - case BPF_SPIN_LOCK: - case BPF_TIMER: - break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: btf_get(fields[i].kptr.btf); @@ -584,7 +592,11 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) break; case BPF_LIST_HEAD: case BPF_LIST_NODE: - /* Nothing to acquire for bpf_list_head */ + case BPF_RB_ROOT: + case BPF_RB_NODE: + case BPF_SPIN_LOCK: + case BPF_TIMER: + /* Nothing to acquire */ break; default: ret = -EFAULT; @@ -664,7 +676,13 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; + case BPF_RB_ROOT: + if (WARN_ON_ONCE(rec->spin_lock_off < 0)) + continue; + bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); + break; case BPF_LIST_NODE: + case BPF_RB_NODE: break; default: WARN_ON_ONCE(1); @@ -706,13 +724,13 @@ static void bpf_map_put_uref(struct bpf_map *map) } /* decrement map refcnt and schedule it for freeing via workqueue - * (unrelying map implementation ops->map_free() might sleep) + * (underlying map implementation ops->map_free() might sleep) */ -static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) +void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ - bpf_map_free_id(map, do_idr_lock); + bpf_map_free_id(map); btf_put(map->btf); INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend @@ -721,11 +739,6 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) queue_work(system_unbound_wq, &map->work); } } - -void bpf_map_put(struct bpf_map *map) -{ - __bpf_map_put(map, true); -} EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) @@ -882,10 +895,10 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; - vma->vm_flags &= ~VM_MAYEXEC; + vm_flags_clear(vma, VM_MAYEXEC); if (!(vma->vm_flags & VM_WRITE)) /* disallow re-mapping with PROT_WRITE */ - vma->vm_flags &= ~VM_MAYWRITE; + vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) @@ -1005,7 +1018,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return -EINVAL; map->record = btf_parse_fields(btf, value_type, - BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD, + BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | + BPF_RB_ROOT, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1053,6 +1067,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, } break; case BPF_LIST_HEAD: + case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { @@ -1483,7 +1498,7 @@ static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) goto err_put; } - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || @@ -1547,7 +1562,7 @@ static int map_get_next_key(union bpf_attr *attr) if (!next_key) goto free_key; - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } @@ -1605,7 +1620,7 @@ int generic_map_delete_batch(struct bpf_map *map, map->key_size)) break; - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } @@ -1851,7 +1866,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { - if (!bpf_map_is_dev_bound(map)) { + if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); @@ -1944,7 +1959,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) if (!ops) return -EINVAL; - if (!bpf_prog_is_dev_bound(prog->aux)) + if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; @@ -1972,7 +1987,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) return; if (audit_enabled == AUDIT_OFF) return; - if (op == BPF_AUDIT_LOAD) + if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) @@ -2001,7 +2016,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog) return id > 0 ? 0 : id; } -void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) +void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; @@ -2013,18 +2028,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) if (!prog->aux->id) return; - if (do_idr_lock) - spin_lock_irqsave(&prog_idr_lock, flags); - else - __acquire(&prog_idr_lock); - + spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; - - if (do_idr_lock) - spin_unlock_irqrestore(&prog_idr_lock, flags); - else - __release(&prog_idr_lock); + spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) @@ -2067,17 +2074,15 @@ static void bpf_prog_put_deferred(struct work_struct *work) prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } -static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) +static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { - /* bpf_prog_free_id() must be called first */ - bpf_prog_free_id(prog, do_idr_lock); - if (in_irq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); @@ -2089,7 +2094,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) void bpf_prog_put(struct bpf_prog *prog) { - __bpf_prog_put(prog, true); + __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); @@ -2255,7 +2260,7 @@ bool bpf_prog_get_ok(struct bpf_prog *prog, if (prog->type != *attach_type) return false; - if (bpf_prog_is_dev_bound(prog->aux) && !attach_drv) + if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; @@ -2491,7 +2496,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | - BPF_F_XDP_HAS_FRAGS)) + BPF_F_XDP_HAS_FRAGS | + BPF_F_XDP_DEV_BOUND_ONLY)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2575,7 +2581,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; - prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; @@ -2599,7 +2605,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->gpl_compatible = is_gpl ? 1 : 0; if (bpf_prog_is_dev_bound(prog->aux)) { - err = bpf_prog_offload_init(prog, attr); + err = bpf_prog_dev_bound_init(prog, attr); + if (err) + goto free_prog_sec; + } + + if (type == BPF_PROG_TYPE_EXT && dst_prog && + bpf_prog_is_dev_bound(dst_prog->aux)) { + err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) goto free_prog_sec; } @@ -3997,7 +4010,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, return -EFAULT; } - if (bpf_prog_is_dev_bound(prog->aux)) { + if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; @@ -4225,7 +4238,7 @@ static int bpf_map_get_info_by_fd(struct file *file, } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; - if (bpf_map_is_dev_bound(map)) { + if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; @@ -5319,7 +5332,6 @@ static struct ctl_table bpf_syscall_table[] = { { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, - .maxlen = sizeof(bpf_stats_enabled_key), .mode = 0644, .proc_handler = bpf_stats_handler, }, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 85f96c1e9f62..272563a0b770 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -190,6 +190,10 @@ struct bpf_verifier_stack_elem { static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx); static int release_reference(struct bpf_verifier_env *env, int ref_obj_id); +static void invalidate_non_owning_refs(struct bpf_verifier_env *env); +static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env); +static int ref_set_non_owning(struct bpf_verifier_env *env, + struct bpf_reg_state *reg); static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux) { @@ -255,6 +259,7 @@ struct bpf_call_arg_meta { int mem_size; u64 msize_max_value; int ref_obj_id; + int dynptr_id; int map_uid; int func_id; struct btf *btf; @@ -456,6 +461,11 @@ static bool type_is_ptr_alloc_obj(u32 type) return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC; } +static bool type_is_non_owning_ref(u32 type) +{ + return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF; +} + static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg) { struct btf_record *rec = NULL; @@ -638,31 +648,57 @@ static void print_liveness(struct bpf_verifier_env *env, verbose(env, "D"); } -static int get_spi(s32 off) +static int __get_spi(s32 off) { return (-off - 1) / BPF_REG_SIZE; } +static struct bpf_func_state *func(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg) +{ + struct bpf_verifier_state *cur = env->cur_state; + + return cur->frame[reg->frameno]; +} + static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots) { - int allocated_slots = state->allocated_stack / BPF_REG_SIZE; + int allocated_slots = state->allocated_stack / BPF_REG_SIZE; - /* We need to check that slots between [spi - nr_slots + 1, spi] are - * within [0, allocated_stack). - * - * Please note that the spi grows downwards. For example, a dynptr - * takes the size of two stack slots; the first slot will be at - * spi and the second slot will be at spi - 1. - */ - return spi - nr_slots + 1 >= 0 && spi < allocated_slots; + /* We need to check that slots between [spi - nr_slots + 1, spi] are + * within [0, allocated_stack). + * + * Please note that the spi grows downwards. For example, a dynptr + * takes the size of two stack slots; the first slot will be at + * spi and the second slot will be at spi - 1. + */ + return spi - nr_slots + 1 >= 0 && spi < allocated_slots; } -static struct bpf_func_state *func(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg) +static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - struct bpf_verifier_state *cur = env->cur_state; + int off, spi; - return cur->frame[reg->frameno]; + if (!tnum_is_const(reg->var_off)) { + verbose(env, "dynptr has to be at a constant offset\n"); + return -EINVAL; + } + + off = reg->off + reg->var_off.value; + if (off % BPF_REG_SIZE) { + verbose(env, "cannot pass in dynptr at an offset=%d\n", off); + return -EINVAL; + } + + spi = __get_spi(off); + if (spi < 1) { + verbose(env, "cannot pass in dynptr at an offset=%d\n", off); + return -EINVAL; + } + + if (!is_spi_bounds_valid(func(env, reg), spi, BPF_DYNPTR_NR_SLOTS)) + return -ERANGE; + return spi; } static const char *kernel_type_name(const struct btf* btf, u32 id) @@ -727,37 +763,58 @@ static bool dynptr_type_refcounted(enum bpf_dynptr_type type) static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, - bool first_slot); + bool first_slot, int dynptr_id); static void __mark_reg_not_init(const struct bpf_verifier_env *env, struct bpf_reg_state *reg); -static void mark_dynptr_stack_regs(struct bpf_reg_state *sreg1, +static void mark_dynptr_stack_regs(struct bpf_verifier_env *env, + struct bpf_reg_state *sreg1, struct bpf_reg_state *sreg2, enum bpf_dynptr_type type) { - __mark_dynptr_reg(sreg1, type, true); - __mark_dynptr_reg(sreg2, type, false); + int id = ++env->id_gen; + + __mark_dynptr_reg(sreg1, type, true, id); + __mark_dynptr_reg(sreg2, type, false, id); } -static void mark_dynptr_cb_reg(struct bpf_reg_state *reg, +static void mark_dynptr_cb_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, enum bpf_dynptr_type type) { - __mark_dynptr_reg(reg, type, true); + __mark_dynptr_reg(reg, type, true, ++env->id_gen); } +static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi); static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx) { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type type; - int spi, i, id; - - spi = get_spi(reg->off); - - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) - return -EINVAL; + int spi, i, id, err; + + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + + /* We cannot assume both spi and spi - 1 belong to the same dynptr, + * hence we need to call destroy_if_dynptr_stack_slot twice for both, + * to ensure that for the following example: + * [d1][d1][d2][d2] + * spi 3 2 1 0 + * So marking spi = 2 should lead to destruction of both d1 and d2. In + * case they do belong to same dynptr, second call won't see slot_type + * as STACK_DYNPTR and will simply skip destruction. + */ + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + err = destroy_if_dynptr_stack_slot(env, state, spi - 1); + if (err) + return err; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_DYNPTR; @@ -768,7 +825,7 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; - mark_dynptr_stack_regs(&state->stack[spi].spilled_ptr, + mark_dynptr_stack_regs(env, &state->stack[spi].spilled_ptr, &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { @@ -781,6 +838,9 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; + return 0; } @@ -789,10 +849,9 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re struct bpf_func_state *state = func(env, reg); int spi, i; - spi = get_spi(reg->off); - - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) - return -EINVAL; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; for (i = 0; i < BPF_REG_SIZE; i++) { state->stack[spi].slot_type[i] = STACK_INVALID; @@ -805,43 +864,133 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); + + /* Why do we need to set REG_LIVE_WRITTEN for STACK_INVALID slot? + * + * While we don't allow reading STACK_INVALID, it is still possible to + * do <8 byte writes marking some but not all slots as STACK_MISC. Then, + * helpers or insns can do partial read of that part without failing, + * but check_stack_range_initialized, check_stack_read_var_off, and + * check_stack_read_fixed_off will do mark_reg_read for all 8-bytes of + * the slot conservatively. Hence we need to prevent those liveness + * marking walks. + * + * This was not a problem before because STACK_INVALID is only set by + * default (where the default reg state has its reg->parent as NULL), or + * in clean_live_states after REG_LIVE_DONE (at which point + * mark_reg_read won't walk reg->parent chain), but not randomly during + * verifier state exploration (like we did above). Hence, for our case + * parentage chain will still be live (i.e. reg->parent may be + * non-NULL), while earlier reg->parent was NULL, so we need + * REG_LIVE_WRITTEN to screen off read marker propagation when it is + * done later on reads or by mark_dynptr_read as well to unnecessary + * mark registers in verifier state. + */ + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; + return 0; } -static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); + +static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env, + struct bpf_func_state *state, int spi) { - struct bpf_func_state *state = func(env, reg); - int spi, i; + struct bpf_func_state *fstate; + struct bpf_reg_state *dreg; + int i, dynptr_id; - if (reg->type == CONST_PTR_TO_DYNPTR) - return false; + /* We always ensure that STACK_DYNPTR is never set partially, + * hence just checking for slot_type[0] is enough. This is + * different for STACK_SPILL, where it may be only set for + * 1 byte, so code has to use is_spilled_reg. + */ + if (state->stack[spi].slot_type[0] != STACK_DYNPTR) + return 0; - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) - return true; + /* Reposition spi to first slot */ + if (!state->stack[spi].spilled_ptr.dynptr.first_slot) + spi = spi + 1; + if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { + verbose(env, "cannot overwrite referenced dynptr\n"); + return -EINVAL; + } + + mark_stack_slot_scratched(env, spi); + mark_stack_slot_scratched(env, spi - 1); + + /* Writing partially to one dynptr stack slot destroys both. */ for (i = 0; i < BPF_REG_SIZE; i++) { - if (state->stack[spi].slot_type[i] == STACK_DYNPTR || - state->stack[spi - 1].slot_type[i] == STACK_DYNPTR) - return false; + state->stack[spi].slot_type[i] = STACK_INVALID; + state->stack[spi - 1].slot_type[i] = STACK_INVALID; } + dynptr_id = state->stack[spi].spilled_ptr.id; + /* Invalidate any slices associated with this dynptr */ + bpf_for_each_reg_in_vstate(env->cur_state, fstate, dreg, ({ + /* Dynptr slices are only PTR_TO_MEM_OR_NULL and PTR_TO_MEM */ + if (dreg->type != (PTR_TO_MEM | PTR_MAYBE_NULL) && dreg->type != PTR_TO_MEM) + continue; + if (dreg->dynptr_id == dynptr_id) { + if (!env->allow_ptr_leaks) + __mark_reg_not_init(env, dreg); + else + __mark_reg_unknown(env, dreg); + } + })); + + /* Do not release reference state, we are destroying dynptr on stack, + * not using some helper to release it. Just reset register. + */ + __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); + __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); + + /* Same reason as unmark_stack_slots_dynptr above */ + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; + state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN; + + return 0; +} + +static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi) +{ + if (reg->type == CONST_PTR_TO_DYNPTR) + return false; + + /* For -ERANGE (i.e. spi not falling into allocated stack slots), we + * will do check_mem_access to check and update stack bounds later, so + * return true for that case. + */ + if (spi < 0) + return spi == -ERANGE; + /* We allow overwriting existing unreferenced STACK_DYNPTR slots, see + * mark_stack_slots_dynptr which calls destroy_if_dynptr_stack_slot to + * ensure dynptr objects at the slots we are touching are completely + * destructed before we reinitialize them for a new one. For referenced + * ones, destroy_if_dynptr_stack_slot returns an error early instead of + * delaying it until the end where the user will get "Unreleased + * reference" error. + */ return true; } -static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, + int spi) { struct bpf_func_state *state = func(env, reg); - int spi; int i; /* This already represents first slot of initialized bpf_dynptr */ if (reg->type == CONST_PTR_TO_DYNPTR) return true; - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.dynptr.first_slot) + if (spi < 0) + return false; + if (!state->stack[spi].spilled_ptr.dynptr.first_slot) return false; for (i = 0; i < BPF_REG_SIZE; i++) { @@ -868,7 +1017,9 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg if (reg->type == CONST_PTR_TO_DYNPTR) { return reg->dynptr.type == dynptr_type; } else { - spi = get_spi(reg->off); + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return false; return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; } } @@ -931,6 +1082,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose_a("id=%d", reg->id); if (reg->ref_obj_id) verbose_a("ref_obj_id=%d", reg->ref_obj_id); + if (type_is_non_owning_ref(reg->type)) + verbose_a("%s", "non_own_ref"); if (t != SCALAR_VALUE) verbose_a("off=%d", reg->off); if (type_is_pkt_pointer(t)) @@ -1404,9 +1557,11 @@ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) */ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) { - /* Clear id, off, and union(map_ptr, range) */ + /* Clear off and union(map_ptr, range) */ memset(((u8 *)reg) + sizeof(reg->type), 0, offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type)); + reg->id = 0; + reg->ref_obj_id = 0; ___mark_reg_known(reg, imm); } @@ -1447,7 +1602,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, } static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, - bool first_slot) + bool first_slot, int dynptr_id) { /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply @@ -1455,6 +1610,8 @@ static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type ty */ __mark_reg_known_zero(reg); reg->type = CONST_PTR_TO_DYNPTR; + /* Give each dynptr a unique id to uniquely associate slices to it. */ + reg->id = dynptr_id; reg->dynptr.type = type; reg->dynptr.first_slot = first_slot; } @@ -1486,6 +1643,16 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) reg->type &= ~PTR_MAYBE_NULL; } +static void mark_reg_graph_node(struct bpf_reg_state *regs, u32 regno, + struct btf_field_graph_root *ds_head) +{ + __mark_reg_known_zero(®s[regno]); + regs[regno].type = PTR_TO_BTF_ID | MEM_ALLOC; + regs[regno].btf = ds_head->btf; + regs[regno].btf_id = ds_head->value_btf_id; + regs[regno].off = ds_head->node_offset; +} + static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) { return type_is_pkt_pointer(reg->type); @@ -1752,11 +1919,13 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env, struct bpf_reg_state *reg) { /* - * Clear type, id, off, and union(map_ptr, range) and + * Clear type, off, and union(map_ptr, range) and * padding between 'type' and union */ memset(reg, 0, offsetof(struct bpf_reg_state, var_off)); reg->type = SCALAR_VALUE; + reg->id = 0; + reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; reg->precise = !env->bpf_capable; @@ -2185,6 +2354,12 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) return -EINVAL; } + if (bpf_dev_bound_kfunc_id(func_id)) { + err = bpf_dev_bound_kfunc_check(&env->log, prog_aux); + if (err) + return err; + } + desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; desc->imm = call_imm; @@ -2386,6 +2561,32 @@ static int mark_reg_read(struct bpf_verifier_env *env, return 0; } +static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi, ret; + + /* For CONST_PTR_TO_DYNPTR, it must have already been done by + * check_reg_arg in check_helper_call and mark_btf_func_reg_size in + * check_kfunc_call. + */ + if (reg->type == CONST_PTR_TO_DYNPTR) + return 0; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + /* Caller ensures dynptr is valid and initialized, which means spi is in + * bounds and spi is the first dynptr slot. Simply mark stack slot as + * read. + */ + ret = mark_reg_read(env, &state->stack[spi].spilled_ptr, + state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64); + if (ret) + return ret; + return mark_reg_read(env, &state->stack[spi - 1].spilled_ptr, + state->stack[spi - 1].spilled_ptr.parent, REG_LIVE_READ64); +} + /* This function is supposed to be used by the following 32-bit optimization * code only. It returns TRUE if the source or destination register operates * on 64-bit, otherwise return FALSE. @@ -2748,6 +2949,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg == 0 && is_callback_calling_function(insn->imm)) return -ENOTSUPP; + /* kfunc with imm==0 is invalid and fixup_kfunc_call will + * catch this error later. Make backtracking conservative + * with ENOTSUPP. + */ + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) + return -ENOTSUPP; /* regular helper call sets R0 */ *reg_mask &= ~1; if (*reg_mask & 0x3f) { @@ -3237,13 +3444,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; + copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; @@ -3255,6 +3473,11 @@ static void save_register_state(struct bpf_func_state *state, scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]); } +static bool is_bpf_st_mem(struct bpf_insn *insn) +{ + return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -3266,8 +3489,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, { struct bpf_func_state *cur; /* state of the current function */ int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; - u32 dst_reg = env->prog->insnsi[insn_idx].dst_reg; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; struct bpf_reg_state *reg = NULL; + u32 dst_reg = insn->dst_reg; err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE)); if (err) @@ -3289,7 +3513,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } @@ -3299,6 +3525,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { @@ -3314,6 +3544,13 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; } save_register_state(state, spi, reg, size); + } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && + insn->imm != 0 && env->bpf_capable) { + struct bpf_reg_state fake_reg = {}; + + __mark_reg_known(&fake_reg, (u32)insn->imm); + fake_reg.type = SCALAR_VALUE; + save_register_state(state, spi, &fake_reg, size); } else if (reg && is_spillable_regtype(reg->type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { @@ -3348,7 +3585,8 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; /* when we zero initialize stack slots mark them as such */ - if (reg && register_is_null(reg)) { + if ((reg && register_is_null(reg)) || + (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) { /* backtracking doesn't work for STACK_ZERO yet. */ err = mark_chain_precision(env, value_regno); if (err) @@ -3393,6 +3631,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, int min_off, max_off; int i, err; struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL; + struct bpf_insn *insn = &env->prog->insnsi[insn_idx]; bool writing_zero = false; /* set if the fact that we're writing a zero is used to let any * stack slots remain STACK_ZERO @@ -3405,13 +3644,22 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, max_off = ptr_reg->smax_value + off + size; if (value_regno >= 0) value_reg = &cur->regs[value_regno]; - if (value_reg && register_is_null(value_reg)) + if ((value_reg && register_is_null(value_reg)) || + (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0)) writing_zero = true; err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE)); if (err) return err; + for (i = min_off; i < max_off; i++) { + int spi; + + spi = __get_spi(i); + err = destroy_if_dynptr_stack_slot(env, state, spi); + if (err) + return err; + } /* Variable offset writes destroy any spilled pointers in range. */ for (i = min_off; i < max_off; i++) { @@ -3569,7 +3817,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { @@ -3590,7 +3838,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -4751,6 +4999,25 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) return 0; } +#define BTF_TYPE_SAFE_NESTED(__type) __PASTE(__type, __safe_fields) + +BTF_TYPE_SAFE_NESTED(struct task_struct) { + const cpumask_t *cpus_ptr; +}; + +static bool nested_ptr_is_trusted(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, + int off) +{ + /* If its parent is not trusted, it can't regain its trusted status. */ + if (!is_trusted_reg(reg)) + return false; + + BTF_TYPE_EMIT(BTF_TYPE_SAFE_NESTED(struct task_struct)); + + return btf_nested_type_is_trusted(&env->log, reg, off); +} + static int check_ptr_to_btf_access(struct bpf_verifier_env *env, struct bpf_reg_state *regs, int regno, int off, int size, @@ -4822,7 +5089,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, return -EACCES; } - if (type_is_alloc(reg->type) && !reg->ref_obj_id) { + if (type_is_alloc(reg->type) && !type_is_non_owning_ref(reg->type) && + !reg->ref_obj_id) { verbose(env, "verifier internal error: ref_obj_id for allocated object must be non-zero\n"); return -EFAULT; } @@ -4839,10 +5107,17 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, if (type_flag(reg->type) & PTR_UNTRUSTED) flag |= PTR_UNTRUSTED; - /* By default any pointer obtained from walking a trusted pointer is - * no longer trusted except the rcu case below. + /* By default any pointer obtained from walking a trusted pointer is no + * longer trusted, unless the field being accessed has explicitly been + * marked as inheriting its parent's state of trust. + * + * An RCU-protected pointer can also be deemed trusted if we are in an + * RCU read region. This case is handled below. */ - flag &= ~PTR_TRUSTED; + if (nested_ptr_is_trusted(env, reg, off)) + flag |= PTR_TRUSTED; + else + flag &= ~PTR_TRUSTED; if (flag & MEM_RCU) { /* Mark value register as MEM_RCU only if it is protected by @@ -5439,6 +5714,31 @@ static int check_stack_range_initialized( } if (meta && meta->raw_mode) { + /* Ensure we won't be overwriting dynptrs when simulating byte + * by byte access in check_helper_call using meta.access_size. + * This would be a problem if we have a helper in the future + * which takes: + * + * helper(uninit_mem, len, dynptr) + * + * Now, uninint_mem may overlap with dynptr pointer. Hence, it + * may end up writing to dynptr itself when touching memory from + * arg 1. This can be relaxed on a case by case basis for known + * safe cases, but reject due to the possibilitiy of aliasing by + * default. + */ + for (i = min_off; i < max_off + access_size; i++) { + int stack_off = -i - 1; + + spi = __get_spi(i); + /* raw_mode may write past allocated_stack */ + if (state->allocated_stack <= stack_off) + continue; + if (state->stack[spi].slot_type[stack_off % BPF_REG_SIZE] == STACK_DYNPTR) { + verbose(env, "potential write to dynptr at off=%d disallowed\n", i); + return -EACCES; + } + } meta->access_size = access_size; meta->regno = regno; return 0; @@ -5780,9 +6080,7 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, cur->active_lock.ptr = btf; cur->active_lock.id = reg->id; } else { - struct bpf_func_state *fstate = cur_func(env); void *ptr; - int i; if (map) ptr = map; @@ -5798,25 +6096,11 @@ static int process_spin_lock(struct bpf_verifier_env *env, int regno, verbose(env, "bpf_spin_unlock of different lock\n"); return -EINVAL; } - cur->active_lock.ptr = NULL; - cur->active_lock.id = 0; - for (i = fstate->acquired_refs - 1; i >= 0; i--) { - int err; + invalidate_non_owning_refs(env); - /* Complain on error because this reference state cannot - * be freed before this point, as bpf_spin_lock critical - * section does not allow functions that release the - * allocated object immediately. - */ - if (!fstate->refs[i].release_on_unlock) - continue; - err = release_reference(env, fstate->refs[i].id); - if (err) { - verbose(env, "failed to release release_on_unlock reference"); - return err; - } - } + cur->active_lock.ptr = NULL; + cur->active_lock.id = 0; } return 0; } @@ -5926,6 +6210,7 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + int spi = 0; /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): @@ -5936,12 +6221,14 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, } /* CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to * check_func_arg_reg_off's logic. We only need to check offset - * alignment for PTR_TO_STACK. + * and its alignment for PTR_TO_STACK. */ - if (reg->type == PTR_TO_STACK && (reg->off % BPF_REG_SIZE)) { - verbose(env, "cannot pass in dynptr at an offset=%d\n", reg->off); - return -EINVAL; + if (reg->type == PTR_TO_STACK) { + spi = dynptr_get_spi(env, reg); + if (spi < 0 && spi != -ERANGE) + return spi; } + /* MEM_UNINIT - Points to memory that is an appropriate candidate for * constructing a mutable bpf_dynptr object. * @@ -5958,7 +6245,7 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, * to. */ if (arg_type & MEM_UNINIT) { - if (!is_dynptr_reg_valid_uninit(env, reg)) { + if (!is_dynptr_reg_valid_uninit(env, reg, spi)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); return -EINVAL; } @@ -5973,13 +6260,15 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, meta->uninit_dynptr_regno = regno; } else /* MEM_RDONLY and None case from above */ { + int err; + /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); return -EINVAL; } - if (!is_dynptr_reg_valid_init(env, reg)) { + if (!is_dynptr_reg_valid_init(env, reg, spi)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", regno); @@ -6006,6 +6295,10 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, err_extra, regno); return -EINVAL; } + + err = mark_dynptr_read(env, reg); + if (err) + return err; } return 0; } @@ -6275,6 +6568,23 @@ found: return 0; } +static struct btf_field * +reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields) +{ + struct btf_field *field; + struct btf_record *rec; + + rec = reg_btf_record(reg); + if (!rec) + return NULL; + + field = btf_record_find(rec, off, fields); + if (!field) + return NULL; + + return field; +} + int check_func_arg_reg_off(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, int regno, enum bpf_arg_type arg_type) @@ -6296,6 +6606,18 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, */ if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK) return 0; + + if ((type_is_ptr_alloc_obj(type) || type_is_non_owning_ref(type)) && reg->off) { + if (reg_find_field_offset(reg, reg->off, BPF_GRAPH_NODE_OR_ROOT)) + return __check_ptr_off_reg(env, reg, regno, true); + + verbose(env, "R%d must have zero offset when passed to release func\n", + regno); + verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno, + kernel_type_name(reg->btf, reg->btf_id), reg->off); + return -EINVAL; + } + /* Doing check_ptr_off_reg check for the offset will catch this * because fixed_off_ok is false, but checking here allows us * to give the user a better error message. @@ -6330,6 +6652,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_BTF_ID | PTR_TRUSTED: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED: + case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF: /* When referenced PTR_TO_BTF_ID is passed to release function, * its fixed offset must be 0. In the other cases, fixed offset * can be non-zero. This was already checked above. So pass @@ -6343,15 +6666,29 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, } } -static u32 dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static int dynptr_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); int spi; if (reg->type == CONST_PTR_TO_DYNPTR) - return reg->ref_obj_id; + return reg->id; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; + return state->stack[spi].spilled_ptr.id; +} - spi = get_spi(reg->off); +static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +{ + struct bpf_func_state *state = func(env, reg); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->ref_obj_id; + spi = dynptr_get_spi(env, reg); + if (spi < 0) + return spi; return state->stack[spi].spilled_ptr.ref_obj_id; } @@ -6425,9 +6762,8 @@ skip_type_check: * PTR_TO_STACK. */ if (reg->type == PTR_TO_STACK) { - spi = get_spi(reg->off); - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.ref_obj_id) { + spi = dynptr_get_spi(env, reg); + if (spi < 0 || !state->stack[spi].spilled_ptr.ref_obj_id) { verbose(env, "arg %d is an unacquired reference\n", regno); return -EINVAL; } @@ -6528,6 +6864,10 @@ skip_type_check: meta->ret_btf_id = reg->btf_id; break; case ARG_PTR_TO_SPIN_LOCK: + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "can't spin_{lock,unlock} in rbtree cb\n"); + return -EACCES; + } if (meta->func_id == BPF_FUNC_spin_lock) { err = process_spin_lock(env, regno, true); if (err) @@ -7079,6 +7419,17 @@ static int release_reference(struct bpf_verifier_env *env, return 0; } +static void invalidate_non_owning_refs(struct bpf_verifier_env *env) +{ + struct bpf_func_state *unused; + struct bpf_reg_state *reg; + + bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ + if (type_is_non_owning_ref(reg->type)) + __mark_reg_unknown(env, reg); + })); +} + static void clear_caller_saved_regs(struct bpf_verifier_env *env, struct bpf_reg_state *regs) { @@ -7100,6 +7451,8 @@ static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); +static bool is_callback_calling_kfunc(u32 btf_id); + static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx, int subprog, set_callee_state_fn set_callee_state_cb) @@ -7154,10 +7507,18 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn * interested in validating only BPF helpers that can call subprogs as * callbacks */ - if (set_callee_state_cb != set_callee_state && !is_callback_calling_function(insn->imm)) { - verbose(env, "verifier bug: helper %s#%d is not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); - return -EFAULT; + if (set_callee_state_cb != set_callee_state) { + if (bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_kfunc(insn->imm)) { + verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } else if (!bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_function(insn->imm)) { /* helper */ + verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } } if (insn->code == (BPF_JMP | BPF_CALL) && @@ -7409,7 +7770,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); - mark_dynptr_cb_reg(&callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); + mark_dynptr_cb_reg(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ @@ -7422,6 +7783,63 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_rbtree_add_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* void bpf_rbtree_add(struct bpf_rb_root *root, struct bpf_rb_node *node, + * bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b)); + * + * 'struct bpf_rb_node *node' arg to bpf_rbtree_add is the same PTR_TO_BTF_ID w/ offset + * that 'less' callback args will be receiving. However, 'node' arg was release_reference'd + * by this point, so look at 'root' + */ + struct btf_field *field; + + field = reg_find_field_offset(&caller->regs[BPF_REG_1], caller->regs[BPF_REG_1].off, + BPF_RB_ROOT); + if (!field || !field->graph_root.value_btf_id) + return -EFAULT; + + mark_reg_graph_node(callee->regs, BPF_REG_1, &field->graph_root); + ref_set_non_owning(env, &callee->regs[BPF_REG_1]); + mark_reg_graph_node(callee->regs, BPF_REG_2, &field->graph_root); + ref_set_non_owning(env, &callee->regs[BPF_REG_2]); + + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_callback_fn = true; + callee->callback_ret_range = tnum_range(0, 1); + return 0; +} + +static bool is_rbtree_lock_required_kfunc(u32 btf_id); + +/* Are we currently verifying the callback for a rbtree helper that must + * be called with lock held? If so, no need to complain about unreleased + * lock + */ +static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_insn *insn = env->prog->insnsi; + struct bpf_func_state *callee; + int kfunc_btf_id; + + if (!state->curframe) + return false; + + callee = state->frame[state->curframe]; + + if (!callee->in_callback_fn) + return false; + + kfunc_btf_id = insn[callee->callsite].imm; + return is_rbtree_lock_required_kfunc(kfunc_btf_id); +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -7614,6 +8032,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, struct bpf_reg_state *fmt_reg = ®s[BPF_REG_3]; struct bpf_reg_state *data_len_reg = ®s[BPF_REG_5]; struct bpf_map *fmt_map = fmt_reg->map_ptr; + struct bpf_bprintf_data data = {}; int err, fmt_map_off, num_args; u64 fmt_addr; char *fmt; @@ -7638,7 +8057,7 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, /* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we * can focus on validating the format specifiers. */ - err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, NULL, num_args); + err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data); if (err < 0) verbose(env, "Invalid format string\n"); @@ -7914,13 +8333,32 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) { if (arg_type_is_dynptr(fn->arg_type[i])) { struct bpf_reg_state *reg = ®s[BPF_REG_1 + i]; + int id, ref_obj_id; + + if (meta.dynptr_id) { + verbose(env, "verifier internal error: meta.dynptr_id already set\n"); + return -EFAULT; + } if (meta.ref_obj_id) { verbose(env, "verifier internal error: meta.ref_obj_id already set\n"); return -EFAULT; } - meta.ref_obj_id = dynptr_ref_obj_id(env, reg); + id = dynptr_id(env, reg); + if (id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr id\n"); + return id; + } + + ref_obj_id = dynptr_ref_obj_id(env, reg); + if (ref_obj_id < 0) { + verbose(env, "verifier internal error: failed to obtain dynptr ref_obj_id\n"); + return ref_obj_id; + } + + meta.dynptr_id = id; + meta.ref_obj_id = ref_obj_id; break; } } @@ -8076,6 +8514,9 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EFAULT; } + if (is_dynptr_ref_function(func_id)) + regs[BPF_REG_0].dynptr_id = meta.dynptr_id; + if (is_ptr_cast_function(func_id) || is_dynptr_ref_function(func_id)) { /* For release_reference() */ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id; @@ -8167,6 +8608,7 @@ struct bpf_kfunc_call_arg_meta { bool r0_rdonly; u32 ret_btf_id; u64 r0_size; + u32 subprogno; struct { u64 value; bool found; @@ -8178,6 +8620,9 @@ struct bpf_kfunc_call_arg_meta { struct { struct btf_field *field; } arg_list_head; + struct { + struct btf_field *field; + } arg_rbtree_root; }; static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta) @@ -8289,12 +8734,16 @@ enum { KF_ARG_DYNPTR_ID, KF_ARG_LIST_HEAD_ID, KF_ARG_LIST_NODE_ID, + KF_ARG_RB_ROOT_ID, + KF_ARG_RB_NODE_ID, }; BTF_ID_LIST(kf_arg_btf_ids) BTF_ID(struct, bpf_dynptr_kern) BTF_ID(struct, bpf_list_head) BTF_ID(struct, bpf_list_node) +BTF_ID(struct, bpf_rb_root) +BTF_ID(struct, bpf_rb_node) static bool __is_kfunc_ptr_arg_type(const struct btf *btf, const struct btf_param *arg, int type) @@ -8328,6 +8777,28 @@ static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID); } +static bool is_kfunc_arg_rbtree_root(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_ROOT_ID); +} + +static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_param *arg) +{ + return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_NODE_ID); +} + +static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf, + const struct btf_param *arg) +{ + const struct btf_type *t; + + t = btf_type_resolve_func_ptr(btf, arg->type, NULL); + if (!t) + return false; + + return true; +} + /* Returns true if struct is composed of scalars, 4 levels of nesting allowed */ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env, const struct btf *btf, @@ -8387,6 +8858,9 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_BTF_ID, /* Also covers reg2btf_ids conversions */ KF_ARG_PTR_TO_MEM, KF_ARG_PTR_TO_MEM_SIZE, /* Size derived from next argument, skip it */ + KF_ARG_PTR_TO_CALLBACK, + KF_ARG_PTR_TO_RB_ROOT, + KF_ARG_PTR_TO_RB_NODE, }; enum special_kfunc_type { @@ -8400,6 +8874,9 @@ enum special_kfunc_type { KF_bpf_rdonly_cast, KF_bpf_rcu_read_lock, KF_bpf_rcu_read_unlock, + KF_bpf_rbtree_remove, + KF_bpf_rbtree_add, + KF_bpf_rbtree_first, }; BTF_SET_START(special_kfunc_set) @@ -8411,6 +8888,9 @@ BTF_ID(func, bpf_list_pop_front) BTF_ID(func, bpf_list_pop_back) BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) +BTF_ID(func, bpf_rbtree_remove) +BTF_ID(func, bpf_rbtree_add) +BTF_ID(func, bpf_rbtree_first) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -8424,6 +8904,9 @@ BTF_ID(func, bpf_cast_to_kern_ctx) BTF_ID(func, bpf_rdonly_cast) BTF_ID(func, bpf_rcu_read_lock) BTF_ID(func, bpf_rcu_read_unlock) +BTF_ID(func, bpf_rbtree_remove) +BTF_ID(func, bpf_rbtree_add) +BTF_ID(func, bpf_rbtree_first) static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta) { @@ -8485,6 +8968,12 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_list_node(meta->btf, &args[argno])) return KF_ARG_PTR_TO_LIST_NODE; + if (is_kfunc_arg_rbtree_root(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_RB_ROOT; + + if (is_kfunc_arg_rbtree_node(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_RB_NODE; + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", @@ -8494,6 +8983,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, return KF_ARG_PTR_TO_BTF_ID; } + if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) + return KF_ARG_PTR_TO_CALLBACK; + if (argno + 1 < nargs && is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1])) arg_mem_size = true; @@ -8532,9 +9024,37 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env, reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } - if (is_kfunc_trusted_args(meta) || (is_kfunc_release(meta) && reg->ref_obj_id)) + /* Enforce strict type matching for calls to kfuncs that are acquiring + * or releasing a reference, or are no-cast aliases. We do _not_ + * enforce strict matching for plain KF_TRUSTED_ARGS kfuncs by default, + * as we want to enable BPF programs to pass types that are bitwise + * equivalent without forcing them to explicitly cast with something + * like bpf_cast_to_kern_ctx(). + * + * For example, say we had a type like the following: + * + * struct bpf_cpumask { + * cpumask_t cpumask; + * refcount_t usage; + * }; + * + * Note that as specified in <linux/cpumask.h>, cpumask_t is typedef'ed + * to a struct cpumask, so it would be safe to pass a struct + * bpf_cpumask * to a kfunc expecting a struct cpumask *. + * + * The philosophy here is similar to how we allow scalars of different + * types to be passed to kfuncs as long as the size is the same. The + * only difference here is that we're simply allowing + * btf_struct_ids_match() to walk the struct at the 0th offset, and + * resolve types. + */ + if (is_kfunc_acquire(meta) || + (is_kfunc_release(meta) && reg->ref_obj_id) || + btf_type_ids_nocast_alias(&env->log, reg_btf, reg_ref_id, meta->btf, ref_id)) strict_type_match = true; + WARN_ON_ONCE(is_kfunc_trusted_args(meta) && reg->off); + reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, ®_ref_id); reg_ref_tname = btf_name_by_offset(reg_btf, reg_ref_t->name_off); if (!btf_struct_ids_match(&env->log, reg_btf, reg_ref_id, reg->off, meta->btf, ref_id, strict_type_match)) { @@ -8580,38 +9100,54 @@ static int process_kf_arg_ptr_to_kptr(struct bpf_verifier_env *env, return 0; } -static int ref_set_release_on_unlock(struct bpf_verifier_env *env, u32 ref_obj_id) +static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { - struct bpf_func_state *state = cur_func(env); + struct bpf_verifier_state *state = env->cur_state; + + if (!state->active_lock.ptr) { + verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n"); + return -EFAULT; + } + + if (type_flag(reg->type) & NON_OWN_REF) { + verbose(env, "verifier internal error: NON_OWN_REF already set\n"); + return -EFAULT; + } + + reg->type |= NON_OWN_REF; + return 0; +} + +static int ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 ref_obj_id) +{ + struct bpf_func_state *state, *unused; struct bpf_reg_state *reg; int i; - /* bpf_spin_lock only allows calling list_push and list_pop, no BPF - * subprogs, no global functions. This means that the references would - * not be released inside the critical section but they may be added to - * the reference state, and the acquired_refs are never copied out for a - * different frame as BPF to BPF calls don't work in bpf_spin_lock - * critical sections. - */ + state = cur_func(env); + if (!ref_obj_id) { - verbose(env, "verifier internal error: ref_obj_id is zero for release_on_unlock\n"); + verbose(env, "verifier internal error: ref_obj_id is zero for " + "owning -> non-owning conversion\n"); return -EFAULT; } + for (i = 0; i < state->acquired_refs; i++) { - if (state->refs[i].id == ref_obj_id) { - if (state->refs[i].release_on_unlock) { - verbose(env, "verifier internal error: expected false release_on_unlock"); - return -EFAULT; + if (state->refs[i].id != ref_obj_id) + continue; + + /* Clear ref_obj_id here so release_reference doesn't clobber + * the whole reg + */ + bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({ + if (reg->ref_obj_id == ref_obj_id) { + reg->ref_obj_id = 0; + ref_set_non_owning(env, reg); } - state->refs[i].release_on_unlock = true; - /* Now mark everyone sharing same ref_obj_id as untrusted */ - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ - if (reg->ref_obj_id == ref_obj_id) - reg->type |= PTR_UNTRUSTED; - })); - return 0; - } + })); + return 0; } + verbose(env, "verifier internal error: ref state missing for ref_obj_id\n"); return -EFAULT; } @@ -8697,101 +9233,226 @@ static bool is_bpf_list_api_kfunc(u32 btf_id) btf_id == special_kfunc_list[KF_bpf_list_pop_back]; } -static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, - struct bpf_reg_state *reg, u32 regno, - struct bpf_kfunc_call_arg_meta *meta) +static bool is_bpf_rbtree_api_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_rbtree_add] || + btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || + btf_id == special_kfunc_list[KF_bpf_rbtree_first]; +} + +static bool is_bpf_graph_api_kfunc(u32 btf_id) +{ + return is_bpf_list_api_kfunc(btf_id) || is_bpf_rbtree_api_kfunc(btf_id); +} + +static bool is_callback_calling_kfunc(u32 btf_id) +{ + return btf_id == special_kfunc_list[KF_bpf_rbtree_add]; +} + +static bool is_rbtree_lock_required_kfunc(u32 btf_id) +{ + return is_bpf_rbtree_api_kfunc(btf_id); +} + +static bool check_kfunc_is_graph_root_api(struct bpf_verifier_env *env, + enum btf_field_type head_field_type, + u32 kfunc_btf_id) +{ + bool ret; + + switch (head_field_type) { + case BPF_LIST_HEAD: + ret = is_bpf_list_api_kfunc(kfunc_btf_id); + break; + case BPF_RB_ROOT: + ret = is_bpf_rbtree_api_kfunc(kfunc_btf_id); + break; + default: + verbose(env, "verifier internal error: unexpected graph root argument type %s\n", + btf_field_type_name(head_field_type)); + return false; + } + + if (!ret) + verbose(env, "verifier internal error: %s head arg for unknown kfunc\n", + btf_field_type_name(head_field_type)); + return ret; +} + +static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env, + enum btf_field_type node_field_type, + u32 kfunc_btf_id) { + bool ret; + + switch (node_field_type) { + case BPF_LIST_NODE: + ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_front] || + kfunc_btf_id == special_kfunc_list[KF_bpf_list_push_back]); + break; + case BPF_RB_NODE: + ret = (kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] || + kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_add]); + break; + default: + verbose(env, "verifier internal error: unexpected graph node argument type %s\n", + btf_field_type_name(node_field_type)); + return false; + } + + if (!ret) + verbose(env, "verifier internal error: %s node arg for unknown kfunc\n", + btf_field_type_name(node_field_type)); + return ret; +} + +static int +__process_kf_arg_ptr_to_graph_root(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta, + enum btf_field_type head_field_type, + struct btf_field **head_field) +{ + const char *head_type_name; struct btf_field *field; struct btf_record *rec; - u32 list_head_off; + u32 head_off; - if (meta->btf != btf_vmlinux || !is_bpf_list_api_kfunc(meta->func_id)) { - verbose(env, "verifier internal error: bpf_list_head argument for unknown kfunc\n"); + if (meta->btf != btf_vmlinux) { + verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); return -EFAULT; } + if (!check_kfunc_is_graph_root_api(env, head_field_type, meta->func_id)) + return -EFAULT; + + head_type_name = btf_field_type_name(head_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, - "R%d doesn't have constant offset. bpf_list_head has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s has to be at the constant offset\n", + regno, head_type_name); return -EINVAL; } rec = reg_btf_record(reg); - list_head_off = reg->off + reg->var_off.value; - field = btf_record_find(rec, list_head_off, BPF_LIST_HEAD); + head_off = reg->off + reg->var_off.value; + field = btf_record_find(rec, head_off, head_field_type); if (!field) { - verbose(env, "bpf_list_head not found at offset=%u\n", list_head_off); + verbose(env, "%s not found at offset=%u\n", head_type_name, head_off); return -EINVAL; } /* All functions require bpf_list_head to be protected using a bpf_spin_lock */ if (check_reg_allocation_locked(env, reg)) { - verbose(env, "bpf_spin_lock at off=%d must be held for bpf_list_head\n", - rec->spin_lock_off); + verbose(env, "bpf_spin_lock at off=%d must be held for %s\n", + rec->spin_lock_off, head_type_name); return -EINVAL; } - if (meta->arg_list_head.field) { - verbose(env, "verifier internal error: repeating bpf_list_head arg\n"); + if (*head_field) { + verbose(env, "verifier internal error: repeating %s arg\n", head_type_name); return -EFAULT; } - meta->arg_list_head.field = field; + *head_field = field; return 0; } -static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, +static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, struct bpf_kfunc_call_arg_meta *meta) { + return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_LIST_HEAD, + &meta->arg_list_head.field); +} + +static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_root(env, reg, regno, meta, BPF_RB_ROOT, + &meta->arg_rbtree_root.field); +} + +static int +__process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta, + enum btf_field_type head_field_type, + enum btf_field_type node_field_type, + struct btf_field **node_field) +{ + const char *node_type_name; const struct btf_type *et, *t; struct btf_field *field; - struct btf_record *rec; - u32 list_node_off; + u32 node_off; - if (meta->btf != btf_vmlinux || - (meta->func_id != special_kfunc_list[KF_bpf_list_push_front] && - meta->func_id != special_kfunc_list[KF_bpf_list_push_back])) { - verbose(env, "verifier internal error: bpf_list_node argument for unknown kfunc\n"); + if (meta->btf != btf_vmlinux) { + verbose(env, "verifier internal error: unexpected btf mismatch in kfunc call\n"); return -EFAULT; } + if (!check_kfunc_is_graph_node_api(env, node_field_type, meta->func_id)) + return -EFAULT; + + node_type_name = btf_field_type_name(node_field_type); if (!tnum_is_const(reg->var_off)) { verbose(env, - "R%d doesn't have constant offset. bpf_list_node has to be at the constant offset\n", - regno); + "R%d doesn't have constant offset. %s has to be at the constant offset\n", + regno, node_type_name); return -EINVAL; } - rec = reg_btf_record(reg); - list_node_off = reg->off + reg->var_off.value; - field = btf_record_find(rec, list_node_off, BPF_LIST_NODE); - if (!field || field->offset != list_node_off) { - verbose(env, "bpf_list_node not found at offset=%u\n", list_node_off); + node_off = reg->off + reg->var_off.value; + field = reg_find_field_offset(reg, node_off, node_field_type); + if (!field || field->offset != node_off) { + verbose(env, "%s not found at offset=%u\n", node_type_name, node_off); return -EINVAL; } - field = meta->arg_list_head.field; + field = *node_field; - et = btf_type_by_id(field->list_head.btf, field->list_head.value_btf_id); + et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id); t = btf_type_by_id(reg->btf, reg->btf_id); - if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->list_head.btf, - field->list_head.value_btf_id, true)) { - verbose(env, "operation on bpf_list_head expects arg#1 bpf_list_node at offset=%d " + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf, + field->graph_root.value_btf_id, true)) { + verbose(env, "operation on %s expects arg#1 %s at offset=%d " "in struct %s, but arg is at offset=%d in struct %s\n", - field->list_head.node_offset, btf_name_by_offset(field->list_head.btf, et->name_off), - list_node_off, btf_name_by_offset(reg->btf, t->name_off)); + btf_field_type_name(head_field_type), + btf_field_type_name(node_field_type), + field->graph_root.node_offset, + btf_name_by_offset(field->graph_root.btf, et->name_off), + node_off, btf_name_by_offset(reg->btf, t->name_off)); return -EINVAL; } - if (list_node_off != field->list_head.node_offset) { - verbose(env, "arg#1 offset=%d, but expected bpf_list_node at offset=%d in struct %s\n", - list_node_off, field->list_head.node_offset, - btf_name_by_offset(field->list_head.btf, et->name_off)); + if (node_off != field->graph_root.node_offset) { + verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n", + node_off, btf_field_type_name(node_field_type), + field->graph_root.node_offset, + btf_name_by_offset(field->graph_root.btf, et->name_off)); return -EINVAL; } - /* Set arg#1 for expiration after unlock */ - return ref_set_release_on_unlock(env, reg->ref_obj_id); + + return 0; +} + +static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, + BPF_LIST_HEAD, BPF_LIST_NODE, + &meta->arg_list_head.field); +} + +static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, + struct bpf_reg_state *reg, u32 regno, + struct bpf_kfunc_call_arg_meta *meta) +{ + return __process_kf_arg_ptr_to_graph_node(env, reg, regno, meta, + BPF_RB_ROOT, BPF_RB_NODE, + &meta->arg_rbtree_root.field); } static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta) @@ -8877,6 +9538,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return -EINVAL; } + if (is_kfunc_trusted_args(meta) && + (register_is_null(reg) || type_may_be_null(reg->type))) { + verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); + return -EACCES; + } + if (reg->ref_obj_id) { if (is_kfunc_release(meta) && meta->ref_obj_id) { verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n", @@ -8922,8 +9589,11 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ case KF_ARG_PTR_TO_DYNPTR: case KF_ARG_PTR_TO_LIST_HEAD: case KF_ARG_PTR_TO_LIST_NODE: + case KF_ARG_PTR_TO_RB_ROOT: + case KF_ARG_PTR_TO_RB_NODE: case KF_ARG_PTR_TO_MEM: case KF_ARG_PTR_TO_MEM_SIZE: + case KF_ARG_PTR_TO_CALLBACK: /* Trusted by default */ break; default: @@ -9000,6 +9670,20 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_RB_ROOT: + if (reg->type != PTR_TO_MAP_VALUE && + reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to map value or allocated object\n", i); + return -EINVAL; + } + if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) && !reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + ret = process_kf_arg_ptr_to_rbtree_root(env, reg, regno, meta); + if (ret < 0) + return ret; + break; case KF_ARG_PTR_TO_LIST_NODE: if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { verbose(env, "arg#%d expected pointer to allocated object\n", i); @@ -9013,6 +9697,31 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_RB_NODE: + if (meta->func_id == special_kfunc_list[KF_bpf_rbtree_remove]) { + if (!type_is_non_owning_ref(reg->type) || reg->ref_obj_id) { + verbose(env, "rbtree_remove node input must be non-owning ref\n"); + return -EINVAL; + } + if (in_rbtree_lock_required_cb(env)) { + verbose(env, "rbtree_remove not allowed in rbtree cb\n"); + return -EINVAL; + } + } else { + if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) { + verbose(env, "arg#%d expected pointer to allocated object\n", i); + return -EINVAL; + } + if (!reg->ref_obj_id) { + verbose(env, "allocated object must be referenced\n"); + return -EINVAL; + } + } + + ret = process_kf_arg_ptr_to_rbtree_node(env, reg, regno, meta); + if (ret < 0) + return ret; + break; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || @@ -9048,6 +9757,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ /* Skip next '__sz' argument */ i++; break; + case KF_ARG_PTR_TO_CALLBACK: + meta->subprogno = reg->subprogno; + break; } } @@ -9064,11 +9776,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx_p) { const struct btf_type *t, *func, *func_proto, *ptr_type; + u32 i, nargs, func_id, ptr_type_id, release_ref_obj_id; struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; bool sleepable, rcu_lock, rcu_unlock; struct bpf_kfunc_call_arg_meta meta; - u32 i, nargs, func_id, ptr_type_id; int err, insn_idx = *insn_idx_p; const struct btf_param *args; const struct btf_type *ret_t; @@ -9163,6 +9875,35 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } + if (meta.func_id == special_kfunc_list[KF_bpf_list_push_front] || + meta.func_id == special_kfunc_list[KF_bpf_list_push_back] || + meta.func_id == special_kfunc_list[KF_bpf_rbtree_add]) { + release_ref_obj_id = regs[BPF_REG_2].ref_obj_id; + err = ref_convert_owning_non_owning(env, release_ref_obj_id); + if (err) { + verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n", + func_name, func_id); + return err; + } + + err = release_reference(env, release_ref_obj_id); + if (err) { + verbose(env, "kfunc %s#%d reference has not been acquired before\n", + func_name, func_id); + return err; + } + } + + if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add]) { + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_rbtree_add_callback_state); + if (err) { + verbose(env, "kfunc %s#%d failed callback verification\n", + func_name, func_id); + return err; + } + } + for (i = 0; i < CALLER_SAVED_REGS; i++) mark_reg_not_init(env, regs, caller_saved[i]); @@ -9227,11 +9968,12 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) { struct btf_field *field = meta.arg_list_head.field; - mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC; - regs[BPF_REG_0].btf = field->list_head.btf; - regs[BPF_REG_0].btf_id = field->list_head.value_btf_id; - regs[BPF_REG_0].off = field->list_head.node_offset; + mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); + } else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_remove] || + meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { + struct btf_field *field = meta.arg_rbtree_root.field; + + mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root); } else if (meta.func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx]) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED; @@ -9297,7 +10039,13 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (is_kfunc_ret_null(&meta)) regs[BPF_REG_0].id = id; regs[BPF_REG_0].ref_obj_id = id; + } else if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_first]) { + ref_set_non_owning(env, ®s[BPF_REG_0]); } + + if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_remove]) + invalidate_non_owning_refs(env); + if (reg_may_point_to_spin_lock(®s[BPF_REG_0]) && !regs[BPF_REG_0].id) regs[BPF_REG_0].id = ++env->id_gen; } /* else { add_kfunc_call() ensures it is btf_type_is_void(t) } */ @@ -9584,7 +10332,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -10837,7 +11585,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -10848,7 +11596,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -11483,8 +12231,10 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, */ if (WARN_ON_ONCE(reg->smin_value || reg->smax_value || !tnum_equals_const(reg->var_off, 0))) return; - if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL) && WARN_ON_ONCE(reg->off)) + if (!(type_is_ptr_alloc_obj(reg->type) || type_is_non_owning_ref(reg->type)) && + WARN_ON_ONCE(reg->off)) return; + if (is_null) { reg->type = SCALAR_VALUE; /* We don't need id and ref_obj_id from this point @@ -11647,7 +12397,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } @@ -12950,6 +13700,13 @@ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap) { unsigned int i; + /* either both IDs should be set or both should be zero */ + if (!!old_id != !!cur_id) + return false; + + if (old_id == 0) /* cur_id == 0 as well */ + return true; + for (i = 0; i < BPF_ID_MAP_SIZE; i++) { if (!idmap[i].old) { /* Reached an empty slot; haven't seen this id before */ @@ -13061,79 +13818,74 @@ next: } } +static bool regs_exact(const struct bpf_reg_state *rold, + const struct bpf_reg_state *rcur, + struct bpf_id_pair *idmap) +{ + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + check_ids(rold->id, rcur->id, idmap) && + check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); +} + /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, struct bpf_reg_state *rcur, struct bpf_id_pair *idmap) { - bool equal; - if (!(rold->live & REG_LIVE_READ)) /* explored state didn't use this */ return true; - - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; - if (rold->type == NOT_INIT) /* explored state can't have used this */ return true; if (rcur->type == NOT_INIT) return false; + + /* Enforce that register types have to match exactly, including their + * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general + * rule. + * + * One can make a point that using a pointer register as unbounded + * SCALAR would be technically acceptable, but this could lead to + * pointer leaks because scalars are allowed to leak while pointers + * are not. We could make this safe in special cases if root is + * calling us, but it's probably not worth the hassle. + * + * Also, register types that are *not* MAYBE_NULL could technically be + * safe to use as their MAYBE_NULL variants (e.g., PTR_TO_MAP_VALUE + * is safe to be used as PTR_TO_MAP_VALUE_OR_NULL, provided both point + * to the same map). + * However, if the old MAYBE_NULL register then got NULL checked, + * doing so could have affected others with the same id, and we can't + * check for that because we lost the id when we converted to + * a non-MAYBE_NULL variant. + * So, as a general rule we don't allow mixing MAYBE_NULL and + * non-MAYBE_NULL registers as well. + */ + if (rold->type != rcur->type) + return false; + switch (base_type(rold->type)) { case SCALAR_VALUE: - if (equal) + if (regs_exact(rold, rcur, idmap)) return true; if (env->explore_alu_limits) return false; - if (rcur->type == SCALAR_VALUE) { - if (!rold->precise) - return true; - /* new val must satisfy old val knowledge */ - return range_within(rold, rcur) && - tnum_in(rold->var_off, rcur->var_off); - } else { - /* We're trying to use a pointer in place of a scalar. - * Even if the scalar was unbounded, this could lead to - * pointer leaks because scalars are allowed to leak - * while pointers are not. We could make this safe in - * special cases if root is calling us, but it's - * probably not worth the hassle. - */ - return false; - } + if (!rold->precise) + return true; + /* new val must satisfy old val knowledge */ + return range_within(rold, rcur) && + tnum_in(rold->var_off, rcur->var_off); case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: - /* a PTR_TO_MAP_VALUE could be safe to use as a - * PTR_TO_MAP_VALUE_OR_NULL into the same map. - * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- - * checked, doing so could have affected others with the same - * id, and we can't check for that because we lost the id when - * we converted to a PTR_TO_MAP_VALUE. - */ - if (type_may_be_null(rold->type)) { - if (!type_may_be_null(rcur->type)) - return false; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) - return false; - /* Check our ids match any regs they're supposed to */ - return check_ids(rold->id, rcur->id, idmap); - } - /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. - * 'id' is not compared, since it's only used for maps with - * bpf_spin_lock inside map element and in such cases if - * the rest of the prog is valid for one map element then - * it's valid for all map elements regardless of the key - * used in bpf_map_lookup() */ - return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && + return memcmp(rold, rcur, offsetof(struct bpf_reg_state, var_off)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off) && check_ids(rold->id, rcur->id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != rold->type) - return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are * still safe. This is true even if old range < old off, @@ -13148,7 +13900,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, if (rold->off != rcur->off) return false; /* id relations must be preserved */ - if (rold->id && !check_ids(rold->id, rcur->id, idmap)) + if (!check_ids(rold->id, rcur->id, idmap)) return false; /* new val must satisfy old val knowledge */ return range_within(rold, rcur) && @@ -13157,15 +13909,10 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, /* two stack pointers are equal only if they're pointing to * the same stack frame, since fp-8 in foo != fp-8 in bar */ - return equal && rold->frameno == rcur->frameno; + return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; default: - /* Only valid matches are exact, which memcmp() */ - return equal; + return regs_exact(rold, rcur, idmap); } - - /* Shouldn't get here; if we do, say it's not safe */ - WARN_ON_ONCE(1); - return false; } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, @@ -13212,10 +13959,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, return false; if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (!is_spilled_reg(&old->stack[spi])) - continue; - if (!regsafe(env, &old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, idmap)) + /* Both old and cur are having same slot_type */ + switch (old->stack[spi].slot_type[BPF_REG_SIZE - 1]) { + case STACK_SPILL: /* when explored and current stack slot are both storing * spilled registers, check that stored pointers types * are the same as well. @@ -13226,17 +13972,48 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * such verifier states are not equivalent. * return false to continue verification of this path */ + if (!regsafe(env, &old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, idmap)) + return false; + break; + case STACK_DYNPTR: + { + const struct bpf_reg_state *old_reg, *cur_reg; + + old_reg = &old->stack[spi].spilled_ptr; + cur_reg = &cur->stack[spi].spilled_ptr; + if (old_reg->dynptr.type != cur_reg->dynptr.type || + old_reg->dynptr.first_slot != cur_reg->dynptr.first_slot || + !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap)) + return false; + break; + } + case STACK_MISC: + case STACK_ZERO: + case STACK_INVALID: + continue; + /* Ensure that new unhandled slot types return false by default */ + default: return false; + } } return true; } -static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur) +static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, + struct bpf_id_pair *idmap) { + int i; + if (old->acquired_refs != cur->acquired_refs) return false; - return !memcmp(old->refs, cur->refs, - sizeof(*old->refs) * old->acquired_refs); + + for (i = 0; i < old->acquired_refs; i++) { + if (!check_ids(old->refs[i].id, cur->refs[i].id, idmap)) + return false; + } + + return true; } /* compare two verifier states @@ -13278,7 +14055,7 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat if (!stacksafe(env, old, cur, env->idmap_scratch)) return false; - if (!refsafe(old, cur)) + if (!refsafe(old, cur, env->idmap_scratch)) return false; return true; @@ -13815,7 +14592,7 @@ static int do_check(struct bpf_verifier_env *env) env->prev_log_len = env->log.len_used; } - if (bpf_prog_is_dev_bound(env->prog->aux)) { + if (bpf_prog_is_offloaded(env->prog->aux)) { err = bpf_prog_offload_verify_insn(env, env->insn_idx, env->prev_insn_idx); if (err) @@ -13966,7 +14743,7 @@ static int do_check(struct bpf_verifier_env *env) if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || (insn->src_reg == BPF_PSEUDO_CALL) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && - (insn->off != 0 || !is_bpf_list_api_kfunc(insn->imm)))) { + (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); return -EINVAL; } @@ -14002,7 +14779,8 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - if (env->cur_state->active_lock.ptr) { + if (env->cur_state->active_lock.ptr && + !in_rbtree_lock_required_cb(env)) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } @@ -14264,9 +15042,10 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); - if (btf_record_has_field(map->record, BPF_LIST_HEAD)) { + if (btf_record_has_field(map->record, BPF_LIST_HEAD) || + btf_record_has_field(map->record, BPF_RB_ROOT)) { if (is_tracing_prog_type(prog_type)) { - verbose(env, "tracing progs cannot use bpf_list_head yet\n"); + verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n"); return -EINVAL; } } @@ -14295,7 +15074,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } - if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && + if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; @@ -14776,7 +15555,7 @@ static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) unsigned int orig_prog_len = env->prog->len; int err; - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_remove_insns(env, off, cnt); err = bpf_remove_insns(env->prog, off, cnt); @@ -14857,7 +15636,7 @@ static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env) else continue; - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) bpf_prog_offload_replace_insn(env, i, &ja); memcpy(insn, &ja, sizeof(ja)); @@ -15044,7 +15823,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) } } - if (bpf_prog_is_dev_bound(env->prog->aux)) + if (bpf_prog_is_offloaded(env->prog->aux)) return 0; insn = env->prog->insnsi + delta; @@ -15444,7 +16223,7 @@ static int fixup_call_args(struct bpf_verifier_env *env) int err = 0; if (env->prog->jit_requested && - !bpf_prog_is_dev_bound(env->prog->aux)) { + !bpf_prog_is_offloaded(env->prog->aux)) { err = jit_subprogs(env); if (err == 0) return 0; @@ -15488,12 +16267,25 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_insn *insn_buf, int insn_idx, int *cnt) { const struct bpf_kfunc_desc *desc; + void *xdp_kfunc; if (!insn->imm) { verbose(env, "invalid kernel function call not eliminated in verifier pass\n"); return -EINVAL; } + *cnt = 0; + + if (bpf_dev_bound_kfunc_id(insn->imm)) { + xdp_kfunc = bpf_dev_bound_resolve_kfunc(env->prog, insn->imm); + if (xdp_kfunc) { + insn->imm = BPF_CALL_IMM(xdp_kfunc); + return 0; + } + + /* fallback to default kfunc when not supported by netdev */ + } + /* insn->imm has the btf func_id. Replace it with * an address (relative to __bpf_call_base). */ @@ -15504,7 +16296,6 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EFAULT; } - *cnt = 0; insn->imm = desc->imm; if (insn->off) return 0; @@ -16430,7 +17221,7 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } if (st_ops->check_member) { - int err = st_ops->check_member(t, member); + int err = st_ops->check_member(t, member, prog); if (err) { verbose(env, "attach to unsupported member %s of struct %s\n", @@ -16511,6 +17302,12 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, if (tgt_prog) { struct bpf_prog_aux *aux = tgt_prog->aux; + if (bpf_prog_is_dev_bound(prog->aux) && + !bpf_prog_dev_bound_match(prog, tgt_prog)) { + bpf_log(log, "Target program bound device mismatch"); + return -EINVAL; + } + for (i = 0; i < aux->func_info_cnt; i++) if (aux->func_info[i].type_id == btf_id) { subprog = i; @@ -16732,6 +17529,24 @@ BTF_ID(func, rcu_read_unlock_strict) #endif BTF_SET_END(btf_id_deny) +static bool can_be_sleepable(struct bpf_prog *prog) +{ + if (prog->type == BPF_PROG_TYPE_TRACING) { + switch (prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + case BPF_MODIFY_RETURN: + case BPF_TRACE_ITER: + return true; + default: + return false; + } + } + return prog->type == BPF_PROG_TYPE_LSM || + prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ || + prog->type == BPF_PROG_TYPE_STRUCT_OPS; +} + static int check_attach_btf_id(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; @@ -16750,9 +17565,8 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return -EINVAL; } - if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_LSM && prog->type != BPF_PROG_TYPE_KPROBE) { - verbose(env, "Only fentry/fexit/fmod_ret, lsm, and kprobe/uprobe programs can be sleepable\n"); + if (prog->aux->sleepable && !can_be_sleepable(prog)) { + verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } @@ -16931,7 +17745,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) if (ret < 0) goto skip_full_check; - if (bpf_prog_is_dev_bound(env->prog->aux)) { + if (bpf_prog_is_offloaded(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env->prog); if (ret) goto skip_full_check; @@ -16944,7 +17758,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) ret = do_check_subprogs(env); ret = ret ?: do_check_main(env); - if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux)) + if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux)) ret = bpf_prog_offload_finalize(env); skip_full_check: @@ -16979,7 +17793,7 @@ skip_full_check: /* do 32-bit optimization after insn patching has done so those patched * insns could be handled correctly. */ - if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) { + if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) { ret = opt_subreg_zext_lo32_rnd_hi32(env, attr); env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret : false; diff --git a/kernel/capability.c b/kernel/capability.c index 860fd22117c1..3e058f41df32 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -20,13 +20,6 @@ #include <linux/user_namespace.h> #include <linux/uaccess.h> -/* - * Leveraged for setting/resetting capabilities - */ - -const kernel_cap_t __cap_empty_set = CAP_EMPTY_SET; -EXPORT_SYMBOL(__cap_empty_set); - int file_caps_enabled = 1; static int __init file_caps_disable(char *str) @@ -151,6 +144,7 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) pid_t pid; unsigned tocopy; kernel_cap_t pE, pI, pP; + struct __user_cap_data_struct kdata[2]; ret = cap_validate_magic(header, &tocopy); if ((dataptr == NULL) || (ret != 0)) @@ -163,42 +157,46 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); - if (!ret) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i; - - for (i = 0; i < tocopy; i++) { - kdata[i].effective = pE.cap[i]; - kdata[i].permitted = pP.cap[i]; - kdata[i].inheritable = pI.cap[i]; - } - - /* - * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, - * we silently drop the upper capabilities here. This - * has the effect of making older libcap - * implementations implicitly drop upper capability - * bits when they perform a: capget/modify/capset - * sequence. - * - * This behavior is considered fail-safe - * behavior. Upgrading the application to a newer - * version of libcap will enable access to the newer - * capabilities. - * - * An alternative would be to return an error here - * (-ERANGE), but that causes legacy applications to - * unexpectedly fail; the capget/modify/capset aborts - * before modification is attempted and the application - * fails. - */ - if (copy_to_user(dataptr, kdata, tocopy - * sizeof(struct __user_cap_data_struct))) { - return -EFAULT; - } - } + if (ret) + return ret; - return ret; + /* + * Annoying legacy format with 64-bit capabilities exposed + * as two sets of 32-bit fields, so we need to split the + * capability values up. + */ + kdata[0].effective = pE.val; kdata[1].effective = pE.val >> 32; + kdata[0].permitted = pP.val; kdata[1].permitted = pP.val >> 32; + kdata[0].inheritable = pI.val; kdata[1].inheritable = pI.val >> 32; + + /* + * Note, in the case, tocopy < _KERNEL_CAPABILITY_U32S, + * we silently drop the upper capabilities here. This + * has the effect of making older libcap + * implementations implicitly drop upper capability + * bits when they perform a: capget/modify/capset + * sequence. + * + * This behavior is considered fail-safe + * behavior. Upgrading the application to a newer + * version of libcap will enable access to the newer + * capabilities. + * + * An alternative would be to return an error here + * (-ERANGE), but that causes legacy applications to + * unexpectedly fail; the capget/modify/capset aborts + * before modification is attempted and the application + * fails. + */ + if (copy_to_user(dataptr, kdata, tocopy * sizeof(kdata[0]))) + return -EFAULT; + + return 0; +} + +static kernel_cap_t mk_kernel_cap(u32 low, u32 high) +{ + return (kernel_cap_t) { (low | ((u64)high << 32)) & CAP_VALID_MASK }; } /** @@ -221,8 +219,8 @@ SYSCALL_DEFINE2(capget, cap_user_header_t, header, cap_user_data_t, dataptr) */ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) { - struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; - unsigned i, tocopy, copybytes; + struct __user_cap_data_struct kdata[2] = { { 0, }, }; + unsigned tocopy, copybytes; kernel_cap_t inheritable, permitted, effective; struct cred *new; int ret; @@ -246,21 +244,9 @@ SYSCALL_DEFINE2(capset, cap_user_header_t, header, const cap_user_data_t, data) if (copy_from_user(&kdata, data, copybytes)) return -EFAULT; - for (i = 0; i < tocopy; i++) { - effective.cap[i] = kdata[i].effective; - permitted.cap[i] = kdata[i].permitted; - inheritable.cap[i] = kdata[i].inheritable; - } - while (i < _KERNEL_CAPABILITY_U32S) { - effective.cap[i] = 0; - permitted.cap[i] = 0; - inheritable.cap[i] = 0; - i++; - } - - effective.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; - inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; + effective = mk_kernel_cap(kdata[0].effective, kdata[1].effective); + permitted = mk_kernel_cap(kdata[0].permitted, kdata[1].permitted); + inheritable = mk_kernel_cap(kdata[0].inheritable, kdata[1].inheritable); new = prepare_creds(); if (!new) @@ -486,11 +472,11 @@ EXPORT_SYMBOL(file_ns_capable); * Return true if the inode uid and gid are within the namespace. */ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, - struct user_namespace *mnt_userns, + struct mnt_idmap *idmap, const struct inode *inode) { - return vfsuid_has_mapping(ns, i_uid_into_vfsuid(mnt_userns, inode)) && - vfsgid_has_mapping(ns, i_gid_into_vfsgid(mnt_userns, inode)); + return vfsuid_has_mapping(ns, i_uid_into_vfsuid(idmap, inode)) && + vfsgid_has_mapping(ns, i_gid_into_vfsgid(idmap, inode)); } /** @@ -502,13 +488,13 @@ bool privileged_wrt_inode_uidgid(struct user_namespace *ns, * its own user namespace and that the given inode's uid and gid are * mapped into the current user namespace. */ -bool capable_wrt_inode_uidgid(struct user_namespace *mnt_userns, +bool capable_wrt_inode_uidgid(struct mnt_idmap *idmap, const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); return ns_capable(ns, cap) && - privileged_wrt_inode_uidgid(ns, mnt_userns, inode); + privileged_wrt_inode_uidgid(ns, idmap, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c099cf3fa02d..935e8121b21e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5065,7 +5065,7 @@ static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) if (!inode) return -ENOMEM; - ret = inode_permission(&init_user_ns, inode, MAY_WRITE); + ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a29c0b13706b..636f1c682ac0 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void) /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ -static void update_tasks_cpumask(struct cpuset *cs) +static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { struct css_task_iter it; struct task_struct *task; @@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs) if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; - set_cpus_allowed_ptr(task, cs->effective_cpus); + + cpumask_and(new_cpus, cs->effective_cpus, + task_cpu_possible_mask(task)); + set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); } @@ -1267,7 +1271,7 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on); /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset - * @cpuset: The cpuset that requests change in partition root state + * @cs: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask @@ -1346,7 +1350,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * A parent can be left with no CPU as long as there is no * task directly associated with the parent partition. */ - if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && + if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) && partition_is_populated(parent, cs)) return PERR_NOCPUS; @@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, spin_unlock_irq(&callback_lock); if (adding || deleting) - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmp->new_cpus); /* * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. @@ -1661,7 +1665,7 @@ update_parent_subparts: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - update_tasks_cpumask(cp); + update_tasks_cpumask(cp, tmp->new_cpus); /* * On legacy hierarchy, if the effective cpumask of any non- @@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) } } - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmpmask.new_cpus); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); @@ -2324,6 +2328,7 @@ out: new_prs = -new_prs; spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; + WRITE_ONCE(cs->prs_err, err); spin_unlock_irq(&callback_lock); /* * Update child cpusets, if present. @@ -3281,8 +3286,6 @@ struct cgroup_subsys cpuset_cgrp_subsys = { int __init cpuset_init(void) { - BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); - BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); @@ -3347,7 +3350,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, * as the tasks will be migrated to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); @@ -3384,7 +3387,7 @@ hotplug_update_tasks(struct cpuset *cs, spin_unlock_irq(&callback_lock); if (cpus_updated) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated) update_tasks_nodemask(cs); } @@ -3691,15 +3694,38 @@ void __init cpuset_init_smp(void) * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the - * tasks cpuset. + * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; + struct cpuset *cs; spin_lock_irqsave(&callback_lock, flags); - guarantee_online_cpus(tsk, pmask); + rcu_read_lock(); + + cs = task_cs(tsk); + if (cs != &top_cpuset) + guarantee_online_cpus(tsk, pmask); + /* + * Tasks in the top cpuset won't get update to their cpumasks + * when a hotplug online/offline event happens. So we include all + * offline cpus in the allowed cpu list. + */ + if ((cs == &top_cpuset) || cpumask_empty(pmask)) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + + /* + * We first exclude cpus allocated to partitions. If there is no + * allowable online cpu left, we fall back to all possible cpus. + */ + cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus); + if (!cpumask_intersects(pmask, cpu_online_mask)) + cpumask_copy(pmask, possible_mask); + } + + rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } @@ -3879,8 +3905,7 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) } /** - * cpuset_mem_spread_node() - On which node to begin search for a file page - * cpuset_slab_spread_node() - On which node to begin search for a slab page + * cpuset_spread_node() - On which node to begin search for a page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), @@ -3904,12 +3929,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ - static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } +/** + * cpuset_mem_spread_node() - On which node to begin search for a file page + */ int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) @@ -3919,6 +3946,9 @@ int cpuset_mem_spread_node(void) return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } +/** + * cpuset_slab_spread_node() - On which node to begin search for a slab page + */ int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) @@ -3927,7 +3957,6 @@ int cpuset_slab_spread_node(void) return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } - EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 793ecff29038..831f1f472bb8 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -26,7 +26,7 @@ static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ -void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) +__bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; @@ -231,7 +231,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) * * This function may block. */ -void cgroup_rstat_flush(struct cgroup *cgrp) +__bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 77978e372377..a09f1c19336a 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -510,7 +510,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * In this we case we don't care about any concurrency/ordering. */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) - atomic_set(&ct->state, state); + arch_atomic_set(&ct->state, state); } else { /* * Even if context tracking is disabled on this CPU, because it's outside @@ -527,7 +527,7 @@ void noinstr __ct_user_enter(enum ctx_state state) */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { /* Tracking for vtime only, no concurrent RCU EQS accounting */ - atomic_set(&ct->state, state); + arch_atomic_set(&ct->state, state); } else { /* * Tracking for vtime and RCU EQS. Make sure we don't race @@ -535,7 +535,7 @@ void noinstr __ct_user_enter(enum ctx_state state) * RCU only requires RCU_DYNTICKS_IDX increments to be fully * ordered. */ - atomic_add(state, &ct->state); + arch_atomic_add(state, &ct->state); } } } @@ -630,12 +630,12 @@ void noinstr __ct_user_exit(enum ctx_state state) * In this we case we don't care about any concurrency/ordering. */ if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) - atomic_set(&ct->state, CONTEXT_KERNEL); + arch_atomic_set(&ct->state, CONTEXT_KERNEL); } else { if (!IS_ENABLED(CONFIG_CONTEXT_TRACKING_IDLE)) { /* Tracking for vtime only, no concurrent RCU EQS accounting */ - atomic_set(&ct->state, CONTEXT_KERNEL); + arch_atomic_set(&ct->state, CONTEXT_KERNEL); } else { /* * Tracking for vtime and RCU EQS. Make sure we don't race @@ -643,7 +643,7 @@ void noinstr __ct_user_exit(enum ctx_state state) * RCU only requires RCU_DYNTICKS_IDX increments to be fully * ordered. */ - atomic_sub(state, &ct->state); + arch_atomic_sub(state, &ct->state); } } } diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c index ba4ba71facf9..b0f0d15085db 100644 --- a/kernel/cpu_pm.c +++ b/kernel/cpu_pm.c @@ -30,16 +30,9 @@ static int cpu_pm_notify(enum cpu_pm_event event) { int ret; - /* - * This introduces a RCU read critical section, which could be - * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know - * this. - */ - ct_irq_enter_irqson(); rcu_read_lock(); ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL); rcu_read_unlock(); - ct_irq_exit_irqson(); return notifier_to_errno(ret); } @@ -49,11 +42,9 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev unsigned long flags; int ret; - ct_irq_enter_irqson(); raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags); ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL); raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags); - ct_irq_exit_irqson(); return notifier_to_errno(ret); } diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 87ef6096823f..755f5f08ab38 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -455,8 +455,8 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_OFFSET(page, lru); VMCOREINFO_OFFSET(page, _mapcount); VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_dtor); - VMCOREINFO_OFFSET(page, compound_order); + VMCOREINFO_OFFSET(folio, _folio_dtor); + VMCOREINFO_OFFSET(folio, _folio_order); VMCOREINFO_OFFSET(page, compound_head); VMCOREINFO_OFFSET(pglist_data, node_zones); VMCOREINFO_OFFSET(pglist_data, nr_zones); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index a34c38bbe28f..03e3251cd9d2 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -156,14 +156,6 @@ setup_io_tlb_npages(char *str) } early_param("swiotlb", setup_io_tlb_npages); -unsigned int swiotlb_max_segment(void) -{ - if (!io_tlb_default_mem.nslabs) - return 0; - return rounddown(io_tlb_default_mem.nslabs << IO_TLB_SHIFT, PAGE_SIZE); -} -EXPORT_SYMBOL_GPL(swiotlb_max_segment); - unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; @@ -300,7 +292,8 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, return; } -static void *swiotlb_memblock_alloc(unsigned long nslabs, unsigned int flags, +static void __init *swiotlb_memblock_alloc(unsigned long nslabs, + unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); diff --git a/kernel/events/core.c b/kernel/events/core.c index d56328e5080e..f79fd8b87f75 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); epc = &cpc->epc; - + raw_spin_lock_irq(&ctx->lock); if (!epc->ctx) { atomic_set(&epc->refcount, 1); epc->embedded = 1; - raw_spin_lock_irq(&ctx->lock); list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; - raw_spin_unlock_irq(&ctx->lock); } else { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); } - + raw_spin_unlock_irq(&ctx->lock); return epc; } @@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head) static void put_pmu_ctx(struct perf_event_pmu_context *epc) { + struct perf_event_context *ctx = epc->ctx; unsigned long flags; - if (!atomic_dec_and_test(&epc->refcount)) + /* + * XXX + * + * lockdep_assert_held(&ctx->mutex); + * + * can't because of the call-site in _free_event()/put_event() + * which isn't always called under ctx->mutex. + */ + if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags)) return; - if (epc->ctx) { - struct perf_event_context *ctx = epc->ctx; + WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - /* - * XXX - * - * lockdep_assert_held(&ctx->mutex); - * - * can't because of the call-site in _free_event()/put_event() - * which isn't always called under ctx->mutex. - */ - - WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - raw_spin_lock_irqsave(&ctx->lock, flags); - list_del_init(&epc->pmu_ctx_entry); - epc->ctx = NULL; - raw_spin_unlock_irqrestore(&ctx->lock, flags); - } + list_del_init(&epc->pmu_ctx_entry); + epc->ctx = NULL; WARN_ON_ONCE(!list_empty(&epc->pinned_active)); WARN_ON_ONCE(!list_empty(&epc->flexible_active)); + raw_spin_unlock_irqrestore(&ctx->lock, flags); + if (epc->embedded) return; @@ -6573,7 +6568,7 @@ aux_unlock: * Since pinned accounting is per vm we cannot allow fork() to copy our * vma. */ - vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_ops = &perf_mmap_vmops; if (event->pmu->event_mapped) @@ -7046,13 +7041,20 @@ out_put: ring_buffer_put(rb); } -static void __perf_event_header__init_id(struct perf_event_header *header, - struct perf_sample_data *data, +/* + * A set of common sample data types saved even for non-sample records + * when event->attr.sample_id_all is set. + */ +#define PERF_SAMPLE_ID_ALL (PERF_SAMPLE_TID | PERF_SAMPLE_TIME | \ + PERF_SAMPLE_ID | PERF_SAMPLE_STREAM_ID | \ + PERF_SAMPLE_CPU | PERF_SAMPLE_IDENTIFIER) + +static void __perf_event_header__init_id(struct perf_sample_data *data, struct perf_event *event, u64 sample_type) { data->type = event->attr.sample_type; - header->size += event->id_header_size; + data->sample_flags |= data->type & PERF_SAMPLE_ID_ALL; if (sample_type & PERF_SAMPLE_TID) { /* namespace issues */ @@ -7079,8 +7081,10 @@ void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) { - if (event->attr.sample_id_all) - __perf_event_header__init_id(header, data, event, event->attr.sample_type); + if (event->attr.sample_id_all) { + header->size += event->id_header_size; + __perf_event_header__init_id(data, event, event->attr.sample_type); + } } static void __perf_event__output_id_sample(struct perf_output_handle *handle, @@ -7310,7 +7314,7 @@ void perf_output_sample(struct perf_output_handle *handle, } if (sample_type & PERF_SAMPLE_BRANCH_STACK) { - if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) { + if (data->br_stack) { size_t size; size = data->br_stack->nr @@ -7554,83 +7558,68 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) return callchain ?: &__empty_callchain; } -void perf_prepare_sample(struct perf_event_header *header, - struct perf_sample_data *data, +static __always_inline u64 __cond_set(u64 flags, u64 s, u64 d) +{ + return d * !!(flags & s); +} + +void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { u64 sample_type = event->attr.sample_type; u64 filtered_sample_type; - header->type = PERF_RECORD_SAMPLE; - header->size = sizeof(*header) + event->header_size; - - header->misc = 0; - header->misc |= perf_misc_flags(regs); - /* - * Clear the sample flags that have already been done by the - * PMU driver. + * Add the sample flags that are dependent to others. And clear the + * sample flags that have already been done by the PMU driver. */ - filtered_sample_type = sample_type & ~data->sample_flags; - __perf_event_header__init_id(header, data, event, filtered_sample_type); - - if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE)) - data->ip = perf_instruction_pointer(regs); - - if (sample_type & PERF_SAMPLE_CALLCHAIN) { - int size = 1; - - if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN) - data->callchain = perf_callchain(event, regs); + filtered_sample_type = sample_type; + filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_CODE_PAGE_SIZE, + PERF_SAMPLE_IP); + filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_DATA_PAGE_SIZE | + PERF_SAMPLE_PHYS_ADDR, PERF_SAMPLE_ADDR); + filtered_sample_type |= __cond_set(sample_type, PERF_SAMPLE_STACK_USER, + PERF_SAMPLE_REGS_USER); + filtered_sample_type &= ~data->sample_flags; - size += data->callchain->nr; - - header->size += size * sizeof(u64); + if (filtered_sample_type == 0) { + /* Make sure it has the correct data->type for output */ + data->type = event->attr.sample_type; + return; } - if (sample_type & PERF_SAMPLE_RAW) { - struct perf_raw_record *raw = data->raw; - int size; + __perf_event_header__init_id(data, event, filtered_sample_type); - if (raw && (data->sample_flags & PERF_SAMPLE_RAW)) { - struct perf_raw_frag *frag = &raw->frag; - u32 sum = 0; + if (filtered_sample_type & PERF_SAMPLE_IP) { + data->ip = perf_instruction_pointer(regs); + data->sample_flags |= PERF_SAMPLE_IP; + } - do { - sum += frag->size; - if (perf_raw_frag_last(frag)) - break; - frag = frag->next; - } while (1); + if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN) + perf_sample_save_callchain(data, event, regs); - size = round_up(sum + sizeof(u32), sizeof(u64)); - raw->size = size - sizeof(u32); - frag->pad = raw->size - sum; - } else { - size = sizeof(u64); - data->raw = NULL; - } - - header->size += size; + if (filtered_sample_type & PERF_SAMPLE_RAW) { + data->raw = NULL; + data->dyn_size += sizeof(u64); + data->sample_flags |= PERF_SAMPLE_RAW; } - if (sample_type & PERF_SAMPLE_BRANCH_STACK) { - int size = sizeof(u64); /* nr */ - if (data->sample_flags & PERF_SAMPLE_BRANCH_STACK) { - if (branch_sample_hw_index(event)) - size += sizeof(u64); - - size += data->br_stack->nr - * sizeof(struct perf_branch_entry); - } - header->size += size; + if (filtered_sample_type & PERF_SAMPLE_BRANCH_STACK) { + data->br_stack = NULL; + data->dyn_size += sizeof(u64); + data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } - if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER)) + if (filtered_sample_type & PERF_SAMPLE_REGS_USER) perf_sample_regs_user(&data->regs_user, regs); - if (sample_type & PERF_SAMPLE_REGS_USER) { + /* + * It cannot use the filtered_sample_type here as REGS_USER can be set + * by STACK_USER (using __cond_set() above) and we don't want to update + * the dyn_size if it's not requested by users. + */ + if ((sample_type & ~data->sample_flags) & PERF_SAMPLE_REGS_USER) { /* regs dump ABI info */ int size = sizeof(u64); @@ -7639,10 +7628,11 @@ void perf_prepare_sample(struct perf_event_header *header, size += hweight64(mask) * sizeof(u64); } - header->size += size; + data->dyn_size += size; + data->sample_flags |= PERF_SAMPLE_REGS_USER; } - if (sample_type & PERF_SAMPLE_STACK_USER) { + if (filtered_sample_type & PERF_SAMPLE_STACK_USER) { /* * Either we need PERF_SAMPLE_STACK_USER bit to be always * processed as the last one or have additional check added @@ -7650,9 +7640,10 @@ void perf_prepare_sample(struct perf_event_header *header, * up the rest of the sample size. */ u16 stack_size = event->attr.sample_stack_user; + u16 header_size = perf_sample_data_size(data, event); u16 size = sizeof(u64); - stack_size = perf_sample_ustack_size(stack_size, header->size, + stack_size = perf_sample_ustack_size(stack_size, header_size, data->regs_user.regs); /* @@ -7664,24 +7655,31 @@ void perf_prepare_sample(struct perf_event_header *header, size += sizeof(u64) + stack_size; data->stack_user_size = stack_size; - header->size += size; + data->dyn_size += size; + data->sample_flags |= PERF_SAMPLE_STACK_USER; } - if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE) + if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE) { data->weight.full = 0; + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } - if (filtered_sample_type & PERF_SAMPLE_DATA_SRC) + if (filtered_sample_type & PERF_SAMPLE_DATA_SRC) { data->data_src.val = PERF_MEM_NA; + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } - if (filtered_sample_type & PERF_SAMPLE_TRANSACTION) + if (filtered_sample_type & PERF_SAMPLE_TRANSACTION) { data->txn = 0; + data->sample_flags |= PERF_SAMPLE_TRANSACTION; + } - if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_DATA_PAGE_SIZE)) { - if (filtered_sample_type & PERF_SAMPLE_ADDR) - data->addr = 0; + if (filtered_sample_type & PERF_SAMPLE_ADDR) { + data->addr = 0; + data->sample_flags |= PERF_SAMPLE_ADDR; } - if (sample_type & PERF_SAMPLE_REGS_INTR) { + if (filtered_sample_type & PERF_SAMPLE_REGS_INTR) { /* regs dump ABI info */ int size = sizeof(u64); @@ -7693,20 +7691,23 @@ void perf_prepare_sample(struct perf_event_header *header, size += hweight64(mask) * sizeof(u64); } - header->size += size; + data->dyn_size += size; + data->sample_flags |= PERF_SAMPLE_REGS_INTR; } - if (sample_type & PERF_SAMPLE_PHYS_ADDR && - filtered_sample_type & PERF_SAMPLE_PHYS_ADDR) + if (filtered_sample_type & PERF_SAMPLE_PHYS_ADDR) { data->phys_addr = perf_virt_to_phys(data->addr); + data->sample_flags |= PERF_SAMPLE_PHYS_ADDR; + } #ifdef CONFIG_CGROUP_PERF - if (sample_type & PERF_SAMPLE_CGROUP) { + if (filtered_sample_type & PERF_SAMPLE_CGROUP) { struct cgroup *cgrp; /* protected by RCU */ cgrp = task_css_check(current, perf_event_cgrp_id, 1)->cgroup; data->cgroup = cgroup_id(cgrp); + data->sample_flags |= PERF_SAMPLE_CGROUP; } #endif @@ -7715,16 +7716,21 @@ void perf_prepare_sample(struct perf_event_header *header, * require PERF_SAMPLE_ADDR, kernel implicitly retrieve the data->addr, * but the value will not dump to the userspace. */ - if (sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) + if (filtered_sample_type & PERF_SAMPLE_DATA_PAGE_SIZE) { data->data_page_size = perf_get_page_size(data->addr); + data->sample_flags |= PERF_SAMPLE_DATA_PAGE_SIZE; + } - if (sample_type & PERF_SAMPLE_CODE_PAGE_SIZE) + if (filtered_sample_type & PERF_SAMPLE_CODE_PAGE_SIZE) { data->code_page_size = perf_get_page_size(data->ip); + data->sample_flags |= PERF_SAMPLE_CODE_PAGE_SIZE; + } - if (sample_type & PERF_SAMPLE_AUX) { + if (filtered_sample_type & PERF_SAMPLE_AUX) { u64 size; + u16 header_size = perf_sample_data_size(data, event); - header->size += sizeof(u64); /* size */ + header_size += sizeof(u64); /* size */ /* * Given the 16bit nature of header::size, an AUX sample can @@ -7732,14 +7738,26 @@ void perf_prepare_sample(struct perf_event_header *header, * Make sure this doesn't happen by using up to U16_MAX bytes * per sample in total (rounded down to 8 byte boundary). */ - size = min_t(size_t, U16_MAX - header->size, + size = min_t(size_t, U16_MAX - header_size, event->attr.aux_sample_size); size = rounddown(size, 8); size = perf_prepare_sample_aux(event, data, size); - WARN_ON_ONCE(size + header->size > U16_MAX); - header->size += size; + WARN_ON_ONCE(size + header_size > U16_MAX); + data->dyn_size += size + sizeof(u64); /* size above */ + data->sample_flags |= PERF_SAMPLE_AUX; } +} + +void perf_prepare_header(struct perf_event_header *header, + struct perf_sample_data *data, + struct perf_event *event, + struct pt_regs *regs) +{ + header->type = PERF_RECORD_SAMPLE; + header->size = perf_sample_data_size(data, event); + header->misc = perf_misc_flags(regs); + /* * If you're adding more sample types here, you likely need to do * something about the overflowing header::size, like repurpose the @@ -7767,7 +7785,8 @@ __perf_event_output(struct perf_event *event, /* protect the callchain buffers */ rcu_read_lock(); - perf_prepare_sample(&header, data, event, regs); + perf_prepare_sample(data, event, regs); + perf_prepare_header(&header, data, event, regs); err = output_begin(&handle, data, event, header.size); if (err) @@ -9399,6 +9418,7 @@ void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) perf_output_end(&handle); } +EXPORT_SYMBOL_GPL(perf_report_aux_output_id); static int __perf_event_account_interrupt(struct perf_event *event, int throttle) @@ -10125,8 +10145,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, }; perf_sample_data_init(&data, 0, 0); - data.raw = &raw; - data.sample_flags |= PERF_SAMPLE_RAW; + perf_sample_save_raw_data(&data, &raw); perf_trace_buf_update(record, event_type); @@ -10333,13 +10352,7 @@ static void bpf_overflow_handler(struct perf_event *event, rcu_read_lock(); prog = READ_ONCE(event->prog); if (prog) { - if (prog->call_get_stack && - (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) && - !(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) { - data->callchain = perf_callchain(event, regs); - data->sample_flags |= PERF_SAMPLE_CALLCHAIN; - } - + perf_prepare_sample(data, event, regs); ret = bpf_prog_run(prog, &ctx); } rcu_read_unlock(); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index d9e357b7e17c..59887c69d54c 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -22,7 +22,6 @@ #include <linux/swap.h> /* folio_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ -#include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/percpu-rwsem.h> #include <linux/task_work.h> #include <linux/shmem_fs.h> @@ -161,7 +160,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, int err; struct mmu_notifier_range range; - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + PAGE_SIZE); if (new_page) { @@ -1352,7 +1351,7 @@ static int delayed_ref_ctr_inc(struct vm_area_struct *vma) } /* - * Called from mmap_region/vma_adjust with mm->mmap_lock acquired. + * Called from mmap_region/vma_merge with mm->mmap_lock acquired. * * Currently we ignore all errors and always return 0, the callers * can't handle the failure anyway. diff --git a/kernel/exit.c b/kernel/exit.c index 15dc2ec80c46..f2afdb0add7c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -807,6 +807,8 @@ void __noreturn do_exit(long code) struct task_struct *tsk = current; int group_dead; + WARN_ON(irqs_disabled()); + synchronize_group_exit(tsk, code); WARN_ON(tsk->plug); @@ -938,6 +940,11 @@ void __noreturn make_task_dead(int signr) if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); + if (unlikely(irqs_disabled())) { + pr_info("note: %s[%d] exited with irqs disabled\n", + current->comm, task_pid_nr(current)); + local_irq_enable(); + } if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), @@ -1898,7 +1905,14 @@ bool thread_group_exited(struct pid *pid) } EXPORT_SYMBOL(thread_group_exited); -__weak void abort(void) +/* + * This needs to be __function_aligned as GCC implicitly makes any + * implementation of abort() cold and drops alignment specified by + * -falign-functions=N. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11 + */ +__weak __function_aligned void abort(void) { BUG(); diff --git a/kernel/fail_function.c b/kernel/fail_function.c index a7ccd2930c5f..d971a0189319 100644 --- a/kernel/fail_function.c +++ b/kernel/fail_function.c @@ -163,10 +163,7 @@ static void fei_debugfs_add_attr(struct fei_attr *attr) static void fei_debugfs_remove_attr(struct fei_attr *attr) { - struct dentry *dir; - - dir = debugfs_lookup(attr->kp.symbol_name, fei_debugfs_dir); - debugfs_remove_recursive(dir); + debugfs_lookup_and_remove(attr->kp.symbol_name, fei_debugfs_dir); } static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs) diff --git a/kernel/fork.c b/kernel/fork.c index 9f7fe3541897..d8cda4c6de6c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -472,7 +472,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) * orig->shared.rb may be modified concurrently, but the clone * will be reinitialized. */ - *new = data_race(*orig); + data_race(memcpy(new, orig, sizeof(*new))); INIT_LIST_HEAD(&new->anon_vma_chain); dup_anon_vma_name(orig, new); } @@ -585,8 +585,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, int retval; unsigned long charge = 0; LIST_HEAD(uf); - MA_STATE(old_mas, &oldmm->mm_mt, 0, 0); - MA_STATE(mas, &mm->mm_mt, 0, 0); + VMA_ITERATOR(old_vmi, oldmm, 0); + VMA_ITERATOR(vmi, mm, 0); uprobe_start_dup_mmap(); if (mmap_write_lock_killable(oldmm)) { @@ -613,11 +613,11 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; khugepaged_fork(mm, oldmm); - retval = mas_expected_entries(&mas, oldmm->map_count); + retval = vma_iter_bulk_alloc(&vmi, oldmm->map_count); if (retval) goto out; - mas_for_each(&old_mas, mpnt, ULONG_MAX) { + for_each_vma(old_vmi, mpnt) { struct file *file; if (mpnt->vm_flags & VM_DONTCOPY) { @@ -659,7 +659,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, tmp->anon_vma = NULL; } else if (anon_vma_fork(tmp, mpnt)) goto fail_nomem_anon_vma_fork; - tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT); + vm_flags_clear(tmp, VM_LOCKED_MASK); file = tmp->vm_file; if (file) { struct address_space *mapping = file->f_mapping; @@ -683,11 +683,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, hugetlb_dup_vma_private(tmp); /* Link the vma into the MT */ - mas.index = tmp->vm_start; - mas.last = tmp->vm_end - 1; - mas_store(&mas, tmp); - if (mas_is_err(&mas)) - goto fail_nomem_mas_store; + if (vma_iter_bulk_store(&vmi, tmp)) + goto fail_nomem_vmi_store; mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) @@ -702,7 +699,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, /* a new mm has just been created */ retval = arch_dup_mmap(oldmm, mm); loop_out: - mas_destroy(&mas); + vma_iter_free(&vmi); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); @@ -712,7 +709,7 @@ fail_uprobe_end: uprobe_end_dup_mmap(); return retval; -fail_nomem_mas_store: +fail_nomem_vmi_store: unlink_anon_vmas(tmp); fail_nomem_anon_vma_fork: mpol_put(vma_policy(tmp)); @@ -1044,7 +1041,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) #endif #ifdef CONFIG_BLK_CGROUP - tsk->throttle_queue = NULL; + tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif @@ -1060,6 +1057,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->reported_split_lock = 0; #endif +#ifdef CONFIG_SCHED_MM_CID + tsk->mm_cid = -1; + tsk->mm_cid_active = 0; +#endif return tsk; free_stack: @@ -1169,6 +1170,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); + mm_init_cid(mm); return mm; fail_pcpu: @@ -1601,6 +1603,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) tsk->mm = mm; tsk->active_mm = mm; + sched_mm_cid_fork(tsk); return 0; } @@ -2933,7 +2936,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs) * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ - if (kargs->flags & (CLONE_DETACHED | CSIGNAL)) + if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == @@ -3034,7 +3037,7 @@ void __init mm_cache_init(void) * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ - mm_size = sizeof(struct mm_struct) + cpumask_size(); + mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 473036b43c83..1ef9a87511f5 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -7,13 +7,15 @@ set -e sfile="$(readlink -f "$0")" outdir="$(pwd)" tarfile=$1 -cpio_dir=$outdir/$tarfile.tmp +cpio_dir=$outdir/${tarfile%/*}/.tmp_cpio_dir dir_list=" include/ arch/$SRCARCH/include/ " +type cpio > /dev/null + # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. diff --git a/kernel/hung_task.c b/kernel/hung_task.c index c71889f3f3fc..322813366c6c 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -142,6 +142,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; + if (!sysctl_hung_task_warnings) + pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n"); } touch_nmi_watchdog(); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index b64c44ae4c25..2531f3496ab6 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -86,6 +86,11 @@ config GENERIC_IRQ_IPI depends on SMP select IRQ_DOMAIN_HIERARCHY +# Generic IRQ IPI Mux support +config GENERIC_IRQ_IPI_MUX + bool + depends on SMP + # Generic MSI hierarchical interrupt domain support config GENERIC_MSI_IRQ bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index b4f53717d143..f19d3080bf11 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_GENERIC_IRQ_MIGRATION) += cpuhotplug.o obj-$(CONFIG_PM_SLEEP) += pm.o obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o obj-$(CONFIG_GENERIC_IRQ_IPI) += ipi.o +obj-$(CONFIG_GENERIC_IRQ_IPI_MUX) += ipi-mux.o obj-$(CONFIG_SMP) += affinity.o obj-$(CONFIG_GENERIC_IRQ_DEBUGFS) += debugfs.o obj-$(CONFIG_GENERIC_IRQ_MATRIX_ALLOCATOR) += matrix.o diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d9a5c1d65a79..44a4eba80315 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -7,398 +7,7 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/cpu.h> -#include <linux/sort.h> - -static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk, - unsigned int cpus_per_vec) -{ - const struct cpumask *siblmsk; - int cpu, sibl; - - for ( ; cpus_per_vec > 0; ) { - cpu = cpumask_first(nmsk); - - /* Should not happen, but I'm too lazy to think about it */ - if (cpu >= nr_cpu_ids) - return; - - cpumask_clear_cpu(cpu, nmsk); - cpumask_set_cpu(cpu, irqmsk); - cpus_per_vec--; - - /* If the cpu has siblings, use them first */ - siblmsk = topology_sibling_cpumask(cpu); - for (sibl = -1; cpus_per_vec > 0; ) { - sibl = cpumask_next(sibl, siblmsk); - if (sibl >= nr_cpu_ids) - break; - if (!cpumask_test_and_clear_cpu(sibl, nmsk)) - continue; - cpumask_set_cpu(sibl, irqmsk); - cpus_per_vec--; - } - } -} - -static cpumask_var_t *alloc_node_to_cpumask(void) -{ - cpumask_var_t *masks; - int node; - - masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL); - if (!masks) - return NULL; - - for (node = 0; node < nr_node_ids; node++) { - if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL)) - goto out_unwind; - } - - return masks; - -out_unwind: - while (--node >= 0) - free_cpumask_var(masks[node]); - kfree(masks); - return NULL; -} - -static void free_node_to_cpumask(cpumask_var_t *masks) -{ - int node; - - for (node = 0; node < nr_node_ids; node++) - free_cpumask_var(masks[node]); - kfree(masks); -} - -static void build_node_to_cpumask(cpumask_var_t *masks) -{ - int cpu; - - for_each_possible_cpu(cpu) - cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]); -} - -static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask, - const struct cpumask *mask, nodemask_t *nodemsk) -{ - int n, nodes = 0; - - /* Calculate the number of nodes in the supplied affinity mask */ - for_each_node(n) { - if (cpumask_intersects(mask, node_to_cpumask[n])) { - node_set(n, *nodemsk); - nodes++; - } - } - return nodes; -} - -struct node_vectors { - unsigned id; - - union { - unsigned nvectors; - unsigned ncpus; - }; -}; - -static int ncpus_cmp_func(const void *l, const void *r) -{ - const struct node_vectors *ln = l; - const struct node_vectors *rn = r; - - return ln->ncpus - rn->ncpus; -} - -/* - * Allocate vector number for each node, so that for each node: - * - * 1) the allocated number is >= 1 - * - * 2) the allocated numbver is <= active CPU number of this node - * - * The actual allocated total vectors may be less than @numvecs when - * active total CPU number is less than @numvecs. - * - * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]' - * for each node. - */ -static void alloc_nodes_vectors(unsigned int numvecs, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - const nodemask_t nodemsk, - struct cpumask *nmsk, - struct node_vectors *node_vectors) -{ - unsigned n, remaining_ncpus = 0; - - for (n = 0; n < nr_node_ids; n++) { - node_vectors[n].id = n; - node_vectors[n].ncpus = UINT_MAX; - } - - for_each_node_mask(n, nodemsk) { - unsigned ncpus; - - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - ncpus = cpumask_weight(nmsk); - - if (!ncpus) - continue; - remaining_ncpus += ncpus; - node_vectors[n].ncpus = ncpus; - } - - numvecs = min_t(unsigned, remaining_ncpus, numvecs); - - sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]), - ncpus_cmp_func, NULL); - - /* - * Allocate vectors for each node according to the ratio of this - * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is - * bigger than number of active numa nodes. Always start the - * allocation from the node with minimized nr_cpus. - * - * This way guarantees that each active node gets allocated at - * least one vector, and the theory is simple: over-allocation - * is only done when this node is assigned by one vector, so - * other nodes will be allocated >= 1 vector, since 'numvecs' is - * bigger than number of numa nodes. - * - * One perfect invariant is that number of allocated vectors for - * each node is <= CPU count of this node: - * - * 1) suppose there are two nodes: A and B - * ncpu(X) is CPU count of node X - * vecs(X) is the vector count allocated to node X via this - * algorithm - * - * ncpu(A) <= ncpu(B) - * ncpu(A) + ncpu(B) = N - * vecs(A) + vecs(B) = V - * - * vecs(A) = max(1, round_down(V * ncpu(A) / N)) - * vecs(B) = V - vecs(A) - * - * both N and V are integer, and 2 <= V <= N, suppose - * V = N - delta, and 0 <= delta <= N - 2 - * - * 2) obviously vecs(A) <= ncpu(A) because: - * - * if vecs(A) is 1, then vecs(A) <= ncpu(A) given - * ncpu(A) >= 1 - * - * otherwise, - * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N - * - * 3) prove how vecs(B) <= ncpu(B): - * - * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be - * over-allocated, so vecs(B) <= ncpu(B), - * - * otherwise: - * - * vecs(A) = - * round_down(V * ncpu(A) / N) = - * round_down((N - delta) * ncpu(A) / N) = - * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >= - * round_down((N * ncpu(A) - delta * N) / N) = - * cpu(A) - delta - * - * then: - * - * vecs(A) - V >= ncpu(A) - delta - V - * => - * V - vecs(A) <= V + delta - ncpu(A) - * => - * vecs(B) <= N - ncpu(A) - * => - * vecs(B) <= cpu(B) - * - * For nodes >= 3, it can be thought as one node and another big - * node given that is exactly what this algorithm is implemented, - * and we always re-calculate 'remaining_ncpus' & 'numvecs', and - * finally for each node X: vecs(X) <= ncpu(X). - * - */ - for (n = 0; n < nr_node_ids; n++) { - unsigned nvectors, ncpus; - - if (node_vectors[n].ncpus == UINT_MAX) - continue; - - WARN_ON_ONCE(numvecs == 0); - - ncpus = node_vectors[n].ncpus; - nvectors = max_t(unsigned, 1, - numvecs * ncpus / remaining_ncpus); - WARN_ON_ONCE(nvectors > ncpus); - - node_vectors[n].nvectors = nvectors; - - remaining_ncpus -= ncpus; - numvecs -= nvectors; - } -} - -static int __irq_build_affinity_masks(unsigned int startvec, - unsigned int numvecs, - unsigned int firstvec, - cpumask_var_t *node_to_cpumask, - const struct cpumask *cpu_mask, - struct cpumask *nmsk, - struct irq_affinity_desc *masks) -{ - unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0; - unsigned int last_affv = firstvec + numvecs; - unsigned int curvec = startvec; - nodemask_t nodemsk = NODE_MASK_NONE; - struct node_vectors *node_vectors; - - if (cpumask_empty(cpu_mask)) - return 0; - - nodes = get_nodes_in_cpumask(node_to_cpumask, cpu_mask, &nodemsk); - - /* - * If the number of nodes in the mask is greater than or equal the - * number of vectors we just spread the vectors across the nodes. - */ - if (numvecs <= nodes) { - for_each_node_mask(n, nodemsk) { - /* Ensure that only CPUs which are in both masks are set */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]); - cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk); - if (++curvec == last_affv) - curvec = firstvec; - } - return numvecs; - } - - node_vectors = kcalloc(nr_node_ids, - sizeof(struct node_vectors), - GFP_KERNEL); - if (!node_vectors) - return -ENOMEM; - - /* allocate vector number for each node */ - alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask, - nodemsk, nmsk, node_vectors); - - for (i = 0; i < nr_node_ids; i++) { - unsigned int ncpus, v; - struct node_vectors *nv = &node_vectors[i]; - - if (nv->nvectors == UINT_MAX) - continue; - - /* Get the cpus on this node which are in the mask */ - cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]); - ncpus = cpumask_weight(nmsk); - if (!ncpus) - continue; - - WARN_ON_ONCE(nv->nvectors > ncpus); - - /* Account for rounding errors */ - extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors); - - /* Spread allocated vectors on CPUs of the current node */ - for (v = 0; v < nv->nvectors; v++, curvec++) { - cpus_per_vec = ncpus / nv->nvectors; - - /* Account for extra vectors to compensate rounding errors */ - if (extra_vecs) { - cpus_per_vec++; - --extra_vecs; - } - - /* - * wrapping has to be considered given 'startvec' - * may start anywhere - */ - if (curvec >= last_affv) - curvec = firstvec; - irq_spread_init_one(&masks[curvec].mask, nmsk, - cpus_per_vec); - } - done += nv->nvectors; - } - kfree(node_vectors); - return done; -} - -/* - * build affinity in two stages: - * 1) spread present CPU on these vectors - * 2) spread other possible CPUs on these vectors - */ -static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs, - unsigned int firstvec, - struct irq_affinity_desc *masks) -{ - unsigned int curvec = startvec, nr_present = 0, nr_others = 0; - cpumask_var_t *node_to_cpumask; - cpumask_var_t nmsk, npresmsk; - int ret = -ENOMEM; - - if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) - return ret; - - if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL)) - goto fail_nmsk; - - node_to_cpumask = alloc_node_to_cpumask(); - if (!node_to_cpumask) - goto fail_npresmsk; - - /* Stabilize the cpumasks */ - cpus_read_lock(); - build_node_to_cpumask(node_to_cpumask); - - /* Spread on present CPUs starting from affd->pre_vectors */ - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, cpu_present_mask, - nmsk, masks); - if (ret < 0) - goto fail_build_affinity; - nr_present = ret; - - /* - * Spread on non present CPUs starting from the next vector to be - * handled. If the spreading of present CPUs already exhausted the - * vector space, assign the non present CPUs to the already spread - * out vectors. - */ - if (nr_present >= numvecs) - curvec = firstvec; - else - curvec = firstvec + nr_present; - cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); - ret = __irq_build_affinity_masks(curvec, numvecs, firstvec, - node_to_cpumask, npresmsk, nmsk, - masks); - if (ret >= 0) - nr_others = ret; - - fail_build_affinity: - cpus_read_unlock(); - - if (ret >= 0) - WARN_ON(nr_present + nr_others < numvecs); - - free_node_to_cpumask(node_to_cpumask); - - fail_npresmsk: - free_cpumask_var(npresmsk); - - fail_nmsk: - free_cpumask_var(nmsk); - return ret < 0 ? ret : 0; -} +#include <linux/group_cpus.h> static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs) { @@ -461,14 +70,18 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd) */ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) { unsigned int this_vecs = affd->set_size[i]; - int ret; + int j; + struct cpumask *result = group_cpus_evenly(this_vecs); - ret = irq_build_affinity_masks(curvec, this_vecs, - curvec, masks); - if (ret) { + if (!result) { kfree(masks); return NULL; } + + for (j = 0; j < this_vecs; j++) + cpumask_copy(&masks[curvec + j].mask, &result[j]); + kfree(result); + curvec += this_vecs; usedvecs += this_vecs; } diff --git a/kernel/irq/ipi-mux.c b/kernel/irq/ipi-mux.c new file mode 100644 index 000000000000..fa4fc18c6131 --- /dev/null +++ b/kernel/irq/ipi-mux.c @@ -0,0 +1,206 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Multiplex several virtual IPIs over a single HW IPI. + * + * Copyright The Asahi Linux Contributors + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "ipi-mux: " fmt +#include <linux/cpu.h> +#include <linux/init.h> +#include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/jump_label.h> +#include <linux/percpu.h> +#include <linux/smp.h> + +struct ipi_mux_cpu { + atomic_t enable; + atomic_t bits; +}; + +static struct ipi_mux_cpu __percpu *ipi_mux_pcpu; +static struct irq_domain *ipi_mux_domain; +static void (*ipi_mux_send)(unsigned int cpu); + +static void ipi_mux_mask(struct irq_data *d) +{ + struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu); + + atomic_andnot(BIT(irqd_to_hwirq(d)), &icpu->enable); +} + +static void ipi_mux_unmask(struct irq_data *d) +{ + struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu); + u32 ibit = BIT(irqd_to_hwirq(d)); + + atomic_or(ibit, &icpu->enable); + + /* + * The atomic_or() above must complete before the atomic_read() + * below to avoid racing ipi_mux_send_mask(). + */ + smp_mb__after_atomic(); + + /* If a pending IPI was unmasked, raise a parent IPI immediately. */ + if (atomic_read(&icpu->bits) & ibit) + ipi_mux_send(smp_processor_id()); +} + +static void ipi_mux_send_mask(struct irq_data *d, const struct cpumask *mask) +{ + struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu); + u32 ibit = BIT(irqd_to_hwirq(d)); + unsigned long pending; + int cpu; + + for_each_cpu(cpu, mask) { + icpu = per_cpu_ptr(ipi_mux_pcpu, cpu); + + /* + * This sequence is the mirror of the one in ipi_mux_unmask(); + * see the comment there. Additionally, release semantics + * ensure that the vIPI flag set is ordered after any shared + * memory accesses that precede it. This therefore also pairs + * with the atomic_fetch_andnot in ipi_mux_process(). + */ + pending = atomic_fetch_or_release(ibit, &icpu->bits); + + /* + * The atomic_fetch_or_release() above must complete + * before the atomic_read() below to avoid racing with + * ipi_mux_unmask(). + */ + smp_mb__after_atomic(); + + /* + * The flag writes must complete before the physical IPI is + * issued to another CPU. This is implied by the control + * dependency on the result of atomic_read() below, which is + * itself already ordered after the vIPI flag write. + */ + if (!(pending & ibit) && (atomic_read(&icpu->enable) & ibit)) + ipi_mux_send(cpu); + } +} + +static const struct irq_chip ipi_mux_chip = { + .name = "IPI Mux", + .irq_mask = ipi_mux_mask, + .irq_unmask = ipi_mux_unmask, + .ipi_send_mask = ipi_mux_send_mask, +}; + +static int ipi_mux_domain_alloc(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_set_percpu_devid(virq + i); + irq_domain_set_info(d, virq + i, i, &ipi_mux_chip, NULL, + handle_percpu_devid_irq, NULL, NULL); + } + + return 0; +} + +static const struct irq_domain_ops ipi_mux_domain_ops = { + .alloc = ipi_mux_domain_alloc, + .free = irq_domain_free_irqs_top, +}; + +/** + * ipi_mux_process - Process multiplexed virtual IPIs + */ +void ipi_mux_process(void) +{ + struct ipi_mux_cpu *icpu = this_cpu_ptr(ipi_mux_pcpu); + irq_hw_number_t hwirq; + unsigned long ipis; + unsigned int en; + + /* + * Reading enable mask does not need to be ordered as long as + * this function is called from interrupt handler because only + * the CPU itself can change it's own enable mask. + */ + en = atomic_read(&icpu->enable); + + /* + * Clear the IPIs we are about to handle. This pairs with the + * atomic_fetch_or_release() in ipi_mux_send_mask(). + */ + ipis = atomic_fetch_andnot(en, &icpu->bits) & en; + + for_each_set_bit(hwirq, &ipis, BITS_PER_TYPE(int)) + generic_handle_domain_irq(ipi_mux_domain, hwirq); +} + +/** + * ipi_mux_create - Create virtual IPIs multiplexed on top of a single + * parent IPI. + * @nr_ipi: number of virtual IPIs to create. This should + * be <= BITS_PER_TYPE(int) + * @mux_send: callback to trigger parent IPI for a particular CPU + * + * Returns first virq of the newly created virtual IPIs upon success + * or <=0 upon failure + */ +int ipi_mux_create(unsigned int nr_ipi, void (*mux_send)(unsigned int cpu)) +{ + struct fwnode_handle *fwnode; + struct irq_domain *domain; + int rc; + + if (ipi_mux_domain) + return -EEXIST; + + if (BITS_PER_TYPE(int) < nr_ipi || !mux_send) + return -EINVAL; + + ipi_mux_pcpu = alloc_percpu(typeof(*ipi_mux_pcpu)); + if (!ipi_mux_pcpu) + return -ENOMEM; + + fwnode = irq_domain_alloc_named_fwnode("IPI-Mux"); + if (!fwnode) { + pr_err("unable to create IPI Mux fwnode\n"); + rc = -ENOMEM; + goto fail_free_cpu; + } + + domain = irq_domain_create_linear(fwnode, nr_ipi, + &ipi_mux_domain_ops, NULL); + if (!domain) { + pr_err("unable to add IPI Mux domain\n"); + rc = -ENOMEM; + goto fail_free_fwnode; + } + + domain->flags |= IRQ_DOMAIN_FLAG_IPI_SINGLE; + irq_domain_update_bus_token(domain, DOMAIN_BUS_IPI); + + rc = irq_domain_alloc_irqs(domain, nr_ipi, NUMA_NO_NODE, NULL); + if (rc <= 0) { + pr_err("unable to alloc IRQs from IPI Mux domain\n"); + goto fail_free_domain; + } + + ipi_mux_domain = domain; + ipi_mux_send = mux_send; + + return rc; + +fail_free_domain: + irq_domain_remove(domain); +fail_free_fwnode: + irq_domain_free_fwnode(fwnode); +fail_free_cpu: + free_percpu(ipi_mux_pcpu); + return rc; +} diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index bbd945bacef0..961d4af76af3 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -188,9 +188,9 @@ EXPORT_SYMBOL_GPL(ipi_get_hwirq); static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, const struct cpumask *dest, unsigned int cpu) { - const struct cpumask *ipimask = irq_data_get_affinity_mask(data); + const struct cpumask *ipimask; - if (!chip || !ipimask) + if (!chip || !data) return -EINVAL; if (!chip->ipi_send_single && !chip->ipi_send_mask) @@ -199,6 +199,10 @@ static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, if (cpu >= nr_cpu_ids) return -EINVAL; + ipimask = irq_data_get_affinity_mask(data); + if (!ipimask) + return -EINVAL; + if (dest) { if (!cpumask_subset(dest, ipimask)) return -EINVAL; diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index fd0996274401..240e145e969f 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -277,7 +277,7 @@ static struct attribute *irq_attrs[] = { }; ATTRIBUTE_GROUPS(irq); -static struct kobj_type irq_kobj_type = { +static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = irq_groups, @@ -335,7 +335,7 @@ postcore_initcall(irq_sysfs_init); #else /* !CONFIG_SYSFS */ -static struct kobj_type irq_kobj_type = { +static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, }; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8fe1da9614ee..f34760a1e222 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -25,6 +25,9 @@ static DEFINE_MUTEX(irq_domain_mutex); static struct irq_domain *irq_default_domain; +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity); static void irq_domain_check_hierarchy(struct irq_domain *domain); struct irqchip_fwid { @@ -114,7 +117,7 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) { struct irqchip_fwid *fwid; - if (WARN_ON(!is_fwnode_irqchip(fwnode))) + if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode))) return; fwid = container_of(fwnode, struct irqchip_fwid, fwnode); @@ -123,23 +126,12 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(irq_domain_free_fwnode); -/** - * __irq_domain_add() - Allocate a new irq_domain data structure - * @fwnode: firmware node for the interrupt controller - * @size: Size of linear map; 0 for radix mapping only - * @hwirq_max: Maximum number of interrupts supported by controller - * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no - * direct mapping - * @ops: domain callbacks - * @host_data: Controller private data pointer - * - * Allocates and initializes an irq_domain structure. - * Returns pointer to IRQ domain, or NULL on failure. - */ -struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, - irq_hw_number_t hwirq_max, int direct_max, - const struct irq_domain_ops *ops, - void *host_data) +static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode, + unsigned int size, + irq_hw_number_t hwirq_max, + int direct_max, + const struct irq_domain_ops *ops, + void *host_data) { struct irqchip_fwid *fwid; struct irq_domain *domain; @@ -214,25 +206,66 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int s /* Fill structure */ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL); - mutex_init(&domain->revmap_mutex); domain->ops = ops; domain->host_data = host_data; domain->hwirq_max = hwirq_max; - if (direct_max) { + if (direct_max) domain->flags |= IRQ_DOMAIN_FLAG_NO_MAP; - } domain->revmap_size = size; + /* + * Hierarchical domains use the domain lock of the root domain + * (innermost domain). + * + * For non-hierarchical domains (as for root domains), the root + * pointer is set to the domain itself so that &domain->root->mutex + * always points to the right lock. + */ + mutex_init(&domain->mutex); + domain->root = domain; + irq_domain_check_hierarchy(domain); + return domain; +} + +static void __irq_domain_publish(struct irq_domain *domain) +{ mutex_lock(&irq_domain_mutex); debugfs_add_domain_dir(domain); list_add(&domain->link, &irq_domain_list); mutex_unlock(&irq_domain_mutex); pr_debug("Added domain %s\n", domain->name); +} + +/** + * __irq_domain_add() - Allocate a new irq_domain data structure + * @fwnode: firmware node for the interrupt controller + * @size: Size of linear map; 0 for radix mapping only + * @hwirq_max: Maximum number of interrupts supported by controller + * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no + * direct mapping + * @ops: domain callbacks + * @host_data: Controller private data pointer + * + * Allocates and initializes an irq_domain structure. + * Returns pointer to IRQ domain, or NULL on failure. + */ +struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size, + irq_hw_number_t hwirq_max, int direct_max, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + domain = __irq_domain_create(fwnode, size, hwirq_max, direct_max, + ops, host_data); + if (domain) + __irq_domain_publish(domain); + return domain; } EXPORT_SYMBOL_GPL(__irq_domain_add); @@ -437,31 +470,6 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, EXPORT_SYMBOL_GPL(irq_find_matching_fwspec); /** - * irq_domain_check_msi_remap - Check whether all MSI irq domains implement - * IRQ remapping - * - * Return: false if any MSI irq domain does not support IRQ remapping, - * true otherwise (including if there is no MSI irq domain) - */ -bool irq_domain_check_msi_remap(void) -{ - struct irq_domain *h; - bool ret = true; - - mutex_lock(&irq_domain_mutex); - list_for_each_entry(h, &irq_domain_list, link) { - if (irq_domain_is_msi(h) && - !irq_domain_hierarchical_is_msi_remap(h)) { - ret = false; - break; - } - } - mutex_unlock(&irq_domain_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(irq_domain_check_msi_remap); - -/** * irq_set_default_host() - Set a "default" irq domain * @domain: default domain pointer * @@ -502,30 +510,34 @@ static bool irq_domain_is_nomap(struct irq_domain *domain) static void irq_domain_clear_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { + lockdep_assert_held(&domain->root->mutex); + if (irq_domain_is_nomap(domain)) return; - mutex_lock(&domain->revmap_mutex); if (hwirq < domain->revmap_size) rcu_assign_pointer(domain->revmap[hwirq], NULL); else radix_tree_delete(&domain->revmap_tree, hwirq); - mutex_unlock(&domain->revmap_mutex); } static void irq_domain_set_mapping(struct irq_domain *domain, irq_hw_number_t hwirq, struct irq_data *irq_data) { + /* + * This also makes sure that all domains point to the same root when + * called from irq_domain_insert_irq() for each domain in a hierarchy. + */ + lockdep_assert_held(&domain->root->mutex); + if (irq_domain_is_nomap(domain)) return; - mutex_lock(&domain->revmap_mutex); if (hwirq < domain->revmap_size) rcu_assign_pointer(domain->revmap[hwirq], irq_data); else radix_tree_insert(&domain->revmap_tree, hwirq, irq_data); - mutex_unlock(&domain->revmap_mutex); } static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) @@ -538,6 +550,9 @@ static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) return; hwirq = irq_data->hwirq; + + mutex_lock(&domain->root->mutex); + irq_set_status_flags(irq, IRQ_NOREQUEST); /* remove chip and handler */ @@ -557,10 +572,12 @@ static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq) /* Clear reverse map for this hwirq */ irq_domain_clear_mapping(domain, hwirq); + + mutex_unlock(&domain->root->mutex); } -int irq_domain_associate(struct irq_domain *domain, unsigned int virq, - irq_hw_number_t hwirq) +static int irq_domain_associate_locked(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) { struct irq_data *irq_data = irq_get_irq_data(virq); int ret; @@ -573,7 +590,6 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, if (WARN(irq_data->domain, "error: virq%i is already associated", virq)) return -EINVAL; - mutex_lock(&irq_domain_mutex); irq_data->hwirq = hwirq; irq_data->domain = domain; if (domain->ops->map) { @@ -590,23 +606,29 @@ int irq_domain_associate(struct irq_domain *domain, unsigned int virq, } irq_data->domain = NULL; irq_data->hwirq = 0; - mutex_unlock(&irq_domain_mutex); return ret; } - - /* If not already assigned, give the domain the chip's name */ - if (!domain->name && irq_data->chip) - domain->name = irq_data->chip->name; } domain->mapcount++; irq_domain_set_mapping(domain, hwirq, irq_data); - mutex_unlock(&irq_domain_mutex); irq_clear_status_flags(virq, IRQ_NOREQUEST); return 0; } + +int irq_domain_associate(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq) +{ + int ret; + + mutex_lock(&domain->root->mutex); + ret = irq_domain_associate_locked(domain, virq, hwirq); + mutex_unlock(&domain->root->mutex); + + return ret; +} EXPORT_SYMBOL_GPL(irq_domain_associate); void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, @@ -619,9 +641,8 @@ void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base, pr_debug("%s(%s, irqbase=%i, hwbase=%i, count=%i)\n", __func__, of_node_full_name(of_node), irq_base, (int)hwirq_base, count); - for (i = 0; i < count; i++) { + for (i = 0; i < count; i++) irq_domain_associate(domain, irq_base + i, hwirq_base + i); - } } EXPORT_SYMBOL_GPL(irq_domain_associate_many); @@ -668,6 +689,34 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain) EXPORT_SYMBOL_GPL(irq_create_direct_mapping); #endif +static unsigned int irq_create_mapping_affinity_locked(struct irq_domain *domain, + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) +{ + struct device_node *of_node = irq_domain_get_of_node(domain); + int virq; + + pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); + + /* Allocate a virtual interrupt number */ + virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), + affinity); + if (virq <= 0) { + pr_debug("-> virq allocation failed\n"); + return 0; + } + + if (irq_domain_associate_locked(domain, virq, hwirq)) { + irq_free_desc(virq); + return 0; + } + + pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", + hwirq, of_node_full_name(of_node), virq); + + return virq; +} + /** * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space * @domain: domain owning this hardware interrupt or NULL for default domain @@ -680,14 +729,11 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping); * on the number returned from that call. */ unsigned int irq_create_mapping_affinity(struct irq_domain *domain, - irq_hw_number_t hwirq, - const struct irq_affinity_desc *affinity) + irq_hw_number_t hwirq, + const struct irq_affinity_desc *affinity) { - struct device_node *of_node; int virq; - pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); - /* Look for default domain if necessary */ if (domain == NULL) domain = irq_default_domain; @@ -695,32 +741,19 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain, WARN(1, "%s(, %lx) called with NULL domain\n", __func__, hwirq); return 0; } - pr_debug("-> using domain @%p\n", domain); - of_node = irq_domain_get_of_node(domain); + mutex_lock(&domain->root->mutex); /* Check if mapping already exists */ virq = irq_find_mapping(domain, hwirq); if (virq) { - pr_debug("-> existing mapping on virq %d\n", virq); - return virq; - } - - /* Allocate a virtual interrupt number */ - virq = irq_domain_alloc_descs(-1, 1, hwirq, of_node_to_nid(of_node), - affinity); - if (virq <= 0) { - pr_debug("-> virq allocation failed\n"); - return 0; - } - - if (irq_domain_associate(domain, virq, hwirq)) { - irq_free_desc(virq); - return 0; + pr_debug("existing mapping on virq %d\n", virq); + goto out; } - pr_debug("irq %lu on domain %s mapped to virtual irq %u\n", - hwirq, of_node_full_name(of_node), virq); + virq = irq_create_mapping_affinity_locked(domain, hwirq, affinity); +out: + mutex_unlock(&domain->root->mutex); return virq; } @@ -789,6 +822,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) if (WARN_ON(type & ~IRQ_TYPE_SENSE_MASK)) type &= IRQ_TYPE_SENSE_MASK; + mutex_lock(&domain->root->mutex); + /* * If we've already configured this interrupt, * don't do it again, or hell will break loose. @@ -801,7 +836,7 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) * interrupt number. */ if (type == IRQ_TYPE_NONE || type == irq_get_trigger_type(virq)) - return virq; + goto out; /* * If the trigger type has not been set yet, then set @@ -809,40 +844,45 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) */ if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) { irq_data = irq_get_irq_data(virq); - if (!irq_data) - return 0; + if (!irq_data) { + virq = 0; + goto out; + } irqd_set_trigger_type(irq_data, type); - return virq; + goto out; } pr_warn("type mismatch, failed to map hwirq-%lu for %s!\n", hwirq, of_node_full_name(to_of_node(fwspec->fwnode))); - return 0; + virq = 0; + goto out; } if (irq_domain_is_hierarchy(domain)) { - virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec); - if (virq <= 0) - return 0; + virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE, + fwspec, false, NULL); + if (virq <= 0) { + virq = 0; + goto out; + } } else { /* Create mapping */ - virq = irq_create_mapping(domain, hwirq); + virq = irq_create_mapping_affinity_locked(domain, hwirq, NULL); if (!virq) - return virq; + goto out; } irq_data = irq_get_irq_data(virq); - if (!irq_data) { - if (irq_domain_is_hierarchy(domain)) - irq_domain_free_irqs(virq, 1); - else - irq_dispose_mapping(virq); - return 0; + if (WARN_ON(!irq_data)) { + virq = 0; + goto out; } /* Store trigger type */ irqd_set_trigger_type(irq_data, type); +out: + mutex_unlock(&domain->root->mutex); return virq; } @@ -1102,12 +1142,17 @@ struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent, struct irq_domain *domain; if (size) - domain = irq_domain_create_linear(fwnode, size, ops, host_data); + domain = __irq_domain_create(fwnode, size, size, 0, ops, host_data); else - domain = irq_domain_create_tree(fwnode, ops, host_data); + domain = __irq_domain_create(fwnode, 0, ~0, 0, ops, host_data); + if (domain) { + if (parent) + domain->root = parent->root; domain->parent = parent; domain->flags |= flags; + + __irq_domain_publish(domain); } return domain; @@ -1123,10 +1168,6 @@ static void irq_domain_insert_irq(int virq) domain->mapcount++; irq_domain_set_mapping(domain, data->hwirq, data); - - /* If not already assigned, give the domain the chip's name */ - if (!domain->name && data->chip) - domain->name = data->chip->name; } irq_clear_status_flags(virq, IRQ_NOREQUEST); @@ -1426,40 +1467,12 @@ int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain, return domain->ops->alloc(domain, irq_base, nr_irqs, arg); } -/** - * __irq_domain_alloc_irqs - Allocate IRQs from domain - * @domain: domain to allocate from - * @irq_base: allocate specified IRQ number if irq_base >= 0 - * @nr_irqs: number of IRQs to allocate - * @node: NUMA node id for memory allocation - * @arg: domain specific argument - * @realloc: IRQ descriptors have already been allocated if true - * @affinity: Optional irq affinity mask for multiqueue devices - * - * Allocate IRQ numbers and initialized all data structures to support - * hierarchy IRQ domains. - * Parameter @realloc is mainly to support legacy IRQs. - * Returns error code or allocated IRQ number - * - * The whole process to setup an IRQ has been split into two steps. - * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ - * descriptor and required hardware resources. The second step, - * irq_domain_activate_irq(), is to program the hardware with preallocated - * resources. In this way, it's easier to rollback when failing to - * allocate resources. - */ -int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, - unsigned int nr_irqs, int node, void *arg, - bool realloc, const struct irq_affinity_desc *affinity) +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity) { int i, ret, virq; - if (domain == NULL) { - domain = irq_default_domain; - if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n")) - return -EINVAL; - } - if (realloc && irq_base >= 0) { virq = irq_base; } else { @@ -1478,24 +1491,18 @@ int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, goto out_free_desc; } - mutex_lock(&irq_domain_mutex); ret = irq_domain_alloc_irqs_hierarchy(domain, virq, nr_irqs, arg); - if (ret < 0) { - mutex_unlock(&irq_domain_mutex); + if (ret < 0) goto out_free_irq_data; - } for (i = 0; i < nr_irqs; i++) { ret = irq_domain_trim_hierarchy(virq + i); - if (ret) { - mutex_unlock(&irq_domain_mutex); + if (ret) goto out_free_irq_data; - } } - + for (i = 0; i < nr_irqs; i++) irq_domain_insert_irq(virq + i); - mutex_unlock(&irq_domain_mutex); return virq; @@ -1505,6 +1512,48 @@ out_free_desc: irq_free_descs(virq, nr_irqs); return ret; } + +/** + * __irq_domain_alloc_irqs - Allocate IRQs from domain + * @domain: domain to allocate from + * @irq_base: allocate specified IRQ number if irq_base >= 0 + * @nr_irqs: number of IRQs to allocate + * @node: NUMA node id for memory allocation + * @arg: domain specific argument + * @realloc: IRQ descriptors have already been allocated if true + * @affinity: Optional irq affinity mask for multiqueue devices + * + * Allocate IRQ numbers and initialized all data structures to support + * hierarchy IRQ domains. + * Parameter @realloc is mainly to support legacy IRQs. + * Returns error code or allocated IRQ number + * + * The whole process to setup an IRQ has been split into two steps. + * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ + * descriptor and required hardware resources. The second step, + * irq_domain_activate_irq(), is to program the hardware with preallocated + * resources. In this way, it's easier to rollback when failing to + * allocate resources. + */ +int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity) +{ + int ret; + + if (domain == NULL) { + domain = irq_default_domain; + if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n")) + return -EINVAL; + } + + mutex_lock(&domain->root->mutex); + ret = irq_domain_alloc_irqs_locked(domain, irq_base, nr_irqs, node, arg, + realloc, affinity); + mutex_unlock(&domain->root->mutex); + + return ret; +} EXPORT_SYMBOL_GPL(__irq_domain_alloc_irqs); /* The irq_data was moved, fix the revmap to refer to the new location */ @@ -1512,11 +1561,12 @@ static void irq_domain_fix_revmap(struct irq_data *d) { void __rcu **slot; + lockdep_assert_held(&d->domain->root->mutex); + if (irq_domain_is_nomap(d->domain)) return; /* Fix up the revmap. */ - mutex_lock(&d->domain->revmap_mutex); if (d->hwirq < d->domain->revmap_size) { /* Not using radix tree */ rcu_assign_pointer(d->domain->revmap[d->hwirq], d); @@ -1525,7 +1575,6 @@ static void irq_domain_fix_revmap(struct irq_data *d) if (slot) radix_tree_replace_slot(&d->domain->revmap_tree, slot, d); } - mutex_unlock(&d->domain->revmap_mutex); } /** @@ -1541,8 +1590,8 @@ static void irq_domain_fix_revmap(struct irq_data *d) */ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg) { - struct irq_data *child_irq_data; - struct irq_data *root_irq_data = irq_get_irq_data(virq); + struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_data *parent_irq_data; struct irq_desc *desc; int rv = 0; @@ -1567,47 +1616,46 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg) if (WARN_ON(!irq_domain_is_hierarchy(domain))) return -EINVAL; - if (!root_irq_data) + if (!irq_data) return -EINVAL; - if (domain->parent != root_irq_data->domain) + if (domain->parent != irq_data->domain) return -EINVAL; - child_irq_data = kzalloc_node(sizeof(*child_irq_data), GFP_KERNEL, - irq_data_get_node(root_irq_data)); - if (!child_irq_data) + parent_irq_data = kzalloc_node(sizeof(*parent_irq_data), GFP_KERNEL, + irq_data_get_node(irq_data)); + if (!parent_irq_data) return -ENOMEM; - mutex_lock(&irq_domain_mutex); + mutex_lock(&domain->root->mutex); /* Copy the original irq_data. */ - *child_irq_data = *root_irq_data; + *parent_irq_data = *irq_data; /* - * Overwrite the root_irq_data, which is embedded in struct - * irq_desc, with values for this domain. + * Overwrite the irq_data, which is embedded in struct irq_desc, with + * values for this domain. */ - root_irq_data->parent_data = child_irq_data; - root_irq_data->domain = domain; - root_irq_data->mask = 0; - root_irq_data->hwirq = 0; - root_irq_data->chip = NULL; - root_irq_data->chip_data = NULL; + irq_data->parent_data = parent_irq_data; + irq_data->domain = domain; + irq_data->mask = 0; + irq_data->hwirq = 0; + irq_data->chip = NULL; + irq_data->chip_data = NULL; /* May (probably does) set hwirq, chip, etc. */ rv = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg); if (rv) { /* Restore the original irq_data. */ - *root_irq_data = *child_irq_data; - kfree(child_irq_data); + *irq_data = *parent_irq_data; + kfree(parent_irq_data); goto error; } - irq_domain_fix_revmap(child_irq_data); - irq_domain_set_mapping(domain, root_irq_data->hwirq, root_irq_data); - + irq_domain_fix_revmap(parent_irq_data); + irq_domain_set_mapping(domain, irq_data->hwirq, irq_data); error: - mutex_unlock(&irq_domain_mutex); + mutex_unlock(&domain->root->mutex); return rv; } @@ -1623,8 +1671,8 @@ EXPORT_SYMBOL_GPL(irq_domain_push_irq); */ int irq_domain_pop_irq(struct irq_domain *domain, int virq) { - struct irq_data *root_irq_data = irq_get_irq_data(virq); - struct irq_data *child_irq_data; + struct irq_data *irq_data = irq_get_irq_data(virq); + struct irq_data *parent_irq_data; struct irq_data *tmp_irq_data; struct irq_desc *desc; @@ -1646,37 +1694,37 @@ int irq_domain_pop_irq(struct irq_domain *domain, int virq) if (domain == NULL) return -EINVAL; - if (!root_irq_data) + if (!irq_data) return -EINVAL; tmp_irq_data = irq_domain_get_irq_data(domain, virq); /* We can only "pop" if this domain is at the top of the list */ - if (WARN_ON(root_irq_data != tmp_irq_data)) + if (WARN_ON(irq_data != tmp_irq_data)) return -EINVAL; - if (WARN_ON(root_irq_data->domain != domain)) + if (WARN_ON(irq_data->domain != domain)) return -EINVAL; - child_irq_data = root_irq_data->parent_data; - if (WARN_ON(!child_irq_data)) + parent_irq_data = irq_data->parent_data; + if (WARN_ON(!parent_irq_data)) return -EINVAL; - mutex_lock(&irq_domain_mutex); + mutex_lock(&domain->root->mutex); - root_irq_data->parent_data = NULL; + irq_data->parent_data = NULL; - irq_domain_clear_mapping(domain, root_irq_data->hwirq); + irq_domain_clear_mapping(domain, irq_data->hwirq); irq_domain_free_irqs_hierarchy(domain, virq, 1); /* Restore the original irq_data. */ - *root_irq_data = *child_irq_data; + *irq_data = *parent_irq_data; - irq_domain_fix_revmap(root_irq_data); + irq_domain_fix_revmap(irq_data); - mutex_unlock(&irq_domain_mutex); + mutex_unlock(&domain->root->mutex); - kfree(child_irq_data); + kfree(parent_irq_data); return 0; } @@ -1690,17 +1738,20 @@ EXPORT_SYMBOL_GPL(irq_domain_pop_irq); void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) { struct irq_data *data = irq_get_irq_data(virq); + struct irq_domain *domain; int i; if (WARN(!data || !data->domain || !data->domain->ops->free, "NULL pointer, cannot free irq\n")) return; - mutex_lock(&irq_domain_mutex); + domain = data->domain; + + mutex_lock(&domain->root->mutex); for (i = 0; i < nr_irqs; i++) irq_domain_remove_irq(virq + i); - irq_domain_free_irqs_hierarchy(data->domain, virq, nr_irqs); - mutex_unlock(&irq_domain_mutex); + irq_domain_free_irqs_hierarchy(domain, virq, nr_irqs); + mutex_unlock(&domain->root->mutex); irq_domain_free_irq_data(virq, nr_irqs); irq_free_descs(virq, nr_irqs); @@ -1815,20 +1866,6 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain) if (domain->ops->alloc) domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY; } - -/** - * irq_domain_hierarchical_is_msi_remap - Check if the domain or any - * parent has MSI remapping support - * @domain: domain pointer - */ -bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain) -{ - for (; domain; domain = domain->parent) { - if (irq_domain_is_msi_remap(domain)) - return true; - } - return false; -} #else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ /** * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain @@ -1865,6 +1902,13 @@ void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, irq_set_handler_data(virq, handler_data); } +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc, const struct irq_affinity_desc *affinity) +{ + return -EINVAL; +} + static void irq_domain_check_hierarchy(struct irq_domain *domain) { } @@ -1915,7 +1959,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { - debugfs_remove(debugfs_lookup(d->name, domain_dir)); + debugfs_lookup_and_remove(d->name, domain_dir); } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 5b7cf28df290..8ce75495e04f 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -723,10 +723,13 @@ EXPORT_SYMBOL(disable_irq_nosync); * to complete before returning. If you use this function while * holding a resource the IRQ handler may need you will deadlock. * - * This function may be called - with care - from IRQ context. + * Can only be called from preemptible code as it might sleep when + * an interrupt thread is associated to @irq. + * */ void disable_irq(unsigned int irq) { + might_sleep(); if (!__disable_irq_nosync(irq)) synchronize_irq(irq); } diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 955267bbc2be..7a97bcb086bf 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -830,11 +830,8 @@ static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode, domain = irq_domain_create_hierarchy(parent, flags | IRQ_DOMAIN_FLAG_MSI, 0, fwnode, &msi_domain_ops, info); - if (domain) { - if (!domain->name && info->chip) - domain->name = info->chip->name; + if (domain) irq_domain_update_bus_token(domain, info->bus_token); - } return domain; } @@ -1000,7 +997,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, fail: msi_unlock_descs(dev); free_fwnode: - kfree(fwnode); + irq_domain_free_fwnode(fwnode); free_bundle: kfree(bundle); return false; @@ -1013,6 +1010,7 @@ free_bundle: */ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) { + struct fwnode_handle *fwnode = NULL; struct msi_domain_info *info; struct irq_domain *domain; @@ -1025,7 +1023,10 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) dev->msi.data->__domains[domid].domain = NULL; info = domain->host_data; + if (irq_domain_is_msi_device(domain)) + fwnode = domain->fwnode; irq_domain_remove(domain); + irq_domain_free_fwnode(fwnode); kfree(container_of(info, struct msi_domain_template, info)); unlock: @@ -1080,10 +1081,13 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, struct xarray *xa; int ret, virq; - if (!msi_ctrl_valid(dev, &ctrl)) - return -EINVAL; - msi_lock_descs(dev); + + if (!msi_ctrl_valid(dev, &ctrl)) { + ret = -EINVAL; + goto unlock; + } + ret = msi_domain_add_simple_msi_descs(dev, &ctrl); if (ret) goto unlock; @@ -1105,14 +1109,35 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, return 0; fail: - for (--virq; virq >= virq_base; virq--) + for (--virq; virq >= virq_base; virq--) { + msi_domain_depopulate_descs(dev, virq, 1); irq_domain_free_irqs_common(domain, virq, 1); + } msi_domain_free_descs(dev, &ctrl); unlock: msi_unlock_descs(dev); return ret; } +void msi_domain_depopulate_descs(struct device *dev, int virq_base, int nvec) +{ + struct msi_ctrl ctrl = { + .domid = MSI_DEFAULT_DOMAIN, + .first = virq_base, + .last = virq_base + nvec - 1, + }; + struct msi_desc *desc; + struct xarray *xa; + unsigned long idx; + + if (!msi_ctrl_valid(dev, &ctrl)) + return; + + xa = &dev->msi.data->__domains[ctrl.domid].store; + xa_for_each_range(xa, idx, desc, ctrl.first, ctrl.last) + desc->irq = 0; +} + /* * Carefully check whether the device can use reservation mode. If * reservation mode is enabled then the early activation will assign a @@ -1623,3 +1648,30 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { return (struct msi_domain_info *)domain->host_data; } + +/** + * msi_device_has_isolated_msi - True if the device has isolated MSI + * @dev: The device to check + * + * Isolated MSI means that HW modeled by an irq_domain on the path from the + * initiating device to the CPU will validate that the MSI message specifies an + * interrupt number that the device is authorized to trigger. This must block + * devices from triggering interrupts they are not authorized to trigger. + * Currently authorization means the MSI vector is one assigned to the device. + * + * This is interesting for securing VFIO use cases where a rouge MSI (eg created + * by abusing a normal PCI MemWr DMA) must not allow the VFIO userspace to + * impact outside its security domain, eg userspace triggering interrupts on + * kernel drivers, a VM triggering interrupts on the hypervisor, or a VM + * triggering interrupts on another VM. + */ +bool msi_device_has_isolated_msi(struct device *dev) +{ + struct irq_domain *domain = dev_get_msi_domain(dev); + + for (; domain; domain = domain->parent) + if (domain->flags & IRQ_DOMAIN_FLAG_ISOLATED_MSI) + return true; + return arch_is_isolated_msi(); +} +EXPORT_SYMBOL_GPL(msi_device_has_isolated_msi); diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index f35d9cc1aab1..bfbc12da3326 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -157,14 +157,11 @@ static void test_kallsyms_compression_ratio(void) static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr) { u64 t0, t1, t; - unsigned long flags; struct test_stat *stat = (struct test_stat *)data; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); (void)kallsyms_lookup_name(name); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); t = t1 - t0; if (t < stat->min) @@ -234,18 +231,15 @@ static int find_symbol(void *data, const char *name, struct module *mod, unsigne static void test_perf_kallsyms_on_each_symbol(void) { u64 t0, t1; - unsigned long flags; struct test_stat stat; memset(&stat, 0, sizeof(stat)); stat.max = INT_MAX; stat.name = stub_name; stat.perf = 1; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); kallsyms_on_each_symbol(find_symbol, &stat); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0); } @@ -270,17 +264,14 @@ static int match_symbol(void *data, unsigned long addr) static void test_perf_kallsyms_on_each_match_symbol(void) { u64 t0, t1; - unsigned long flags; struct test_stat stat; memset(&stat, 0, sizeof(stat)); stat.max = INT_MAX; stat.name = stub_name; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0); } diff --git a/kernel/kcov.c b/kernel/kcov.c index e5cd09fd8a05..84c717337df0 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -489,7 +489,7 @@ static int kcov_mmap(struct file *filep, struct vm_area_struct *vma) goto exit; } spin_unlock_irqrestore(&kcov->lock, flags); - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); for (off = 0; off < size; off += PAGE_SIZE) { page = vmalloc_to_page(kcov->area + off); res = vm_insert_page(vma, vma->vm_start + off, page); diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index dcec1b743c69..a60c561724be 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -159,7 +159,7 @@ static bool __report_matches(const struct expect_report *r) const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; bool ret = false; unsigned long flags; - typeof(observed.lines) expect; + typeof(*observed.lines) *expect; const char *end; char *cur; int i; @@ -168,6 +168,10 @@ static bool __report_matches(const struct expect_report *r) if (!report_available()) return false; + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + /* Generate expected report contents. */ /* Title */ @@ -253,6 +257,7 @@ static bool __report_matches(const struct expect_report *r) strstr(observed.lines[2], expect[1]))); out: spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); return ret; } diff --git a/kernel/kexec.c b/kernel/kexec.c index cb8e6e6f983c..92d301f98776 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -190,10 +190,12 @@ out_unlock: static inline int kexec_load_check(unsigned long nr_segments, unsigned long flags) { + int image_type = (flags & KEXEC_ON_CRASH) ? + KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; int result; /* We only trust the superuser with rebooting the system. */ - if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + if (!kexec_load_permitted(image_type)) return -EPERM; /* Permit LSMs and IMA to fail the kexec */ diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 969e8f52f7da..3d578c6fefee 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/btf.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> @@ -920,10 +921,64 @@ int kimage_load_segment(struct kimage *image, return result; } +struct kexec_load_limit { + /* Mutex protects the limit count. */ + struct mutex mutex; + int limit; +}; + +static struct kexec_load_limit load_limit_reboot = { + .mutex = __MUTEX_INITIALIZER(load_limit_reboot.mutex), + .limit = -1, +}; + +static struct kexec_load_limit load_limit_panic = { + .mutex = __MUTEX_INITIALIZER(load_limit_panic.mutex), + .limit = -1, +}; + struct kimage *kexec_image; struct kimage *kexec_crash_image; -int kexec_load_disabled; +static int kexec_load_disabled; + #ifdef CONFIG_SYSCTL +static int kexec_limit_handler(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct kexec_load_limit *limit = table->data; + int val; + struct ctl_table tmp = { + .data = &val, + .maxlen = sizeof(val), + .mode = table->mode, + }; + int ret; + + if (write) { + ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (val < 0) + return -EINVAL; + + mutex_lock(&limit->mutex); + if (limit->limit != -1 && val >= limit->limit) + ret = -EINVAL; + else + limit->limit = val; + mutex_unlock(&limit->mutex); + + return ret; + } + + mutex_lock(&limit->mutex); + val = limit->limit; + mutex_unlock(&limit->mutex); + + return proc_dointvec(&tmp, write, buffer, lenp, ppos); +} + static struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", @@ -935,6 +990,18 @@ static struct ctl_table kexec_core_sysctls[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_ONE, }, + { + .procname = "kexec_load_limit_panic", + .data = &load_limit_panic, + .mode = 0644, + .proc_handler = kexec_limit_handler, + }, + { + .procname = "kexec_load_limit_reboot", + .data = &load_limit_reboot, + .mode = 0644, + .proc_handler = kexec_limit_handler, + }, { } }; @@ -946,6 +1013,32 @@ static int __init kexec_core_sysctl_init(void) late_initcall(kexec_core_sysctl_init); #endif +bool kexec_load_permitted(int kexec_image_type) +{ + struct kexec_load_limit *limit; + + /* + * Only the superuser can use the kexec syscall and if it has not + * been disabled. + */ + if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + return false; + + /* Check limit counter and decrease it.*/ + limit = (kexec_image_type == KEXEC_TYPE_CRASH) ? + &load_limit_panic : &load_limit_reboot; + mutex_lock(&limit->mutex); + if (!limit->limit) { + mutex_unlock(&limit->mutex); + return false; + } + if (limit->limit != -1) + limit->limit--; + mutex_unlock(&limit->mutex); + + return true; +} + /* * No panic_cpu check version of crash_kexec(). This function is called * only when panic_cpu holds the current CPU number; this is the only CPU @@ -975,7 +1068,7 @@ void __noclone __crash_kexec(struct pt_regs *regs) } STACK_FRAME_NON_STANDARD(__crash_kexec); -void crash_kexec(struct pt_regs *regs) +__bpf_kfunc void crash_kexec(struct pt_regs *regs) { int old_cpu, this_cpu; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index dd5983010b7b..f1a0e4e3fb5c 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -326,11 +326,13 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags) { - int ret = 0, i; + int image_type = (flags & KEXEC_FILE_ON_CRASH) ? + KEXEC_TYPE_CRASH : KEXEC_TYPE_DEFAULT; struct kimage **dest_image, *image; + int ret = 0, i; /* We only trust the superuser with rebooting the system. */ - if (!capable(CAP_SYS_BOOT) || kexec_load_disabled) + if (!kexec_load_permitted(image_type)) return -EPERM; /* Make sure we have a legal set of flags */ @@ -342,11 +344,12 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (!kexec_trylock()) return -EBUSY; - dest_image = &kexec_image; - if (flags & KEXEC_FILE_ON_CRASH) { + if (image_type == KEXEC_TYPE_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); + } else { + dest_image = &kexec_image; } if (flags & KEXEC_FILE_UNLOAD) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 1c18ecf9f98b..00e177de91cc 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -458,7 +458,7 @@ static inline int kprobe_optready(struct kprobe *p) } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ -static inline bool kprobe_disarmed(struct kprobe *p) +bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; @@ -555,17 +555,15 @@ static void do_unoptimize_kprobes(void) /* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held(); - /* Unoptimization must be done anytime */ - if (list_empty(&unoptimizing_list)) - return; + if (!list_empty(&unoptimizing_list)) + arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); - arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); - /* Loop on 'freeing_list' for disarming */ + /* Loop on 'freeing_list' for disarming and removing from kprobe hash list */ 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)) + /* Disarm probes if marked disabled and not gone */ + if (kprobe_disabled(&op->kp) && !kprobe_gone(&op->kp)) arch_disarm_kprobe(&op->kp); if (kprobe_unused(&op->kp)) { /* @@ -662,7 +660,7 @@ void wait_for_kprobe_optimizer(void) mutex_unlock(&kprobe_mutex); } -static bool optprobe_queued_unopt(struct optimized_kprobe *op) +bool optprobe_queued_unopt(struct optimized_kprobe *op) { struct optimized_kprobe *_op; @@ -797,14 +795,13 @@ static void kill_optimized_kprobe(struct kprobe *p) op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; if (kprobe_unused(p)) { - /* Enqueue if it is unused */ - list_add(&op->list, &freeing_list); /* - * Remove unused probes from the hash list. After waiting - * for synchronization, this probe is reclaimed. - * (reclaiming is done by do_free_cleaned_kprobes().) + * Unused kprobe is on unoptimizing or freeing list. We move it + * to freeing_list and let the kprobe_optimizer() remove it from + * the kprobe hash list and free it. */ - hlist_del_rcu(&op->kp.hlist); + if (optprobe_queued_unopt(op)) + list_move(&op->list, &freeing_list); } /* Don't touch the code, because it is already freed. */ diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 2df00b789b90..0408aab80941 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -51,6 +51,14 @@ static ssize_t cpu_byteorder_show(struct kobject *kobj, } KERNEL_ATTR_RO(cpu_byteorder); +/* address bits */ +static ssize_t address_bits_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%zu\n", sizeof(void *) * 8 /* CHAR_BIT */); +} +KERNEL_ATTR_RO(address_bits); + #ifdef CONFIG_UEVENT_HELPER /* uevent helper program, used during early boot */ static ssize_t uevent_helper_show(struct kobject *kobj, @@ -233,6 +241,7 @@ static struct attribute * kernel_attrs[] = { &fscaps_attr.attr, &uevent_seqnum_attr.attr, &cpu_byteorder_attr.attr, + &address_bits_attr.attr, #ifdef CONFIG_UEVENT_HELPER &uevent_helper_attr.attr, #endif diff --git a/kernel/kthread.c b/kernel/kthread.c index f97fd01a2932..7e6751b29101 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1382,6 +1382,10 @@ EXPORT_SYMBOL_GPL(kthread_flush_worker); * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. + * + * Note that this function is not responsible for handling delayed work, so + * caller should be responsible for queuing or canceling all delayed work items + * before invoke this function. */ void kthread_destroy_worker(struct kthread_worker *worker) { @@ -1393,6 +1397,7 @@ void kthread_destroy_worker(struct kthread_worker *worker) kthread_flush_worker(worker); kthread_stop(task); + WARN_ON(!list_empty(&worker->delayed_work_list)); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index 201f0c0482fb..4bd2d5e10f20 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -118,7 +118,6 @@ static struct klp_object *klp_find_object(struct klp_patch *patch, } struct klp_find_arg { - const char *objname; const char *name; unsigned long addr; unsigned long count; @@ -148,15 +147,9 @@ static int klp_find_callback(void *data, const char *name, { struct klp_find_arg *args = data; - if ((mod && !args->objname) || (!mod && args->objname)) - return 0; - if (strcmp(args->name, name)) return 0; - if (args->objname && strcmp(args->objname, mod->name)) - return 0; - return klp_match_callback(data, addr); } @@ -164,7 +157,6 @@ static int klp_find_object_symbol(const char *objname, const char *name, unsigned long sympos, unsigned long *addr) { struct klp_find_arg args = { - .objname = objname, .name = name, .addr = 0, .count = 0, @@ -172,7 +164,7 @@ static int klp_find_object_symbol(const char *objname, const char *name, }; if (objname) - module_kallsyms_on_each_symbol(klp_find_callback, &args); + module_kallsyms_on_each_symbol(objname, klp_find_callback, &args); else kallsyms_on_each_match_symbol(klp_match_callback, name, &args); @@ -268,6 +260,14 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, return 0; } +void __weak clear_relocate_add(Elf_Shdr *sechdrs, + const char *strtab, + unsigned int symindex, + unsigned int relsec, + struct module *me) +{ +} + /* * At a high-level, there are two types of klp relocation sections: those which * reference symbols which live in vmlinux; and those which reference symbols @@ -291,10 +291,10 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, * the to-be-patched module to be loaded and patched sometime *after* the * klp module is loaded. */ -int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, - const char *shstrtab, const char *strtab, - unsigned int symndx, unsigned int secndx, - const char *objname) +static int klp_write_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symndx, unsigned int secndx, + const char *objname, bool apply) { int cnt, ret; char sec_objname[MODULE_NAME_LEN]; @@ -316,11 +316,26 @@ int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, if (strcmp(objname ? objname : "vmlinux", sec_objname)) return 0; - ret = klp_resolve_symbols(sechdrs, strtab, symndx, sec, sec_objname); - if (ret) - return ret; + if (apply) { + ret = klp_resolve_symbols(sechdrs, strtab, symndx, + sec, sec_objname); + if (ret) + return ret; + + return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod); + } + + clear_relocate_add(sechdrs, strtab, symndx, secndx, pmod); + return 0; +} - return apply_relocate_add(sechdrs, strtab, symndx, secndx, pmod); +int klp_apply_section_relocs(struct module *pmod, Elf_Shdr *sechdrs, + const char *shstrtab, const char *strtab, + unsigned int symndx, unsigned int secndx, + const char *objname) +{ + return klp_write_section_relocs(pmod, sechdrs, shstrtab, strtab, symndx, + secndx, objname, true); } /* @@ -769,8 +784,9 @@ static int klp_init_func(struct klp_object *obj, struct klp_func *func) func->old_sympos ? func->old_sympos : 1); } -static int klp_apply_object_relocs(struct klp_patch *patch, - struct klp_object *obj) +static int klp_write_object_relocs(struct klp_patch *patch, + struct klp_object *obj, + bool apply) { int i, ret; struct klp_modinfo *info = patch->mod->klp_info; @@ -781,10 +797,10 @@ static int klp_apply_object_relocs(struct klp_patch *patch, if (!(sec->sh_flags & SHF_RELA_LIVEPATCH)) continue; - ret = klp_apply_section_relocs(patch->mod, info->sechdrs, + ret = klp_write_section_relocs(patch->mod, info->sechdrs, info->secstrings, patch->mod->core_kallsyms.strtab, - info->symndx, i, obj->name); + info->symndx, i, obj->name, apply); if (ret) return ret; } @@ -792,6 +808,18 @@ static int klp_apply_object_relocs(struct klp_patch *patch, return 0; } +static int klp_apply_object_relocs(struct klp_patch *patch, + struct klp_object *obj) +{ + return klp_write_object_relocs(patch, obj, true); +} + +static void klp_clear_object_relocs(struct klp_patch *patch, + struct klp_object *obj) +{ + klp_write_object_relocs(patch, obj, false); +} + /* parts of the initialization that is done only when the object is loaded */ static int klp_init_object_loaded(struct klp_patch *patch, struct klp_object *obj) @@ -1179,7 +1207,7 @@ static void klp_cleanup_module_patches_limited(struct module *mod, klp_unpatch_object(obj); klp_post_unpatch_callback(obj); - + klp_clear_object_relocs(patch, obj); klp_free_object_loaded(obj); break; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e3375bc40dad..50d4863974e7 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -55,6 +55,7 @@ #include <linux/rcupdate.h> #include <linux/kprobes.h> #include <linux/lockdep.h> +#include <linux/context_tracking.h> #include <asm/sections.h> @@ -6555,6 +6556,7 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) { struct task_struct *curr = current; int dl = READ_ONCE(debug_locks); + bool rcu = warn_rcu_enter(); /* Note: the following can be executed concurrently, so be careful. */ pr_warn("\n"); @@ -6595,5 +6597,6 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) lockdep_print_held_locks(curr); pr_warn("\nstack backtrace:\n"); dump_stack(); + warn_rcu_exit(rcu); } EXPORT_SYMBOL_GPL(lockdep_rcu_suspicious); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 9c2fb613a55d..f04b1978899d 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -46,6 +46,9 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); +torture_param(int, rt_boost, 2, + "Do periodic rt-boost. 0=Disable, 1=Only for rt_mutex, 2=For all lock types."); +torture_param(int, rt_boost_factor, 50, "A factor determining how often rt-boost happens."); torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); @@ -127,15 +130,50 @@ static void torture_lock_busted_write_unlock(int tid __maybe_unused) /* BUGGY, do not use in real life!!! */ } -static void torture_boost_dummy(struct torture_random_state *trsp) +static void __torture_rt_boost(struct torture_random_state *trsp) { - /* Only rtmutexes care about priority */ + const unsigned int factor = rt_boost_factor; + + if (!rt_task(current)) { + /* + * Boost priority once every rt_boost_factor operations. When + * the task tries to take the lock, the rtmutex it will account + * for the new priority, and do any corresponding pi-dance. + */ + if (trsp && !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor))) { + sched_set_fifo(current); + } else /* common case, do nothing */ + return; + } else { + /* + * The task will remain boosted for another 10 * rt_boost_factor + * operations, then restored back to its original prio, and so + * forth. + * + * When @trsp is nil, we want to force-reset the task for + * stopping the kthread. + */ + if (!trsp || !(torture_random(trsp) % + (cxt.nrealwriters_stress * factor * 2))) { + sched_set_normal(current, 0); + } else /* common case, do nothing */ + return; + } +} + +static void torture_rt_boost(struct torture_random_state *trsp) +{ + if (rt_boost != 2) + return; + + __torture_rt_boost(trsp); } static struct lock_torture_ops lock_busted_ops = { .writelock = torture_lock_busted_write_lock, .write_delay = torture_lock_busted_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_lock_busted_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -179,7 +217,7 @@ __releases(torture_spinlock) static struct lock_torture_ops spin_lock_ops = { .writelock = torture_spin_lock_write_lock, .write_delay = torture_spin_lock_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_spin_lock_write_unlock, .readlock = NULL, .read_delay = NULL, @@ -206,7 +244,7 @@ __releases(torture_spinlock) static struct lock_torture_ops spin_lock_irq_ops = { .writelock = torture_spin_lock_write_lock_irq, .write_delay = torture_spin_lock_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_lock_spin_write_unlock_irq, .readlock = NULL, .read_delay = NULL, @@ -275,7 +313,7 @@ __releases(torture_rwlock) static struct lock_torture_ops rw_lock_ops = { .writelock = torture_rwlock_write_lock, .write_delay = torture_rwlock_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_rwlock_write_unlock, .readlock = torture_rwlock_read_lock, .read_delay = torture_rwlock_read_delay, @@ -318,7 +356,7 @@ __releases(torture_rwlock) static struct lock_torture_ops rw_lock_irq_ops = { .writelock = torture_rwlock_write_lock_irq, .write_delay = torture_rwlock_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_rwlock_write_unlock_irq, .readlock = torture_rwlock_read_lock_irq, .read_delay = torture_rwlock_read_delay, @@ -358,7 +396,7 @@ __releases(torture_mutex) static struct lock_torture_ops mutex_lock_ops = { .writelock = torture_mutex_lock, .write_delay = torture_mutex_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_mutex_unlock, .readlock = NULL, .read_delay = NULL, @@ -456,7 +494,7 @@ static struct lock_torture_ops ww_mutex_lock_ops = { .exit = torture_ww_mutex_exit, .writelock = torture_ww_mutex_lock, .write_delay = torture_mutex_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_ww_mutex_unlock, .readlock = NULL, .read_delay = NULL, @@ -474,37 +512,6 @@ __acquires(torture_rtmutex) return 0; } -static void torture_rtmutex_boost(struct torture_random_state *trsp) -{ - const unsigned int factor = 50000; /* yes, quite arbitrary */ - - if (!rt_task(current)) { - /* - * Boost priority once every ~50k operations. When the - * task tries to take the lock, the rtmutex it will account - * for the new priority, and do any corresponding pi-dance. - */ - if (trsp && !(torture_random(trsp) % - (cxt.nrealwriters_stress * factor))) { - sched_set_fifo(current); - } else /* common case, do nothing */ - return; - } else { - /* - * The task will remain boosted for another ~500k operations, - * then restored back to its original prio, and so forth. - * - * When @trsp is nil, we want to force-reset the task for - * stopping the kthread. - */ - if (!trsp || !(torture_random(trsp) % - (cxt.nrealwriters_stress * factor * 2))) { - sched_set_normal(current, 0); - } else /* common case, do nothing */ - return; - } -} - static void torture_rtmutex_delay(struct torture_random_state *trsp) { const unsigned long shortdelay_us = 2; @@ -530,10 +537,18 @@ __releases(torture_rtmutex) rt_mutex_unlock(&torture_rtmutex); } +static void torture_rt_boost_rtmutex(struct torture_random_state *trsp) +{ + if (!rt_boost) + return; + + __torture_rt_boost(trsp); +} + static struct lock_torture_ops rtmutex_lock_ops = { .writelock = torture_rtmutex_lock, .write_delay = torture_rtmutex_delay, - .task_boost = torture_rtmutex_boost, + .task_boost = torture_rt_boost_rtmutex, .writeunlock = torture_rtmutex_unlock, .readlock = NULL, .read_delay = NULL, @@ -600,7 +615,7 @@ __releases(torture_rwsem) static struct lock_torture_ops rwsem_lock_ops = { .writelock = torture_rwsem_down_write, .write_delay = torture_rwsem_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_rwsem_up_write, .readlock = torture_rwsem_down_read, .read_delay = torture_rwsem_read_delay, @@ -652,7 +667,7 @@ static struct lock_torture_ops percpu_rwsem_lock_ops = { .exit = torture_percpu_rwsem_exit, .writelock = torture_percpu_rwsem_down_write, .write_delay = torture_rwsem_write_delay, - .task_boost = torture_boost_dummy, + .task_boost = torture_rt_boost, .writeunlock = torture_percpu_rwsem_up_write, .readlock = torture_percpu_rwsem_down_read, .read_delay = torture_rwsem_read_delay, diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 2b23378775fe..ebe6b8ec7cb3 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -371,7 +371,7 @@ void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) /* * We're pending, wait for the owner to go away. * - * 0,1,1 -> 0,1,0 + * 0,1,1 -> *,1,0 * * this wait loop must be a load-acquire such that we match the * store-release that clears the locked bit and create lock @@ -380,7 +380,7 @@ void __lockfunc queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * barriers. */ if (val & _Q_LOCKED_MASK) - atomic_cond_read_acquire(&lock->val, !(VAL & _Q_LOCKED_MASK)); + smp_cond_load_acquire(&lock->locked, !VAL); /* * take ownership and clear the pending bit. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 010cf4e6d0b8..728f434de2bb 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -901,8 +901,9 @@ static int __sched rt_mutex_adjust_prio_chain(struct task_struct *task, * then we need to wake the new top waiter up to try * to get the lock. */ - if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) - wake_up_state(waiter->task, waiter->wake_state); + top_waiter = rt_mutex_top_waiter(lock); + if (prerequeue_top_waiter != top_waiter) + wake_up_state(top_waiter->task, top_waiter->wake_state); raw_spin_unlock_irq(&lock->wait_lock); return 0; } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 44873594de03..acb5a50309a1 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -256,16 +256,13 @@ static inline bool rwsem_read_trylock(struct rw_semaphore *sem, long *cntp) static inline bool rwsem_write_trylock(struct rw_semaphore *sem) { long tmp = RWSEM_UNLOCKED_VALUE; - bool ret = false; - preempt_disable(); if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) { rwsem_set_owner(sem); - ret = true; + return true; } - preempt_enable(); - return ret; + return false; } /* @@ -624,18 +621,16 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, */ if (first->handoff_set && (waiter != first)) return false; - - /* - * First waiter can inherit a previously set handoff - * bit and spin on rwsem if lock acquisition fails. - */ - if (waiter == first) - waiter->handoff_set = true; } new = count; if (count & RWSEM_LOCK_MASK) { + /* + * A waiter (first or not) can set the handoff bit + * if it is an RT task or wait in the wait queue + * for too long. + */ if (has_handoff || (!rt_task(waiter->task) && !time_after(jiffies, waiter->timeout))) return false; @@ -651,11 +646,12 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, } while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new)); /* - * We have either acquired the lock with handoff bit cleared or - * set the handoff bit. + * We have either acquired the lock with handoff bit cleared or set + * the handoff bit. Only the first waiter can have its handoff_set + * set here to enable optimistic spinning in slowpath loop. */ if (new & RWSEM_FLAG_HANDOFF) { - waiter->handoff_set = true; + first->handoff_set = true; lockevent_inc(rwsem_wlock_handoff); return false; } @@ -717,7 +713,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) return false; } - preempt_disable(); /* * Disable preemption is equal to the RCU read-side crital section, * thus the task_strcut structure won't go away. @@ -729,7 +724,6 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) if ((flags & RWSEM_NONSPINNABLE) || (owner && !(flags & RWSEM_READER_OWNED) && !owner_on_cpu(owner))) ret = false; - preempt_enable(); lockevent_cond_inc(rwsem_opt_fail, !ret); return ret; @@ -829,8 +823,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) int loop = 0; u64 rspin_threshold = 0; - preempt_disable(); - /* sem->wait_lock should not be held when doing optimistic spinning */ if (!osq_lock(&sem->osq)) goto done; @@ -938,7 +930,6 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) } osq_unlock(&sem->osq); done: - preempt_enable(); lockevent_cond_inc(rwsem_opt_fail, !taken); return taken; } @@ -1092,7 +1083,7 @@ queue: /* Ordered by sem->wait_lock against rwsem_mark_wake(). */ break; } - schedule(); + schedule_preempt_disabled(); lockevent_inc(rwsem_sleep_reader); } @@ -1179,15 +1170,12 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state) if (waiter.handoff_set) { enum owner_state owner_state; - preempt_disable(); owner_state = rwsem_spin_on_owner(sem); - preempt_enable(); - if (owner_state == OWNER_NULL) goto trylock_again; } - schedule(); + schedule_preempt_disabled(); lockevent_inc(rwsem_sleep_writer); set_current_state(state); trylock_again: @@ -1254,14 +1242,20 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) */ static inline int __down_read_common(struct rw_semaphore *sem, int state) { + int ret = 0; long count; + preempt_disable(); if (!rwsem_read_trylock(sem, &count)) { - if (IS_ERR(rwsem_down_read_slowpath(sem, count, state))) - return -EINTR; + if (IS_ERR(rwsem_down_read_slowpath(sem, count, state))) { + ret = -EINTR; + goto out; + } DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem); } - return 0; +out: + preempt_enable(); + return ret; } static inline void __down_read(struct rw_semaphore *sem) @@ -1281,19 +1275,23 @@ static inline int __down_read_killable(struct rw_semaphore *sem) static inline int __down_read_trylock(struct rw_semaphore *sem) { + int ret = 0; long tmp; DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); + preempt_disable(); tmp = atomic_long_read(&sem->count); while (!(tmp & RWSEM_READ_FAILED_MASK)) { if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, tmp + RWSEM_READER_BIAS)) { rwsem_set_reader_owned(sem); - return 1; + ret = 1; + break; } } - return 0; + preempt_enable(); + return ret; } /* @@ -1301,12 +1299,15 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) */ static inline int __down_write_common(struct rw_semaphore *sem, int state) { + int ret = 0; + + preempt_disable(); if (unlikely(!rwsem_write_trylock(sem))) { if (IS_ERR(rwsem_down_write_slowpath(sem, state))) - return -EINTR; + ret = -EINTR; } - - return 0; + preempt_enable(); + return ret; } static inline void __down_write(struct rw_semaphore *sem) @@ -1321,8 +1322,14 @@ static inline int __down_write_killable(struct rw_semaphore *sem) static inline int __down_write_trylock(struct rw_semaphore *sem) { + int ret; + + preempt_disable(); DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); - return rwsem_write_trylock(sem); + ret = rwsem_write_trylock(sem); + preempt_enable(); + + return ret; } /* @@ -1335,6 +1342,7 @@ static inline void __up_read(struct rw_semaphore *sem) DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem); DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem); + preempt_disable(); rwsem_clear_reader_owned(sem); tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count); DEBUG_RWSEMS_WARN_ON(tmp < 0, sem); @@ -1343,6 +1351,7 @@ static inline void __up_read(struct rw_semaphore *sem) clear_nonspinnable(sem); rwsem_wake(sem); } + preempt_enable(); } /* @@ -1363,9 +1372,9 @@ static inline void __up_write(struct rw_semaphore *sem) preempt_disable(); rwsem_clear_owner(sem); tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count); - preempt_enable(); if (unlikely(tmp & RWSEM_FLAG_WAITERS)) rwsem_wake(sem); + preempt_enable(); } /* @@ -1383,11 +1392,13 @@ static inline void __downgrade_write(struct rw_semaphore *sem) * write side. As such, rely on RELEASE semantics. */ DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem); + preempt_disable(); tmp = atomic_long_fetch_add_release( -RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count); rwsem_set_reader_owned(sem); if (tmp & RWSEM_FLAG_WAITERS) rwsem_downgrade_wake(sem); + preempt_enable(); } #else /* !CONFIG_PREEMPT_RT */ @@ -1662,6 +1673,12 @@ void down_read_non_owner(struct rw_semaphore *sem) { might_sleep(); __down_read(sem); + /* + * The owner value for a reader-owned lock is mostly for debugging + * purpose only and is not critical to the correct functioning of + * rwsem. So it is perfectly fine to set it in a preempt-enabled + * context here. + */ __rwsem_set_reader_owned(sem, NULL); } EXPORT_SYMBOL(down_read_non_owner); diff --git a/kernel/module/kallsyms.c b/kernel/module/kallsyms.c index 4523f99b0358..ab2376a1be88 100644 --- a/kernel/module/kallsyms.c +++ b/kernel/module/kallsyms.c @@ -494,7 +494,8 @@ unsigned long module_kallsyms_lookup_name(const char *name) return ret; } -int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, +int module_kallsyms_on_each_symbol(const char *modname, + int (*fn)(void *, const char *, struct module *, unsigned long), void *data) { @@ -509,6 +510,9 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, if (mod->state == MODULE_STATE_UNFORMED) continue; + if (modname && strcmp(modname, mod->name)) + continue; + /* Use rcu_dereference_sched() to remain compliant with the sparse tool */ preempt_disable(); kallsyms = rcu_dereference_sched(mod->kallsyms); @@ -525,6 +529,13 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, if (ret != 0) goto out; } + + /* + * The given module is found, the subsequent modules do not + * need to be compared. + */ + if (modname) + break; } out: mutex_unlock(&module_mutex); diff --git a/kernel/module/main.c b/kernel/module/main.c index 48568a0f5651..d3be89de706d 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include <linux/kernel.h> #include <linux/kernel_read_file.h> +#include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/elf.h> @@ -2393,7 +2394,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; @@ -2569,20 +2571,35 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; -again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); @@ -2659,7 +2676,7 @@ static int unknown_module_param_cb(char *param, char *val, const char *modname, int ret; if (strcmp(param, "async_probe") == 0) { - if (strtobool(val, &mod->async_probe_requested)) + if (kstrtobool(val, &mod->async_probe_requested)) mod->async_probe_requested = true; return 0; } diff --git a/kernel/notifier.c b/kernel/notifier.c index ab75637fd904..d353e4b5402d 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -456,7 +456,6 @@ int raw_notifier_call_chain(struct raw_notifier_head *nh, } EXPORT_SYMBOL_GPL(raw_notifier_call_chain); -#ifdef CONFIG_SRCU /* * SRCU notifier chain routines. Registration and unregistration * use a mutex, and call_chain is synchronized by SRCU (no locks). @@ -573,8 +572,6 @@ void srcu_init_notifier_head(struct srcu_notifier_head *nh) } EXPORT_SYMBOL_GPL(srcu_init_notifier_head); -#endif /* CONFIG_SRCU */ - static ATOMIC_NOTIFIER_HEAD(die_chain); int notrace notify_die(enum die_val val, const char *str, diff --git a/kernel/panic.c b/kernel/panic.c index 463c9295bc28..5cfea8302d23 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -34,6 +34,7 @@ #include <linux/ratelimit.h> #include <linux/debugfs.h> #include <linux/sysfs.h> +#include <linux/context_tracking.h> #include <trace/events/error_report.h> #include <asm/sections.h> @@ -211,9 +212,6 @@ static void panic_print_sys_info(bool console_flush) return; } - if (panic_print & PANIC_PRINT_ALL_CPU_BT) - trigger_all_cpu_backtrace(); - if (panic_print & PANIC_PRINT_TASK_INFO) show_state(); @@ -243,6 +241,30 @@ void check_panic_on_warn(const char *origin) origin, limit); } +/* + * Helper that triggers the NMI backtrace (if set in panic_print) + * and then performs the secondary CPUs shutdown - we cannot have + * the NMI backtrace after the CPUs are off! + */ +static void panic_other_cpus_shutdown(bool crash_kexec) +{ + if (panic_print & PANIC_PRINT_ALL_CPU_BT) + trigger_all_cpu_backtrace(); + + /* + * Note that smp_send_stop() is the usual SMP shutdown function, + * which unfortunately may not be hardened to work in a panic + * situation. If we want to do crash dump after notifier calls + * and kmsg_dump, we will need architecture dependent extra + * bits in addition to stopping other CPUs, hence we rely on + * crash_smp_send_stop() for that. + */ + if (!crash_kexec) + smp_send_stop(); + else + crash_smp_send_stop(); +} + /** * panic - halt the system * @fmt: The text string to print @@ -333,23 +355,10 @@ void panic(const char *fmt, ...) * * Bypass the panic_cpu check and call __crash_kexec directly. */ - if (!_crash_kexec_post_notifiers) { + if (!_crash_kexec_post_notifiers) __crash_kexec(NULL); - /* - * Note smp_send_stop is the usual smp shutdown function, which - * unfortunately means it may not be hardened to work in a - * panic situation. - */ - smp_send_stop(); - } else { - /* - * If we want to do crash dump after notifier calls and - * kmsg_dump, we will need architecture dependent extra - * works in addition to stopping other CPUs. - */ - crash_smp_send_stop(); - } + panic_other_cpus_shutdown(_crash_kexec_post_notifiers); /* * Run any panic handlers, including those that might need to @@ -679,6 +688,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint, void warn_slowpath_fmt(const char *file, int line, unsigned taint, const char *fmt, ...) { + bool rcu = warn_rcu_enter(); struct warn_args args; pr_warn(CUT_HERE); @@ -693,11 +703,13 @@ void warn_slowpath_fmt(const char *file, int line, unsigned taint, va_start(args.args, fmt); __warn(file, line, __builtin_return_address(0), taint, NULL, &args); va_end(args.args); + warn_rcu_exit(rcu); } EXPORT_SYMBOL(warn_slowpath_fmt); #else void __warn_printk(const char *fmt, ...) { + bool rcu = warn_rcu_enter(); va_list args; pr_warn(CUT_HERE); @@ -705,6 +717,7 @@ void __warn_printk(const char *fmt, ...) va_start(args, fmt); vprintk(fmt, args); va_end(args); + warn_rcu_exit(rcu); } EXPORT_SYMBOL(__warn_printk); #endif diff --git a/kernel/params.c b/kernel/params.c index 14d66070757b..6e34ca89ebae 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -4,6 +4,7 @@ */ #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/module.h> @@ -310,7 +311,7 @@ int param_set_bool(const char *val, const struct kernel_param *kp) if (!val) val = "1"; /* One of =[yYnN01] */ - return strtobool(val, kp->arg); + return kstrtobool(val, kp->arg); } EXPORT_SYMBOL(param_set_bool); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f4f8cb0435b4..46e0d5a3f91f 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -23,6 +23,7 @@ #include <linux/sched/task.h> #include <linux/sched/signal.h> #include <linux/idr.h> +#include "pid_sysctl.h" static DEFINE_MUTEX(pid_caches_mutex); static struct kmem_cache *pid_ns_cachep; @@ -110,6 +111,8 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; + initialize_memfd_noexec_scope(ns); + return ns; out_free_idr: @@ -244,7 +247,24 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) set_current_state(TASK_INTERRUPTIBLE); if (pid_ns->pid_allocated == init_pids) break; + /* + * Release tasks_rcu_exit_srcu to avoid following deadlock: + * + * 1) TASK A unshare(CLONE_NEWPID) + * 2) TASK A fork() twice -> TASK B (child reaper for new ns) + * and TASK C + * 3) TASK B exits, kills TASK C, waits for TASK A to reap it + * 4) TASK A calls synchronize_rcu_tasks() + * -> synchronize_srcu(tasks_rcu_exit_srcu) + * 5) *DEADLOCK* + * + * It is considered safe to release tasks_rcu_exit_srcu here + * because we assume the current task can not be concurrently + * reaped at this point. + */ + exit_tasks_rcu_stop(); schedule(); + exit_tasks_rcu_start(); } __set_current_state(TASK_RUNNING); @@ -455,6 +475,8 @@ static __init int pid_namespaces_init(void) #ifdef CONFIG_CHECKPOINT_RESTORE register_sysctl_paths(kern_path, pid_ns_ctl_table); #endif + + register_pid_ns_sysctl_table_vm(); return 0; } diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h new file mode 100644 index 000000000000..e22d072e1e24 --- /dev/null +++ b/kernel/pid_sysctl.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef LINUX_PID_SYSCTL_H +#define LINUX_PID_SYSCTL_H + +#include <linux/pid_namespace.h> + +#if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) +{ + ns->memfd_noexec_scope = + task_active_pid_ns(current)->memfd_noexec_scope; +} + +static int pid_mfd_noexec_dointvec_minmax(struct ctl_table *table, + int write, void *buf, size_t *lenp, loff_t *ppos) +{ + struct pid_namespace *ns = task_active_pid_ns(current); + struct ctl_table table_copy; + + if (write && !ns_capable(ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + table_copy = *table; + if (ns != &init_pid_ns) + table_copy.data = &ns->memfd_noexec_scope; + + /* + * set minimum to current value, the effect is only bigger + * value is accepted. + */ + if (*(int *)table_copy.data > *(int *)table_copy.extra1) + table_copy.extra1 = table_copy.data; + + return proc_dointvec_minmax(&table_copy, write, buf, lenp, ppos); +} + +static struct ctl_table pid_ns_ctl_table_vm[] = { + { + .procname = "memfd_noexec", + .data = &init_pid_ns.memfd_noexec_scope, + .maxlen = sizeof(init_pid_ns.memfd_noexec_scope), + .mode = 0644, + .proc_handler = pid_mfd_noexec_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; +static struct ctl_path vm_path[] = { { .procname = "vm", }, { } }; +static inline void register_pid_ns_sysctl_table_vm(void) +{ + register_sysctl_paths(vm_path, pid_ns_ctl_table_vm); +} +#else +static inline void initialize_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void set_memfd_noexec_scope(struct pid_namespace *ns) {} +static inline void register_pid_ns_sysctl_table_vm(void) {} +#endif + +#endif /* LINUX_PID_SYSCTL_H */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 60a1d3051cc7..4b31629c5be4 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -118,7 +118,6 @@ config PM_SLEEP def_bool y depends on SUSPEND || HIBERNATE_CALLBACKS select PM - select SRCU config PM_SLEEP_SMP def_bool y diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index f82111837b8d..7b44f5b89fa1 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -87,10 +87,7 @@ static void em_debug_create_pd(struct device *dev) static void em_debug_remove_pd(struct device *dev) { - struct dentry *debug_dir; - - debug_dir = debugfs_lookup(dev_name(dev), rootdir); - debugfs_remove_recursive(debug_dir); + debugfs_lookup_and_remove(dev_name(dev), rootdir); } static int __init em_debug_init(void) diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 277434b6c0bf..36a1df48280c 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -581,7 +581,7 @@ static int save_image(struct swap_map_handle *handle, return ret; } -/** +/* * Structure used for CRC32. */ struct crc_data { @@ -596,7 +596,7 @@ struct crc_data { unsigned char *unc[LZO_THREADS]; /* uncompressed data */ }; -/** +/* * CRC32 update function that runs in its own thread. */ static int crc32_threadfn(void *data) @@ -623,7 +623,7 @@ static int crc32_threadfn(void *data) } return 0; } -/** +/* * Structure used for LZO data compression. */ struct cmp_data { @@ -640,7 +640,7 @@ struct cmp_data { unsigned char wrk[LZO1X_1_MEM_COMPRESS]; /* compression workspace */ }; -/** +/* * Compression function that runs in its own thread. */ static int lzo_compress_threadfn(void *data) @@ -948,9 +948,9 @@ out_finish: return error; } -/** +/* * The following functions allow us to read data using a swap map - * in a file-alike way + * in a file-like way. */ static void release_swap_reader(struct swap_map_handle *handle) @@ -1107,7 +1107,7 @@ static int load_image(struct swap_map_handle *handle, return ret; } -/** +/* * Structure used for LZO data decompression. */ struct dec_data { @@ -1123,7 +1123,7 @@ struct dec_data { unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ }; -/** +/* * Decompression function that runs in its own thread. */ static int lzo_decompress_threadfn(void *data) diff --git a/kernel/printk/index.c b/kernel/printk/index.c index c85be186a783..a6b27526baaf 100644 --- a/kernel/printk/index.c +++ b/kernel/printk/index.c @@ -145,7 +145,7 @@ static void pi_create_file(struct module *mod) #ifdef CONFIG_MODULES static void pi_remove_file(struct module *mod) { - debugfs_remove(debugfs_lookup(pi_get_module_name(mod), dfs_index)); + debugfs_lookup_and_remove(pi_get_module_name(mod), dfs_index); } static int pi_module_notify(struct notifier_block *nb, unsigned long op, diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index d947ca6c84f9..2a17704136f1 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -14,6 +14,21 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, #ifdef CONFIG_PRINTK +#ifdef CONFIG_PRINTK_CALLER +#define PRINTK_PREFIX_MAX 48 +#else +#define PRINTK_PREFIX_MAX 32 +#endif + +/* + * the maximum size of a formatted record (i.e. with prefix added + * per line and dropped messages or in extended message format) + */ +#define PRINTK_MESSAGE_MAX 2048 + +/* the maximum size allowed to be reserved for a record */ +#define PRINTKRB_RECORD_MAX 1024 + /* Flags for a single printk record. */ enum printk_info_flags { LOG_NEWLINE = 2, /* text ended with a newline */ @@ -48,6 +63,10 @@ u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); #else +#define PRINTK_PREFIX_MAX 0 +#define PRINTK_MESSAGE_MAX 0 +#define PRINTKRB_RECORD_MAX 0 + /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so @@ -58,3 +77,29 @@ u16 printk_parse_prefix(const char *text, int *level, static inline bool printk_percpu_data_ready(void) { return false; } #endif /* CONFIG_PRINTK */ + +/** + * struct printk_buffers - Buffers to read/format/output printk messages. + * @outbuf: After formatting, contains text to output. + * @scratchbuf: Used as temporary ringbuffer reading and string-print space. + */ +struct printk_buffers { + char outbuf[PRINTK_MESSAGE_MAX]; + char scratchbuf[PRINTKRB_RECORD_MAX]; +}; + +/** + * struct printk_message - Container for a prepared printk message. + * @pbufs: printk buffers used to prepare the message. + * @outbuf_len: The length of prepared text in @pbufs->outbuf to output. This + * does not count the terminator. A value of 0 means there is + * nothing to output and this record should be skipped. + * @seq: The sequence number of the record used for @pbufs->outbuf. + * @dropped: The number of dropped records from reading @seq. + */ +struct printk_message { + struct printk_buffers *pbufs; + unsigned int outbuf_len; + u64 seq; + unsigned long dropped; +}; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7decf1e9c486..fd0c9f913940 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -123,6 +123,7 @@ bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } +EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { @@ -465,21 +466,6 @@ static struct latched_seq clear_seq = { .val[1] = 0, }; -#ifdef CONFIG_PRINTK_CALLER -#define PREFIX_MAX 48 -#else -#define PREFIX_MAX 32 -#endif - -/* the maximum size of a formatted record (i.e. with prefix added per line) */ -#define CONSOLE_LOG_MAX 1024 - -/* the maximum size for a dropped text message */ -#define DROPPED_TEXT_MAX 64 - -/* the maximum size allowed to be reserved for a record */ -#define LOG_LINE_MAX (CONSOLE_LOG_MAX - PREFIX_MAX) - #define LOG_LEVEL(v) ((v) & 0x07) #define LOG_FACILITY(v) ((v) >> 3 & 0xff) @@ -710,16 +696,15 @@ out: return len; } +static bool printk_get_next_message(struct printk_message *pmsg, u64 seq, + bool is_extended, bool may_supress); + /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { atomic64_t seq; struct ratelimit_state rs; struct mutex lock; - char buf[CONSOLE_EXT_LOG_MAX]; - - struct printk_info info; - char text_buf[CONSOLE_EXT_LOG_MAX]; - struct printk_record record; + struct printk_buffers pbufs; }; static __printf(3, 4) __cold @@ -745,7 +730,7 @@ static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from) size_t len = iov_iter_count(from); ssize_t ret = len; - if (!user || len > LOG_LINE_MAX) + if (!user || len > PRINTKRB_RECORD_MAX) return -EINVAL; /* Ignore when user logging is disabled. */ @@ -801,8 +786,10 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct devkmsg_user *user = file->private_data; - struct printk_record *r = &user->record; - size_t len; + char *outbuf = &user->pbufs.outbuf[0]; + struct printk_message pmsg = { + .pbufs = &user->pbufs, + }; ssize_t ret; if (!user) @@ -812,7 +799,7 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, if (ret) return ret; - if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) { + if (!printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, false)) { if (file->f_flags & O_NONBLOCK) { ret = -EAGAIN; goto out; @@ -829,36 +816,31 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf, * This pairs with __wake_up_klogd:A. */ ret = wait_event_interruptible(log_wait, - prb_read_valid(prb, - atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */ + printk_get_next_message(&pmsg, atomic64_read(&user->seq), true, + false)); /* LMM(devkmsg_read:A) */ if (ret) goto out; } - if (r->info->seq != atomic64_read(&user->seq)) { + if (pmsg.dropped) { /* our last seen message is gone, return error and reset */ - atomic64_set(&user->seq, r->info->seq); + atomic64_set(&user->seq, pmsg.seq); ret = -EPIPE; goto out; } - len = info_print_ext_header(user->buf, sizeof(user->buf), r->info); - len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len, - &r->text_buf[0], r->info->text_len, - &r->info->dev_info); - - atomic64_set(&user->seq, r->info->seq + 1); + atomic64_set(&user->seq, pmsg.seq + 1); - if (len > count) { + if (pmsg.outbuf_len > count) { ret = -EINVAL; goto out; } - if (copy_to_user(buf, user->buf, len)) { + if (copy_to_user(buf, outbuf, pmsg.outbuf_len)) { ret = -EFAULT; goto out; } - ret = len; + ret = pmsg.outbuf_len; out: mutex_unlock(&user->lock); return ret; @@ -952,9 +934,6 @@ static int devkmsg_open(struct inode *inode, struct file *file) mutex_init(&user->lock); - prb_rec_init_rd(&user->record, &user->info, - &user->text_buf[0], sizeof(user->text_buf)); - atomic64_set(&user->seq, prb_first_valid_seq(prb)); file->private_data = user; @@ -1149,7 +1128,7 @@ static unsigned int __init add_to_rb(struct printk_ringbuffer *rb, return prb_record_text_space(&e); } -static char setup_text_buf[LOG_LINE_MAX] __initdata; +static char setup_text_buf[PRINTKRB_RECORD_MAX] __initdata; void __init setup_log_buf(int early) { @@ -1415,7 +1394,7 @@ static size_t record_print_text(struct printk_record *r, bool syslog, size_t text_len = r->info->text_len; size_t buf_size = r->text_buf_size; char *text = r->text_buf; - char prefix[PREFIX_MAX]; + char prefix[PRINTK_PREFIX_MAX]; bool truncated = false; size_t prefix_len; size_t line_len; @@ -1514,7 +1493,7 @@ static size_t get_record_print_text_size(struct printk_info *info, unsigned int line_count, bool syslog, bool time) { - char prefix[PREFIX_MAX]; + char prefix[PRINTK_PREFIX_MAX]; size_t prefix_len; prefix_len = info_print_prefix(info, syslog, time, prefix); @@ -1580,11 +1559,11 @@ static int syslog_print(char __user *buf, int size) int len = 0; u64 seq; - text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; - prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); mutex_lock(&syslog_lock); @@ -1685,7 +1664,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) u64 seq; bool time; - text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL); + text = kmalloc(PRINTK_MESSAGE_MAX, GFP_KERNEL); if (!text) return -ENOMEM; @@ -1697,7 +1676,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear) seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1, size, true, time); - prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + prb_rec_init_rd(&r, &info, text, PRINTK_MESSAGE_MAX); len = 0; prb_for_each_record(seq, prb, seq, &r) { @@ -1891,6 +1870,7 @@ static void console_lock_spinning_enable(void) /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter + * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer @@ -2011,27 +1991,6 @@ static int console_trylock_spinning(void) } /* - * Call the specified console driver, asking it to write out the specified - * text and length. If @dropped_text is non-NULL and any records have been - * dropped, a dropped message will be written out first. - */ -static void call_console_driver(struct console *con, const char *text, size_t len, - char *dropped_text) -{ - size_t dropped_len; - - if (con->dropped && dropped_text) { - dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX, - "** %lu printk messages dropped **\n", - con->dropped); - con->dropped = 0; - con->write(con, dropped_text, dropped_len); - } - - con->write(con, text, len); -} - -/* * Recursion is tracked separately on each CPU. If NMIs are supported, an * additional NMI context per CPU is also separately tracked. Until per-CPU * is available, a separate "early tracking" is performed. @@ -2194,7 +2153,7 @@ static u16 printk_sprint(char *text, u16 size, int facility, } } - trace_console_rcuidle(text, text_len); + trace_console(text, text_len); return text_len; } @@ -2241,8 +2200,8 @@ int vprintk_store(int facility, int level, reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1; va_end(args2); - if (reserve_size > LOG_LINE_MAX) - reserve_size = LOG_LINE_MAX; + if (reserve_size > PRINTKRB_RECORD_MAX) + reserve_size = PRINTKRB_RECORD_MAX; /* Extract log level or control flags. */ if (facility == 0) @@ -2256,7 +2215,7 @@ int vprintk_store(int facility, int level, if (flags & LOG_CONT) { prb_rec_init_wr(&r, reserve_size); - if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) { + if (prb_reserve_in_last(&e, prb, &r, caller_id, PRINTKRB_RECORD_MAX)) { text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size, facility, &flags, fmt, args); r.info->text_len += text_len; @@ -2387,8 +2346,6 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre #else /* CONFIG_PRINTK */ -#define CONSOLE_LOG_MAX 0 -#define DROPPED_TEXT_MAX 0 #define printk_time false #define prb_read_valid(rb, seq, r) false @@ -2412,10 +2369,6 @@ static ssize_t msg_print_ext_body(char *buf, size_t size, struct dev_printk_info *dev_info) { return 0; } static void console_lock_spinning_enable(void) { } static int console_lock_spinning_disable_and_check(int cookie) { return 0; } -static void call_console_driver(struct console *con, const char *text, size_t len, - char *dropped_text) -{ -} static bool suppress_message_printing(int level) { return false; } static bool pr_flush(int timeout_ms, bool reset_on_progress) { return true; } static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; } @@ -2742,16 +2695,136 @@ static void __console_unlock(void) } /* - * Print one record for the given console. The record printed is whatever - * record is the next available record for the given console. + * Prepend the message in @pmsg->pbufs->outbuf with a "dropped message". This + * is achieved by shifting the existing message over and inserting the dropped + * message. * - * @text is a buffer of size CONSOLE_LOG_MAX. + * @pmsg is the printk message to prepend. * - * If extended messages should be printed, @ext_text is a buffer of size - * CONSOLE_EXT_LOG_MAX. Otherwise @ext_text must be NULL. + * @dropped is the dropped count to report in the dropped message. * - * If dropped messages should be printed, @dropped_text is a buffer of size - * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL. + * If the message text in @pmsg->pbufs->outbuf does not have enough space for + * the dropped message, the message text will be sufficiently truncated. + * + * If @pmsg->pbufs->outbuf is modified, @pmsg->outbuf_len is updated. + */ +#ifdef CONFIG_PRINTK +static void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) +{ + struct printk_buffers *pbufs = pmsg->pbufs; + const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); + const size_t outbuf_sz = sizeof(pbufs->outbuf); + char *scratchbuf = &pbufs->scratchbuf[0]; + char *outbuf = &pbufs->outbuf[0]; + size_t len; + + len = scnprintf(scratchbuf, scratchbuf_sz, + "** %lu printk messages dropped **\n", dropped); + + /* + * Make sure outbuf is sufficiently large before prepending. + * Keep at least the prefix when the message must be truncated. + * It is a rather theoretical problem when someone tries to + * use a minimalist buffer. + */ + if (WARN_ON_ONCE(len + PRINTK_PREFIX_MAX >= outbuf_sz)) + return; + + if (pmsg->outbuf_len + len >= outbuf_sz) { + /* Truncate the message, but keep it terminated. */ + pmsg->outbuf_len = outbuf_sz - (len + 1); + outbuf[pmsg->outbuf_len] = 0; + } + + memmove(outbuf + len, outbuf, pmsg->outbuf_len + 1); + memcpy(outbuf, scratchbuf, len); + pmsg->outbuf_len += len; +} +#else +#define console_prepend_dropped(pmsg, dropped) +#endif /* CONFIG_PRINTK */ + +/* + * Read and format the specified record (or a later record if the specified + * record is not available). + * + * @pmsg will contain the formatted result. @pmsg->pbufs must point to a + * struct printk_buffers. + * + * @seq is the record to read and format. If it is not available, the next + * valid record is read. + * + * @is_extended specifies if the message should be formatted for extended + * console output. + * + * @may_supress specifies if records may be skipped based on loglevel. + * + * Returns false if no record is available. Otherwise true and all fields + * of @pmsg are valid. (See the documentation of struct printk_message + * for information about the @pmsg fields.) + */ +static bool printk_get_next_message(struct printk_message *pmsg, u64 seq, + bool is_extended, bool may_suppress) +{ + static int panic_console_dropped; + + struct printk_buffers *pbufs = pmsg->pbufs; + const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); + const size_t outbuf_sz = sizeof(pbufs->outbuf); + char *scratchbuf = &pbufs->scratchbuf[0]; + char *outbuf = &pbufs->outbuf[0]; + struct printk_info info; + struct printk_record r; + size_t len = 0; + + /* + * Formatting extended messages requires a separate buffer, so use the + * scratch buffer to read in the ringbuffer text. + * + * Formatting normal messages is done in-place, so read the ringbuffer + * text directly into the output buffer. + */ + if (is_extended) + prb_rec_init_rd(&r, &info, scratchbuf, scratchbuf_sz); + else + prb_rec_init_rd(&r, &info, outbuf, outbuf_sz); + + if (!prb_read_valid(prb, seq, &r)) + return false; + + pmsg->seq = r.info->seq; + pmsg->dropped = r.info->seq - seq; + + /* + * Check for dropped messages in panic here so that printk + * suppression can occur as early as possible if necessary. + */ + if (pmsg->dropped && + panic_in_progress() && + panic_console_dropped++ > 10) { + suppress_panic_printk = 1; + pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); + } + + /* Skip record that has level above the console loglevel. */ + if (may_suppress && suppress_message_printing(r.info->level)) + goto out; + + if (is_extended) { + len = info_print_ext_header(outbuf, outbuf_sz, r.info); + len += msg_print_ext_body(outbuf + len, outbuf_sz - len, + &r.text_buf[0], r.info->text_len, &r.info->dev_info); + } else { + len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + } +out: + pmsg->outbuf_len = len; + return true; +} + +/* + * Print one record for the given console. The record printed is whatever + * record is the next available record for the given console. * * @handover will be set to true if a printk waiter has taken over the * console_lock, in which case the caller is no longer holding both the @@ -2764,46 +2837,33 @@ static void __console_unlock(void) * * Requires the console_lock and the SRCU read lock. */ -static bool console_emit_next_record(struct console *con, char *text, char *ext_text, - char *dropped_text, bool *handover, int cookie) +static bool console_emit_next_record(struct console *con, bool *handover, int cookie) { - static int panic_console_dropped; - struct printk_info info; - struct printk_record r; - unsigned long flags; - char *write_text; - size_t len; + static struct printk_buffers pbufs; - prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX); + bool is_extended = console_srcu_read_flags(con) & CON_EXTENDED; + char *outbuf = &pbufs.outbuf[0]; + struct printk_message pmsg = { + .pbufs = &pbufs, + }; + unsigned long flags; *handover = false; - if (!prb_read_valid(prb, con->seq, &r)) + if (!printk_get_next_message(&pmsg, con->seq, is_extended, true)) return false; - if (con->seq != r.info->seq) { - con->dropped += r.info->seq - con->seq; - con->seq = r.info->seq; - if (panic_in_progress() && panic_console_dropped++ > 10) { - suppress_panic_printk = 1; - pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); - } - } + con->dropped += pmsg.dropped; - /* Skip record that has level above the console loglevel. */ - if (suppress_message_printing(r.info->level)) { - con->seq++; + /* Skip messages of formatted length 0. */ + if (pmsg.outbuf_len == 0) { + con->seq = pmsg.seq + 1; goto skip; } - if (ext_text) { - write_text = ext_text; - len = info_print_ext_header(ext_text, CONSOLE_EXT_LOG_MAX, r.info); - len += msg_print_ext_body(ext_text + len, CONSOLE_EXT_LOG_MAX - len, - &r.text_buf[0], r.info->text_len, &r.info->dev_info); - } else { - write_text = text; - len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time); + if (con->dropped && !is_extended) { + console_prepend_dropped(&pmsg, con->dropped); + con->dropped = 0; } /* @@ -2819,11 +2879,15 @@ static bool console_emit_next_record(struct console *con, char *text, char *ext_ printk_safe_enter_irqsave(flags); console_lock_spinning_enable(); - stop_critical_timings(); /* don't trace print latency */ - call_console_driver(con, write_text, len, dropped_text); + /* Do not trace print latency. */ + stop_critical_timings(); + + /* Write everything out to the hardware. */ + con->write(con, outbuf, pmsg.outbuf_len); + start_critical_timings(); - con->seq++; + con->seq = pmsg.seq + 1; *handover = console_lock_spinning_disable_and_check(cookie); printk_safe_exit_irqrestore(flags); @@ -2856,9 +2920,6 @@ skip: */ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover) { - static char dropped_text[DROPPED_TEXT_MAX]; - static char ext_text[CONSOLE_EXT_LOG_MAX]; - static char text[CONSOLE_LOG_MAX]; bool any_usable = false; struct console *con; bool any_progress; @@ -2878,16 +2939,7 @@ static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handove continue; any_usable = true; - if (console_srcu_read_flags(con) & CON_EXTENDED) { - /* Extended consoles do not print "dropped messages". */ - progress = console_emit_next_record(con, &text[0], - &ext_text[0], NULL, - handover, cookie); - } else { - progress = console_emit_next_record(con, &text[0], - NULL, &dropped_text[0], - handover, cookie); - } + progress = console_emit_next_record(con, handover, cookie); /* * If a handover has occurred, the SRCU read lock diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 54482193e1ed..0786450074c1 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -813,7 +813,7 @@ static long ptrace_get_rseq_configuration(struct task_struct *task, { struct ptrace_rseq_configuration conf = { .rseq_abi_pointer = (u64)(uintptr_t)task->rseq, - .rseq_abi_size = sizeof(*task->rseq), + .rseq_abi_size = task->rseq_len, .signature = task->rseq_sig, .flags = 0, }; diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug index 232e29fe3e5e..2984de629f74 100644 --- a/kernel/rcu/Kconfig.debug +++ b/kernel/rcu/Kconfig.debug @@ -82,7 +82,7 @@ config RCU_CPU_STALL_TIMEOUT config RCU_EXP_CPU_STALL_TIMEOUT int "Expedited RCU CPU stall timeout in milliseconds" depends on RCU_STALL_COMMON - range 0 21000 + range 0 300000 default 0 help If a given expedited RCU grace period extends more than the @@ -92,6 +92,19 @@ config RCU_EXP_CPU_STALL_TIMEOUT says to use the RCU_CPU_STALL_TIMEOUT value converted from seconds to milliseconds. +config RCU_CPU_STALL_CPUTIME + bool "Provide additional RCU stall debug information" + depends on RCU_STALL_COMMON + default n + help + Collect statistics during the sampling period, such as the number of + (hard interrupts, soft interrupts, task switches) and the cputime of + (hard interrupts, soft interrupts, kernel tasks) are added to the + RCU stall report. For multiple continuous RCU stalls, all sampling + periods begin at half of the first RCU stall timeout. + The boot option rcupdate.rcu_cpu_stall_cputime has the same function + as this one, but will override this if it exists. + config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index c5aa934de59b..115616ac3bfa 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -224,6 +224,8 @@ extern int rcu_cpu_stall_ftrace_dump; extern int rcu_cpu_stall_suppress; extern int rcu_cpu_stall_timeout; extern int rcu_exp_cpu_stall_timeout; +extern int rcu_cpu_stall_cputime; +extern bool rcu_exp_stall_task_details __read_mostly; int rcu_jiffies_till_stall_check(void); int rcu_exp_jiffies_till_stall_check(void); @@ -447,14 +449,20 @@ do { \ /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ static inline bool rcu_gp_is_normal(void) { return true; } static inline bool rcu_gp_is_expedited(void) { return false; } +static inline bool rcu_async_should_hurry(void) { return false; } static inline void rcu_expedite_gp(void) { } static inline void rcu_unexpedite_gp(void) { } +static inline void rcu_async_hurry(void) { } +static inline void rcu_async_relax(void) { } static inline void rcu_request_urgent_qs_task(struct task_struct *t) { } #else /* #ifdef CONFIG_TINY_RCU */ bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ +bool rcu_async_should_hurry(void); /* Internal RCU use. */ void rcu_expedite_gp(void); void rcu_unexpedite_gp(void); +void rcu_async_hurry(void); +void rcu_async_relax(void); void rcupdate_announce_bootup_oddness(void); #ifdef CONFIG_TASKS_RCU_GENERIC void show_rcu_tasks_gp_kthreads(void); diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index c54ea2b6a36b..f71fac422c8f 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -89,7 +89,7 @@ static void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v) } /* Get the length of a segment of the rcu_segcblist structure. */ -static long rcu_segcblist_get_seglen(struct rcu_segcblist *rsclp, int seg) +long rcu_segcblist_get_seglen(struct rcu_segcblist *rsclp, int seg) { return READ_ONCE(rsclp->seglen[seg]); } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 431cee212467..4fe877f5f654 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -15,6 +15,8 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp) return READ_ONCE(rclp->len); } +long rcu_segcblist_get_seglen(struct rcu_segcblist *rsclp, int seg); + /* Return number of callbacks in segmented callback list by summing seglen. */ long rcu_segcblist_n_segment_cbs(struct rcu_segcblist *rsclp); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 634df26a2c27..8e6c023212cb 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -399,7 +399,7 @@ static int torture_readlock_not_held(void) return rcu_read_lock_bh_held() || rcu_read_lock_sched_held(); } -static int rcu_torture_read_lock(void) __acquires(RCU) +static int rcu_torture_read_lock(void) { rcu_read_lock(); return 0; @@ -441,7 +441,7 @@ rcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) } } -static void rcu_torture_read_unlock(int idx) __releases(RCU) +static void rcu_torture_read_unlock(int idx) { rcu_read_unlock(); } @@ -625,7 +625,7 @@ static struct srcu_struct srcu_ctld; static struct srcu_struct *srcu_ctlp = &srcu_ctl; static struct rcu_torture_ops srcud_ops; -static int srcu_torture_read_lock(void) __acquires(srcu_ctlp) +static int srcu_torture_read_lock(void) { if (cur_ops == &srcud_ops) return srcu_read_lock_nmisafe(srcu_ctlp); @@ -652,7 +652,7 @@ srcu_read_delay(struct torture_random_state *rrsp, struct rt_read_seg *rtrsp) } } -static void srcu_torture_read_unlock(int idx) __releases(srcu_ctlp) +static void srcu_torture_read_unlock(int idx) { if (cur_ops == &srcud_ops) srcu_read_unlock_nmisafe(srcu_ctlp, idx); @@ -814,13 +814,13 @@ static void synchronize_rcu_trivial(void) } } -static int rcu_torture_read_lock_trivial(void) __acquires(RCU) +static int rcu_torture_read_lock_trivial(void) { preempt_disable(); return 0; } -static void rcu_torture_read_unlock_trivial(int idx) __releases(RCU) +static void rcu_torture_read_unlock_trivial(int idx) { preempt_enable(); } diff --git a/kernel/rcu/refscale.c b/kernel/rcu/refscale.c index 435c884c02b5..afa3e1a2f690 100644 --- a/kernel/rcu/refscale.c +++ b/kernel/rcu/refscale.c @@ -76,6 +76,8 @@ torture_param(int, verbose_batched, 0, "Batch verbose debugging printk()s"); // Wait until there are multiple CPUs before starting test. torture_param(int, holdoff, IS_BUILTIN(CONFIG_RCU_REF_SCALE_TEST) ? 10 : 0, "Holdoff time before test start (s)"); +// Number of typesafe_lookup structures, that is, the degree of concurrency. +torture_param(long, lookup_instances, 0, "Number of typesafe_lookup structures."); // Number of loops per experiment, all readers execute operations concurrently. torture_param(long, loops, 10000, "Number of loops per experiment."); // Number of readers, with -1 defaulting to about 75% of the CPUs. @@ -124,7 +126,7 @@ static int exp_idx; // Operations vector for selecting different types of tests. struct ref_scale_ops { - void (*init)(void); + bool (*init)(void); void (*cleanup)(void); void (*readsection)(const int nloops); void (*delaysection)(const int nloops, const int udl, const int ndl); @@ -162,8 +164,9 @@ static void ref_rcu_delay_section(const int nloops, const int udl, const int ndl } } -static void rcu_sync_scale_init(void) +static bool rcu_sync_scale_init(void) { + return true; } static struct ref_scale_ops rcu_ops = { @@ -315,9 +318,10 @@ static struct ref_scale_ops refcnt_ops = { // Definitions for rwlock static rwlock_t test_rwlock; -static void ref_rwlock_init(void) +static bool ref_rwlock_init(void) { rwlock_init(&test_rwlock); + return true; } static void ref_rwlock_section(const int nloops) @@ -351,9 +355,10 @@ static struct ref_scale_ops rwlock_ops = { // Definitions for rwsem static struct rw_semaphore test_rwsem; -static void ref_rwsem_init(void) +static bool ref_rwsem_init(void) { init_rwsem(&test_rwsem); + return true; } static void ref_rwsem_section(const int nloops) @@ -523,6 +528,237 @@ static struct ref_scale_ops clock_ops = { .name = "clock" }; +//////////////////////////////////////////////////////////////////////// +// +// Methods leveraging SLAB_TYPESAFE_BY_RCU. +// + +// Item to look up in a typesafe manner. Array of pointers to these. +struct refscale_typesafe { + atomic_t rts_refctr; // Used by all flavors + spinlock_t rts_lock; + seqlock_t rts_seqlock; + unsigned int a; + unsigned int b; +}; + +static struct kmem_cache *typesafe_kmem_cachep; +static struct refscale_typesafe **rtsarray; +static long rtsarray_size; +static DEFINE_TORTURE_RANDOM_PERCPU(refscale_rand); +static bool (*rts_acquire)(struct refscale_typesafe *rtsp, unsigned int *start); +static bool (*rts_release)(struct refscale_typesafe *rtsp, unsigned int start); + +// Conditionally acquire an explicit in-structure reference count. +static bool typesafe_ref_acquire(struct refscale_typesafe *rtsp, unsigned int *start) +{ + return atomic_inc_not_zero(&rtsp->rts_refctr); +} + +// Unconditionally release an explicit in-structure reference count. +static bool typesafe_ref_release(struct refscale_typesafe *rtsp, unsigned int start) +{ + if (!atomic_dec_return(&rtsp->rts_refctr)) { + WRITE_ONCE(rtsp->a, rtsp->a + 1); + kmem_cache_free(typesafe_kmem_cachep, rtsp); + } + return true; +} + +// Unconditionally acquire an explicit in-structure spinlock. +static bool typesafe_lock_acquire(struct refscale_typesafe *rtsp, unsigned int *start) +{ + spin_lock(&rtsp->rts_lock); + return true; +} + +// Unconditionally release an explicit in-structure spinlock. +static bool typesafe_lock_release(struct refscale_typesafe *rtsp, unsigned int start) +{ + spin_unlock(&rtsp->rts_lock); + return true; +} + +// Unconditionally acquire an explicit in-structure sequence lock. +static bool typesafe_seqlock_acquire(struct refscale_typesafe *rtsp, unsigned int *start) +{ + *start = read_seqbegin(&rtsp->rts_seqlock); + return true; +} + +// Conditionally release an explicit in-structure sequence lock. Return +// true if this release was successful, that is, if no retry is required. +static bool typesafe_seqlock_release(struct refscale_typesafe *rtsp, unsigned int start) +{ + return !read_seqretry(&rtsp->rts_seqlock, start); +} + +// Do a read-side critical section with the specified delay in +// microseconds and nanoseconds inserted so as to increase probability +// of failure. +static void typesafe_delay_section(const int nloops, const int udl, const int ndl) +{ + unsigned int a; + unsigned int b; + int i; + long idx; + struct refscale_typesafe *rtsp; + unsigned int start; + + for (i = nloops; i >= 0; i--) { + preempt_disable(); + idx = torture_random(this_cpu_ptr(&refscale_rand)) % rtsarray_size; + preempt_enable(); +retry: + rcu_read_lock(); + rtsp = rcu_dereference(rtsarray[idx]); + a = READ_ONCE(rtsp->a); + if (!rts_acquire(rtsp, &start)) { + rcu_read_unlock(); + goto retry; + } + if (a != READ_ONCE(rtsp->a)) { + (void)rts_release(rtsp, start); + rcu_read_unlock(); + goto retry; + } + un_delay(udl, ndl); + // Remember, seqlock read-side release can fail. + if (!rts_release(rtsp, start)) { + rcu_read_unlock(); + goto retry; + } + b = READ_ONCE(rtsp->a); + WARN_ONCE(a != b, "Re-read of ->a changed from %u to %u.\n", a, b); + b = rtsp->b; + rcu_read_unlock(); + WARN_ON_ONCE(a * a != b); + } +} + +// Because the acquisition and release methods are expensive, there +// is no point in optimizing away the un_delay() function's two checks. +// Thus simply define typesafe_read_section() as a simple wrapper around +// typesafe_delay_section(). +static void typesafe_read_section(const int nloops) +{ + typesafe_delay_section(nloops, 0, 0); +} + +// Allocate and initialize one refscale_typesafe structure. +static struct refscale_typesafe *typesafe_alloc_one(void) +{ + struct refscale_typesafe *rtsp; + + rtsp = kmem_cache_alloc(typesafe_kmem_cachep, GFP_KERNEL); + if (!rtsp) + return NULL; + atomic_set(&rtsp->rts_refctr, 1); + WRITE_ONCE(rtsp->a, rtsp->a + 1); + WRITE_ONCE(rtsp->b, rtsp->a * rtsp->a); + return rtsp; +} + +// Slab-allocator constructor for refscale_typesafe structures created +// out of a new slab of system memory. +static void refscale_typesafe_ctor(void *rtsp_in) +{ + struct refscale_typesafe *rtsp = rtsp_in; + + spin_lock_init(&rtsp->rts_lock); + seqlock_init(&rtsp->rts_seqlock); + preempt_disable(); + rtsp->a = torture_random(this_cpu_ptr(&refscale_rand)); + preempt_enable(); +} + +static struct ref_scale_ops typesafe_ref_ops; +static struct ref_scale_ops typesafe_lock_ops; +static struct ref_scale_ops typesafe_seqlock_ops; + +// Initialize for a typesafe test. +static bool typesafe_init(void) +{ + long idx; + long si = lookup_instances; + + typesafe_kmem_cachep = kmem_cache_create("refscale_typesafe", + sizeof(struct refscale_typesafe), sizeof(void *), + SLAB_TYPESAFE_BY_RCU, refscale_typesafe_ctor); + if (!typesafe_kmem_cachep) + return false; + if (si < 0) + si = -si * nr_cpu_ids; + else if (si == 0) + si = nr_cpu_ids; + rtsarray_size = si; + rtsarray = kcalloc(si, sizeof(*rtsarray), GFP_KERNEL); + if (!rtsarray) + return false; + for (idx = 0; idx < rtsarray_size; idx++) { + rtsarray[idx] = typesafe_alloc_one(); + if (!rtsarray[idx]) + return false; + } + if (cur_ops == &typesafe_ref_ops) { + rts_acquire = typesafe_ref_acquire; + rts_release = typesafe_ref_release; + } else if (cur_ops == &typesafe_lock_ops) { + rts_acquire = typesafe_lock_acquire; + rts_release = typesafe_lock_release; + } else if (cur_ops == &typesafe_seqlock_ops) { + rts_acquire = typesafe_seqlock_acquire; + rts_release = typesafe_seqlock_release; + } else { + WARN_ON_ONCE(1); + return false; + } + return true; +} + +// Clean up after a typesafe test. +static void typesafe_cleanup(void) +{ + long idx; + + if (rtsarray) { + for (idx = 0; idx < rtsarray_size; idx++) + kmem_cache_free(typesafe_kmem_cachep, rtsarray[idx]); + kfree(rtsarray); + rtsarray = NULL; + rtsarray_size = 0; + } + kmem_cache_destroy(typesafe_kmem_cachep); + typesafe_kmem_cachep = NULL; + rts_acquire = NULL; + rts_release = NULL; +} + +// The typesafe_init() function distinguishes these structures by address. +static struct ref_scale_ops typesafe_ref_ops = { + .init = typesafe_init, + .cleanup = typesafe_cleanup, + .readsection = typesafe_read_section, + .delaysection = typesafe_delay_section, + .name = "typesafe_ref" +}; + +static struct ref_scale_ops typesafe_lock_ops = { + .init = typesafe_init, + .cleanup = typesafe_cleanup, + .readsection = typesafe_read_section, + .delaysection = typesafe_delay_section, + .name = "typesafe_lock" +}; + +static struct ref_scale_ops typesafe_seqlock_ops = { + .init = typesafe_init, + .cleanup = typesafe_cleanup, + .readsection = typesafe_read_section, + .delaysection = typesafe_delay_section, + .name = "typesafe_seqlock" +}; + static void rcu_scale_one_reader(void) { if (readdelay <= 0) @@ -812,6 +1048,7 @@ ref_scale_init(void) static struct ref_scale_ops *scale_ops[] = { &rcu_ops, &srcu_ops, RCU_TRACE_OPS RCU_TASKS_OPS &refcnt_ops, &rwlock_ops, &rwsem_ops, &lock_ops, &lock_irq_ops, &acqrel_ops, &clock_ops, + &typesafe_ref_ops, &typesafe_lock_ops, &typesafe_seqlock_ops, }; if (!torture_init_begin(scale_type, verbose)) @@ -833,7 +1070,10 @@ ref_scale_init(void) goto unwind; } if (cur_ops->init) - cur_ops->init(); + if (!cur_ops->init()) { + firsterr = -EUCLEAN; + goto unwind; + } ref_scale_print_module_parms(cur_ops, "Start of test"); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index ca4b5dcec675..ab4ee58af84b 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -154,7 +154,7 @@ static void init_srcu_struct_data(struct srcu_struct *ssp) */ static inline bool srcu_invl_snp_seq(unsigned long s) { - return rcu_seq_state(s) == SRCU_SNP_INIT_SEQ; + return s == SRCU_SNP_INIT_SEQ; } /* @@ -469,24 +469,59 @@ static bool srcu_readers_active_idx_check(struct srcu_struct *ssp, int idx) /* * If the locks are the same as the unlocks, then there must have - * been no readers on this index at some time in between. This does - * not mean that there are no more readers, as one could have read - * the current index but not have incremented the lock counter yet. + * been no readers on this index at some point in this function. + * But there might be more readers, as a task might have read + * the current ->srcu_idx but not yet have incremented its CPU's + * ->srcu_lock_count[idx] counter. In fact, it is possible + * that most of the tasks have been preempted between fetching + * ->srcu_idx and incrementing ->srcu_lock_count[idx]. And there + * could be almost (ULONG_MAX / sizeof(struct task_struct)) tasks + * in a system whose address space was fully populated with memory. + * Call this quantity Nt. * - * So suppose that the updater is preempted here for so long - * that more than ULONG_MAX non-nested readers come and go in - * the meantime. It turns out that this cannot result in overflow - * because if a reader modifies its unlock count after we read it - * above, then that reader's next load of ->srcu_idx is guaranteed - * to get the new value, which will cause it to operate on the - * other bank of counters, where it cannot contribute to the - * overflow of these counters. This means that there is a maximum - * of 2*NR_CPUS increments, which cannot overflow given current - * systems, especially not on 64-bit systems. + * So suppose that the updater is preempted at this point in the + * code for a long time. That now-preempted updater has already + * flipped ->srcu_idx (possibly during the preceding grace period), + * done an smp_mb() (again, possibly during the preceding grace + * period), and summed up the ->srcu_unlock_count[idx] counters. + * How many times can a given one of the aforementioned Nt tasks + * increment the old ->srcu_idx value's ->srcu_lock_count[idx] + * counter, in the absence of nesting? * - * OK, how about nesting? This does impose a limit on nesting - * of floor(ULONG_MAX/NR_CPUS/2), which should be sufficient, - * especially on 64-bit systems. + * It can clearly do so once, given that it has already fetched + * the old value of ->srcu_idx and is just about to use that value + * to index its increment of ->srcu_lock_count[idx]. But as soon as + * it leaves that SRCU read-side critical section, it will increment + * ->srcu_unlock_count[idx], which must follow the updater's above + * read from that same value. Thus, as soon the reading task does + * an smp_mb() and a later fetch from ->srcu_idx, that task will be + * guaranteed to get the new index. Except that the increment of + * ->srcu_unlock_count[idx] in __srcu_read_unlock() is after the + * smp_mb(), and the fetch from ->srcu_idx in __srcu_read_lock() + * is before the smp_mb(). Thus, that task might not see the new + * value of ->srcu_idx until the -second- __srcu_read_lock(), + * which in turn means that this task might well increment + * ->srcu_lock_count[idx] for the old value of ->srcu_idx twice, + * not just once. + * + * However, it is important to note that a given smp_mb() takes + * effect not just for the task executing it, but also for any + * later task running on that same CPU. + * + * That is, there can be almost Nt + Nc further increments of + * ->srcu_lock_count[idx] for the old index, where Nc is the number + * of CPUs. But this is OK because the size of the task_struct + * structure limits the value of Nt and current systems limit Nc + * to a few thousand. + * + * OK, but what about nesting? This does impose a limit on + * nesting of half of the size of the task_struct structure + * (measured in bytes), which should be sufficient. A late 2022 + * TREE01 rcutorture run reported this size to be no less than + * 9408 bytes, allowing up to 4704 levels of nesting, which is + * comfortably beyond excessive. Especially on 64-bit systems, + * which are unlikely to be configured with an address space fully + * populated with memory, at least not anytime soon. */ return srcu_readers_lock_idx(ssp, idx) == unlocks; } @@ -726,7 +761,7 @@ static void srcu_gp_start(struct srcu_struct *ssp) int state; if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) - sdp = per_cpu_ptr(ssp->sda, 0); + sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id()); else sdp = this_cpu_ptr(ssp->sda); lockdep_assert_held(&ACCESS_PRIVATE(ssp, lock)); @@ -837,7 +872,8 @@ static void srcu_gp_end(struct srcu_struct *ssp) /* Initiate callback invocation as needed. */ ss_state = smp_load_acquire(&ssp->srcu_size_state); if (ss_state < SRCU_SIZE_WAIT_BARRIER) { - srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, 0), cbdelay); + srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, get_boot_cpu_id()), + cbdelay); } else { idx = rcu_seq_ctr(gpseq) % ARRAY_SIZE(snp->srcu_have_cbs); srcu_for_each_node_breadth_first(ssp, snp) { @@ -914,7 +950,7 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp if (snp) for (; snp != NULL; snp = snp->srcu_parent) { sgsne = READ_ONCE(snp->srcu_gp_seq_needed_exp); - if (rcu_seq_done(&ssp->srcu_gp_seq, s) || + if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) || (!srcu_invl_snp_seq(sgsne) && ULONG_CMP_GE(sgsne, s))) return; spin_lock_irqsave_rcu_node(snp, flags); @@ -941,6 +977,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *ssp, struct srcu_node *snp * * Note that this function also does the work of srcu_funnel_exp_start(), * in some cases by directly invoking it. + * + * The srcu read lock should be hold around this function. And s is a seq snap + * after holding that lock. */ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, unsigned long s, bool do_norm) @@ -961,7 +1000,7 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, if (snp_leaf) /* Each pass through the loop does one level of the srcu_node tree. */ for (snp = snp_leaf; snp != NULL; snp = snp->srcu_parent) { - if (rcu_seq_done(&ssp->srcu_gp_seq, s) && snp != snp_leaf) + if (WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) && snp != snp_leaf) return; /* GP already done and CBs recorded. */ spin_lock_irqsave_rcu_node(snp, flags); snp_seq = snp->srcu_have_cbs[idx]; @@ -998,8 +1037,8 @@ static void srcu_funnel_gp_start(struct srcu_struct *ssp, struct srcu_data *sdp, if (!do_norm && ULONG_CMP_LT(ssp->srcu_gp_seq_needed_exp, s)) WRITE_ONCE(ssp->srcu_gp_seq_needed_exp, s); - /* If grace period not already done and none in progress, start it. */ - if (!rcu_seq_done(&ssp->srcu_gp_seq, s) && + /* If grace period not already in progress, start it. */ + if (!WARN_ON_ONCE(rcu_seq_done(&ssp->srcu_gp_seq, s)) && rcu_seq_state(ssp->srcu_gp_seq) == SRCU_STATE_IDLE) { WARN_ON_ONCE(ULONG_CMP_GE(ssp->srcu_gp_seq, ssp->srcu_gp_seq_needed)); srcu_gp_start(ssp); @@ -1059,10 +1098,11 @@ static void srcu_flip(struct srcu_struct *ssp) /* * Ensure that if the updater misses an __srcu_read_unlock() - * increment, that task's next __srcu_read_lock() will see the - * above counter update. Note that both this memory barrier - * and the one in srcu_readers_active_idx_check() provide the - * guarantee for __srcu_read_lock(). + * increment, that task's __srcu_read_lock() following its next + * __srcu_read_lock() or __srcu_read_unlock() will see the above + * counter update. Note that both this memory barrier and the + * one in srcu_readers_active_idx_check() provide the guarantee + * for __srcu_read_lock(). */ smp_mb(); /* D */ /* Pairs with C. */ } @@ -1161,7 +1201,7 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, idx = __srcu_read_lock_nmisafe(ssp); ss_state = smp_load_acquire(&ssp->srcu_size_state); if (ss_state < SRCU_SIZE_WAIT_CALL) - sdp = per_cpu_ptr(ssp->sda, 0); + sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id()); else sdp = raw_cpu_ptr(ssp->sda); spin_lock_irqsave_sdp_contention(sdp, &flags); @@ -1497,7 +1537,7 @@ void srcu_barrier(struct srcu_struct *ssp) idx = __srcu_read_lock_nmisafe(ssp); if (smp_load_acquire(&ssp->srcu_size_state) < SRCU_SIZE_WAIT_BARRIER) - srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, 0)); + srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, get_boot_cpu_id())); else for_each_possible_cpu(cpu) srcu_barrier_one_cpu(ssp, per_cpu_ptr(ssp->sda, cpu)); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index fe9840d90e96..bfb5e1549f2b 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -384,6 +384,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) { int cpu; unsigned long flags; + bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq); long n; long ncbs = 0; long ncbsnz = 0; @@ -425,21 +426,23 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids)); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); + gpdone = false; pr_info("Starting switch %s to CPU-0 callback queuing.\n", rtp->name); } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); } - if (rcu_task_cb_adjust && !ncbsnz && - poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq)) { + if (rcu_task_cb_adjust && !ncbsnz && gpdone) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim < rtp->percpu_dequeue_lim) { WRITE_ONCE(rtp->percpu_dequeue_lim, 1); pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name); } - for (cpu = rtp->percpu_dequeue_lim; cpu < nr_cpu_ids; cpu++) { - struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); + if (rtp->percpu_dequeue_lim == 1) { + for (cpu = rtp->percpu_dequeue_lim; cpu < nr_cpu_ids; cpu++) { + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); - WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist)); + WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist)); + } } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); } @@ -560,8 +563,9 @@ static int __noreturn rcu_tasks_kthread(void *arg) static void synchronize_rcu_tasks_generic(struct rcu_tasks *rtp) { /* Complain if the scheduler has not started. */ - WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, - "synchronize_rcu_tasks called too soon"); + if (WARN_ONCE(rcu_scheduler_active == RCU_SCHEDULER_INACTIVE, + "synchronize_%s() called too soon", rtp->name)) + return; // If the grace-period kthread is running, use it. if (READ_ONCE(rtp->kthread_ptr)) { @@ -827,11 +831,21 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) static void rcu_tasks_postscan(struct list_head *hop) { /* - * Wait for tasks that are in the process of exiting. This - * does only part of the job, ensuring that all tasks that were - * previously exiting reach the point where they have disabled - * preemption, allowing the later synchronize_rcu() to finish - * the job. + * Exiting tasks may escape the tasklist scan. Those are vulnerable + * until their final schedule() with TASK_DEAD state. To cope with + * this, divide the fragile exit path part in two intersecting + * read side critical sections: + * + * 1) An _SRCU_ read side starting before calling exit_notify(), + * which may remove the task from the tasklist, and ending after + * the final preempt_disable() call in do_exit(). + * + * 2) An _RCU_ read side starting with the final preempt_disable() + * call in do_exit() and ending with the final call to schedule() + * with TASK_DEAD state. + * + * This handles the part 1). And postgp will handle part 2) with a + * call to synchronize_rcu(). */ synchronize_srcu(&tasks_rcu_exit_srcu); } @@ -898,7 +912,10 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) * * In addition, this synchronize_rcu() waits for exiting tasks * to complete their final preempt_disable() region of execution, - * cleaning up after the synchronize_srcu() above. + * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu), + * enforcing the whole region before tasklist removal until + * the final schedule() with TASK_DEAD state to be an RCU TASKS + * read side critical section. */ synchronize_rcu(); } @@ -988,27 +1005,42 @@ void show_rcu_tasks_classic_gp_kthread(void) EXPORT_SYMBOL_GPL(show_rcu_tasks_classic_gp_kthread); #endif // !defined(CONFIG_TINY_RCU) -/* Do the srcu_read_lock() for the above synchronize_srcu(). */ +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) { - preempt_disable(); current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu); - preempt_enable(); } -/* Do the srcu_read_unlock() for the above synchronize_srcu(). */ -void exit_tasks_rcu_finish(void) __releases(&tasks_rcu_exit_srcu) +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ +void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu) { struct task_struct *t = current; - preempt_disable(); __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx); - preempt_enable(); - exit_tasks_rcu_finish_trace(t); +} + +/* + * Contribute to protect against tasklist scan blind spot while the + * task is exiting and may be removed from the tasklist. See + * corresponding synchronize_srcu() for further details. + */ +void exit_tasks_rcu_finish(void) +{ + exit_tasks_rcu_stop(); + exit_tasks_rcu_finish_trace(current); } #else /* #ifdef CONFIG_TASKS_RCU */ void exit_tasks_rcu_start(void) { } +void exit_tasks_rcu_stop(void) { } void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); } #endif /* #else #ifdef CONFIG_TASKS_RCU */ @@ -1036,9 +1068,6 @@ static void rcu_tasks_be_rude(struct work_struct *work) // Wait for one rude RCU-tasks grace period. static void rcu_tasks_rude_wait_gp(struct rcu_tasks *rtp) { - if (num_online_cpus() <= 1) - return; // Fastpath for only one CPU. - rtp->n_ipis += cpumask_weight(cpu_online_mask); schedule_on_each_cpu(rcu_tasks_be_rude); } @@ -1815,23 +1844,21 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp) static void rcu_tasks_initiate_self_tests(void) { - unsigned long j = jiffies; - pr_info("Running RCU-tasks wait API self tests\n"); #ifdef CONFIG_TASKS_RCU - tests[0].runstart = j; + tests[0].runstart = jiffies; synchronize_rcu_tasks(); call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback); #endif #ifdef CONFIG_TASKS_RUDE_RCU - tests[1].runstart = j; + tests[1].runstart = jiffies; synchronize_rcu_tasks_rude(); call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback); #endif #ifdef CONFIG_TASKS_TRACE_RCU - tests[2].runstart = j; + tests[2].runstart = jiffies; synchronize_rcu_tasks_trace(); call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback); #endif diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 72913ce21258..42f7589e51e0 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -246,15 +246,12 @@ bool poll_state_synchronize_rcu(unsigned long oldstate) EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu); #ifdef CONFIG_KASAN_GENERIC -void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +void kvfree_call_rcu(struct rcu_head *head, void *ptr) { - if (head) { - void *ptr = (void *) head - (unsigned long) func; - + if (head) kasan_record_aux_stack_noalloc(ptr); - } - __kvfree_call_rcu(head, func); + __kvfree_call_rcu(head, ptr); } EXPORT_SYMBOL_GPL(kvfree_call_rcu); #endif diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cf34a961821a..8e880c09ab59 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -144,14 +144,16 @@ static int rcu_scheduler_fully_active __read_mostly; static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); -static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); -static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); static void check_cb_ovld_locked(struct rcu_data *rdp, struct rcu_node *rnp); static bool rcu_rdp_is_offloaded(struct rcu_data *rdp); +static bool rcu_rdp_cpu_online(struct rcu_data *rdp); +static bool rcu_init_invoked(void); +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf); +static void rcu_init_new_rnp(struct rcu_node *rnp_leaf); /* * rcuc/rcub/rcuop kthread realtime priority. The "rcuop" @@ -215,27 +217,6 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio); #define PER_RCU_NODE_PERIOD 3 /* Number of grace periods between delays for debugging. */ /* - * Compute the mask of online CPUs for the specified rcu_node structure. - * This will not be stable unless the rcu_node structure's ->lock is - * held, but the bit corresponding to the current CPU will be stable - * in most contexts. - */ -static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) -{ - return READ_ONCE(rnp->qsmaskinitnext); -} - -/* - * Is the CPU corresponding to the specified rcu_data structure online - * from RCU's perspective? This perspective is given by that structure's - * ->qsmaskinitnext field rather than by the global cpu_online_mask. - */ -static bool rcu_rdp_cpu_online(struct rcu_data *rdp) -{ - return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode)); -} - -/* * Return true if an RCU grace period is in progress. The READ_ONCE()s * permit this function to be invoked without holding the root rcu_node * structure's ->lock, but of course results can be subject to change. @@ -734,46 +715,6 @@ void rcu_request_urgent_qs_task(struct task_struct *t) smp_store_release(per_cpu_ptr(&rcu_data.rcu_urgent_qs, cpu), true); } -#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) - -/* - * Is the current CPU online as far as RCU is concerned? - * - * Disable preemption to avoid false positives that could otherwise - * happen due to the current CPU number being sampled, this task being - * preempted, its old CPU being taken offline, resuming on some other CPU, - * then determining that its old CPU is now offline. - * - * Disable checking if in an NMI handler because we cannot safely - * report errors from NMI handlers anyway. In addition, it is OK to use - * RCU on an offline processor during initial boot, hence the check for - * rcu_scheduler_fully_active. - */ -bool rcu_lockdep_current_cpu_online(void) -{ - struct rcu_data *rdp; - bool ret = false; - - if (in_nmi() || !rcu_scheduler_fully_active) - return true; - preempt_disable_notrace(); - rdp = this_cpu_ptr(&rcu_data); - /* - * Strictly, we care here about the case where the current CPU is - * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask - * not being up to date. So arch_spin_is_locked() might have a - * false positive if it's held by some *other* CPU, but that's - * OK because that just means a false *negative* on the warning. - */ - if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock)) - ret = true; - preempt_enable_notrace(); - return ret; -} -EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); - -#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ - /* * When trying to report a quiescent state on behalf of some other CPU, * it is our responsibility to check for and handle potential overflow @@ -925,6 +866,24 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) rdp->rcu_iw_gp_seq = rnp->gp_seq; irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); } + + if (rcu_cpu_stall_cputime && rdp->snap_record.gp_seq != rdp->gp_seq) { + int cpu = rdp->cpu; + struct rcu_snap_record *rsrp; + struct kernel_cpustat *kcsp; + + kcsp = &kcpustat_cpu(cpu); + + rsrp = &rdp->snap_record; + rsrp->cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu); + rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu); + rsrp->cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu); + rsrp->nr_hardirqs = kstat_cpu_irqs_sum(rdp->cpu); + rsrp->nr_softirqs = kstat_cpu_softirqs_sum(rdp->cpu); + rsrp->nr_csw = nr_context_switches_cpu(rdp->cpu); + rsrp->jiffies = jiffies; + rsrp->gp_seq = rdp->gp_seq; + } } return 0; @@ -1350,13 +1309,6 @@ static void rcu_strict_gp_boundary(void *unused) invoke_rcu_core(); } -// Has rcu_init() been invoked? This is used (for example) to determine -// whether spinlocks may be acquired safely. -static bool rcu_init_invoked(void) -{ - return !!rcu_state.n_online_cpus; -} - // Make the polled API aware of the beginning of a grace period. static void rcu_poll_gp_seq_start(unsigned long *snap) { @@ -2092,92 +2044,6 @@ rcu_check_quiescent_state(struct rcu_data *rdp) } /* - * Near the end of the offline process. Trace the fact that this CPU - * is going offline. - */ -int rcutree_dying_cpu(unsigned int cpu) -{ - bool blkd; - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct rcu_node *rnp = rdp->mynode; - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return 0; - - blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask); - trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), - blkd ? TPS("cpuofl-bgp") : TPS("cpuofl")); - return 0; -} - -/* - * All CPUs for the specified rcu_node structure have gone offline, - * and all tasks that were preempted within an RCU read-side critical - * section while running on one of those CPUs have since exited their RCU - * read-side critical section. Some other CPU is reporting this fact with - * the specified rcu_node structure's ->lock held and interrupts disabled. - * This function therefore goes up the tree of rcu_node structures, - * clearing the corresponding bits in the ->qsmaskinit fields. Note that - * the leaf rcu_node structure's ->qsmaskinit field has already been - * updated. - * - * This function does check that the specified rcu_node structure has - * all CPUs offline and no blocked tasks, so it is OK to invoke it - * prematurely. That said, invoking it after the fact will cost you - * a needless lock acquisition. So once it has done its work, don't - * invoke it again. - */ -static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) -{ - long mask; - struct rcu_node *rnp = rnp_leaf; - - raw_lockdep_assert_held_rcu_node(rnp_leaf); - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || - WARN_ON_ONCE(rnp_leaf->qsmaskinit) || - WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) - return; - for (;;) { - mask = rnp->grpmask; - rnp = rnp->parent; - if (!rnp) - break; - raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ - rnp->qsmaskinit &= ~mask; - /* Between grace periods, so better already be zero! */ - WARN_ON_ONCE(rnp->qsmask); - if (rnp->qsmaskinit) { - raw_spin_unlock_rcu_node(rnp); - /* irqs remain disabled. */ - return; - } - raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ - } -} - -/* - * The CPU has been completely removed, and some other CPU is reporting - * this fact from process context. Do the remainder of the cleanup. - * There can only be one CPU hotplug operation at a time, so no need for - * explicit locking. - */ -int rcutree_dead_cpu(unsigned int cpu) -{ - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); - struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ - - if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) - return 0; - - WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1); - /* Adjust any no-longer-needed kthreads. */ - rcu_boost_kthread_setaffinity(rnp, -1); - // Stop-machine done, so allow nohz_full to disable tick. - tick_dep_clear(TICK_DEP_BIT_RCU); - return 0; -} - -/* * Invoke any RCU callbacks that have made it to the end of their grace * period. Throttle as specified by rdp->blimit. */ @@ -2209,7 +2075,7 @@ static void rcu_do_batch(struct rcu_data *rdp) */ rcu_nocb_lock_irqsave(rdp, flags); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); - pending = rcu_segcblist_n_cbs(&rdp->cblist); + pending = rcu_segcblist_get_seglen(&rdp->cblist, RCU_DONE_TAIL); div = READ_ONCE(rcu_divisor); div = div < 0 ? 7 : div > sizeof(long) * 8 - 2 ? sizeof(long) * 8 - 2 : div; bl = max(rdp->blimit, pending >> div); @@ -2727,10 +2593,11 @@ static void check_cb_ovld(struct rcu_data *rdp) } static void -__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy) +__call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) { static atomic_t doublefrees; unsigned long flags; + bool lazy; struct rcu_data *rdp; bool was_alldone; @@ -2755,6 +2622,7 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy) kasan_record_aux_stack_noalloc(head); local_irq_save(flags); rdp = this_cpu_ptr(&rcu_data); + lazy = lazy_in && !rcu_async_should_hurry(); /* Add the callback to our list. */ if (unlikely(!rcu_segcblist_is_enabled(&rdp->cblist))) { @@ -2876,13 +2744,15 @@ EXPORT_SYMBOL_GPL(call_rcu); /** * struct kvfree_rcu_bulk_data - single block to store kvfree_rcu() pointers + * @list: List node. All blocks are linked between each other + * @gp_snap: Snapshot of RCU state for objects placed to this bulk * @nr_records: Number of active pointers in the array - * @next: Next bulk object in the block chain * @records: Array of the kvfree_rcu() pointers */ struct kvfree_rcu_bulk_data { + struct list_head list; + unsigned long gp_snap; unsigned long nr_records; - struct kvfree_rcu_bulk_data *next; void *records[]; }; @@ -2898,26 +2768,28 @@ struct kvfree_rcu_bulk_data { * 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 - * @bkvhead_free: Bulk-List of kvfree_rcu() objects waiting for a grace period + * @bulk_head_free: Bulk-List of kvfree_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 kvfree_rcu_bulk_data *bkvhead_free[FREE_N_CHANNELS]; + struct list_head bulk_head_free[FREE_N_CHANNELS]; 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 - * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period + * @head_gp_snap: Snapshot of RCU state for objects placed to "@head" + * @bulk_head: Bulk-List of kvfree_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 * @initialized: The @rcu_work fields have been initialized - * @count: Number of objects for which GP not started + * @head_count: Number of objects in rcu_head singular list + * @bulk_count: Number of objects in bulk-list * @bkvcache: * A simple cache list that contains objects for reuse purpose. * In order to save some per-cpu space the list is singular. @@ -2935,13 +2807,20 @@ struct kfree_rcu_cpu_work { * the interactions with the slab allocators. */ struct kfree_rcu_cpu { + // Objects queued on a linked list + // through their rcu_head structures. struct rcu_head *head; - struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS]; + unsigned long head_gp_snap; + atomic_t head_count; + + // Objects queued on a bulk-list. + struct list_head bulk_head[FREE_N_CHANNELS]; + atomic_t bulk_count[FREE_N_CHANNELS]; + struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES]; raw_spinlock_t lock; struct delayed_work monitor_work; bool initialized; - int count; struct delayed_work page_cache_work; atomic_t backoff_page_cache_fill; @@ -3029,29 +2908,87 @@ drain_page_cache(struct kfree_rcu_cpu *krcp) return freed; } +static void +kvfree_rcu_bulk(struct kfree_rcu_cpu *krcp, + struct kvfree_rcu_bulk_data *bnode, int idx) +{ + unsigned long flags; + int i; + + debug_rcu_bhead_unqueue(bnode); + + rcu_lock_acquire(&rcu_callback_map); + if (idx == 0) { // kmalloc() / kfree(). + trace_rcu_invoke_kfree_bulk_callback( + rcu_state.name, bnode->nr_records, + bnode->records); + + kfree_bulk(bnode->nr_records, bnode->records); + } else { // vmalloc() / vfree(). + for (i = 0; i < bnode->nr_records; i++) { + trace_rcu_invoke_kvfree_callback( + rcu_state.name, bnode->records[i], 0); + + vfree(bnode->records[i]); + } + } + rcu_lock_release(&rcu_callback_map); + + raw_spin_lock_irqsave(&krcp->lock, flags); + if (put_cached_bnode(krcp, bnode)) + bnode = NULL; + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + if (bnode) + free_page((unsigned long) bnode); + + cond_resched_tasks_rcu_qs(); +} + +static void +kvfree_rcu_list(struct rcu_head *head) +{ + struct rcu_head *next; + + for (; head; head = next) { + void *ptr = (void *) head->func; + unsigned long offset = (void *) head - ptr; + + next = head->next; + debug_rcu_head_unqueue((struct rcu_head *)ptr); + rcu_lock_acquire(&rcu_callback_map); + trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); + + if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) + kvfree(ptr); + + rcu_lock_release(&rcu_callback_map); + cond_resched_tasks_rcu_qs(); + } +} + /* * This function is invoked in workqueue context after a grace period. - * It frees all the objects queued on ->bkvhead_free or ->head_free. + * It frees all the objects queued on ->bulk_head_free or ->head_free. */ static void kfree_rcu_work(struct work_struct *work) { unsigned long flags; - struct kvfree_rcu_bulk_data *bkvhead[FREE_N_CHANNELS], *bnext; - struct rcu_head *head, *next; + struct kvfree_rcu_bulk_data *bnode, *n; + struct list_head bulk_head[FREE_N_CHANNELS]; + struct rcu_head *head; struct kfree_rcu_cpu *krcp; struct kfree_rcu_cpu_work *krwp; - int i, j; + int i; krwp = container_of(to_rcu_work(work), - struct kfree_rcu_cpu_work, rcu_work); + struct kfree_rcu_cpu_work, rcu_work); krcp = krwp->krcp; raw_spin_lock_irqsave(&krcp->lock, flags); // Channels 1 and 2. - for (i = 0; i < FREE_N_CHANNELS; i++) { - bkvhead[i] = krwp->bkvhead_free[i]; - krwp->bkvhead_free[i] = NULL; - } + for (i = 0; i < FREE_N_CHANNELS; i++) + list_replace_init(&krwp->bulk_head_free[i], &bulk_head[i]); // Channel 3. head = krwp->head_free; @@ -3060,39 +2997,9 @@ static void kfree_rcu_work(struct work_struct *work) // Handle the first two channels. for (i = 0; i < FREE_N_CHANNELS; i++) { - for (; bkvhead[i]; bkvhead[i] = bnext) { - bnext = bkvhead[i]->next; - debug_rcu_bhead_unqueue(bkvhead[i]); - - rcu_lock_acquire(&rcu_callback_map); - if (i == 0) { // kmalloc() / kfree(). - trace_rcu_invoke_kfree_bulk_callback( - rcu_state.name, bkvhead[i]->nr_records, - bkvhead[i]->records); - - kfree_bulk(bkvhead[i]->nr_records, - bkvhead[i]->records); - } else { // vmalloc() / vfree(). - for (j = 0; j < bkvhead[i]->nr_records; j++) { - trace_rcu_invoke_kvfree_callback( - rcu_state.name, - bkvhead[i]->records[j], 0); - - vfree(bkvhead[i]->records[j]); - } - } - rcu_lock_release(&rcu_callback_map); - - raw_spin_lock_irqsave(&krcp->lock, flags); - if (put_cached_bnode(krcp, bkvhead[i])) - bkvhead[i] = NULL; - raw_spin_unlock_irqrestore(&krcp->lock, flags); - - if (bkvhead[i]) - free_page((unsigned long) bkvhead[i]); - - cond_resched_tasks_rcu_qs(); - } + // Start from the tail page, so a GP is likely passed for it. + list_for_each_entry_safe(bnode, n, &bulk_head[i], list) + kvfree_rcu_bulk(krcp, bnode, i); } /* @@ -3102,21 +3009,7 @@ static void kfree_rcu_work(struct work_struct *work) * queued on a linked list through their rcu_head structures. * This list is named "Channel 3". */ - for (; head; head = next) { - unsigned long offset = (unsigned long)head->func; - void *ptr = (void *)head - offset; - - next = head->next; - debug_rcu_head_unqueue((struct rcu_head *)ptr); - rcu_lock_acquire(&rcu_callback_map); - trace_rcu_invoke_kvfree_callback(rcu_state.name, head, offset); - - if (!WARN_ON_ONCE(!__is_kvfree_rcu_offset(offset))) - kvfree(ptr); - - rcu_lock_release(&rcu_callback_map); - cond_resched_tasks_rcu_qs(); - } + kvfree_rcu_list(head); } static bool @@ -3125,10 +3018,21 @@ need_offload_krc(struct kfree_rcu_cpu *krcp) int i; for (i = 0; i < FREE_N_CHANNELS; i++) - if (krcp->bkvhead[i]) + if (!list_empty(&krcp->bulk_head[i])) return true; - return !!krcp->head; + return !!READ_ONCE(krcp->head); +} + +static int krc_count(struct kfree_rcu_cpu *krcp) +{ + int sum = atomic_read(&krcp->head_count); + int i; + + for (i = 0; i < FREE_N_CHANNELS; i++) + sum += atomic_read(&krcp->bulk_count[i]); + + return sum; } static void @@ -3136,7 +3040,7 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) { long delay, delay_left; - delay = READ_ONCE(krcp->count) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; + delay = krc_count(krcp) >= KVFREE_BULK_MAX_ENTR ? 1:KFREE_DRAIN_JIFFIES; if (delayed_work_pending(&krcp->monitor_work)) { delay_left = krcp->monitor_work.timer.expires - jiffies; if (delay < delay_left) @@ -3146,6 +3050,44 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp) queue_delayed_work(system_wq, &krcp->monitor_work, delay); } +static void +kvfree_rcu_drain_ready(struct kfree_rcu_cpu *krcp) +{ + struct list_head bulk_ready[FREE_N_CHANNELS]; + struct kvfree_rcu_bulk_data *bnode, *n; + struct rcu_head *head_ready = NULL; + unsigned long flags; + int i; + + raw_spin_lock_irqsave(&krcp->lock, flags); + for (i = 0; i < FREE_N_CHANNELS; i++) { + INIT_LIST_HEAD(&bulk_ready[i]); + + list_for_each_entry_safe_reverse(bnode, n, &krcp->bulk_head[i], list) { + if (!poll_state_synchronize_rcu(bnode->gp_snap)) + break; + + atomic_sub(bnode->nr_records, &krcp->bulk_count[i]); + list_move(&bnode->list, &bulk_ready[i]); + } + } + + if (krcp->head && poll_state_synchronize_rcu(krcp->head_gp_snap)) { + head_ready = krcp->head; + atomic_set(&krcp->head_count, 0); + WRITE_ONCE(krcp->head, NULL); + } + raw_spin_unlock_irqrestore(&krcp->lock, flags); + + for (i = 0; i < FREE_N_CHANNELS; i++) { + list_for_each_entry_safe(bnode, n, &bulk_ready[i], list) + kvfree_rcu_bulk(krcp, bnode, i); + } + + if (head_ready) + kvfree_rcu_list(head_ready); +} + /* * This function is invoked after the KFREE_DRAIN_JIFFIES timeout. */ @@ -3156,26 +3098,31 @@ static void kfree_rcu_monitor(struct work_struct *work) unsigned long flags; int i, j; + // Drain ready for reclaim. + kvfree_rcu_drain_ready(krcp); + raw_spin_lock_irqsave(&krcp->lock, flags); // Attempt to start a new batch. for (i = 0; i < KFREE_N_BATCHES; i++) { struct kfree_rcu_cpu_work *krwp = &(krcp->krw_arr[i]); - // Try to detach bkvhead or head and attach it over any + // Try to detach bulk_head or head and attach it over any // available corresponding free channel. It can be that // a previous RCU batch is in progress, it means that // immediately to queue another one is not possible so // in that case the monitor work is rearmed. - if ((krcp->bkvhead[0] && !krwp->bkvhead_free[0]) || - (krcp->bkvhead[1] && !krwp->bkvhead_free[1]) || - (krcp->head && !krwp->head_free)) { + if ((!list_empty(&krcp->bulk_head[0]) && list_empty(&krwp->bulk_head_free[0])) || + (!list_empty(&krcp->bulk_head[1]) && list_empty(&krwp->bulk_head_free[1])) || + (READ_ONCE(krcp->head) && !krwp->head_free)) { + // Channel 1 corresponds to the SLAB-pointer bulk path. // Channel 2 corresponds to vmalloc-pointer bulk path. for (j = 0; j < FREE_N_CHANNELS; j++) { - if (!krwp->bkvhead_free[j]) { - krwp->bkvhead_free[j] = krcp->bkvhead[j]; - krcp->bkvhead[j] = NULL; + if (list_empty(&krwp->bulk_head_free[j])) { + atomic_set(&krcp->bulk_count[j], 0); + list_replace_init(&krcp->bulk_head[j], + &krwp->bulk_head_free[j]); } } @@ -3183,11 +3130,10 @@ static void kfree_rcu_monitor(struct work_struct *work) // objects queued on the linked list. if (!krwp->head_free) { krwp->head_free = krcp->head; - krcp->head = NULL; + atomic_set(&krcp->head_count, 0); + WRITE_ONCE(krcp->head, NULL); } - WRITE_ONCE(krcp->count, 0); - // One work is per one batch, so there are three // "free channels", the batch can handle. It can // be that the work is in the pending state when @@ -3197,6 +3143,8 @@ static void kfree_rcu_monitor(struct work_struct *work) } } + raw_spin_unlock_irqrestore(&krcp->lock, flags); + // If there is nothing to detach, it means that our job is // successfully done here. In case of having at least one // of the channels that is still busy we should rearm the @@ -3204,8 +3152,6 @@ static void kfree_rcu_monitor(struct work_struct *work) // still in progress. if (need_offload_krc(krcp)) schedule_delayed_monitor_work(krcp); - - raw_spin_unlock_irqrestore(&krcp->lock, flags); } static enum hrtimer_restart @@ -3288,10 +3234,11 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, return false; idx = !!is_vmalloc_addr(ptr); + bnode = list_first_entry_or_null(&(*krcp)->bulk_head[idx], + struct kvfree_rcu_bulk_data, list); /* Check if a new block is required. */ - if (!(*krcp)->bkvhead[idx] || - (*krcp)->bkvhead[idx]->nr_records == KVFREE_BULK_MAX_ENTR) { + if (!bnode || bnode->nr_records == KVFREE_BULK_MAX_ENTR) { bnode = get_cached_bnode(*krcp); if (!bnode && can_alloc) { krc_this_cpu_unlock(*krcp, *flags); @@ -3315,17 +3262,15 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, if (!bnode) return false; - /* Initialize the new block. */ + // Initialize the new block and attach it. bnode->nr_records = 0; - bnode->next = (*krcp)->bkvhead[idx]; - - /* Attach it to the head. */ - (*krcp)->bkvhead[idx] = bnode; + list_add(&bnode->list, &(*krcp)->bulk_head[idx]); } - /* Finally insert. */ - (*krcp)->bkvhead[idx]->records - [(*krcp)->bkvhead[idx]->nr_records++] = ptr; + // Finally insert and update the GP for this page. + bnode->records[bnode->nr_records++] = ptr; + bnode->gp_snap = get_state_synchronize_rcu(); + atomic_inc(&(*krcp)->bulk_count[idx]); return true; } @@ -3342,26 +3287,21 @@ add_ptr_to_bulk_krc_lock(struct kfree_rcu_cpu **krcp, * be free'd in workqueue context. This allows us to: batch requests together to * reduce the number of grace periods during heavy kfree_rcu()/kvfree_rcu() load. */ -void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) +void kvfree_call_rcu(struct rcu_head *head, void *ptr) { unsigned long flags; struct kfree_rcu_cpu *krcp; bool success; - void *ptr; - if (head) { - ptr = (void *) head - (unsigned long) func; - } else { - /* - * Please note there is a limitation for the head-less - * variant, that is why there is a clear rule for such - * objects: it can be used from might_sleep() context - * only. For other places please embed an rcu_head to - * your data. - */ + /* + * Please note there is a limitation for the head-less + * variant, that is why there is a clear rule for such + * objects: it can be used from might_sleep() context + * only. For other places please embed an rcu_head to + * your data. + */ + if (!head) might_sleep(); - ptr = (unsigned long *) func; - } // Queue the object but don't yet schedule the batch. if (debug_rcu_head_queue(ptr)) { @@ -3382,14 +3322,16 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) // Inline if kvfree_rcu(one_arg) call. goto unlock_return; - head->func = func; + head->func = ptr; head->next = krcp->head; - krcp->head = head; + WRITE_ONCE(krcp->head, head); + atomic_inc(&krcp->head_count); + + // Take a snapshot for this krcp. + krcp->head_gp_snap = get_state_synchronize_rcu(); success = true; } - WRITE_ONCE(krcp->count, krcp->count + 1); - // Set timer to drain after KFREE_DRAIN_JIFFIES. if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING) schedule_delayed_monitor_work(krcp); @@ -3420,7 +3362,7 @@ kfree_rcu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - count += READ_ONCE(krcp->count); + count += krc_count(krcp); count += READ_ONCE(krcp->nr_bkv_objs); atomic_set(&krcp->backoff_page_cache_fill, 1); } @@ -3437,7 +3379,7 @@ kfree_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) int count; struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - count = krcp->count; + count = krc_count(krcp); count += drain_page_cache(krcp); kfree_rcu_monitor(&krcp->monitor_work.work); @@ -3461,15 +3403,12 @@ static struct shrinker kfree_rcu_shrinker = { void __init kfree_rcu_scheduler_running(void) { int cpu; - unsigned long flags; for_each_possible_cpu(cpu) { struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu); - raw_spin_lock_irqsave(&krcp->lock, flags); if (need_offload_krc(krcp)) schedule_delayed_monitor_work(krcp); - raw_spin_unlock_irqrestore(&krcp->lock, flags); } } @@ -3485,9 +3424,10 @@ void __init kfree_rcu_scheduler_running(void) */ static int rcu_blocking_is_gp(void) { - if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) + if (rcu_scheduler_active != RCU_SCHEDULER_INACTIVE) { + might_sleep(); return false; - might_sleep(); /* Check for RCU read-side critical section. */ + } return true; } @@ -3711,7 +3651,9 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_full); * If @false is returned, it is the caller's responsibility to invoke this * function later on until it does return @true. Alternatively, the caller * can explicitly wait for a grace period, for example, by passing @oldstate - * to cond_synchronize_rcu() or by directly invoking synchronize_rcu(). + * to either cond_synchronize_rcu() or cond_synchronize_rcu_expedited() + * on the one hand or by directly invoking either synchronize_rcu() or + * synchronize_rcu_expedited() on the other. * * Yes, this function does not take counter wrap into account. * But counter wrap is harmless. If the counter wraps, we have waited for @@ -3722,6 +3664,12 @@ EXPORT_SYMBOL_GPL(start_poll_synchronize_rcu_full); * completed. Alternatively, they can use get_completed_synchronize_rcu() * to get a guaranteed-completed grace-period state. * + * In addition, because oldstate compresses the grace-period state for + * both normal and expedited grace periods into a single unsigned long, + * it can miss a grace period when synchronize_rcu() runs concurrently + * with synchronize_rcu_expedited(). If this is unacceptable, please + * instead use the _full() variant of these polling APIs. + * * This function provides the same memory-ordering guarantees that * would be provided by a synchronize_rcu() that was invoked at the call * to the function that provided @oldstate, and that returned at the end @@ -4080,6 +4028,155 @@ retry: EXPORT_SYMBOL_GPL(rcu_barrier); /* + * Compute the mask of online CPUs for the specified rcu_node structure. + * This will not be stable unless the rcu_node structure's ->lock is + * held, but the bit corresponding to the current CPU will be stable + * in most contexts. + */ +static unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp) +{ + return READ_ONCE(rnp->qsmaskinitnext); +} + +/* + * Is the CPU corresponding to the specified rcu_data structure online + * from RCU's perspective? This perspective is given by that structure's + * ->qsmaskinitnext field rather than by the global cpu_online_mask. + */ +static bool rcu_rdp_cpu_online(struct rcu_data *rdp) +{ + return !!(rdp->grpmask & rcu_rnp_online_cpus(rdp->mynode)); +} + +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) + +/* + * Is the current CPU online as far as RCU is concerned? + * + * Disable preemption to avoid false positives that could otherwise + * happen due to the current CPU number being sampled, this task being + * preempted, its old CPU being taken offline, resuming on some other CPU, + * then determining that its old CPU is now offline. + * + * Disable checking if in an NMI handler because we cannot safely + * report errors from NMI handlers anyway. In addition, it is OK to use + * RCU on an offline processor during initial boot, hence the check for + * rcu_scheduler_fully_active. + */ +bool rcu_lockdep_current_cpu_online(void) +{ + struct rcu_data *rdp; + bool ret = false; + + if (in_nmi() || !rcu_scheduler_fully_active) + return true; + preempt_disable_notrace(); + rdp = this_cpu_ptr(&rcu_data); + /* + * Strictly, we care here about the case where the current CPU is + * in rcu_cpu_starting() and thus has an excuse for rdp->grpmask + * not being up to date. So arch_spin_is_locked() might have a + * false positive if it's held by some *other* CPU, but that's + * OK because that just means a false *negative* on the warning. + */ + if (rcu_rdp_cpu_online(rdp) || arch_spin_is_locked(&rcu_state.ofl_lock)) + ret = true; + preempt_enable_notrace(); + return ret; +} +EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); + +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ + +// Has rcu_init() been invoked? This is used (for example) to determine +// whether spinlocks may be acquired safely. +static bool rcu_init_invoked(void) +{ + return !!rcu_state.n_online_cpus; +} + +/* + * Near the end of the offline process. Trace the fact that this CPU + * is going offline. + */ +int rcutree_dying_cpu(unsigned int cpu) +{ + bool blkd; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct rcu_node *rnp = rdp->mynode; + + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return 0; + + blkd = !!(READ_ONCE(rnp->qsmask) & rdp->grpmask); + trace_rcu_grace_period(rcu_state.name, READ_ONCE(rnp->gp_seq), + blkd ? TPS("cpuofl-bgp") : TPS("cpuofl")); + return 0; +} + +/* + * All CPUs for the specified rcu_node structure have gone offline, + * and all tasks that were preempted within an RCU read-side critical + * section while running on one of those CPUs have since exited their RCU + * read-side critical section. Some other CPU is reporting this fact with + * the specified rcu_node structure's ->lock held and interrupts disabled. + * This function therefore goes up the tree of rcu_node structures, + * clearing the corresponding bits in the ->qsmaskinit fields. Note that + * the leaf rcu_node structure's ->qsmaskinit field has already been + * updated. + * + * This function does check that the specified rcu_node structure has + * all CPUs offline and no blocked tasks, so it is OK to invoke it + * prematurely. That said, invoking it after the fact will cost you + * a needless lock acquisition. So once it has done its work, don't + * invoke it again. + */ +static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf) +{ + long mask; + struct rcu_node *rnp = rnp_leaf; + + raw_lockdep_assert_held_rcu_node(rnp_leaf); + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) || + WARN_ON_ONCE(rnp_leaf->qsmaskinit) || + WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf))) + return; + for (;;) { + mask = rnp->grpmask; + rnp = rnp->parent; + if (!rnp) + break; + raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ + rnp->qsmaskinit &= ~mask; + /* Between grace periods, so better already be zero! */ + WARN_ON_ONCE(rnp->qsmask); + if (rnp->qsmaskinit) { + raw_spin_unlock_rcu_node(rnp); + /* irqs remain disabled. */ + return; + } + raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + } +} + +/* + * The CPU has been completely removed, and some other CPU is reporting + * this fact from process context. Do the remainder of the cleanup. + * There can only be one CPU hotplug operation at a time, so no need for + * explicit locking. + */ +int rcutree_dead_cpu(unsigned int cpu) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return 0; + + WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus - 1); + // Stop-machine done, so allow nohz_full to disable tick. + tick_dep_clear(TICK_DEP_BIT_RCU); + return 0; +} + +/* * Propagate ->qsinitmask bits up the rcu_node tree to account for the * first CPU in a given leaf rcu_node structure coming online. The caller * must hold the corresponding leaf rcu_node ->lock with interrupts @@ -4408,11 +4505,13 @@ static int rcu_pm_notify(struct notifier_block *self, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + rcu_async_hurry(); rcu_expedite_gp(); break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: rcu_unexpedite_gp(); + rcu_async_relax(); break; default: break; @@ -4766,7 +4865,7 @@ struct workqueue_struct *rcu_gp_wq; static void __init kfree_rcu_batch_init(void) { int cpu; - int i; + int i, j; /* Clamp it to [0:100] seconds interval. */ if (rcu_delay_page_cache_fill_msec < 0 || @@ -4786,8 +4885,14 @@ static void __init kfree_rcu_batch_init(void) for (i = 0; i < KFREE_N_BATCHES; i++) { INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work); krcp->krw_arr[i].krcp = krcp; + + for (j = 0; j < FREE_N_CHANNELS; j++) + INIT_LIST_HEAD(&krcp->krw_arr[i].bulk_head_free[j]); } + for (i = 0; i < FREE_N_CHANNELS; i++) + INIT_LIST_HEAD(&krcp->bulk_head[i]); + INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor); INIT_DELAYED_WORK(&krcp->page_cache_work, fill_page_cache_func); krcp->initialized = true; @@ -4838,6 +4943,8 @@ void __init rcu_init(void) // Kick-start any polled grace periods that started early. if (!(per_cpu_ptr(&rcu_data, cpu)->mynode->exp_seq_poll_rq & 0x1)) (void)start_poll_synchronize_rcu_expedited(); + + rcu_test_sync_prims(); } #include "tree_stall.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index fcb5d696eb17..192536916f9a 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -158,6 +158,23 @@ union rcu_noqs { u16 s; /* Set of bits, aggregate OR here. */ }; +/* + * Record the snapshot of the core stats at half of the first RCU stall timeout. + * The member gp_seq is used to ensure that all members are updated only once + * during the sampling period. The snapshot is taken only if this gp_seq is not + * equal to rdp->gp_seq. + */ +struct rcu_snap_record { + unsigned long gp_seq; /* Track rdp->gp_seq counter */ + u64 cputime_irq; /* Accumulated cputime of hard irqs */ + u64 cputime_softirq;/* Accumulated cputime of soft irqs */ + u64 cputime_system; /* Accumulated cputime of kernel tasks */ + unsigned long nr_hardirqs; /* Accumulated number of hard irqs */ + unsigned int nr_softirqs; /* Accumulated number of soft irqs */ + unsigned long long nr_csw; /* Accumulated number of task switches */ + unsigned long jiffies; /* Track jiffies value */ +}; + /* Per-CPU data for read-copy update. */ struct rcu_data { /* 1) quiescent-state and grace-period handling : */ @@ -262,6 +279,8 @@ struct rcu_data { short rcu_onl_gp_flags; /* ->gp_flags at last online. */ unsigned long last_fqs_resched; /* Time of last rcu_resched(). */ unsigned long last_sched_clock; /* Jiffies of last rcu_sched_clock_irq(). */ + struct rcu_snap_record snap_record; /* Snapshot of core stats at half of */ + /* the first RCU stall timeout */ long lazy_len; /* Length of buffered lazy callbacks. */ int cpu; diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index ed6c3cce28f2..249c2967d9e6 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -11,6 +11,7 @@ static void rcu_exp_handler(void *unused); static int rcu_print_task_exp_stall(struct rcu_node *rnp); +static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp); /* * Record the start of an expedited grace period. @@ -667,8 +668,11 @@ static void synchronize_rcu_expedited_wait(void) mask = leaf_node_cpu_bit(rnp, cpu); if (!(READ_ONCE(rnp->expmask) & mask)) continue; + preempt_disable(); // For smp_processor_id() in dump_cpu_task(). dump_cpu_task(cpu); + preempt_enable(); } + rcu_exp_print_detail_task_stall_rnp(rnp); } jiffies_stall = 3 * rcu_exp_jiffies_till_stall_check() + 3; panic_on_rcu_stall(); @@ -811,6 +815,36 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) return ndetected; } +/* + * Scan the current list of tasks blocked within RCU read-side critical + * sections, dumping the stack of each that is blocking the current + * expedited grace period. + */ +static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ + unsigned long flags; + struct task_struct *t; + + if (!rcu_exp_stall_task_details) + return; + raw_spin_lock_irqsave_rcu_node(rnp, flags); + if (!READ_ONCE(rnp->exp_tasks)) { + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + return; + } + t = list_entry(rnp->exp_tasks->prev, + struct task_struct, rcu_node_entry); + list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) { + /* + * We could be printing a lot while holding a spinlock. + * Avoid triggering hard lockup. + */ + touch_nmi_watchdog(); + sched_show_task(t); + } + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); +} + #else /* #ifdef CONFIG_PREEMPT_RCU */ /* Request an expedited quiescent state. */ @@ -883,6 +917,15 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp) return 0; } +/* + * Because preemptible RCU does not exist, we never have to print out + * tasks blocked within RCU read-side critical sections that are blocking + * the current expedited grace period. + */ +static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) +{ +} + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /** diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 5653560573e2..b10b8349bb2a 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -39,7 +39,7 @@ int rcu_exp_jiffies_till_stall_check(void) // CONFIG_RCU_EXP_CPU_STALL_TIMEOUT, so check the allowed range. // The minimum clamped value is "2UL", because at least one full // tick has to be guaranteed. - till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 21UL * HZ); + till_stall_check = clamp(msecs_to_jiffies(cpu_stall_timeout), 2UL, 300UL * HZ); if (cpu_stall_timeout && jiffies_to_msecs(till_stall_check) != cpu_stall_timeout) WRITE_ONCE(rcu_exp_cpu_stall_timeout, jiffies_to_msecs(till_stall_check)); @@ -428,6 +428,35 @@ static bool rcu_is_rcuc_kthread_starving(struct rcu_data *rdp, unsigned long *jp return j > 2 * HZ; } +static void print_cpu_stat_info(int cpu) +{ + struct rcu_snap_record rsr, *rsrp; + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + struct kernel_cpustat *kcsp = &kcpustat_cpu(cpu); + + if (!rcu_cpu_stall_cputime) + return; + + rsrp = &rdp->snap_record; + if (rsrp->gp_seq != rdp->gp_seq) + return; + + rsr.cputime_irq = kcpustat_field(kcsp, CPUTIME_IRQ, cpu); + rsr.cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu); + rsr.cputime_system = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu); + + pr_err("\t hardirqs softirqs csw/system\n"); + pr_err("\t number: %8ld %10d %12lld\n", + kstat_cpu_irqs_sum(cpu) - rsrp->nr_hardirqs, + kstat_cpu_softirqs_sum(cpu) - rsrp->nr_softirqs, + nr_context_switches_cpu(cpu) - rsrp->nr_csw); + pr_err("\tcputime: %8lld %10lld %12lld ==> %d(ms)\n", + div_u64(rsr.cputime_irq - rsrp->cputime_irq, NSEC_PER_MSEC), + div_u64(rsr.cputime_softirq - rsrp->cputime_softirq, NSEC_PER_MSEC), + div_u64(rsr.cputime_system - rsrp->cputime_system, NSEC_PER_MSEC), + jiffies_to_msecs(jiffies - rsrp->jiffies)); +} + /* * Print out diagnostic information for the specified stalled CPU. * @@ -484,6 +513,8 @@ static void print_cpu_stall_info(int cpu) data_race(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart, rcuc_starved ? buf : "", falsepositive ? " (false positive?)" : ""); + + print_cpu_stat_info(cpu); } /* Complain about starvation of grace-period kthread. */ @@ -588,7 +619,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n", + pr_err("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu ncpus=%d)\n", smp_processor_id(), (long)(jiffies - gps), (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); if (ndetected) { @@ -649,7 +680,7 @@ static void print_cpu_stall(unsigned long gps) raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags); for_each_possible_cpu(cpu) totqlen += rcu_get_n_cbs_cpu(cpu); - pr_cont("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n", + pr_err("\t(t=%lu jiffies g=%ld q=%lu ncpus=%d)\n", jiffies - gps, (long)rcu_seq_current(&rcu_state.gp_seq), totqlen, rcu_state.n_online_cpus); diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f5e6a2f95a2a..19bf6fa3ee6a 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -144,8 +144,45 @@ bool rcu_gp_is_normal(void) } EXPORT_SYMBOL_GPL(rcu_gp_is_normal); -static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); +static atomic_t rcu_async_hurry_nesting = ATOMIC_INIT(1); +/* + * Should call_rcu() callbacks be processed with urgency or are + * they OK being executed with arbitrary delays? + */ +bool rcu_async_should_hurry(void) +{ + return !IS_ENABLED(CONFIG_RCU_LAZY) || + atomic_read(&rcu_async_hurry_nesting); +} +EXPORT_SYMBOL_GPL(rcu_async_should_hurry); + +/** + * rcu_async_hurry - Make future async RCU callbacks not lazy. + * + * After a call to this function, future calls to call_rcu() + * will be processed in a timely fashion. + */ +void rcu_async_hurry(void) +{ + if (IS_ENABLED(CONFIG_RCU_LAZY)) + atomic_inc(&rcu_async_hurry_nesting); +} +EXPORT_SYMBOL_GPL(rcu_async_hurry); +/** + * rcu_async_relax - Make future async RCU callbacks lazy. + * + * After a call to this function, future calls to call_rcu() + * will be processed in a lazy fashion. + */ +void rcu_async_relax(void) +{ + if (IS_ENABLED(CONFIG_RCU_LAZY)) + atomic_dec(&rcu_async_hurry_nesting); +} +EXPORT_SYMBOL_GPL(rcu_async_relax); + +static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); /* * Should normal grace-period primitives be expedited? Intended for * use within RCU. Note that this function takes the rcu_expedited @@ -195,6 +232,7 @@ static bool rcu_boot_ended __read_mostly; void rcu_end_inkernel_boot(void) { rcu_unexpedite_gp(); + rcu_async_relax(); if (rcu_normal_after_boot) WRITE_ONCE(rcu_normal, 1); rcu_boot_ended = true; @@ -220,6 +258,7 @@ void rcu_test_sync_prims(void) { if (!IS_ENABLED(CONFIG_PROVE_RCU)) return; + pr_info("Running RCU synchronous self tests\n"); synchronize_rcu(); synchronize_rcu_expedited(); } @@ -508,6 +547,10 @@ int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_timeout, int, 0644); int rcu_exp_cpu_stall_timeout __read_mostly = CONFIG_RCU_EXP_CPU_STALL_TIMEOUT; module_param(rcu_exp_cpu_stall_timeout, int, 0644); +int rcu_cpu_stall_cputime __read_mostly = IS_ENABLED(CONFIG_RCU_CPU_STALL_CPUTIME); +module_param(rcu_cpu_stall_cputime, int, 0644); +bool rcu_exp_stall_task_details __read_mostly; +module_param(rcu_exp_stall_task_details, bool, 0644); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall @@ -555,9 +598,12 @@ struct early_boot_kfree_rcu { static void early_boot_test_call_rcu(void) { static struct rcu_head head; + int idx; static struct rcu_head shead; struct early_boot_kfree_rcu *rhp; + idx = srcu_down_read(&early_srcu); + srcu_up_read(&early_srcu, idx); call_rcu(&head, test_callback); early_srcu_cookie = start_poll_synchronize_srcu(&early_srcu); call_srcu(&early_srcu, &shead, test_callback); @@ -586,6 +632,7 @@ static int rcu_verify_early_boot_tests(void) early_boot_test_counter++; srcu_barrier(&early_srcu); WARN_ON_ONCE(!poll_state_synchronize_srcu(&early_srcu, early_srcu_cookie)); + cleanup_srcu_struct(&early_srcu); } if (rcu_self_test_counter != early_boot_test_counter) { WARN_ON(1); diff --git a/kernel/relay.c b/kernel/relay.c index ef12532168d9..9aa70ae53d24 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -91,7 +91,7 @@ static int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma) return -EINVAL; vma->vm_ops = &relay_file_mmap_ops; - vma->vm_flags |= VM_DONTEXPAND; + vm_flags_set(vma, VM_DONTEXPAND); vma->vm_private_data = buf; return 0; diff --git a/kernel/resource.c b/kernel/resource.c index ddbbacb9fb50..b1763b2fd7ef 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1343,20 +1343,6 @@ retry: continue; } - /* - * All memory regions added from memory-hotplug path have the - * flag IORESOURCE_SYSTEM_RAM. If the resource does not have - * this flag, we know that we are dealing with a resource coming - * from HMM/devm. HMM/devm use another mechanism to add/release - * a resource. This goes via devm_request_mem_region and - * devm_release_mem_region. - * HMM/devm take care to release their resources when they want, - * so if we are dealing with them, let us just back off here. - */ - if (!(res->flags & IORESOURCE_SYSRAM)) { - break; - } - if (!(res->flags & IORESOURCE_MEM)) break; diff --git a/kernel/rseq.c b/kernel/rseq.c index d38ab944105d..9de6e35fe679 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -18,6 +18,9 @@ #define CREATE_TRACE_POINTS #include <trace/events/rseq.h> +/* The original rseq structure size (including padding) is 32 bytes. */ +#define ORIG_RSEQ_SIZE 32 + #define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \ RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) @@ -82,15 +85,25 @@ * F1. <failure> */ -static int rseq_update_cpu_id(struct task_struct *t) +static int rseq_update_cpu_node_id(struct task_struct *t) { - u32 cpu_id = raw_smp_processor_id(); struct rseq __user *rseq = t->rseq; + u32 cpu_id = raw_smp_processor_id(); + u32 node_id = cpu_to_node(cpu_id); + u32 mm_cid = task_mm_cid(t); - if (!user_write_access_begin(rseq, sizeof(*rseq))) + WARN_ON_ONCE((int) mm_cid < 0); + if (!user_write_access_begin(rseq, t->rseq_len)) goto efault; unsafe_put_user(cpu_id, &rseq->cpu_id_start, efault_end); unsafe_put_user(cpu_id, &rseq->cpu_id, efault_end); + unsafe_put_user(node_id, &rseq->node_id, efault_end); + unsafe_put_user(mm_cid, &rseq->mm_cid, efault_end); + /* + * Additional feature fields added after ORIG_RSEQ_SIZE + * need to be conditionally updated only if + * t->rseq_len != ORIG_RSEQ_SIZE. + */ user_write_access_end(); trace_rseq_update(t); return 0; @@ -101,9 +114,10 @@ efault: return -EFAULT; } -static int rseq_reset_rseq_cpu_id(struct task_struct *t) +static int rseq_reset_rseq_cpu_node_id(struct task_struct *t) { - u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED; + u32 cpu_id_start = 0, cpu_id = RSEQ_CPU_ID_UNINITIALIZED, node_id = 0, + mm_cid = 0; /* * Reset cpu_id_start to its initial state (0). @@ -117,6 +131,21 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t) */ if (put_user(cpu_id, &t->rseq->cpu_id)) return -EFAULT; + /* + * Reset node_id to its initial state (0). + */ + if (put_user(node_id, &t->rseq->node_id)) + return -EFAULT; + /* + * Reset mm_cid to its initial state (0). + */ + if (put_user(mm_cid, &t->rseq->mm_cid)) + return -EFAULT; + /* + * Additional feature fields added after ORIG_RSEQ_SIZE + * need to be conditionally reset only if + * t->rseq_len != ORIG_RSEQ_SIZE. + */ return 0; } @@ -301,7 +330,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(ret < 0)) goto error; } - if (unlikely(rseq_update_cpu_id(t))) + if (unlikely(rseq_update_cpu_node_id(t))) goto error; return; @@ -344,15 +373,16 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; - if (rseq_len != sizeof(*rseq)) + if (rseq_len != current->rseq_len) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; - ret = rseq_reset_rseq_cpu_id(current); + ret = rseq_reset_rseq_cpu_node_id(current); if (ret) return ret; current->rseq = NULL; current->rseq_sig = 0; + current->rseq_len = 0; return 0; } @@ -365,7 +395,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, * the provided address differs from the prior * one. */ - if (current->rseq != rseq || rseq_len != sizeof(*rseq)) + if (current->rseq != rseq || rseq_len != current->rseq_len) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; @@ -374,15 +404,24 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, } /* - * If there was no rseq previously registered, - * ensure the provided rseq is properly aligned and valid. + * If there was no rseq previously registered, ensure the provided rseq + * is properly aligned, as communcated to user-space through the ELF + * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq + * size, the required alignment is the original struct rseq alignment. + * + * In order to be valid, rseq_len is either the original rseq size, or + * large enough to contain all supported fields, as communicated to + * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. */ - if (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || - rseq_len != sizeof(*rseq)) + if (rseq_len < ORIG_RSEQ_SIZE || + (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || + (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || + rseq_len < offsetof(struct rseq, end)))) return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; current->rseq = rseq; + current->rseq_len = rseq_len; current->rseq_sig = sig; /* * If rseq was previously inactive, and has just been diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index e374c0c923da..5732fa75ebab 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -93,7 +93,7 @@ struct sched_clock_data { static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); -notrace static inline struct sched_clock_data *this_scd(void) +static __always_inline struct sched_clock_data *this_scd(void) { return this_cpu_ptr(&sched_clock_data); } @@ -244,12 +244,12 @@ late_initcall(sched_clock_init_late); * min, max except they take wrapping into account */ -notrace static inline u64 wrap_min(u64 x, u64 y) +static __always_inline u64 wrap_min(u64 x, u64 y) { return (s64)(x - y) < 0 ? x : y; } -notrace static inline u64 wrap_max(u64 x, u64 y) +static __always_inline u64 wrap_max(u64 x, u64 y) { return (s64)(x - y) > 0 ? x : y; } @@ -260,7 +260,7 @@ notrace static inline u64 wrap_max(u64 x, u64 y) * - filter out backward motion * - use the GTOD tick value to create a window to filter crazy TSC values */ -notrace static u64 sched_clock_local(struct sched_clock_data *scd) +static __always_inline u64 sched_clock_local(struct sched_clock_data *scd) { u64 now, clock, old_clock, min_clock, max_clock, gtod; s64 delta; @@ -287,13 +287,28 @@ again: clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); - if (!try_cmpxchg64(&scd->clock, &old_clock, clock)) + if (!arch_try_cmpxchg64(&scd->clock, &old_clock, clock)) goto again; return clock; } -notrace static u64 sched_clock_remote(struct sched_clock_data *scd) +noinstr u64 local_clock(void) +{ + u64 clock; + + if (static_branch_likely(&__sched_clock_stable)) + return sched_clock() + __sched_clock_offset; + + preempt_disable_notrace(); + clock = sched_clock_local(this_scd()); + preempt_enable_notrace(); + + return clock; +} +EXPORT_SYMBOL_GPL(local_clock); + +static notrace u64 sched_clock_remote(struct sched_clock_data *scd) { struct sched_clock_data *my_scd = this_scd(); u64 this_clock, remote_clock; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 25b582b6ee5f..af017e038b48 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -152,7 +152,7 @@ __read_mostly int scheduler_running; DEFINE_STATIC_KEY_FALSE(__sched_core_enabled); /* kernel prio, less is more */ -static inline int __task_prio(struct task_struct *p) +static inline int __task_prio(const struct task_struct *p) { if (p->sched_class == &stop_sched_class) /* trumps deadline */ return -2; @@ -174,7 +174,8 @@ static inline int __task_prio(struct task_struct *p) */ /* real prio, less is less */ -static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi) +static inline bool prio_less(const struct task_struct *a, + const struct task_struct *b, bool in_fi) { int pa = __task_prio(a), pb = __task_prio(b); @@ -194,7 +195,8 @@ static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool return false; } -static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b) +static inline bool __sched_core_less(const struct task_struct *a, + const struct task_struct *b) { if (a->core_cookie < b->core_cookie) return true; @@ -2604,27 +2606,71 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) .user_mask = NULL, .flags = SCA_USER, /* clear the user requested mask */ }; + union cpumask_rcuhead { + cpumask_t cpumask; + struct rcu_head rcu; + }; __do_set_cpus_allowed(p, &ac); - kfree(ac.user_mask); + + /* + * Because this is called with p->pi_lock held, it is not possible + * to use kfree() here (when PREEMPT_RT=y), therefore punt to using + * kfree_rcu(). + */ + kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu); +} + +static cpumask_t *alloc_user_cpus_ptr(int node) +{ + /* + * See do_set_cpus_allowed() above for the rcu_head usage. + */ + int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); + + return kmalloc_node(size, GFP_KERNEL, node); } int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { + cpumask_t *user_mask; unsigned long flags; - if (!src->user_cpus_ptr) + /* + * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's + * may differ by now due to racing. + */ + dst->user_cpus_ptr = NULL; + + /* + * This check is racy and losing the race is a valid situation. + * It is not worth the extra overhead of taking the pi_lock on + * every fork/clone. + */ + if (data_race(!src->user_cpus_ptr)) return 0; - dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node); - if (!dst->user_cpus_ptr) + user_mask = alloc_user_cpus_ptr(node); + if (!user_mask) return -ENOMEM; - /* Use pi_lock to protect content of user_cpus_ptr */ + /* + * Use pi_lock to protect content of user_cpus_ptr + * + * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent + * do_set_cpus_allowed(). + */ raw_spin_lock_irqsave(&src->pi_lock, flags); - cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + if (src->user_cpus_ptr) { + swap(dst->user_cpus_ptr, user_mask); + cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + } raw_spin_unlock_irqrestore(&src->pi_lock, flags); + + if (unlikely(user_mask)) + kfree(user_mask); + return 0; } @@ -2907,8 +2953,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, } if (!(ctx->flags & SCA_MIGRATE_ENABLE)) { - if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) + if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) { + if (ctx->flags & SCA_USER) + swap(p->user_cpus_ptr, ctx->user_mask); goto out; + } if (WARN_ON_ONCE(p == current && is_migration_disabled(p) && @@ -3581,6 +3630,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return false; } +static inline cpumask_t *alloc_user_cpus_ptr(int node) +{ + return NULL; +} + #endif /* !CONFIG_SMP */ static void @@ -3623,14 +3677,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } /* - * Mark the task runnable and perform wakeup-preemption. + * Mark the task runnable. */ -static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, - struct rq_flags *rf) +static inline void ttwu_do_wakeup(struct task_struct *p) { - check_preempt_curr(rq, p, wake_flags); WRITE_ONCE(p->__state, TASK_RUNNING); trace_sched_wakeup(p); +} + +static void +ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, + struct rq_flags *rf) +{ + int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK; + + lockdep_assert_rq_held(rq); + + if (p->sched_contributes_to_load) + rq->nr_uninterruptible--; + +#ifdef CONFIG_SMP + if (wake_flags & WF_MIGRATED) + en_flags |= ENQUEUE_MIGRATED; + else +#endif + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + + activate_task(rq, p, en_flags); + check_preempt_curr(rq, p, wake_flags); + + ttwu_do_wakeup(p); #ifdef CONFIG_SMP if (p->sched_class->task_woken) { @@ -3660,31 +3739,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, #endif } -static void -ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, - struct rq_flags *rf) -{ - int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK; - - lockdep_assert_rq_held(rq); - - if (p->sched_contributes_to_load) - rq->nr_uninterruptible--; - -#ifdef CONFIG_SMP - if (wake_flags & WF_MIGRATED) - en_flags |= ENQUEUE_MIGRATED; - else -#endif - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - - activate_task(rq, p, en_flags); - ttwu_do_wakeup(rq, p, wake_flags, rf); -} - /* * Consider @p being inside a wait loop: * @@ -3718,9 +3772,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags) rq = __task_rq_lock(p, &rf); if (task_on_rq_queued(p)) { - /* check_preempt_curr() may use rq clock */ - update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags, &rf); + if (!task_on_cpu(rq, p)) { + /* + * When on_rq && !on_cpu the task is preempted, see if + * it should preempt the task that is current now. + */ + update_rq_clock(rq); + check_preempt_curr(rq, p, wake_flags); + } + ttwu_do_wakeup(p); ret = 1; } __task_rq_unlock(rq, &rf); @@ -4086,8 +4146,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) goto out; trace_sched_waking(p); - WRITE_ONCE(p->__state, TASK_RUNNING); - trace_sched_wakeup(p); + ttwu_do_wakeup(p); goto out; } @@ -5052,6 +5111,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, sched_info_switch(rq, prev, next); perf_event_task_sched_out(prev, next); rseq_preempt(prev); + switch_mm_cid(prev, next); fire_sched_out_preempt_notifiers(prev, next); kmap_local_sched_out(); prepare_task(next); @@ -5282,6 +5342,11 @@ bool single_task_running(void) } EXPORT_SYMBOL(single_task_running); +unsigned long long nr_context_switches_cpu(int cpu) +{ + return cpu_rq(cpu)->nr_switches; +} + unsigned long long nr_context_switches(void) { int i; @@ -5504,7 +5569,9 @@ void scheduler_tick(void) unsigned long thermal_pressure; u64 resched_latency; - arch_scale_freq_tick(); + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + arch_scale_freq_tick(); + sched_clock_tick(); rq_lock(rq, &rf); @@ -6206,7 +6273,7 @@ static bool steal_cookie_task(int cpu, struct sched_domain *sd) { int i; - for_each_cpu_wrap(i, sched_domain_span(sd), cpu) { + for_each_cpu_wrap(i, sched_domain_span(sd), cpu + 1) { if (i == cpu) continue; @@ -8239,12 +8306,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) if (retval) goto out_put_task; - user_mask = kmalloc(cpumask_size(), GFP_KERNEL); - if (!user_mask) { + /* + * With non-SMP configs, user_cpus_ptr/user_mask isn't used and + * alloc_user_cpus_ptr() returns NULL. + */ + user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); + if (user_mask) { + cpumask_copy(user_mask, in_mask); + } else if (IS_ENABLED(CONFIG_SMP)) { retval = -ENOMEM; goto out_put_task; } - cpumask_copy(user_mask, in_mask); + ac = (struct affinity_context){ .new_mask = in_mask, .user_mask = user_mask, @@ -11305,3 +11378,53 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) { trace_sched_update_nr_running_tp(rq, count); } + +#ifdef CONFIG_SCHED_MM_CID +void sched_mm_cid_exit_signals(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + unsigned long flags; + + if (!mm) + return; + local_irq_save(flags); + mm_cid_put(mm, t->mm_cid); + t->mm_cid = -1; + t->mm_cid_active = 0; + local_irq_restore(flags); +} + +void sched_mm_cid_before_execve(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + unsigned long flags; + + if (!mm) + return; + local_irq_save(flags); + mm_cid_put(mm, t->mm_cid); + t->mm_cid = -1; + t->mm_cid_active = 0; + local_irq_restore(flags); +} + +void sched_mm_cid_after_execve(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + unsigned long flags; + + if (!mm) + return; + local_irq_save(flags); + t->mm_cid = mm_cid_get(mm); + t->mm_cid_active = 1; + local_irq_restore(flags); + rseq_set_notify_resume(t); +} + +void sched_mm_cid_fork(struct task_struct *t) +{ + WARN_ON_ONCE(!t->mm || t->mm_cid != -1); + t->mm_cid_active = 1; +} +#endif diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 1207c78f85c1..e3211455b203 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -48,7 +48,6 @@ struct sugov_cpu { unsigned long util; unsigned long bw_dl; - unsigned long max; /* The field below is for single-CPU policies only: */ #ifdef CONFIG_NO_HZ_COMMON @@ -158,7 +157,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->bw_dl = cpu_bw_dl(rq); sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), FREQUENCY_UTIL, NULL); @@ -238,6 +236,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * sugov_iowait_apply() - Apply the IO boost to a CPU. * @sg_cpu: the sugov data for the cpu to boost * @time: the update time from the caller + * @max_cap: the max CPU capacity * * A CPU running a task which woken up after an IO operation can have its * utilization boosted to speed up the completion of those IO operations. @@ -251,7 +250,8 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, * This mechanism is designed to boost high frequently IO waiting tasks, while * being more conservative on tasks which does sporadic IO operations. */ -static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) +static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time, + unsigned long max_cap) { unsigned long boost; @@ -280,7 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time) * sg_cpu->util is already in capacity scale; convert iowait_boost * into the same scale so we can compare. */ - boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT; + boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT; boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL); if (sg_cpu->util < boost) sg_cpu->util = boost; @@ -310,7 +310,8 @@ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu) } static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, - u64 time, unsigned int flags) + u64 time, unsigned long max_cap, + unsigned int flags) { sugov_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; @@ -321,7 +322,7 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu, return false; sugov_get_util(sg_cpu); - sugov_iowait_apply(sg_cpu, time); + sugov_iowait_apply(sg_cpu, time, max_cap); return true; } @@ -332,12 +333,15 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time, struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); struct sugov_policy *sg_policy = sg_cpu->sg_policy; unsigned int cached_freq = sg_policy->cached_raw_freq; + unsigned long max_cap; unsigned int next_f; - if (!sugov_update_single_common(sg_cpu, time, flags)) + max_cap = arch_scale_cpu_capacity(sg_cpu->cpu); + + if (!sugov_update_single_common(sg_cpu, time, max_cap, flags)) return; - next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max); + next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap); /* * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. @@ -374,6 +378,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); unsigned long prev_util = sg_cpu->util; + unsigned long max_cap; /* * Fall back to the "frequency" path if frequency invariance is not @@ -385,7 +390,9 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, return; } - if (!sugov_update_single_common(sg_cpu, time, flags)) + max_cap = arch_scale_cpu_capacity(sg_cpu->cpu); + + if (!sugov_update_single_common(sg_cpu, time, max_cap, flags)) return; /* @@ -399,7 +406,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time, sg_cpu->util = prev_util; cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl), - map_util_perf(sg_cpu->util), sg_cpu->max); + map_util_perf(sg_cpu->util), max_cap); sg_cpu->sg_policy->last_freq_update_time = time; } @@ -408,25 +415,21 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time) { struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; - unsigned long util = 0, max = 1; + unsigned long util = 0, max_cap; unsigned int j; + max_cap = arch_scale_cpu_capacity(sg_cpu->cpu); + for_each_cpu(j, policy->cpus) { struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j); - unsigned long j_util, j_max; sugov_get_util(j_sg_cpu); - sugov_iowait_apply(j_sg_cpu, time); - j_util = j_sg_cpu->util; - j_max = j_sg_cpu->max; + sugov_iowait_apply(j_sg_cpu, time, max_cap); - if (j_util * max > j_max * util) { - util = j_util; - max = j_max; - } + util = max(j_sg_cpu->util, util); } - return get_next_freq(sg_policy, util, max); + return get_next_freq(sg_policy, util, max_cap); } static void @@ -543,7 +546,7 @@ static void sugov_tunables_free(struct kobject *kobj) kfree(to_sugov_tunables(attr_set)); } -static struct kobj_type sugov_tunables_ktype = { +static const struct kobj_type sugov_tunables_ktype = { .default_groups = sugov_groups, .sysfs_ops = &governor_sysfs_ops, .release = &sugov_tunables_free, diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 95fc77853743..af7952f12e6c 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -3,6 +3,10 @@ * Simple CPU accounting cgroup controller */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + #include <asm/cputime.h> +#endif + #ifdef CONFIG_IRQ_TIME_ACCOUNTING /* diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 0d97d54276cc..71b24371a6f7 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2663,17 +2663,20 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) static void prio_changed_dl(struct rq *rq, struct task_struct *p, int oldprio) { - if (task_on_rq_queued(p) || task_current(rq, p)) { + if (!task_on_rq_queued(p)) + return; + #ifdef CONFIG_SMP - /* - * This might be too much, but unfortunately - * we don't have the old deadline value, and - * we can't argue if the task is increasing - * or lowering its prio, so... - */ - if (!rq->dl.overloaded) - deadline_queue_pull_task(rq); + /* + * This might be too much, but unfortunately + * we don't have the old deadline value, and + * we can't argue if the task is increasing + * or lowering its prio, so... + */ + if (!rq->dl.overloaded) + deadline_queue_pull_task(rq); + if (task_current(rq, p)) { /* * If we now have a earlier deadline task than p, * then reschedule, provided p is still on this @@ -2681,15 +2684,24 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline)) resched_curr(rq); -#else + } else { /* - * Again, we don't know if p has a earlier - * or later deadline, so let's blindly set a - * (maybe not needed) rescheduling point. + * Current may not be deadline in case p was throttled but we + * have just replenished it (e.g. rt_mutex_setprio()). + * + * Otherwise, if p was given an earlier deadline, reschedule. */ - resched_curr(rq); -#endif /* CONFIG_SMP */ + if (!dl_task(rq->curr) || + dl_time_before(p->dl.deadline, rq->curr->dl.deadline)) + resched_curr(rq); } +#else + /* + * We don't know if p has a earlier or later deadline, so let's blindly + * set a (maybe not needed) rescheduling point. + */ + resched_curr(rq); +#endif } DEFINE_SCHED_CLASS(dl) = { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c36aa54ae071..7a1b1f855b96 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -468,7 +468,7 @@ is_same_group(struct sched_entity *se, struct sched_entity *pse) return NULL; } -static inline struct sched_entity *parent_entity(struct sched_entity *se) +static inline struct sched_entity *parent_entity(const struct sched_entity *se) { return se->parent; } @@ -595,8 +595,8 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) return min_vruntime; } -static inline bool entity_before(struct sched_entity *a, - struct sched_entity *b) +static inline bool entity_before(const struct sched_entity *a, + const struct sched_entity *b) { return (s64)(a->vruntime - b->vruntime) < 0; } @@ -1804,7 +1804,7 @@ static void update_numa_stats(struct task_numa_env *env, ns->nr_running += rq->cfs.h_nr_running; ns->compute_capacity += capacity_of(cpu); - if (find_idle && !rq->nr_running && idle_cpu(cpu)) { + if (find_idle && idle_core < 0 && !rq->nr_running && idle_cpu(cpu)) { if (READ_ONCE(rq->numa_migrate_on) || !cpumask_test_cpu(cpu, env->p->cpus_ptr)) continue; @@ -1836,7 +1836,7 @@ static void task_numa_assign(struct task_numa_env *env, int start = env->dst_cpu; /* Find alternative idle CPU. */ - for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) { + for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start + 1) { if (cpu == env->best_cpu || !idle_cpu(cpu) || !cpumask_test_cpu(cpu, env->p->cpus_ptr)) { continue; @@ -2938,11 +2938,11 @@ static void task_numa_work(struct callback_head *work) struct task_struct *p = current; struct mm_struct *mm = p->mm; u64 runtime = p->se.sum_exec_runtime; - MA_STATE(mas, &mm->mm_mt, 0, 0); struct vm_area_struct *vma; unsigned long start, end; unsigned long nr_pte_updates = 0; long pages, virtpages; + struct vma_iterator vmi; SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); @@ -2995,16 +2995,16 @@ static void task_numa_work(struct callback_head *work) if (!mmap_read_trylock(mm)) return; - mas_set(&mas, start); - vma = mas_find(&mas, ULONG_MAX); + vma_iter_init(&vmi, mm, start); + vma = vma_next(&vmi); if (!vma) { reset_ptenuma_scan(p); start = 0; - mas_set(&mas, start); - vma = mas_find(&mas, ULONG_MAX); + vma_iter_set(&vmi, start); + vma = vma_next(&vmi); } - for (; vma; vma = mas_find(&mas, ULONG_MAX)) { + do { if (!vma_migratable(vma) || !vma_policy_mof(vma) || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { continue; @@ -3051,7 +3051,7 @@ static void task_numa_work(struct callback_head *work) cond_resched(); } while (end != vma->vm_end); - } + } for_each_vma(vmi, vma); out: /* @@ -4476,17 +4476,9 @@ static inline int util_fits_cpu(unsigned long util, * * For uclamp_max, we can tolerate a drop in performance level as the * goal is to cap the task. So it's okay if it's getting less. - * - * In case of capacity inversion we should honour the inverted capacity - * for both uclamp_min and uclamp_max all the time. */ - capacity_orig = cpu_in_capacity_inversion(cpu); - if (capacity_orig) { - capacity_orig_thermal = capacity_orig; - } else { - capacity_orig = capacity_orig_of(cpu); - capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); - } + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); /* * We want to force a task to fit a cpu as implied by uclamp_max. @@ -4561,8 +4553,8 @@ static inline int util_fits_cpu(unsigned long util, * handle the case uclamp_min > uclamp_max. */ uclamp_min = min(uclamp_min, uclamp_max); - if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE) - fits = fits && (uclamp_min <= capacity_orig_thermal); + if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal)) + return -1; return fits; } @@ -4572,7 +4564,11 @@ static inline int task_fits_cpu(struct task_struct *p, int cpu) unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN); unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX); unsigned long util = task_util_est(p); - return util_fits_cpu(util, uclamp_min, uclamp_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements, which + * include the utilization but also the performance hints. + */ + return (util_fits_cpu(util, uclamp_min, uclamp_max, cpu) > 0); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -4656,6 +4652,7 @@ static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) { u64 vruntime = cfs_rq->min_vruntime; + u64 sleep_time; /* * The 'current' period is already promised to the current tasks, @@ -4685,8 +4682,18 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) vruntime -= thresh; } - /* ensure we never gain time by being placed backwards. */ - se->vruntime = max_vruntime(se->vruntime, vruntime); + /* + * Pull vruntime of the entity being placed to the base level of + * cfs_rq, to prevent boosting it if placed backwards. If the entity + * slept for a long time, don't even try to compare its vruntime with + * the base as it may be too far off and the comparison may get + * inversed due to s64 overflow. + */ + sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start; + if ((s64)sleep_time > 60LL * NSEC_PER_SEC) + se->vruntime = vruntime; + else + se->vruntime = max_vruntime(se->vruntime, vruntime); } static void check_enqueue_throttle(struct cfs_rq *cfs_rq); @@ -4896,7 +4903,13 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) struct sched_entity *se; s64 delta; - ideal_runtime = sched_slice(cfs_rq, curr); + /* + * When many tasks blow up the sched_period; it is possible that + * sched_slice() reports unusually large results (when many tasks are + * very light for example). Therefore impose a maximum. + */ + ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; if (delta_exec > ideal_runtime) { resched_curr(rq_of(cfs_rq)); @@ -5461,22 +5474,105 @@ unthrottle_throttle: resched_curr(rq); } -static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) +#ifdef CONFIG_SMP +static void __cfsb_csd_unthrottle(void *arg) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cursor, *tmp; + struct rq *rq = arg; + struct rq_flags rf; + + rq_lock(rq, &rf); + + /* + * Since we hold rq lock we're safe from concurrent manipulation of + * the CSD list. However, this RCU critical section annotates the + * fact that we pair with sched_free_group_rcu(), so that we cannot + * race with group being freed in the window between removing it + * from the list and advancing to the next entry in the list. + */ + rcu_read_lock(); + + list_for_each_entry_safe(cursor, tmp, &rq->cfsb_csd_list, + throttled_csd_list) { + list_del_init(&cursor->throttled_csd_list); + + if (cfs_rq_throttled(cursor)) + unthrottle_cfs_rq(cursor); + } + + rcu_read_unlock(); + + rq_unlock(rq, &rf); +} + +static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + bool first; + + if (rq == this_rq()) { + unthrottle_cfs_rq(cfs_rq); + return; + } + + /* Already enqueued */ + if (SCHED_WARN_ON(!list_empty(&cfs_rq->throttled_csd_list))) + return; + + first = list_empty(&rq->cfsb_csd_list); + list_add_tail(&cfs_rq->throttled_csd_list, &rq->cfsb_csd_list); + if (first) + smp_call_function_single_async(cpu_of(rq), &rq->cfsb_csd); +} +#else +static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) +{ + unthrottle_cfs_rq(cfs_rq); +} +#endif + +static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq) +{ + lockdep_assert_rq_held(rq_of(cfs_rq)); + + if (SCHED_WARN_ON(!cfs_rq_throttled(cfs_rq) || + cfs_rq->runtime_remaining <= 0)) + return; + + __unthrottle_cfs_rq_async(cfs_rq); +} + +static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) +{ + struct cfs_rq *local_unthrottle = NULL; + int this_cpu = smp_processor_id(); u64 runtime, remaining = 1; + bool throttled = false; + struct cfs_rq *cfs_rq; + struct rq_flags rf; + struct rq *rq; rcu_read_lock(); list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, throttled_list) { - struct rq *rq = rq_of(cfs_rq); - struct rq_flags rf; + rq = rq_of(cfs_rq); + + if (!remaining) { + throttled = true; + break; + } rq_lock_irqsave(rq, &rf); if (!cfs_rq_throttled(cfs_rq)) goto next; - /* By the above check, this should never be true */ +#ifdef CONFIG_SMP + /* Already queued for async unthrottle */ + if (!list_empty(&cfs_rq->throttled_csd_list)) + goto next; +#endif + + /* By the above checks, this should never be true */ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); raw_spin_lock(&cfs_b->lock); @@ -5490,16 +5586,30 @@ static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) cfs_rq->runtime_remaining += runtime; /* we check whether we're throttled above */ - if (cfs_rq->runtime_remaining > 0) - unthrottle_cfs_rq(cfs_rq); + if (cfs_rq->runtime_remaining > 0) { + if (cpu_of(rq) != this_cpu || + SCHED_WARN_ON(local_unthrottle)) + unthrottle_cfs_rq_async(cfs_rq); + else + local_unthrottle = cfs_rq; + } else { + throttled = true; + } next: rq_unlock_irqrestore(rq, &rf); - - if (!remaining) - break; } rcu_read_unlock(); + + if (local_unthrottle) { + rq = cpu_rq(this_cpu); + rq_lock_irqsave(rq, &rf); + if (cfs_rq_throttled(local_unthrottle)) + unthrottle_cfs_rq(local_unthrottle); + rq_unlock_irqrestore(rq, &rf); + } + + return throttled; } /* @@ -5544,10 +5654,8 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u while (throttled && cfs_b->runtime > 0) { raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ - distribute_cfs_runtime(cfs_b); + throttled = distribute_cfs_runtime(cfs_b); raw_spin_lock_irqsave(&cfs_b->lock, flags); - - throttled = !list_empty(&cfs_b->throttled_cfs_rq); } /* @@ -5824,6 +5932,9 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) { cfs_rq->runtime_enabled = 0; INIT_LIST_HEAD(&cfs_rq->throttled_list); +#ifdef CONFIG_SMP + INIT_LIST_HEAD(&cfs_rq->throttled_csd_list); +#endif } void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) @@ -5840,12 +5951,38 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { + int __maybe_unused i; + /* init_cfs_bandwidth() was not called */ if (!cfs_b->throttled_cfs_rq.next) return; hrtimer_cancel(&cfs_b->period_timer); hrtimer_cancel(&cfs_b->slack_timer); + + /* + * It is possible that we still have some cfs_rq's pending on a CSD + * list, though this race is very rare. In order for this to occur, we + * must have raced with the last task leaving the group while there + * exist throttled cfs_rq(s), and the period_timer must have queued the + * CSD item but the remote cpu has not yet processed it. To handle this, + * we can simply flush all pending CSD work inline here. We're + * guaranteed at this point that no additional cfs_rq of this group can + * join a CSD list. + */ +#ifdef CONFIG_SMP + for_each_possible_cpu(i) { + struct rq *rq = cpu_rq(i); + unsigned long flags; + + if (list_empty(&rq->cfsb_csd_list)) + continue; + + local_irq_save(flags); + __cfsb_csd_unthrottle(rq); + local_irq_restore(flags); + } +#endif } /* @@ -6008,6 +6145,7 @@ static inline bool cpu_overutilized(int cpu) unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + /* Return true only if the utilization doesn't fit CPU's capacity */ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); } @@ -6801,6 +6939,7 @@ static int select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) { unsigned long task_util, util_min, util_max, best_cap = 0; + int fits, best_fits = 0; int cpu, best_cpu = -1; struct cpumask *cpus; @@ -6811,17 +6950,33 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) util_min = uclamp_eff_value(p, UCLAMP_MIN); util_max = uclamp_eff_value(p, UCLAMP_MAX); - for_each_cpu_wrap(cpu, cpus, target) { + for_each_cpu_wrap(cpu, cpus, target + 1) { unsigned long cpu_cap = capacity_of(cpu); if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) continue; - if (util_fits_cpu(task_util, util_min, util_max, cpu)) + + fits = util_fits_cpu(task_util, util_min, util_max, cpu); + + /* This CPU fits with all requirements */ + if (fits > 0) return cpu; + /* + * Only the min performance hint (i.e. uclamp_min) doesn't fit. + * Look for the CPU with best capacity. + */ + else if (fits < 0) + cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu)); - if (cpu_cap > best_cap) { + /* + * First, select CPU which fits better (-1 being better than 0). + * Then, select the one with best capacity at same level. + */ + if ((fits < best_fits) || + ((fits == best_fits) && (cpu_cap > best_cap))) { best_cap = cpu_cap; best_cpu = cpu; + best_fits = fits; } } @@ -6834,7 +6989,11 @@ static inline bool asym_fits_cpu(unsigned long util, int cpu) { if (sched_asym_cpucap_active()) - return util_fits_cpu(util, util_min, util_max, cpu); + /* + * Return true only if the cpu fully fits the task requirements + * which include the utilization and the performance hints. + */ + return (util_fits_cpu(util, util_min, util_max, cpu) > 0); return true; } @@ -7201,6 +7360,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; struct root_domain *rd = this_rq()->rd; int cpu, best_energy_cpu, target = -1; + int prev_fits = -1, best_fits = -1; + unsigned long best_thermal_cap = 0; + unsigned long prev_thermal_cap = 0; struct sched_domain *sd; struct perf_domain *pd; struct energy_env eenv; @@ -7229,13 +7391,14 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) eenv_task_busy_time(&eenv, p, prev_cpu); for (; pd; pd = pd->next) { + unsigned long util_min = p_util_min, util_max = p_util_max; unsigned long cpu_cap, cpu_thermal_cap, util; unsigned long cur_delta, max_spare_cap = 0; unsigned long rq_util_min, rq_util_max; - unsigned long util_min, util_max; unsigned long prev_spare_cap = 0; int max_spare_cap_cpu = -1; unsigned long base_energy; + int fits, max_fits = -1; cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); @@ -7251,6 +7414,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) eenv.pd_cap = 0; for_each_cpu(cpu, cpus) { + struct rq *rq = cpu_rq(cpu); + eenv.pd_cap += cpu_thermal_cap; if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) @@ -7269,26 +7434,23 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * much capacity we can get out of the CPU; this is * aligned with sched_cpu_util(). */ - if (uclamp_is_used()) { - if (uclamp_rq_is_idle(cpu_rq(cpu))) { - util_min = p_util_min; - util_max = p_util_max; - } else { - /* - * Open code uclamp_rq_util_with() except for - * the clamp() part. Ie: apply max aggregation - * only. util_fits_cpu() logic requires to - * operate on non clamped util but must use the - * max-aggregated uclamp_{min, max}. - */ - rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); - - util_min = max(rq_util_min, p_util_min); - util_max = max(rq_util_max, p_util_max); - } + if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN); + rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX); + + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); } - if (!util_fits_cpu(util, util_min, util_max, cpu)) + + fits = util_fits_cpu(util, util_min, util_max, cpu); + if (!fits) continue; lsub_positive(&cpu_cap, util); @@ -7296,7 +7458,9 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (cpu == prev_cpu) { /* Always use prev_cpu as a candidate. */ prev_spare_cap = cpu_cap; - } else if (cpu_cap > max_spare_cap) { + prev_fits = fits; + } else if ((fits > max_fits) || + ((fits == max_fits) && (cpu_cap > max_spare_cap))) { /* * Find the CPU with the maximum spare capacity * among the remaining CPUs in the performance @@ -7304,6 +7468,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) */ max_spare_cap = cpu_cap; max_spare_cap_cpu = cpu; + max_fits = fits; } } @@ -7322,26 +7487,50 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (prev_delta < base_energy) goto unlock; prev_delta -= base_energy; + prev_thermal_cap = cpu_thermal_cap; best_delta = min(best_delta, prev_delta); } /* Evaluate the energy impact of using max_spare_cap_cpu. */ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) { + /* Current best energy cpu fits better */ + if (max_fits < best_fits) + continue; + + /* + * Both don't fit performance hint (i.e. uclamp_min) + * but best energy cpu has better capacity. + */ + if ((max_fits < 0) && + (cpu_thermal_cap <= best_thermal_cap)) + continue; + cur_delta = compute_energy(&eenv, pd, cpus, p, max_spare_cap_cpu); /* CPU utilization has changed */ if (cur_delta < base_energy) goto unlock; cur_delta -= base_energy; - if (cur_delta < best_delta) { - best_delta = cur_delta; - best_energy_cpu = max_spare_cap_cpu; - } + + /* + * Both fit for the task but best energy cpu has lower + * energy impact. + */ + if ((max_fits > 0) && (best_fits > 0) && + (cur_delta >= best_delta)) + continue; + + best_delta = cur_delta; + best_energy_cpu = max_spare_cap_cpu; + best_fits = max_fits; + best_thermal_cap = cpu_thermal_cap; } } rcu_read_unlock(); - if (best_delta < prev_delta) + if ((best_fits > prev_fits) || + ((best_fits > 0) && (best_delta < prev_delta)) || + ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap))) target = best_energy_cpu; return target; @@ -8841,73 +9030,16 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity_orig = arch_scale_cpu_capacity(cpu); unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; - struct rq *rq = cpu_rq(cpu); - rq->cpu_capacity_orig = capacity_orig; + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; - rq->cpu_capacity = capacity; - - /* - * Detect if the performance domain is in capacity inversion state. - * - * Capacity inversion happens when another perf domain with equal or - * lower capacity_orig_of() ends up having higher capacity than this - * domain after subtracting thermal pressure. - * - * We only take into account thermal pressure in this detection as it's - * the only metric that actually results in *real* reduction of - * capacity due to performance points (OPPs) being dropped/become - * unreachable due to thermal throttling. - * - * We assume: - * * That all cpus in a perf domain have the same capacity_orig - * (same uArch). - * * Thermal pressure will impact all cpus in this perf domain - * equally. - */ - if (static_branch_unlikely(&sched_asym_cpucapacity)) { - unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd = rcu_dereference(rq->rd->pd); - - rq->cpu_capacity_inverted = 0; - - for (; pd; pd = pd->next) { - struct cpumask *pd_span = perf_domain_span(pd); - unsigned long pd_cap_orig, pd_cap; - - cpu = cpumask_any(pd_span); - pd_cap_orig = arch_scale_cpu_capacity(cpu); - - if (capacity_orig < pd_cap_orig) - continue; - - /* - * handle the case of multiple perf domains have the - * same capacity_orig but one of them is under higher - * thermal pressure. We record it as capacity - * inversion. - */ - if (capacity_orig == pd_cap_orig) { - pd_cap = pd_cap_orig - thermal_load_avg(cpu_rq(cpu)); - - if (pd_cap > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } else if (pd_cap_orig > inv_cap) { - rq->cpu_capacity_inverted = inv_cap; - break; - } - } - } - - trace_sched_cpu_capacity_tp(rq); + cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; @@ -10135,24 +10267,23 @@ static struct sched_group *find_busiest_group(struct lb_env *env) */ update_sd_lb_stats(env, &sds); - if (sched_energy_enabled()) { - struct root_domain *rd = env->dst_rq->rd; - - if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) - goto out_balanced; - } - - local = &sds.local_stat; - busiest = &sds.busiest_stat; - /* There is no busy sibling group to pull tasks from */ if (!sds.busiest) goto out_balanced; + busiest = &sds.busiest_stat; + /* Misfit tasks should be dealt with regardless of the avg load */ if (busiest->group_type == group_misfit_task) goto force_balance; + if (sched_energy_enabled()) { + struct root_domain *rd = env->dst_rq->rd; + + if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) + goto out_balanced; + } + /* ASYM feature bypasses nice load balance check */ if (busiest->group_type == group_asym_packing) goto force_balance; @@ -10165,6 +10296,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (busiest->group_type == group_imbalanced) goto force_balance; + local = &sds.local_stat; /* * If the local group is busier than the selected busiest group * don't try and pull any tasks. @@ -11728,7 +11860,8 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) /* * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed. */ -static void se_fi_update(struct sched_entity *se, unsigned int fi_seq, bool forceidle) +static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq, + bool forceidle) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -11753,11 +11886,12 @@ void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi) se_fi_update(se, rq->core->core_forceidle_seq, in_fi); } -bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool in_fi) +bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b, + bool in_fi) { struct rq *rq = task_rq(a); - struct sched_entity *sea = &a->se; - struct sched_entity *seb = &b->se; + const struct sched_entity *sea = &a->se; + const struct sched_entity *seb = &b->se; struct cfs_rq *cfs_rqa; struct cfs_rq *cfs_rqb; s64 delta; @@ -12474,6 +12608,11 @@ __init void init_sched_fair_class(void) for_each_possible_cpu(i) { zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i)); zalloc_cpumask_var_node(&per_cpu(select_rq_mask, i), GFP_KERNEL, cpu_to_node(i)); + +#ifdef CONFIG_CFS_BANDWIDTH + INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i)); + INIT_LIST_HEAD(&cpu_rq(i)->cfsb_csd_list); +#endif } open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index f26ab2675f7d..e9ef66be2870 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -51,18 +51,22 @@ __setup("hlt", cpu_idle_nopoll_setup); static noinline int __cpuidle cpu_idle_poll(void) { + instrumentation_begin(); trace_cpu_idle(0, smp_processor_id()); stop_critical_timings(); - ct_idle_enter(); - local_irq_enable(); + ct_cpuidle_enter(); + raw_local_irq_enable(); while (!tif_need_resched() && (cpu_idle_force_poll || tick_check_broadcast_expired())) cpu_relax(); + raw_local_irq_disable(); - ct_idle_exit(); + ct_cpuidle_exit(); start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + local_irq_enable(); + instrumentation_end(); return 1; } @@ -75,7 +79,6 @@ void __weak arch_cpu_idle_dead(void) { } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; - raw_local_irq_enable(); } /** @@ -85,44 +88,20 @@ void __weak arch_cpu_idle(void) */ void __cpuidle default_idle_call(void) { - if (current_clr_polling_and_test()) { - local_irq_enable(); - } else { - + instrumentation_begin(); + if (!current_clr_polling_and_test()) { trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); - /* - * arch_cpu_idle() is supposed to enable IRQs, however - * we can't do that because of RCU and tracing. - * - * Trace IRQs enable here, then switch off RCU, and have - * arch_cpu_idle() use raw_local_irq_enable(). Note that - * ct_idle_enter() relies on lockdep IRQ state, so switch that - * last -- this is very similar to the entry code. - */ - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(); - ct_idle_enter(); - lockdep_hardirqs_on(_THIS_IP_); - + ct_cpuidle_enter(); arch_cpu_idle(); - - /* - * OK, so IRQs are enabled here, but RCU needs them disabled to - * turn itself back on.. funny thing is that disabling IRQs - * will cause tracing, which needs RCU. Jump through hoops to - * make it 'work'. - */ - raw_local_irq_disable(); - lockdep_hardirqs_off(_THIS_IP_); - ct_idle_exit(); - lockdep_hardirqs_on(_THIS_IP_); - raw_local_irq_enable(); + ct_cpuidle_exit(); start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } + local_irq_enable(); + instrumentation_end(); } static int call_cpuidle_s2idle(struct cpuidle_driver *drv, diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 0c5be7ebb1dc..2ad881d07752 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -159,7 +159,8 @@ | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \ | MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \ - | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK) + | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ + | MEMBARRIER_CMD_GET_REGISTRATIONS) static void ipi_mb(void *info) { @@ -540,6 +541,40 @@ static int membarrier_register_private_expedited(int flags) return 0; } +static int membarrier_get_registrations(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + int registrations_mask = 0, membarrier_state, i; + static const int states[] = { + MEMBARRIER_STATE_GLOBAL_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY, + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ | + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY + }; + static const int registration_cmds[] = { + MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE, + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ + }; + BUILD_BUG_ON(ARRAY_SIZE(states) != ARRAY_SIZE(registration_cmds)); + + membarrier_state = atomic_read(&mm->membarrier_state); + for (i = 0; i < ARRAY_SIZE(states); ++i) { + if (membarrier_state & states[i]) { + registrations_mask |= registration_cmds[i]; + membarrier_state &= ~states[i]; + } + } + WARN_ON_ONCE(membarrier_state != 0); + return registrations_mask; +} + /** * sys_membarrier - issue memory barriers on a set of threads * @cmd: Takes command values defined in enum membarrier_cmd. @@ -623,6 +658,8 @@ SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id) return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id); case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ: return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ); + case MEMBARRIER_CMD_GET_REGISTRATIONS: + return membarrier_get_registrations(); default: return -EINVAL; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 8ac8b81bfee6..02e011cabe91 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1343,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t) group = t->group; /* - * Wakeup waiters to stop polling. Can happen if cgroup is deleted - * from under a polling process. + * Wakeup waiters to stop polling and clear the queue to prevent it from + * being accessed later. Can happen if cgroup is deleted from under a + * polling process. */ - wake_up_interruptible(&t->event_wait); + wake_up_pollfree(&t->event_wait); mutex_lock(&group->trigger_lock); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index ed2a47e4ddae..0a11f44adee5 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1777,6 +1777,8 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq) BUG_ON(idx >= MAX_RT_PRIO); queue = array->queue + idx; + if (SCHED_WARN_ON(list_empty(queue))) + return NULL; next = list_entry(queue->next, struct sched_rt_entity, run_list); return next; @@ -1789,7 +1791,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) do { rt_se = pick_next_rt_entity(rt_rq); - BUG_ON(!rt_se); + if (unlikely(!rt_se)) + return NULL; rt_rq = group_rt_rq(rt_se); } while (rt_rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 771f8ddb7053..3e8df6d31c1e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -248,7 +248,7 @@ static inline void update_avg(u64 *avg, u64 sample) #define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV) -static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se) +static inline bool dl_entity_is_special(const struct sched_dl_entity *dl_se) { #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL return unlikely(dl_se->flags & SCHED_FLAG_SUGOV); @@ -260,8 +260,8 @@ static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se) /* * Tells if entity @a should preempt entity @b. */ -static inline bool -dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) +static inline bool dl_entity_preempt(const struct sched_dl_entity *a, + const struct sched_dl_entity *b) { return dl_entity_is_special(a) || dl_time_before(a->deadline, b->deadline); @@ -645,6 +645,9 @@ struct cfs_rq { int throttled; int throttle_count; struct list_head throttled_list; +#ifdef CONFIG_SMP + struct list_head throttled_csd_list; +#endif #endif /* CONFIG_CFS_BANDWIDTH */ #endif /* CONFIG_FAIR_GROUP_SCHED */ }; @@ -1041,7 +1044,6 @@ struct rq { unsigned long cpu_capacity; unsigned long cpu_capacity_orig; - unsigned long cpu_capacity_inverted; struct balance_callback *balance_callback; @@ -1154,6 +1156,11 @@ struct rq { /* Scratch cpumask to be temporarily used under rq_lock */ cpumask_var_t scratch_mask; + +#if defined(CONFIG_CFS_BANDWIDTH) && defined(CONFIG_SMP) + call_single_data_t cfsb_csd; + struct list_head cfsb_csd_list; +#endif }; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -1236,7 +1243,8 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq) return &rq->__lock; } -bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool fi); +bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b, + bool fi); /* * Helpers to check if the CPU's core cookie matches with the task's cookie @@ -1415,7 +1423,7 @@ static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) } /* runqueue on which this entity is (to be) queued */ -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +static inline struct cfs_rq *cfs_rq_of(const struct sched_entity *se) { return se->cfs_rq; } @@ -1428,19 +1436,16 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) #else -static inline struct task_struct *task_of(struct sched_entity *se) -{ - return container_of(se, struct task_struct, se); -} +#define task_of(_se) container_of(_se, struct task_struct, se) -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +static inline struct cfs_rq *task_cfs_rq(const struct task_struct *p) { return &task_rq(p)->cfs; } -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +static inline struct cfs_rq *cfs_rq_of(const struct sched_entity *se) { - struct task_struct *p = task_of(se); + const struct task_struct *p = task_of(se); struct rq *rq = task_rq(p); return &rq->cfs; @@ -2893,24 +2898,6 @@ static inline unsigned long capacity_orig_of(int cpu) return cpu_rq(cpu)->cpu_capacity_orig; } -/* - * Returns inverted capacity if the CPU is in capacity inversion state. - * 0 otherwise. - * - * Capacity inversion detection only considers thermal impact where actual - * performance points (OPPs) gets dropped. - * - * Capacity inversion state happens when another performance domain that has - * equal or lower capacity_orig_of() becomes effectively larger than the perf - * domain this CPU belongs to due to thermal pressure throttling it hard. - * - * See comment in update_cpu_capacity(). - */ -static inline unsigned long cpu_in_capacity_inversion(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_inverted; -} - /** * enum cpu_util_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency @@ -3261,4 +3248,62 @@ static inline void update_current_exec_runtime(struct task_struct *curr, cgroup_account_cputime(curr, delta_exec); } +#ifdef CONFIG_SCHED_MM_CID +static inline int __mm_cid_get(struct mm_struct *mm) +{ + struct cpumask *cpumask; + int cid; + + cpumask = mm_cidmask(mm); + cid = cpumask_first_zero(cpumask); + if (cid >= nr_cpu_ids) + return -1; + __cpumask_set_cpu(cid, cpumask); + return cid; +} + +static inline void mm_cid_put(struct mm_struct *mm, int cid) +{ + lockdep_assert_irqs_disabled(); + if (cid < 0) + return; + raw_spin_lock(&mm->cid_lock); + __cpumask_clear_cpu(cid, mm_cidmask(mm)); + raw_spin_unlock(&mm->cid_lock); +} + +static inline int mm_cid_get(struct mm_struct *mm) +{ + int ret; + + lockdep_assert_irqs_disabled(); + raw_spin_lock(&mm->cid_lock); + ret = __mm_cid_get(mm); + raw_spin_unlock(&mm->cid_lock); + return ret; +} + +static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) +{ + if (prev->mm_cid_active) { + if (next->mm_cid_active && next->mm == prev->mm) { + /* + * Context switch between threads in same mm, hand over + * the mm_cid from prev to next. + */ + next->mm_cid = prev->mm_cid; + prev->mm_cid = -1; + return; + } + mm_cid_put(prev->mm, prev->mm_cid); + prev->mm_cid = -1; + } + if (next->mm_cid_active) + next->mm_cid = mm_cid_get(next->mm); +} + +#else +static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) { } +#endif + #endif /* _KERNEL_SCHED_SCHED_H */ diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8739c2a5a54e..051aaf65c749 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -3,6 +3,8 @@ * Scheduler topology setup/handling methods */ +#include <linux/bsearch.h> + DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ @@ -578,7 +580,7 @@ out: */ struct root_domain def_root_domain; -void init_defrootdomain(void) +void __init init_defrootdomain(void) { init_rootdomain(&def_root_domain); @@ -2067,6 +2069,99 @@ unlock: return found; } +struct __cmp_key { + const struct cpumask *cpus; + struct cpumask ***masks; + int node; + int cpu; + int w; +}; + +static int hop_cmp(const void *a, const void *b) +{ + struct cpumask **prev_hop, **cur_hop = *(struct cpumask ***)b; + struct __cmp_key *k = (struct __cmp_key *)a; + + if (cpumask_weight_and(k->cpus, cur_hop[k->node]) <= k->cpu) + return 1; + + if (b == k->masks) { + k->w = 0; + return 0; + } + + prev_hop = *((struct cpumask ***)b - 1); + k->w = cpumask_weight_and(k->cpus, prev_hop[k->node]); + if (k->w <= k->cpu) + return 0; + + return -1; +} + +/* + * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: Nth cpu to find + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) +{ + struct __cmp_key k = { .cpus = cpus, .node = node, .cpu = cpu }; + struct cpumask ***hop_masks; + int hop, ret = nr_cpu_ids; + + rcu_read_lock(); + + k.masks = rcu_dereference(sched_domains_numa_masks); + if (!k.masks) + goto unlock; + + hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp); + hop = hop_masks - k.masks; + + ret = hop ? + cpumask_nth_and_andnot(cpu - k.w, cpus, k.masks[hop][node], k.masks[hop-1][node]) : + cpumask_nth_and(cpu, cpus, k.masks[0][node]); +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu); + +/** + * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away from + * @node + * @node: The node to count hops from. + * @hops: Include CPUs up to that many hops away. 0 means local node. + * + * Return: On success, a pointer to a cpumask of CPUs at most @hops away from + * @node, an error value otherwise. + * + * Requires rcu_lock to be held. Returned cpumask is only valid within that + * read-side section, copy it if required beyond that. + * + * Note that not all hops are equal in distance; see sched_init_numa() for how + * distances and masks are handled. + * Also note that this is a reflection of sched_domains_numa_masks, which may change + * during the lifetime of the system (offline nodes are taken out of the masks). + */ +const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops) +{ + struct cpumask ***masks; + + if (node >= nr_node_ids || hops >= sched_domains_numa_levels) + return ERR_PTR(-EINVAL); + + masks = rcu_dereference(sched_domains_numa_masks); + if (!masks) + return ERR_PTR(-EBUSY); + + return masks[hops][node]; +} +EXPORT_SYMBOL_GPL(sched_numa_hop_mask); + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -2451,7 +2546,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) * Set up scheduler domains and groups. For now this just excludes isolated * CPUs, but could be used to exclude other special cases in the future. */ -int sched_init_domains(const struct cpumask *cpu_map) +int __init sched_init_domains(const struct cpumask *cpu_map) { int err; diff --git a/kernel/seccomp.c b/kernel/seccomp.c index e9852d1b4a5e..cebf26445f9e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -388,6 +388,7 @@ static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilte } #endif /* SECCOMP_ARCH_NATIVE */ +#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters @@ -397,7 +398,6 @@ static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilte * * Returns valid seccomp BPF response codes. */ -#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { diff --git a/kernel/signal.c b/kernel/signal.c index ae26da61c4d9..8cb28f1df294 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2951,6 +2951,7 @@ void exit_signals(struct task_struct *tsk) cgroup_threadgroup_change_begin(tsk); if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { + sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; @@ -2961,6 +2962,7 @@ void exit_signals(struct task_struct *tsk) * From now this task is not visible for group-wide signals, * see wants_signal(), do_signal_stop(). */ + sched_mm_cid_exit_signals(tsk); tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); diff --git a/kernel/sys.c b/kernel/sys.c index 5fd54bf0e886..495cd87d9bf4 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1442,6 +1442,8 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; @@ -2348,6 +2350,33 @@ static int prctl_set_vma(unsigned long opt, unsigned long start, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg3 || arg4 || arg5) + return -EINVAL; + + if (bits & ~(PR_MDWE_REFUSE_EXEC_GAIN)) + return -EINVAL; + + if (bits & PR_MDWE_REFUSE_EXEC_GAIN) + set_bit(MMF_HAS_MDWE, ¤t->mm->flags); + else if (test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return -EPERM; /* Cannot unset the flag */ + + return 0; +} + +static inline int prctl_get_mdwe(unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5) +{ + if (arg2 || arg3 || arg4 || arg5) + return -EINVAL; + + return test_bit(MMF_HAS_MDWE, ¤t->mm->flags) ? + PR_MDWE_REFUSE_EXEC_GAIN : 0; +} + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2623,6 +2652,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_MDWE: + error = prctl_set_mdwe(arg2, arg3, arg4, arg5); + break; + case PR_GET_MDWE: + error = prctl_get_mdwe(arg2, arg3, arg4, arg5); + break; case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 137d4abe3eda..1c240d2c99bc 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -425,21 +425,6 @@ static void proc_put_char(void **buf, size_t *size, char c) } } -static int do_proc_dobool_conv(bool *negp, unsigned long *lvalp, - int *valp, - int write, void *data) -{ - if (write) { - *(bool *)valp = *lvalp; - } else { - int val = *(bool *)valp; - - *lvalp = (unsigned long)val; - *negp = false; - } - return 0; -} - static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, int *valp, int write, void *data) @@ -710,16 +695,36 @@ int do_proc_douintvec(struct ctl_table *table, int write, * @lenp: the size of the user buffer * @ppos: file position * - * Reads/writes up to table->maxlen/sizeof(unsigned int) integer - * values from/to the user buffer, treated as an ASCII string. + * Reads/writes one integer value from/to the user buffer, + * treated as an ASCII string. + * + * table->data must point to a bool variable and table->maxlen must + * be sizeof(bool). * * Returns 0 on success. */ int proc_dobool(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table, write, buffer, lenp, ppos, - do_proc_dobool_conv, NULL); + struct ctl_table tmp; + bool *data = table->data; + int res, val; + + /* Do not support arrays yet. */ + if (table->maxlen != sizeof(bool)) + return -EINVAL; + + tmp = *table; + tmp.maxlen = sizeof(val); + tmp.data = &val; + + val = READ_ONCE(*data); + res = proc_dointvec(&tmp, write, buffer, lenp, ppos); + if (res) + return res; + if (write) + WRITE_ONCE(*data, val); + return 0; } /** diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index a41753be1a2b..bae8f11070be 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -200,10 +200,14 @@ config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US int "Clocksource watchdog maximum allowable skew (in μs)" depends on CLOCKSOURCE_WATCHDOG range 50 1000 - default 100 + default 125 help Specify the maximum amount of allowable watchdog skew in microseconds before reporting the clocksource to be unstable. + The default is based on a half-second clocksource watchdog + interval and NTP's maximum frequency drift of 500 parts + per million. If the clocksource is good enough for NTP, + it is good enough for the clocksource watchdog! endmenu endif diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 5897828b9d7e..7e5dff602585 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -470,11 +470,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) { struct alarm_base *base = &alarm_bases[alarm->type]; + ktime_t now = base->get_ktime(); + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { + /* + * Same issue as with posix_timer_fn(). Timers which are + * periodic but the signal is ignored can starve the system + * with a very small interval. The real fix which was + * promised in the context of posix_timer_fn() never + * materialized, but someone should really work on it. + * + * To prevent DOS fake @now to be 1 jiffie out which keeps + * the overrun accounting correct but creates an + * inconsistency vs. timer_gettime(2). + */ + ktime_t kj = NSEC_PER_SEC / HZ; + + if (interval < kj) + now = ktime_add(now, kj); + } + + return alarm_forward(alarm, now, interval); +} - return alarm_forward(alarm, base->get_ktime(), interval); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + return __alarm_forward_now(alarm, interval, false); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -551,9 +575,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, if (posix_timer_event(ptr, si_private) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. + * away once we handle ignored signals proper. Ensure that + * small intervals cannot starve the system. */ - ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_requeue_pending; ptr->it_active = 1; result = ALARMTIMER_RESTART; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 9cf32ccda715..91836b727cef 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -96,6 +96,11 @@ static int finished_booting; static u64 suspend_start; /* + * Interval: 0.5sec. + */ +#define WATCHDOG_INTERVAL (HZ >> 1) + +/* * Threshold: 0.0312s, when doubled: 0.0625s. * Also a default for cs->uncertainty_margin when registering clocks. */ @@ -106,11 +111,14 @@ static u64 suspend_start; * clocksource surrounding a read of the clocksource being validated. * This delay could be due to SMIs, NMIs, or to VCPU preemptions. Used as * a lower bound for cs->uncertainty_margin values when registering clocks. + * + * The default of 500 parts per million is based on NTP's limits. + * If a clocksource is good enough for NTP, it is good enough for us! */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US #define MAX_SKEW_USEC CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US #else -#define MAX_SKEW_USEC 100 +#define MAX_SKEW_USEC (125 * WATCHDOG_INTERVAL / HZ) #endif #define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC) @@ -140,11 +148,6 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); -/* - * Interval: 0.5sec. - */ -#define WATCHDOG_INTERVAL (HZ >> 1) - static void clocksource_watchdog_work(struct work_struct *work) { /* @@ -257,8 +260,8 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, goto skip_test; } - pr_warn("timekeeping watchdog on CPU%d: %s read-back delay of %lldns, attempt %d, marking unstable\n", - smp_processor_id(), watchdog->name, wd_delay, nretries); + pr_warn("timekeeping watchdog on CPU%d: wd-%s-wd excessive read-back delay of %lldns vs. limit of %ldns, wd-wd read-back delay only %lldns, attempt %d, marking %s unstable\n", + smp_processor_id(), cs->name, wd_delay, WATCHDOG_MAX_SKEW, wd_seq_delay, nretries, cs->name); return WD_READ_UNSTABLE; skip_test: @@ -384,6 +387,15 @@ void clocksource_verify_percpu(struct clocksource *cs) } EXPORT_SYMBOL_GPL(clocksource_verify_percpu); +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + + static void clocksource_watchdog(struct timer_list *unused) { u64 csnow, wdnow, cslast, wdlast, delta; @@ -391,6 +403,7 @@ static void clocksource_watchdog(struct timer_list *unused) int64_t wd_nsec, cs_nsec; struct clocksource *cs; enum wd_read_status read_ret; + unsigned long extra_wait = 0; u32 md; spin_lock(&watchdog_lock); @@ -410,13 +423,30 @@ static void clocksource_watchdog(struct timer_list *unused) read_ret = cs_watchdog_read(cs, &csnow, &wdnow); - if (read_ret != WD_READ_SUCCESS) { - if (read_ret == WD_READ_UNSTABLE) - /* Clock readout unreliable, so give it up. */ - __clocksource_unstable(cs); + if (read_ret == WD_READ_UNSTABLE) { + /* Clock readout unreliable, so give it up. */ + __clocksource_unstable(cs); continue; } + /* + * When WD_READ_SKIP is returned, it means the system is likely + * under very heavy load, where the latency of reading + * watchdog/clocksource is very big, and affect the accuracy of + * watchdog check. So give system some space and suspend the + * watchdog check for 5 minutes. + */ + if (read_ret == WD_READ_SKIP) { + /* + * As the watchdog timer will be suspended, and + * cs->last could keep unchanged for 5 minutes, reset + * the counters. + */ + clocksource_reset_watchdog(); + extra_wait = HZ * 300; + break; + } + /* Clocksource initialized ? */ if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || atomic_read(&watchdog_reset_pending)) { @@ -443,12 +473,20 @@ static void clocksource_watchdog(struct timer_list *unused) /* Check the deviation from the watchdog clocksource. */ md = cs->uncertainty_margin + watchdog->uncertainty_margin; if (abs(cs_nsec - wd_nsec) > md) { + u64 cs_wd_msec; + u64 wd_msec; + u32 wd_rem; + pr_warn("timekeeping watchdog on CPU%d: Marking clocksource '%s' as unstable because the skew is too large:\n", smp_processor_id(), cs->name); pr_warn(" '%s' wd_nsec: %lld wd_now: %llx wd_last: %llx mask: %llx\n", watchdog->name, wd_nsec, wdnow, wdlast, watchdog->mask); pr_warn(" '%s' cs_nsec: %lld cs_now: %llx cs_last: %llx mask: %llx\n", cs->name, cs_nsec, csnow, cslast, cs->mask); + cs_wd_msec = div_u64_rem(cs_nsec - wd_nsec, 1000U * 1000U, &wd_rem); + wd_msec = div_u64_rem(wd_nsec, 1000U * 1000U, &wd_rem); + pr_warn(" Clocksource '%s' skewed %lld ns (%lld ms) over watchdog '%s' interval of %lld ns (%lld ms)\n", + cs->name, cs_nsec - wd_nsec, cs_wd_msec, watchdog->name, wd_nsec, wd_msec); if (curr_clocksource == cs) pr_warn(" '%s' is current clocksource.\n", cs->name); else if (curr_clocksource) @@ -512,7 +550,7 @@ static void clocksource_watchdog(struct timer_list *unused) * pair clocksource_stop_watchdog() clocksource_start_watchdog(). */ if (!timer_pending(&watchdog_timer)) { - watchdog_timer.expires += WATCHDOG_INTERVAL; + watchdog_timer.expires += WATCHDOG_INTERVAL + extra_wait; add_timer_on(&watchdog_timer, next_cpu); } out: @@ -537,14 +575,6 @@ static inline void clocksource_stop_watchdog(void) watchdog_running = 0; } -static inline void clocksource_reset_watchdog(void) -{ - struct clocksource *cs; - - list_for_each_entry(cs, &watchdog_list, wd_list) - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; -} - static void clocksource_resume_watchdog(void) { atomic_inc(&watchdog_reset_pending); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 3ae661ab6260..e8c08292defc 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2089,7 +2089,7 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, u64 slack; slack = current->timer_slack_ns; - if (dl_task(current) || rt_task(current)) + if (rt_task(current)) slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); @@ -2126,6 +2126,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, @@ -2147,6 +2148,7 @@ SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, if (!timespec64_valid(&tu)) return -EINVAL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, @@ -2270,7 +2272,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2297,6 +2299,13 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } + /* + * Override any slack passed by the user if under + * rt contraints. + */ + if (rt_task(current)) + delta = 0; + hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2316,7 +2325,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) + * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks * @mode: timer mode * * Make the current task sleep until the given expiry time has @@ -2324,7 +2333,8 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); * the current task state has been set (see set_current_state()). * * The @delta argument gives the kernel the freedom to schedule the - * actual wakeup to a time that is both power and performance friendly. + * actual wakeup to a time that is both power and performance friendly + * for regular (non RT/DL) tasks. * The kernel give the normal best effort behavior for "@expires+@delta", * but may decide to fire the timer earlier, but no earlier than @expires. * diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index cb925e8ef9a8..2f5e9b34022c 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -243,13 +243,12 @@ static void proc_sample_cputime_atomic(struct task_cputime_atomic *at, */ static inline void __update_gt_cputime(atomic64_t *cputime, u64 sum_cputime) { - u64 curr_cputime; -retry: - curr_cputime = atomic64_read(cputime); - if (sum_cputime > curr_cputime) { - if (atomic64_cmpxchg(cputime, curr_cputime, sum_cputime) != curr_cputime) - goto retry; - } + u64 curr_cputime = atomic64_read(cputime); + + do { + if (sum_cputime <= curr_cputime) + return; + } while (!atomic64_try_cmpxchg(cputime, &curr_cputime, sum_cputime)); } static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic, diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index 90ea5f373e50..828aeecbd1e8 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -147,6 +147,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; texp = timespec64_to_ktime(t); @@ -240,6 +241,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; texp = timespec64_to_ktime(t); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 5dead89308b7..0c8a87a11b39 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1270,6 +1270,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; @@ -1297,6 +1298,7 @@ SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, return -EINVAL; if (flags & TIMER_ABSTIME) rmtp = NULL; + current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; diff --git a/kernel/time/test_udelay.c b/kernel/time/test_udelay.c index 13b11eb62685..20d5df631570 100644 --- a/kernel/time/test_udelay.c +++ b/kernel/time/test_udelay.c @@ -149,7 +149,7 @@ module_init(udelay_test_init); static void __exit udelay_test_exit(void) { mutex_lock(&udelay_test_lock); - debugfs_remove(debugfs_lookup(DEBUGFS_FILENAME, NULL)); + debugfs_lookup_and_remove(DEBUGFS_FILENAME, NULL); mutex_unlock(&udelay_test_lock); } diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 797eb93103ad..e28f9210f8a1 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -56,25 +56,20 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * hrtimer callback function is currently running, then * hrtimer_start() cannot move it and the timer stays on the CPU on * which it is assigned at the moment. + */ + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD); + /* + * The core tick broadcast mode expects bc->bound_on to be set + * correctly to prevent a CPU which has the broadcast hrtimer + * armed from going deep idle. * - * As this can be called from idle code, the hrtimer_start() - * invocation has to be wrapped with RCU_NONIDLE() as - * hrtimer_start() can call into tracing. + * As tick_broadcast_lock is held, nothing can change the cpu + * base which was just established in hrtimer_start() above. So + * the below access is safe even without holding the hrtimer + * base lock. */ - RCU_NONIDLE( { - hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED_HARD); - /* - * The core tick broadcast mode expects bc->bound_on to be set - * correctly to prevent a CPU which has the broadcast hrtimer - * armed from going deep idle. - * - * As tick_broadcast_lock is held, nothing can change the cpu - * base which was just established in hrtimer_start() above. So - * the below access is safe even without holding the hrtimer - * base lock. - */ - bc->bound_on = bctimer.base->cpu_base->cpu; - } ); + bc->bound_on = bctimer.base->cpu_base->cpu; + return 0; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index f7fe6fe36173..93bf2b4e47e5 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -622,9 +622,13 @@ struct cpumask *tick_get_broadcast_oneshot_mask(void) * to avoid a deep idle transition as we are about to get the * broadcast IPI right away. */ -int tick_check_broadcast_expired(void) +noinstr int tick_check_broadcast_expired(void) { +#ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H + return arch_test_bit(smp_processor_id(), cpumask_bits(tick_broadcast_force_mask)); +#else return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask); +#endif } /* diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 475ecceda768..5e2c2c26b3cc 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -18,7 +18,7 @@ #include "tick-internal.h" /** - * tick_program_event + * tick_program_event - program the CPU local timer device for the next event */ int tick_program_event(ktime_t expires, int force) { @@ -99,7 +99,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) } /** - * tick_check_oneshot_mode - check whether the system is in oneshot mode + * tick_oneshot_mode_active - check whether the system is in oneshot mode * * returns 1 when either nohz or highres are enabled. otherwise 0. */ diff --git a/kernel/time/time.c b/kernel/time/time.c index 526257b3727c..f4198af60fee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -462,7 +462,7 @@ struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** - * set_normalized_timespec - set timespec sec and nsec parts and normalize + * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set @@ -526,7 +526,7 @@ struct timespec64 ns_to_timespec64(s64 nsec) EXPORT_SYMBOL(ns_to_timespec64); /** - * msecs_to_jiffies: - convert milliseconds to jiffies + * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: @@ -541,12 +541,12 @@ EXPORT_SYMBOL(ns_to_timespec64); * handling any 32-bit overflows. * for the details see __msecs_to_jiffies() * - * msecs_to_jiffies() checks for the passed in value being a constant + * __msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. - * the _msecs_to_jiffies helpers are the HZ dependent conversion + * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h */ unsigned long __msecs_to_jiffies(const unsigned int m) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f72b9f1de178..5579ead449f2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1590,10 +1590,10 @@ void __weak read_persistent_clock64(struct timespec64 *ts) /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. + * @wall_time: current time as returned by persistent clock + * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. - * @wall_time: - current time as returned by persistent clock - * @boot_offset: - offset that is defined as wall_time - boot_time * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't @@ -1701,7 +1701,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) -/** +/* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource @@ -1722,7 +1722,7 @@ bool timekeeping_rtc_skipresume(void) return !suspend_timing_needed; } -/** +/* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). diff --git a/kernel/torture.c b/kernel/torture.c index 789aeb0e1159..1a0519b836ac 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -450,7 +450,7 @@ unsigned long torture_random(struct torture_random_state *trsp) { if (--trsp->trs_count < 0) { - trsp->trs_state += (unsigned long)local_clock(); + trsp->trs_state += (unsigned long)local_clock() + raw_smp_processor_id(); trsp->trs_count = TORTURE_RANDOM_REFRESH; } trsp->trs_state = trsp->trs_state * TORTURE_RANDOM_MULT + @@ -915,7 +915,7 @@ void torture_kthread_stopping(char *title) VERBOSE_TOROUT_STRING(buf); while (!kthread_should_stop()) { torture_shutdown_absorb(title); - schedule_timeout_uninterruptible(1); + schedule_timeout_uninterruptible(HZ / 20); } } EXPORT_SYMBOL_GPL(torture_kthread_stopping); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 197545241ab8..a856d4a34c67 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -42,6 +42,9 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS bool +config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + bool + config HAVE_DYNAMIC_FTRACE_WITH_ARGS bool help @@ -239,7 +242,7 @@ config DYNAMIC_FTRACE enabled, and the functions not enabled will not affect performance of the system. - See the files in /sys/kernel/debug/tracing: + See the files in /sys/kernel/tracing: available_filter_functions set_ftrace_filter set_ftrace_notrace @@ -257,6 +260,10 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +config DYNAMIC_FTRACE_WITH_CALL_OPS + def_bool y + depends on HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + config DYNAMIC_FTRACE_WITH_ARGS def_bool y depends on DYNAMIC_FTRACE @@ -299,7 +306,7 @@ config STACK_TRACER select KALLSYMS help This special tracer records the maximum stack footprint of the - kernel and displays it in /sys/kernel/debug/tracing/stack_trace. + kernel and displays it in /sys/kernel/tracing/stack_trace. This tracer works by hooking into every function call that the kernel executes, and keeping a maximum stack depth value and @@ -339,7 +346,7 @@ config IRQSOFF_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + echo 0 > /sys/kernel/tracing/tracing_max_latency (Note that kernel size and overhead increase with this option enabled. This option and the preempt-off timing option can be @@ -363,7 +370,7 @@ config PREEMPT_TRACER disabled by default and can be runtime (re-)started via: - echo 0 > /sys/kernel/debug/tracing/tracing_max_latency + echo 0 > /sys/kernel/tracing/tracing_max_latency (Note that kernel size and overhead increase with this option enabled. This option and the irqs-off timing option can be @@ -515,7 +522,7 @@ config TRACER_SNAPSHOT Allow tracing users to take snapshot of the current buffer using the ftrace interface, e.g.: - echo 1 > /sys/kernel/debug/tracing/snapshot + echo 1 > /sys/kernel/tracing/snapshot cat snapshot config TRACER_SNAPSHOT_PER_CPU_SWAP @@ -527,7 +534,7 @@ config TRACER_SNAPSHOT_PER_CPU_SWAP full swap (all buffers). If this is set, then the following is allowed: - echo 1 > /sys/kernel/debug/tracing/per_cpu/cpu2/snapshot + echo 1 > /sys/kernel/tracing/per_cpu/cpu2/snapshot After which, only the tracing buffer for CPU 2 was swapped with the main tracing buffer, and the other CPU buffers remain the same. @@ -574,7 +581,7 @@ config PROFILE_ANNOTATED_BRANCHES This tracer profiles all likely and unlikely macros in the kernel. It will display the results in: - /sys/kernel/debug/tracing/trace_stat/branch_annotated + /sys/kernel/tracing/trace_stat/branch_annotated Note: this will add a significant overhead; only turn this on if you need to profile the system's use of these macros. @@ -587,7 +594,7 @@ config PROFILE_ALL_BRANCHES taken in the kernel is recorded whether it hit or miss. The results will be displayed in: - /sys/kernel/debug/tracing/trace_stat/branch_all + /sys/kernel/tracing/trace_stat/branch_all This option also enables the likely/unlikely profiler. @@ -638,8 +645,8 @@ config BLK_DEV_IO_TRACE Tracing also is possible using the ftrace interface, e.g.: echo 1 > /sys/block/sda/sda1/trace/enable - echo blk > /sys/kernel/debug/tracing/current_tracer - cat /sys/kernel/debug/tracing/trace_pipe + echo blk > /sys/kernel/tracing/current_tracer + cat /sys/kernel/tracing/trace_pipe If unsure, say N. @@ -933,8 +940,8 @@ config RING_BUFFER_RECORD_RECURSION default y help The ring buffer has its own internal recursion. Although when - recursion happens it wont cause harm because of the protection, - but it does cause an unwanted overhead. Enabling this option will + recursion happens it won't cause harm because of the protection, + but it does cause unwanted overhead. Enabling this option will place where recursion was detected into the ftrace "recursed_functions" file. @@ -1017,8 +1024,8 @@ config RING_BUFFER_STARTUP_TEST The test runs for 10 seconds. This will slow your boot time by at least 10 more seconds. - At the end of the test, statics and more checks are done. - It will output the stats of each per cpu buffer. What + At the end of the test, statistics and more checks are done. + It will output the stats of each per cpu buffer: What was written, the sizes, what was read, what was lost, and other similar details. diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 918a7d12df8f..d5d94510afd3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -320,8 +320,8 @@ static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) * under 'q->debugfs_dir', thus lookup and remove them. */ if (!bt->dir) { - debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir)); - debugfs_remove(debugfs_lookup("msg", q->debugfs_dir)); + debugfs_lookup_and_remove("dropped", q->debugfs_dir); + debugfs_lookup_and_remove("msg", q->debugfs_dir); } else { debugfs_remove(bt->dir); } @@ -729,14 +729,10 @@ EXPORT_SYMBOL_GPL(blk_trace_startstop); **/ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) { - struct request_queue *q; + struct request_queue *q = bdev_get_queue(bdev); int ret, start = 0; char b[BDEVNAME_SIZE]; - q = bdev_get_queue(bdev); - if (!q) - return -ENXIO; - mutex_lock(&q->debugfs_mutex); switch (cmd) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 3bbd3f0c810c..e8da032bb6fc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -369,8 +369,6 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) return &bpf_probe_write_user_proto; } -static DEFINE_RAW_SPINLOCK(trace_printk_lock); - #define MAX_TRACE_PRINTK_VARARGS 3 #define BPF_TRACE_PRINTK_SIZE 1024 @@ -378,23 +376,22 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { u64 args[MAX_TRACE_PRINTK_VARARGS] = { arg1, arg2, arg3 }; - u32 *bin_args; - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret; - ret = bpf_bprintf_prepare(fmt, fmt_size, args, &bin_args, - MAX_TRACE_PRINTK_VARARGS); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, + MAX_TRACE_PRINTK_VARARGS, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -427,30 +424,29 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, args, u32, data_len) { - static char buf[BPF_TRACE_PRINTK_SIZE]; - unsigned long flags; + struct bpf_bprintf_data data = { + .get_bin_args = true, + .get_buf = true, + }; int ret, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (ret < 0) return ret; - raw_spin_lock_irqsave(&trace_printk_lock, flags); - ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt, data.bin_args); - trace_bpf_trace_printk(buf); - raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + trace_bpf_trace_printk(data.buf); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return ret; } @@ -472,23 +468,25 @@ const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) } BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, - const void *, data, u32, data_len) + const void *, args, u32, data_len) { + struct bpf_bprintf_data data = { + .get_bin_args = true, + }; int err, num_args; - u32 *bin_args; if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || - (data_len && !data)) + (data_len && !args)) return -EINVAL; num_args = data_len / 8; - err = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + err = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data); if (err < 0) return err; - seq_bprintf(m, fmt, bin_args); + seq_bprintf(m, fmt, data.bin_args); - bpf_bprintf_cleanup(); + bpf_bprintf_cleanup(&data); return seq_has_overflowed(m) ? -EOVERFLOW : 0; } @@ -687,8 +685,7 @@ BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, } perf_sample_data_init(sd, 0, 0); - sd->raw = &raw; - sd->sample_flags |= PERF_SAMPLE_RAW; + perf_sample_save_raw_data(sd, &raw); err = __bpf_perf_event_output(regs, map, flags, sd); @@ -746,8 +743,7 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); - sd->raw = &raw; - sd->sample_flags |= PERF_SAMPLE_RAW; + perf_sample_save_raw_data(sd, &raw); ret = __bpf_perf_event_output(regs, map, flags, sd); out: @@ -833,6 +829,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -848,6 +845,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; + /* Task should not be pid=1 to avoid kernel panic. */ + if (unlikely(is_global_init(current))) + return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, @@ -864,7 +864,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); @@ -1235,7 +1235,7 @@ __diag_ignore_all("-Wmissing-prototypes", * Return: a bpf_key pointer with a valid key pointer if the key is found, a * NULL pointer otherwise. */ -struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) +__bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) { key_ref_t key_ref; struct bpf_key *bkey; @@ -1284,7 +1284,7 @@ struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) * Return: a bpf_key pointer with an invalid key pointer set from the * pre-determined ID on success, a NULL pointer otherwise */ -struct bpf_key *bpf_lookup_system_key(u64 id) +__bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id) { struct bpf_key *bkey; @@ -1308,7 +1308,7 @@ struct bpf_key *bpf_lookup_system_key(u64 id) * Decrement the reference count of the key inside *bkey*, if the pointer * is valid, and free *bkey*. */ -void bpf_key_put(struct bpf_key *bkey) +__bpf_kfunc void bpf_key_put(struct bpf_key *bkey) { if (bkey->has_ref) key_put(bkey->key); @@ -1328,7 +1328,7 @@ void bpf_key_put(struct bpf_key *bkey) * * Return: 0 on success, a negative value on error. */ -int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, +__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, struct bpf_dynptr_kern *sig_ptr, struct bpf_key *trusted_keyring) { @@ -2684,69 +2684,77 @@ static void symbols_swap_r(void *a, void *b, int size, const void *priv) } } -struct module_addr_args { - unsigned long *addrs; - u32 addrs_cnt; +struct modules_array { struct module **mods; int mods_cnt; int mods_cap; }; -static int module_callback(void *data, const char *name, - struct module *mod, unsigned long addr) +static int add_module(struct modules_array *arr, struct module *mod) { - struct module_addr_args *args = data; struct module **mods; - /* We iterate all modules symbols and for each we: - * - search for it in provided addresses array - * - if found we check if we already have the module pointer stored - * (we iterate modules sequentially, so we can check just the last - * module pointer) - * - take module reference and store it - */ - if (!bsearch(&addr, args->addrs, args->addrs_cnt, sizeof(addr), - bpf_kprobe_multi_addrs_cmp)) - return 0; - - if (args->mods && args->mods[args->mods_cnt - 1] == mod) - return 0; - - if (args->mods_cnt == args->mods_cap) { - args->mods_cap = max(16, args->mods_cap * 3 / 2); - mods = krealloc_array(args->mods, args->mods_cap, sizeof(*mods), GFP_KERNEL); + if (arr->mods_cnt == arr->mods_cap) { + arr->mods_cap = max(16, arr->mods_cap * 3 / 2); + mods = krealloc_array(arr->mods, arr->mods_cap, sizeof(*mods), GFP_KERNEL); if (!mods) return -ENOMEM; - args->mods = mods; + arr->mods = mods; } - if (!try_module_get(mod)) - return -EINVAL; - - args->mods[args->mods_cnt] = mod; - args->mods_cnt++; + arr->mods[arr->mods_cnt] = mod; + arr->mods_cnt++; return 0; } +static bool has_module(struct modules_array *arr, struct module *mod) +{ + int i; + + for (i = arr->mods_cnt - 1; i >= 0; i--) { + if (arr->mods[i] == mod) + return true; + } + return false; +} + static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u32 addrs_cnt) { - struct module_addr_args args = { - .addrs = addrs, - .addrs_cnt = addrs_cnt, - }; - int err; + struct modules_array arr = {}; + u32 i, err = 0; + + for (i = 0; i < addrs_cnt; i++) { + struct module *mod; + + preempt_disable(); + mod = __module_address(addrs[i]); + /* Either no module or we it's already stored */ + if (!mod || has_module(&arr, mod)) { + preempt_enable(); + continue; + } + if (!try_module_get(mod)) + err = -EINVAL; + preempt_enable(); + if (err) + break; + err = add_module(&arr, mod); + if (err) { + module_put(mod); + break; + } + } /* We return either err < 0 in case of error, ... */ - err = module_kallsyms_on_each_symbol(module_callback, &args); if (err) { - kprobe_multi_put_modules(args.mods, args.mods_cnt); - kfree(args.mods); + kprobe_multi_put_modules(arr.mods, arr.mods_cnt); + kfree(arr.mods); return err; } /* or number of modules found if everything is ok. */ - *mods = args.mods; - return args.mods_cnt; + *mods = arr.mods; + return arr.mods_cnt; } int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -2859,13 +2867,6 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr bpf_kprobe_multi_cookie_cmp, bpf_kprobe_multi_cookie_swap, link); - } else { - /* - * We need to sort addrs array even if there are no cookies - * provided, to allow bsearch in get_modules_for_addrs. - */ - sort(addrs, cnt, sizeof(*addrs), - bpf_kprobe_multi_addrs_cmp, NULL); } err = get_modules_for_addrs(&link->mods, addrs, cnt); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 442438b93fe9..29baa97d0d53 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -125,6 +125,33 @@ struct ftrace_ops global_ops; void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +/* + * Stub used to invoke the list ops without requiring a separate trampoline. + */ +const struct ftrace_ops ftrace_list_ops = { + .func = ftrace_ops_list_func, + .flags = FTRACE_OPS_FL_STUB, +}; + +static void ftrace_ops_nop_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, + struct ftrace_regs *fregs) +{ + /* do nothing */ +} + +/* + * Stub used when a call site is disabled. May be called transiently by threads + * which have made it into ftrace_caller but haven't yet recovered the ops at + * the point the call site is disabled. + */ +const struct ftrace_ops ftrace_nop_ops = { + .func = ftrace_ops_nop_func, + .flags = FTRACE_OPS_FL_STUB, +}; +#endif + static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE @@ -1248,12 +1275,17 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) call_rcu(&hash->rcu, __free_ftrace_hash_rcu); } +/** + * ftrace_free_filter - remove all filters for an ftrace_ops + * @ops - the ops to remove the filters from + */ void ftrace_free_filter(struct ftrace_ops *ops) { ftrace_ops_init(ops); free_ftrace_hash(ops->func_hash->filter_hash); free_ftrace_hash(ops->func_hash->notrace_hash); } +EXPORT_SYMBOL_GPL(ftrace_free_filter); static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { @@ -1814,6 +1846,18 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * if rec count is zero. */ } + + /* + * If the rec has a single associated ops, and ops->func can be + * called directly, allow the call site to call via the ops. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) && + ftrace_rec_count(rec) == 1 && + ftrace_ops_get_func(ops) == ops->func) + rec->flags |= FTRACE_FL_CALL_OPS; + else + rec->flags &= ~FTRACE_FL_CALL_OPS; + count++; /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ @@ -2108,8 +2152,9 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec) struct ftrace_ops *ops = NULL; pr_info("ftrace record flags: %lx\n", rec->flags); - pr_cont(" (%ld)%s", ftrace_rec_count(rec), - rec->flags & FTRACE_FL_REGS ? " R" : " "); + pr_cont(" (%ld)%s%s", ftrace_rec_count(rec), + rec->flags & FTRACE_FL_REGS ? " R" : " ", + rec->flags & FTRACE_FL_CALL_OPS ? " O" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -2177,6 +2222,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * want the direct enabled (it will be done via the * direct helper). But if DIRECT_EN is set, and * the count is not one, we need to clear it. + * */ if (ftrace_rec_count(rec) == 1) { if (!(rec->flags & FTRACE_FL_DIRECT) != @@ -2185,6 +2231,19 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) } else if (rec->flags & FTRACE_FL_DIRECT_EN) { flag |= FTRACE_FL_DIRECT; } + + /* + * Ops calls are special, as count matters. + * As with direct calls, they must only be enabled when count + * is one, otherwise they'll be handled via the list ops. + */ + if (ftrace_rec_count(rec) == 1) { + if (!(rec->flags & FTRACE_FL_CALL_OPS) != + !(rec->flags & FTRACE_FL_CALL_OPS_EN)) + flag |= FTRACE_FL_CALL_OPS; + } else if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + flag |= FTRACE_FL_CALL_OPS; + } } /* If the state of this record hasn't changed, then do nothing */ @@ -2229,6 +2288,21 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) rec->flags &= ~FTRACE_FL_DIRECT_EN; } } + + if (flag & FTRACE_FL_CALL_OPS) { + if (ftrace_rec_count(rec) == 1) { + if (rec->flags & FTRACE_FL_CALL_OPS) + rec->flags |= FTRACE_FL_CALL_OPS_EN; + else + rec->flags &= ~FTRACE_FL_CALL_OPS_EN; + } else { + /* + * Can only call directly if there's + * only one set of associated ops. + */ + rec->flags &= ~FTRACE_FL_CALL_OPS_EN; + } + } } /* @@ -2258,7 +2332,8 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * and REGS states. The _EN flags must be disabled though. */ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | - FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN); + FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN | + FTRACE_FL_CALL_OPS_EN); } ftrace_bug_type = FTRACE_BUG_NOP; @@ -2431,6 +2506,25 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) return NULL; } +struct ftrace_ops * +ftrace_find_unique_ops(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op, *found = NULL; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (hash_contains_ip(ip, op->func_hash)) { + if (found) + return NULL; + found = op; + } + + } while_for_each_ftrace_op(op); + + return found; +} + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* Protected by rcu_tasks for reading, and direct_mutex for writing */ static struct ftrace_hash *direct_functions = EMPTY_HASH; @@ -3780,11 +3874,12 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; - seq_printf(m, " (%ld)%s%s%s", + seq_printf(m, " (%ld)%s%s%s%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " ", rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ", - rec->flags & FTRACE_FL_DIRECT ? " D" : " "); + rec->flags & FTRACE_FL_DIRECT ? " D" : " ", + rec->flags & FTRACE_FL_CALL_OPS ? " O" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -3800,6 +3895,15 @@ static int t_show(struct seq_file *m, void *v) } else { add_trampoline_func(m, NULL, rec); } + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + if (ops) { + seq_printf(m, "\tops: %pS (%pS)", + ops, ops->func); + } else { + seq_puts(m, "\tops: ERROR!"); + } + } if (rec->flags & FTRACE_FL_DIRECT) { unsigned long direct; @@ -5839,6 +5943,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi); * * Filters denote which functions should be enabled when tracing is enabled * If @ip is NULL, it fails to update filter. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset) @@ -5858,7 +5966,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); * * Filters denote which functions should be enabled when tracing is enabled * If @ips array or any ip specified within is NULL , it fails to update filter. - */ + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). +*/ int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset) { @@ -5900,6 +6012,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) @@ -5919,6 +6035,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); * Notrace Filters denote which functions should not be enabled when tracing * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) @@ -8324,7 +8444,7 @@ int ftrace_lookup_symbols(const char **sorted_syms, size_t cnt, unsigned long *a found_all = kallsyms_on_each_symbol(kallsyms_callback, &args); if (found_all) return 0; - found_all = module_kallsyms_on_each_symbol(kallsyms_callback, &args); + found_all = module_kallsyms_on_each_symbol(NULL, kallsyms_callback, &args); return found_all ? 0 : -ESRCH; } diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index c736487fc0e4..4850fdfe27f1 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -21,7 +21,7 @@ * Then: * * # insmod kernel/trace/kprobe_event_gen_test.ko - * # cat /sys/kernel/debug/tracing/trace + * # cat /sys/kernel/tracing/trace * * You should see many instances of the "gen_kprobe_test" and * "gen_kretprobe_test" events in the trace buffer. diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c366a0a9ddba..af50d931b020 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1581,19 +1581,6 @@ static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer, } /** - * rb_check_list - make sure a pointer to a list has the last bits zero - */ -static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, - struct list_head *list) -{ - if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev)) - return 1; - if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next)) - return 1; - return 0; -} - -/** * rb_check_pages - integrity check of buffer pages * @cpu_buffer: CPU buffer with pages to test * @@ -1602,36 +1589,27 @@ static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer, */ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer) { - struct list_head *head = cpu_buffer->pages; - struct buffer_page *bpage, *tmp; - - /* Reset the head page if it exists */ - if (cpu_buffer->head_page) - rb_set_head_page(cpu_buffer); - - rb_head_page_deactivate(cpu_buffer); + struct list_head *head = rb_list_head(cpu_buffer->pages); + struct list_head *tmp; - if (RB_WARN_ON(cpu_buffer, head->next->prev != head)) - return -1; - if (RB_WARN_ON(cpu_buffer, head->prev->next != head)) + if (RB_WARN_ON(cpu_buffer, + rb_list_head(rb_list_head(head->next)->prev) != head)) return -1; - if (rb_check_list(cpu_buffer, head)) + if (RB_WARN_ON(cpu_buffer, + rb_list_head(rb_list_head(head->prev)->next) != head)) return -1; - list_for_each_entry_safe(bpage, tmp, head, list) { + for (tmp = rb_list_head(head->next); tmp != head; tmp = rb_list_head(tmp->next)) { if (RB_WARN_ON(cpu_buffer, - bpage->list.next->prev != &bpage->list)) + rb_list_head(rb_list_head(tmp->next)->prev) != tmp)) return -1; + if (RB_WARN_ON(cpu_buffer, - bpage->list.prev->next != &bpage->list)) - return -1; - if (rb_check_list(cpu_buffer, &bpage->list)) + rb_list_head(rb_list_head(tmp->prev)->next) != tmp)) return -1; } - rb_head_page_activate(cpu_buffer); - return 0; } @@ -2886,7 +2864,7 @@ rb_check_timestamp(struct ring_buffer_per_cpu *cpu_buffer, sched_clock_stable() ? "" : "If you just came from a suspend/resume,\n" "please switch to the trace global clock:\n" - " echo global > /sys/kernel/debug/tracing/trace_clock\n" + " echo global > /sys/kernel/tracing/trace_clock\n" "or add trace_clock=global to the kernel command line\n"); } @@ -5626,11 +5604,16 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page); */ void ring_buffer_free_read_page(struct trace_buffer *buffer, int cpu, void *data) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = data; struct page *page = virt_to_page(bpage); unsigned long flags; + if (!buffer || !buffer->buffers || !buffer->buffers[cpu]) + return; + + cpu_buffer = buffer->buffers[cpu]; + /* If the page is still in use someplace else, we can't reuse it */ if (page_ref_count(page) > 1) goto out; diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 6c97cc2d754a..7e9061828c24 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -516,7 +516,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user struct rv_monitor_def *mdef; int retval = -EINVAL; bool enable = true; - char *ptr = buff; + char *ptr; int len; if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1) diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c index 8d77526892f4..8dfe85499d4a 100644 --- a/kernel/trace/synth_event_gen_test.c +++ b/kernel/trace/synth_event_gen_test.c @@ -22,7 +22,7 @@ * Then: * * # insmod kernel/trace/synth_event_gen_test.ko - * # cat /sys/kernel/debug/tracing/trace + * # cat /sys/kernel/tracing/trace * * You should see several events in the trace buffer - * "create_synth_test", "empty_synth_test", and several instances of diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a555a861b978..45551c7b4c36 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -49,6 +49,8 @@ #include <linux/irq_work.h> #include <linux/workqueue.h> +#include <asm/setup.h> /* COMMAND_LINE_SIZE */ + #include "trace.h" #include "trace_output.h" @@ -186,6 +188,12 @@ static char *default_bootup_tracer; static bool allocate_snapshot; static bool snapshot_at_boot; +static char boot_instance_info[COMMAND_LINE_SIZE] __initdata; +static int boot_instance_index; + +static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata; +static int boot_snapshot_index; + static int __init set_cmdline_ftrace(char *str) { strlcpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); @@ -222,9 +230,22 @@ __setup("traceoff_on_warning", stop_trace_on_warning); static int __init boot_alloc_snapshot(char *str) { - allocate_snapshot = true; - /* We also need the main ring buffer expanded */ - ring_buffer_expanded = true; + char *slot = boot_snapshot_info + boot_snapshot_index; + int left = sizeof(boot_snapshot_info) - boot_snapshot_index; + int ret; + + if (str[0] == '=') { + str++; + if (strlen(str) >= left) + return -1; + + ret = snprintf(slot, left, "%s\t", str); + boot_snapshot_index += ret; + } else { + allocate_snapshot = true; + /* We also need the main ring buffer expanded */ + ring_buffer_expanded = true; + } return 1; } __setup("alloc_snapshot", boot_alloc_snapshot); @@ -239,6 +260,23 @@ static int __init boot_snapshot(char *str) __setup("ftrace_boot_snapshot", boot_snapshot); +static int __init boot_instance(char *str) +{ + char *slot = boot_instance_info + boot_instance_index; + int left = sizeof(boot_instance_info) - boot_instance_index; + int ret; + + if (strlen(str) >= left) + return -1; + + ret = snprintf(slot, left, "%s\t", str); + boot_instance_index += ret; + + return 1; +} +__setup("trace_instance=", boot_instance); + + static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) @@ -1001,13 +1039,8 @@ __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *ev ring_buffer_unlock_commit(buffer); } -/** - * __trace_puts - write a constant string into the trace buffer. - * @ip: The address of the caller - * @str: The constant string to write - * @size: The size of the string. - */ -int __trace_puts(unsigned long ip, const char *str, int size) +int __trace_array_puts(struct trace_array *tr, unsigned long ip, + const char *str, int size) { struct ring_buffer_event *event; struct trace_buffer *buffer; @@ -1015,7 +1048,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) unsigned int trace_ctx; int alloc; - if (!(global_trace.trace_flags & TRACE_ITER_PRINTK)) + if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running || tracing_disabled)) @@ -1024,7 +1057,7 @@ int __trace_puts(unsigned long ip, const char *str, int size) alloc = sizeof(*entry) + size + 2; /* possible \n added */ trace_ctx = tracing_gen_ctx(); - buffer = global_trace.array_buffer.buffer; + buffer = tr->array_buffer.buffer; ring_buffer_nest_start(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, trace_ctx); @@ -1046,11 +1079,23 @@ int __trace_puts(unsigned long ip, const char *str, int size) entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(&global_trace, buffer, trace_ctx, 4, NULL); + ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); out: ring_buffer_nest_end(buffer); return size; } +EXPORT_SYMBOL_GPL(__trace_array_puts); + +/** + * __trace_puts - write a constant string into the trace buffer. + * @ip: The address of the caller + * @str: The constant string to write + * @size: The size of the string. + */ +int __trace_puts(unsigned long ip, const char *str, int size) +{ + return __trace_array_puts(&global_trace, ip, str, size); +} EXPORT_SYMBOL_GPL(__trace_puts); /** @@ -1142,7 +1187,7 @@ void tracing_snapshot_instance(struct trace_array *tr) * * Note, make sure to allocate the snapshot with either * a tracing_snapshot_alloc(), or by doing it manually - * with: echo 1 > /sys/kernel/debug/tracing/snapshot + * with: echo 1 > /sys/kernel/tracing/snapshot * * If the snapshot buffer is not allocated, it will stop tracing. * Basically making a permanent snapshot. @@ -3128,6 +3173,9 @@ void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, return; } + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_GENERIC_ENTRY))) + return; + /* * When an NMI triggers, RCU is enabled via ct_nmi_enter(), * but if the above rcu_is_watching() failed, then the NMI @@ -5598,7 +5646,7 @@ static const char readme_msg[] = #ifdef CONFIG_HIST_TRIGGERS "\t s:[synthetic/]<event> <field> [<field>]\n" #endif - "\t e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]\n" + "\t e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>] [if <filter>]\n" "\t -:[<group>/][<event>]\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" @@ -5615,7 +5663,7 @@ static const char readme_msg[] = "\t $stack<index>, $stack, $retval, $comm,\n" #endif "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" - "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n" + "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t symstr, <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS @@ -5757,7 +5805,7 @@ static const char readme_msg[] = #ifdef CONFIG_SYNTH_EVENTS " events/synthetic_events\t- Create/append/remove/show synthetic events\n" "\t Write into this file to define/undefine new synthetic events.\n" - "\t example: echo 'myevent u64 lat; char name[]' >> synthetic_events\n" + "\t example: echo 'myevent u64 lat; char name[]; long[] stack' >> synthetic_events\n" #endif #endif ; @@ -9148,9 +9196,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; @@ -9225,10 +9270,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) } tr->allocated_snapshot = allocate_snapshot; - /* - * Only the top level trace array gets its snapshot allocated - * from the kernel command line. - */ allocate_snapshot = false; #endif @@ -10144,6 +10185,79 @@ out: return ret; } +#ifdef CONFIG_TRACER_MAX_TRACE +__init static bool tr_needs_alloc_snapshot(const char *name) +{ + char *test; + int len = strlen(name); + bool ret; + + if (!boot_snapshot_index) + return false; + + if (strncmp(name, boot_snapshot_info, len) == 0 && + boot_snapshot_info[len] == '\t') + return true; + + test = kmalloc(strlen(name) + 3, GFP_KERNEL); + if (!test) + return false; + + sprintf(test, "\t%s\t", name); + ret = strstr(boot_snapshot_info, test) == NULL; + kfree(test); + return ret; +} + +__init static void do_allocate_snapshot(const char *name) +{ + if (!tr_needs_alloc_snapshot(name)) + return; + + /* + * When allocate_snapshot is set, the next call to + * allocate_trace_buffers() (called by trace_array_get_by_name()) + * will allocate the snapshot buffer. That will alse clear + * this flag. + */ + allocate_snapshot = true; +} +#else +static inline void do_allocate_snapshot(const char *name) { } +#endif + +__init static void enable_instances(void) +{ + struct trace_array *tr; + char *curr_str; + char *str; + char *tok; + + /* A tab is always appended */ + boot_instance_info[boot_instance_index - 1] = '\0'; + str = boot_instance_info; + + while ((curr_str = strsep(&str, "\t"))) { + + tok = strsep(&curr_str, ","); + + if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) + do_allocate_snapshot(tok); + + tr = trace_array_get_by_name(tok); + if (!tr) { + pr_warn("Failed to create instance buffer %s\n", curr_str); + continue; + } + /* Allow user space to delete it */ + trace_array_put(tr); + + while ((tok = strsep(&curr_str, ","))) { + early_enable_events(tr, tok, true); + } + } +} + __init static int tracer_alloc_buffers(void) { int ring_buf_size; @@ -10277,10 +10391,19 @@ out: void __init ftrace_boot_snapshot(void) { + struct trace_array *tr; + if (snapshot_at_boot) { tracing_snapshot(); internal_trace_puts("** Boot snapshot taken **\n"); } + + list_for_each_entry(tr, &ftrace_trace_arrays, list) { + if (tr == &global_trace) + continue; + trace_array_puts(tr, "** Boot snapshot taken **\n"); + tracing_snapshot_instance(tr); + } } void __init early_trace_init(void) @@ -10295,11 +10418,16 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) { trace_event_init(); + + if (boot_instance_index) + enable_instances(); } __init static void clear_boot_tracer(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e46a49269be2..616e1aa1c4da 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -25,7 +25,7 @@ #include "pid_list.h" #ifdef CONFIG_FTRACE_SYSCALLS -#include <asm/unistd.h> /* For NR_SYSCALLS */ +#include <asm/unistd.h> /* For NR_syscalls */ #include <asm/syscall.h> /* some archs define it here */ #endif @@ -113,6 +113,10 @@ enum trace_type { #define MEM_FAIL(condition, fmt, ...) \ DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__) +#define HIST_STACKTRACE_DEPTH 16 +#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long)) +#define HIST_STACKTRACE_SKIP 5 + /* * syscalls are special, and need special handling, this is why * they are not included in trace_entries.h @@ -1282,6 +1286,7 @@ struct ftrace_event_field { int offset; int size; int is_signed; + int len; }; struct prog_entry; @@ -1330,6 +1335,8 @@ DECLARE_PER_CPU(int, trace_buffered_event_cnt); void trace_buffered_event_disable(void); void trace_buffered_event_enable(void); +void early_enable_events(struct trace_array *tr, char *buf, bool disable_first); + static inline void __trace_event_discard_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) @@ -1490,6 +1497,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 352b65e2b910..67e854979d53 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -311,7 +311,7 @@ print_eprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; @@ -320,7 +320,8 @@ print_eprobe_event(struct trace_iterator *iter, int flags, return trace_handle_return(s); } -static unsigned long get_event_field(struct fetch_insn *code, void *rec) +static nokprobe_inline unsigned long +get_event_field(struct fetch_insn *code, void *rec) { struct ftrace_event_field *field = code->data; unsigned long val; @@ -395,20 +396,12 @@ static int get_eprobe_size(struct trace_probe *tp, void *rec) case FETCH_OP_TP_ARG: val = get_event_field(code, rec); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; goto retry; default: - continue; + if (process_common_fetch_insn(code, &val) < 0) + continue; } code++; len = process_fetch_insn_bottom(code, val, NULL, NULL); @@ -428,84 +421,26 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, void *base) { unsigned long val; + int ret; retry: switch (code->op) { case FETCH_OP_TP_ARG: val = get_event_field(code, rec); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; goto retry; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; return process_fetch_insn_bottom(code, val, dest, base); } NOKPROBE_SYMBOL(process_fetch_insn) -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen_user(unsigned long addr) -{ - return kern_fetch_store_strlen_user(addr); -} - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen(unsigned long addr) -{ - return kern_fetch_store_strlen(addr); -} - -/* - * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf - * with max length and relative data location. - */ -static nokprobe_inline int -fetch_store_string_user(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string_user(addr, dest, base); -} - -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max - * length and relative data location. - */ -static nokprobe_inline int -fetch_store_string(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string(addr, dest, base); -} - -static nokprobe_inline int -probe_mem_read_user(void *dest, void *src, size_t size) -{ - const void __user *uaddr = (__force const void __user *)src; - - return copy_from_user_nofault(dest, uaddr, size); -} - -static nokprobe_inline int -probe_mem_read(void *dest, void *src, size_t size) -{ -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE - if ((unsigned long)src < TASK_SIZE) - return probe_mem_read_user(dest, src, size); -#endif - return copy_from_kernel_nofault(dest, src, size); -} - /* eprobe handler */ static inline void __eprobe_trace_func(struct eprobe_data *edata, void *rec) @@ -923,17 +858,13 @@ static int trace_eprobe_parse_filter(struct trace_eprobe *ep, int argc, const ch p = ep->filter_str; for (i = 0; i < argc; i++) { - ret = snprintf(p, len, "%s ", argv[i]); - if (ret < 0) - goto error; - if (ret > len) { - ret = -E2BIG; - goto error; - } + if (i) + ret = snprintf(p, len, " %s", argv[i]); + else + ret = snprintf(p, len, "%s", argv[i]); p += ret; len -= ret; } - p[-1] = '\0'; /* * Ensure the filter string can be parsed correctly. Note, this diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 33e0b4f8ebe6..654ffa40457a 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -114,7 +114,7 @@ trace_find_event_field(struct trace_event_call *call, char *name) static int __trace_define_field(struct list_head *head, const char *type, const char *name, int offset, int size, - int is_signed, int filter_type) + int is_signed, int filter_type, int len) { struct ftrace_event_field *field; @@ -133,6 +133,7 @@ static int __trace_define_field(struct list_head *head, const char *type, field->offset = offset; field->size = size; field->is_signed = is_signed; + field->len = len; list_add(&field->link, head); @@ -150,14 +151,28 @@ int trace_define_field(struct trace_event_call *call, const char *type, head = trace_get_fields(call); return __trace_define_field(head, type, name, offset, size, - is_signed, filter_type); + is_signed, filter_type, 0); } EXPORT_SYMBOL_GPL(trace_define_field); +static int trace_define_field_ext(struct trace_event_call *call, const char *type, + const char *name, int offset, int size, int is_signed, + int filter_type, int len) +{ + struct list_head *head; + + if (WARN_ON(!call->class)) + return 0; + + head = trace_get_fields(call); + return __trace_define_field(head, type, name, offset, size, + is_signed, filter_type, len); +} + #define __generic_field(type, item, filter_type) \ ret = __trace_define_field(&ftrace_generic_fields, #type, \ #item, 0, 0, is_signed_type(type), \ - filter_type); \ + filter_type, 0); \ if (ret) \ return ret; @@ -166,7 +181,7 @@ EXPORT_SYMBOL_GPL(trace_define_field); "common_" #item, \ offsetof(typeof(ent), item), \ sizeof(ent.item), \ - is_signed_type(type), FILTER_OTHER); \ + is_signed_type(type), FILTER_OTHER, 0); \ if (ret) \ return ret; @@ -1588,12 +1603,17 @@ static int f_show(struct seq_file *m, void *v) seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", field->type, field->name, field->offset, field->size, !!field->is_signed); - else - seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", + else if (field->len) + seq_printf(m, "\tfield:%.*s %s[%d];\toffset:%u;\tsize:%u;\tsigned:%d;\n", (int)(array_descriptor - field->type), field->type, field->name, - array_descriptor, field->offset, + field->len, field->offset, field->size, !!field->is_signed); + else + seq_printf(m, "\tfield:%.*s %s[];\toffset:%u;\tsize:%u;\tsigned:%d;\n", + (int)(array_descriptor - field->type), + field->type, field->name, + field->offset, field->size, !!field->is_signed); return 0; } @@ -2261,8 +2281,6 @@ create_new_subsystem(const char *name) if (!system->name) goto out_free; - system->filter = NULL; - system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL); if (!system->filter) goto out_free; @@ -2379,9 +2397,10 @@ event_define_fields(struct trace_event_call *call) } offset = ALIGN(offset, field->align); - ret = trace_define_field(call, field->type, field->name, + ret = trace_define_field_ext(call, field->type, field->name, offset, field->size, - field->is_signed, field->filter_type); + field->is_signed, field->filter_type, + field->len); if (WARN_ON_ONCE(ret)) { pr_err("error code is %d\n", ret); break; @@ -2822,7 +2841,7 @@ static __init int setup_trace_triggers(char *str) if (!trigger) break; bootup_triggers[i].event = strsep(&trigger, "."); - bootup_triggers[i].trigger = strsep(&trigger, "."); + bootup_triggers[i].trigger = trigger; if (!bootup_triggers[i].trigger) break; } @@ -3750,10 +3769,9 @@ static __init int event_trace_memsetup(void) return 0; } -static __init void -early_enable_events(struct trace_array *tr, bool disable_first) +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) { - char *buf = bootup_event_buf; char *token; int ret; @@ -3806,7 +3824,7 @@ static __init int event_trace_enable(void) */ __trace_early_add_events(tr); - early_enable_events(tr, false); + early_enable_events(tr, bootup_event_buf, false); trace_printk_start_comm(); @@ -3834,7 +3852,7 @@ static __init int event_trace_enable_again(void) if (!tr) return -ENODEV; - early_enable_events(tr, true); + early_enable_events(tr, bootup_event_buf, true); return 0; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 96acc2b71ac7..1dad64267878 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -64,6 +64,7 @@ enum filter_pred_fn { FILTER_PRED_FN_PCHAR_USER, FILTER_PRED_FN_PCHAR, FILTER_PRED_FN_CPU, + FILTER_PRED_FN_FUNCTION, FILTER_PRED_FN_, FILTER_PRED_TEST_VISITED, }; @@ -71,6 +72,7 @@ enum filter_pred_fn { struct filter_pred { enum filter_pred_fn fn_num; u64 val; + u64 val2; struct regex regex; unsigned short *ops; struct ftrace_event_field *field; @@ -103,6 +105,7 @@ struct filter_pred { C(INVALID_FILTER, "Meaningless filter expression"), \ C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \ + C(NO_FUNCTION, "Function not found"), \ C(ERRNO, "Error"), \ C(NO_FILTER, "No filter found") @@ -128,7 +131,7 @@ static bool is_not(const char *str) } /** - * prog_entry - a singe entry in the filter program + * struct prog_entry - a singe entry in the filter program * @target: Index to jump to on a branch (actually one minus the index) * @when_to_branch: The value of the result of the predicate to do a branch * @pred: The predicate to execute. @@ -140,16 +143,16 @@ struct prog_entry { }; /** - * update_preds- assign a program entry a label target + * update_preds - assign a program entry a label target * @prog: The program array * @N: The index of the current entry in @prog - * @when_to_branch: What to assign a program entry for its branch condition + * @invert: What to assign a program entry for its branch condition * * The program entry at @N has a target that points to the index of a program * entry that can have its target and when_to_branch fields updated. * Update the current program entry denoted by index @N target field to be * that of the updated entry. This will denote the entry to update if - * we are processing an "||" after an "&&" + * we are processing an "||" after an "&&". */ static void update_preds(struct prog_entry *prog, int N, int invert) { @@ -876,6 +879,17 @@ static int filter_pred_comm(struct filter_pred *pred, void *event) return cmp ^ pred->not; } +/* Filter predicate for functions. */ +static int filter_pred_function(struct filter_pred *pred, void *event) +{ + unsigned long *addr = (unsigned long *)(event + pred->offset); + unsigned long start = (unsigned long)pred->val; + unsigned long end = (unsigned long)pred->val2; + int ret = *addr >= start && *addr < end; + + return pred->op == OP_EQ ? ret : !ret; +} + /* * regex_match_foo - Basic regex callbacks * @@ -1335,6 +1349,8 @@ static int filter_pred_fn_call(struct filter_pred *pred, void *event) return filter_pred_pchar(pred, event); case FILTER_PRED_FN_CPU: return filter_pred_cpu(pred, event); + case FILTER_PRED_FN_FUNCTION: + return filter_pred_function(pred, event); case FILTER_PRED_TEST_VISITED: return test_pred_visited_fn(pred, event); default: @@ -1350,8 +1366,13 @@ static int parse_pred(const char *str, void *data, struct trace_event_call *call = data; struct ftrace_event_field *field; struct filter_pred *pred = NULL; + unsigned long offset; + unsigned long size; + unsigned long ip; char num_buf[24]; /* Big enough to hold an address */ char *field_name; + char *name; + bool function = false; bool ustring = false; char q; u64 val; @@ -1393,6 +1414,12 @@ static int parse_pred(const char *str, void *data, i += len; } + /* See if the field is a kernel function name */ + if ((len = str_has_prefix(str + i, ".function"))) { + function = true; + i += len; + } + while (isspace(str[i])) i++; @@ -1423,7 +1450,71 @@ static int parse_pred(const char *str, void *data, pred->offset = field->offset; pred->op = op; - if (ftrace_event_is_function(call)) { + if (function) { + /* The field must be the same size as long */ + if (field->size != sizeof(long)) { + parse_error(pe, FILT_ERR_ILLEGAL_FIELD_OP, pos + i); + goto err_free; + } + + /* Function only works with '==' or '!=' and an unquoted string */ + switch (op) { + case OP_NE: + case OP_EQ: + break; + default: + parse_error(pe, FILT_ERR_INVALID_OP, pos + i); + goto err_free; + } + + if (isdigit(str[i])) { + /* We allow 0xDEADBEEF */ + while (isalnum(str[i])) + i++; + + len = i - s; + /* 0xfeedfacedeadbeef is 18 chars max */ + if (len >= sizeof(num_buf)) { + parse_error(pe, FILT_ERR_OPERAND_TOO_LONG, pos + i); + goto err_free; + } + + strncpy(num_buf, str + s, len); + num_buf[len] = 0; + + ret = kstrtoul(num_buf, 0, &ip); + if (ret) { + parse_error(pe, FILT_ERR_INVALID_VALUE, pos + i); + goto err_free; + } + } else { + s = i; + for (; str[i] && !isspace(str[i]); i++) + ; + + len = i - s; + name = kmemdup_nul(str + s, len, GFP_KERNEL); + if (!name) + goto err_mem; + ip = kallsyms_lookup_name(name); + kfree(name); + if (!ip) { + parse_error(pe, FILT_ERR_NO_FUNCTION, pos + i); + goto err_free; + } + } + + /* Now find the function start and end address */ + if (!kallsyms_lookup_size_offset(ip, &size, &offset)) { + parse_error(pe, FILT_ERR_NO_FUNCTION, pos + i); + goto err_free; + } + + pred->fn_num = FILTER_PRED_FN_FUNCTION; + pred->val = ip - offset; + pred->val2 = pred->val + size; + + } else if (ftrace_event_is_function(call)) { /* * Perf does things different with function events. * It only allows an "ip" field, and expects a string. diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fcaf226b7744..89877a18f933 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -135,6 +135,7 @@ enum hist_field_fn { HIST_FIELD_FN_DIV_NOT_POWER2, HIST_FIELD_FN_DIV_MULT_SHIFT, HIST_FIELD_FN_EXECNAME, + HIST_FIELD_FN_STACK, }; /* @@ -480,10 +481,6 @@ DEFINE_HIST_FIELD_FN(u8); #define for_each_hist_key_field(i, hist_data) \ for ((i) = (hist_data)->n_vals; (i) < (hist_data)->n_fields; (i)++) -#define HIST_STACKTRACE_DEPTH 16 -#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long)) -#define HIST_STACKTRACE_SKIP 5 - #define HITCOUNT_IDX 0 #define HIST_KEY_SIZE_MAX (MAX_FILTER_STR_VAL + HIST_STACKTRACE_SIZE) @@ -1360,7 +1357,12 @@ static const char *hist_field_name(struct hist_field *field, field_name = field->name; } else if (field->flags & HIST_FIELD_FL_TIMESTAMP) field_name = "common_timestamp"; - else if (field->flags & HIST_FIELD_FL_HITCOUNT) + else if (field->flags & HIST_FIELD_FL_STACKTRACE) { + if (field->field) + field_name = field->field->name; + else + field_name = "stacktrace"; + } else if (field->flags & HIST_FIELD_FL_HITCOUNT) field_name = "hitcount"; if (field_name == NULL) @@ -1718,6 +1720,8 @@ static const char *get_hist_field_flags(struct hist_field *hist_field) flags_str = "percent"; else if (hist_field->flags & HIST_FIELD_FL_GRAPH) flags_str = "graph"; + else if (hist_field->flags & HIST_FIELD_FL_STACKTRACE) + flags_str = "stacktrace"; return flags_str; } @@ -1979,7 +1983,14 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, } if (flags & HIST_FIELD_FL_STACKTRACE) { - hist_field->fn_num = HIST_FIELD_FN_NOP; + if (field) + hist_field->fn_num = HIST_FIELD_FN_STACK; + else + hist_field->fn_num = HIST_FIELD_FN_NOP; + hist_field->size = HIST_STACKTRACE_SIZE; + hist_field->type = kstrdup_const("unsigned long[]", GFP_KERNEL); + if (!hist_field->type) + goto free; goto out; } @@ -1988,6 +1999,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 : HIST_FIELD_FN_BUCKET; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) @@ -2310,6 +2323,8 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, *flags |= HIST_FIELD_FL_EXECNAME; else if (strcmp(modifier, "syscall") == 0) *flags |= HIST_FIELD_FL_SYSCALL; + else if (strcmp(modifier, "stacktrace") == 0) + *flags |= HIST_FIELD_FL_STACKTRACE; else if (strcmp(modifier, "log2") == 0) *flags |= HIST_FIELD_FL_LOG2; else if (strcmp(modifier, "usecs") == 0) @@ -2349,6 +2364,8 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, hist_data->enable_timestamps = true; if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS) hist_data->attrs->ts_in_usecs = true; + } else if (strcmp(field_name, "stacktrace") == 0) { + *flags |= HIST_FIELD_FL_STACKTRACE; } else if (strcmp(field_name, "common_cpu") == 0) *flags |= HIST_FIELD_FL_CPU; else if (strcmp(field_name, "hitcount") == 0) @@ -3109,6 +3126,9 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, unsigned int i, j, var_idx; u64 var_val; + /* Make sure stacktrace can fit in the string variable length */ + BUILD_BUG_ON((HIST_STACKTRACE_DEPTH + 1) * sizeof(long) >= STR_VAR_LEN_MAX); + for (i = 0, j = field_var_str_start; i < n_field_vars; i++) { struct field_var *field_var = field_vars[i]; struct hist_field *var = field_var->var; @@ -3117,13 +3137,26 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, var_val = hist_fn_call(val, elt, buffer, rbe, rec); var_idx = var->var.idx; - if (val->flags & HIST_FIELD_FL_STRING) { + if (val->flags & (HIST_FIELD_FL_STRING | + HIST_FIELD_FL_STACKTRACE)) { char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; unsigned int size; - size = min(val->size, STR_VAR_LEN_MAX); - strscpy(str, val_str, size); + if (val->flags & HIST_FIELD_FL_STRING) { + size = min(val->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); + } else { + char *stack_start = str + sizeof(unsigned long); + int e; + + e = stack_trace_save((void *)stack_start, + HIST_STACKTRACE_DEPTH, + HIST_STACKTRACE_SKIP); + if (e < HIST_STACKTRACE_DEPTH - 1) + ((unsigned long *)stack_start)[e] = 0; + *((unsigned long *)str) = e; + } var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -3822,7 +3855,8 @@ static void save_field_var(struct hist_trigger_data *hist_data, { hist_data->field_vars[hist_data->n_field_vars++] = field_var; - if (field_var->val->flags & HIST_FIELD_FL_STRING) + /* Stack traces are saved in the string storage too */ + if (field_var->val->flags & (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE)) hist_data->n_field_var_str++; } @@ -3847,6 +3881,9 @@ static int check_synth_field(struct synth_event *event, && field->is_dynamic) return 0; + if (strstr(hist_field->type, "long[") && field->is_stack) + return 0; + if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || (!field->is_string && field->is_signed != hist_field->is_signed)) @@ -4101,7 +4138,8 @@ static int action_create(struct hist_trigger_data *hist_data, } hist_data->save_vars[hist_data->n_save_vars++] = field_var; - if (field_var->val->flags & HIST_FIELD_FL_STRING) + if (field_var->val->flags & + (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE)) hist_data->n_save_var_str++; kfree(param); } @@ -4240,6 +4278,19 @@ static u64 hist_field_execname(struct hist_field *hist_field, return (u64)(unsigned long)(elt_data->comm); } +static u64 hist_field_stack(struct hist_field *hist_field, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, + struct ring_buffer_event *rbe, + void *event) +{ + u32 str_item = *(u32 *)(event + hist_field->field->offset); + int str_loc = str_item & 0xffff; + char *addr = (char *)(event + str_loc); + + return (u64)(unsigned long)addr; +} + static u64 hist_fn_call(struct hist_field *hist_field, struct tracing_map_elt *elt, struct trace_buffer *buffer, @@ -4303,6 +4354,8 @@ static u64 hist_fn_call(struct hist_field *hist_field, return div_by_mult_and_shift(hist_field, elt, buffer, rbe, event); case HIST_FIELD_FN_EXECNAME: return hist_field_execname(hist_field, elt, buffer, rbe, event); + case HIST_FIELD_FN_STACK: + return hist_field_stack(hist_field, elt, buffer, rbe, event); default: return 0; } @@ -4349,7 +4402,8 @@ static int create_var_field(struct hist_trigger_data *hist_data, if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_EXECNAME) update_var_execname(hist_data->fields[val_idx]); - if (!ret && hist_data->fields[val_idx]->flags & HIST_FIELD_FL_STRING) + if (!ret && hist_data->fields[val_idx]->flags & + (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE)) hist_data->fields[val_idx]->var_str_idx = hist_data->n_var_str++; return ret; @@ -5090,7 +5144,8 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, if (hist_field->flags & HIST_FIELD_FL_VAR) { var_idx = hist_field->var.idx; - if (hist_field->flags & HIST_FIELD_FL_STRING) { + if (hist_field->flags & + (HIST_FIELD_FL_STRING | HIST_FIELD_FL_STACKTRACE)) { unsigned int str_start, var_str_idx, idx; char *str, *val_str; unsigned int size; @@ -5103,9 +5158,20 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - size = min(hist_field->size, STR_VAR_LEN_MAX); - strscpy(str, val_str, size); - + if (hist_field->flags & HIST_FIELD_FL_STRING) { + size = min(hist_field->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); + } else { + char *stack_start = str + sizeof(unsigned long); + int e; + + e = stack_trace_save((void *)stack_start, + HIST_STACKTRACE_DEPTH, + HIST_STACKTRACE_SKIP); + if (e < HIST_STACKTRACE_DEPTH - 1) + ((unsigned long *)stack_start)[e] = 0; + *((unsigned long *)str) = e; + } hist_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, hist_val); @@ -5191,8 +5257,17 @@ static void event_hist_trigger(struct event_trigger_data *data, if (key_field->flags & HIST_FIELD_FL_STACKTRACE) { memset(entries, 0, HIST_STACKTRACE_SIZE); - stack_trace_save(entries, HIST_STACKTRACE_DEPTH, - HIST_STACKTRACE_SKIP); + if (key_field->field) { + unsigned long *stack, n_entries; + + field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec); + stack = (unsigned long *)(long)field_contents; + n_entries = *stack; + memcpy(entries, ++stack, n_entries * sizeof(unsigned long)); + } else { + stack_trace_save(entries, HIST_STACKTRACE_DEPTH, + HIST_STACKTRACE_SKIP); + } key = entries; } else { field_contents = hist_fn_call(key_field, elt, buffer, rbe, rec); @@ -5295,7 +5370,10 @@ static void hist_trigger_print_key(struct seq_file *m, seq_printf(m, "%s: %-30s[%3llu]", field_name, syscall_name, uval); } else if (key_field->flags & HIST_FIELD_FL_STACKTRACE) { - seq_puts(m, "stacktrace:\n"); + if (key_field->field) + seq_printf(m, "%s.stacktrace", key_field->field->name); + else + seq_puts(m, "stacktrace:\n"); hist_trigger_stacktrace_print(m, key + key_field->offset, HIST_STACKTRACE_DEPTH); @@ -5840,7 +5918,8 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) if (hist_field->flags) { if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) && - !(hist_field->flags & HIST_FIELD_FL_EXPR)) { + !(hist_field->flags & HIST_FIELD_FL_EXPR) && + !(hist_field->flags & HIST_FIELD_FL_STACKTRACE)) { const char *flags = get_hist_field_flags(hist_field); if (flags) @@ -5873,9 +5952,12 @@ static int event_hist_trigger_print(struct seq_file *m, if (i > hist_data->n_vals) seq_puts(m, ","); - if (field->flags & HIST_FIELD_FL_STACKTRACE) - seq_puts(m, "stacktrace"); - else + if (field->flags & HIST_FIELD_FL_STACKTRACE) { + if (field->field) + seq_printf(m, "%s.stacktrace", field->field->name); + else + seq_puts(m, "stacktrace"); + } else hist_field_print(m, field); } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 67592eed0be8..46d0abb32d0f 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -173,6 +173,14 @@ static int synth_field_is_string(char *type) return false; } +static int synth_field_is_stack(char *type) +{ + if (strstr(type, "long[") != NULL) + return true; + + return false; +} + static int synth_field_string_size(char *type) { char buf[4], *end, *start; @@ -248,6 +256,8 @@ static int synth_field_size(char *type) size = sizeof(gfp_t); else if (synth_field_is_string(type)) size = synth_field_string_size(type); + else if (synth_field_is_stack(type)) + size = 0; return size; } @@ -292,6 +302,8 @@ static const char *synth_field_fmt(char *type) fmt = "%x"; else if (synth_field_is_string(type)) fmt = "%.*s"; + else if (synth_field_is_stack(type)) + fmt = "%s"; return fmt; } @@ -371,6 +383,23 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter, i == se->n_fields - 1 ? "" : " "); n_u64 += STR_VAR_LEN_MAX / sizeof(u64); } + } else if (se->fields[i]->is_stack) { + u32 offset, data_offset, len; + unsigned long *p, *end; + + offset = (u32)entry->fields[n_u64]; + data_offset = offset & 0xffff; + len = offset >> 16; + + p = (void *)entry + data_offset; + end = (void *)p + len - (sizeof(long) - 1); + + trace_seq_printf(s, "%s=STACK:\n", se->fields[i]->name); + + for (; *p && p < end; p++) + trace_seq_printf(s, "=> %pS\n", (void *)*p); + n_u64++; + } else { struct trace_print_flags __flags[] = { __def_gfpflag_names, {-1, NULL} }; @@ -416,16 +445,15 @@ static unsigned int trace_string(struct synth_trace_event *entry, if (is_dynamic) { u32 data_offset; - data_offset = offsetof(typeof(*entry), fields); - data_offset += event->n_u64 * sizeof(u64); + data_offset = struct_size(entry, fields, event->n_u64); data_offset += data_size; - len = kern_fetch_store_strlen((unsigned long)str_val); + len = fetch_store_strlen((unsigned long)str_val); data_offset |= len << 16; *(u32 *)&entry->fields[*n_u64] = data_offset; - ret = kern_fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); + ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); (*n_u64)++; } else { @@ -447,6 +475,43 @@ static unsigned int trace_string(struct synth_trace_event *entry, return len; } +static unsigned int trace_stack(struct synth_trace_event *entry, + struct synth_event *event, + long *stack, + unsigned int data_size, + unsigned int *n_u64) +{ + unsigned int len; + u32 data_offset; + void *data_loc; + + data_offset = struct_size(entry, fields, event->n_u64); + data_offset += data_size; + + for (len = 0; len < HIST_STACKTRACE_DEPTH; len++) { + if (!stack[len]) + break; + } + + /* Include the zero'd element if it fits */ + if (len < HIST_STACKTRACE_DEPTH) + len++; + + len *= sizeof(long); + + /* Find the dynamic section to copy the stack into. */ + data_loc = (void *)entry + data_offset; + memcpy(data_loc, stack, len); + + /* Fill in the field that holds the offset/len combo */ + data_offset |= len << 16; + *(u32 *)&entry->fields[*n_u64] = data_offset; + + (*n_u64)++; + + return len; +} + static notrace void trace_event_raw_event_synth(void *__data, u64 *var_ref_vals, unsigned int *var_ref_idx) @@ -473,7 +538,12 @@ static notrace void trace_event_raw_event_synth(void *__data, val_idx = var_ref_idx[field_pos]; str_val = (char *)(long)var_ref_vals[val_idx]; - len = kern_fetch_store_strlen((unsigned long)str_val); + if (event->dynamic_fields[i]->is_stack) { + len = *((unsigned long *)str_val); + len *= sizeof(unsigned long); + } else { + len = fetch_store_strlen((unsigned long)str_val); + } fields_size += len; } @@ -499,6 +569,12 @@ static notrace void trace_event_raw_event_synth(void *__data, event->fields[i]->is_dynamic, data_size, &n_u64); data_size += len; /* only dynamic string increments */ + } else if (event->fields[i]->is_stack) { + long *stack = (long *)(long)var_ref_vals[val_idx]; + + len = trace_stack(entry, event, stack, + data_size, &n_u64); + data_size += len; } else { struct synth_field *field = event->fields[i]; u64 val = var_ref_vals[val_idx]; @@ -561,6 +637,9 @@ static int __set_synth_event_print_fmt(struct synth_event *event, event->fields[i]->is_dynamic) pos += snprintf(buf + pos, LEN_OR_ZERO, ", __get_str(%s)", event->fields[i]->name); + else if (event->fields[i]->is_stack) + pos += snprintf(buf + pos, LEN_OR_ZERO, + ", __get_stacktrace(%s)", event->fields[i]->name); else pos += snprintf(buf + pos, LEN_OR_ZERO, ", REC->%s", event->fields[i]->name); @@ -697,7 +776,8 @@ static struct synth_field *parse_synth_field(int argc, char **argv, ret = -EINVAL; goto free; } else if (size == 0) { - if (synth_field_is_string(field->type)) { + if (synth_field_is_string(field->type) || + synth_field_is_stack(field->type)) { char *type; len = sizeof("__data_loc ") + strlen(field->type) + 1; @@ -728,6 +808,8 @@ static struct synth_field *parse_synth_field(int argc, char **argv, if (synth_field_is_string(field->type)) field->is_string = true; + else if (synth_field_is_stack(field->type)) + field->is_stack = true; field->is_signed = synth_field_signed(field->type); out: diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index d960f6b11b5e..58f3946081e2 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -111,7 +111,8 @@ static void __always_unused ____ftrace_check_##name(void) \ #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 }, + is_signed_type(_type), .filter_type = FILTER_OTHER, \ + .len = _len }, #undef __array_desc #define __array_desc(_type, _container, _item, _len) __array(_type, _item, _len) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ee77c8203bd5..59cda19a9033 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1218,60 +1218,6 @@ static const struct file_operations kprobe_profile_ops = { .release = seq_release, }; -/* Kprobe specific fetch functions */ - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen_user(unsigned long addr) -{ - return kern_fetch_store_strlen_user(addr); -} - -/* Return the length of string -- including null terminal byte */ -static nokprobe_inline int -fetch_store_strlen(unsigned long addr) -{ - return kern_fetch_store_strlen(addr); -} - -/* - * Fetch a null-terminated string from user. Caller MUST set *(u32 *)buf - * with max length and relative data location. - */ -static nokprobe_inline int -fetch_store_string_user(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string_user(addr, dest, base); -} - -/* - * Fetch a null-terminated string. Caller MUST set *(u32 *)buf with max - * length and relative data location. - */ -static nokprobe_inline int -fetch_store_string(unsigned long addr, void *dest, void *base) -{ - return kern_fetch_store_string(addr, dest, base); -} - -static nokprobe_inline int -probe_mem_read_user(void *dest, void *src, size_t size) -{ - const void __user *uaddr = (__force const void __user *)src; - - return copy_from_user_nofault(dest, uaddr, size); -} - -static nokprobe_inline int -probe_mem_read(void *dest, void *src, size_t size) -{ -#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE - if ((unsigned long)src < TASK_SIZE) - return probe_mem_read_user(dest, src, size); -#endif - return copy_from_kernel_nofault(dest, src, size); -} - /* Note that we don't verify it, since the code does not come from user space */ static int process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, @@ -1279,6 +1225,7 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, { struct pt_regs *regs = rec; unsigned long val; + int ret; retry: /* 1st stage: get value from context */ @@ -1295,15 +1242,6 @@ retry: case FETCH_OP_RETVAL: val = regs_return_value(regs); break; - case FETCH_OP_IMM: - val = code->immediate; - break; - case FETCH_OP_COMM: - val = (unsigned long)current->comm; - break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); @@ -1313,7 +1251,9 @@ retry: code++; goto retry; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; @@ -1424,7 +1364,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; @@ -1459,7 +1399,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags, trace_seq_putc(s, ')'); - if (print_probe_args(s, tp->args, tp->nr_args, + if (trace_probe_print_args(s, tp->args, tp->nr_args, (u8 *)&field[1], field) < 0) goto out; diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 94c1b5eb1dc0..04f0fdae19a1 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -147,9 +147,8 @@ static void osnoise_unregister_instance(struct trace_array *tr) * register/unregister serialization is provided by trace's * trace_types_lock. */ - lockdep_assert_held(&trace_types_lock); - - list_for_each_entry_rcu(inst, &osnoise_instances, list) { + list_for_each_entry_rcu(inst, &osnoise_instances, list, + lockdep_is_held(&trace_types_lock)) { if (inst->tr == tr) { list_del_rcu(&inst->list); found = 1; @@ -1540,7 +1539,7 @@ static void osnoise_sleep(void) wake_time = ktime_add_us(ktime_get(), interval); __set_current_state(TASK_INTERRUPTIBLE); - while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) { + while (schedule_hrtimeout(&wake_time, HRTIMER_MODE_ABS)) { if (kthread_should_stop()) break; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 57a13b61f186..bd475a00f96d 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1535,7 +1535,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1548,4 +1548,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index 1e130da1b742..e37446f7916e 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -15,6 +15,20 @@ #define CREATE_TRACE_POINTS #include <trace/events/preemptirq.h> +/* + * Use regular trace points on architectures that implement noinstr + * tooling: these calls will only happen with RCU enabled, which can + * use a regular tracepoint. + * + * On older architectures, use the rcuidle tracing methods (which + * aren't NMI-safe - so exclude NMI contexts): + */ +#ifdef CONFIG_ARCH_WANTS_NO_INSTR +#define trace(point) trace_##point +#else +#define trace(point) if (!in_nmi()) trace_##point##_rcuidle +#endif + #ifdef CONFIG_TRACE_IRQFLAGS /* Per-cpu variable to prevent redundant calls when IRQs already off */ static DEFINE_PER_CPU(int, tracing_irq_cpu); @@ -28,8 +42,7 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu); void trace_hardirqs_on_prepare(void) { if (this_cpu_read(tracing_irq_cpu)) { - if (!in_nmi()) - trace_irq_enable(CALLER_ADDR0, CALLER_ADDR1); + trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } @@ -40,8 +53,7 @@ NOKPROBE_SYMBOL(trace_hardirqs_on_prepare); void trace_hardirqs_on(void) { if (this_cpu_read(tracing_irq_cpu)) { - if (!in_nmi()) - trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + trace(irq_enable)(CALLER_ADDR0, CALLER_ADDR1); tracer_hardirqs_on(CALLER_ADDR0, CALLER_ADDR1); this_cpu_write(tracing_irq_cpu, 0); } @@ -63,8 +75,7 @@ void trace_hardirqs_off_finish(void) if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); - if (!in_nmi()) - trace_irq_disable(CALLER_ADDR0, CALLER_ADDR1); + trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1); } } @@ -78,56 +89,24 @@ void trace_hardirqs_off(void) if (!this_cpu_read(tracing_irq_cpu)) { this_cpu_write(tracing_irq_cpu, 1); tracer_hardirqs_off(CALLER_ADDR0, CALLER_ADDR1); - if (!in_nmi()) - trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + trace(irq_disable)(CALLER_ADDR0, CALLER_ADDR1); } } EXPORT_SYMBOL(trace_hardirqs_off); NOKPROBE_SYMBOL(trace_hardirqs_off); - -__visible void trace_hardirqs_on_caller(unsigned long caller_addr) -{ - if (this_cpu_read(tracing_irq_cpu)) { - if (!in_nmi()) - trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); - tracer_hardirqs_on(CALLER_ADDR0, caller_addr); - this_cpu_write(tracing_irq_cpu, 0); - } - - lockdep_hardirqs_on_prepare(); - lockdep_hardirqs_on(caller_addr); -} -EXPORT_SYMBOL(trace_hardirqs_on_caller); -NOKPROBE_SYMBOL(trace_hardirqs_on_caller); - -__visible void trace_hardirqs_off_caller(unsigned long caller_addr) -{ - lockdep_hardirqs_off(caller_addr); - - if (!this_cpu_read(tracing_irq_cpu)) { - this_cpu_write(tracing_irq_cpu, 1); - tracer_hardirqs_off(CALLER_ADDR0, caller_addr); - if (!in_nmi()) - trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); - } -} -EXPORT_SYMBOL(trace_hardirqs_off_caller); -NOKPROBE_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ #ifdef CONFIG_TRACE_PREEMPT_TOGGLE void trace_preempt_on(unsigned long a0, unsigned long a1) { - if (!in_nmi()) - trace_preempt_enable_rcuidle(a0, a1); + trace(preempt_enable)(a0, a1); tracer_preempt_on(a0, a1); } void trace_preempt_off(unsigned long a0, unsigned long a1) { - if (!in_nmi()) - trace_preempt_disable_rcuidle(a0, a1); + trace(preempt_disable)(a0, a1); tracer_preempt_off(a0, a1); } #endif diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 01ebabbbe8c9..20d0c4a97633 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -50,6 +50,7 @@ DEFINE_BASIC_PRINT_TYPE_FUNC(x8, u8, "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(x16, u16, "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(x32, u32, "0x%x") DEFINE_BASIC_PRINT_TYPE_FUNC(x64, u64, "0x%Lx") +DEFINE_BASIC_PRINT_TYPE_FUNC(char, u8, "'%c'") int PRINT_TYPE_FUNC_NAME(symbol)(struct trace_seq *s, void *data, void *ent) { @@ -95,6 +96,7 @@ static const struct fetch_type probe_fetch_types[] = { ASSIGN_FETCH_TYPE_ALIAS(x16, u16, u16, 0), ASSIGN_FETCH_TYPE_ALIAS(x32, u32, u32, 0), ASSIGN_FETCH_TYPE_ALIAS(x64, u64, u64, 0), + ASSIGN_FETCH_TYPE_ALIAS(char, u8, u8, 0), ASSIGN_FETCH_TYPE_ALIAS(symbol, ADDR_FETCH_TYPE, ADDR_FETCH_TYPE, 0), ASSIGN_FETCH_TYPE_END @@ -1237,3 +1239,30 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char return ret; } + +int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, + u8 *data, void *field) +{ + void *p; + int i, j; + + for (i = 0; i < nr_args; i++) { + struct probe_arg *a = args + i; + + trace_seq_printf(s, " %s=", a->name); + if (likely(!a->count)) { + if (!a->type->print(s, data + a->offset, field)) + return -ENOMEM; + continue; + } + trace_seq_putc(s, '{'); + p = data + a->offset; + for (j = 0; j < a->count; j++) { + if (!a->type->print(s, p, field)) + return -ENOMEM; + trace_seq_putc(s, j == a->count - 1 ? '}' : ','); + p += a->type->size; + } + } + return 0; +} diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 23acfd1c3812..ef8ed3b65d05 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -166,6 +166,7 @@ DECLARE_BASIC_PRINT_TYPE_FUNC(x16); DECLARE_BASIC_PRINT_TYPE_FUNC(x32); DECLARE_BASIC_PRINT_TYPE_FUNC(x64); +DECLARE_BASIC_PRINT_TYPE_FUNC(char); DECLARE_BASIC_PRINT_TYPE_FUNC(string); DECLARE_BASIC_PRINT_TYPE_FUNC(symbol); @@ -348,6 +349,8 @@ int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b); bool trace_probe_match_command_args(struct trace_probe *tp, int argc, const char **argv); int trace_probe_create(const char *raw_command, int (*createfn)(int, const char **)); +int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, + u8 *data, void *field); #define trace_probe_for_each_link(pos, tp) \ list_for_each_entry(pos, &(tp)->event->files, list) diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h index 77dbd9ff9782..c4e1d4c03a85 100644 --- a/kernel/trace/trace_probe_kernel.h +++ b/kernel/trace/trace_probe_kernel.h @@ -12,7 +12,7 @@ */ /* Return the length of string -- including null terminal byte */ static nokprobe_inline int -kern_fetch_store_strlen_user(unsigned long addr) +fetch_store_strlen_user(unsigned long addr) { const void __user *uaddr = (__force const void __user *)addr; int ret; @@ -29,14 +29,14 @@ kern_fetch_store_strlen_user(unsigned long addr) /* Return the length of string -- including null terminal byte */ static nokprobe_inline int -kern_fetch_store_strlen(unsigned long addr) +fetch_store_strlen(unsigned long addr) { int ret, len = 0; u8 c; #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if (addr < TASK_SIZE) - return kern_fetch_store_strlen_user(addr); + return fetch_store_strlen_user(addr); #endif do { @@ -63,7 +63,7 @@ static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void * with max length and relative data location. */ static nokprobe_inline int -kern_fetch_store_string_user(unsigned long addr, void *dest, void *base) +fetch_store_string_user(unsigned long addr, void *dest, void *base) { const void __user *uaddr = (__force const void __user *)addr; int maxlen = get_loc_len(*(u32 *)dest); @@ -86,7 +86,7 @@ kern_fetch_store_string_user(unsigned long addr, void *dest, void *base) * length and relative data location. */ static nokprobe_inline int -kern_fetch_store_string(unsigned long addr, void *dest, void *base) +fetch_store_string(unsigned long addr, void *dest, void *base) { int maxlen = get_loc_len(*(u32 *)dest); void *__dest; @@ -94,7 +94,7 @@ kern_fetch_store_string(unsigned long addr, void *dest, void *base) #ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE if ((unsigned long)addr < TASK_SIZE) - return kern_fetch_store_string_user(addr, dest, base); + return fetch_store_string_user(addr, dest, base); #endif if (unlikely(!maxlen)) @@ -112,4 +112,22 @@ kern_fetch_store_string(unsigned long addr, void *dest, void *base) return ret; } +static nokprobe_inline int +probe_mem_read_user(void *dest, void *src, size_t size) +{ + const void __user *uaddr = (__force const void __user *)src; + + return copy_from_user_nofault(dest, uaddr, size); +} + +static nokprobe_inline int +probe_mem_read(void *dest, void *src, size_t size) +{ +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + if ((unsigned long)src < TASK_SIZE) + return probe_mem_read_user(dest, src, size); +#endif + return copy_from_kernel_nofault(dest, src, size); +} + #endif /* __TRACE_PROBE_KERNEL_H_ */ diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5cea672243f6..00707630788d 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -98,6 +98,26 @@ fetch_store_symstring(unsigned long addr, void *dest, void *base) return sprint_symbol(__dest, addr); } +/* common part of process_fetch_insn*/ +static nokprobe_inline int +process_common_fetch_insn(struct fetch_insn *code, unsigned long *val) +{ + switch (code->op) { + case FETCH_OP_IMM: + *val = code->immediate; + break; + case FETCH_OP_COMM: + *val = (unsigned long)current->comm; + break; + case FETCH_OP_DATA: + *val = (unsigned long)code->data; + break; + default: + return -EILSEQ; + } + return 0; +} + /* From the 2nd stage, routine is same */ static nokprobe_inline int process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val, @@ -253,31 +273,3 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec, } } } - -static inline int -print_probe_args(struct trace_seq *s, struct probe_arg *args, int nr_args, - u8 *data, void *field) -{ - void *p; - int i, j; - - for (i = 0; i < nr_args; i++) { - struct probe_arg *a = args + i; - - trace_seq_printf(s, " %s=", a->name); - if (likely(!a->count)) { - if (!a->type->print(s, data + a->offset, field)) - return -ENOMEM; - continue; - } - trace_seq_putc(s, '{'); - p = data + a->offset; - for (j = 0; j < a->count; j++) { - if (!a->type->print(s, p, field)) - return -ENOMEM; - trace_seq_putc(s, j == a->count - 1 ? '}' : ','); - p += a->type->size; - } - } - return 0; -} diff --git a/kernel/trace/trace_seq.c b/kernel/trace/trace_seq.c index 9c90b3a7dce2..e5e299260d0c 100644 --- a/kernel/trace/trace_seq.c +++ b/kernel/trace/trace_seq.c @@ -403,3 +403,26 @@ int trace_seq_hex_dump(struct trace_seq *s, const char *prefix_str, return 1; } EXPORT_SYMBOL(trace_seq_hex_dump); + +/* + * trace_seq_acquire - acquire seq buffer with size len + * @s: trace sequence descriptor + * @len: size of buffer to be acquired + * + * acquire buffer with size of @len from trace_seq for output usage, + * user can fill string into that buffer. + * + * Returns start address of acquired buffer. + * + * it allow multiple usage in one trace output function call. + */ +char *trace_seq_acquire(struct trace_seq *s, unsigned int len) +{ + char *ret = trace_seq_buffer_ptr(s); + + if (!WARN_ON_ONCE(seq_buf_buffer_left(&s->seq) < len)) + seq_buf_commit(&s->seq, len); + + return ret; +} +EXPORT_SYMBOL(trace_seq_acquire); diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h index b29595fe3ac5..43f6fb6078db 100644 --- a/kernel/trace/trace_synth.h +++ b/kernel/trace/trace_synth.h @@ -18,6 +18,7 @@ struct synth_field { bool is_signed; bool is_string; bool is_dynamic; + bool is_stack; }; struct synth_event { diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 8d64b6553aed..8b92e34ff0c8 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -220,6 +220,7 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, { struct pt_regs *regs = rec; unsigned long val; + int ret; /* 1st stage: get value from context */ switch (code->op) { @@ -235,20 +236,16 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, case FETCH_OP_RETVAL: val = regs_return_value(regs); break; - case FETCH_OP_IMM: - val = code->immediate; - break; case FETCH_OP_COMM: val = FETCH_TOKEN_COMM; break; - case FETCH_OP_DATA: - val = (unsigned long)code->data; - break; case FETCH_OP_FOFFS: val = translate_user_vaddr(code->immediate); break; default: - return -EILSEQ; + ret = process_common_fetch_insn(code, &val); + if (ret < 0) + return ret; } code++; @@ -1042,7 +1039,7 @@ print_uprobe_event(struct trace_iterator *iter, int flags, struct trace_event *e data = DATAOF_TRACE_ENTRY(entry, false); } - if (print_probe_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) + if (trace_probe_print_args(s, tu->tp.args, tu->tp.nr_args, data, entry) < 0) goto out; trace_seq_putc(s, '\n'); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index f23144af5743..8d1507dd0724 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -571,8 +571,8 @@ static void for_each_tracepoint_range( bool trace_module_has_bad_taint(struct module *mod) { return mod->taints & ~((1 << TAINT_OOT_MODULE) | (1 << TAINT_CRAP) | - (1 << TAINT_UNSIGNED_MODULE) | - (1 << TAINT_TEST)); + (1 << TAINT_UNSIGNED_MODULE) | (1 << TAINT_TEST) | + (1 << TAINT_LIVEPATCH)); } static BLOCKING_NOTIFIER_HEAD(tracepoint_notify_list); diff --git a/kernel/umh.c b/kernel/umh.c index 850631518665..60aa9e764a38 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -32,9 +32,6 @@ #include <trace/events/module.h> -#define CAP_BSET (void *)1 -#define CAP_PI (void *)2 - static kernel_cap_t usermodehelper_bset = CAP_FULL_SET; static kernel_cap_t usermodehelper_inheritable = CAP_FULL_SET; static DEFINE_SPINLOCK(umh_sysctl_lock); @@ -438,21 +435,27 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) if (wait == UMH_NO_WAIT) /* task has freed sub_info */ goto unlock; - if (wait & UMH_KILLABLE) - state |= TASK_KILLABLE; - if (wait & UMH_FREEZABLE) state |= TASK_FREEZABLE; - retval = wait_for_completion_state(&done, state); - if (!retval) - goto wait_done; - if (wait & UMH_KILLABLE) { + retval = wait_for_completion_state(&done, state | TASK_KILLABLE); + if (!retval) + goto wait_done; + /* umh_complete() will see NULL and free sub_info */ if (xchg(&sub_info->complete, NULL)) goto unlock; + + /* + * fallthrough; in case of -ERESTARTSYS now do uninterruptible + * wait_for_completion_state(). Since umh_complete() shall call + * complete() in a moment if xchg() above returned NULL, this + * uninterruptible wait_for_completion_state() will not block + * SIGKILL'ed processes for long. + */ } + wait_for_completion_state(&done, state); wait_done: retval = sub_info->retval; @@ -495,9 +498,9 @@ static int proc_cap_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; - unsigned long cap_array[_KERNEL_CAPABILITY_U32S]; - kernel_cap_t new_cap; - int err, i; + unsigned long cap_array[2]; + kernel_cap_t new_cap, *cap; + int err; if (write && (!capable(CAP_SETPCAP) || !capable(CAP_SYS_MODULE))) @@ -506,16 +509,13 @@ static int proc_cap_handler(struct ctl_table *table, int write, /* * convert from the global kernel_cap_t to the ulong array to print to * userspace if this is a read. + * + * Legacy format: capabilities are exposed as two 32-bit values */ + cap = table->data; spin_lock(&umh_sysctl_lock); - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) { - if (table->data == CAP_BSET) - cap_array[i] = usermodehelper_bset.cap[i]; - else if (table->data == CAP_PI) - cap_array[i] = usermodehelper_inheritable.cap[i]; - else - BUG(); - } + cap_array[0] = (u32) cap->val; + cap_array[1] = cap->val >> 32; spin_unlock(&umh_sysctl_lock); t = *table; @@ -529,22 +529,15 @@ static int proc_cap_handler(struct ctl_table *table, int write, if (err < 0) return err; - /* - * convert from the sysctl array of ulongs to the kernel_cap_t - * internal representation - */ - for (i = 0; i < _KERNEL_CAPABILITY_U32S; i++) - new_cap.cap[i] = cap_array[i]; + new_cap.val = (u32)cap_array[0]; + new_cap.val += (u64)cap_array[1] << 32; /* * Drop everything not in the new_cap (but don't add things) */ if (write) { spin_lock(&umh_sysctl_lock); - if (table->data == CAP_BSET) - usermodehelper_bset = cap_intersect(usermodehelper_bset, new_cap); - if (table->data == CAP_PI) - usermodehelper_inheritable = cap_intersect(usermodehelper_inheritable, new_cap); + *cap = cap_intersect(*cap, new_cap); spin_unlock(&umh_sysctl_lock); } @@ -554,15 +547,15 @@ static int proc_cap_handler(struct ctl_table *table, int write, struct ctl_table usermodehelper_table[] = { { .procname = "bset", - .data = CAP_BSET, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .data = &usermodehelper_bset, + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, { .procname = "inheritable", - .data = CAP_PI, - .maxlen = _KERNEL_CAPABILITY_U32S * sizeof(unsigned long), + .data = &usermodehelper_inheritable, + .maxlen = 2 * sizeof(unsigned long), .mode = 0600, .proc_handler = proc_cap_handler, }, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 54211dbd516c..1d8e47bed3f1 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -229,7 +229,7 @@ void __put_user_ns(struct user_namespace *ns) EXPORT_SYMBOL(__put_user_ns); /** - * idmap_key struct holds the information necessary to find an idmapping in a + * struct idmap_key - holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index a6f9bdd956c3..f10f403104e7 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -273,6 +273,7 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) if (ret < 0) goto error; + ret = -ENOMEM; pages = kcalloc(sizeof(struct page *), nr_pages, GFP_KERNEL); if (!pages) goto error; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 07895deca271..b8b541caed48 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -169,7 +169,9 @@ struct worker_pool { struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ - struct timer_list mayday_timer; /* L: SOS timer for workers */ + struct work_struct idle_cull_work; /* L: worker idle cleanup */ + + struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); @@ -177,6 +179,7 @@ struct worker_pool { struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ + struct list_head dying_workers; /* A: workers about to die */ struct completion *detach_completion; /* all workers detached */ struct ida worker_ida; /* worker IDs for task name */ @@ -326,7 +329,7 @@ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ -/* PL: allowable cpus for unbound wqs and work items */ +/* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* CPU where unbound work was last round robin scheduled from this CPU */ @@ -1433,9 +1436,13 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, lockdep_assert_irqs_disabled(); - /* if draining, only works from the same workqueue are allowed */ - if (unlikely(wq->flags & __WQ_DRAINING) && - WARN_ON_ONCE(!is_chained_work(wq))) + /* + * For a draining wq, only works from the same workqueue are + * allowed. The __WQ_DESTROYING helps to spot the issue that + * queues a new work item to a wq after destroy_workqueue(wq). + */ + if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq)))) return; rcu_read_lock(); retry: @@ -1900,7 +1907,7 @@ static void worker_detach_from_pool(struct worker *worker) list_del(&worker->node); worker->pool = NULL; - if (list_empty(&pool->workers)) + if (list_empty(&pool->workers) && list_empty(&pool->dying_workers)) detach_completion = pool->detach_completion; mutex_unlock(&wq_pool_attach_mutex); @@ -1972,21 +1979,55 @@ fail: return NULL; } +static void unbind_worker(struct worker *worker) +{ + lockdep_assert_held(&wq_pool_attach_mutex); + + kthread_set_per_cpu(worker->task, -1); + if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); + else + WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); +} + +static void wake_dying_workers(struct list_head *cull_list) +{ + struct worker *worker, *tmp; + + list_for_each_entry_safe(worker, tmp, cull_list, entry) { + list_del_init(&worker->entry); + unbind_worker(worker); + /* + * If the worker was somehow already running, then it had to be + * in pool->idle_list when set_worker_dying() happened or we + * wouldn't have gotten here. + * + * Thus, the worker must either have observed the WORKER_DIE + * flag, or have set its state to TASK_IDLE. Either way, the + * below will be observed by the worker and is safe to do + * outside of pool->lock. + */ + wake_up_process(worker->task); + } +} + /** - * destroy_worker - destroy a workqueue worker + * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed + * @list: transfer worker away from its pool->idle_list and into list * - * Destroy @worker and adjust @pool stats accordingly. The worker should - * be idle. + * Tag @worker for destruction and adjust @pool stats accordingly. The worker + * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ -static void destroy_worker(struct worker *worker) +static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); + lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || @@ -1997,34 +2038,94 @@ static void destroy_worker(struct worker *worker) pool->nr_workers--; pool->nr_idle--; - list_del_init(&worker->entry); worker->flags |= WORKER_DIE; - wake_up_process(worker->task); + + list_move(&worker->entry, list); + list_move(&worker->node, &pool->dying_workers); } +/** + * idle_worker_timeout - check if some idle workers can now be deleted. + * @t: The pool's idle_timer that just expired + * + * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in + * worker_leave_idle(), as a worker flicking between idle and active while its + * pool is at the too_many_workers() tipping point would cause too much timer + * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let + * it expire and re-evaluate things from there. + */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); + bool do_cull = false; + + if (work_pending(&pool->idle_cull_work)) + return; raw_spin_lock_irq(&pool->lock); - while (too_many_workers(pool)) { + if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_entry(pool->idle_list.prev, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; + do_cull = !time_before(jiffies, expires); + + if (!do_cull) + mod_timer(&pool->idle_timer, expires); + } + raw_spin_unlock_irq(&pool->lock); + + if (do_cull) + queue_work(system_unbound_wq, &pool->idle_cull_work); +} + +/** + * idle_cull_fn - cull workers that have been idle for too long. + * @work: the pool's work for handling these idle workers + * + * This goes through a pool's idle workers and gets rid of those that have been + * idle for at least IDLE_WORKER_TIMEOUT seconds. + * + * We don't want to disturb isolated CPUs because of a pcpu kworker being + * culled, so this also resets worker affinity. This requires a sleepable + * context, hence the split between timer callback and work item. + */ +static void idle_cull_fn(struct work_struct *work) +{ + struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); + struct list_head cull_list; + + INIT_LIST_HEAD(&cull_list); + /* + * Grabbing wq_pool_attach_mutex here ensures an already-running worker + * cannot proceed beyong worker_detach_from_pool() in its self-destruct + * path. This is required as a previously-preempted worker could run after + * set_worker_dying() has happened but before wake_dying_workers() did. + */ + mutex_lock(&wq_pool_attach_mutex); + raw_spin_lock_irq(&pool->lock); + + while (too_many_workers(pool)) { + struct worker *worker; + unsigned long expires; + + worker = list_entry(pool->idle_list.prev, struct worker, entry); + expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } - destroy_worker(worker); + set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); + wake_dying_workers(&cull_list); + mutex_unlock(&wq_pool_attach_mutex); } static void send_mayday(struct work_struct *work) @@ -2388,12 +2489,12 @@ woke_up: /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); - WARN_ON_ONCE(!list_empty(&worker->entry)); set_pf_worker(false); set_task_comm(worker->task, "kworker/dying"); ida_free(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); + WARN_ON_ONCE(!list_empty(&worker->entry)); kfree(worker); return 0; } @@ -3462,10 +3563,12 @@ static int init_worker_pool(struct worker_pool *pool) hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); + INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); + INIT_LIST_HEAD(&pool->dying_workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); @@ -3540,18 +3643,6 @@ static void rcu_free_pool(struct rcu_head *rcu) kfree(pool); } -/* This returns with the lock held on success (pool manager is inactive). */ -static bool wq_manager_inactive(struct worker_pool *pool) -{ - raw_spin_lock_irq(&pool->lock); - - if (pool->flags & POOL_MANAGER_ACTIVE) { - raw_spin_unlock_irq(&pool->lock); - return false; - } - return true; -} - /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put @@ -3566,8 +3657,11 @@ static bool wq_manager_inactive(struct worker_pool *pool) static void put_unbound_pool(struct worker_pool *pool) { DECLARE_COMPLETION_ONSTACK(detach_completion); + struct list_head cull_list; struct worker *worker; + INIT_LIST_HEAD(&cull_list); + lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) @@ -3587,20 +3681,38 @@ static void put_unbound_pool(struct worker_pool *pool) * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. - * Because of how wq_manager_inactive() works, we will hold the - * spinlock after a successful wait. + * + * Having a concurrent manager is quite unlikely to happen as we can + * only get here with + * pwq->refcnt == pool->refcnt == 0 + * which implies no work queued to the pool, which implies no worker can + * become the manager. However a worker could have taken the role of + * manager before the refcnts dropped to 0, since maybe_create_worker() + * drops pool->lock */ - rcuwait_wait_event(&manager_wait, wq_manager_inactive(pool), - TASK_UNINTERRUPTIBLE); - pool->flags |= POOL_MANAGER_ACTIVE; + while (true) { + rcuwait_wait_event(&manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), + TASK_UNINTERRUPTIBLE); + + mutex_lock(&wq_pool_attach_mutex); + raw_spin_lock_irq(&pool->lock); + if (!(pool->flags & POOL_MANAGER_ACTIVE)) { + pool->flags |= POOL_MANAGER_ACTIVE; + break; + } + raw_spin_unlock_irq(&pool->lock); + mutex_unlock(&wq_pool_attach_mutex); + } while ((worker = first_idle_worker(pool))) - destroy_worker(worker); + set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); - mutex_lock(&wq_pool_attach_mutex); - if (!list_empty(&pool->workers)) + wake_dying_workers(&cull_list); + + if (!list_empty(&pool->workers) || !list_empty(&pool->dying_workers)) pool->detach_completion = &detach_completion; mutex_unlock(&wq_pool_attach_mutex); @@ -3609,6 +3721,7 @@ static void put_unbound_pool(struct worker_pool *pool) /* shut down the timers */ del_timer_sync(&pool->idle_timer); + cancel_work_sync(&pool->idle_cull_work); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ @@ -3952,7 +4065,8 @@ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, - const struct workqueue_attrs *attrs) + const struct workqueue_attrs *attrs, + const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs, *tmp_attrs; @@ -3968,14 +4082,15 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, goto out_free; /* - * Calculate the attrs of the default pwq. + * Calculate the attrs of the default pwq with unbound_cpumask + * which is wq_unbound_cpumask or to set to wq_unbound_cpumask. * If the user configured cpumask doesn't overlap with the * wq_unbound_cpumask, we fallback to the wq_unbound_cpumask. */ copy_workqueue_attrs(new_attrs, attrs); - cpumask_and(new_attrs->cpumask, new_attrs->cpumask, wq_unbound_cpumask); + cpumask_and(new_attrs->cpumask, new_attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(new_attrs->cpumask))) - cpumask_copy(new_attrs->cpumask, wq_unbound_cpumask); + cpumask_copy(new_attrs->cpumask, unbound_cpumask); /* * We may create multiple pwqs with differing cpumasks. Make a @@ -4072,7 +4187,7 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, wq->flags &= ~__WQ_ORDERED; } - ctx = apply_wqattrs_prepare(wq, attrs); + ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (!ctx) return -ENOMEM; @@ -4414,6 +4529,11 @@ void destroy_workqueue(struct workqueue_struct *wq) */ workqueue_sysfs_unregister(wq); + /* mark the workqueue destruction is in progress */ + mutex_lock(&wq->mutex); + wq->flags |= __WQ_DESTROYING; + mutex_unlock(&wq->mutex); + /* drain it before proceeding with destruction */ drain_workqueue(wq); @@ -4709,22 +4829,53 @@ static void pr_cont_pool_info(struct worker_pool *pool) pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); } -static void pr_cont_work(bool comma, struct work_struct *work) +struct pr_cont_work_struct { + bool comma; + work_func_t func; + long ctr; +}; + +static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) +{ + if (!pcwsp->ctr) + goto out_record; + if (func == pcwsp->func) { + pcwsp->ctr++; + return; + } + if (pcwsp->ctr == 1) + pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); + else + pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); + pcwsp->ctr = 0; +out_record: + if ((long)func == -1L) + return; + pcwsp->comma = comma; + pcwsp->func = func; + pcwsp->ctr = 1; +} + +static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); + pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { - pr_cont("%s %ps", comma ? "," : "", work->func); + if (!comma) + pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); + pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { + struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; @@ -4757,7 +4908,8 @@ static void show_pwq(struct pool_workqueue *pwq) worker->rescue_wq ? "(RESCUER)" : "", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) - pr_cont_work(false, work); + pr_cont_work(false, work, &pcws); + pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); @@ -4777,9 +4929,10 @@ static void show_pwq(struct pool_workqueue *pwq) if (get_work_pwq(work) != pwq) continue; - pr_cont_work(comma, work); + pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } + pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } @@ -4788,9 +4941,10 @@ static void show_pwq(struct pool_workqueue *pwq) pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { - pr_cont_work(comma, work); + pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } + pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } @@ -5006,13 +5160,8 @@ static void unbind_workers(int cpu) raw_spin_unlock_irq(&pool->lock); - for_each_pool_worker(worker, pool) { - kthread_set_per_cpu(worker->task, -1); - if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); - else - WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); - } + for_each_pool_worker(worker, pool) + unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } @@ -5334,7 +5483,7 @@ out_unlock: } #endif /* CONFIG_FREEZER */ -static int workqueue_apply_unbound_cpumask(void) +static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; @@ -5350,7 +5499,7 @@ static int workqueue_apply_unbound_cpumask(void) if (wq->flags & __WQ_ORDERED) continue; - ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs); + ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (!ctx) { ret = -ENOMEM; break; @@ -5365,6 +5514,11 @@ static int workqueue_apply_unbound_cpumask(void) apply_wqattrs_cleanup(ctx); } + if (!ret) { + mutex_lock(&wq_pool_attach_mutex); + cpumask_copy(wq_unbound_cpumask, unbound_cpumask); + mutex_unlock(&wq_pool_attach_mutex); + } return ret; } @@ -5383,7 +5537,6 @@ static int workqueue_apply_unbound_cpumask(void) int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; - cpumask_var_t saved_cpumask; /* * Not excluding isolated cpus on purpose. @@ -5397,23 +5550,8 @@ int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) goto out_unlock; } - if (!zalloc_cpumask_var(&saved_cpumask, GFP_KERNEL)) { - ret = -ENOMEM; - goto out_unlock; - } - - /* save the old wq_unbound_cpumask. */ - cpumask_copy(saved_cpumask, wq_unbound_cpumask); - - /* update wq_unbound_cpumask at first and apply it to wqs. */ - cpumask_copy(wq_unbound_cpumask, cpumask); - ret = workqueue_apply_unbound_cpumask(); - - /* restore the wq_unbound_cpumask when failed. */ - if (ret < 0) - cpumask_copy(wq_unbound_cpumask, saved_cpumask); + ret = workqueue_apply_unbound_cpumask(cpumask); - free_cpumask_var(saved_cpumask); out_unlock: apply_wqattrs_unlock(); } |