diff options
Diffstat (limited to 'kernel')
177 files changed, 4119 insertions, 1693 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index ed470aac53da..172d151d429c 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the linux kernel. # diff --git a/kernel/acct.c b/kernel/acct.c index 5e72af29ab73..6670fbd3e466 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/acct.c * diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 011d46e5f73f..d4b050d9a66e 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "audit.h" #include <linux/fsnotify_backend.h> #include <linux/namei.h> diff --git a/kernel/bounds.c b/kernel/bounds.c index e1d1d1952bfa..c373e887c066 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generate definitions needed by the preprocessor. * This code generates raw asm output which is post-processed diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 897daa005b23..e691da0b3bab 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,9 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 98c0f00c3f5e..7c25426d3cf5 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -19,6 +19,9 @@ #include "map_in_map.h" +#define ARRAY_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + static void bpf_array_free_percpu(struct bpf_array *array) { int i; @@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + attr->value_size == 0 || + attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); @@ -98,7 +102,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array_size += (u64) attr->max_entries * elem_size * num_possible_cpus(); if (array_size >= U32_MAX - PAGE_SIZE || - elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) { + bpf_array_alloc_percpu(array)) { bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } @@ -492,7 +496,7 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, ee = ERR_PTR(-EOPNOTSUPP); event = perf_file->private_data; - if (perf_event_read_local(event, &value) == -EOPNOTSUPP) + if (perf_event_read_local(event, &value, NULL, NULL) == -EOPNOTSUPP) goto err_out; ee = bpf_event_entry_gen(perf_file, map_file); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 546113430049..b789ab78d28f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -27,129 +27,405 @@ 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; + 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.flags[type] = flags; - cgrp->bpf.prog[type] = prog; + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); - css_for_each_descendant_pre(pos, &cgrp->self) { - struct cgroup *desc = container_of(pos, struct cgroup, self); - - /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) { - 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 +447,26 @@ 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 +487,10 @@ 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; + int ret; - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); - - 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 +515,77 @@ 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; + int 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); + +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type) +{ + struct cgroup *cgrp; + struct bpf_cgroup_dev_ctx ctx = { + .access_type = (access << 16) | dev_type, + .major = major, + .minor = minor, + }; + int allow = 1; rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, + BPF_PROG_RUN); + rcu_read_unlock(); - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; + return !allow; +} +EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); - rcu_read_unlock(); +static const struct bpf_func_proto * +cgroup_dev_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_get_current_uid_gid: + return &bpf_get_current_uid_gid_proto; + case BPF_FUNC_trace_printk: + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); + default: + return NULL; + } +} - return ret; +static bool cgroup_dev_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) + return false; + + if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx)) + return false; + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + if (size != sizeof(__u32)) + return false; + + return true; } -EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); + +const struct bpf_prog_ops cg_dev_prog_ops = { +}; + +const struct bpf_verifier_ops cg_dev_verifier_ops = { + .get_func_proto = cgroup_dev_func_proto, + .is_valid_access = cgroup_dev_is_valid_access, +}; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..8a6c37762330 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -309,12 +309,25 @@ bpf_get_prog_addr_region(const struct bpf_prog *prog, static void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) { + const char *end = sym + KSYM_NAME_LEN; + BUILD_BUG_ON(sizeof("bpf_prog_") + - sizeof(prog->tag) * 2 + 1 > KSYM_NAME_LEN); + sizeof(prog->tag) * 2 + + /* name has been null terminated. + * We should need +1 for the '_' preceding + * the name. However, the null character + * is double counted between the name and the + * sizeof("bpf_prog_") above, so we omit + * the +1 here. + */ + sizeof(prog->aux->name) > KSYM_NAME_LEN); sym += snprintf(sym, KSYM_NAME_LEN, "bpf_prog_"); sym = bin2hex(sym, prog->tag, sizeof(prog->tag)); - *sym = 0; + if (prog->aux->name[0]) + snprintf(sym, (size_t)(end - sym), "_%s", prog->aux->name); + else + *sym = 0; } static __always_inline unsigned long @@ -1022,7 +1035,7 @@ 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; @@ -1367,7 +1380,13 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ - fp = bpf_int_jit_compile(fp); + if (!bpf_prog_is_dev_bound(fp->aux)) { + fp = bpf_int_jit_compile(fp); + } else { + *err = bpf_prog_offload_compile(fp); + if (*err) + return fp; + } bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at @@ -1381,11 +1400,163 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); +static unsigned int __bpf_prog_ret1(const void *ctx, + const struct bpf_insn *insn) +{ + return 1; +} + +static struct bpf_prog_dummy { + struct bpf_prog prog; +} dummy_bpf_prog = { + .prog = { + .bpf_func = __bpf_prog_ret1, + }, +}; + +/* 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; +} + +void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, + struct bpf_prog *old_prog) +{ + struct bpf_prog **prog = progs->progs; + + for (; *prog; prog++) + if (*prog == old_prog) { + WRITE_ONCE(*prog, &dummy_bpf_prog.prog); + break; + } +} + +int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, + struct bpf_prog *exclude_prog, + struct bpf_prog *include_prog, + struct bpf_prog_array **new_array) +{ + int new_prog_cnt, carry_prog_cnt = 0; + struct bpf_prog **existing_prog; + struct bpf_prog_array *array; + int new_prog_idx = 0; + + /* Figure out how many existing progs we need to carry over to + * the new array. + */ + if (old_array) { + existing_prog = old_array->progs; + for (; *existing_prog; existing_prog++) { + if (*existing_prog != exclude_prog && + *existing_prog != &dummy_bpf_prog.prog) + carry_prog_cnt++; + if (*existing_prog == include_prog) + return -EEXIST; + } + } + + /* How many progs (not NULL) will be in the new array? */ + new_prog_cnt = carry_prog_cnt; + if (include_prog) + new_prog_cnt += 1; + + /* Do we have any prog (not NULL) in the new array? */ + if (!new_prog_cnt) { + *new_array = NULL; + return 0; + } + + /* +1 as the end of prog_array is marked with NULL */ + array = bpf_prog_array_alloc(new_prog_cnt + 1, GFP_KERNEL); + if (!array) + return -ENOMEM; + + /* Fill in the new prog array */ + if (carry_prog_cnt) { + existing_prog = old_array->progs; + for (; *existing_prog; existing_prog++) + if (*existing_prog != exclude_prog && + *existing_prog != &dummy_bpf_prog.prog) + array->progs[new_prog_idx++] = *existing_prog; + } + if (include_prog) + array->progs[new_prog_idx++] = include_prog; + array->progs[new_prog_idx] = NULL; + *new_array = array; + return 0; +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; aux = container_of(work, struct bpf_prog_aux, work); + if (bpf_prog_is_dev_bound(aux)) + bpf_prog_offload_destroy(aux->prog); bpf_jit_free(aux->prog); } @@ -1498,5 +1669,8 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); +/* These are only used within the BPF_SYSCALL code */ +#ifdef CONFIG_BPF_SYSCALL EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); +#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c new file mode 100644 index 000000000000..ce5b669003b2 --- /dev/null +++ b/kernel/bpf/cpumap.c @@ -0,0 +1,706 @@ +/* bpf/cpumap.c + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ + +/* The 'cpumap' is primarily used as a backend map for XDP BPF helper + * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. + * + * Unlike devmap which redirects XDP frames out another NIC device, + * this map type redirects raw XDP frames to another CPU. The remote + * CPU will do SKB-allocation and call the normal network stack. + * + * This is a scalability and isolation mechanism, that allow + * separating the early driver network XDP layer, from the rest of the + * netstack, and assigning dedicated CPUs for this stage. This + * basically allows for 10G wirespeed pre-filtering via bpf. + */ +#include <linux/bpf.h> +#include <linux/filter.h> +#include <linux/ptr_ring.h> + +#include <linux/sched.h> +#include <linux/workqueue.h> +#include <linux/kthread.h> +#include <linux/capability.h> +#include <trace/events/xdp.h> + +#include <linux/netdevice.h> /* netif_receive_skb_core */ +#include <linux/etherdevice.h> /* eth_type_trans */ + +/* General idea: XDP packets getting XDP redirected to another CPU, + * will maximum be stored/queued for one driver ->poll() call. It is + * guaranteed that setting flush bit and flush operation happen on + * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() + * which queue in bpf_cpu_map_entry contains packets. + */ + +#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct xdp_bulk_queue { + void *q[CPU_MAP_BULK_SIZE]; + unsigned int count; +}; + +/* Struct for every remote "destination" CPU in map */ +struct bpf_cpu_map_entry { + u32 cpu; /* kthread CPU and map index */ + int map_id; /* Back reference to map */ + u32 qsize; /* Queue size placeholder for map lookup */ + + /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ + struct xdp_bulk_queue __percpu *bulkq; + + /* Queue with potential multi-producers, and single-consumer kthread */ + struct ptr_ring *queue; + struct task_struct *kthread; + struct work_struct kthread_stop_wq; + + atomic_t refcnt; /* Control when this struct can be free'ed */ + struct rcu_head rcu; +}; + +struct bpf_cpu_map { + struct bpf_map map; + /* Below members specific for map type */ + struct bpf_cpu_map_entry **cpu_map; + unsigned long __percpu *flush_needed; +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq); + +static u64 cpu_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) +{ + struct bpf_cpu_map *cmap; + int err = -ENOMEM; + u64 cost; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + cmap = kzalloc(sizeof(*cmap), GFP_USER); + if (!cmap) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + cmap->map.map_type = attr->map_type; + cmap->map.key_size = attr->key_size; + cmap->map.value_size = attr->value_size; + cmap->map.max_entries = attr->max_entries; + cmap->map.map_flags = attr->map_flags; + cmap->map.numa_node = bpf_map_attr_numa_node(attr); + + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (cmap->map.max_entries > NR_CPUS) { + err = -E2BIG; + goto free_cmap; + } + + /* make sure page count doesn't overflow */ + cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); + cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_cmap; + cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + ret = bpf_map_precharge_memlock(cmap->map.pages); + if (ret) { + err = ret; + goto free_cmap; + } + + /* A per cpu bitfield with a bit per possible CPU in map */ + cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!cmap->flush_needed) + goto free_cmap; + + /* Alloc array for possible remote "destination" CPUs */ + cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * + sizeof(struct bpf_cpu_map_entry *), + cmap->map.numa_node); + if (!cmap->cpu_map) + goto free_percpu; + + return &cmap->map; +free_percpu: + free_percpu(cmap->flush_needed); +free_cmap: + kfree(cmap); + return ERR_PTR(err); +} + +void __cpu_map_queue_destructor(void *ptr) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + if (WARN_ON_ONCE(ptr)) + page_frag_free(ptr); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); + kfree(rcpu->queue); + kfree(rcpu); + } +} + +static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + atomic_inc(&rcpu->refcnt); +} + +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + kthread_stop(rcpu->kthread); +} + +/* For now, xdp_pkt is a cpumap internal data structure, with info + * carried between enqueue to dequeue. It is mapped into the top + * headroom of the packet, to avoid allocating separate mem. + */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; + u16 metasize; + struct net_device *dev_rx; +}; + +/* Convert xdp_buff to xdp_pkt */ +static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) +{ + struct xdp_pkt *xdp_pkt; + int metasize; + int headroom; + + /* Assure headroom is available for storing info */ + headroom = xdp->data - xdp->data_hard_start; + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if (unlikely((headroom - metasize) < sizeof(*xdp_pkt))) + return NULL; + + /* Store info in top of packet */ + xdp_pkt = xdp->data_hard_start; + + xdp_pkt->data = xdp->data; + xdp_pkt->len = xdp->data_end - xdp->data; + xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); + xdp_pkt->metasize = metasize; + + return xdp_pkt; +} + +struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, + struct xdp_pkt *xdp_pkt) +{ + unsigned int frame_size; + void *pkt_data_start; + struct sk_buff *skb; + + /* build_skb need to place skb_shared_info after SKB end, and + * also want to know the memory "truesize". Thus, need to + * know the memory frame size backing xdp_buff. + * + * XDP was designed to have PAGE_SIZE frames, but this + * assumption is not longer true with ixgbe and i40e. It + * would be preferred to set frame_size to 2048 or 4096 + * depending on the driver. + * frame_size = 2048; + * frame_len = frame_size - sizeof(*xdp_pkt); + * + * Instead, with info avail, skb_shared_info in placed after + * packet len. This, unfortunately fakes the truesize. + * Another disadvantage of this approach, the skb_shared_info + * is not at a fixed memory location, with mixed length + * packets, which is bad for cache-line hotness. + */ + frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + skb = build_skb(pkt_data_start, frame_size); + if (!skb) + return NULL; + + skb_reserve(skb, xdp_pkt->headroom); + __skb_put(skb, xdp_pkt->len); + if (xdp_pkt->metasize) + skb_metadata_set(skb, xdp_pkt->metasize); + + /* Essential SKB info: protocol and skb->dev */ + skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + + /* Optional SKB info, currently missing: + * - HW checksum info (skb->ip_summed) + * - HW RX hash (skb_set_hash) + * - RX ring dev queue index (skb_record_rx_queue) + */ + + return skb; +} + +static int cpu_map_kthread_run(void *data) +{ + struct bpf_cpu_map_entry *rcpu = data; + + set_current_state(TASK_INTERRUPTIBLE); + + /* When kthread gives stop order, then rcpu have been disconnected + * from map, thus no new packets can enter. Remaining in-flight + * per CPU stored packets are flushed to this queue. Wait honoring + * kthread_stop signal until queue is empty. + */ + while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + unsigned int processed = 0, drops = 0, sched = 0; + struct xdp_pkt *xdp_pkt; + + /* Release CPU reschedule checks */ + if (__ptr_ring_empty(rcpu->queue)) { + set_current_state(TASK_INTERRUPTIBLE); + /* Recheck to avoid lost wake-up */ + if (__ptr_ring_empty(rcpu->queue)) { + schedule(); + sched = 1; + } else { + __set_current_state(TASK_RUNNING); + } + } else { + sched = cond_resched(); + } + + /* Process packets in rcpu->queue */ + local_bh_disable(); + /* + * The bpf_cpu_map_entry is single consumer, with this + * kthread CPU pinned. Lockless access to ptr_ring + * consume side valid as no-resize allowed of queue. + */ + while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + struct sk_buff *skb; + int ret; + + skb = cpu_map_build_skb(rcpu, xdp_pkt); + if (!skb) { + page_frag_free(xdp_pkt); + continue; + } + + /* Inject into network stack */ + ret = netif_receive_skb_core(skb); + if (ret == NET_RX_DROP) + drops++; + + /* Limit BH-disable period */ + if (++processed == 8) + break; + } + /* Feedback loop via tracepoint */ + trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched); + + local_bh_enable(); /* resched point, may call do_softirq() */ + } + __set_current_state(TASK_RUNNING); + + put_cpu_map_entry(rcpu); + return 0; +} + +struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +{ + gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + struct bpf_cpu_map_entry *rcpu; + int numa, err; + + /* Have map->numa_node, but choose node of redirect target CPU */ + numa = cpu_to_node(cpu); + + rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + if (!rcpu) + return NULL; + + /* Alloc percpu bulkq */ + rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), + sizeof(void *), gfp); + if (!rcpu->bulkq) + goto free_rcu; + + /* Alloc queue */ + rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + if (!rcpu->queue) + goto free_bulkq; + + err = ptr_ring_init(rcpu->queue, qsize, gfp); + if (err) + goto free_queue; + + rcpu->cpu = cpu; + rcpu->map_id = map_id; + rcpu->qsize = qsize; + + /* Setup kthread */ + rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, + "cpumap/%d/map:%d", cpu, map_id); + if (IS_ERR(rcpu->kthread)) + goto free_ptr_ring; + + get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ + get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + + /* Make sure kthread runs on a single CPU */ + kthread_bind(rcpu->kthread, cpu); + wake_up_process(rcpu->kthread); + + return rcpu; + +free_ptr_ring: + ptr_ring_cleanup(rcpu->queue, NULL); +free_queue: + kfree(rcpu->queue); +free_bulkq: + free_percpu(rcpu->bulkq); +free_rcu: + kfree(rcpu); + return NULL; +} + +void __cpu_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_cpu_map_entry *rcpu; + int cpu; + + /* This cpu_map_entry have been disconnected from map and one + * RCU graze-period have elapsed. Thus, XDP cannot queue any + * new packets and cannot change/set flush_needed that can + * find this entry. + */ + rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + + /* Flush remaining packets in percpu bulkq */ + for_each_online_cpu(cpu) { + struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); + + /* No concurrent bq_enqueue can run at this point */ + bq_flush_to_queue(rcpu, bq); + } + free_percpu(rcpu->bulkq); + /* Cannot kthread_stop() here, last put free rcpu resources */ + put_cpu_map_entry(rcpu); +} + +/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to + * ensure any driver rcu critical sections have completed, but this + * does not guarantee a flush has happened yet. Because driver side + * rcu_read_lock/unlock only protects the running XDP program. The + * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a + * pending flush op doesn't fail. + * + * The bpf_cpu_map_entry is still used by the kthread, and there can + * still be pending packets (in queue and percpu bulkq). A refcnt + * makes sure to last user (kthread_stop vs. call_rcu) free memory + * resources. + * + * The rcu callback __cpu_map_entry_free flush remaining packets in + * percpu bulkq to queue. Due to caller map_delete_elem() disable + * preemption, cannot call kthread_stop() to make sure queue is empty. + * Instead a work_queue is started for stopping kthread, + * cpu_map_kthread_stop, which waits for an RCU graze period before + * stopping kthread, emptying the queue. + */ +void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +{ + struct bpf_cpu_map_entry *old_rcpu; + + old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + if (old_rcpu) { + call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); + INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); + schedule_work(&old_rcpu->kthread_stop_wq); + } +} + +int cpu_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 key_cpu = *(u32 *)key; + + if (key_cpu >= map->max_entries) + return -EINVAL; + + /* notice caller map_delete_elem() use preempt_disable() */ + __cpu_map_entry_replace(cmap, key_cpu, NULL); + return 0; +} + +int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + /* Array index key correspond to CPU number */ + u32 key_cpu = *(u32 *)key; + /* Value is the queue size */ + u32 qsize = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(key_cpu >= cmap->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + return -EOVERFLOW; + + /* Make sure CPU is a valid possible cpu */ + if (!cpu_possible(key_cpu)) + return -ENODEV; + + if (qsize == 0) { + rcpu = NULL; /* Same as deleting */ + } else { + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + if (!rcpu) + return -ENOMEM; + } + rcu_read_lock(); + __cpu_map_entry_replace(cmap, key_cpu, rcpu); + rcu_read_unlock(); + return 0; +} + +void cpu_map_free(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + int cpu; + u32 i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the bpf programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. + * It does __not__ ensure pending flush operations (if any) are + * complete. + */ + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + + while (!bitmap_empty(bitmap, cmap->map.max_entries)) + cond_resched(); + } + + /* For cpu_map the remote CPUs can still be using the entries + * (struct bpf_cpu_map_entry). + */ + for (i = 0; i < cmap->map.max_entries; i++) { + struct bpf_cpu_map_entry *rcpu; + + rcpu = READ_ONCE(cmap->cpu_map[i]); + if (!rcpu) + continue; + + /* bq flush and cleanup happens after RCU graze-period */ + __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + } + free_percpu(cmap->flush_needed); + bpf_map_area_free(cmap->cpu_map); + kfree(cmap); +} + +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + if (key >= map->max_entries) + return NULL; + + rcpu = READ_ONCE(cmap->cpu_map[key]); + return rcpu; +} + +static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map_entry *rcpu = + __cpu_map_lookup_elem(map, *(u32 *)key); + + return rcpu ? &rcpu->qsize : NULL; +} + +static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= cmap->map.max_entries) { + *next = 0; + return 0; + } + + if (index == cmap->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +const struct bpf_map_ops cpu_map_ops = { + .map_alloc = cpu_map_alloc, + .map_free = cpu_map_free, + .map_delete_elem = cpu_map_delete_elem, + .map_update_elem = cpu_map_update_elem, + .map_lookup_elem = cpu_map_lookup_elem, + .map_get_next_key = cpu_map_get_next_key, +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq) +{ + unsigned int processed = 0, drops = 0; + const int to_cpu = rcpu->cpu; + struct ptr_ring *q; + int i; + + if (unlikely(!bq->count)) + return 0; + + q = rcpu->queue; + spin_lock(&q->producer_lock); + + for (i = 0; i < bq->count; i++) { + void *xdp_pkt = bq->q[i]; + int err; + + err = __ptr_ring_produce(q, xdp_pkt); + if (err) { + drops++; + page_frag_free(xdp_pkt); /* Free xdp_pkt */ + } + processed++; + } + bq->count = 0; + spin_unlock(&q->producer_lock); + + /* Feedback loop via tracepoints */ + trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); + return 0; +} + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + + if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) + bq_flush_to_queue(rcpu, bq); + + /* Notice, xdp_buff/page MUST be queued here, long enough for + * driver to code invoking us to finished, due to driver + * (e.g. ixgbe) recycle tricks based on page-refcnt. + * + * Thus, incoming xdp_pkt is always queued here (else we race + * with another CPU on page-refcnt and remaining driver code). + * Queue time is very short, as driver will invoke flush + * operation, when completing napi->poll call. + */ + bq->q[bq->count++] = xdp_pkt; + return 0; +} + +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, + struct net_device *dev_rx) +{ + struct xdp_pkt *xdp_pkt; + + xdp_pkt = convert_to_xdp_pkt(xdp); + if (unlikely(!xdp_pkt)) + return -EOVERFLOW; + + /* Info needed when constructing SKB on remote CPU */ + xdp_pkt->dev_rx = dev_rx; + + bq_enqueue(rcpu, xdp_pkt); + return 0; +} + +void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + + __set_bit(bit, bitmap); +} + +void __cpu_map_flush(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + u32 bit; + + /* The napi->poll softirq makes sure __cpu_map_insert_ctx() + * and __cpu_map_flush() happen on same CPU. Thus, the percpu + * bitmap indicate which percpu bulkq have packets. + */ + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); + struct xdp_bulk_queue *bq; + + /* This is possible if entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!rcpu)) + continue; + + __clear_bit(bit, bitmap); + + /* Flush all frames in bulkq to real queue */ + bq = this_cpu_ptr(rcpu->bulkq); + bq_flush_to_queue(rcpu, bq); + + /* If already running, costs spin_lock_irqsave + smb_mb */ + wake_up_process(rcpu->kthread); + } +} diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..ebdef54bf7df 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -50,6 +50,9 @@ #include <linux/bpf.h> #include <linux/filter.h> +#define DEV_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_dtab_netdev { struct net_device *dev; struct bpf_dtab *dtab; @@ -69,7 +72,7 @@ static LIST_HEAD(dev_map_list); static u64 dev_map_bitmap_size(const union bpf_attr *attr) { - return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); + return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -78,9 +81,12 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); @@ -111,8 +117,9 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) 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)); + dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), + __alignof__(unsigned long), + GFP_KERNEL | __GFP_NOWARN); if (!dtab->flush_needed) goto free_dtab; diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c new file mode 100644 index 000000000000..e682850c9715 --- /dev/null +++ b/kernel/bpf/disasm.c @@ -0,0 +1,214 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/bpf.h> + +#include "disasm.h" + +#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) +static const char * const func_id_str[] = { + __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) +}; +#undef __BPF_FUNC_STR_FN + +const char *func_id_name(int id) +{ + BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); + + if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) + return func_id_str[id]; + else + return "unknown"; +} + +const char *const bpf_class_string[8] = { + [BPF_LD] = "ld", + [BPF_LDX] = "ldx", + [BPF_ST] = "st", + [BPF_STX] = "stx", + [BPF_ALU] = "alu", + [BPF_JMP] = "jmp", + [BPF_RET] = "BUG", + [BPF_ALU64] = "alu64", +}; + +const char *const bpf_alu_string[16] = { + [BPF_ADD >> 4] = "+=", + [BPF_SUB >> 4] = "-=", + [BPF_MUL >> 4] = "*=", + [BPF_DIV >> 4] = "/=", + [BPF_OR >> 4] = "|=", + [BPF_AND >> 4] = "&=", + [BPF_LSH >> 4] = "<<=", + [BPF_RSH >> 4] = ">>=", + [BPF_NEG >> 4] = "neg", + [BPF_MOD >> 4] = "%=", + [BPF_XOR >> 4] = "^=", + [BPF_MOV >> 4] = "=", + [BPF_ARSH >> 4] = "s>>=", + [BPF_END >> 4] = "endian", +}; + +static const char *const bpf_ldst_string[] = { + [BPF_W >> 3] = "u32", + [BPF_H >> 3] = "u16", + [BPF_B >> 3] = "u8", + [BPF_DW >> 3] = "u64", +}; + +static const char *const bpf_jmp_string[16] = { + [BPF_JA >> 4] = "jmp", + [BPF_JEQ >> 4] = "==", + [BPF_JGT >> 4] = ">", + [BPF_JLT >> 4] = "<", + [BPF_JGE >> 4] = ">=", + [BPF_JLE >> 4] = "<=", + [BPF_JSET >> 4] = "&", + [BPF_JNE >> 4] = "!=", + [BPF_JSGT >> 4] = "s>", + [BPF_JSLT >> 4] = "s<", + [BPF_JSGE >> 4] = "s>=", + [BPF_JSLE >> 4] = "s<=", + [BPF_CALL >> 4] = "call", + [BPF_EXIT >> 4] = "exit", +}; + +static void print_bpf_end_insn(bpf_insn_print_cb verbose, + struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose(env, "(%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); +} + +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks) +{ + u8 class = BPF_CLASS(insn->code); + + if (class == BPF_ALU || class == BPF_ALU64) { + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose(env, "BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(verbose, env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose(env, "(%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(env, "(%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 { + verbose(env, "(%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(env, "(%02x) *(%s *)(r%d %+d) = r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->src_reg); + else if (BPF_MODE(insn->code) == BPF_XADD) + verbose(env, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, insn->off, + insn->src_reg); + else + verbose(env, "BUG_%02x\n", insn->code); + } else if (class == BPF_ST) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_st_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) *(%s *)(r%d %+d) = %d\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->dst_reg, + insn->off, insn->imm); + } else if (class == BPF_LDX) { + if (BPF_MODE(insn->code) != BPF_MEM) { + verbose(env, "BUG_ldx_%02x\n", insn->code); + return; + } + verbose(env, "(%02x) r%d = *(%s *)(r%d %+d)\n", + insn->code, insn->dst_reg, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->off); + } else if (class == BPF_LD) { + if (BPF_MODE(insn->code) == BPF_ABS) { + verbose(env, "(%02x) r0 = *(%s *)skb[%d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IND) { + verbose(env, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", + insn->code, + bpf_ldst_string[BPF_SIZE(insn->code) >> 3], + insn->src_reg, insn->imm); + } else if (BPF_MODE(insn->code) == BPF_IMM && + BPF_SIZE(insn->code) == BPF_DW) { + /* At this point, we already made sure that the second + * part of the ldimm64 insn is accessible. + */ + u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; + bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + + if (map_ptr && !allow_ptr_leaks) + imm = 0; + + verbose(env, "(%02x) r%d = 0x%llx\n", insn->code, + insn->dst_reg, (unsigned long long)imm); + } else { + verbose(env, "BUG_ld_%02x\n", insn->code); + return; + } + } else if (class == BPF_JMP) { + u8 opcode = BPF_OP(insn->code); + + if (opcode == BPF_CALL) { + verbose(env, "(%02x) call %s#%d\n", insn->code, + func_id_name(insn->imm), insn->imm); + } else if (insn->code == (BPF_JMP | BPF_JA)) { + verbose(env, "(%02x) goto pc%+d\n", + insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_EXIT)) { + verbose(env, "(%02x) exit\n", insn->code); + } else if (BPF_SRC(insn->code) == BPF_X) { + verbose(env, "(%02x) if r%d %s r%d goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->src_reg, insn->off); + } else { + verbose(env, "(%02x) if r%d %s 0x%x goto pc%+d\n", + insn->code, insn->dst_reg, + bpf_jmp_string[BPF_OP(insn->code) >> 4], + insn->imm, insn->off); + } + } else { + verbose(env, "(%02x) %s\n", + insn->code, bpf_class_string[class]); + } +} diff --git a/kernel/bpf/disasm.h b/kernel/bpf/disasm.h new file mode 100644 index 000000000000..8de977e420b6 --- /dev/null +++ b/kernel/bpf/disasm.h @@ -0,0 +1,32 @@ +/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com + * Copyright (c) 2016 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef __BPF_DISASM_H__ +#define __BPF_DISASM_H__ + +#include <linux/bpf.h> +#include <linux/kernel.h> +#include <linux/stringify.h> + +extern const char *const bpf_alu_string[16]; +extern const char *const bpf_class_string[8]; + +const char *func_id_name(int id); + +struct bpf_verifier_env; +typedef void (*bpf_insn_print_cb)(struct bpf_verifier_env *env, + const char *, ...); +void print_bpf_insn(bpf_insn_print_cb verbose, struct bpf_verifier_env *env, + const struct bpf_insn *insn, bool allow_ptr_leaks); + +#endif diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..e469e05c8e83 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,8 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" -#define HTAB_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) struct bucket { struct hlist_nulls_head head; @@ -317,10 +318,6 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) */ goto free_htab; - if (percpu && round_up(htab->map.value_size, 8) > PCPU_MIN_UNIT_SIZE) - /* make sure the size for pcpu_alloc() is reasonable */ - goto free_htab; - htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..01aaef1a77c5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -295,7 +295,7 @@ out: } static void *bpf_obj_do_get(const struct filename *pathname, - enum bpf_type *type) + enum bpf_type *type, int flags) { struct inode *inode; struct path path; @@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; @@ -326,18 +326,23 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname) +int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; + int f_flags; void *raw; + f_flags = bpf_get_file_flag(flags); + if (f_flags < 0) + return f_flags; + pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); - raw = bpf_obj_do_get(pname, &type); + raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; @@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname) if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) - ret = bpf_map_new_fd(raw); + ret = bpf_map_new_fd(raw, f_flags); else goto out; @@ -363,6 +368,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b767844a76f..885e45479680 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 @@ -406,7 +495,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c new file mode 100644 index 000000000000..2816feb38be1 --- /dev/null +++ b/kernel/bpf/offload.c @@ -0,0 +1,194 @@ +#include <linux/bpf.h> +#include <linux/bpf_verifier.h> +#include <linux/bug.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/printk.h> +#include <linux/rtnetlink.h> + +/* protected by RTNL */ +static LIST_HEAD(bpf_prog_offload_devs); + +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_dev_offload *offload; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->prog_flags) + return -EINVAL; + + offload = kzalloc(sizeof(*offload), GFP_USER); + if (!offload) + return -ENOMEM; + + offload->prog = prog; + init_waitqueue_head(&offload->verifier_done); + + rtnl_lock(); + offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex); + if (!offload->netdev) { + rtnl_unlock(); + kfree(offload); + return -EINVAL; + } + + prog->aux->offload = offload; + list_add_tail(&offload->offloads, &bpf_prog_offload_devs); + rtnl_unlock(); + + return 0; +} + +static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, + struct netdev_bpf *data) +{ + struct net_device *netdev = prog->aux->offload->netdev; + + ASSERT_RTNL(); + + if (!netdev) + return -ENODEV; + if (!netdev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + data->command = cmd; + + return netdev->netdev_ops->ndo_bpf(netdev, data); +} + +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + struct netdev_bpf data = {}; + int err; + + data.verifier.prog = env->prog; + + rtnl_lock(); + err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data); + if (err) + goto exit_unlock; + + env->dev_ops = data.verifier.ops; + + env->prog->aux->offload->dev_state = true; + env->prog->aux->offload->verifier_running = true; +exit_unlock: + rtnl_unlock(); + return err; +} + +static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + + data.offload.prog = prog; + + if (offload->verifier_running) + wait_event(offload->verifier_done, !offload->verifier_running); + + if (offload->dev_state) + WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data)); + + offload->dev_state = false; + list_del_init(&offload->offloads); + offload->netdev = NULL; +} + +void bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + __bpf_prog_offload_destroy(prog); + rtnl_unlock(); + + kfree(offload); +} + +static int bpf_prog_offload_translate(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + int ret; + + data.offload.prog = prog; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data); + rtnl_unlock(); + + return ret; +} + +static unsigned int bpf_prog_warn_on_exec(const void *ctx, + const struct bpf_insn *insn) +{ + WARN(1, "attempt to execute device eBPF program on the host!"); + return 0; +} + +int bpf_prog_offload_compile(struct bpf_prog *prog) +{ + prog->bpf_func = bpf_prog_warn_on_exec; + + return bpf_prog_offload_translate(prog); +} + +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + u32 ifindex; + + rtnl_lock(); + ifindex = offload->netdev ? offload->netdev->ifindex : 0; + rtnl_unlock(); + + return ifindex; +} + +const struct bpf_prog_ops bpf_offload_prog_ops = { +}; + +static int bpf_offload_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_dev_offload *offload, *tmp; + + ASSERT_RTNL(); + + switch (event) { + case NETDEV_UNREGISTER: + list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, + offloads) { + if (offload->netdev == netdev) + __bpf_prog_offload_destroy(offload->prog); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block bpf_offload_notifier = { + .notifier_call = bpf_offload_notification, +}; + +static int __init bpf_offload_init(void) +{ + register_netdevice_notifier(&bpf_offload_notifier); + return 0; +} + +subsys_initcall(bpf_offload_init); diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e4969..5ee2e41893d9 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -39,6 +39,10 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <net/strparser.h> +#include <net/tcp.h> + +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) struct bpf_stab { struct bpf_map map; @@ -92,21 +96,45 @@ static inline struct smap_psock *smap_psock_sk(const struct sock *sk) return rcu_dereference_sk_user_data(sk); } +/* compute the linear packet data range [data, data_end) for skb when + * sk_skb type programs are in use. + */ +static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) +{ + TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); +} + +enum __sk_action { + __SK_DROP = 0, + __SK_PASS, + __SK_REDIRECT, +}; + static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) { struct bpf_prog *prog = READ_ONCE(psock->bpf_verdict); int rc; if (unlikely(!prog)) - return SK_DROP; + return __SK_DROP; skb_orphan(skb); + /* We need to ensure that BPF metadata for maps is also cleared + * when we orphan the skb so that we don't have the possibility + * to reference a stale map. + */ + TCP_SKB_CB(skb)->bpf.map = NULL; skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); + preempt_disable(); rc = (*prog->bpf_func)(skb, prog->insnsi); + preempt_enable(); skb->sk = NULL; - return rc; + /* Moving return codes from UAPI namespace into internal namespace */ + return rc == SK_PASS ? + (TCP_SKB_CB(skb)->bpf.map ? __SK_REDIRECT : __SK_PASS) : + __SK_DROP; } static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) @@ -114,17 +142,10 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) struct sock *sk; int rc; - /* Because we use per cpu values to feed input from sock redirect - * in BPF program to do_sk_redirect_map() call we need to ensure we - * are not preempted. RCU read lock is not sufficient in this case - * with CONFIG_PREEMPT_RCU enabled so we must be explicit here. - */ - preempt_disable(); rc = smap_verdict_func(psock, skb); switch (rc) { - case SK_REDIRECT: - sk = do_sk_redirect_map(); - preempt_enable(); + case __SK_REDIRECT: + sk = do_sk_redirect_map(skb); if (likely(sk)) { struct smap_psock *peer = smap_psock_sk(sk); @@ -139,10 +160,8 @@ static void smap_do_verdict(struct smap_psock *psock, struct sk_buff *skb) } } /* Fall through and free skb otherwise */ - case SK_DROP: + case __SK_DROP: default: - if (rc != SK_REDIRECT) - preempt_enable(); kfree_skb(skb); } } @@ -369,7 +388,7 @@ 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(); @@ -487,9 +506,12 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) int err = -EINVAL; u64 cost; + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) @@ -840,6 +862,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP) { + fput(socket->file); + return -EOPNOTSUPP; + } + err = sock_map_ctx_update_elem(&skops, map, key, flags); fput(socket->file); return err; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..a15bc636cc98 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,9 @@ #include <linux/perf_event.h> #include "percpu_freelist.h" +#define STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; @@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags & ~BPF_F_NUMA_NODE) + if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 25d074920a00..09badc37e864 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 || \ @@ -31,6 +34,8 @@ #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) + DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); @@ -207,6 +212,7 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); bpf_map_uncharge_memlock(map); + security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -291,17 +297,54 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_map_fops = { +static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, + loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_READ. + */ + return -EINVAL; +} + +static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, + size_t siz, loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_WRITE. + */ + return -EINVAL; +} + +const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; -int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map, int flags) { + int ret; + + ret = security_bpf_map(map, OPEN_FMODE(flags)); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-map", &bpf_map_fops, map, - O_RDWR | O_CLOEXEC); + flags | O_CLOEXEC); +} + +int bpf_get_file_flag(int flags) +{ + if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) + return -EINVAL; + if (flags & BPF_F_RDONLY) + return O_RDONLY; + if (flags & BPF_F_WRONLY) + return O_WRONLY; + return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ @@ -312,18 +355,46 @@ 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; + + memset(dst, 0, 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; + + return 0; +} + +#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; + int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); + if (f_flags < 0) + return f_flags; + if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) @@ -334,18 +405,26 @@ 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); - err = bpf_map_charge_memlock(map); + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; + err = bpf_map_charge_memlock(map); + if (err) + goto free_map_sec; + err = bpf_map_alloc_id(map); if (err) goto free_map; - err = bpf_map_new_fd(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put() is needed because the above @@ -362,6 +441,8 @@ static int map_create(union bpf_attr *attr) free_map: bpf_map_uncharge_memlock(map); +free_map_sec: + security_bpf_map_free(map); free_map_nouncharge: map->ops->map_free(map); return err; @@ -460,6 +541,11 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -540,6 +626,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -562,6 +653,12 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* Need to create a kthread, thus must support schedule */ + if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + err = map->ops->map_update_elem(map, key, value, attr->flags); + goto out; + } + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ @@ -592,7 +689,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_update_elem(map, ufd, key, value); free_value: @@ -623,6 +720,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -666,6 +768,11 @@ static int map_get_next_key(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + if (ukey) { key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { @@ -703,9 +810,9 @@ err_put: return err; } -static const struct bpf_verifier_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _ops) \ - [_id] = &_ops, +static const struct bpf_prog_ops * const bpf_prog_types[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE @@ -717,7 +824,10 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) return -EINVAL; - prog->aux->ops = bpf_prog_types[type]; + if (!bpf_prog_is_dev_bound(prog->aux)) + prog->aux->ops = bpf_prog_types[type]; + else + prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } @@ -820,6 +930,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); + security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -867,15 +978,23 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_prog_fops = { +const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { + int ret; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } @@ -938,7 +1057,22 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) +static bool bpf_prog_can_attach(struct bpf_prog *prog, + enum bpf_prog_type *attach_type, + struct net_device *netdev) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + if (prog->type != *attach_type) + return false; + if (offload && offload->netdev != netdev) + return false; + + return true; +} + +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, + struct net_device *netdev) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -946,7 +1080,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (type && prog->type != *type) { + if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -959,12 +1093,12 @@ out: struct bpf_prog *bpf_prog_get(u32 ufd) { - return __bpf_prog_get(ufd, NULL); + return __bpf_prog_get(ufd, NULL, NULL); } struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type); + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL); if (!IS_ERR(prog)) trace_bpf_prog_get_type(prog); @@ -972,8 +1106,19 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) } EXPORT_SYMBOL_GPL(bpf_prog_get_type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev) +{ + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev); + + if (!IS_ERR(prog)) + trace_bpf_prog_get_type(prog); + return prog; +} +EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); + /* 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_target_ifindex static int bpf_prog_load(union bpf_attr *attr) { @@ -1015,10 +1160,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (!prog) return -ENOMEM; - err = bpf_prog_charge_memlock(prog); + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog_nouncharge; + err = bpf_prog_charge_memlock(prog); + if (err) + goto free_prog_sec; + prog->len = attr->insn_cnt; err = -EFAULT; @@ -1032,11 +1181,22 @@ static int bpf_prog_load(union bpf_attr *attr) atomic_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; + if (attr->prog_target_ifindex) { + err = bpf_prog_offload_init(prog, attr); + if (err) + goto free_prog; + } + /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); 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) @@ -1071,16 +1231,18 @@ free_used_maps: free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); +free_prog_sec: + security_bpf_prog_free(prog->aux); free_prog_nouncharge: bpf_prog_free(prog); return err; } -#define BPF_OBJ_LAST_FIELD bpf_fd +#define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ)) + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); @@ -1088,10 +1250,12 @@ static int bpf_obj_pin(const union bpf_attr *attr) static int bpf_obj_get(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || + attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); + return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + attr->file_flags); } #ifdef CONFIG_CGROUP_BPF @@ -1132,6 +1296,9 @@ 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; @@ -1145,7 +1312,7 @@ 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) { @@ -1159,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, true); @@ -1176,8 +1346,8 @@ 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); @@ -1189,6 +1359,8 @@ 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; @@ -1201,26 +1373,71 @@ 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_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; 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: + case BPF_CGROUP_DEVICE: + 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 @@ -1305,20 +1522,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) return fd; } -#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; + int f_flags; int fd; - if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || + attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + f_flags = bpf_get_file_flag(attr->open_flags); + if (f_flags < 0) + return f_flags; + spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) @@ -1330,7 +1553,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - fd = bpf_map_new_fd(map); + fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put(map); @@ -1358,8 +1581,25 @@ 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; @@ -1385,6 +1625,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + if (bpf_prog_is_dev_bound(prog->aux)) { + info.status |= BPF_PROG_STATUS_DEV_BOUND; + info.ifindex = bpf_prog_offload_ifindex(prog); + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) @@ -1413,6 +1658,7 @@ 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)) @@ -1467,6 +1713,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (copy_from_user(&attr, uattr, size) != 0) return -EFAULT; + err = security_bpf(cmd, &attr, size); + if (err < 0) + return err; + switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); @@ -1499,6 +1749,9 @@ 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 b914fbe1383e..4a942e2e753d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -21,6 +21,17 @@ #include <linux/vmalloc.h> #include <linux/stringify.h> +#include "disasm.h" + +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include <linux/bpf_types.h> +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -153,28 +164,42 @@ struct bpf_call_arg_meta { int access_size; }; -/* verbose verifier prints what it's seeing - * bpf_check() is called under lock, so no race to access these global vars - */ -static u32 log_level, log_size, log_len; -static char *log_buf; - static DEFINE_MUTEX(bpf_verifier_lock); /* log_level controls verbosity level of eBPF verifier. * verbose() is used to dump the verification trace to the log, so the user * can figure out what's wrong with the program */ -static __printf(1, 2) void verbose(const char *fmt, ...) +static __printf(2, 3) void verbose(struct bpf_verifier_env *env, + const char *fmt, ...) { + struct bpf_verifer_log *log = &env->log; + unsigned int n; va_list args; - if (log_level == 0 || log_len >= log_size - 1) + if (!log->level || !log->ubuf || bpf_verifier_log_full(log)) return; va_start(args, fmt); - log_len += vscnprintf(log_buf + log_len, log_size - log_len, fmt, args); + n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args); va_end(args); + + WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1, + "verifier log line truncated - local buffer too short\n"); + + n = min(log->len_total - log->len_used - 1, n); + log->kbuf[n] = '\0'; + + if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1)) + log->len_used += n; + else + log->ubuf = NULL; +} + +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' */ @@ -187,26 +212,12 @@ 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", }; -#define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) -static const char * const func_id_str[] = { - __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) -}; -#undef __BPF_FUNC_STR_FN - -static const char *func_id_name(int id) -{ - BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); - - if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) - return func_id_str[id]; - else - return "unknown"; -} - -static void print_verifier_state(struct bpf_verifier_state *state) +static void print_verifier_state(struct bpf_verifier_env *env, + struct bpf_verifier_state *state) { struct bpf_reg_state *reg; enum bpf_reg_type t; @@ -217,21 +228,21 @@ static void print_verifier_state(struct bpf_verifier_state *state) t = reg->type; if (t == NOT_INIT) continue; - verbose(" R%d=%s", i, reg_type_str[t]); + verbose(env, " R%d=%s", i, reg_type_str[t]); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && tnum_is_const(reg->var_off)) { /* reg->off should be 0 for SCALAR_VALUE */ - verbose("%lld", reg->var_off.value + reg->off); + verbose(env, "%lld", reg->var_off.value + reg->off); } else { - verbose("(id=%d", reg->id); + verbose(env, "(id=%d", reg->id); if (t != SCALAR_VALUE) - verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) - verbose(",r=%d", reg->range); + verbose(env, ",off=%d", reg->off); + if (type_is_pkt_pointer(t)) + verbose(env, ",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || t == PTR_TO_MAP_VALUE_OR_NULL) - verbose(",ks=%d,vs=%d", + verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); if (tnum_is_const(reg->var_off)) { @@ -239,243 +250,174 @@ static void print_verifier_state(struct bpf_verifier_state *state) * could be a pointer whose offset is too big * for reg->off */ - verbose(",imm=%llx", reg->var_off.value); + verbose(env, ",imm=%llx", reg->var_off.value); } else { if (reg->smin_value != reg->umin_value && reg->smin_value != S64_MIN) - verbose(",smin_value=%lld", + verbose(env, ",smin_value=%lld", (long long)reg->smin_value); if (reg->smax_value != reg->umax_value && reg->smax_value != S64_MAX) - verbose(",smax_value=%lld", + verbose(env, ",smax_value=%lld", (long long)reg->smax_value); if (reg->umin_value != 0) - verbose(",umin_value=%llu", + verbose(env, ",umin_value=%llu", (unsigned long long)reg->umin_value); if (reg->umax_value != U64_MAX) - verbose(",umax_value=%llu", + verbose(env, ",umax_value=%llu", (unsigned long long)reg->umax_value); if (!tnum_is_unknown(reg->var_off)) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(",var_off=%s", tn_buf); + verbose(env, ",var_off=%s", tn_buf); } } - verbose(")"); + verbose(env, ")"); } } - for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { - if (state->stack_slot_type[i] == STACK_SPILL) - verbose(" fp%d=%s", -MAX_BPF_STACK + i, - reg_type_str[state->spilled_regs[i / BPF_REG_SIZE].type]); + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] == STACK_SPILL) + verbose(env, " fp%d=%s", + -MAX_BPF_STACK + i * BPF_REG_SIZE, + reg_type_str[state->stack[i].spilled_ptr.type]); } - verbose("\n"); + verbose(env, "\n"); } -static const char *const bpf_class_string[] = { - [BPF_LD] = "ld", - [BPF_LDX] = "ldx", - [BPF_ST] = "st", - [BPF_STX] = "stx", - [BPF_ALU] = "alu", - [BPF_JMP] = "jmp", - [BPF_RET] = "BUG", - [BPF_ALU64] = "alu64", -}; - -static const char *const bpf_alu_string[16] = { - [BPF_ADD >> 4] = "+=", - [BPF_SUB >> 4] = "-=", - [BPF_MUL >> 4] = "*=", - [BPF_DIV >> 4] = "/=", - [BPF_OR >> 4] = "|=", - [BPF_AND >> 4] = "&=", - [BPF_LSH >> 4] = "<<=", - [BPF_RSH >> 4] = ">>=", - [BPF_NEG >> 4] = "neg", - [BPF_MOD >> 4] = "%=", - [BPF_XOR >> 4] = "^=", - [BPF_MOV >> 4] = "=", - [BPF_ARSH >> 4] = "s>>=", - [BPF_END >> 4] = "endian", -}; - -static const char *const bpf_ldst_string[] = { - [BPF_W >> 3] = "u32", - [BPF_H >> 3] = "u16", - [BPF_B >> 3] = "u8", - [BPF_DW >> 3] = "u64", -}; - -static const char *const bpf_jmp_string[16] = { - [BPF_JA >> 4] = "jmp", - [BPF_JEQ >> 4] = "==", - [BPF_JGT >> 4] = ">", - [BPF_JLT >> 4] = "<", - [BPF_JGE >> 4] = ">=", - [BPF_JLE >> 4] = "<=", - [BPF_JSET >> 4] = "&", - [BPF_JNE >> 4] = "!=", - [BPF_JSGT >> 4] = "s>", - [BPF_JSLT >> 4] = "s<", - [BPF_JSGE >> 4] = "s>=", - [BPF_JSLE >> 4] = "s<=", - [BPF_CALL >> 4] = "call", - [BPF_EXIT >> 4] = "exit", -}; +static int copy_stack_state(struct bpf_verifier_state *dst, + const struct bpf_verifier_state *src) +{ + if (!src->stack) + return 0; + if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) { + /* internal bug, make state invalid to reject the program */ + memset(dst, 0, sizeof(*dst)); + return -EFAULT; + } + memcpy(dst->stack, src->stack, + sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE)); + return 0; +} -static void print_bpf_insn(const struct bpf_verifier_env *env, - const struct bpf_insn *insn) +/* do_check() starts with zero-sized stack in struct bpf_verifier_state to + * make it consume minimal amount of memory. check_stack_write() access from + * the program calls into realloc_verifier_state() to grow the stack size. + * Note there is a non-zero 'parent' pointer inside bpf_verifier_state + * which this function copies over. It points to previous bpf_verifier_state + * which is never reallocated + */ +static int realloc_verifier_state(struct bpf_verifier_state *state, int size, + bool copy_old) { - u8 class = BPF_CLASS(insn->code); - - if (class == BPF_ALU || class == BPF_ALU64) { - 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 - 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", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->src_reg); - else if (BPF_MODE(insn->code) == BPF_XADD) - verbose("(%02x) lock *(%s *)(r%d %+d) += r%d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, insn->off, - insn->src_reg); - else - verbose("BUG_%02x\n", insn->code); - } else if (class == BPF_ST) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_st_%02x\n", insn->code); - return; - } - verbose("(%02x) *(%s *)(r%d %+d) = %d\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->dst_reg, - insn->off, insn->imm); - } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM) { - verbose("BUG_ldx_%02x\n", insn->code); - return; + u32 old_size = state->allocated_stack; + struct bpf_stack_state *new_stack; + int slot = size / BPF_REG_SIZE; + + if (size <= old_size || !size) { + if (copy_old) + return 0; + state->allocated_stack = slot * BPF_REG_SIZE; + if (!size && old_size) { + kfree(state->stack); + state->stack = NULL; } - verbose("(%02x) r%d = *(%s *)(r%d %+d)\n", - insn->code, insn->dst_reg, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->off); - } else if (class == BPF_LD) { - if (BPF_MODE(insn->code) == BPF_ABS) { - verbose("(%02x) r0 = *(%s *)skb[%d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IND) { - verbose("(%02x) r0 = *(%s *)skb[r%d + %d]\n", - insn->code, - bpf_ldst_string[BPF_SIZE(insn->code) >> 3], - insn->src_reg, insn->imm); - } else if (BPF_MODE(insn->code) == BPF_IMM && - BPF_SIZE(insn->code) == BPF_DW) { - /* At this point, we already made sure that the second - * part of the ldimm64 insn is accessible. - */ - u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; - bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD; + return 0; + } + new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state), + GFP_KERNEL); + if (!new_stack) + return -ENOMEM; + if (copy_old) { + if (state->stack) + memcpy(new_stack, state->stack, + sizeof(*new_stack) * (old_size / BPF_REG_SIZE)); + memset(new_stack + old_size / BPF_REG_SIZE, 0, + sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE); + } + state->allocated_stack = slot * BPF_REG_SIZE; + kfree(state->stack); + state->stack = new_stack; + return 0; +} - if (map_ptr && !env->allow_ptr_leaks) - imm = 0; +static void free_verifier_state(struct bpf_verifier_state *state, + bool free_self) +{ + kfree(state->stack); + if (free_self) + kfree(state); +} - verbose("(%02x) r%d = 0x%llx\n", insn->code, - insn->dst_reg, (unsigned long long)imm); - } else { - verbose("BUG_ld_%02x\n", insn->code); - return; - } - } else if (class == BPF_JMP) { - u8 opcode = BPF_OP(insn->code); +/* copy verifier state from src to dst growing dst stack space + * when necessary to accommodate larger src stack + */ +static int copy_verifier_state(struct bpf_verifier_state *dst, + const struct bpf_verifier_state *src) +{ + int err; - if (opcode == BPF_CALL) { - verbose("(%02x) call %s#%d\n", insn->code, - func_id_name(insn->imm), insn->imm); - } else if (insn->code == (BPF_JMP | BPF_JA)) { - verbose("(%02x) goto pc%+d\n", - insn->code, insn->off); - } else if (insn->code == (BPF_JMP | BPF_EXIT)) { - verbose("(%02x) exit\n", insn->code); - } else if (BPF_SRC(insn->code) == BPF_X) { - verbose("(%02x) if r%d %s r%d goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->src_reg, insn->off); - } else { - verbose("(%02x) if r%d %s 0x%x goto pc%+d\n", - insn->code, insn->dst_reg, - bpf_jmp_string[BPF_OP(insn->code) >> 4], - insn->imm, insn->off); - } - } else { - verbose("(%02x) %s\n", insn->code, bpf_class_string[class]); - } + err = realloc_verifier_state(dst, src->allocated_stack, false); + if (err) + return err; + memcpy(dst, src, offsetof(struct bpf_verifier_state, allocated_stack)); + return copy_stack_state(dst, src); } -static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx) +static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, + int *insn_idx) { - struct bpf_verifier_stack_elem *elem; - int insn_idx; + struct bpf_verifier_state *cur = env->cur_state; + struct bpf_verifier_stack_elem *elem, *head = env->head; + int err; if (env->head == NULL) - return -1; + return -ENOENT; - memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state)); - insn_idx = env->head->insn_idx; + if (cur) { + err = copy_verifier_state(cur, &head->st); + if (err) + return err; + } + if (insn_idx) + *insn_idx = head->insn_idx; if (prev_insn_idx) - *prev_insn_idx = env->head->prev_insn_idx; - elem = env->head->next; - kfree(env->head); + *prev_insn_idx = head->prev_insn_idx; + elem = head->next; + free_verifier_state(&head->st, false); + kfree(head); env->head = elem; env->stack_size--; - return insn_idx; + return 0; } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) { + struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; + int err; - elem = kmalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); + elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL); if (!elem) goto err; - memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state)); elem->insn_idx = insn_idx; elem->prev_insn_idx = prev_insn_idx; elem->next = env->head; env->head = elem; env->stack_size++; + err = copy_verifier_state(&elem->st, cur); + if (err) + goto err; if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { - verbose("BPF program is too complex\n"); + verbose(env, "BPF program is too complex\n"); goto err; } return &elem->st; err: /* pop all elements and return */ - while (pop_stack(env, NULL) >= 0); + while (!pop_stack(env, NULL, NULL)); return NULL; } @@ -507,10 +449,11 @@ static void __mark_reg_known_zero(struct bpf_reg_state *reg) __mark_reg_known(reg, 0); } -static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_known_zero(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_known_zero(regs, %u)\n", regno); + verbose(env, "mark_reg_known_zero(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -519,6 +462,31 @@ 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) { @@ -595,10 +563,11 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg) __mark_reg_unbounded(reg); } -static void mark_reg_unknown(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_unknown(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_unknown(regs, %u)\n", regno); + verbose(env, "mark_reg_unknown(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -613,10 +582,11 @@ static void __mark_reg_not_init(struct bpf_reg_state *reg) reg->type = NOT_INIT; } -static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) +static void mark_reg_not_init(struct bpf_verifier_env *env, + struct bpf_reg_state *regs, u32 regno) { if (WARN_ON(regno >= MAX_BPF_REG)) { - verbose("mark_reg_not_init(regs, %u)\n", regno); + verbose(env, "mark_reg_not_init(regs, %u)\n", regno); /* Something bad happened, let's kill all regs */ for (regno = 0; regno < MAX_BPF_REG; regno++) __mark_reg_not_init(regs + regno); @@ -625,22 +595,23 @@ static void mark_reg_not_init(struct bpf_reg_state *regs, u32 regno) __mark_reg_not_init(regs + regno); } -static void init_reg_state(struct bpf_reg_state *regs) +static void init_reg_state(struct bpf_verifier_env *env, + struct bpf_reg_state *regs) { int i; for (i = 0; i < MAX_BPF_REG; i++) { - mark_reg_not_init(regs, i); + mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; } /* frame pointer */ regs[BPF_REG_FP].type = PTR_TO_STACK; - mark_reg_known_zero(regs, BPF_REG_FP); + mark_reg_known_zero(env, regs, BPF_REG_FP); /* 1st arg to a function */ regs[BPF_REG_1].type = PTR_TO_CTX; - mark_reg_known_zero(regs, BPF_REG_1); + mark_reg_known_zero(env, regs, BPF_REG_1); } enum reg_arg_type { @@ -653,6 +624,10 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) { struct bpf_verifier_state *parent = state->parent; + if (regno == BPF_REG_FP) + /* We don't need to worry about FP liveness because it's read-only */ + return; + while (parent) { /* if read wasn't screened by an earlier write ... */ if (state->regs[regno].live & REG_LIVE_WRITTEN) @@ -667,29 +642,29 @@ static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno) static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, enum reg_arg_type t) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = env->cur_state->regs; if (regno >= MAX_BPF_REG) { - verbose("R%d is invalid\n", regno); + verbose(env, "R%d is invalid\n", regno); return -EINVAL; } if (t == SRC_OP) { /* check whether register used as source operand can be read */ if (regs[regno].type == NOT_INIT) { - verbose("R%d !read_ok\n", regno); + verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - mark_reg_read(&env->cur_state, regno); + mark_reg_read(env->cur_state, regno); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { - verbose("frame pointer is read only\n"); + verbose(env, "frame pointer is read only\n"); return -EACCES; } regs[regno].live |= REG_LIVE_WRITTEN; if (t == DST_OP) - mark_reg_unknown(regs, regno); + mark_reg_unknown(env, regs, regno); } return 0; } @@ -702,6 +677,7 @@ 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; @@ -713,35 +689,48 @@ static bool is_spillable_regtype(enum bpf_reg_type type) /* check_stack_read/write functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ -static int check_stack_write(struct bpf_verifier_state *state, int off, +static int check_stack_write(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { - int i, spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; + int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err; + + err = realloc_verifier_state(state, round_up(slot + 1, BPF_REG_SIZE), + true); + if (err) + return err; /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0, * so it's aligned access and [off, off + size) are within stack limits */ + if (!env->allow_ptr_leaks && + state->stack[spi].slot_type[0] == STACK_SPILL && + size != BPF_REG_SIZE) { + verbose(env, "attempt to corrupt spilled pointer on stack\n"); + return -EACCES; + } if (value_regno >= 0 && is_spillable_regtype(state->regs[value_regno].type)) { /* register containing pointer is being spilled into stack */ if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } /* save register state */ - state->spilled_regs[spi] = state->regs[value_regno]; - state->spilled_regs[spi].live |= REG_LIVE_WRITTEN; + state->stack[spi].spilled_ptr = state->regs[value_regno]; + state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; for (i = 0; i < BPF_REG_SIZE; i++) - state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_SPILL; + state->stack[spi].slot_type[i] = STACK_SPILL; } else { /* regular write of data into stack */ - state->spilled_regs[spi] = (struct bpf_reg_state) {}; + state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; for (i = 0; i < size; i++) - state->stack_slot_type[MAX_BPF_STACK + off + i] = STACK_MISC; + state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] = + STACK_MISC; } return 0; } @@ -752,54 +741,58 @@ static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slo while (parent) { /* if read wasn't screened by an earlier write ... */ - if (state->spilled_regs[slot].live & REG_LIVE_WRITTEN) + if (state->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) break; /* ... then we depend on parent's value */ - parent->spilled_regs[slot].live |= REG_LIVE_READ; + parent->stack[slot].spilled_ptr.live |= REG_LIVE_READ; state = parent; parent = state->parent; } } -static int check_stack_read(struct bpf_verifier_state *state, int off, int size, +static int check_stack_read(struct bpf_verifier_env *env, + struct bpf_verifier_state *state, int off, int size, int value_regno) { - u8 *slot_type; - int i, spi; + int i, slot = -off - 1, spi = slot / BPF_REG_SIZE; + u8 *stype; - slot_type = &state->stack_slot_type[MAX_BPF_STACK + off]; + if (state->allocated_stack <= slot) { + verbose(env, "invalid read from stack off %d+0 size %d\n", + off, size); + return -EACCES; + } + stype = state->stack[spi].slot_type; - if (slot_type[0] == STACK_SPILL) { + if (stype[0] == STACK_SPILL) { if (size != BPF_REG_SIZE) { - verbose("invalid size of register spill\n"); + verbose(env, "invalid size of register spill\n"); return -EACCES; } for (i = 1; i < BPF_REG_SIZE; i++) { - if (slot_type[i] != STACK_SPILL) { - verbose("corrupted spill memory\n"); + if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) { + verbose(env, "corrupted spill memory\n"); return -EACCES; } } - spi = (MAX_BPF_STACK + off) / BPF_REG_SIZE; - if (value_regno >= 0) { /* restore register state from stack */ - state->regs[value_regno] = state->spilled_regs[spi]; + state->regs[value_regno] = state->stack[spi].spilled_ptr; mark_stack_slot_read(state, spi); } return 0; } else { for (i = 0; i < size; i++) { - if (slot_type[i] != STACK_MISC) { - verbose("invalid read from stack off %d+%d size %d\n", + if (stype[(slot - i) % BPF_REG_SIZE] != STACK_MISC) { + verbose(env, "invalid read from stack off %d+%d size %d\n", off, i, size); return -EACCES; } } if (value_regno >= 0) /* have read misc data from the stack */ - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, state->regs, value_regno); return 0; } } @@ -808,10 +801,11 @@ static int check_stack_read(struct bpf_verifier_state *state, int off, int size, static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { - struct bpf_map *map = env->cur_state.regs[regno].map_ptr; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_map *map = regs[regno].map_ptr; if (off < 0 || size <= 0 || off + size > map->value_size) { - verbose("invalid access to map value, value_size=%d off=%d size=%d\n", + verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n", map->value_size, off, size); return -EACCES; } @@ -820,9 +814,9 @@ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, /* check read/write into a map element with possible variable offset */ static int check_map_access(struct bpf_verifier_env *env, u32 regno, - int off, int size) + int off, int size) { - struct bpf_verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *reg = &state->regs[regno]; int err; @@ -830,8 +824,8 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. */ - if (log_level) - print_verifier_state(state); + if (env->log.level) + print_verifier_state(env, state); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our @@ -839,13 +833,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * will have a set floor within our range. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->smin_value + off, size); if (err) { - verbose("R%d min value is outside of the array range\n", regno); + verbose(env, "R%d min value is outside of the array range\n", + regno); return err; } @@ -854,13 +849,14 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, * If reg->umax_value + off could overflow, treat that as unbounded too. */ if (reg->umax_value >= BPF_MAX_VAR_OFF) { - verbose("R%d unbounded memory access, make sure to bounds check any array access into a map\n", + verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n", regno); return -EACCES; } err = __check_map_access(env, regno, reg->umax_value + off, size); if (err) - verbose("R%d max value is outside of the array range\n", regno); + verbose(env, "R%d max value is outside of the array range\n", + regno); return err; } @@ -895,11 +891,11 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; if (off < 0 || size <= 0 || (u64)off + size > reg->range) { - verbose("invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", + verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n", off, size, regno, reg->id, reg->off, reg->range); return -EACCES; } @@ -909,7 +905,7 @@ static int __check_packet_access(struct bpf_verifier_env *env, u32 regno, static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, int size) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; int err; @@ -922,13 +918,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, * detail to prove they're safe. */ if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", + verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; } err = __check_packet_access(env, regno, off, size); if (err) { - verbose("R%d offset is outside of the packet\n", regno); + verbose(env, "R%d offset is outside of the packet\n", regno); return err; } return err; @@ -942,12 +938,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, .reg_type = *reg_type, }; - /* for analyzer ctx accesses are already validated and converted */ - if (env->analyzer_ops) - return 0; - - if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + if (env->ops->is_valid_access && + env->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -955,16 +947,16 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, * will only allow for whole field access and rejects any other * type of narrower access. */ - env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; *reg_type = info.reg_type; + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; return 0; } - verbose("invalid bpf_context access off=%d size=%d\n", off, size); + verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size); return -EACCES; } @@ -979,10 +971,11 @@ static bool __is_pointer_value(bool allow_ptr_leaks, static bool is_pointer_value(struct bpf_verifier_env *env, int regno) { - return __is_pointer_value(env->allow_ptr_leaks, &env->cur_state.regs[regno]); + return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno); } -static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, +static int check_pkt_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int off, int size, bool strict) { struct tnum reg_off; @@ -1007,7 +1000,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned packet access off %d+%s+%d+%d size %d\n", + verbose(env, + "misaligned packet access off %d+%s+%d+%d size %d\n", ip_align, tn_buf, reg->off, off, size); return -EACCES; } @@ -1015,7 +1009,8 @@ static int check_pkt_ptr_alignment(const struct bpf_reg_state *reg, return 0; } -static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, +static int check_generic_ptr_alignment(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, const char *pointer_desc, int off, int size, bool strict) { @@ -1030,7 +1025,7 @@ static int check_generic_ptr_alignment(const struct bpf_reg_state *reg, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("misaligned %saccess off %s+%d+%d size %d\n", + verbose(env, "misaligned %saccess off %s+%d+%d size %d\n", pointer_desc, tn_buf, reg->off, off, size); return -EACCES; } @@ -1047,8 +1042,11 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ - return check_pkt_ptr_alignment(reg, off, size, strict); + 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(env, reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; break; @@ -1061,7 +1059,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, default: break; } - return check_generic_ptr_alignment(reg, pointer_desc, off, size, strict); + return check_generic_ptr_alignment(env, reg, pointer_desc, off, size, + strict); } /* check whether memory at (regno + off) is accessible for t = (read | write) @@ -1074,8 +1073,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn int bpf_size, enum bpf_access_type t, int value_regno) { - struct bpf_verifier_state *state = &env->cur_state; - struct bpf_reg_state *reg = &state->regs[regno]; + struct bpf_verifier_state *state = env->cur_state; + struct bpf_reg_state *regs = cur_regs(env); + struct bpf_reg_state *reg = regs + regno; int size, err = 0; size = bpf_size_to_bytes(bpf_size); @@ -1093,48 +1093,55 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (reg->type == PTR_TO_MAP_VALUE) { if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into map\n", value_regno); + verbose(env, "R%d leaks addr into map\n", value_regno); return -EACCES; } err = check_map_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into ctx\n", value_regno); + verbose(env, "R%d leaks addr into ctx\n", value_regno); return -EACCES; } /* ctx accesses must be at a fixed offset, so that we can * determine what type of data were returned. */ - if (!tnum_is_const(reg->var_off)) { + if (reg->off) { + verbose(env, + "dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n", + regno, reg->off, off - reg->off); + return -EACCES; + } + if (!tnum_is_const(reg->var_off) || reg->var_off.value) { char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable ctx access var_off=%s off=%d size=%d", + verbose(env, + "variable ctx access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } - off += reg->var_off.value; 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); + mark_reg_unknown(env, regs, value_regno); else - mark_reg_known_zero(state->regs, value_regno); - state->regs[value_regno].id = 0; - state->regs[value_regno].off = 0; - state->regs[value_regno].range = 0; - state->regs[value_regno].type = reg_type; + mark_reg_known_zero(env, regs, + value_regno); + regs[value_regno].id = 0; + regs[value_regno].off = 0; + regs[value_regno].range = 0; + regs[value_regno].type = reg_type; } } else if (reg->type == PTR_TO_STACK) { @@ -1146,55 +1153,52 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose("variable stack access var_off=%s off=%d size=%d", + verbose(env, "variable stack access var_off=%s off=%d size=%d", tn_buf, off, size); return -EACCES; } off += reg->var_off.value; if (off >= 0 || off < -MAX_BPF_STACK) { - verbose("invalid stack off=%d size=%d\n", off, size); + verbose(env, "invalid stack off=%d size=%d\n", off, + size); return -EACCES; } if (env->prog->aux->stack_depth < -off) env->prog->aux->stack_depth = -off; - if (t == BPF_WRITE) { - if (!env->allow_ptr_leaks && - state->stack_slot_type[MAX_BPF_STACK + off] == STACK_SPILL && - size != BPF_REG_SIZE) { - verbose("attempt to corrupt spilled pointer on stack\n"); - return -EACCES; - } - err = check_stack_write(state, off, size, value_regno); - } else { - err = check_stack_read(state, off, size, value_regno); - } - } else if (reg->type == PTR_TO_PACKET) { + if (t == BPF_WRITE) + err = check_stack_write(env, state, off, size, + value_regno); + else + err = check_stack_read(env, state, off, size, + value_regno); + } 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"); + verbose(env, "cannot write into packet\n"); return -EACCES; } if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { - verbose("R%d leaks addr into packet\n", value_regno); + verbose(env, "R%d leaks addr into packet\n", + value_regno); return -EACCES; } err = check_packet_access(env, regno, off, size); if (!err && t == BPF_READ && value_regno >= 0) - mark_reg_unknown(state->regs, value_regno); + mark_reg_unknown(env, regs, value_regno); } else { - verbose("R%d invalid mem access '%s'\n", - regno, reg_type_str[reg->type]); + verbose(env, "R%d invalid mem access '%s'\n", regno, + reg_type_str[reg->type]); return -EACCES; } if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && - state->regs[value_regno].type == SCALAR_VALUE) { + regs[value_regno].type == SCALAR_VALUE) { /* b/h/w load zero-extends, mark upper bits as known 0 */ - state->regs[value_regno].var_off = tnum_cast( - state->regs[value_regno].var_off, size); - __update_reg_bounds(&state->regs[value_regno]); + regs[value_regno].var_off = + tnum_cast(regs[value_regno].var_off, size); + __update_reg_bounds(®s[value_regno]); } return err; } @@ -1205,7 +1209,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) || insn->imm != 0) { - verbose("BPF_XADD uses reserved fields\n"); + verbose(env, "BPF_XADD uses reserved fields\n"); return -EINVAL; } @@ -1220,7 +1224,7 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d leaks addr into mem\n", insn->src_reg); + verbose(env, "R%d leaks addr into mem\n", insn->src_reg); return -EACCES; } @@ -1251,9 +1255,9 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { - struct bpf_verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = state->regs; - int off, i; + int off, i, slot, spi; if (regs[regno].type != PTR_TO_STACK) { /* Allow zero-byte read from NULL, regardless of pointer type */ @@ -1261,7 +1265,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, register_is_null(regs[regno])) return 0; - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[regs[regno].type], reg_type_str[PTR_TO_STACK]); return -EACCES; @@ -1272,13 +1276,13 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off); - verbose("invalid variable stack read R%d var_off=%s\n", + verbose(env, "invalid variable stack read R%d var_off=%s\n", regno, tn_buf); } off = regs[regno].off + regs[regno].var_off.value; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || access_size <= 0) { - verbose("invalid stack type R%d off=%d access_size=%d\n", + verbose(env, "invalid stack type R%d off=%d access_size=%d\n", regno, off, access_size); return -EACCES; } @@ -1293,8 +1297,12 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, } for (i = 0; i < access_size; i++) { - if (state->stack_slot_type[MAX_BPF_STACK + off + i] != STACK_MISC) { - verbose("invalid indirect read from stack off %d+%d size %d\n", + slot = -(off + i) - 1; + spi = slot / BPF_REG_SIZE; + if (state->allocated_stack <= slot || + state->stack[spi].slot_type[slot % BPF_REG_SIZE] != + STACK_MISC) { + verbose(env, "invalid indirect read from stack off %d+%d size %d\n", off, i, access_size); return -EACCES; } @@ -1306,10 +1314,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, int access_size, bool zero_size_allowed, struct bpf_call_arg_meta *meta) { - struct bpf_reg_state *regs = env->cur_state.regs, *reg = ®s[regno]; + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[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); @@ -1323,7 +1332,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) { - struct bpf_reg_state *regs = env->cur_state.regs, *reg = ®s[regno]; + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; enum bpf_reg_type expected_type, type = reg->type; int err = 0; @@ -1336,22 +1345,24 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_ANYTHING) { if (is_pointer_value(env, regno)) { - verbose("R%d leaks addr into helper function\n", regno); + verbose(env, "R%d leaks addr into helper function\n", + regno); return -EACCES; } 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"); + verbose(env, "helper access to the packet is not allowed\n"); return -EACCES; } 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) { @@ -1375,12 +1386,13 @@ 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; } else { - verbose("unsupported arg_type %d\n", arg_type); + verbose(env, "unsupported arg_type %d\n", arg_type); return -EFAULT; } @@ -1398,10 +1410,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, * we have to check map_key here. Otherwise it means * that kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->key\n"); + verbose(env, "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 @@ -1414,10 +1426,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (!meta->map_ptr) { /* kernel subsystem misconfigured verifier */ - verbose("invalid map_ptr to access map->value\n"); + verbose(env, "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 @@ -1434,7 +1446,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (regno == 0) { /* kernel subsystem misconfigured verifier */ - verbose("ARG_CONST_SIZE cannot be first argument\n"); + verbose(env, + "ARG_CONST_SIZE cannot be first argument\n"); return -EACCES; } @@ -1451,7 +1464,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, meta = NULL; if (reg->smin_value < 0) { - verbose("R%d min value is negative, either use unsigned or 'var &= const'\n", + verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n", regno); return -EACCES; } @@ -1465,7 +1478,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (reg->umax_value >= BPF_MAX_VAR_SIZ) { - verbose("R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", + verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n", regno); return -EACCES; } @@ -1476,12 +1489,13 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return err; err_type: - verbose("R%d type=%s expected=%s\n", regno, + verbose(env, "R%d type=%s expected=%s\n", regno, reg_type_str[type], reg_type_str[expected_type]); return -EACCES; } -static int check_map_func_compatibility(struct bpf_map *map, int func_id) +static int check_map_func_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, int func_id) { if (!map) return 0; @@ -1494,7 +1508,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_MAP_TYPE_PERF_EVENT_ARRAY: if (func_id != BPF_FUNC_perf_event_read && - func_id != BPF_FUNC_perf_event_output) + func_id != BPF_FUNC_perf_event_output && + func_id != BPF_FUNC_perf_event_read_value) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -1514,6 +1529,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (func_id != BPF_FUNC_redirect_map) goto error; break; + /* Restrict bpf side of cpumap, open when use-cases appear */ + case BPF_MAP_TYPE_CPUMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) @@ -1537,6 +1557,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) break; case BPF_FUNC_perf_event_read: case BPF_FUNC_perf_event_output: + case BPF_FUNC_perf_event_read_value: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -1550,7 +1571,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_FUNC_redirect_map: - if (map->map_type != BPF_MAP_TYPE_DEVMAP) + if (map->map_type != BPF_MAP_TYPE_DEVMAP && + map->map_type != BPF_MAP_TYPE_CPUMAP) goto error; break; case BPF_FUNC_sk_redirect_map: @@ -1567,7 +1589,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) return 0; error: - verbose("cannot pass map_type %d into func %s#%d\n", + verbose(env, "cannot pass map_type %d into func %s#%d\n", map->map_type, func_id_name(func_id), func_id); return -EINVAL; } @@ -1590,57 +1612,55 @@ 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) { - struct bpf_verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state = env->cur_state; struct bpf_reg_state *regs = state->regs, *reg; int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) - mark_reg_unknown(regs, i); + if (reg_is_pkt_pointer_any(®s[i])) + mark_reg_unknown(env, 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) + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) continue; - __mark_reg_unknown(reg); + reg = &state->stack[i].spilled_ptr; + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { - struct bpf_verifier_state *state = &env->cur_state; const struct bpf_func_proto *fn = NULL; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; bool changes_data; int i, err; /* find function prototype */ if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) { - verbose("invalid func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "invalid func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } - if (env->prog->aux->ops->get_func_proto) - fn = env->prog->aux->ops->get_func_proto(func_id); + if (env->ops->get_func_proto) + fn = env->ops->get_func_proto(func_id); if (!fn) { - verbose("unknown func %s#%d\n", func_id_name(func_id), func_id); + verbose(env, "unknown func %s#%d\n", func_id_name(func_id), + func_id); return -EINVAL; } /* eBPF programs must be GPL compatible to use GPL-ed functions */ if (!env->prog->gpl_compatible && fn->gpl_only) { - verbose("cannot call GPL only function from proprietary program\n"); + verbose(env, "cannot call GPL only function from proprietary program\n"); return -EINVAL; } @@ -1654,7 +1674,7 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) */ err = check_raw_mode(fn); if (err) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, "kernel subsystem misconfigured func %s#%d\n", func_id_name(func_id), func_id); return err; } @@ -1685,16 +1705,17 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return err; } + regs = cur_regs(env); /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } /* update return register (already marked as written above) */ if (fn->ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); } else if (fn->ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) { @@ -1702,14 +1723,15 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ - mark_reg_known_zero(regs, BPF_REG_0); + mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].off = 0; /* remember map_ptr, so that check_map_access() * can check 'value_size' boundary of memory access * to map element returned from bpf_map_lookup_elem() */ if (meta.map_ptr == NULL) { - verbose("kernel subsystem misconfigured verifier\n"); + verbose(env, + "kernel subsystem misconfigured verifier\n"); return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; @@ -1720,12 +1742,12 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) else if (insn_aux->map_ptr != meta.map_ptr) insn_aux->map_ptr = BPF_MAP_PTR_POISON; } else { - verbose("unknown return type %d of func %s#%d\n", + verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } - err = check_map_func_compatibility(meta.map_ptr, func_id); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; @@ -1772,7 +1794,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, const struct bpf_reg_state *ptr_reg, const struct bpf_reg_state *off_reg) { - struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; + struct bpf_reg_state *regs = cur_regs(env), *dst_reg; bool known = tnum_is_const(off_reg->var_off); s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; @@ -1784,39 +1806,42 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[dst]; if (WARN_ON_ONCE(known && (smin_val != smax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad sbounds\n"); + print_verifier_state(env, env->cur_state); + verbose(env, + "verifier internal error: known but bad sbounds\n"); return -EINVAL; } if (WARN_ON_ONCE(known && (umin_val != umax_val))) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: known but bad ubounds\n"); + print_verifier_state(env, env->cur_state); + verbose(env, + "verifier internal error: known but bad ubounds\n"); return -EINVAL; } if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ if (!env->allow_ptr_leaks) - verbose("R%d 32-bit pointer arithmetic prohibited\n", + verbose(env, + "R%d 32-bit pointer arithmetic prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", dst); return -EACCES; } @@ -1871,7 +1896,7 @@ 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; @@ -1881,7 +1906,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ if (!env->allow_ptr_leaks) - verbose("R%d tried to subtract pointer from scalar\n", + verbose(env, "R%d tried to subtract pointer from scalar\n", dst); return -EACCES; } @@ -1891,7 +1916,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, */ if (ptr_reg->type == PTR_TO_STACK) { if (!env->allow_ptr_leaks) - verbose("R%d subtraction from stack pointer prohibited\n", + verbose(env, "R%d subtraction from stack pointer prohibited\n", dst); return -EACCES; } @@ -1931,7 +1956,7 @@ 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) @@ -1946,13 +1971,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * ptr &= ~3 which would reduce min_value by 3.) */ if (!env->allow_ptr_leaks) - verbose("R%d bitwise operator %s on pointer prohibited\n", + verbose(env, "R%d bitwise operator %s on pointer prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ if (!env->allow_ptr_leaks) - verbose("R%d pointer arithmetic with %s operator prohibited\n", + verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", dst, bpf_alu_string[opcode >> 4]); return -EACCES; } @@ -1968,7 +1993,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *dst_reg, struct bpf_reg_state src_reg) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); bool src_known, dst_known; s64 smin_val, smax_val; @@ -2118,7 +2143,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* We lose all sign bit information (except what we can pick @@ -2146,7 +2171,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, /* Shifts greater than 63 are undefined. This includes * shifts by a negative number. */ - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } /* BPF_RSH is an unsigned shift, so make the appropriate casts */ @@ -2174,7 +2199,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); break; default: - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); break; } @@ -2189,7 +2214,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg, *src_reg; + struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); int rc; @@ -2206,12 +2231,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. */ if (!env->allow_ptr_leaks) { - verbose("R%d pointer %s pointer prohibited\n", + verbose(env, "R%d pointer %s pointer prohibited\n", insn->dst_reg, bpf_alu_string[opcode >> 4]); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); return 0; } else { /* scalar += pointer @@ -2263,13 +2288,13 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: unexpected ptr_reg\n"); + print_verifier_state(env, env->cur_state); + verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(&env->cur_state); - verbose("verifier internal error: no src_reg\n"); + print_verifier_state(env, env->cur_state); + verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg); @@ -2278,7 +2303,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* check validity of 32-bit and 64-bit arithmetic operations */ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); u8 opcode = BPF_OP(insn->code); int err; @@ -2287,14 +2312,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) != 0 || insn->src_reg != BPF_REG_0 || insn->off != 0 || insn->imm != 0) { - verbose("BPF_NEG uses reserved fields\n"); + verbose(env, "BPF_NEG uses reserved fields\n"); return -EINVAL; } } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0 || (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) || BPF_CLASS(insn->code) == BPF_ALU64) { - verbose("BPF_END uses reserved fields\n"); + verbose(env, "BPF_END uses reserved fields\n"); return -EINVAL; } } @@ -2305,7 +2330,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer arithmetic prohibited\n", + verbose(env, "R%d pointer arithmetic prohibited\n", insn->dst_reg); return -EACCES; } @@ -2319,7 +2344,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } @@ -2329,7 +2354,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_MOV uses reserved fields\n"); + verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } } @@ -2345,14 +2370,16 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * copy register state to dest reg */ regs[insn->dst_reg] = regs[insn->src_reg]; + regs[insn->dst_reg].live |= REG_LIVE_WRITTEN; } else { /* R1 = (u32) R2 */ if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d partial copy of pointer\n", + verbose(env, + "R%d partial copy of pointer\n", insn->src_reg); return -EACCES; } - mark_reg_unknown(regs, insn->dst_reg); + mark_reg_unknown(env, regs, insn->dst_reg); /* high 32 bits are known zero. */ regs[insn->dst_reg].var_off = tnum_cast( regs[insn->dst_reg].var_off, 4); @@ -2367,14 +2394,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } } else if (opcode > BPF_END) { - verbose("invalid BPF_ALU opcode %x\n", opcode); + verbose(env, "invalid BPF_ALU opcode %x\n", opcode); return -EINVAL; } else { /* all other ALU ops: and, sub, xor, add, ... */ if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } /* check src1 operand */ @@ -2383,7 +2410,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } else { if (insn->src_reg != BPF_REG_0 || insn->off != 0) { - verbose("BPF_ALU uses reserved fields\n"); + verbose(env, "BPF_ALU uses reserved fields\n"); return -EINVAL; } } @@ -2395,7 +2422,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if ((opcode == BPF_MOD || opcode == BPF_DIV) && BPF_SRC(insn->code) == BPF_K && insn->imm == 0) { - verbose("div by zero\n"); + verbose(env, "div by zero\n"); return -EINVAL; } @@ -2404,7 +2431,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; if (insn->imm < 0 || insn->imm >= size) { - verbose("invalid shift %d\n", insn->imm); + verbose(env, "invalid shift %d\n", insn->imm); return -EINVAL; } } @@ -2421,12 +2448,16 @@ 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, + bool range_right_open) { struct bpf_reg_state *regs = state->regs, *reg; + u16 new_range; int i; - if (dst_reg->off < 0) + if (dst_reg->off < 0 || + (dst_reg->off == 0 && range_right_open)) /* This doesn't give us any range */ return; @@ -2437,9 +2468,13 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, */ return; - /* LLVM can generate four kind of checks: + new_range = dst_reg->off; + if (range_right_open) + new_range--; + + /* Examples for register markings: * - * Type 1/2: + * pkt_data in dst register: * * r2 = r3; * r2 += 8; @@ -2456,7 +2491,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r2=pkt(id=n,off=8,r=0) * r3=pkt(id=n,off=0,r=0) * - * Type 3/4: + * pkt_data in src register: * * r2 = r3; * r2 += 8; @@ -2474,7 +2509,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * r3=pkt(id=n,off=0,r=0) * * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8) - * so that range of bytes [r3, r3 + 8) is safe to access. + * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8) + * and [r3, r3 + 8-1) respectively is safe to access depending on + * the check. */ /* If our ids match, then we must have the same max_value. And we @@ -2483,16 +2520,16 @@ 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); + regs[i].range = max(regs[i].range, new_range); - for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { - if (state->stack_slot_type[i] != STACK_SPILL) + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) continue; - reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) - reg->range = max_t(u16, reg->range, dst_reg->off); + reg = &state->stack[i].spilled_ptr; + if (reg->type == type && reg->id == dst_reg->id) + reg->range = max(reg->range, new_range); } } @@ -2740,29 +2777,122 @@ static void mark_map_regs(struct bpf_verifier_state *state, u32 regno, for (i = 0; i < MAX_BPF_REG; i++) mark_map_reg(regs, i, id, is_null); - for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { - if (state->stack_slot_type[i] != STACK_SPILL) + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) continue; - mark_map_reg(state->spilled_regs, i / BPF_REG_SIZE, id, is_null); + mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null); + } +} + +static bool try_match_pkt_pointers(const struct bpf_insn *insn, + struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg, + struct bpf_verifier_state *this_branch, + struct bpf_verifier_state *other_branch) +{ + if (BPF_SRC(insn->code) != BPF_X) + return false; + + switch (BPF_OP(insn->code)) { + case BPF_JGT: + if ((dst_reg->type == PTR_TO_PACKET && + src_reg->type == PTR_TO_PACKET_END) || + (dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { + /* pkt_data' > pkt_end, pkt_meta' > pkt_data */ + find_good_pkt_pointers(this_branch, dst_reg, + dst_reg->type, false); + } else if ((dst_reg->type == PTR_TO_PACKET_END && + src_reg->type == PTR_TO_PACKET) || + (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + src_reg->type == PTR_TO_PACKET_META)) { + /* pkt_end > pkt_data', pkt_data > pkt_meta' */ + find_good_pkt_pointers(other_branch, src_reg, + src_reg->type, true); + } else { + return false; + } + break; + case BPF_JLT: + if ((dst_reg->type == PTR_TO_PACKET && + src_reg->type == PTR_TO_PACKET_END) || + (dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { + /* pkt_data' < pkt_end, pkt_meta' < pkt_data */ + find_good_pkt_pointers(other_branch, dst_reg, + dst_reg->type, true); + } else if ((dst_reg->type == PTR_TO_PACKET_END && + src_reg->type == PTR_TO_PACKET) || + (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + src_reg->type == PTR_TO_PACKET_META)) { + /* pkt_end < pkt_data', pkt_data > pkt_meta' */ + find_good_pkt_pointers(this_branch, src_reg, + src_reg->type, false); + } else { + return false; + } + break; + case BPF_JGE: + if ((dst_reg->type == PTR_TO_PACKET && + src_reg->type == PTR_TO_PACKET_END) || + (dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { + /* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */ + find_good_pkt_pointers(this_branch, dst_reg, + dst_reg->type, true); + } else if ((dst_reg->type == PTR_TO_PACKET_END && + src_reg->type == PTR_TO_PACKET) || + (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + src_reg->type == PTR_TO_PACKET_META)) { + /* pkt_end >= pkt_data', pkt_data >= pkt_meta' */ + find_good_pkt_pointers(other_branch, src_reg, + src_reg->type, false); + } else { + return false; + } + break; + case BPF_JLE: + if ((dst_reg->type == PTR_TO_PACKET && + src_reg->type == PTR_TO_PACKET_END) || + (dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) { + /* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */ + find_good_pkt_pointers(other_branch, dst_reg, + dst_reg->type, false); + } else if ((dst_reg->type == PTR_TO_PACKET_END && + src_reg->type == PTR_TO_PACKET) || + (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + src_reg->type == PTR_TO_PACKET_META)) { + /* pkt_end <= pkt_data', pkt_data <= pkt_meta' */ + find_good_pkt_pointers(this_branch, src_reg, + src_reg->type, true); + } else { + return false; + } + break; + default: + return false; } + + return true; } static int check_cond_jmp_op(struct bpf_verifier_env *env, struct bpf_insn *insn, int *insn_idx) { - struct bpf_verifier_state *other_branch, *this_branch = &env->cur_state; + struct bpf_verifier_state *other_branch, *this_branch = env->cur_state; struct bpf_reg_state *regs = this_branch->regs, *dst_reg; u8 opcode = BPF_OP(insn->code); int err; if (opcode > BPF_JSLE) { - verbose("invalid BPF_JMP opcode %x\n", opcode); + verbose(env, "invalid BPF_JMP opcode %x\n", opcode); return -EINVAL; } if (BPF_SRC(insn->code) == BPF_X) { if (insn->imm != 0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } @@ -2772,13 +2902,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return err; if (is_pointer_value(env, insn->src_reg)) { - verbose("R%d pointer comparison prohibited\n", + verbose(env, "R%d pointer comparison prohibited\n", insn->src_reg); return -EACCES; } } else { if (insn->src_reg != BPF_REG_0) { - verbose("BPF_JMP uses reserved fields\n"); + verbose(env, "BPF_JMP uses reserved fields\n"); return -EINVAL; } } @@ -2853,28 +2983,15 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE); mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ); - } 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); - } 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); - } 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]); - } 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]); - } else if (is_pointer_value(env, insn->dst_reg)) { - verbose("R%d pointer comparison prohibited\n", insn->dst_reg); + } else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg], + this_branch, other_branch) && + is_pointer_value(env, insn->dst_reg)) { + verbose(env, "R%d pointer comparison prohibited\n", + insn->dst_reg); return -EACCES; } - if (log_level) - print_verifier_state(this_branch); + if (env->log.level) + print_verifier_state(env, this_branch); return 0; } @@ -2889,15 +3006,15 @@ static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn) /* verify BPF_LD_IMM64 instruction */ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); int err; if (BPF_SIZE(insn->code) != BPF_DW) { - verbose("invalid BPF_LD_IMM insn\n"); + verbose(env, "invalid BPF_LD_IMM insn\n"); return -EINVAL; } if (insn->off != 0) { - verbose("BPF_LD_IMM64 uses reserved fields\n"); + verbose(env, "BPF_LD_IMM64 uses reserved fields\n"); return -EINVAL; } @@ -2950,19 +3067,19 @@ static bool may_access_skb(enum bpf_prog_type type) */ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) { - struct bpf_reg_state *regs = env->cur_state.regs; + struct bpf_reg_state *regs = cur_regs(env); u8 mode = BPF_MODE(insn->code); int i, err; if (!may_access_skb(env->prog->type)) { - verbose("BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); + verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n"); return -EINVAL; } if (insn->dst_reg != BPF_REG_0 || insn->off != 0 || BPF_SIZE(insn->code) == BPF_DW || (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) { - verbose("BPF_LD_[ABS|IND] uses reserved fields\n"); + verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n"); return -EINVAL; } @@ -2972,7 +3089,8 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; if (regs[BPF_REG_6].type != PTR_TO_CTX) { - verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); + verbose(env, + "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); return -EINVAL; } @@ -2985,7 +3103,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) /* reset caller saved regs to unreadable */ for (i = 0; i < CALLER_SAVED_REGS; i++) { - mark_reg_not_init(regs, caller_saved[i]); + mark_reg_not_init(env, regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); } @@ -2993,7 +3111,45 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) * the value fetched from the packet. * Already marked as written above. */ - mark_reg_unknown(regs, BPF_REG_0); + mark_reg_unknown(env, regs, BPF_REG_0); + 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: + case BPF_PROG_TYPE_CGROUP_DEVICE: + break; + default: + return 0; + } + + reg = cur_regs(env) + BPF_REG_0; + if (reg->type != SCALAR_VALUE) { + verbose(env, "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(env, "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(env, "has value %s", tn_buf); + } else { + verbose(env, "has unknown scalar value"); + } + verbose(env, " should have been 0 or 1\n"); + return -EINVAL; + } return 0; } @@ -3057,7 +3213,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) return 0; if (w < 0 || w >= env->prog->len) { - verbose("jump out of range from insn %d to %d\n", t, w); + verbose(env, "jump out of range from insn %d to %d\n", t, w); return -EINVAL; } @@ -3074,13 +3230,13 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env) insn_stack[cur_stack++] = w; return 1; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { - verbose("back-edge from insn %d to %d\n", t, w); + verbose(env, "back-edge from insn %d to %d\n", t, w); return -EINVAL; } else if (insn_state[w] == EXPLORED) { /* forward- or cross-edge */ insn_state[t] = DISCOVERED | e; } else { - verbose("insn state internal bug\n"); + verbose(env, "insn state internal bug\n"); return -EFAULT; } return 0; @@ -3174,7 +3330,7 @@ peek_stack: mark_explored: insn_state[t] = EXPLORED; if (cur_stack-- <= 0) { - verbose("pop stack internal bug\n"); + verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } @@ -3183,7 +3339,7 @@ mark_explored: check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { - verbose("unreachable insn %d\n", i); + verbose(env, "unreachable insn %d\n", i); ret = -EINVAL; goto err_free; } @@ -3298,8 +3454,9 @@ 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 @@ -3337,6 +3494,57 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; } +static bool stacksafe(struct bpf_verifier_state *old, + struct bpf_verifier_state *cur, + struct idpair *idmap) +{ + int i, spi; + + /* if explored stack has more populated slots than current stack + * such stacks are not equivalent + */ + if (old->allocated_stack > cur->allocated_stack) + return false; + + /* walk slots of the explored stack and ignore any additional + * slots in the current stack, since explored(safe) state + * didn't use them + */ + for (i = 0; i < old->allocated_stack; i++) { + spi = i / BPF_REG_SIZE; + + if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID) + continue; + if (old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + /* Ex: old explored (safe) state has STACK_SPILL in + * this stack slot, but current has has STACK_MISC -> + * this verifier states are not equivalent, + * return false to continue verification of this path + */ + return false; + if (i % BPF_REG_SIZE) + continue; + if (old->stack[spi].slot_type[0] != STACK_SPILL) + continue; + if (!regsafe(&old->stack[spi].spilled_ptr, + &cur->stack[spi].spilled_ptr, + idmap)) + /* when explored and current stack slot are both storing + * spilled registers, check that stored pointers types + * are the same as well. + * Ex: explored safe path could have stored + * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} + * but current path has stored: + * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} + * such verifier states are not equivalent. + * return false to continue verification of this path + */ + return false; + } + return true; +} + /* compare two verifier states * * all states stored in state_list are known to be valid, since @@ -3381,37 +3589,8 @@ static bool states_equal(struct bpf_verifier_env *env, goto out_free; } - for (i = 0; i < MAX_BPF_STACK; i++) { - if (old->stack_slot_type[i] == STACK_INVALID) - continue; - if (old->stack_slot_type[i] != cur->stack_slot_type[i]) - /* Ex: old explored (safe) state has STACK_SPILL in - * this stack slot, but current has has STACK_MISC -> - * this verifier states are not equivalent, - * return false to continue verification of this path - */ - goto out_free; - if (i % BPF_REG_SIZE) - continue; - if (old->stack_slot_type[i] != STACK_SPILL) - continue; - if (!regsafe(&old->spilled_regs[i / BPF_REG_SIZE], - &cur->spilled_regs[i / BPF_REG_SIZE], - idmap)) - /* when explored and current stack slot are both storing - * spilled registers, check that stored pointers types - * are the same as well. - * Ex: explored safe path could have stored - * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -8} - * but current path has stored: - * (bpf_reg_state) {.type = PTR_TO_STACK, .off = -16} - * such verifier states are not equivalent. - * return false to continue verification of this path - */ - goto out_free; - else - continue; - } + if (!stacksafe(old, cur, idmap)) + goto out_free; ret = true; out_free: kfree(idmap); @@ -3447,17 +3626,19 @@ static bool do_propagate_liveness(const struct bpf_verifier_state *state, } } /* ... and stack slots */ - for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) { - if (parent->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL) + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE && + i < parent->allocated_stack / BPF_REG_SIZE; i++) { + if (parent->stack[i].slot_type[0] != STACK_SPILL) continue; - if (state->stack_slot_type[i * BPF_REG_SIZE] != STACK_SPILL) + if (state->stack[i].slot_type[0] != STACK_SPILL) continue; - if (parent->spilled_regs[i].live & REG_LIVE_READ) + if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) continue; - if (writes && (state->spilled_regs[i].live & REG_LIVE_WRITTEN)) + if (writes && + (state->stack[i].spilled_ptr.live & REG_LIVE_WRITTEN)) continue; - if (state->spilled_regs[i].live & REG_LIVE_READ) { - parent->spilled_regs[i].live |= REG_LIVE_READ; + if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) { + parent->stack[i].spilled_ptr.live |= REG_LIVE_READ; touched = true; } } @@ -3487,7 +3668,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; - int i; + struct bpf_verifier_state *cur = env->cur_state; + int i, err; sl = env->explored_states[insn_idx]; if (!sl) @@ -3497,7 +3679,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return 0; while (sl != STATE_LIST_MARK) { - if (states_equal(env, &sl->state, &env->cur_state)) { + if (states_equal(env, &sl->state, cur)) { /* reached equivalent register/stack state, * prune the search. * Registers read by the continuation are read by us. @@ -3508,7 +3690,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * they'll be immediately forgotten as we're pruning * this state and will pop a new one. */ - propagate_liveness(&sl->state, &env->cur_state); + propagate_liveness(&sl->state, cur); return 1; } sl = sl->next; @@ -3520,16 +3702,21 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * it will be rejected. Since there are no loops, we won't be * seeing this 'insn_idx' instruction again on the way to bpf_exit */ - new_sl = kmalloc(sizeof(struct bpf_verifier_state_list), GFP_USER); + new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL); if (!new_sl) return -ENOMEM; /* add new state to the head of linked list */ - memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state)); + err = copy_verifier_state(&new_sl->state, cur); + if (err) { + free_verifier_state(&new_sl->state, false); + kfree(new_sl); + return err; + } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; /* connect new state to parentage chain */ - env->cur_state.parent = &new_sl->state; + cur->parent = &new_sl->state; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -3537,33 +3724,37 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * explored_states can get read marks.) */ for (i = 0; i < BPF_REG_FP; i++) - env->cur_state.regs[i].live = REG_LIVE_NONE; - for (i = 0; i < MAX_BPF_STACK / BPF_REG_SIZE; i++) - if (env->cur_state.stack_slot_type[i * BPF_REG_SIZE] == STACK_SPILL) - env->cur_state.spilled_regs[i].live = REG_LIVE_NONE; + cur->regs[i].live = REG_LIVE_NONE; + for (i = 0; i < cur->allocated_stack / BPF_REG_SIZE; i++) + if (cur->stack[i].slot_type[0] == STACK_SPILL) + cur->stack[i].spilled_ptr.live = REG_LIVE_NONE; return 0; } static int ext_analyzer_insn_hook(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) { - if (!env->analyzer_ops || !env->analyzer_ops->insn_hook) - return 0; + if (env->dev_ops && env->dev_ops->insn_hook) + return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx); - return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx); + return 0; } static int do_check(struct bpf_verifier_env *env) { - struct bpf_verifier_state *state = &env->cur_state; + struct bpf_verifier_state *state; struct bpf_insn *insns = env->prog->insnsi; - struct bpf_reg_state *regs = state->regs; + struct bpf_reg_state *regs; int insn_cnt = env->prog->len; int insn_idx, prev_insn_idx = 0; int insn_processed = 0; bool do_print_state = false; - init_reg_state(regs); + state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL); + if (!state) + return -ENOMEM; + env->cur_state = state; + init_reg_state(env, state->regs); state->parent = NULL; insn_idx = 0; for (;;) { @@ -3572,7 +3763,7 @@ static int do_check(struct bpf_verifier_env *env) int err; if (insn_idx >= insn_cnt) { - verbose("invalid insn idx %d insn_cnt %d\n", + verbose(env, "invalid insn idx %d insn_cnt %d\n", insn_idx, insn_cnt); return -EFAULT; } @@ -3581,7 +3772,8 @@ static int do_check(struct bpf_verifier_env *env) class = BPF_CLASS(insn->code); if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { - verbose("BPF program is too large. Processed %d insn\n", + verbose(env, + "BPF program is too large. Processed %d insn\n", insn_processed); return -E2BIG; } @@ -3591,12 +3783,12 @@ static int do_check(struct bpf_verifier_env *env) return err; if (err == 1) { /* found equivalent state, can prune the search */ - if (log_level) { + if (env->log.level) { if (do_print_state) - verbose("\nfrom %d to %d: safe\n", + verbose(env, "\nfrom %d to %d: safe\n", prev_insn_idx, insn_idx); else - verbose("%d: safe\n", insn_idx); + verbose(env, "%d: safe\n", insn_idx); } goto process_bpf_exit; } @@ -3604,25 +3796,27 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (log_level > 1 || (log_level && do_print_state)) { - if (log_level > 1) - verbose("%d:", insn_idx); + if (env->log.level > 1 || (env->log.level && do_print_state)) { + if (env->log.level > 1) + verbose(env, "%d:", insn_idx); else - verbose("\nfrom %d to %d:", + verbose(env, "\nfrom %d to %d:", prev_insn_idx, insn_idx); - print_verifier_state(&env->cur_state); + print_verifier_state(env, state); do_print_state = false; } - if (log_level) { - verbose("%d: ", insn_idx); - print_bpf_insn(env, insn); + if (env->log.level) { + verbose(env, "%d: ", insn_idx); + print_bpf_insn(verbose, env, insn, + env->allow_ptr_leaks); } err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx); if (err) return err; + regs = cur_regs(env); if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); if (err) @@ -3672,7 +3866,7 @@ static int do_check(struct bpf_verifier_env *env) * src_reg == stack|map in some other branch. * Reject it. */ - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } @@ -3712,14 +3906,14 @@ static int do_check(struct bpf_verifier_env *env) } else if (dst_reg_type != *prev_dst_type && (dst_reg_type == PTR_TO_CTX || *prev_dst_type == PTR_TO_CTX)) { - verbose("same insn cannot be used with different pointers\n"); + verbose(env, "same insn cannot be used with different pointers\n"); return -EINVAL; } } else if (class == BPF_ST) { if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) { - verbose("BPF_ST uses reserved fields\n"); + verbose(env, "BPF_ST uses reserved fields\n"); return -EINVAL; } /* check src operand */ @@ -3742,7 +3936,7 @@ static int do_check(struct bpf_verifier_env *env) insn->off != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_CALL uses reserved fields\n"); + verbose(env, "BPF_CALL uses reserved fields\n"); return -EINVAL; } @@ -3755,7 +3949,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_JA uses reserved fields\n"); + verbose(env, "BPF_JA uses reserved fields\n"); return -EINVAL; } @@ -3767,7 +3961,7 @@ static int do_check(struct bpf_verifier_env *env) insn->imm != 0 || insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0) { - verbose("BPF_EXIT uses reserved fields\n"); + verbose(env, "BPF_EXIT uses reserved fields\n"); return -EINVAL; } @@ -3782,13 +3976,18 @@ static int do_check(struct bpf_verifier_env *env) return err; if (is_pointer_value(env, BPF_REG_0)) { - verbose("R0 leaks addr as return value\n"); + verbose(env, "R0 leaks addr as return value\n"); 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) { + err = pop_stack(env, &prev_insn_idx, &insn_idx); + if (err < 0) { + if (err != -ENOENT) + return err; break; } else { do_print_state = true; @@ -3814,19 +4013,19 @@ process_bpf_exit: insn_idx++; } else { - verbose("invalid BPF_LD mode\n"); + verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; } } else { - verbose("unknown insn class %d\n", class); + verbose(env, "unknown insn class %d\n", class); return -EINVAL; } insn_idx++; } - verbose("processed %d insns, stack depth %d\n", - insn_processed, env->prog->aux->stack_depth); + verbose(env, "processed %d insns, stack depth %d\n", insn_processed, + env->prog->aux->stack_depth); return 0; } @@ -3838,7 +4037,8 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } -static int check_map_prog_compatibility(struct bpf_map *map, +static int check_map_prog_compatibility(struct bpf_verifier_env *env, + struct bpf_map *map, struct bpf_prog *prog) { @@ -3849,12 +4049,12 @@ static int check_map_prog_compatibility(struct bpf_map *map, */ if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { if (!check_map_prealloc(map)) { - verbose("perf_event programs can only use preallocated hash map\n"); + verbose(env, "perf_event programs can only use preallocated hash map\n"); return -EINVAL; } if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) { - verbose("perf_event programs can only use preallocated inner hash map\n"); + verbose(env, "perf_event programs can only use preallocated inner hash map\n"); return -EINVAL; } } @@ -3877,14 +4077,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) for (i = 0; i < insn_cnt; i++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) { - verbose("BPF_LDX uses reserved fields\n"); + verbose(env, "BPF_LDX uses reserved fields\n"); return -EINVAL; } if (BPF_CLASS(insn->code) == BPF_STX && ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_XADD) || insn->imm != 0)) { - verbose("BPF_STX uses reserved fields\n"); + verbose(env, "BPF_STX uses reserved fields\n"); return -EINVAL; } @@ -3895,7 +4095,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) if (i == insn_cnt - 1 || insn[1].code != 0 || insn[1].dst_reg != 0 || insn[1].src_reg != 0 || insn[1].off != 0) { - verbose("invalid bpf_ld_imm64 insn\n"); + verbose(env, "invalid bpf_ld_imm64 insn\n"); return -EINVAL; } @@ -3904,19 +4104,20 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) goto next_insn; if (insn->src_reg != BPF_PSEUDO_MAP_FD) { - verbose("unrecognized bpf_ld_imm64 insn\n"); + verbose(env, + "unrecognized bpf_ld_imm64 insn\n"); return -EINVAL; } f = fdget(insn->imm); map = __bpf_map_get(f); if (IS_ERR(map)) { - verbose("fd %d is not pointing to valid bpf_map\n", + verbose(env, "fd %d is not pointing to valid bpf_map\n", insn->imm); return PTR_ERR(map); } - err = check_map_prog_compatibility(map, env->prog); + err = check_map_prog_compatibility(env, map, env->prog); if (err) { fdput(f); return err; @@ -4025,7 +4226,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->ops; + const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4038,7 +4239,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) cnt = ops->gen_prologue(insn_buf, env->seen_direct_write, env->prog); if (cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } else if (cnt) { new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt); @@ -4086,7 +4287,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) u8 size_code; if (type == BPF_WRITE) { - verbose("bpf verifier narrow ctx access misconfigured\n"); + verbose(env, "bpf verifier narrow ctx access misconfigured\n"); return -EINVAL; } @@ -4105,7 +4306,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) &target_size); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) || (ctx_field_size && !target_size)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4187,7 +4388,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) cnt = map_ptr->ops->map_gen_lookup(map_ptr, insn_buf); if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { - verbose("bpf verifier is misconfigured\n"); + verbose(env, "bpf verifier is misconfigured\n"); return -EINVAL; } @@ -4226,12 +4427,13 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->ops->get_func_proto(insn->imm); + fn = env->ops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ if (!fn->func) { - verbose("kernel subsystem misconfigured func %s#%d\n", + verbose(env, + "kernel subsystem misconfigured func %s#%d\n", func_id_name(insn->imm), insn->imm); return -EFAULT; } @@ -4255,6 +4457,7 @@ static void free_states(struct bpf_verifier_env *env) if (sl) while (sl != STATE_LIST_MARK) { sln = sl->next; + free_verifier_state(&sl->state, false); kfree(sl); sl = sln; } @@ -4265,16 +4468,21 @@ static void free_states(struct bpf_verifier_env *env) int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { - char __user *log_ubuf = NULL; struct bpf_verifier_env *env; + struct bpf_verifer_log *log; int ret = -EINVAL; + /* no program is valid */ + if (ARRAY_SIZE(bpf_verifier_ops) == 0) + return -EINVAL; + /* 'struct bpf_verifier_env' can be global, but since it's not small, * allocate/free it every time bpf_check() is called */ env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); if (!env) return -ENOMEM; + log = &env->log; env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * (*prog)->len); @@ -4282,6 +4490,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->insn_aux_data) goto err_free_env; env->prog = *prog; + env->ops = bpf_verifier_ops[env->prog->type]; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -4290,29 +4499,27 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) /* user requested verbose verifier output * and supplied buffer to store the verification trace */ - log_level = attr->log_level; - log_ubuf = (char __user *) (unsigned long) attr->log_buf; - log_size = attr->log_size; - log_len = 0; + log->level = attr->log_level; + log->ubuf = (char __user *) (unsigned long) attr->log_buf; + log->len_total = attr->log_size; ret = -EINVAL; - /* log_* values have to be sane */ - if (log_size < 128 || log_size > UINT_MAX >> 8 || - log_level == 0 || log_ubuf == NULL) + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) goto err_unlock; - - ret = -ENOMEM; - log_buf = vmalloc(log_size); - if (!log_buf) - goto err_unlock; - } else { - log_level = 0; } env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT); if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + if (env->prog->aux->offload) { + ret = bpf_prog_offload_verifier_prep(env); + if (ret) + goto err_unlock; + } + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; @@ -4331,9 +4538,13 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); ret = do_check(env); + if (env->cur_state) { + free_verifier_state(env->cur_state, true); + env->cur_state = NULL; + } skip_full_check: - while (pop_stack(env, NULL) >= 0); + while (!pop_stack(env, NULL, NULL)); free_states(env); if (ret == 0) @@ -4343,17 +4554,11 @@ skip_full_check: if (ret == 0) ret = fixup_bpf_calls(env); - if (log_level && log_len >= log_size - 1) { - BUG_ON(log_len >= log_size); - /* verifier log exceeded user supplied buffer */ + if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; - /* fall through to return what was recorded */ - } - - /* copy verifier log back to user space including trailing zero */ - if (log_level && copy_to_user(log_ubuf, log_buf, log_len + 1) != 0) { + if (log->level && !log->ubuf) { ret = -EFAULT; - goto free_log_buf; + goto err_release_maps; } if (ret == 0 && env->used_map_cnt) { @@ -4364,7 +4569,7 @@ skip_full_check: if (!env->prog->aux->used_maps) { ret = -ENOMEM; - goto free_log_buf; + goto err_release_maps; } memcpy(env->prog->aux->used_maps, env->used_maps, @@ -4377,9 +4582,7 @@ skip_full_check: convert_pseudo_ld_imm64(env); } -free_log_buf: - if (log_level) - vfree(log_buf); +err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. @@ -4393,58 +4596,3 @@ err_free_env: kfree(env); return ret; } - -int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, - void *priv) -{ - struct bpf_verifier_env *env; - int ret; - - env = kzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL); - if (!env) - return -ENOMEM; - - env->insn_aux_data = vzalloc(sizeof(struct bpf_insn_aux_data) * - prog->len); - ret = -ENOMEM; - if (!env->insn_aux_data) - goto err_free_env; - env->prog = prog; - env->analyzer_ops = ops; - env->analyzer_priv = priv; - - /* grab the mutex to protect few globals used by verifier */ - mutex_lock(&bpf_verifier_lock); - - log_level = 0; - - env->strict_alignment = false; - if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) - env->strict_alignment = true; - - env->explored_states = kcalloc(env->prog->len, - sizeof(struct bpf_verifier_state_list *), - GFP_KERNEL); - ret = -ENOMEM; - if (!env->explored_states) - goto skip_full_check; - - ret = check_cfg(env); - if (ret < 0) - goto skip_full_check; - - env->allow_ptr_leaks = capable(CAP_SYS_ADMIN); - - ret = do_check(env); - -skip_full_check: - while (pop_stack(env, NULL) >= 0); - free_states(env); - - mutex_unlock(&bpf_verifier_lock); - vfree(env->insn_aux_data); -err_free_env: - kfree(env); - return ret; -} -EXPORT_SYMBOL_GPL(bpf_analyzer); diff --git a/kernel/capability.c b/kernel/capability.c index f97fe77ceb88..1e1c0236f55b 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/capability.c * diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index ce693ccb8c58..ae448f7632cc 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y := cgroup.o namespace.o cgroup-v1.o obj-$(CONFIG_CGROUP_FREEZER) += freezer.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 5151ff256c29..bf54ade001be 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 44857278eb8a..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); /* @@ -4721,6 +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; @@ -4755,13 +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: @@ -5744,14 +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/cgroup/debug.c b/kernel/cgroup/debug.c index f661b4cc5efd..5f780d8f6a9d 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Debug controller * diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index 66129eb4371d..b05f1dd58a62 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "cgroup-internal.h" #include <linux/sched/task.h> diff --git a/kernel/cpu.c b/kernel/cpu.c index 8de11a29e495..04892a82f6ac 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -24,6 +24,7 @@ #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> +#include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> @@ -631,6 +632,11 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, __cpuhp_kick_ap(st); } + /* + * Clean up the leftovers so the next hotplug operation wont use stale + * data. + */ + st->node = st->last = NULL; return ret; } @@ -897,6 +903,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, out: cpus_write_unlock(); + /* + * Do post unplug cleanup. This is still protected against + * concurrent CPU hotplug via cpu_add_remove_lock. + */ + lockup_detector_cleanup(); return ret; } diff --git a/kernel/dma.c b/kernel/dma.c index 6c6262f86c17..3506fc34a712 100644 --- a/kernel/dma.c +++ b/kernel/dma.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/dma.c: A DMA channel allocator. Inspired by linux/kernel/irq.c. * diff --git a/kernel/elfcore.c b/kernel/elfcore.c index e556751d15d9..fc482c8e0bd8 100644 --- a/kernel/elfcore.c +++ b/kernel/elfcore.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/elf.h> #include <linux/fs.h> #include <linux/mm.h> diff --git a/kernel/events/Makefile b/kernel/events/Makefile index 2925188f50ea..3c022e33c109 100644 --- a/kernel/events/Makefile +++ b/kernel/events/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_core.o = $(CC_FLAGS_FTRACE) endif diff --git a/kernel/events/core.c b/kernel/events/core.c index 6bc21e202ae4..42d24bd64ea4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -662,7 +662,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgrp == event->cgrp) + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) __update_cgrp_time(event->cgrp); } @@ -901,9 +901,11 @@ list_update_cgroup_event(struct perf_event *event, cpuctx_entry = &cpuctx->cgrp_cpuctx_entry; /* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/ if (add) { + struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx); + list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list)); - if (perf_cgroup_from_task(current, ctx) == event->cgrp) - cpuctx->cgrp = event->cgrp; + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) + cpuctx->cgrp = cgrp; } else { list_del(cpuctx_entry); cpuctx->cgrp = NULL; @@ -3684,10 +3686,12 @@ static inline u64 perf_event_count(struct perf_event *event) * will not be local and we cannot read them atomically * - must not have a pmu::count method */ -int perf_event_read_local(struct perf_event *event, u64 *value) +int perf_event_read_local(struct perf_event *event, u64 *value, + u64 *enabled, u64 *running) { unsigned long flags; int ret = 0; + u64 now; /* * Disabling interrupts avoids all counter scheduling (context @@ -3718,13 +3722,21 @@ int perf_event_read_local(struct perf_event *event, u64 *value) goto out; } + now = event->shadow_ctx_time + perf_clock(); + if (enabled) + *enabled = now - event->tstamp_enabled; /* * If the event is currently on this CPU, its either a per-task event, * or local to this CPU. Furthermore it means its ACTIVE (otherwise * oncpu == -1). */ - if (event->oncpu == smp_processor_id()) + if (event->oncpu == smp_processor_id()) { event->pmu->read(event); + if (running) + *running = now - event->tstamp_running; + } else if (running) { + *running = event->total_time_running; + } *value = local64_read(&event->count); out: @@ -7944,11 +7956,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, struct pt_regs *regs, struct hlist_head *head, struct task_struct *task) { - struct bpf_prog *prog = call->prog; - - if (prog) { + if (bpf_prog_array_valid(call)) { *(struct pt_regs **)raw_data = regs; - if (!trace_call_bpf(prog, raw_data) || hlist_empty(head)) { + if (!trace_call_bpf(call, raw_data) || hlist_empty(head)) { perf_swevent_put_recursion_context(rctx); return; } @@ -8072,6 +8082,7 @@ static void bpf_overflow_handler(struct perf_event *event, struct bpf_perf_event_data_kern ctx = { .data = data, .regs = regs, + .event = event, }; int ret = 0; @@ -8136,13 +8147,11 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) { bool is_kprobe, is_tracepoint, is_syscall_tp; struct bpf_prog *prog; + int ret; if (event->attr.type != PERF_TYPE_TRACEPOINT) return perf_event_set_bpf_handler(event, prog_fd); - if (event->tp_event->prog) - return -EEXIST; - is_kprobe = event->tp_event->flags & TRACE_EVENT_FL_UKPROBE; is_tracepoint = event->tp_event->flags & TRACE_EVENT_FL_TRACEPOINT; is_syscall_tp = is_syscall_trace_event(event->tp_event); @@ -8170,26 +8179,20 @@ static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd) return -EACCES; } } - event->tp_event->prog = prog; - event->tp_event->bpf_prog_owner = event; - return 0; + ret = perf_event_attach_bpf_prog(event, prog); + if (ret) + bpf_prog_put(prog); + return ret; } static void perf_event_free_bpf_prog(struct perf_event *event) { - struct bpf_prog *prog; - - perf_event_free_bpf_handler(event); - - if (!event->tp_event) + if (event->attr.type != PERF_TYPE_TRACEPOINT) { + perf_event_free_bpf_handler(event); return; - - prog = event->tp_event->prog; - if (prog && event->tp_event->bpf_prog_owner == event) { - event->tp_event->prog = NULL; - bpf_prog_put(prog); } + perf_event_detach_bpf_prog(event); } #else @@ -8955,6 +8958,14 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn) static void free_pmu_context(struct pmu *pmu) { + /* + * Static contexts such as perf_sw_context have a global lifetime + * and may be shared between different PMUs. Avoid freeing them + * when a single PMU is going away. + */ + if (pmu->task_ctx_nr > perf_invalid_context) + return; + mutex_lock(&pmus_lock); free_percpu(pmu->pmu_cpu_context); mutex_unlock(&pmus_lock); diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 843e97047335..09b1537ae06c 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_EVENTS_INTERNAL_H #define _KERNEL_EVENTS_INTERNAL_H diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c index 6873bb3e6b7e..0975b0268545 100644 --- a/kernel/exec_domain.c +++ b/kernel/exec_domain.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Handling of different ABIs (personalities). * diff --git a/kernel/exit.c b/kernel/exit.c index f2cd53e92147..f6cad39f35df 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1610,6 +1610,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); @@ -1735,6 +1738,9 @@ COMPAT_SYSCALL_DEFINE5(waitid, if (!infop) return err; + if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop))) + return -EFAULT; + user_access_begin(); unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..07cc743698d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } @@ -946,6 +950,24 @@ 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 0518a0bfc746..76ed5921117a 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -903,11 +903,27 @@ void exit_pi_state_list(struct task_struct *curr) */ raw_spin_lock_irq(&curr->pi_lock); while (!list_empty(head)) { - next = head->next; pi_state = list_entry(next, struct futex_pi_state, list); key = pi_state->key; hb = hash_futex(&key); + + /* + * We can race against put_pi_state() removing itself from the + * list (a waiter going away). put_pi_state() will first + * decrement the reference count and then modify the list, so + * its possible to see the list entry but fail this reference + * acquire. + * + * In that case; drop the locks to let put_pi_state() make + * progress and retry the loop. + */ + if (!atomic_inc_not_zero(&pi_state->refcount)) { + raw_spin_unlock_irq(&curr->pi_lock); + cpu_relax(); + raw_spin_lock_irq(&curr->pi_lock); + continue; + } raw_spin_unlock_irq(&curr->pi_lock); spin_lock(&hb->lock); @@ -918,8 +934,10 @@ void exit_pi_state_list(struct task_struct *curr) * task still owns the PI-state: */ if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ raw_spin_unlock(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); + put_pi_state(pi_state); continue; } @@ -927,9 +945,8 @@ 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(&curr->pi_lock); - get_pi_state(pi_state); + raw_spin_unlock(&curr->pi_lock); raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); @@ -1570,8 +1587,16 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) int oldval, ret; if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28)) { - if (oparg < 0 || oparg > 31) - return -EINVAL; + if (oparg < 0 || oparg > 31) { + char comm[sizeof(current->comm)]; + /* + * kill this print and return -EINVAL when userspace + * is sane again + */ + pr_info_ratelimited("futex_wake_op: %s tries to shift op by %d; fix this program\n", + get_task_comm(comm, current), oparg); + oparg &= 31; + } oparg = 1 << oparg; } diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 3f409968e466..83f830acbb5f 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/futex_compat.c * diff --git a/kernel/gcov/Makefile b/kernel/gcov/Makefile index 752d6486b67e..c6c50e5c680e 100644 --- a/kernel/gcov/Makefile +++ b/kernel/gcov/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ccflags-y := -DSRCTREE='"$(srctree)"' -DOBJTREE='"$(objtree)"' obj-y := base.o fs.o diff --git a/kernel/gcov/base.c b/kernel/gcov/base.c index c51a49c9be70..9c7c8d5c18f2 100644 --- a/kernel/gcov/base.c +++ b/kernel/gcov/base.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This code maintains a list of active profiling data structures. * diff --git a/kernel/gcov/fs.c b/kernel/gcov/fs.c index edf67c493a8e..6e40ff6be083 100644 --- a/kernel/gcov/fs.c +++ b/kernel/gcov/fs.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This code exports profiling data as debugfs files to userspace. * diff --git a/kernel/gcov/gcc_3_4.c b/kernel/gcov/gcc_3_4.c index 27bc88a35013..1e32e66c9563 100644 --- a/kernel/gcov/gcc_3_4.c +++ b/kernel/gcov/gcc_3_4.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This code provides functions to handle gcc's profiling data format * introduced with gcc 3.4. Future versions of gcc may change the gcov diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index 46a18e72bce6..ca5e5c0ef853 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * This code provides functions to handle gcc's profiling data format * introduced with gcc 4.7. diff --git a/kernel/gcov/gcov.h b/kernel/gcov/gcov.h index 92c8e22a29ed..de118ad4a024 100644 --- a/kernel/gcov/gcov.h +++ b/kernel/gcov/gcov.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Profiling infrastructure declarations. * diff --git a/kernel/groups.c b/kernel/groups.c index 434f6665f187..e357bc800111 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index 1970cafe8f2a..ed15d142694b 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o obj-$(CONFIG_IRQ_TIMINGS) += timings.o diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d69bd77252a7..e12d35108225 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2016 Thomas Gleixner. * Copyright (C) 2016-2017 Christoph Hellwig. diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c index d30a0dd5cc02..befa671fba64 100644 --- a/kernel/irq/autoprobe.c +++ b/kernel/irq/autoprobe.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/irq/autoprobe.c * diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 6fc89fd93824..5a2ef92c2782 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,8 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: + irq_do_set_affinity(d, aff, false); ret = __irq_startup(desc); - irq_set_affinity_locked(d, aff, false); break; case IRQ_STARTUP_ABORT: return 0; diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c index 638eb9c83d9f..9eb09aef0313 100644 --- a/kernel/irq/cpuhotplug.c +++ b/kernel/irq/cpuhotplug.c @@ -18,8 +18,34 @@ static inline bool irq_needs_fixup(struct irq_data *d) { const struct cpumask *m = irq_data_get_effective_affinity_mask(d); + unsigned int cpu = smp_processor_id(); - return cpumask_test_cpu(smp_processor_id(), m); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + /* + * The cpumask_empty() check is a workaround for interrupt chips, + * which do not implement effective affinity, but the architecture has + * enabled the config switch. Use the general affinity mask instead. + */ + if (cpumask_empty(m)) + m = irq_data_get_affinity_mask(d); + + /* + * Sanity check. If the mask is not empty when excluding the outgoing + * CPU then it must contain at least one online CPU. The outgoing CPU + * has been removed from the online mask already. + */ + if (cpumask_any_but(m, cpu) < nr_cpu_ids && + cpumask_any_and(m, cpu_online_mask) >= nr_cpu_ids) { + /* + * If this happens then there was a missed IRQ fixup at some + * point. Warn about it and enforce fixup. + */ + pr_warn("Eff. affinity %*pbl of IRQ %u contains only offline CPUs after offlining CPU %u\n", + cpumask_pr_args(m), d->irq, cpu); + return true; + } +#endif + return cpumask_test_cpu(cpu, m); } static bool migrate_one_irq(struct irq_desc *desc) diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h index e75e29e4434a..17f05ef8f575 100644 --- a/kernel/irq/debug.h +++ b/kernel/irq/debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Debugging printout: */ diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 5270a54b9fa4..c26c5bb6b491 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -135,17 +135,26 @@ void irq_gc_ack_clr_bit(struct irq_data *d) } /** - * irq_gc_mask_disable_reg_and_ack - Mask and ack pending interrupt + * irq_gc_mask_disable_and_ack_set - Mask and ack pending interrupt * @d: irq_data + * + * This generic implementation of the irq_mask_ack method is for chips + * with separate enable/disable registers instead of a single mask + * register and where a pending interrupt is acknowledged by setting a + * bit. + * + * Note: This is the only permutation currently used. Similar generic + * functions should be added here if other permutations are required. */ -void irq_gc_mask_disable_reg_and_ack(struct irq_data *d) +void irq_gc_mask_disable_and_ack_set(struct irq_data *d) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct irq_chip_type *ct = irq_data_get_chip_type(d); u32 mask = d->mask; irq_gc_lock(gc); - irq_reg_writel(gc, mask, ct->regs.mask); + irq_reg_writel(gc, mask, ct->regs.disable); + *ct->mask_cache &= ~mask; irq_reg_writel(gc, mask, ct->regs.ack); irq_gc_unlock(gc); } diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index a4aa39009f0d..44ed5f8c8759 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * IRQ subsystem internal functions and variables: * diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d00132b5c325..4bff6a10ae8e 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -168,6 +168,19 @@ void irq_set_thread_affinity(struct irq_desc *desc) set_bit(IRQTF_AFFINITY, &action->thread_flags); } +static void irq_validate_effective_affinity(struct irq_data *data) +{ +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + const struct cpumask *m = irq_data_get_effective_affinity_mask(data); + struct irq_chip *chip = irq_data_get_irq_chip(data); + + if (!cpumask_empty(m)) + return; + pr_warn_once("irq_chip %s did not update eff. affinity mask of irq %u\n", + chip->name, data->irq); +#endif +} + int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { @@ -175,12 +188,16 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; + if (!chip || !chip->irq_set_affinity) + return -EINVAL; + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: case IRQ_SET_MASK_OK_DONE: cpumask_copy(desc->irq_common_data.affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: + irq_validate_effective_affinity(data); irq_set_thread_affinity(desc); ret = 0; } diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index 6ca054a3f91d..86ae0eb80b53 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/irq.h> #include <linux/interrupt.h> diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 6376b4a598d3..c010cc0daf79 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/irq/proc.c * diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c index b86886beee4f..1d08f45135c2 100644 --- a/kernel/irq/resend.c +++ b/kernel/irq/resend.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/irq/resend.c * diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h index 320579d89091..e43795cd2ccf 100644 --- a/kernel/irq/settings.h +++ b/kernel/irq/settings.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Internal header to deal with irq_desc->status which will be renamed * to irq_desc->settings. diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index c805e8691c22..1215229d1c12 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/irq/spurious.c * diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..a0e3d7a0e8b8 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/fdtable.h> @@ -131,7 +132,7 @@ 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/kcov.c b/kernel/kcov.c index 3f693a0f6f3e..fc6af9e1308b 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) "kcov: " fmt #define DISABLE_BRANCH_PROFILING diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 50dfcb039a41..48aaf2ac0d0d 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_KEXEC_INTERNAL_H #define LINUX_KEXEC_INTERNAL_H diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index b9628e43c78f..bf8c8fd72589 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -830,6 +830,41 @@ int klp_register_patch(struct klp_patch *patch) } EXPORT_SYMBOL_GPL(klp_register_patch); +/* + * Remove parts of patches that touch a given kernel module. The list of + * patches processed might be limited. When limit is NULL, all patches + * will be handled. + */ +static void klp_cleanup_module_patches_limited(struct module *mod, + struct klp_patch *limit) +{ + struct klp_patch *patch; + struct klp_object *obj; + + list_for_each_entry(patch, &klp_patches, list) { + if (patch == limit) + break; + + klp_for_each_object(patch, obj) { + if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) + continue; + + /* + * Only unpatch the module if the patch is enabled or + * is in transition. + */ + if (patch->enabled || patch == klp_transition_patch) { + pr_notice("reverting patch '%s' on unloading module '%s'\n", + patch->mod->name, obj->mod->name); + klp_unpatch_object(obj); + } + + klp_free_object_loaded(obj); + break; + } + } +} + int klp_module_coming(struct module *mod) { int ret; @@ -894,7 +929,7 @@ err: pr_warn("patch '%s' failed for module '%s', refusing to load module '%s'\n", patch->mod->name, obj->mod->name, obj->mod->name); mod->klp_alive = false; - klp_free_object_loaded(obj); + klp_cleanup_module_patches_limited(mod, patch); mutex_unlock(&klp_mutex); return ret; @@ -902,9 +937,6 @@ err: void klp_module_going(struct module *mod) { - struct klp_patch *patch; - struct klp_object *obj; - if (WARN_ON(mod->state != MODULE_STATE_GOING && mod->state != MODULE_STATE_COMING)) return; @@ -917,25 +949,7 @@ void klp_module_going(struct module *mod) */ mod->klp_alive = false; - list_for_each_entry(patch, &klp_patches, list) { - klp_for_each_object(patch, obj) { - if (!klp_is_module(obj) || strcmp(obj->name, mod->name)) - continue; - - /* - * Only unpatch the module if the patch is enabled or - * is in transition. - */ - if (patch->enabled || patch == klp_transition_patch) { - pr_notice("reverting patch '%s' on unloading module '%s'\n", - patch->mod->name, obj->mod->name); - klp_unpatch_object(obj); - } - - klp_free_object_loaded(obj); - break; - } - } + klp_cleanup_module_patches_limited(mod, NULL); mutex_unlock(&klp_mutex); } diff --git a/kernel/livepatch/core.h b/kernel/livepatch/core.h index c74f24c47837..a351601d7f76 100644 --- a/kernel/livepatch/core.h +++ b/kernel/livepatch/core.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LIVEPATCH_CORE_H #define _LIVEPATCH_CORE_H diff --git a/kernel/livepatch/patch.h b/kernel/livepatch/patch.h index 0db227170c36..e72d8250d04b 100644 --- a/kernel/livepatch/patch.h +++ b/kernel/livepatch/patch.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LIVEPATCH_PATCH_H #define _LIVEPATCH_PATCH_H diff --git a/kernel/livepatch/transition.h b/kernel/livepatch/transition.h index ce09b326546c..0f6e27c481f9 100644 --- a/kernel/livepatch/transition.h +++ b/kernel/livepatch/transition.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LIVEPATCH_TRANSITION_H #define _LIVEPATCH_TRANSITION_H diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 760158d9d98d..392c7f23af76 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Any varying coverage in these files is non-deterministic # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 44c8d0d17170..e36e652d996f 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -1873,10 +1873,10 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, struct held_lock *next, int distance, struct stack_trace *trace, int (*save)(struct stack_trace *trace)) { + struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; - int ret; struct lock_list this; - struct lock_list *uninitialized_var(target_entry); + int ret; /* * Prove that the new <prev> -> <next> dependency would not @@ -1890,8 +1890,17 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.class = hlock_class(next); this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); - if (unlikely(!ret)) + if (unlikely(!ret)) { + if (!trace->entries) { + /* + * If @save fails here, the printing might trigger + * a WARN but because of the !nr_entries it should + * not do bad things. + */ + save(trace); + } return print_circular_bug(&this, target_entry, next, prev, trace); + } else if (unlikely(ret < 0)) return print_bfs_bug(ret); @@ -1938,7 +1947,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (save && !save(trace)) + if (!trace->entries && !save(trace)) return 0; /* @@ -1958,20 +1967,6 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, if (!ret) return 0; - /* - * Debugging printouts: - */ - if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { - graph_unlock(); - printk("\n new dependency: "); - print_lock_name(hlock_class(prev)); - printk(KERN_CONT " => "); - print_lock_name(hlock_class(next)); - printk(KERN_CONT "\n"); - dump_stack(); - if (!graph_lock()) - return 0; - } return 2; } @@ -1986,8 +1981,12 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) { int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace; - int (*save)(struct stack_trace *trace) = save_trace; + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = 0, + .entries = NULL, + .skip = 0, + }; /* * Debugging checks. @@ -2018,18 +2017,11 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) */ if (hlock->read != 2 && hlock->check) { int ret = check_prev_add(curr, hlock, next, - distance, &trace, save); + distance, &trace, save_trace); if (!ret) return 0; /* - * Stop saving stack_trace if save_trace() was - * called at least once: - */ - if (save && ret == 2) - save = NULL; - - /* * Stop after the first non-trylock entry, * as non-trylock entries have added their * own direct dependencies already, so this diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 1da4669d57a7..d459d624ba2a 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/lockdep_internals.h * diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index 68d9e267ccd4..ad69bbc9bd28 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/lockdep_proc.c * diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 6a385aabcce7..f046b7ce9dd6 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * MCS lock defines * diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 4174417d5309..1edd3f45a4ec 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Mutexes: blocking mutual exclusion locks * diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 6ebc1902f779..1c2287d3fa71 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Mutexes: blocking mutual exclusion locks * diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index a74ee6abd039..6ef600aa0f47 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/percpu.h> #include <linux/sched.h> #include <linux/osq_lock.h> diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 43555681c40b..15b6a39366c6 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _GEN_PV_LOCK_SLOWPATH #error "do not include this file" #endif diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c index f4a74e78d467..fd4fe1f5b458 100644 --- a/kernel/locking/rtmutex-debug.c +++ b/kernel/locking/rtmutex-debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * RT-Mutexes: blocking mutual exclusion locks with PI support * diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h index 5078c6ddf4a5..fc549713bba3 100644 --- a/kernel/locking/rtmutex-debug.h +++ b/kernel/locking/rtmutex-debug.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * RT-Mutexes: blocking mutual exclusion locks with PI support * diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h index 5c253caffe91..732f96abf462 100644 --- a/kernel/locking/rtmutex.h +++ b/kernel/locking/rtmutex.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * RT-Mutexes: blocking mutual exclusion locks with PI support * diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 7453be0485a5..124e98ca0b17 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * RT Mutexes: blocking mutual exclusion locks with PI support * diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c index 0848634c5512..a7ffb2a96ede 100644 --- a/kernel/locking/rwsem-spinlock.c +++ b/kernel/locking/rwsem-spinlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* rwsem-spinlock.c: R/W semaphores: contention handling functions for * generic spinlock implementation * diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 1fefe6dcafd7..e795908f3607 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* rwsem.c: R/W semaphores: contention handling functions * * Written by David Howells (dhowells@redhat.com). diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 4d48b1c4870d..a6c76a4832b4 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* kernel/rwsem.c: R/W semaphores, public implementation * * Written by David Howells (dhowells@redhat.com). diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index a699f4048ba1..a883b8f1fdc6 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * The owner field of the rw_semaphore structure will be set to * RWSEM_READ_OWNED when a reader grabs the lock. A writer will clear diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index 4b082b5cac9e..6e40fdfba326 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (2004) Linus Torvalds * 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/Makefile b/kernel/power/Makefile index eb4f717705ba..a3f79f0eef36 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG diff --git a/kernel/power/autosleep.c b/kernel/power/autosleep.c index 9012ecf7b814..41e83a779e19 100644 --- a/kernel/power/autosleep.c +++ b/kernel/power/autosleep.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/power/autosleep.c * diff --git a/kernel/power/console.c b/kernel/power/console.c index 0e781798b0b3..fcdf0e14a47d 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Functions for saving/restoring console. * diff --git a/kernel/power/power.h b/kernel/power/power.h index 1d2d761e3c25..f29cd178df90 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/suspend.h> #include <linux/suspend_ioctls.h> #include <linux/utsname.h> diff --git a/kernel/power/process.c b/kernel/power/process.c index 50f25cb370c6..7381d49a44db 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * drivers/power/process.c - Functions for starting/stopping processes on * suspend transitions. 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/power/wakelock.c b/kernel/power/wakelock.c index 1896386e16bb..dfba59be190b 100644 --- a/kernel/power/wakelock.c +++ b/kernel/power/wakelock.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/power/wakelock.c * diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c index 61d41ca41844..1d21ebacfdb8 100644 --- a/kernel/printk/braille.c +++ b/kernel/printk/braille.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> diff --git a/kernel/printk/braille.h b/kernel/printk/braille.h index 749a6756843a..123154f86304 100644 --- a/kernel/printk/braille.h +++ b/kernel/printk/braille.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _PRINTK_BRAILLE_H #define _PRINTK_BRAILLE_H diff --git a/kernel/printk/console_cmdline.h b/kernel/printk/console_cmdline.h index 2ca4a8b5fe57..11f19c466af5 100644 --- a/kernel/printk/console_cmdline.h +++ b/kernel/printk/console_cmdline.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _CONSOLE_CMDLINE_H #define _CONSOLE_CMDLINE_H diff --git a/kernel/range.c b/kernel/range.c index 82cfc285b046..d84de6766472 100644 --- a/kernel/range.c +++ b/kernel/range.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Range add and subtract */ diff --git a/kernel/rcu/Makefile b/kernel/rcu/Makefile index 13c0fc852767..020e8b6a644b 100644 --- a/kernel/rcu/Makefile +++ b/kernel/rcu/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Any varying coverage in these files is non-deterministic # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 729a8706751d..6d5880089ff6 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp, /** * call_srcu() - Queue a callback for invocation after an SRCU grace period * @sp: srcu_struct in queue the callback - * @head: structure to be used for queueing the SRCU callback. + * @rhp: structure to be used for queueing the SRCU callback. * @func: function to be invoked after the SRCU grace period * * The callback function will be invoked some time after a full SRCU diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index 50d1861f7759..3f943efcf61c 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -85,6 +85,9 @@ void rcu_sync_init(struct rcu_sync *rsp, enum rcu_sync_type type) } /** + * rcu_sync_enter_start - Force readers onto slow path for multiple updates + * @rsp: Pointer to rcu_sync structure to use for synchronization + * * Must be called after rcu_sync_init() and before first use. * * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}() @@ -142,7 +145,7 @@ void rcu_sync_enter(struct rcu_sync *rsp) /** * rcu_sync_func() - Callback function managing reader access to fastpath - * @rsp: Pointer to rcu_sync structure to use for synchronization + * @rhp: Pointer to rcu_head in rcu_sync structure to use for synchronization * * This function is passed to one of the call_rcu() functions by * rcu_sync_exit(), so that it is invoked after a grace period following the @@ -158,9 +161,9 @@ void rcu_sync_enter(struct rcu_sync *rsp) * rcu_sync_exit(). Otherwise, set all state back to idle so that readers * can again use their fastpaths. */ -static void rcu_sync_func(struct rcu_head *rcu) +static void rcu_sync_func(struct rcu_head *rhp) { - struct rcu_sync *rsp = container_of(rcu, struct rcu_sync, cb_head); + struct rcu_sync *rsp = container_of(rhp, struct rcu_sync, cb_head); unsigned long flags; BUG_ON(rsp->gp_state != GP_PASSED); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 0c44c7b42e6d..3e3650e94ae6 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -884,7 +884,7 @@ void rcu_irq_exit(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && @@ -1022,7 +1022,7 @@ void rcu_irq_enter(void) rdtp = this_cpu_ptr(&rcu_dynticks); /* Page faults can happen in NMI handlers, so check... */ - if (READ_ONCE(rdtp->dynticks_nmi_nesting)) + if (rdtp->dynticks_nmi_nesting) return; oldval = rdtp->dynticks_nesting; @@ -3097,9 +3097,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func, * read-side critical sections have completed. call_rcu_sched() assumes * that the read-side critical sections end on enabling of preemption * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR - * - anything that disables preemption. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock_sched() and rcu_read_unlock_sched(), OR + * - anything that disables preemption. * * These may be nested. * @@ -3124,11 +3125,12 @@ EXPORT_SYMBOL_GPL(call_rcu_sched); * handler. This means that read-side critical sections in process * context must not be interrupted by softirqs. This interface is to be * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. + * RCU read-side critical sections are delimited by: + * + * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context, OR + * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. + * + * These may be nested. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 78f54932ea1d..a9ee16bbc693 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_clock.o = $(CC_FLAGS_FTRACE) endif diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index de6d7f4dfcb5..a43df5193538 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "sched.h" #include <linux/proc_fs.h> diff --git a/kernel/sched/autogroup.h b/kernel/sched/autogroup.h index ce40c810cd5c..27cd22b89824 100644 --- a/kernel/sched/autogroup.h +++ b/kernel/sched/autogroup.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_SCHED_AUTOGROUP #include <linux/kref.h> diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index cc873075c3bd..2ddaec40956f 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Generic wait-for-completion handler; * diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index f95ab29a45d0..44ab32a4fab6 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/cgroup.h> #include <linux/slab.h> #include <linux/percpu.h> diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h index ba72807c73d4..a8358a57a316 100644 --- a/kernel/sched/cpuacct.h +++ b/kernel/sched/cpuacct.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_CGROUP_CPUACCT extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h index f7da8c55bba0..b010d26e108e 100644 --- a/kernel/sched/cpudeadline.h +++ b/kernel/sched/cpudeadline.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUDL_H #define _LINUX_CPUDL_H diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 9209d83ecdcf..ba0da243fdd8 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -649,6 +649,7 @@ static int sugov_start(struct cpufreq_policy *policy) struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); memset(sg_cpu, 0, sizeof(*sg_cpu)); + sg_cpu->cpu = cpu; sg_cpu->sg_policy = sg_policy; sg_cpu->flags = SCHED_CPUFREQ_RT; sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; @@ -714,11 +715,6 @@ struct cpufreq_governor *cpufreq_default_governor(void) static int __init sugov_register(void) { - int cpu; - - for_each_possible_cpu(cpu) - per_cpu(sugov_cpu, cpu).cpu = cpu; - return cpufreq_register_governor(&schedutil_gov); } fs_initcall(sugov_register); diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h index 63cbb9ca0496..bab050019071 100644 --- a/kernel/sched/cpupri.h +++ b/kernel/sched/cpupri.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUPRI_H #define _LINUX_CPUPRI_H diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 0191ec7667c3..4ae5c1ea90e2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Deadline Scheduling Class (SCHED_DEADLINE) * diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 70ba32e08a23..5c09ddf8c832 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH) * @@ -5356,91 +5357,62 @@ static int wake_wide(struct task_struct *p) return 1; } -struct llc_stats { - unsigned long nr_running; - unsigned long load; - unsigned long capacity; - int has_capacity; -}; +/* + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. + * + * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or + * will be) idle. + * + * wake_affine_weight() - considers the weight to reflect the average + * scheduling latency of the CPUs. This seems to work + * for the overloaded case. + */ -static bool get_llc_stats(struct llc_stats *stats, int cpu) +static bool +wake_affine_idle(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - - if (!sds) - return false; + if (idle_cpu(this_cpu)) + return true; - stats->nr_running = READ_ONCE(sds->nr_running); - stats->load = READ_ONCE(sds->load); - stats->capacity = READ_ONCE(sds->capacity); - stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu); + if (sync && cpu_rq(this_cpu)->nr_running == 1) + return true; - return true; + return false; } -/* - * Can a task be moved from prev_cpu to this_cpu without causing a load - * imbalance that would trigger the load balancer? - * - * Since we're running on 'stale' values, we might in fact create an imbalance - * but recomputing these values is expensive, as that'd mean iteration 2 cache - * domains worth of CPUs. - */ static bool -wake_affine_llc(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +wake_affine_weight(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct llc_stats prev_stats, this_stats; s64 this_eff_load, prev_eff_load; unsigned long task_load; - if (!get_llc_stats(&prev_stats, prev_cpu) || - !get_llc_stats(&this_stats, this_cpu)) - return false; + this_eff_load = target_load(this_cpu, sd->wake_idx); + prev_eff_load = source_load(prev_cpu, sd->wake_idx); - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current LLC. - */ if (sync) { unsigned long current_load = task_h_load(current); - /* in this case load hits 0 and this LLC is considered 'idle' */ - if (current_load > this_stats.load) + if (current_load > this_eff_load) return true; - this_stats.load -= current_load; + this_eff_load -= current_load; } - /* - * The has_capacity stuff is not SMT aware, but by trying to balance - * the nr_running on both ends we try and fill the domain at equal - * rates, thereby first consuming cores before siblings. - */ - - /* if the old cache has capacity, stay there */ - if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) - return false; - - /* if this cache has capacity, come here */ - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) - return true; - - /* - * Check to see if we can move the load without causing too much - * imbalance. - */ task_load = task_h_load(p); - this_eff_load = 100; - this_eff_load *= prev_stats.capacity; - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= this_stats.capacity; + this_eff_load += task_load; + if (sched_feat(WA_BIAS)) + this_eff_load *= 100; + this_eff_load *= capacity_of(prev_cpu); - this_eff_load *= this_stats.load + task_load; - prev_eff_load *= prev_stats.load - task_load; + prev_eff_load -= task_load; + if (sched_feat(WA_BIAS)) + prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); return this_eff_load <= prev_eff_load; } @@ -5449,22 +5421,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine; + bool affine = false; - /* - * Default to no affine wakeups; wake_affine() should not effect a task - * placement the load-balancer feels inclined to undo. The conservative - * option is therefore to not move tasks when they wake up. - */ - affine = false; + if (sched_feat(WA_IDLE) && !affine) + affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); - /* - * If the wakeup is across cache domains, try to evaluate if movement - * makes sense, otherwise rely on select_idle_siblings() to do - * placement inside the cache domain. - */ - if (!cpus_share_cache(prev_cpu, this_cpu)) - affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_WEIGHT) && !affine) + affine = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (affine) { @@ -7600,7 +7563,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) */ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { - struct sched_domain_shared *shared = env->sd->shared; struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; @@ -7672,22 +7634,6 @@ next_group: if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; } - - if (!shared) - return; - - /* - * Since these are sums over groups they can contain some CPUs - * multiple times for the NUMA domains. - * - * Currently only wake_affine_llc() and find_busiest_group() - * uses these numbers, only the last is affected by this problem. - * - * XXX fix that. - */ - WRITE_ONCE(shared->nr_running, sds->total_running); - WRITE_ONCE(shared->load, sds->total_load); - WRITE_ONCE(shared->capacity, sds->total_capacity); } /** @@ -8098,6 +8044,13 @@ static int should_we_balance(struct lb_env *env) int cpu, balance_cpu = -1; /* + * Ensure the balancing environment is consistent; can happen + * when the softirq triggers 'during' hotplug. + */ + if (!cpumask_test_cpu(env->dst_cpu, env->cpus)) + return 0; + + /* * In the newly idle case, we will allow all the cpu's * to do the newly idle load balance. */ diff --git a/kernel/sched/features.h b/kernel/sched/features.h index d3fb15555291..9552fd5854bf 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Only give sleepers 50% of their service deficit. This allows * them to run sooner, but does not allow tons of sleepers to @@ -81,3 +82,6 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) +SCHED_FEAT(WA_IDLE, true) +SCHED_FEAT(WA_WEIGHT, true) +SCHED_FEAT(WA_BIAS, true) diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 0c00172db63e..d518664cce4f 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "sched.h" /* diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index f14716a3522f..89a989e4d758 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kernel/sched/loadavg.c * diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index a92fddc22747..dd7908743dab 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -18,6 +18,7 @@ #include <linux/membarrier.h> #include <linux/tick.h> #include <linux/cpumask.h> +#include <linux/atomic.h> #include "sched.h" /* for cpu_rq(). */ @@ -26,21 +27,26 @@ * except MEMBARRIER_CMD_QUERY. */ #define MEMBARRIER_CMD_BITMASK \ - (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED) + (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \ + | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED) static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ } -static void membarrier_private_expedited(void) +static int membarrier_private_expedited(void) { int cpu; bool fallback = false; cpumask_var_t tmpmask; + if (!(atomic_read(¤t->mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY)) + return -EPERM; + if (num_online_cpus() == 1) - return; + return 0; /* * Matches memory barriers around rq->curr modification in @@ -94,6 +100,24 @@ static void membarrier_private_expedited(void) * rq->curr modification in scheduler. */ smp_mb(); /* exit from system call is not a mb */ + return 0; +} + +static void membarrier_register_private_expedited(void) +{ + struct task_struct *p = current; + struct mm_struct *mm = p->mm; + + /* + * We need to consider threads belonging to different thread + * groups, which use the same mm. (CLONE_VM but not + * CLONE_THREAD). + */ + if (atomic_read(&mm->membarrier_state) + & MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY) + return; + atomic_or(MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY, + &mm->membarrier_state); } /** @@ -144,7 +168,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) synchronize_sched(); return 0; case MEMBARRIER_CMD_PRIVATE_EXPEDITED: - membarrier_private_expedited(); + return membarrier_private_expedited(); + case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED: + membarrier_register_private_expedited(); return 0; default: return -EINVAL; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 0af5ca9e3e3f..3c96c80e0992 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Real-Time Scheduling Class (mapped to the SCHED_FIFO and SCHED_RR * policies) diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h index cd200d16529e..a26473674fb7 100644 --- a/kernel/sched/sched-pelt.h +++ b/kernel/sched/sched-pelt.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Generated by Documentation/scheduler/sched-pelt; do not modify. */ static const u32 runnable_avg_yN_inv[] = { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 14db76cd496f..3b448ba82225 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #include <linux/sched.h> #include <linux/sched/autogroup.h> diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index 87e2c9f0c33e..940b1fa1d2ce 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/fs.h> diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index d5710651043b..baf500d12b7c 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifdef CONFIG_SCHEDSTATS diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 9f69fb630853..45caf90b24cd 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "sched.h" /* diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index 2227e183e202..9ff1555341ed 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/sched/signal.h> #include <linux/swait.h> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f1cf4f306a82..6798276d29af 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Scheduler topology setup/handling methods */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index bb3a38005b9c..418a1c045933 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/seccomp.c * @@ -473,7 +474,7 @@ static long seccomp_attach_filter(unsigned int flags, return 0; } -void __get_seccomp_filter(struct seccomp_filter *filter) +static void __get_seccomp_filter(struct seccomp_filter *filter) { /* Reference count is bounded by the number of total processes. */ refcount_inc(&filter->usage); diff --git a/kernel/signal.c b/kernel/signal.c index 800a18f77732..8dcd8825b2de 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2698,7 +2698,7 @@ enum siginfo_layout siginfo_layout(int sig, int si_code) [SIGSEGV] = { NSIGSEGV, SIL_FAULT }, [SIGBUS] = { NSIGBUS, SIL_FAULT }, [SIGTRAP] = { NSIGTRAP, SIL_FAULT }, -#if defined(SIGMET) && defined(NSIGEMT) +#if defined(SIGEMT) && defined(NSIGEMT) [SIGEMT] = { NSIGEMT, SIL_FAULT }, #endif [SIGCHLD] = { NSIGCHLD, SIL_CHLD }, diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 1d71c051a951..5043e7433f4b 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); * by the client, but only by calling this function. * This function can only be called on a registered smp_hotplug_thread. */ -int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, - const struct cpumask *new) +void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread, + const struct cpumask *new) { struct cpumask *old = plug_thread->cpumask; - cpumask_var_t tmp; + static struct cpumask tmp; unsigned int cpu; - if (!alloc_cpumask_var(&tmp, GFP_KERNEL)) - return -ENOMEM; - - get_online_cpus(); + lockdep_assert_cpus_held(); mutex_lock(&smpboot_threads_lock); /* Park threads that were exclusively enabled on the old mask. */ - cpumask_andnot(tmp, old, new); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, old, new); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_park_thread(plug_thread, cpu); /* Unpark threads that are exclusively enabled on the new mask. */ - cpumask_andnot(tmp, new, old); - for_each_cpu_and(cpu, tmp, cpu_online_mask) + cpumask_andnot(&tmp, new, old); + for_each_cpu_and(cpu, &tmp, cpu_online_mask) smpboot_unpark_thread(plug_thread, cpu); cpumask_copy(old, new); mutex_unlock(&smpboot_threads_lock); - put_online_cpus(); - - free_cpumask_var(tmp); - - return 0; } -EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread); static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD); diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 485b81cfab34..34dd3d7ba40b 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef SMPBOOT_H #define SMPBOOT_H diff --git a/kernel/sys.c b/kernel/sys.c index 9aebc2935013..524a4cb9bbe2 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/sys.c * diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 8acef8576ce9..b5189762d275 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/linkage.h> #include <linux/errno.h> diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 423554ad3610..d9c31bc2eaea 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -872,9 +872,9 @@ static struct ctl_table kern_table[] = { #if defined(CONFIG_LOCKUP_DETECTOR) { .procname = "watchdog", - .data = &watchdog_user_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_watchdog, .extra1 = &zero, .extra2 = &one, @@ -890,16 +890,12 @@ static struct ctl_table kern_table[] = { }, { .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &nmi_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = NMI_WATCHDOG_SYSCTL_PERM, .proc_handler = proc_nmi_watchdog, .extra1 = &zero, -#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR) .extra2 = &one, -#else - .extra2 = &zero, -#endif }, { .procname = "watchdog_cpumask", @@ -911,9 +907,9 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", - .data = &soft_watchdog_enabled, - .maxlen = sizeof (int), - .mode = 0644, + .data = &soft_watchdog_user_enabled, + .maxlen = sizeof(int), + .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = &zero, .extra2 = &one, @@ -2188,8 +2184,6 @@ 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/sysctl_binary.c b/kernel/sysctl_binary.c index 58ea8c03662e..e8c0dab4fd65 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/stat.h> #include <linux/sysctl.h> #include "../fs/xfs/xfs_sysctl.h" diff --git a/kernel/task_work.c b/kernel/task_work.c index 836a72a66fba..5718b3ea202a 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/tracehook.h> diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 938dbf33ef49..f1e46f338a9c 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y += time.o timer.o hrtimer.o obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o obj-y += timeconv.o timecounter.o alarmtimer.o diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 2ef98a02376a..f26acef5d7b4 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/itimer.c * diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 90f84582a076..8d70da1b9a0d 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NTP state machine interfaces and logic. * diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 74b52cd48209..909bd1f1bfb1 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NTP_INTERNAL_H #define _LINUX_NTP_INTERNAL_H diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 8585ad6e472a..5b117110b55b 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Implement CPU time clocks for the POSIX clock interface. */ diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index fb303c3be4d3..151e28f5bf30 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #define TIMER_RETRY 1 struct k_clock { diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index a7bb8f33ae07..58045eb976c3 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/time/tick-broadcast-hrtimer.c * This file emulates a local clock event device diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index be0ac01f2e12..f8e1845aa464 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * tick internal variable and functions used by low/high res code */ diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 075444e3d48e..954b43dbf21c 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TICK_SCHED_H #define _TICK_SCHED_H diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 44aec7893cdd..7a9b4eb7a1d5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_TIME_TIMEKEEPING_H #define _KERNEL_TIME_TIMEKEEPING_H /* diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 9a18f121f399..fdbeeb02dde9 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TIMEKEEPING_INTERNAL_H #define _TIMEKEEPING_INTERNAL_H /* diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 90f2701d92a7..19a15b2f1190 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # Do not instrument the tracer itself: diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index dc498b605d5d..506efe6e8ed9 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -15,9 +15,11 @@ #include <linux/ctype.h> #include "trace.h" +u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); + /** * trace_call_bpf - invoke BPF program - * @prog: BPF program + * @call: tracepoint event * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. @@ -29,7 +31,7 @@ * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ -unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) +unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) { unsigned int ret; @@ -49,9 +51,22 @@ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) goto out; } - rcu_read_lock(); - ret = BPF_PROG_RUN(prog, ctx); - rcu_read_unlock(); + /* + * Instead of moving rcu_read_lock/rcu_dereference/rcu_read_unlock + * to all call sites, we did a bpf_prog_array_valid() there to check + * whether call->prog_array is empty or not, which is + * a heurisitc to speed up execution. + * + * If bpf_prog_array_valid() fetched prog_array was + * non-NULL, we go into trace_call_bpf() and do the actual + * proper rcu_dereference() under RCU lock. + * If it turns out that prog_array is NULL then, we bail out. + * For the opposite, if the bpf_prog_array_valid() fetched pointer + * was NULL, you'll skip the prog_array with the risk of missing + * out of events when it was updated in between this and the + * rcu_dereference() which is accepted risk. + */ + ret = BPF_PROG_RUN_ARRAY_CHECK(call->prog_array, ctx, BPF_PROG_RUN); out: __this_cpu_dec(bpf_prog_active); @@ -255,14 +270,14 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +static __always_inline int +get_map_perf_counter(struct bpf_map *map, u64 flags, + u64 *value, u64 *enabled, u64 *running) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; - u64 value = 0; - int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; @@ -275,7 +290,15 @@ BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) if (!ee) return -ENOENT; - err = perf_event_read_local(ee->event, &value); + return perf_event_read_local(ee->event, value, enabled, running); +} + +BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) +{ + u64 value = 0; + int err; + + err = get_map_perf_counter(map, flags, &value, NULL, NULL); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi @@ -293,6 +316,33 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_perf_event_read_value, struct bpf_map *, map, u64, flags, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = get_map_perf_counter(map, flags, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_event_read_value_proto = { + .func = bpf_perf_event_read_value, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + static DEFINE_PER_CPU(struct perf_sample_data, bpf_sd); static __always_inline u64 @@ -499,6 +549,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; default: return tracing_func_proto(func_id); } @@ -524,11 +576,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type return true; } -const struct bpf_verifier_ops kprobe_prog_ops = { +const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; +const struct bpf_prog_ops kprobe_prog_ops = { +}; + BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { @@ -576,6 +631,32 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(bpf_perf_prog_read_value_tp, struct bpf_perf_event_data_kern *, ctx, + struct bpf_perf_event_value *, buf, u32, size) +{ + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_perf_event_value))) + goto clear; + err = perf_event_read_local(ctx->event, &buf->counter, &buf->enabled, + &buf->running); + if (unlikely(err)) + goto clear; + return 0; +clear: + memset(buf, 0, size); + return err; +} + +static const struct bpf_func_proto bpf_perf_prog_read_value_proto_tp = { + .func = bpf_perf_prog_read_value_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, +}; + static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -583,6 +664,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_perf_prog_read_value: + return &bpf_perf_prog_read_value_proto_tp; default: return tracing_func_proto(func_id); } @@ -602,11 +685,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type return true; } -const struct bpf_verifier_ops tracepoint_prog_ops = { +const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -662,8 +748,67 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops perf_event_prog_ops = { +const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; + +const struct bpf_prog_ops perf_event_prog_ops = { +}; + +static DEFINE_MUTEX(bpf_event_mutex); + +int perf_event_attach_bpf_prog(struct perf_event *event, + struct bpf_prog *prog) +{ + struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *new_array; + int ret = -EEXIST; + + mutex_lock(&bpf_event_mutex); + + if (event->prog) + goto unlock; + + old_array = event->tp_event->prog_array; + ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); + if (ret < 0) + goto unlock; + + /* set the new array to event->tp_event and set event->prog */ + event->prog = prog; + rcu_assign_pointer(event->tp_event->prog_array, new_array); + bpf_prog_array_free(old_array); + +unlock: + mutex_unlock(&bpf_event_mutex); + return ret; +} + +void perf_event_detach_bpf_prog(struct perf_event *event) +{ + struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *new_array; + int ret; + + mutex_lock(&bpf_event_mutex); + + if (!event->prog) + goto unlock; + + old_array = event->tp_event->prog_array; + ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); + if (ret < 0) { + bpf_prog_array_delete_safe(old_array, event->prog); + } else { + rcu_assign_pointer(event->tp_event->prog_array, new_array); + bpf_prog_array_free(old_array); + } + + bpf_prog_put(event->prog); + event->prog = NULL; + +unlock: + mutex_unlock(&bpf_event_mutex); +} 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/power-traces.c b/kernel/trace/power-traces.c index 0c7dee221dca..21bb161c2316 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Power trace points * diff --git a/kernel/trace/rpm-traces.c b/kernel/trace/rpm-traces.c index 4b3b5eaf94d1..25dec0b00280 100644 --- a/kernel/trace/rpm-traces.c +++ b/kernel/trace/rpm-traces.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Power trace points * diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 652c682707cd..401b0639116f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KERNEL_TRACE_H #define _LINUX_KERNEL_TRACE_H diff --git a/kernel/trace/trace_benchmark.c b/kernel/trace/trace_benchmark.c index 16a8cf02eee9..79f838a75077 100644 --- a/kernel/trace/trace_benchmark.c +++ b/kernel/trace/trace_benchmark.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <linux/delay.h> #include <linux/module.h> #include <linux/kthread.h> diff --git a/kernel/trace/trace_benchmark.h b/kernel/trace/trace_benchmark.h index ebdbfc2f2a64..be1d86ff753d 100644 --- a/kernel/trace/trace_benchmark.h +++ b/kernel/trace/trace_benchmark.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM benchmark diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c index 4d8fdf3184dc..4ad967453b6f 100644 --- a/kernel/trace/trace_branch.c +++ b/kernel/trace/trace_branch.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * unlikely profiler * diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index adcdbbeae010..e954ae3d82c0 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * This file defines the trace event structures that go into the ring * buffer directly. They are created via macros so that changes for them diff --git a/kernel/trace/trace_events_filter_test.h b/kernel/trace/trace_events_filter_test.h index bfd4dba0d603..39d7ef4f57cb 100644 --- a/kernel/trace/trace_events_filter_test.h +++ b/kernel/trace/trace_events_filter_test.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM test diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c index 39aa7aa66468..548e62eb5c46 100644 --- a/kernel/trace/trace_export.c +++ b/kernel/trace/trace_export.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * trace_export.c - export basic ftrace utilities to user space * diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index a0910c0cdf2e..27f7ad12c4b1 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * ring buffer based function tracer * diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index b8f1f54731af..23c0b0cb5fb9 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * * Function graph tracer. diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c index 57149bce6aad..d953c163a079 100644 --- a/kernel/trace/trace_kdb.c +++ b/kernel/trace/trace_kdb.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * kdb helper for dumping the ftrace buffer * diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8a907e12b6b9..abf92e478cfb 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1174,13 +1174,12 @@ static void kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) { struct trace_event_call *call = &tk->tp.call; - struct bpf_prog *prog = call->prog; struct kprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; - if (prog && !trace_call_bpf(prog, regs)) + if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) return; head = this_cpu_ptr(call->perf_events); @@ -1210,13 +1209,12 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_event_call *call = &tk->tp.call; - struct bpf_prog *prog = call->prog; struct kretprobe_trace_entry_head *entry; struct hlist_head *head; int size, __size, dsize; int rctx; - if (prog && !trace_call_bpf(prog, regs)) + if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) return; head = this_cpu_ptr(call->perf_events); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index dca78fc48439..b0388016b687 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Memory mapped I/O tracing * diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c index 49f61fe96a6b..50523f953a5d 100644 --- a/kernel/trace/trace_nop.c +++ b/kernel/trace/trace_nop.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * nop tracer * diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h index fabc49bcd493..dbba03ed96de 100644 --- a/kernel/trace/trace_output.h +++ b/kernel/trace/trace_output.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __TRACE_EVENTS_H #define __TRACE_EVENTS_H diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index b341c02730be..e288168661e1 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * trace context switch * diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0c331978b1a6..7d461dcd4831 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * trace task wakeup timings * diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index b17ec642793b..cd70eb5df38e 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Include in trace.c */ #include <uapi/linux/sched/types.h> diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c index b4c475a0a48b..8cda06a10d66 100644 --- a/kernel/trace/trace_selftest_dynamic.c +++ b/kernel/trace/trace_selftest_dynamic.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "trace.h" int DYN_FTRACE_TEST_NAME(void) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 49cb41412eec..719a52a4064a 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com> * diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 413ff108fbd0..75bf1bcb4a8a 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Infrastructure for statistic tracing (histogram output). * diff --git a/kernel/trace/trace_stat.h b/kernel/trace/trace_stat.h index 8f03914b9a6a..76d30b4ebe83 100644 --- a/kernel/trace/trace_stat.h +++ b/kernel/trace/trace_stat.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __TRACE_STAT_H #define __TRACE_STAT_H diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 696afe72d3b1..19bcaaac884b 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include <trace/syscall.h> #include <trace/events/syscalls.h> #include <linux/syscalls.h> @@ -559,9 +560,10 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls); static int sys_perf_refcount_enter; static int sys_perf_refcount_exit; -static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs, - struct syscall_metadata *sys_data, - struct syscall_trace_enter *rec) { +static int perf_call_bpf_enter(struct trace_event_call *call, struct pt_regs *regs, + struct syscall_metadata *sys_data, + struct syscall_trace_enter *rec) +{ struct syscall_tp_t { unsigned long long regs; unsigned long syscall_nr; @@ -573,7 +575,7 @@ static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs, param.syscall_nr = rec->nr; for (i = 0; i < sys_data->nb_args; i++) param.args[i] = rec->args[i]; - return trace_call_bpf(prog, ¶m); + return trace_call_bpf(call, ¶m); } static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) @@ -581,7 +583,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) struct syscall_metadata *sys_data; struct syscall_trace_enter *rec; struct hlist_head *head; - struct bpf_prog *prog; + bool valid_prog_array; int syscall_nr; int rctx; int size; @@ -596,9 +598,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (!sys_data) return; - prog = READ_ONCE(sys_data->enter_event->prog); head = this_cpu_ptr(sys_data->enter_event->perf_events); - if (!prog && hlist_empty(head)) + valid_prog_array = bpf_prog_array_valid(sys_data->enter_event); + if (!valid_prog_array && hlist_empty(head)) return; /* get the size after alignment with the u32 buffer size field */ @@ -614,7 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) syscall_get_arguments(current, regs, 0, sys_data->nb_args, (unsigned long *)&rec->args); - if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) || + if ((valid_prog_array && + !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) || hlist_empty(head)) { perf_swevent_put_recursion_context(rctx); return; @@ -659,8 +662,9 @@ static void perf_sysenter_disable(struct trace_event_call *call) mutex_unlock(&syscall_trace_lock); } -static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs, - struct syscall_trace_exit *rec) { +static int perf_call_bpf_exit(struct trace_event_call *call, struct pt_regs *regs, + struct syscall_trace_exit *rec) +{ struct syscall_tp_t { unsigned long long regs; unsigned long syscall_nr; @@ -670,7 +674,7 @@ static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs, *(struct pt_regs **)¶m = regs; param.syscall_nr = rec->nr; param.ret = rec->ret; - return trace_call_bpf(prog, ¶m); + return trace_call_bpf(call, ¶m); } static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) @@ -678,7 +682,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) struct syscall_metadata *sys_data; struct syscall_trace_exit *rec; struct hlist_head *head; - struct bpf_prog *prog; + bool valid_prog_array; int syscall_nr; int rctx; int size; @@ -693,9 +697,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!sys_data) return; - prog = READ_ONCE(sys_data->exit_event->prog); head = this_cpu_ptr(sys_data->exit_event->perf_events); - if (!prog && hlist_empty(head)) + valid_prog_array = bpf_prog_array_valid(sys_data->exit_event); + if (!valid_prog_array && hlist_empty(head)) return; /* We can probably do that at build time */ @@ -709,7 +713,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); - if ((prog && !perf_call_bpf_exit(prog, regs, rec)) || + if ((valid_prog_array && + !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) || hlist_empty(head)) { perf_swevent_put_recursion_context(rctx); return; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 4525e0271a53..153c0e411461 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1113,13 +1113,12 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, { struct trace_event_call *call = &tu->tp.call; struct uprobe_trace_entry_head *entry; - struct bpf_prog *prog = call->prog; struct hlist_head *head; void *data; int size, esize; int rctx; - if (prog && !trace_call_bpf(prog, regs)) + if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) return; esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); diff --git a/kernel/trace/tracing_map.h b/kernel/trace/tracing_map.h index 618838f5f30a..ab0ca77331d0 100644 --- a/kernel/trace/tracing_map.h +++ b/kernel/trace/tracing_map.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __TRACING_MAP_H #define __TRACING_MAP_H diff --git a/kernel/uid16.c b/kernel/uid16.c index 5c2dc5b2bf4f..ce74a4901d2b 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Wrapper functions for 16bit uid back compatibility. All nicely tied * together in the faint hope we can take the out in five years time. diff --git a/kernel/watchdog.c b/kernel/watchdog.c index f5d52024f6b7..c8e06703e44c 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * @@ -29,20 +30,29 @@ #include <linux/kvm_para.h> #include <linux/kthread.h> -/* Watchdog configuration */ -static DEFINE_MUTEX(watchdog_proc_mutex); - -int __read_mostly nmi_watchdog_enabled; +static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED | - NMI_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 1 #else -unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; +# define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) +# define NMI_WATCHDOG_DEFAULT 0 #endif +unsigned long __read_mostly watchdog_enabled; +int __read_mostly watchdog_user_enabled = 1; +int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; +int __read_mostly soft_watchdog_user_enabled = 1; +int __read_mostly watchdog_thresh = 10; +int __read_mostly nmi_watchdog_available; + +struct cpumask watchdog_allowed_mask __read_mostly; + +struct cpumask watchdog_cpumask __read_mostly; +unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); + #ifdef CONFIG_HARDLOCKUP_DETECTOR -/* boot commands */ /* * Should we panic when a soft-lockup or hard-lockup occurs: */ @@ -56,9 +66,9 @@ unsigned int __read_mostly hardlockup_panic = * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ -void hardlockup_detector_disable(void) +void __init hardlockup_detector_disable(void) { - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) @@ -68,48 +78,24 @@ static int __init hardlockup_panic_setup(char *str) else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) - watchdog_enabled &= ~NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) - watchdog_enabled |= NMI_WATCHDOG_ENABLED; + nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); -#endif - -#ifdef CONFIG_SOFTLOCKUP_DETECTOR -int __read_mostly soft_watchdog_enabled; -#endif - -int __read_mostly watchdog_user_enabled; -int __read_mostly watchdog_thresh = 10; - -#ifdef CONFIG_SMP -int __read_mostly sysctl_softlockup_all_cpu_backtrace; +# ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; -#endif -struct cpumask watchdog_cpumask __read_mostly; -unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); -/* - * The 'watchdog_running' variable is set to 1 when the watchdog threads - * are registered/started and is set to 0 when the watchdog threads are - * unregistered/stopped, so it is an indicator whether the threads exist. - */ -static int __read_mostly watchdog_running; -/* - * If a subsystem has a need to deactivate the watchdog temporarily, it - * can use the suspend/resume interface to achieve this. The content of - * the 'watchdog_suspended' variable reflects this state. Existing threads - * are parked/unparked by the lockup_detector_{suspend|resume} functions - * (see comment blocks pertaining to those functions for further details). - * - * 'watchdog_suspended' also prevents threads from being registered/started - * or unregistered/stopped via parameters in /proc/sys/kernel, so the state - * of 'watchdog_running' cannot change while the watchdog is deactivated - * temporarily (see related code in 'proc' handlers). - */ -int __read_mostly watchdog_suspended; +static int __init hardlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); +# endif /* CONFIG_SMP */ +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its @@ -121,36 +107,68 @@ int __read_mostly watchdog_suspended; */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } + void __weak watchdog_nmi_disable(unsigned int cpu) { + hardlockup_detector_perf_disable(); } -/* - * watchdog_nmi_reconfigure can be implemented to be notified after any - * watchdog configuration change. The arch hardlockup watchdog should - * respond to the following variables: - * - nmi_watchdog_enabled +/* Return 0, if a NMI watchdog is available. Error code otherwise */ +int __weak __init watchdog_nmi_probe(void) +{ + return hardlockup_detector_perf_init(); +} + +/** + * watchdog_nmi_stop - Stop the watchdog for reconfiguration + * + * The reconfiguration steps are: + * watchdog_nmi_stop(); + * update_variables(); + * watchdog_nmi_start(); + */ +void __weak watchdog_nmi_stop(void) { } + +/** + * watchdog_nmi_start - Start the watchdog after reconfiguration + * + * Counterpart to watchdog_nmi_stop(). + * + * The following variables have been updated in update_variables() and + * contain the currently valid configuration: + * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask - * - sysctl_hardlockup_all_cpu_backtrace - * - hardlockup_panic - * - watchdog_suspended */ -void __weak watchdog_nmi_reconfigure(void) +void __weak watchdog_nmi_start(void) { } + +/** + * lockup_detector_update_enable - Update the sysctl enable bit + * + * Caller needs to make sure that the NMI/perf watchdogs are off, so this + * can't race with watchdog_nmi_disable(). + */ +static void lockup_detector_update_enable(void) { + watchdog_enabled = 0; + if (!watchdog_user_enabled) + return; + if (nmi_watchdog_available && nmi_watchdog_user_enabled) + watchdog_enabled |= NMI_WATCHDOG_ENABLED; + if (soft_watchdog_user_enabled) + watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } - #ifdef CONFIG_SOFTLOCKUP_DETECTOR -/* Helper for online, unparked cpus. */ -#define for_each_watchdog_cpu(cpu) \ - for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask) - -atomic_t watchdog_park_in_progress = ATOMIC_INIT(0); +/* Global variables, exported for sysctl */ +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; +static bool softlockup_threads_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); @@ -164,50 +182,40 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; -unsigned int __read_mostly softlockup_panic = - CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; - static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); - return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { - watchdog_enabled = 0; + watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { - watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED; + soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); #ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; + static int __init softlockup_all_cpu_backtrace_setup(char *str) { - sysctl_softlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); + sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); -#ifdef CONFIG_HARDLOCKUP_DETECTOR -static int __init hardlockup_all_cpu_backtrace_setup(char *str) -{ - sysctl_hardlockup_all_cpu_backtrace = - !!simple_strtol(str, NULL, 0); - return 1; -} -__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); -#endif #endif +static void __lockup_detector_cleanup(void); + /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally @@ -278,11 +286,15 @@ void touch_all_softlockup_watchdogs(void) int cpu; /* - * this is done lockless - * do we care if a 0 races with a timestamp? - * all it means is the softlock check starts one cycle later + * watchdog_mutex cannpt be taken here, as this might be called + * from (soft)interrupt context, so the access to + * watchdog_allowed_cpumask might race with a concurrent update. + * + * The watchdog time stamp can race against a concurrent real + * update as well, the only side effect might be a cycle delay for + * the softlockup check. */ - for_each_watchdog_cpu(cpu) + for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = 0; wq_watchdog_touch(-1); } @@ -322,9 +334,6 @@ static void watchdog_interrupt_count(void) __this_cpu_inc(hrtimer_interrupts); } -static int watchdog_enable_all_cpus(void); -static void watchdog_disable_all_cpus(void); - /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { @@ -333,7 +342,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; - if (atomic_read(&watchdog_park_in_progress) != 0) + if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ @@ -447,32 +456,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio) static void watchdog_enable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); - /* kick off the timer for the hardlockup detector */ + /* + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer->function = watchdog_timer_fn; - - /* Enable the perf event */ - watchdog_nmi_enable(cpu); - - /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED); - /* initialize timestamp */ - watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + /* Initialize timestamp */ __touch_watchdog(); + /* Enable the perf event */ + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); + + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } static void watchdog_disable(unsigned int cpu) { - struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer); + struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); watchdog_set_prio(SCHED_NORMAL, 0); - hrtimer_cancel(hrtimer); - /* disable the perf event */ + /* + * Disable the perf event first. That prevents that a large delay + * between disabling the timer and disabling the perf event causes + * the perf NMI to detect a false positive. + */ watchdog_nmi_disable(cpu); + hrtimer_cancel(hrtimer); } static void watchdog_cleanup(unsigned int cpu, bool online) @@ -499,21 +514,6 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); - - /* - * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the - * failure path. Check for failures that can occur asynchronously - - * for example, when CPUs are on-lined - and shut down the hardware - * perf event on each CPU accordingly. - * - * The only non-obvious place this bit can be cleared is through - * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a - * pr_info here would be too noisy as it would result in a message - * every few seconds if the hardlockup was disabled but the softlockup - * enabled. - */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - watchdog_nmi_disable(cpu); } static struct smp_hotplug_thread watchdog_threads = { @@ -527,295 +527,174 @@ static struct smp_hotplug_thread watchdog_threads = { .unpark = watchdog_enable, }; -/* - * park all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function returns an error if kthread_park() of a watchdog thread - * fails. In this situation, the watchdog threads of some CPUs can already - * be parked and the watchdog threads of other CPUs can still be runnable. - * Callers are expected to handle this special condition as appropriate in - * their context. - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static int watchdog_park_threads(void) +static void softlockup_update_smpboot_threads(void) { - int cpu, ret = 0; + lockdep_assert_held(&watchdog_mutex); - atomic_set(&watchdog_park_in_progress, 1); + if (!softlockup_threads_initialized) + return; - for_each_watchdog_cpu(cpu) { - ret = kthread_park(per_cpu(softlockup_watchdog, cpu)); - if (ret) - break; - } - - atomic_set(&watchdog_park_in_progress, 0); - - return ret; + smpboot_update_cpumask_percpu_thread(&watchdog_threads, + &watchdog_allowed_mask); } -/* - * unpark all watchdog threads that are specified in 'watchdog_cpumask' - * - * This function may only be called in a context that is protected against - * races with CPU hotplug - for example, via get_online_cpus(). - */ -static void watchdog_unpark_threads(void) +/* Temporarily park all watchdog threads */ +static void softlockup_park_all_threads(void) { - int cpu; - - for_each_watchdog_cpu(cpu) - kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + cpumask_clear(&watchdog_allowed_mask); + softlockup_update_smpboot_threads(); } -static int update_watchdog_all_cpus(void) +/* Unpark enabled threads */ +static void softlockup_unpark_threads(void) { - int ret; - - ret = watchdog_park_threads(); - if (ret) - return ret; - - watchdog_unpark_threads(); - - return 0; + cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); + softlockup_update_smpboot_threads(); } -static int watchdog_enable_all_cpus(void) +static void lockup_detector_reconfigure(void) { - int err = 0; - - if (!watchdog_running) { - err = smpboot_register_percpu_thread_cpumask(&watchdog_threads, - &watchdog_cpumask); - if (err) - pr_err("Failed to create watchdog threads, disabled\n"); - else - watchdog_running = 1; - } else { - /* - * Enable/disable the lockup detectors or - * change the sample period 'on the fly'. - */ - err = update_watchdog_all_cpus(); - - if (err) { - watchdog_disable_all_cpus(); - pr_err("Failed to update lockup detectors, disabled\n"); - } - } - - if (err) - watchdog_enabled = 0; - - return err; + cpus_read_lock(); + watchdog_nmi_stop(); + softlockup_park_all_threads(); + set_sample_period(); + lockup_detector_update_enable(); + if (watchdog_enabled && watchdog_thresh) + softlockup_unpark_threads(); + watchdog_nmi_start(); + cpus_read_unlock(); + /* + * Must be called outside the cpus locked section to prevent + * recursive locking in the perf code. + */ + __lockup_detector_cleanup(); } -static void watchdog_disable_all_cpus(void) +/* + * Create the watchdog thread infrastructure and configure the detector(s). + * + * The threads are not unparked as watchdog_allowed_mask is empty. When + * the threads are sucessfully initialized, take the proper locks and + * unpark the threads in the watchdog_cpumask if the watchdog is enabled. + */ +static __init void lockup_detector_setup(void) { - if (watchdog_running) { - watchdog_running = 0; - smpboot_unregister_percpu_thread(&watchdog_threads); - } -} + int ret; -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) -{ - return smpboot_update_cpumask_percpu_thread( - &watchdog_threads, &watchdog_cpumask); -} -#endif + /* + * If sysctl is off and watchdog got disabled on the command line, + * nothing to do here. + */ + lockup_detector_update_enable(); -#else /* SOFTLOCKUP */ -static int watchdog_park_threads(void) -{ - return 0; -} + if (!IS_ENABLED(CONFIG_SYSCTL) && + !(watchdog_enabled && watchdog_thresh)) + return; -static void watchdog_unpark_threads(void) -{ -} + ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads, + &watchdog_allowed_mask); + if (ret) { + pr_err("Failed to initialize soft lockup detector threads\n"); + return; + } -static int watchdog_enable_all_cpus(void) -{ - return 0; + mutex_lock(&watchdog_mutex); + softlockup_threads_initialized = true; + lockup_detector_reconfigure(); + mutex_unlock(&watchdog_mutex); } -static void watchdog_disable_all_cpus(void) +#else /* CONFIG_SOFTLOCKUP_DETECTOR */ +static inline int watchdog_park_threads(void) { return 0; } +static inline void watchdog_unpark_threads(void) { } +static inline int watchdog_enable_all_cpus(void) { return 0; } +static inline void watchdog_disable_all_cpus(void) { } +static void lockup_detector_reconfigure(void) { + cpus_read_lock(); + watchdog_nmi_stop(); + lockup_detector_update_enable(); + watchdog_nmi_start(); + cpus_read_unlock(); } - -#ifdef CONFIG_SYSCTL -static int watchdog_update_cpus(void) +static inline void lockup_detector_setup(void) { - return 0; + lockup_detector_reconfigure(); } -#endif +#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ -static void set_sample_period(void) +static void __lockup_detector_cleanup(void) { + lockdep_assert_held(&watchdog_mutex); + hardlockup_detector_perf_cleanup(); } -#endif /* SOFTLOCKUP */ -/* - * Suspend the hard and soft lockup detector by parking the watchdog threads. +/** + * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes + * + * Caller must not hold the cpu hotplug rwsem. */ -int lockup_detector_suspend(void) +void lockup_detector_cleanup(void) { - int ret = 0; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - /* - * Multiple suspend requests can be active in parallel (counted by - * the 'watchdog_suspended' variable). If the watchdog threads are - * running, the first caller takes care that they will be parked. - * The state of 'watchdog_running' cannot change while a suspend - * request is active (see related code in 'proc' handlers). - */ - if (watchdog_running && !watchdog_suspended) - ret = watchdog_park_threads(); - - if (ret == 0) - watchdog_suspended++; - else { - watchdog_disable_all_cpus(); - pr_err("Failed to suspend lockup detectors, disabled\n"); - watchdog_enabled = 0; - } - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - - return ret; + mutex_lock(&watchdog_mutex); + __lockup_detector_cleanup(); + mutex_unlock(&watchdog_mutex); } -/* - * Resume the hard and soft lockup detector by unparking the watchdog threads. +/** + * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) + * + * Special interface for parisc. It prevents lockup detector warnings from + * the default pm_poweroff() function which busy loops forever. */ -void lockup_detector_resume(void) +void lockup_detector_soft_poweroff(void) { - mutex_lock(&watchdog_proc_mutex); - - watchdog_suspended--; - /* - * The watchdog threads are unparked if they were previously running - * and if there is no more active suspend request. - */ - if (watchdog_running && !watchdog_suspended) - watchdog_unpark_threads(); - - watchdog_nmi_reconfigure(); - - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL -/* - * Update the run state of the lockup detectors. - */ -static int proc_watchdog_update(void) +/* Propagate any changes to the watchdog threads */ +static void proc_watchdog_update(void) { - int err = 0; - - /* - * Watchdog threads won't be started if they are already active. - * The 'watchdog_running' variable in watchdog_*_all_cpus() takes - * care of this. If those threads are already active, the sample - * period will be updated and the lockup detectors will be enabled - * or disabled 'on the fly'. - */ - if (watchdog_enabled && watchdog_thresh) - err = watchdog_enable_all_cpus(); - else - watchdog_disable_all_cpus(); - - watchdog_nmi_reconfigure(); - - return err; - + /* Remove impossible cpus to keep sysctl output clean. */ + cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); + lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * - * caller | table->data points to | 'which' contains the flag(s) - * -------------------|-----------------------|----------------------------- - * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed - * | | with SOFT_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_nmi_watchdog | nmi_watchdog_enabled | NMI_WATCHDOG_ENABLED - * -------------------|-----------------------|----------------------------- - * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED + * caller | table->data points to | 'which' + * -------------------|----------------------------|-------------------------- + * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | + * | | SOFT_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED + * -------------------|----------------------------|-------------------------- + * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - int *watchdog_param = (int *)table->data; + int err, old, *param = table->data; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + mutex_lock(&watchdog_mutex); - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } - - /* - * If the parameter is being read return the state of the corresponding - * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the - * run state of the lockup detectors. - */ if (!write) { - *watchdog_param = (watchdog_enabled & which) != 0; + /* + * On read synchronize the userspace interface. This is a + * racy snapshot. + */ + *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { + old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err) - goto out; - - /* - * There is a race window between fetching the current value - * from 'watchdog_enabled' and storing the new value. During - * this race window, watchdog_nmi_enable() can sneak in and - * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'. - * The 'cmpxchg' detects this race and the loop retries. - */ - do { - old = watchdog_enabled; - /* - * If the parameter value is not zero set the - * corresponding bit(s), else clear it(them). - */ - if (*watchdog_param) - new = old | which; - else - new = old & ~which; - } while (cmpxchg(&watchdog_enabled, old, new) != old); - - /* - * Update the run state of the lockup detectors. There is _no_ - * need to check the value returned by proc_watchdog_update() - * and to restore the previous value of 'watchdog_enabled' as - * both lockup detectors are disabled if proc_watchdog_update() - * returns an error. - */ - if (old == new) - goto out; - - err = proc_watchdog_update(); + if (!err && old != READ_ONCE(*param)) + proc_watchdog_update(); } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -835,6 +714,8 @@ int proc_watchdog(struct ctl_table *table, int write, int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + if (!nmi_watchdog_available && write) + return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } @@ -855,39 +736,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write, int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int err, old, new; - - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); + int err, old; - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); - old = ACCESS_ONCE(watchdog_thresh); + old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (err || !write) - goto out; - - /* - * Update the sample period. Restore on failure. - */ - new = ACCESS_ONCE(watchdog_thresh); - if (old == new) - goto out; + if (!err && write && old != READ_ONCE(watchdog_thresh)) + proc_watchdog_update(); - set_sample_period(); - err = proc_watchdog_update(); - if (err) { - watchdog_thresh = old; - set_sample_period(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } @@ -902,45 +761,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write, { int err; - get_online_cpus(); - mutex_lock(&watchdog_proc_mutex); - - if (watchdog_suspended) { - /* no parameter changes allowed while watchdog is suspended */ - err = -EAGAIN; - goto out; - } + mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); - if (!err && write) { - /* Remove impossible cpus to keep sysctl output cleaner. */ - cpumask_and(&watchdog_cpumask, &watchdog_cpumask, - cpu_possible_mask); - - if (watchdog_running) { - /* - * Failure would be due to being unable to allocate - * a temporary cpumask, so we are likely not in a - * position to do much else to make things better. - */ - if (watchdog_update_cpus() != 0) - pr_err("cpumask update failed\n"); - } + if (!err && write) + proc_watchdog_update(); - watchdog_nmi_reconfigure(); - } -out: - mutex_unlock(&watchdog_proc_mutex); - put_online_cpus(); + mutex_unlock(&watchdog_mutex); return err; } - #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { - set_sample_period(); - #ifdef CONFIG_NO_HZ_FULL if (tick_nohz_full_enabled()) { pr_info("Disabling watchdog on nohz_full cores by default\n"); @@ -951,6 +784,7 @@ void __init lockup_detector_init(void) cpumask_copy(&watchdog_cpumask, cpu_possible_mask); #endif - if (watchdog_enabled) - watchdog_enable_all_cpus(); + if (!watchdog_nmi_probe()) + nmi_watchdog_available = true; + lockup_detector_setup(); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 3a09ea1b1d3d..e449a23e9d59 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Detect hard lockups on a system * @@ -12,6 +13,7 @@ #define pr_fmt(fmt) "NMI watchdog: " fmt #include <linux/nmi.h> +#include <linux/atomic.h> #include <linux/module.h> #include <linux/sched/debug.h> @@ -21,8 +23,11 @@ static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +static DEFINE_PER_CPU(struct perf_event *, dead_event); +static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; +static atomic_t watchdog_cpus = ATOMIC_INIT(0); void arch_touch_nmi_watchdog(void) { @@ -103,15 +108,12 @@ static struct perf_event_attr wd_hw_attr = { /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, - struct perf_sample_data *data, - struct pt_regs *regs) + struct perf_sample_data *data, + struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; - if (atomic_read(&watchdog_park_in_progress) != 0) - return; - if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; @@ -160,104 +162,134 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) +static int hardlockup_detector_event_create(void) { + unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; + struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); + evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, + watchdog_overflow_callback, NULL); + if (IS_ERR(evt)) { + pr_info("Perf event create on CPU %d failed with %ld\n", cpu, + PTR_ERR(evt)); + return PTR_ERR(evt); + } + this_cpu_write(watchdog_ev, evt); + return 0; +} - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); +/** + * hardlockup_detector_perf_enable - Enable the local event + */ +void hardlockup_detector_perf_enable(void) +{ + if (hardlockup_detector_event_create()) + return; - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } + /* use original value for check */ + if (!atomic_fetch_inc(&watchdog_cpus)) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); - /* - * Disable the hard lockup detector if _any_ CPU fails to set up - * set up the hardware perf event. The watchdog() function checks - * the NMI_WATCHDOG_ENABLED bit periodically. - * - * The barriers are for syncing up watchdog_enabled across all the - * cpus, as clear_bit() does not use barriers. - */ - smp_mb__before_atomic(); - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); - smp_mb__after_atomic(); - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Shutting down hard lockup detector on all cpus\n"); - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; + perf_event_enable(this_cpu_read(watchdog_ev)); } -void watchdog_nmi_disable(unsigned int cpu) +/** + * hardlockup_detector_perf_disable - Disable the local event + */ +void hardlockup_detector_perf_disable(void) { - struct perf_event *event = per_cpu(watchdog_ev, cpu); + struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); - per_cpu(watchdog_ev, cpu) = NULL; + this_cpu_write(watchdog_ev, NULL); + this_cpu_write(dead_event, event); + cpumask_set_cpu(smp_processor_id(), &dead_events_mask); + atomic_dec(&watchdog_cpus); + } +} + +/** + * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them + * + * Called from lockup_detector_cleanup(). Serialized by the caller. + */ +void hardlockup_detector_perf_cleanup(void) +{ + int cpu; + + for_each_cpu(cpu, &dead_events_mask) { + struct perf_event *event = per_cpu(dead_event, cpu); - /* should be in cleanup, but blocks oprofile */ - perf_event_release_kernel(event); + /* + * Required because for_each_cpu() reports unconditionally + * CPU0 as set on UP kernels. Sigh. + */ + if (event) + perf_event_release_kernel(event); + per_cpu(dead_event, cpu) = NULL; + } + cpumask_clear(&dead_events_mask); +} + +/** + * hardlockup_detector_perf_stop - Globally stop watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_stop(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_disable(event); + } +} + +/** + * hardlockup_detector_perf_restart - Globally restart watchdog events + * + * Special interface for x86 to handle the perf HT bug. + */ +void __init hardlockup_detector_perf_restart(void) +{ + int cpu; + + lockdep_assert_cpus_held(); + + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + return; + + for_each_online_cpu(cpu) { + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) + perf_event_enable(event); + } +} + +/** + * hardlockup_detector_perf_init - Probe whether NMI event is available at all + */ +int __init hardlockup_detector_perf_init(void) +{ + int ret = hardlockup_detector_event_create(); - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + if (ret) { + pr_info("Perf NMI watchdog permanently disabled\n"); + } else { + perf_event_release_kernel(this_cpu_read(watchdog_ev)); + this_cpu_write(watchdog_ev, NULL); } + return ret; } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 6e5eed58f215..3b67c0a0df16 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -68,6 +68,7 @@ enum { * attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. */ + POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ /* worker flags */ @@ -165,7 +166,6 @@ struct worker_pool { /* L: hash of busy workers */ /* see manage_workers() for details on the two manager mutexes */ - struct mutex manager_arb; /* manager arbitration */ struct worker *manager; /* L: purely informational */ struct mutex attach_mutex; /* attach/detach exclusion */ struct list_head workers; /* A: attached workers */ @@ -299,6 +299,7 @@ static struct workqueue_attrs *wq_update_unbound_numa_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ +static DECLARE_WAIT_QUEUE_HEAD(wq_manager_wait); /* wait for manager to go away */ static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ @@ -801,7 +802,7 @@ static bool need_to_create_worker(struct worker_pool *pool) /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { - bool managing = mutex_is_locked(&pool->manager_arb); + bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; @@ -1979,24 +1980,17 @@ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; - /* - * Anyone who successfully grabs manager_arb wins the arbitration - * and becomes the manager. mutex_trylock() on pool->manager_arb - * failure while holding pool->lock reliably indicates that someone - * else is managing the pool and the worker which failed trylock - * can proceed to executing work items. This means that anyone - * grabbing manager_arb is responsible for actually performing - * manager duties. If manager_arb is grabbed and released without - * actual management, the pool may stall indefinitely. - */ - if (!mutex_trylock(&pool->manager_arb)) + if (pool->flags & POOL_MANAGER_ACTIVE) return false; + + pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; - mutex_unlock(&pool->manager_arb); + pool->flags &= ~POOL_MANAGER_ACTIVE; + wake_up(&wq_manager_wait); return true; } @@ -3245,7 +3239,6 @@ static int init_worker_pool(struct worker_pool *pool) timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); - mutex_init(&pool->manager_arb); mutex_init(&pool->attach_mutex); INIT_LIST_HEAD(&pool->workers); @@ -3315,13 +3308,15 @@ static void put_unbound_pool(struct worker_pool *pool) hash_del(&pool->hash_node); /* - * Become the manager and destroy all workers. Grabbing - * manager_arb prevents @pool's workers from blocking on - * attach_mutex. + * Become the manager and destroy all workers. This prevents + * @pool's workers from blocking on attach_mutex. We're the last + * manager and @pool gets freed with the flag set. */ - mutex_lock(&pool->manager_arb); - spin_lock_irq(&pool->lock); + wait_event_lock_irq(wq_manager_wait, + !(pool->flags & POOL_MANAGER_ACTIVE), pool->lock); + pool->flags |= POOL_MANAGER_ACTIVE; + while ((worker = first_idle_worker(pool))) destroy_worker(worker); WARN_ON(pool->nr_workers || pool->nr_idle); @@ -3335,8 +3330,6 @@ static void put_unbound_pool(struct worker_pool *pool) if (pool->detach_completion) wait_for_completion(pool->detach_completion); - mutex_unlock(&pool->manager_arb); - /* shut down the timers */ del_timer_sync(&pool->idle_timer); del_timer_sync(&pool->mayday_timer); diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 8635417c587b..d390d1be3748 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * kernel/workqueue_internal.h * @@ -9,6 +10,7 @@ #include <linux/workqueue.h> #include <linux/kthread.h> +#include <linux/preempt.h> struct worker_pool; @@ -59,7 +61,7 @@ struct worker { */ static inline struct worker *current_wq_worker(void) { - if (current->flags & PF_WQ_WORKER) + if (in_task() && (current->flags & PF_WQ_WORKER)) return kthread_data(current); return NULL; } |