diff options
Diffstat (limited to 'kernel')
37 files changed, 1791 insertions, 491 deletions
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 546113430049..e88abc0865d5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -27,129 +27,407 @@ void cgroup_bpf_put(struct cgroup *cgrp) { unsigned int type; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) { - struct bpf_prog *prog = cgrp->bpf.prog[type]; - - if (prog) { - bpf_prog_put(prog); + for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog_list *pl, *tmp; + + list_for_each_entry_safe(pl, tmp, progs, node) { + list_del(&pl->node); + bpf_prog_put(pl->prog); + kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } + bpf_prog_array_free(cgrp->bpf.effective[type]); + } +} + +/* count number of elements in the list. + * it's slow but the list cannot be long + */ +static u32 prog_list_length(struct list_head *head) +{ + struct bpf_prog_list *pl; + u32 cnt = 0; + + list_for_each_entry(pl, head, node) { + if (!pl->prog) + continue; + cnt++; } + return cnt; +} + +/* if parent has non-overridable prog attached, + * disallow attaching new programs to the descendent cgroup. + * if parent has overridable or multi-prog, allow attaching + */ +static bool hierarchy_allows_attach(struct cgroup *cgrp, + enum bpf_attach_type type, + u32 new_flags) +{ + struct cgroup *p; + + p = cgroup_parent(cgrp); + if (!p) + return true; + do { + u32 flags = p->bpf.flags[type]; + u32 cnt; + + if (flags & BPF_F_ALLOW_MULTI) + return true; + cnt = prog_list_length(&p->bpf.progs[type]); + WARN_ON_ONCE(cnt > 1); + if (cnt == 1) + return !!(flags & BPF_F_ALLOW_OVERRIDE); + p = cgroup_parent(p); + } while (p); + return true; +} + +/* compute a chain of effective programs for a given cgroup: + * start from the list of programs in this cgroup and add + * all parent programs. + * Note that parent's F_ALLOW_OVERRIDE-type program is yielding + * to programs in this cgroup + */ +static int compute_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu **array) +{ + struct bpf_prog_array __rcu *progs; + struct bpf_prog_list *pl; + struct cgroup *p = cgrp; + int cnt = 0; + + /* count number of effective programs by walking parents */ + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[type]); + p = cgroup_parent(p); + } while (p); + + progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!progs) + return -ENOMEM; + + /* populate the array with effective progs */ + cnt = 0; + p = cgrp; + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + list_for_each_entry(pl, + &p->bpf.progs[type], node) { + if (!pl->prog) + continue; + rcu_dereference_protected(progs, 1)-> + progs[cnt++] = pl->prog; + } + p = cgroup_parent(p); + } while (p); + + *array = progs; + return 0; +} + +static void activate_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu *array) +{ + struct bpf_prog_array __rcu *old_array; + + old_array = xchg(&cgrp->bpf.effective[type], array); + /* free prog array after grace period, since __cgroup_bpf_run_*() + * might be still walking the array + */ + bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify - * @parent: the parent to inherit from */ -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) +int cgroup_bpf_inherit(struct cgroup *cgrp) { - unsigned int type; +/* has to use marco instead of const int, since compiler thinks + * that array below is variable length + */ +#define NR ARRAY_SIZE(cgrp->bpf.effective) + struct bpf_prog_array __rcu *arrays[NR] = {}; + int i; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) { - struct bpf_prog *e; + for (i = 0; i < NR; i++) + INIT_LIST_HEAD(&cgrp->bpf.progs[i]); - e = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - rcu_assign_pointer(cgrp->bpf.effective[type], e); - cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; - } + for (i = 0; i < NR; i++) + if (compute_effective_progs(cgrp, i, &arrays[i])) + goto cleanup; + + for (i = 0; i < NR; i++) + activate_effective_progs(cgrp, i, arrays[i]); + + return 0; +cleanup: + for (i = 0; i < NR; i++) + bpf_prog_array_free(arrays[i]); + return -ENOMEM; } +#define BPF_CGROUP_MAX_PROGS 64 + /** - * __cgroup_bpf_update() - Update the pinned program of a cgroup, and + * __cgroup_bpf_attach() - Attach the program to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse - * @parent: The parent of @cgrp, or %NULL if @cgrp is the root - * @prog: A new program to pin - * @type: Type of pinning operation (ingress/egress) - * - * Each cgroup has a set of two pointers for bpf programs; one for eBPF - * programs it owns, and which is effective for execution. - * - * If @prog is not %NULL, this function attaches a new program to the cgroup - * and releases the one that is currently attached, if any. @prog is then made - * the effective program of type @type in that cgroup. - * - * If @prog is %NULL, the currently attached program of type @type is released, - * and the effective program of the parent cgroup (if any) is inherited to - * @cgrp. - * - * Then, the descendants of @cgrp are walked and the effective program for - * each of them is set to the effective program of @cgrp unless the - * descendant has its own program attached, in which case the subbranch is - * skipped. This ensures that delegated subcgroups with own programs are left - * untouched. + * @prog: A program to attach + * @type: Type of attach operation * * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool new_overridable) +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct bpf_prog *old_prog, *effective = NULL; - struct cgroup_subsys_state *pos; - bool overridable = true; - - if (parent) { - overridable = !parent->bpf.disallow_override[type]; - effective = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - } - - if (prog && effective && !overridable) - /* if parent has non-overridable prog attached, disallow - * attaching new programs to descendent cgroup - */ + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + bool pl_was_allocated; + u32 old_flags; + int err; + + if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + /* invalid combination */ + return -EINVAL; + + if (!hierarchy_allows_attach(cgrp, type, flags)) return -EPERM; - if (prog && effective && overridable != new_overridable) - /* if parent has overridable prog attached, only - * allow overridable programs in descendent cgroup + if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + /* Disallow attaching non-overridable on top + * of existing overridable in this cgroup. + * Disallow attaching multi-prog if overridable or none */ return -EPERM; - old_prog = cgrp->bpf.prog[type]; - - if (prog) { - overridable = new_overridable; - effective = prog; - if (old_prog && - cgrp->bpf.disallow_override[type] == new_overridable) - /* disallow attaching non-overridable on top - * of existing overridable in this cgroup - * and vice versa - */ - return -EPERM; + if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + return -E2BIG; + + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + pl->prog = prog; + list_add_tail(&pl->node, progs); + } else { + if (list_empty(progs)) { + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + list_add_tail(&pl->node, progs); + } else { + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl_was_allocated = false; + } + pl->prog = prog; } - if (!prog && !old_prog) - /* report error when trying to detach and nothing is attached */ - return -ENOENT; - - cgrp->bpf.prog[type] = prog; + old_flags = cgrp->bpf.flags[type]; + cgrp->bpf.flags[type] = flags; - css_for_each_descendant_pre(pos, &cgrp->self) { - struct cgroup *desc = container_of(pos, struct cgroup, self); + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); - /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) { - pos = css_rightmost_descendant(pos); - } else { - rcu_assign_pointer(desc->bpf.effective[type], - effective); - desc->bpf.disallow_override[type] = !overridable; - } + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; } - if (prog) - static_branch_inc(&cgroup_bpf_enabled_key); + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + static_branch_inc(&cgroup_bpf_enabled_key); if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and cleanup the prog list */ + pl->prog = old_prog; + if (pl_was_allocated) { + list_del(&pl->node); + kfree(pl); + } + return err; +} + +/** + * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * propagate the change to descendants + * @cgrp: The cgroup which descendants to traverse + * @prog: A program to detach or NULL + * @type: Type of detach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 unused_flags) +{ + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + int err; + + if (flags & BPF_F_ALLOW_MULTI) { + if (!prog) + /* to detach MULTI prog the user has to specify valid FD + * of the program to be detached + */ + return -EINVAL; + } else { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + } + + if (flags & BPF_F_ALLOW_MULTI) { + /* find the prog and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog != prog) + continue; + old_prog = prog; + /* mark it deleted, so it's ignored while + * recomputing effective + */ + pl->prog = NULL; + break; + } + if (!old_prog) + return -ENOENT; + } else { + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) + */ + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl->prog = NULL; + } + + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; + } + + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* now can actually delete it from this cgroup list */ + list_del(&pl->node); + kfree(pl); + if (list_empty(progs)) + /* last program was detached, reset flags to zero */ + cgrp->bpf.flags[type] = 0; + + bpf_prog_put(old_prog); + static_branch_dec(&cgroup_bpf_enabled_key); + return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and restore back old_prog */ + pl->prog = old_prog; + return err; +} + +/* Must be called with cgroup_mutex held to avoid races. */ +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + enum bpf_attach_type type = attr->query.attach_type; + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + int cnt, ret = 0, i; + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) + cnt = bpf_prog_array_length(cgrp->bpf.effective[type]); + else + cnt = prog_list_length(progs); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + return -EFAULT; + if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + /* return early if user requested only program count + flags */ + return 0; + if (attr->query.prog_cnt < cnt) { + cnt = attr->query.prog_cnt; + ret = -ENOSPC; + } + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type], + prog_ids, cnt); + } else { + struct bpf_prog_list *pl; + u32 id; + + i = 0; + list_for_each_entry(pl, progs, node) { + id = pl->prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + } + return ret; } /** @@ -171,36 +449,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type) { - struct bpf_prog *prog; + unsigned int offset = skb->data - skb_network_header(skb); + struct sock *save_sk; struct cgroup *cgrp; - int ret = 0; + int ret; if (!sk || !sk_fullsock(sk)) return 0; - if (sk->sk_family != AF_INET && - sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) { - unsigned int offset = skb->data - skb_network_header(skb); - struct sock *save_sk = skb->sk; - - skb->sk = sk; - __skb_push(skb, offset); - ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM; - __skb_pull(skb, offset); - skb->sk = save_sk; - } - - rcu_read_unlock(); - - return ret; + save_sk = skb->sk; + skb->sk = sk; + __skb_push(skb, offset); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, + bpf_prog_run_save_cb); + __skb_pull(skb, offset); + skb->sk = save_sk; + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); @@ -221,19 +489,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); + int ret; - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -258,18 +517,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); + int ret; - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); - - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, + BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..c6be15ae83ee 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1022,7 +1022,7 @@ select_insn: struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2; struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_prog *prog; - u64 index = BPF_R3; + u32 index = BPF_R3; if (unlikely(index >= array->map.max_entries)) goto out; @@ -1381,6 +1381,75 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +static struct { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +} empty_prog_array = { + .null_prog = NULL, +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +{ + if (prog_cnt) + return kzalloc(sizeof(struct bpf_prog_array) + + sizeof(struct bpf_prog *) * (prog_cnt + 1), + flags); + + return &empty_prog_array.hdr; +} + +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) +{ + if (!progs || + progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + return; + kfree_rcu(progs, rcu); +} + +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) +{ + struct bpf_prog **prog; + u32 cnt = 0; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) + cnt++; + rcu_read_unlock(); + return cnt; +} + +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt) +{ + struct bpf_prog **prog; + u32 i = 0, id; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) { + id = (*prog)->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) { + rcu_read_unlock(); + return -EFAULT; + } + if (++i == cnt) { + prog++; + break; + } + } + rcu_read_unlock(); + if (*prog) + return -ENOSPC; + return 0; +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 959c9a07f318..e093d9a2c4dd 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -75,8 +75,8 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr) static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; + int err = -EINVAL; u64 cost; - int err; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -108,6 +108,8 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (err) goto free_dtab; + err = -ENOMEM; + /* A per cpu bitfield with a bit per possible net device */ dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr), __alignof__(unsigned long)); @@ -128,7 +130,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) free_dtab: free_percpu(dtab->flush_needed); kfree(dtab); - return ERR_PTR(-ENOMEM); + return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b767844a76f..34d8a690ea05 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -389,10 +389,99 @@ out: return ret; } -static int trie_delete_elem(struct bpf_map *map, void *key) +/* Called from syscall or from eBPF program */ +static int trie_delete_elem(struct bpf_map *map, void *_key) { - /* TODO */ - return -ENOSYS; + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct bpf_lpm_trie_key *key = _key; + struct lpm_trie_node __rcu **trim, **trim2; + struct lpm_trie_node *node, *parent; + unsigned long irq_flags; + unsigned int next_bit; + size_t matchlen = 0; + int ret = 0; + + if (key->prefixlen > trie->max_prefixlen) + return -EINVAL; + + raw_spin_lock_irqsave(&trie->lock, irq_flags); + + /* Walk the tree looking for an exact key/length match and keeping + * track of the path we traverse. We will need to know the node + * we wish to delete, and the slot that points to the node we want + * to delete. We may also need to know the nodes parent and the + * slot that contains it. + */ + trim = &trie->root; + trim2 = trim; + parent = NULL; + while ((node = rcu_dereference_protected( + *trim, lockdep_is_held(&trie->lock)))) { + matchlen = longest_prefix_match(trie, node, key); + + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen) + break; + + parent = node; + trim2 = trim; + next_bit = extract_bit(key->data, node->prefixlen); + trim = &node->child[next_bit]; + } + + if (!node || node->prefixlen != key->prefixlen || + (node->flags & LPM_TREE_NODE_FLAG_IM)) { + ret = -ENOENT; + goto out; + } + + trie->n_entries--; + + /* If the node we are removing has two children, simply mark it + * as intermediate and we are done. + */ + if (rcu_access_pointer(node->child[0]) && + rcu_access_pointer(node->child[1])) { + node->flags |= LPM_TREE_NODE_FLAG_IM; + goto out; + } + + /* If the parent of the node we are about to delete is an intermediate + * node, and the deleted node doesn't have any children, we can delete + * the intermediate parent as well and promote its other child + * up the tree. Doing this maintains the invariant that all + * intermediate nodes have exactly 2 children and that there are no + * unnecessary intermediate nodes in the tree. + */ + if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && + !node->child[0] && !node->child[1]) { + if (node == rcu_access_pointer(parent->child[0])) + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[1])); + else + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[0])); + kfree_rcu(parent, rcu); + kfree_rcu(node, rcu); + goto out; + } + + /* The node we are removing has either zero or one child. If there + * is a child, move it into the removed node's slot then delete + * the node. Otherwise just clear the slot and delete the node. + */ + if (node->child[0]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); + else if (node->child[1]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); + else + RCU_INIT_POINTER(*trim, NULL); + kfree_rcu(node, rcu); + +out: + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + + return ret; } #define LPM_DATA_SIZE_MAX 256 diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e4969..a298d6666698 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -102,7 +102,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) skb_orphan(skb); skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; @@ -369,7 +369,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index cb17e1cd1d43..0048cb24ba7b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,9 @@ #include <linux/version.h> #include <linux/kernel.h> #include <linux/idr.h> +#include <linux/cred.h> +#include <linux/timekeeping.h> +#include <linux/ctype.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -186,15 +189,17 @@ static int bpf_map_alloc_id(struct bpf_map *map) static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) { + unsigned long flags; + if (do_idr_lock) - spin_lock_bh(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); else __acquire(&map_idr_lock); idr_remove(&map_idr, map->id); if (do_idr_lock) - spin_unlock_bh(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); else __release(&map_idr_lock); } @@ -310,7 +315,31 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL -#define BPF_MAP_CREATE_LAST_FIELD numa_node +/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. + * Return 0 on success and < 0 on error. + */ +static int bpf_obj_name_cpy(char *dst, const char *src) +{ + const char *end = src + BPF_OBJ_NAME_LEN; + + /* Copy all isalnum() and '_' char */ + while (src < end && *src) { + if (!isalnum(*src) && *src != '_') + return -EINVAL; + *dst++ = *src++; + } + + /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ + if (src == end) + return -EINVAL; + + /* '\0' terminates dst */ + *dst = 0; + + return 0; +} + +#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -332,6 +361,10 @@ static int map_create(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + err = bpf_obj_name_cpy(map->name, attr->map_name); + if (err) + goto free_map_nouncharge; + atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); @@ -971,7 +1004,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_flags +#define BPF_PROG_LOAD_LAST_FIELD prog_name static int bpf_prog_load(union bpf_attr *attr) { @@ -1035,6 +1068,11 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_prog; + prog->aux->load_time = ktime_get_boot_ns(); + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); + if (err) + goto free_prog; + /* run eBPF verifier */ err = bpf_check(&prog, attr); if (err < 0) @@ -1130,6 +1168,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach) return 0; } +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; @@ -1143,7 +1184,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) return -EINVAL; switch (attr->attach_type) { @@ -1174,8 +1215,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, - attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); if (ret) bpf_prog_put(prog); cgroup_put(cgrp); @@ -1187,6 +1228,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; + struct bpf_prog *prog; struct cgroup *cgrp; int ret; @@ -1199,26 +1242,67 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: + ptype = BPF_PROG_TYPE_CGROUP_SKB; + break; case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; case BPF_CGROUP_SOCK_OPS: - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); - cgroup_put(cgrp); + ptype = BPF_PROG_TYPE_SOCK_OPS; break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ret = sockmap_get_from_fd(attr, false); - break; + return sockmap_get_from_fd(attr, false); default: return -EINVAL; } + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + cgroup_put(cgrp); return ret; } +#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt + +static int bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (CHECK_ATTR(BPF_PROG_QUERY)) + return -EINVAL; + if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) + return -EINVAL; + + switch (attr->query.attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: + break; + default: + return -EINVAL; + } + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + ret = cgroup_bpf_query(cgrp, attr, uattr); + cgroup_put(cgrp); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -1356,8 +1440,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.type = prog->type; info.id = prog->aux->id; + info.load_time = prog->aux->load_time; + info.created_by_uid = from_kuid_munged(current_user_ns(), + prog->aux->user->uid); memcpy(info.tag, prog->tag, sizeof(prog->tag)); + memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + + ulen = info.nr_map_ids; + info.nr_map_ids = prog->aux->used_map_cnt; + ulen = min_t(u32, info.nr_map_ids, ulen); + if (ulen) { + u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); + u32 i; + + for (i = 0; i < ulen; i++) + if (put_user(prog->aux->used_maps[i]->id, + &user_map_ids[i])) + return -EFAULT; + } if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; @@ -1411,6 +1512,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + memcpy(info.name, map->name, sizeof(map->name)); if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -1497,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; + case BPF_PROG_QUERY: + err = bpf_prog_query(&attr, uattr); + break; #endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 799b2451ef2d..52b022310f6a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -325,26 +332,45 @@ static const char *const bpf_jmp_string[16] = { [BPF_EXIT >> 4] = "exit", }; +static void print_bpf_end_insn(const struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose("(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", + insn->imm, insn->dst_reg); +} + static void print_bpf_insn(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); if (class == BPF_ALU || class == BPF_ALU64) { - if (BPF_SRC(insn->code) == BPF_X) + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose("BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose("(%02x) r%d = %s-r%d\n", + insn->code, insn->dst_reg, + class == BPF_ALU ? "(u32) " : "", + insn->dst_reg); + } else if (BPF_SRC(insn->code) == BPF_X) { verbose("(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->src_reg); - else + } else { verbose("(%02x) %sr%d %s %s%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->imm); + } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", @@ -519,6 +545,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +753,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1099,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1179,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1225,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1365,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1398,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1407,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1432,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1459,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1475,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1648,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1658,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1926,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1986,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2476,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2539,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2547,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2912,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -2997,6 +3073,43 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static int check_return_code(struct bpf_verifier_env *env) +{ + struct bpf_reg_state *reg; + struct tnum range = tnum_range(0, 1); + + switch (env->prog->type) { + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_SOCK_OPS: + break; + default: + return 0; + } + + reg = &env->cur_state.regs[BPF_REG_0]; + if (reg->type != SCALAR_VALUE) { + verbose("At program exit the register R0 is not a known value (%s)\n", + reg_type_str[reg->type]); + return -EINVAL; + } + + if (!tnum_in(range, reg->var_off)) { + verbose("At program exit the register R0 "); + if (!tnum_is_unknown(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose("has value %s", tn_buf); + } else { + verbose("has unknown scalar value"); + } + verbose(" should have been 0 or 1\n"); + return -EINVAL; + } + return 0; +} + /* non-recursive DFS pseudo code * 1 procedure DFS-iterative(G,v): * 2 label v as discovered @@ -3298,8 +3411,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != 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 @@ -3786,6 +3900,9 @@ static int do_check(struct bpf_verifier_env *env) return -EACCES; } + err = check_return_code(env); + if (err) + return err; process_bpf_exit: insn_idx = pop_stack(env, &prev_insn_idx); if (insn_idx < 0) { @@ -4205,7 +4322,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) } if (insn->imm == BPF_FUNC_redirect_map) { - u64 addr = (unsigned long)prog; + /* Note, we cannot use prog directly as imm as subsequent + * rewrites would still change the prog pointer. The only + * stable address we can use is aux, which also works with + * prog clones during blinding. + */ + u64 addr = (unsigned long)prog->aux; struct bpf_insn r4_ld[] = { BPF_LD_IMM64(BPF_REG_4, addr), *insn, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..00f5b358aeac 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) if (ret) goto destroy_root; + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + trace_cgroup_setup_root(root); /* @@ -2311,6 +2314,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } @@ -4713,6 +4724,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_idr_free; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4747,13 +4761,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - if (parent) - cgroup_bpf_inherit(cgrp, parent); - cgroup_propagate_control(cgrp); return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5736,14 +5749,33 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable) +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_detach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) { - struct cgroup *parent = cgroup_parent(cgrp); int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); + ret = __cgroup_bpf_query(cgrp, attr, uattr); mutex_unlock(&cgroup_mutex); return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index acf5308fad51..8de11a29e495 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -46,11 +46,13 @@ * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation - * @done: Signal completion to the issuer of the task + * @done_up: Signal completion to the issuer of the task for cpu-up + * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; + enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; @@ -58,18 +60,39 @@ struct cpuhp_cpu_state { bool single; bool bringup; struct hlist_node *node; + struct hlist_node *last; enum cpuhp_state cb_state; int result; - struct completion done; + struct completion done_up; + struct completion done_down; #endif }; -static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state); +static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { + .fail = CPUHP_INVALID, +}; #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) -static struct lock_class_key cpuhp_state_key; -static struct lockdep_map cpuhp_state_lock_map = - STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key); +static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +static struct lockdep_map cpuhp_state_down_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); + + +static void inline cpuhp_lock_acquire(bool bringup) +{ + lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} + +static void inline cpuhp_lock_release(bool bringup) +{ + lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); +} +#else + +static void inline cpuhp_lock_acquire(bool bringup) { } +static void inline cpuhp_lock_release(bool bringup) { } + #endif /** @@ -123,13 +146,16 @@ static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked - * @step: The step in the state machine + * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked + * @node: For multi-instance, do a single entry callback for install/remove + * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, - bool bringup, struct hlist_node *node) + bool bringup, struct hlist_node *node, + struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); @@ -137,7 +163,17 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, int (*cb)(unsigned int cpu); int ret, cnt; + if (st->fail == state) { + st->fail = CPUHP_INVALID; + + if (!(bringup ? step->startup.single : step->teardown.single)) + return 0; + + return -EAGAIN; + } + if (!step->multi_instance) { + WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; @@ -152,6 +188,7 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* Single invocation for instance add/remove */ if (node) { + WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); @@ -161,13 +198,23 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { + if (lastp && node == *lastp) + break; + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); - if (ret) - goto err; + if (ret) { + if (!lastp) + goto err; + + *lastp = node; + return ret; + } cnt++; } + if (lastp) + *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ @@ -178,12 +225,39 @@ err: hlist_for_each(node, &step->list) { if (!cnt--) break; - cbm(cpu, node); + + trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); + ret = cbm(cpu, node); + trace_cpuhp_exit(cpu, st->state, state, ret); + /* + * Rollback must not fail, + */ + WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP +static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + wait_for_completion(done); +} + +static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) +{ + struct completion *done = bringup ? &st->done_up : &st->done_down; + complete(done); +} + +/* + * The former STARTING/DYING states, ran with IRQs disabled and must not fail. + */ +static bool cpuhp_is_atomic_state(enum cpuhp_state state) +{ + return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; +} + /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; @@ -271,14 +345,79 @@ void cpu_hotplug_enable(void) EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #endif /* CONFIG_HOTPLUG_CPU */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st); +static inline enum cpuhp_state +cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + + st->rollback = false; + st->last = NULL; + + st->target = target; + st->single = false; + st->bringup = st->state < target; + + return prev_state; +} + +static inline void +cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) +{ + st->rollback = true; + + /* + * If we have st->last we need to undo partial multi_instance of this + * state first. Otherwise start undo at the previous state. + */ + if (!st->last) { + if (st->bringup) + st->state--; + else + st->state++; + } + + st->target = prev_state; + st->bringup = !st->bringup; +} + +/* Regular hotplug invocation of the AP hotplug thread */ +static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) +{ + if (!st->single && st->state == st->target) + return; + + st->result = 0; + /* + * Make sure the above stores are visible before should_run becomes + * true. Paired with the mb() above in cpuhp_thread_fun() + */ + smp_mb(); + st->should_run = true; + wake_up_process(st->thread); + wait_for_ap_thread(st, st->bringup); +} + +static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) +{ + enum cpuhp_state prev_state; + int ret; + + prev_state = cpuhp_set_state(st, target); + __cpuhp_kick_ap(st); + if ((ret = st->result)) { + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); + } + + return ret; +} static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; @@ -286,12 +425,10 @@ static int bringup_wait_for_ap(unsigned int cpu) stop_machine_unpark(cpu); kthread_unpark(st->thread); - /* Should we go further up ? */ - if (st->target > CPUHP_AP_ONLINE_IDLE) { - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - } - return st->result; + if (st->target <= CPUHP_AP_ONLINE_IDLE) + return 0; + + return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) @@ -317,32 +454,6 @@ static int bringup_cpu(unsigned int cpu) /* * Hotplug state machine related functions */ -static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL); - } -} - -static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, - enum cpuhp_state target) -{ - enum cpuhp_state prev_state = st->state; - int ret = 0; - - for (; st->state > target; st->state--) { - ret = cpuhp_invoke_callback(cpu, st->state, false, NULL); - if (ret) { - st->target = prev_state; - undo_cpu_down(cpu, st); - break; - } - } - return ret; -} static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { @@ -350,7 +461,7 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) struct cpuhp_step *step = cpuhp_get_step(st->state); if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } } @@ -362,7 +473,7 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, while (st->state < target) { st->state++; - ret = cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { st->target = prev_state; undo_cpu_up(cpu, st); @@ -379,7 +490,8 @@ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - init_completion(&st->done); + init_completion(&st->done_up); + init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) @@ -389,69 +501,90 @@ static int cpuhp_should_run(unsigned int cpu) return st->should_run; } -/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */ -static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU); - - return cpuhp_down_callbacks(cpu, st, target); -} - -/* Execute the online startup callbacks. Used to be CPU_ONLINE */ -static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st) -{ - return cpuhp_up_callbacks(cpu, st, st->target); -} - /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. + * + * Each invocation of this function by the smpboot thread does a single AP + * state callback. + * + * It has 3 modes of operation: + * - single: runs st->cb_state + * - up: runs ++st->state, while st->state < st->target + * - down: runs st->state--, while st->state > st->target + * + * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); - int ret = 0; + bool bringup = st->bringup; + enum cpuhp_state state; /* - * Paired with the mb() in cpuhp_kick_ap_work and - * cpuhp_invoke_ap_callback, so the work set is consistent visible. + * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures + * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (!st->should_run) + + if (WARN_ON_ONCE(!st->should_run)) return; - st->should_run = false; + cpuhp_lock_acquire(bringup); - lock_map_acquire(&cpuhp_state_lock_map); - /* Single callback invocation for [un]install ? */ if (st->single) { - if (st->cb_state < CPUHP_AP_ONLINE) { - local_irq_disable(); - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); - local_irq_enable(); + state = st->cb_state; + st->should_run = false; + } else { + if (bringup) { + st->state++; + state = st->state; + st->should_run = (st->state < st->target); + WARN_ON_ONCE(st->state > st->target); } else { - ret = cpuhp_invoke_callback(cpu, st->cb_state, - st->bringup, st->node); + state = st->state; + st->state--; + st->should_run = (st->state > st->target); + WARN_ON_ONCE(st->state < st->target); } - } else if (st->rollback) { - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); + } + + WARN_ON_ONCE(!cpuhp_is_ap_state(state)); - undo_cpu_down(cpu, st); - st->rollback = false; + if (st->rollback) { + struct cpuhp_step *step = cpuhp_get_step(state); + if (step->skip_onerr) + goto next; + } + + if (cpuhp_is_atomic_state(state)) { + local_irq_disable(); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + local_irq_enable(); + + /* + * STARTING/DYING must not fail! + */ + WARN_ON_ONCE(st->result); } else { - /* Cannot happen .... */ - BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE); - - /* Regular hotplug work */ - if (st->state < st->target) - ret = cpuhp_ap_online(cpu, st); - else if (st->state > st->target) - ret = cpuhp_ap_offline(cpu, st); + st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); + } + + if (st->result) { + /* + * If we fail on a rollback, we're up a creek without no + * paddle, no way forward, no way back. We loose, thanks for + * playing. + */ + WARN_ON_ONCE(st->rollback); + st->should_run = false; } - lock_map_release(&cpuhp_state_lock_map); - st->result = ret; - complete(&st->done); + +next: + cpuhp_lock_release(bringup); + + if (!st->should_run) + complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ @@ -460,62 +593,64 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int ret; if (!cpu_online(cpu)) return 0; - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) - return cpuhp_invoke_callback(cpu, state, bringup, node); + return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); + st->rollback = false; + st->last = NULL; + + st->node = node; + st->bringup = bringup; st->cb_state = state; st->single = true; - st->bringup = bringup; - st->node = node; - /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() - */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); - wait_for_completion(&st->done); - return st->result; -} + __cpuhp_kick_ap(st); -/* Regular hotplug invocation of the AP hotplug thread */ -static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st) -{ - st->result = 0; - st->single = false; /* - * Make sure the above stores are visible before should_run becomes - * true. Paired with the mb() above in cpuhp_thread_fun() + * If we failed and did a partial, do a rollback. */ - smp_mb(); - st->should_run = true; - wake_up_process(st->thread); + if ((ret = st->result) && st->last) { + st->rollback = true; + st->bringup = !bringup; + + __cpuhp_kick_ap(st); + } + + return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); - enum cpuhp_state state = st->state; + enum cpuhp_state prev_state = st->state; + int ret; + + cpuhp_lock_acquire(false); + cpuhp_lock_release(false); + + cpuhp_lock_acquire(true); + cpuhp_lock_release(true); + + trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); + ret = cpuhp_kick_ap(st, st->target); + trace_cpuhp_exit(cpu, st->state, prev_state, ret); - trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work); - lock_map_acquire(&cpuhp_state_lock_map); - lock_map_release(&cpuhp_state_lock_map); - __cpuhp_kick_ap_work(st); - wait_for_completion(&st->done); - trace_cpuhp_exit(cpu, st->state, state, st->result); - return st->result; + return ret; } static struct smp_hotplug_thread cpuhp_threads = { @@ -581,6 +716,7 @@ static int take_cpu_down(void *_param) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); + int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); @@ -594,8 +730,13 @@ static int take_cpu_down(void *_param) WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ - for (; st->state > target; st->state--) - cpuhp_invoke_callback(cpu, st->state, false, NULL); + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + /* + * DYING must not fail! + */ + WARN_ON_ONCE(ret); + } /* Give up timekeeping duties */ tick_handover_do_timer(); @@ -639,7 +780,7 @@ static int takedown_cpu(unsigned int cpu) * * Wait for the stop thread to go away. */ - wait_for_completion(&st->done); + wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ @@ -658,7 +799,7 @@ static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; - complete(&st->done); + complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) @@ -676,11 +817,32 @@ void cpuhp_report_idle_dead(void) cpuhp_complete_idle_dead, st, 0); } -#else -#define takedown_cpu NULL -#endif +static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) +{ + for (st->state++; st->state < st->target; st->state++) { + struct cpuhp_step *step = cpuhp_get_step(st->state); -#ifdef CONFIG_HOTPLUG_CPU + if (!step->skip_onerr) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + } +} + +static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, + enum cpuhp_state target) +{ + enum cpuhp_state prev_state = st->state; + int ret = 0; + + for (; st->state > target; st->state--) { + ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); + if (ret) { + st->target = prev_state; + undo_cpu_down(cpu, st); + break; + } + } + return ret; +} /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, @@ -699,13 +861,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, cpuhp_tasks_frozen = tasks_frozen; - prev_state = st->state; - st->target = target; + prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { + st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just @@ -720,6 +882,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; + + st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need @@ -727,9 +891,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { - st->target = prev_state; - st->rollback = true; - cpuhp_kick_ap_work(cpu); + cpuhp_reset_state(st, prev_state); + __cpuhp_kick_ap(st); } out: @@ -754,11 +917,15 @@ out: cpu_maps_update_done(); return err; } + int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); + +#else +#define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** @@ -772,11 +939,16 @@ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); + int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ while (st->state < target) { st->state++; - cpuhp_invoke_callback(cpu, st->state, true, NULL); + ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); + /* + * STARTING must not fail! + */ + WARN_ON_ONCE(ret); } } @@ -794,7 +966,7 @@ void cpuhp_online_idle(enum cpuhp_state state) return; st->state = CPUHP_AP_ONLINE_IDLE; - complete(&st->done); + complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ @@ -829,7 +1001,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) cpuhp_tasks_frozen = tasks_frozen; - st->target = target; + cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. @@ -1296,6 +1468,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct cpuhp_step *sp = cpuhp_get_step(state); int ret; + /* + * If there's nothing to do, we done. + * Relies on the union for multi_instance. + */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; @@ -1307,9 +1483,9 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else - ret = cpuhp_invoke_callback(cpu, state, bringup, node); + ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; @@ -1641,9 +1817,55 @@ static ssize_t show_cpuhp_target(struct device *dev, } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); + +static ssize_t write_cpuhp_fail(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + struct cpuhp_step *sp; + int fail, ret; + + ret = kstrtoint(buf, 10, &fail); + if (ret) + return ret; + + /* + * Cannot fail STARTING/DYING callbacks. + */ + if (cpuhp_is_atomic_state(fail)) + return -EINVAL; + + /* + * Cannot fail anything that doesn't have callbacks. + */ + mutex_lock(&cpuhp_state_mutex); + sp = cpuhp_get_step(fail); + if (!sp->startup.single && !sp->teardown.single) + ret = -EINVAL; + mutex_unlock(&cpuhp_state_mutex); + if (ret) + return ret; + + st->fail = fail; + + return count; +} + +static ssize_t show_cpuhp_fail(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); + + return sprintf(buf, "%d\n", st->fail); +} + +static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); + static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, + &dev_attr_fail.attr, NULL }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 3e691b75b2db..6bc21e202ae4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8171,6 +8171,7 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) } } event->tp_event->prog = prog; + event->tp_event->bpf_prog_owner = event; return 0; } @@ -8185,7 +8186,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event) return; prog = event->tp_event->prog; - if (prog) { + if (prog && event->tp_event->bpf_prog_owner == event) { event->tp_event->prog = NULL; bpf_prog_put(prog); } diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index af71a84e12ee..f684d8e5fa2b 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -412,6 +412,19 @@ err: return NULL; } +static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb) +{ + if (rb->aux_overwrite) + return false; + + if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); + return true; + } + + return false; +} + /* * Commit the data written by hardware into the ring buffer by adjusting * aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the @@ -451,10 +464,8 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) } rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) wakeup = true; - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); - } if (wakeup) { if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED) @@ -484,9 +495,8 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) rb->aux_head += size; rb->user_page->aux_head = rb->aux_head; - if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) { + if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); - rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark); handle->wakeup = rb->aux_wakeup + rb->aux_watermark; } diff --git a/kernel/exit.c b/kernel/exit.c index 3481ababd06a..f2cd53e92147 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1600,12 +1600,10 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; + if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } @@ -1723,16 +1721,15 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (err > 0) { signo = SIGCHLD; err = 0; - } - - if (!err && uru) { - /* kernel_waitid() overwrites everything in ru */ - if (COMPAT_USE_64BIT_TIME) - err = copy_to_user(uru, &ru, sizeof(ru)); - else - err = put_compat_rusage(&ru, uru); - if (err) - return -EFAULT; + if (uru) { + /* kernel_waitid() overwrites everything in ru */ + if (COMPAT_USE_64BIT_TIME) + err = copy_to_user(uru, &ru, sizeof(ru)); + else + err = put_compat_rusage(&ru, uru); + if (err) + return -EFAULT; + } } if (!infop) diff --git a/kernel/extable.c b/kernel/extable.c index 38c2412401a1..9aa1cc41ecf7 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -102,15 +102,7 @@ int core_kernel_data(unsigned long addr) int __kernel_text_address(unsigned long addr) { - if (core_kernel_text(addr)) - return 1; - if (is_module_text_address(addr)) - return 1; - if (is_ftrace_trampoline(addr)) - return 1; - if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; - if (is_bpf_text_address(addr)) + if (kernel_text_address(addr)) return 1; /* * There might be init symbols in saved stacktraces. @@ -127,17 +119,42 @@ int __kernel_text_address(unsigned long addr) int kernel_text_address(unsigned long addr) { + bool no_rcu; + int ret = 1; + if (core_kernel_text(addr)) return 1; + + /* + * If a stack dump happens while RCU is not watching, then + * RCU needs to be notified that it requires to start + * watching again. This can happen either by tracing that + * triggers a stack trace, or a WARN() that happens during + * coming back from idle, or cpu on or offlining. + * + * is_module_text_address() as well as the kprobe slots + * and is_bpf_text_address() require RCU to be watching. + */ + no_rcu = !rcu_is_watching(); + + /* Treat this like an NMI as it can happen anywhere */ + if (no_rcu) + rcu_nmi_enter(); + if (is_module_text_address(addr)) - return 1; + goto out; if (is_ftrace_trampoline(addr)) - return 1; + goto out; if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr)) - return 1; + goto out; if (is_bpf_text_address(addr)) - return 1; - return 0; + goto out; + ret = 0; +out: + if (no_rcu) + rcu_nmi_exit(); + + return ret; } /* diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..e702cb9ffbd8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -946,6 +946,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/futex.c b/kernel/futex.c index 3d38eaf05492..0518a0bfc746 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -821,8 +821,6 @@ static void get_pi_state(struct futex_pi_state *pi_state) /* * Drops a reference to the pi_state object and frees or caches it * when the last reference is gone. - * - * Must be called with the hb lock held. */ static void put_pi_state(struct futex_pi_state *pi_state) { @@ -837,16 +835,22 @@ static void put_pi_state(struct futex_pi_state *pi_state) * and has cleaned up the pi_state already */ if (pi_state->owner) { - raw_spin_lock_irq(&pi_state->owner->pi_lock); - list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + struct task_struct *owner; - rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + owner = pi_state->owner; + if (owner) { + raw_spin_lock(&owner->pi_lock); + list_del_init(&pi_state->list); + raw_spin_unlock(&owner->pi_lock); + } + rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); } - if (current->pi_state_cache) + if (current->pi_state_cache) { kfree(pi_state); - else { + } else { /* * pi_state->list is already empty. * clear pi_state->owner. @@ -907,13 +911,14 @@ void exit_pi_state_list(struct task_struct *curr) raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); - - raw_spin_lock_irq(&curr->pi_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); + raw_spin_lock(&curr->pi_lock); /* * We dropped the pi-lock, so re-check whether this * task still owns the PI-state: */ if (head->next != next) { + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); continue; } @@ -922,9 +927,10 @@ void exit_pi_state_list(struct task_struct *curr) WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); pi_state->owner = NULL; - raw_spin_unlock_irq(&curr->pi_lock); + raw_spin_unlock(&curr->pi_lock); get_pi_state(pi_state); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); rt_mutex_futex_unlock(&pi_state->pi_mutex); @@ -1208,6 +1214,10 @@ static int attach_to_pi_owner(u32 uval, union futex_key *key, WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &p->pi_state_list); + /* + * Assignment without holding pi_state->pi_mutex.wait_lock is safe + * because there is no concurrency as the object is not published yet. + */ pi_state->owner = p; raw_spin_unlock_irq(&p->pi_lock); @@ -2878,6 +2888,7 @@ retry: raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + /* drops pi_state->pi_mutex.wait_lock */ ret = wake_futex_pi(uaddr, uval, pi_state); put_pi_state(pi_state); diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f51b7b6d2451..6fc89fd93824 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -202,7 +202,7 @@ __irq_startup_managed(struct irq_desc *desc, struct cpumask *aff, bool force) irqd_clr_managed_shutdown(d); - if (cpumask_any_and(aff, cpu_online_mask) > nr_cpu_ids) { + if (cpumask_any_and(aff, cpu_online_mask) >= nr_cpu_ids) { /* * Catch code which fiddles with enable_irq() on a managed * and potentially shutdown IRQ. Chained interrupt diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index f7086b78ad6e..5270a54b9fa4 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -322,7 +322,6 @@ int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip, /* Calc pointer to the next generic chip */ tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type); } - d->name = name; return 0; } EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index e84b7056bb08..ac4644e92b49 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -945,7 +945,7 @@ static int virq_debug_show(struct seq_file *m, void *private) struct irq_desc *desc; struct irq_domain *domain; struct radix_tree_iter iter; - void **slot; + void __rcu **slot; int i; seq_printf(m, " %-16s %-6s %-10s %-10s %s\n", @@ -1453,7 +1453,7 @@ out_free_desc: /* The irq_data was moved, fix the revmap to refer to the new location */ static void irq_domain_fix_revmap(struct irq_data *d) { - void **slot; + void __rcu **slot; if (d->hwirq < d->domain->revmap_size) return; /* Not using radix tree. */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 573dc52b0806..d00132b5c325 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1643,6 +1643,10 @@ const void *free_irq(unsigned int irq, void *dev_id) #endif action = __free_irq(irq, dev_id); + + if (!action) + return NULL; + devname = action->name; kfree(action); return devname; diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..055bb2962a0b 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 02f660666ab8..1fefe6dcafd7 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -613,6 +613,33 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) DEFINE_WAKE_Q(wake_q); /* + * __rwsem_down_write_failed_common(sem) + * rwsem_optimistic_spin(sem) + * osq_unlock(sem->osq) + * ... + * atomic_long_add_return(&sem->count) + * + * - VS - + * + * __up_write() + * if (atomic_long_sub_return_release(&sem->count) < 0) + * rwsem_wake(sem) + * osq_is_locked(&sem->osq) + * + * And __up_write() must observe !osq_is_locked() when it observes the + * atomic_long_add_return() in order to not miss a wakeup. + * + * This boils down to: + * + * [S.rel] X = 1 [RmW] r0 = (Y += 0) + * MB RMB + * [RmW] Y += 1 [L] r1 = X + * + * exists (r0=1 /\ r1=0) + */ + smp_rmb(); + + /* * If a spinner is present, it is not necessary to do the wakeup. * Try to do wakeup only if the trylock succeeds to minimize * spinlock contention which may introduce too much delay in the diff --git a/kernel/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fd..403ab9cdb949 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355..cc9108c2a1fd 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } @@ -600,7 +597,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 3e2b4f519009..ccd2d20e6b06 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -120,22 +120,26 @@ static void s2idle_loop(void) * frozen processes + suspended devices + idle processors. * Thus s2idle_enter() should be called right after * all devices have been suspended. + * + * Wakeups during the noirq suspend of devices may be spurious, + * so prevent them from terminating the loop right away. */ error = dpm_noirq_suspend_devices(PMSG_SUSPEND); if (!error) s2idle_enter(); + else if (error == -EBUSY && pm_wakeup_pending()) + error = 0; - dpm_noirq_resume_devices(PMSG_RESUME); - if (error && (error != -EBUSY || !pm_wakeup_pending())) { - dpm_noirq_end(); - break; - } - - if (s2idle_ops && s2idle_ops->wake) + if (!error && s2idle_ops && s2idle_ops->wake) s2idle_ops->wake(); + dpm_noirq_resume_devices(PMSG_RESUME); + dpm_noirq_end(); + if (error) + break; + if (s2idle_ops && s2idle_ops->sync) s2idle_ops->sync(); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 1250e4bd4b85..b0ad62b0e7b8 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -882,6 +882,11 @@ void rcu_irq_exit(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && rdtp->dynticks_nesting < 1); if (rdtp->dynticks_nesting <= 1) { @@ -1015,6 +1020,11 @@ void rcu_irq_enter(void) RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!"); rdtp = this_cpu_ptr(&rcu_dynticks); + + /* Page faults can happen in NMI handlers, so check... */ + if (rdtp->dynticks_nmi_nesting) + return; + oldval = rdtp->dynticks_nesting; rdtp->dynticks_nesting++; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 18a6966567da..d17c5da523a0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5166,6 +5166,28 @@ void sched_show_task(struct task_struct *p) put_task_stack(p); } +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + + void show_state_filter(unsigned long state_filter) { struct task_struct *g, *p; @@ -5188,7 +5210,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 01217fb5a5de..2f93e4a2d9f6 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -466,8 +466,6 @@ static char *task_group_path(struct task_group *tg) } #endif -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; - static void print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) { diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 98b59b5db90b..bb3a38005b9c 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -17,11 +17,13 @@ #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> +#include <linux/kmemleak.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> +#include <linux/sysctl.h> #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER #include <asm/syscall.h> @@ -42,6 +44,7 @@ * get/put helpers should be used when accessing an instance * outside of a lifetime-guarded section. In general, this * is only needed for handling filters shared across tasks. + * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @@ -57,6 +60,7 @@ */ struct seccomp_filter { refcount_t usage; + bool log; struct seccomp_filter *prev; struct bpf_prog *prog; }; @@ -171,10 +175,15 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters + * @match: stores struct seccomp_filter that resulted in the return value, + * unless filter returned SECCOMP_RET_ALLOW, in which case it will + * be unchanged. * * Returns valid seccomp BPF response codes. */ -static u32 seccomp_run_filters(const struct seccomp_data *sd) +#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) +static u32 seccomp_run_filters(const struct seccomp_data *sd, + struct seccomp_filter **match) { struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; @@ -184,7 +193,7 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd) /* Ensure unexpected behavior doesn't result in failing open. */ if (unlikely(WARN_ON(f == NULL))) - return SECCOMP_RET_KILL; + return SECCOMP_RET_KILL_PROCESS; if (!sd) { populate_seccomp_data(&sd_local); @@ -198,8 +207,10 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd) for (; f; f = f->prev) { u32 cur_ret = BPF_PROG_RUN(f->prog, sd); - if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION)) + if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; + *match = f; + } } return ret; } @@ -444,6 +455,10 @@ static long seccomp_attach_filter(unsigned int flags, return ret; } + /* Set log flag, if present. */ + if (flags & SECCOMP_FILTER_FLAG_LOG) + filter->log = true; + /* * If there is an existing filter, make it the prev and don't drop its * task reference. @@ -458,14 +473,19 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } +void __get_seccomp_filter(struct seccomp_filter *filter) +{ + /* Reference count is bounded by the number of total processes. */ + refcount_inc(&filter->usage); +} + /* get_seccomp_filter - increments the reference count of the filter on @tsk */ void get_seccomp_filter(struct task_struct *tsk) { struct seccomp_filter *orig = tsk->seccomp.filter; if (!orig) return; - /* Reference count is bounded by the number of total processes. */ - refcount_inc(&orig->usage); + __get_seccomp_filter(orig); } static inline void seccomp_filter_free(struct seccomp_filter *filter) @@ -476,10 +496,8 @@ static inline void seccomp_filter_free(struct seccomp_filter *filter) } } -/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ -void put_seccomp_filter(struct task_struct *tsk) +static void __put_seccomp_filter(struct seccomp_filter *orig) { - struct seccomp_filter *orig = tsk->seccomp.filter; /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->usage)) { struct seccomp_filter *freeme = orig; @@ -488,6 +506,12 @@ void put_seccomp_filter(struct task_struct *tsk) } } +/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */ +void put_seccomp_filter(struct task_struct *tsk) +{ + __put_seccomp_filter(tsk->seccomp.filter); +} + static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason) { memset(info, 0, sizeof(*info)); @@ -514,6 +538,65 @@ static void seccomp_send_sigsys(int syscall, int reason) } #endif /* CONFIG_SECCOMP_FILTER */ +/* For use with seccomp_actions_logged */ +#define SECCOMP_LOG_KILL_PROCESS (1 << 0) +#define SECCOMP_LOG_KILL_THREAD (1 << 1) +#define SECCOMP_LOG_TRAP (1 << 2) +#define SECCOMP_LOG_ERRNO (1 << 3) +#define SECCOMP_LOG_TRACE (1 << 4) +#define SECCOMP_LOG_LOG (1 << 5) +#define SECCOMP_LOG_ALLOW (1 << 6) + +static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | + SECCOMP_LOG_KILL_THREAD | + SECCOMP_LOG_TRAP | + SECCOMP_LOG_ERRNO | + SECCOMP_LOG_TRACE | + SECCOMP_LOG_LOG; + +static inline void seccomp_log(unsigned long syscall, long signr, u32 action, + bool requested) +{ + bool log = false; + + switch (action) { + case SECCOMP_RET_ALLOW: + break; + case SECCOMP_RET_TRAP: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP; + break; + case SECCOMP_RET_ERRNO: + log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO; + break; + case SECCOMP_RET_TRACE: + log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; + break; + case SECCOMP_RET_LOG: + log = seccomp_actions_logged & SECCOMP_LOG_LOG; + break; + case SECCOMP_RET_KILL_THREAD: + log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD; + break; + case SECCOMP_RET_KILL_PROCESS: + default: + log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS; + } + + /* + * Force an audit message to be emitted when the action is RET_KILL_*, + * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is + * allowed to be logged by the admin. + */ + if (log) + return __audit_seccomp(syscall, signr, action); + + /* + * Let the audit subsystem decide if the action should be audited based + * on whether the current task itself is being audited. + */ + return audit_seccomp(syscall, signr, action); +} + /* * Secure computing mode 1 allows only read/write/exit/sigreturn. * To be fully secure this must be combined with rlimit @@ -539,7 +622,7 @@ static void __secure_computing_strict(int this_syscall) #ifdef SECCOMP_DEBUG dump_stack(); #endif - audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL); + seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true); do_exit(SIGKILL); } @@ -566,6 +649,7 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { u32 filter_ret, action; + struct seccomp_filter *match = NULL; int data; /* @@ -574,9 +658,9 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, */ rmb(); - filter_ret = seccomp_run_filters(sd); + filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; - action = filter_ret & SECCOMP_RET_ACTION; + action = filter_ret & SECCOMP_RET_ACTION_FULL; switch (action) { case SECCOMP_RET_ERRNO: @@ -637,14 +721,25 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; + case SECCOMP_RET_LOG: + seccomp_log(this_syscall, 0, action, true); + return 0; + case SECCOMP_RET_ALLOW: + /* + * Note that the "match" filter will always be NULL for + * this action since SECCOMP_RET_ALLOW is the starting + * state in seccomp_run_filters(). + */ return 0; - case SECCOMP_RET_KILL: + case SECCOMP_RET_KILL_THREAD: + case SECCOMP_RET_KILL_PROCESS: default: - audit_seccomp(this_syscall, SIGSYS, action); + seccomp_log(this_syscall, SIGSYS, action, true); /* Dump core only if this is the last remaining thread. */ - if (get_nr_threads(current) == 1) { + if (action == SECCOMP_RET_KILL_PROCESS || + get_nr_threads(current) == 1) { siginfo_t info; /* Show the original registers in the dump. */ @@ -653,13 +748,16 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, seccomp_init_siginfo(&info, this_syscall, data); do_coredump(&info); } - do_exit(SIGSYS); + if (action == SECCOMP_RET_KILL_PROCESS) + do_group_exit(SIGSYS); + else + do_exit(SIGSYS); } unreachable(); skip: - audit_seccomp(this_syscall, 0, action); + seccomp_log(this_syscall, 0, action, match ? match->log : false); return -1; } #else @@ -794,6 +892,29 @@ static inline long seccomp_set_mode_filter(unsigned int flags, } #endif +static long seccomp_get_action_avail(const char __user *uaction) +{ + u32 action; + + if (copy_from_user(&action, uaction, sizeof(action))) + return -EFAULT; + + switch (action) { + case SECCOMP_RET_KILL_PROCESS: + case SECCOMP_RET_KILL_THREAD: + case SECCOMP_RET_TRAP: + case SECCOMP_RET_ERRNO: + case SECCOMP_RET_TRACE: + case SECCOMP_RET_LOG: + case SECCOMP_RET_ALLOW: + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, const char __user *uargs) @@ -805,6 +926,11 @@ static long do_seccomp(unsigned int op, unsigned int flags, return seccomp_set_mode_strict(); case SECCOMP_SET_MODE_FILTER: return seccomp_set_mode_filter(flags, uargs); + case SECCOMP_GET_ACTION_AVAIL: + if (flags != 0) + return -EINVAL; + + return seccomp_get_action_avail(uargs); default: return -EINVAL; } @@ -908,13 +1034,13 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, if (!data) goto out; - get_seccomp_filter(task); + __get_seccomp_filter(filter); spin_unlock_irq(&task->sighand->siglock); if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) ret = -EFAULT; - put_seccomp_filter(task); + __put_seccomp_filter(filter); return ret; out: @@ -922,3 +1048,185 @@ out: return ret; } #endif + +#ifdef CONFIG_SYSCTL + +/* Human readable action names for friendly sysctl interaction */ +#define SECCOMP_RET_KILL_PROCESS_NAME "kill_process" +#define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" +#define SECCOMP_RET_TRAP_NAME "trap" +#define SECCOMP_RET_ERRNO_NAME "errno" +#define SECCOMP_RET_TRACE_NAME "trace" +#define SECCOMP_RET_LOG_NAME "log" +#define SECCOMP_RET_ALLOW_NAME "allow" + +static const char seccomp_actions_avail[] = + SECCOMP_RET_KILL_PROCESS_NAME " " + SECCOMP_RET_KILL_THREAD_NAME " " + SECCOMP_RET_TRAP_NAME " " + SECCOMP_RET_ERRNO_NAME " " + SECCOMP_RET_TRACE_NAME " " + SECCOMP_RET_LOG_NAME " " + SECCOMP_RET_ALLOW_NAME; + +struct seccomp_log_name { + u32 log; + const char *name; +}; + +static const struct seccomp_log_name seccomp_log_names[] = { + { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME }, + { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME }, + { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME }, + { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME }, + { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, + { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, + { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, + { } +}; + +static bool seccomp_names_from_actions_logged(char *names, size_t size, + u32 actions_logged) +{ + const struct seccomp_log_name *cur; + bool append_space = false; + + for (cur = seccomp_log_names; cur->name && size; cur++) { + ssize_t ret; + + if (!(actions_logged & cur->log)) + continue; + + if (append_space) { + ret = strscpy(names, " ", size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } else + append_space = true; + + ret = strscpy(names, cur->name, size); + if (ret < 0) + return false; + + names += ret; + size -= ret; + } + + return true; +} + +static bool seccomp_action_logged_from_name(u32 *action_logged, + const char *name) +{ + const struct seccomp_log_name *cur; + + for (cur = seccomp_log_names; cur->name; cur++) { + if (!strcmp(cur->name, name)) { + *action_logged = cur->log; + return true; + } + } + + return false; +} + +static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names) +{ + char *name; + + *actions_logged = 0; + while ((name = strsep(&names, " ")) && *name) { + u32 action_logged = 0; + + if (!seccomp_action_logged_from_name(&action_logged, name)) + return false; + + *actions_logged |= action_logged; + } + + return true; +} + +static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + char names[sizeof(seccomp_actions_avail)]; + struct ctl_table table; + int ret; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + memset(names, 0, sizeof(names)); + + if (!write) { + if (!seccomp_names_from_actions_logged(names, sizeof(names), + seccomp_actions_logged)) + return -EINVAL; + } + + table = *ro_table; + table.data = names; + table.maxlen = sizeof(names); + ret = proc_dostring(&table, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (write) { + u32 actions_logged; + + if (!seccomp_actions_logged_from_names(&actions_logged, + table.data)) + return -EINVAL; + + if (actions_logged & SECCOMP_LOG_ALLOW) + return -EINVAL; + + seccomp_actions_logged = actions_logged; + } + + return 0; +} + +static struct ctl_path seccomp_sysctl_path[] = { + { .procname = "kernel", }, + { .procname = "seccomp", }, + { } +}; + +static struct ctl_table seccomp_sysctl_table[] = { + { + .procname = "actions_avail", + .data = (void *) &seccomp_actions_avail, + .maxlen = sizeof(seccomp_actions_avail), + .mode = 0444, + .proc_handler = proc_dostring, + }, + { + .procname = "actions_logged", + .mode = 0644, + .proc_handler = seccomp_actions_logged_handler, + }, + { } +}; + +static int __init seccomp_sysctl_init(void) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table); + if (!hdr) + pr_warn("seccomp: sysctl registration failed\n"); + else + kmemleak_not_leak(hdr); + + return 0; +} + +device_initcall(seccomp_sysctl_init) + +#endif /* CONFIG_SYSCTL */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6648fbbb8157..4da9e622471f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -367,7 +367,8 @@ static struct ctl_table kern_table[] = { .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, }, #ifdef CONFIG_SCHEDSTATS { @@ -2187,8 +2188,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 2a685b45b73b..45a3928544ce 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -648,6 +648,12 @@ int blk_trace_startstop(struct request_queue *q, int start) } EXPORT_SYMBOL_GPL(blk_trace_startstop); +/* + * When reading or writing the blktrace sysfs files, the references to the + * opened sysfs or device files should prevent the underlying block device + * from being removed. So no further delete protection is really needed. + */ + /** * blk_trace_ioctl: - handle the ioctls associated with tracing * @bdev: the block device @@ -665,7 +671,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) if (!q) return -ENXIO; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); switch (cmd) { case BLKTRACESETUP: @@ -691,7 +697,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg) break; } - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); return ret; } @@ -1727,7 +1733,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { ret = sprintf(buf, "%u\n", !!q->blk_trace); @@ -1746,7 +1752,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev, ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba); out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: @@ -1788,7 +1794,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, if (q == NULL) goto out_bdput; - mutex_lock(&bdev->bd_mutex); + mutex_lock(&q->blk_trace_mutex); if (attr == &dev_attr_enable) { if (value) @@ -1814,7 +1820,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev, } out_unlock_bdev: - mutex_unlock(&bdev->bd_mutex); + mutex_unlock(&q->blk_trace_mutex); out_bdput: bdput(bdev); out: diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 6abfafd7f173..8319e09e15b9 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4954,9 +4954,6 @@ static char ftrace_graph_buf[FTRACE_FILTER_SIZE] __initdata; static char ftrace_graph_notrace_buf[FTRACE_FILTER_SIZE] __initdata; static int ftrace_graph_set_hash(struct ftrace_hash *hash, char *buffer); -static unsigned long save_global_trampoline; -static unsigned long save_global_flags; - static int __init set_graph_function(char *str) { strlcpy(ftrace_graph_buf, str, FTRACE_FILTER_SIZE); @@ -6808,17 +6805,6 @@ void unregister_ftrace_graph(void) unregister_pm_notifier(&ftrace_suspend_notifier); unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL); -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * Function graph does not allocate the trampoline, but - * other global_ops do. We need to reset the ALLOC_TRAMP flag - * if one was used. - */ - global_ops.trampoline = save_global_trampoline; - if (save_global_flags & FTRACE_OPS_FL_ALLOC_TRAMP) - global_ops.flags |= FTRACE_OPS_FL_ALLOC_TRAMP; -#endif - out: mutex_unlock(&ftrace_lock); } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5360b7aec57a..752e5daf0896 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4020,11 +4020,17 @@ static int tracing_open(struct inode *inode, struct file *file) /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); + struct trace_buffer *trace_buf = &tr->trace_buffer; + +#ifdef CONFIG_TRACER_MAX_TRACE + if (tr->current_trace->print_max) + trace_buf = &tr->max_buffer; +#endif if (cpu == RING_BUFFER_ALL_CPUS) - tracing_reset_online_cpus(&tr->trace_buffer); + tracing_reset_online_cpus(trace_buf); else - tracing_reset(&tr->trace_buffer, cpu); + tracing_reset(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { @@ -5358,6 +5364,13 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf) if (t == tr->current_trace) goto out; + /* Some tracers won't work on kernel command line */ + if (system_state < SYSTEM_RUNNING && t->noboot) { + pr_warn("Tracer '%s' is not allowed on command line, ignored\n", + t->name); + goto out; + } + /* Some tracers are only allowed for the top level buffer */ if (!trace_ok_for_array(t, tr)) { ret = -EINVAL; @@ -5667,7 +5680,7 @@ static int tracing_wait_pipe(struct file *filp) * * iter->pos will be 0 if we haven't read anything. */ - if (!tracing_is_on() && iter->pos) + if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index fb5d54d0d1b3..652c682707cd 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -444,6 +444,8 @@ struct tracer { #ifdef CONFIG_TRACER_MAX_TRACE bool use_max_tr; #endif + /* True if tracer cannot be enabled in kernel param */ + bool noboot; }; diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index cd7480d0a201..dca78fc48439 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -282,6 +282,7 @@ static struct tracer mmio_tracer __read_mostly = .close = mmio_close, .read = mmio_read, .print_line = mmio_print_line, + .noboot = true, }; __init static int init_mmio_trace(void) diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index bac629af2285..c738e764e2a5 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -656,15 +656,6 @@ int trace_print_lat_context(struct trace_iterator *iter) return !trace_seq_has_overflowed(s); } -static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; - -static int task_state_char(unsigned long state) -{ - int bit = state ? __ffs(state) + 1 : 0; - - return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?'; -} - /** * ftrace_find_event - find a registered event * @type: the type of event to look for @@ -930,8 +921,8 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, trace_assign_type(field, iter->ent); - T = task_state_char(field->next_state); - S = task_state_char(field->prev_state); + T = __task_state_to_char(field->next_state); + S = __task_state_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", @@ -966,8 +957,8 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n", field->prev_pid, field->prev_prio, @@ -1002,8 +993,8 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S) trace_assign_type(field, iter->ent); if (!S) - S = task_state_char(field->prev_state); - T = task_state_char(field->next_state); + S = __task_state_to_char(field->prev_state); + T = __task_state_to_char(field->next_state); SEQ_PUT_HEX_FIELD(s, field->prev_pid); SEQ_PUT_HEX_FIELD(s, field->prev_prio); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ddec53b67646..0c331978b1a6 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -397,10 +397,10 @@ tracing_sched_switch_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = prev->pid; entry->prev_prio = prev->prio; - entry->prev_state = prev->state; + entry->prev_state = __get_task_state(prev); entry->next_pid = next->pid; entry->next_prio = next->prio; - entry->next_state = next->state; + entry->next_state = __get_task_state(next); entry->next_cpu = task_cpu(next); if (!call_filter_check_discard(call, entry, buffer, event)) @@ -425,10 +425,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr, entry = ring_buffer_event_data(event); entry->prev_pid = curr->pid; entry->prev_prio = curr->prio; - entry->prev_state = curr->state; + entry->prev_state = __get_task_state(curr); entry->next_pid = wakee->pid; entry->next_prio = wakee->prio; - entry->next_state = wakee->state; + entry->next_state = __get_task_state(wakee); entry->next_cpu = task_cpu(wakee); if (!call_filter_check_discard(call, entry, buffer, event)) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index a4df67cbc711..49cb41412eec 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -96,23 +96,9 @@ check_stack(unsigned long ip, unsigned long *stack) if (in_nmi()) return; - /* - * There's a slight chance that we are tracing inside the - * RCU infrastructure, and rcu_irq_enter() will not work - * as expected. - */ - if (unlikely(rcu_irq_enter_disabled())) - return; - local_irq_save(flags); arch_spin_lock(&stack_trace_max_lock); - /* - * RCU may not be watching, make it see us. - * The stack trace code uses rcu_sched. - */ - rcu_irq_enter(); - /* In case another CPU set the tracer_frame on us */ if (unlikely(!frame_size)) this_size -= tracer_frame; @@ -205,7 +191,6 @@ check_stack(unsigned long ip, unsigned long *stack) } out: - rcu_irq_exit(); arch_spin_unlock(&stack_trace_max_lock); local_irq_restore(flags); } |