diff options
Diffstat (limited to 'kernel')
62 files changed, 3899 insertions, 1564 deletions
diff --git a/kernel/.gitignore b/kernel/.gitignore index 34d1e77ee9df..78701ea37c97 100644 --- a/kernel/.gitignore +++ b/kernel/.gitignore @@ -1,6 +1,4 @@ -# -# Generated files -# +# SPDX-License-Identifier: GPL-2.0-only kheaders.md5 timeconst.h hz.bc diff --git a/kernel/audit.c b/kernel/audit.c index 9ddfe2aa6671..b69c8b460341 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1800,6 +1800,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, } audit_get_stamp(ab->ctx, &t, &serial); + audit_clear_dummy(ab->ctx); audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); diff --git a/kernel/audit.h b/kernel/audit.h index 6fb7160412d4..2eed4d231624 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -290,6 +290,13 @@ extern int audit_signal_info_syscall(struct task_struct *t); extern void audit_filter_inodes(struct task_struct *tsk, struct audit_context *ctx); extern struct list_head *audit_killed_trees(void); + +static inline void audit_clear_dummy(struct audit_context *ctx) +{ + if (ctx) + ctx->dummy = 0; +} + #else /* CONFIG_AUDITSYSCALL */ #define auditsc_get_stamp(c, t, s) 0 #define audit_put_watch(w) {} @@ -323,6 +330,7 @@ static inline int audit_signal_info_syscall(struct task_struct *t) } #define audit_filter_inodes(t, c) AUDIT_DISABLED +#define audit_clear_dummy(c) {} #endif /* CONFIG_AUDITSYSCALL */ extern char *audit_unpack_string(void **bufp, size_t *remain, size_t len); diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 4508d5e0cf69..8a8fd732ff6d 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -302,8 +302,6 @@ static void audit_update_watch(struct audit_parent *parent, if (oentry->rule.exe) audit_remove_mark(oentry->rule.exe); - audit_watch_log_rule_change(r, owatch, "updated_rules"); - call_rcu(&oentry->rcu, audit_free_rule_rcu); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4effe01ebbe2..814406a35db1 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1406,9 +1406,6 @@ static void audit_log_proctitle(void) struct audit_context *context = audit_context(); struct audit_buffer *ab; - if (!context || context->dummy) - return; - ab = audit_log_start(context, GFP_KERNEL, AUDIT_PROCTITLE); if (!ab) return; /* audit_panic or being filtered */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 046ce5d98033..f2d7be596966 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -29,4 +29,5 @@ obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o endif ifeq ($(CONFIG_BPF_JIT),y) obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o +obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c new file mode 100644 index 000000000000..19636703b24e --- /dev/null +++ b/kernel/bpf/bpf_lsm.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <linux/filter.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/lsm_hooks.h> +#include <linux/bpf_lsm.h> +#include <linux/kallsyms.h> +#include <linux/bpf_verifier.h> + +/* For every LSM hook that allows attachment of BPF programs, declare a nop + * function where a BPF program can be attached. + */ +#define LSM_HOOK(RET, DEFAULT, NAME, ...) \ +noinline RET bpf_lsm_##NAME(__VA_ARGS__) \ +{ \ + return DEFAULT; \ +} + +#include <linux/lsm_hook_defs.h> +#undef LSM_HOOK + +#define BPF_LSM_SYM_PREFX "bpf_lsm_" + +int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, + const struct bpf_prog *prog) +{ + if (!prog->gpl_compatible) { + bpf_log(vlog, + "LSM programs must have a GPL compatible license\n"); + return -EINVAL; + } + + if (strncmp(BPF_LSM_SYM_PREFX, prog->aux->attach_func_name, + sizeof(BPF_LSM_SYM_PREFX) - 1)) { + bpf_log(vlog, "attach_btf_id %u points to wrong type name %s\n", + prog->aux->attach_btf_id, prog->aux->attach_func_name); + return -EINVAL; + } + + return 0; +} + +const struct bpf_prog_ops lsm_prog_ops = { +}; + +const struct bpf_verifier_ops lsm_verifier_ops = { + .get_func_proto = bpf_tracing_func_proto, + .is_valid_access = btf_ctx_access, +}; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 68a89a9f7ccd..26cb51f2db72 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -23,7 +23,7 @@ enum bpf_struct_ops_state { struct bpf_struct_ops_value { BPF_STRUCT_OPS_COMMON_VALUE; - char data[0] ____cacheline_aligned_in_smp; + char data[] ____cacheline_aligned_in_smp; }; struct bpf_struct_ops_map { @@ -320,6 +320,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_struct_ops_value *uvalue, *kvalue; const struct btf_member *member; const struct btf_type *t = st_ops->type; + struct bpf_tramp_progs *tprogs = NULL; void *udata, *kdata; int prog_fd, err = 0; void *image; @@ -343,6 +344,10 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (uvalue->state || refcount_read(&uvalue->refcnt)) return -EINVAL; + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) + return -ENOMEM; + uvalue = (struct bpf_struct_ops_value *)st_map->uvalue; kvalue = (struct bpf_struct_ops_value *)&st_map->kvalue; @@ -425,10 +430,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } + tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; + tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; err = arch_prepare_bpf_trampoline(image, st_map->image + PAGE_SIZE, &st_ops->func_models[i], 0, - &prog, 1, NULL, 0, NULL); + tprogs, NULL); if (err < 0) goto reset_unlock; @@ -469,6 +476,7 @@ reset_unlock: memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); unlock: + kfree(tprogs); mutex_unlock(&st_map->lock); return err; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 7787bdcb5d68..d65c6912bdaf 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3477,8 +3477,8 @@ errout: return ERR_PTR(err); } -extern char __weak _binary__btf_vmlinux_bin_start[]; -extern char __weak _binary__btf_vmlinux_bin_end[]; +extern char __weak __start_BTF[]; +extern char __weak __stop_BTF[]; extern struct btf *btf_vmlinux; #define BPF_MAP_TYPE(_id, _ops) @@ -3605,9 +3605,8 @@ struct btf *btf_parse_vmlinux(void) } env->btf = btf; - btf->data = _binary__btf_vmlinux_bin_start; - btf->data_size = _binary__btf_vmlinux_bin_end - - _binary__btf_vmlinux_bin_start; + btf->data = __start_BTF; + btf->data_size = __stop_BTF - __start_BTF; err = btf_parse_hdr(env); if (err) @@ -3710,23 +3709,60 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, nr_args--; } - if (prog->expected_attach_type == BPF_TRACE_FEXIT && - arg == nr_args) { - if (!t) - /* Default prog with 5 args. 6th arg is retval. */ - return true; - /* function return type */ - t = btf_type_by_id(btf, t->type); - } else if (arg >= nr_args) { + if (arg > nr_args) { bpf_log(log, "func '%s' doesn't have %d-th argument\n", tname, arg + 1); return false; + } + + if (arg == nr_args) { + switch (prog->expected_attach_type) { + case BPF_LSM_MAC: + case BPF_TRACE_FEXIT: + /* When LSM programs are attached to void LSM hooks + * they use FEXIT trampolines and when attached to + * int LSM hooks, they use MODIFY_RETURN trampolines. + * + * While the LSM programs are BPF_MODIFY_RETURN-like + * the check: + * + * if (ret_type != 'int') + * return -EINVAL; + * + * is _not_ done here. This is still safe as LSM hooks + * have only void and int return types. + */ + if (!t) + return true; + t = btf_type_by_id(btf, t->type); + break; + case BPF_MODIFY_RETURN: + /* For now the BPF_MODIFY_RETURN can only be attached to + * functions that return an int. + */ + if (!t) + return false; + + t = btf_type_skip_modifiers(btf, t->type, NULL); + if (!btf_type_is_int(t)) { + bpf_log(log, + "ret type %s not allowed for fmod_ret\n", + btf_kind_str[BTF_INFO_KIND(t->info)]); + return false; + } + break; + default: + bpf_log(log, "func '%s' doesn't have %d-th argument\n", + tname, arg + 1); + return false; + } } else { if (!t) /* Default prog with 5 args */ return true; t = btf_type_by_id(btf, args[arg].type); } + /* skip modifiers */ while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4f1472409ef8..cb305e71e7de 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -28,6 +28,69 @@ void cgroup_bpf_offline(struct cgroup *cgrp) percpu_ref_kill(&cgrp->bpf.refcnt); } +static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_free(storages[stype]); +} + +static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[], + struct bpf_prog *prog) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) { + storages[stype] = bpf_cgroup_storage_alloc(prog, stype); + if (IS_ERR(storages[stype])) { + storages[stype] = NULL; + bpf_cgroup_storages_free(storages); + return -ENOMEM; + } + } + + return 0; +} + +static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[], + struct bpf_cgroup_storage *src[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + dst[stype] = src[stype]; +} + +static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], + struct cgroup* cgrp, + enum bpf_attach_type attach_type) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_link(storages[stype], cgrp, attach_type); +} + +static void bpf_cgroup_storages_unlink(struct bpf_cgroup_storage *storages[]) +{ + enum bpf_cgroup_storage_type stype; + + for_each_cgroup_storage_type(stype) + bpf_cgroup_storage_unlink(storages[stype]); +} + +/* Called when bpf_cgroup_link is auto-detached from dying cgroup. + * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It + * doesn't free link memory, which will eventually be done by bpf_link's + * release() callback, when its last FD is closed. + */ +static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link) +{ + cgroup_put(link->cgroup); + link->cgroup = NULL; +} + /** * cgroup_bpf_release() - put references of all bpf programs and * release all cgroup bpf data @@ -37,7 +100,6 @@ static void cgroup_bpf_release(struct work_struct *work) { struct cgroup *p, *cgrp = container_of(work, struct cgroup, bpf.release_work); - enum bpf_cgroup_storage_type stype; struct bpf_prog_array *old_array; unsigned int type; @@ -49,11 +111,12 @@ static void cgroup_bpf_release(struct work_struct *work) list_for_each_entry_safe(pl, tmp, progs, node) { list_del(&pl->node); - bpf_prog_put(pl->prog); - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_unlink(pl->storage[stype]); - bpf_cgroup_storage_free(pl->storage[stype]); - } + if (pl->prog) + bpf_prog_put(pl->prog); + if (pl->link) + bpf_cgroup_link_auto_detach(pl->link); + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_free(pl->storage); kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } @@ -85,6 +148,18 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref) queue_work(system_wq, &cgrp->bpf.release_work); } +/* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through + * link or direct prog. + */ +static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) +{ + if (pl->prog) + return pl->prog; + if (pl->link) + return pl->link->link.prog; + return NULL; +} + /* count number of elements in the list. * it's slow but the list cannot be long */ @@ -94,7 +169,7 @@ static u32 prog_list_length(struct list_head *head) u32 cnt = 0; list_for_each_entry(pl, head, node) { - if (!pl->prog) + if (!prog_list_prog(pl)) continue; cnt++; } @@ -138,7 +213,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array **array) { - enum bpf_cgroup_storage_type stype; + struct bpf_prog_array_item *item; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; @@ -163,13 +238,13 @@ static int compute_effective_progs(struct cgroup *cgrp, continue; list_for_each_entry(pl, &p->bpf.progs[type], node) { - if (!pl->prog) + if (!prog_list_prog(pl)) continue; - progs->items[cnt].prog = pl->prog; - for_each_cgroup_storage_type(stype) - progs->items[cnt].cgroup_storage[stype] = - pl->storage[stype]; + item = &progs->items[cnt]; + item->prog = prog_list_prog(pl); + bpf_cgroup_storages_assign(item->cgroup_storage, + pl->storage); cnt++; } } while ((p = cgroup_parent(p))); @@ -287,19 +362,60 @@ cleanup: #define BPF_CGROUP_MAX_PROGS 64 +static struct bpf_prog_list *find_attach_entry(struct list_head *progs, + struct bpf_prog *prog, + struct bpf_cgroup_link *link, + struct bpf_prog *replace_prog, + bool allow_multi) +{ + struct bpf_prog_list *pl; + + /* single-attach case */ + if (!allow_multi) { + if (list_empty(progs)) + return NULL; + return list_first_entry(progs, typeof(*pl), node); + } + + list_for_each_entry(pl, progs, node) { + if (prog && pl->prog == prog) + /* disallow attaching the same prog twice */ + return ERR_PTR(-EINVAL); + if (link && pl->link == link) + /* disallow attaching the same link twice */ + return ERR_PTR(-EINVAL); + } + + /* direct prog multi-attach w/ replacement case */ + if (replace_prog) { + list_for_each_entry(pl, progs, node) { + if (pl->prog == replace_prog) + /* a match found */ + return pl; + } + /* prog to replace not found for cgroup */ + return ERR_PTR(-ENOENT); + } + + return NULL; +} + /** - * __cgroup_bpf_attach() - Attach the program to a cgroup, and + * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach + * @link: A link to attach * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * + * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, +int __cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); @@ -307,14 +423,19 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; - struct bpf_prog_list *pl, *replace_pl = NULL; - enum bpf_cgroup_storage_type stype; + struct bpf_prog_list *pl; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; + if (link && (prog || replace_prog)) + /* only either link or prog/replace_prog can be specified */ + return -EINVAL; + if (!!replace_prog != !!(flags & BPF_F_REPLACE)) + /* replace_prog implies BPF_F_REPLACE, and vice versa */ + return -EINVAL; if (!hierarchy_allows_attach(cgrp, type)) return -EPERM; @@ -329,140 +450,203 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; - if (flags & BPF_F_ALLOW_MULTI) { - list_for_each_entry(pl, progs, node) { - if (pl->prog == prog) - /* disallow attaching the same prog twice */ - return -EINVAL; - if (pl->prog == replace_prog) - replace_pl = pl; - } - if ((flags & BPF_F_REPLACE) && !replace_pl) - /* prog to replace not found for cgroup */ - return -ENOENT; - } else if (!list_empty(progs)) { - replace_pl = list_first_entry(progs, typeof(*pl), node); - } + pl = find_attach_entry(progs, prog, link, replace_prog, + flags & BPF_F_ALLOW_MULTI); + if (IS_ERR(pl)) + return PTR_ERR(pl); - for_each_cgroup_storage_type(stype) { - storage[stype] = bpf_cgroup_storage_alloc(prog, stype); - if (IS_ERR(storage[stype])) { - storage[stype] = NULL; - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); - return -ENOMEM; - } - } + if (bpf_cgroup_storages_alloc(storage, prog ? : link->link.prog)) + return -ENOMEM; - if (replace_pl) { - pl = replace_pl; + if (pl) { old_prog = pl->prog; - for_each_cgroup_storage_type(stype) { - old_storage[stype] = pl->storage[stype]; - bpf_cgroup_storage_unlink(old_storage[stype]); - } + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_assign(old_storage, pl->storage); } else { pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_free(storage[stype]); + bpf_cgroup_storages_free(storage); return -ENOMEM; } list_add_tail(&pl->node, progs); } pl->prog = prog; - for_each_cgroup_storage_type(stype) - pl->storage[stype] = storage[stype]; - + pl->link = link; + bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[type] = saved_flags; err = update_effective_progs(cgrp, type); if (err) goto cleanup; - static_branch_inc(&cgroup_bpf_enabled_key); - for_each_cgroup_storage_type(stype) { - if (!old_storage[stype]) - continue; - bpf_cgroup_storage_free(old_storage[stype]); - } - if (old_prog) { + bpf_cgroup_storages_free(old_storage); + if (old_prog) bpf_prog_put(old_prog); - static_branch_dec(&cgroup_bpf_enabled_key); - } - for_each_cgroup_storage_type(stype) - bpf_cgroup_storage_link(storage[stype], cgrp, type); + else + static_branch_inc(&cgroup_bpf_enabled_key); + bpf_cgroup_storages_link(pl->storage, cgrp, type); return 0; cleanup: - /* and cleanup the prog list */ - pl->prog = old_prog; - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_free(pl->storage[stype]); - pl->storage[stype] = old_storage[stype]; - bpf_cgroup_storage_link(old_storage[stype], cgrp, type); + if (old_prog) { + pl->prog = old_prog; + pl->link = NULL; } - if (!replace_pl) { + bpf_cgroup_storages_free(pl->storage); + bpf_cgroup_storages_assign(pl->storage, old_storage); + bpf_cgroup_storages_link(pl->storage, cgrp, type); + if (!old_prog) { list_del(&pl->node); kfree(pl); } return err; } +/* Swap updated BPF program for given link in effective program arrays across + * all descendant cgroups. This function is guaranteed to succeed. + */ +static void replace_effective_prog(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_cgroup_link *link) +{ + struct bpf_prog_array_item *item; + struct cgroup_subsys_state *css; + struct bpf_prog_array *progs; + struct bpf_prog_list *pl; + struct list_head *head; + struct cgroup *cg; + int pos; + + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + if (percpu_ref_is_zero(&desc->bpf.refcnt)) + continue; + + /* find position of link in effective progs array */ + for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { + if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + continue; + + head = &cg->bpf.progs[type]; + list_for_each_entry(pl, head, node) { + if (!prog_list_prog(pl)) + continue; + if (pl->link == link) + goto found; + pos++; + } + } +found: + BUG_ON(!cg); + progs = rcu_dereference_protected( + desc->bpf.effective[type], + lockdep_is_held(&cgroup_mutex)); + item = &progs->items[pos]; + WRITE_ONCE(item->prog, link->link.prog); + } +} + /** - * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * __cgroup_bpf_replace() - Replace link's program and propagate the change + * to descendants + * @cgrp: The cgroup which descendants to traverse + * @link: A link for which to replace BPF program + * @type: Type of attach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, + struct bpf_prog *new_prog) +{ + struct list_head *progs = &cgrp->bpf.progs[link->type]; + struct bpf_prog *old_prog; + struct bpf_prog_list *pl; + bool found = false; + + if (link->link.prog->type != new_prog->type) + return -EINVAL; + + list_for_each_entry(pl, progs, node) { + if (pl->link == link) { + found = true; + break; + } + } + if (!found) + return -ENOENT; + + old_prog = xchg(&link->link.prog, new_prog); + replace_effective_prog(cgrp, link->type, link); + bpf_prog_put(old_prog); + return 0; +} + +static struct bpf_prog_list *find_detach_entry(struct list_head *progs, + struct bpf_prog *prog, + struct bpf_cgroup_link *link, + bool allow_multi) +{ + struct bpf_prog_list *pl; + + if (!allow_multi) { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return ERR_PTR(-ENOENT); + + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) in legacy mode + */ + return list_first_entry(progs, typeof(*pl), node); + } + + if (!prog && !link) + /* to detach MULTI prog the user has to specify valid FD + * of the program or link to be detached + */ + return ERR_PTR(-EINVAL); + + /* find the prog or link and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog == prog && pl->link == link) + return pl; + } + return ERR_PTR(-ENOENT); +} + +/** + * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL + * @prog: A link to detach or NULL * @type: Type of detach operation * + * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type) + struct bpf_cgroup_link *link, enum bpf_attach_type type) { struct list_head *progs = &cgrp->bpf.progs[type]; - enum bpf_cgroup_storage_type stype; u32 flags = cgrp->bpf.flags[type]; - struct bpf_prog *old_prog = NULL; struct bpf_prog_list *pl; + struct bpf_prog *old_prog; 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 (prog && link) + /* only one of prog or link can be specified */ + return -EINVAL; - 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; - } + pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI); + if (IS_ERR(pl)) + return PTR_ERR(pl); + + /* mark it deleted, so it's ignored while recomputing effective */ + old_prog = pl->prog; + pl->prog = NULL; + pl->link = NULL; err = update_effective_progs(cgrp, type); if (err) @@ -470,22 +654,21 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, /* now can actually delete it from this cgroup list */ list_del(&pl->node); - for_each_cgroup_storage_type(stype) { - bpf_cgroup_storage_unlink(pl->storage[stype]); - bpf_cgroup_storage_free(pl->storage[stype]); - } + bpf_cgroup_storages_unlink(pl->storage); + bpf_cgroup_storages_free(pl->storage); kfree(pl); if (list_empty(progs)) /* last program was detached, reset flags to zero */ cgrp->bpf.flags[type] = 0; - - bpf_prog_put(old_prog); + if (old_prog) + bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); return 0; cleanup: - /* and restore back old_prog */ + /* restore back prog or link */ pl->prog = old_prog; + pl->link = link; return err; } @@ -498,6 +681,7 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, struct list_head *progs = &cgrp->bpf.progs[type]; u32 flags = cgrp->bpf.flags[type]; struct bpf_prog_array *effective; + struct bpf_prog *prog; int cnt, ret = 0, i; effective = rcu_dereference_protected(cgrp->bpf.effective[type], @@ -528,7 +712,8 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, i = 0; list_for_each_entry(pl, progs, node) { - id = pl->prog->aux->id; + prog = prog_list_prog(pl); + id = prog->aux->id; if (copy_to_user(prog_ids + i, &id, sizeof(id))) return -EFAULT; if (++i == cnt) @@ -558,8 +743,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr, } } - ret = cgroup_bpf_attach(cgrp, prog, replace_prog, attr->attach_type, - attr->attach_flags); + ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL, + attr->attach_type, attr->attach_flags); if (replace_prog) bpf_prog_put(replace_prog); @@ -581,7 +766,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) if (IS_ERR(prog)) prog = NULL; - ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type); if (prog) bpf_prog_put(prog); @@ -589,6 +774,90 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) return ret; } +static void bpf_cgroup_link_release(struct bpf_link *link) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + + /* link might have been auto-detached by dying cgroup already, + * in that case our work is done here + */ + if (!cg_link->cgroup) + return; + + mutex_lock(&cgroup_mutex); + + /* re-check cgroup under lock again */ + if (!cg_link->cgroup) { + mutex_unlock(&cgroup_mutex); + return; + } + + WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, + cg_link->type)); + + mutex_unlock(&cgroup_mutex); + cgroup_put(cg_link->cgroup); +} + +static void bpf_cgroup_link_dealloc(struct bpf_link *link) +{ + struct bpf_cgroup_link *cg_link = + container_of(link, struct bpf_cgroup_link, link); + + kfree(cg_link); +} + +const struct bpf_link_ops bpf_cgroup_link_lops = { + .release = bpf_cgroup_link_release, + .dealloc = bpf_cgroup_link_dealloc, +}; + +int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_cgroup_link *link; + struct file *link_file; + struct cgroup *cgrp; + int err, link_fd; + + if (attr->link_create.flags) + return -EINVAL; + + cgrp = cgroup_get_from_fd(attr->link_create.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_cgroup; + } + bpf_link_init(&link->link, &bpf_cgroup_link_lops, prog); + link->cgroup = cgrp; + link->type = attr->link_create.attach_type; + + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); + goto out_put_cgroup; + } + + err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, + BPF_F_ALLOW_MULTI); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); + goto out_put_cgroup; + } + + fd_install(link_fd, link_file); + return link_fd; + +out_put_cgroup: + cgroup_put(cgrp); + return err; +} + int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 973a20d49749..916f5132a984 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -97,7 +97,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag fp->aux->prog = fp; fp->jit_requested = ebpf_jit_enabled(); - INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode); + INIT_LIST_HEAD_RCU(&fp->aux->ksym.lnode); return fp; } @@ -523,22 +523,22 @@ int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); int bpf_jit_harden __read_mostly; long bpf_jit_limit __read_mostly; -static __always_inline void -bpf_get_prog_addr_region(const struct bpf_prog *prog, - unsigned long *symbol_start, - unsigned long *symbol_end) +static void +bpf_prog_ksym_set_addr(struct bpf_prog *prog) { const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(prog); unsigned long addr = (unsigned long)hdr; WARN_ON_ONCE(!bpf_prog_ebpf_jited(prog)); - *symbol_start = addr; - *symbol_end = addr + hdr->pages * PAGE_SIZE; + prog->aux->ksym.start = (unsigned long) prog->bpf_func; + prog->aux->ksym.end = addr + hdr->pages * PAGE_SIZE; } -void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) +static void +bpf_prog_ksym_set_name(struct bpf_prog *prog) { + char *sym = prog->aux->ksym.name; const char *end = sym + KSYM_NAME_LEN; const struct btf_type *type; const char *func_name; @@ -572,36 +572,27 @@ void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) *sym = 0; } -static __always_inline unsigned long -bpf_get_prog_addr_start(struct latch_tree_node *n) +static unsigned long bpf_get_ksym_start(struct latch_tree_node *n) { - unsigned long symbol_start, symbol_end; - const struct bpf_prog_aux *aux; - - aux = container_of(n, struct bpf_prog_aux, ksym_tnode); - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); - - return symbol_start; + return container_of(n, struct bpf_ksym, tnode)->start; } static __always_inline bool bpf_tree_less(struct latch_tree_node *a, struct latch_tree_node *b) { - return bpf_get_prog_addr_start(a) < bpf_get_prog_addr_start(b); + return bpf_get_ksym_start(a) < bpf_get_ksym_start(b); } static __always_inline int bpf_tree_comp(void *key, struct latch_tree_node *n) { unsigned long val = (unsigned long)key; - unsigned long symbol_start, symbol_end; - const struct bpf_prog_aux *aux; + const struct bpf_ksym *ksym; - aux = container_of(n, struct bpf_prog_aux, ksym_tnode); - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); + ksym = container_of(n, struct bpf_ksym, tnode); - if (val < symbol_start) + if (val < ksym->start) return -1; - if (val >= symbol_end) + if (val >= ksym->end) return 1; return 0; @@ -616,20 +607,29 @@ static DEFINE_SPINLOCK(bpf_lock); static LIST_HEAD(bpf_kallsyms); static struct latch_tree_root bpf_tree __cacheline_aligned; -static void bpf_prog_ksym_node_add(struct bpf_prog_aux *aux) +void bpf_ksym_add(struct bpf_ksym *ksym) { - WARN_ON_ONCE(!list_empty(&aux->ksym_lnode)); - list_add_tail_rcu(&aux->ksym_lnode, &bpf_kallsyms); - latch_tree_insert(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops); + spin_lock_bh(&bpf_lock); + WARN_ON_ONCE(!list_empty(&ksym->lnode)); + list_add_tail_rcu(&ksym->lnode, &bpf_kallsyms); + latch_tree_insert(&ksym->tnode, &bpf_tree, &bpf_tree_ops); + spin_unlock_bh(&bpf_lock); } -static void bpf_prog_ksym_node_del(struct bpf_prog_aux *aux) +static void __bpf_ksym_del(struct bpf_ksym *ksym) { - if (list_empty(&aux->ksym_lnode)) + if (list_empty(&ksym->lnode)) return; - latch_tree_erase(&aux->ksym_tnode, &bpf_tree, &bpf_tree_ops); - list_del_rcu(&aux->ksym_lnode); + latch_tree_erase(&ksym->tnode, &bpf_tree, &bpf_tree_ops); + list_del_rcu(&ksym->lnode); +} + +void bpf_ksym_del(struct bpf_ksym *ksym) +{ + spin_lock_bh(&bpf_lock); + __bpf_ksym_del(ksym); + spin_unlock_bh(&bpf_lock); } static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) @@ -639,8 +639,8 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { - return list_empty(&fp->aux->ksym_lnode) || - fp->aux->ksym_lnode.prev == LIST_POISON2; + return list_empty(&fp->aux->ksym.lnode) || + fp->aux->ksym.lnode.prev == LIST_POISON2; } void bpf_prog_kallsyms_add(struct bpf_prog *fp) @@ -649,9 +649,11 @@ void bpf_prog_kallsyms_add(struct bpf_prog *fp) !capable(CAP_SYS_ADMIN)) return; - spin_lock_bh(&bpf_lock); - bpf_prog_ksym_node_add(fp->aux); - spin_unlock_bh(&bpf_lock); + bpf_prog_ksym_set_addr(fp); + bpf_prog_ksym_set_name(fp); + fp->aux->ksym.prog = true; + + bpf_ksym_add(&fp->aux->ksym); } void bpf_prog_kallsyms_del(struct bpf_prog *fp) @@ -659,33 +661,30 @@ void bpf_prog_kallsyms_del(struct bpf_prog *fp) if (!bpf_prog_kallsyms_candidate(fp)) return; - spin_lock_bh(&bpf_lock); - bpf_prog_ksym_node_del(fp->aux); - spin_unlock_bh(&bpf_lock); + bpf_ksym_del(&fp->aux->ksym); } -static struct bpf_prog *bpf_prog_kallsyms_find(unsigned long addr) +static struct bpf_ksym *bpf_ksym_find(unsigned long addr) { struct latch_tree_node *n; n = latch_tree_find((void *)addr, &bpf_tree, &bpf_tree_ops); - return n ? - container_of(n, struct bpf_prog_aux, ksym_tnode)->prog : - NULL; + return n ? container_of(n, struct bpf_ksym, tnode) : NULL; } const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { - unsigned long symbol_start, symbol_end; - struct bpf_prog *prog; + struct bpf_ksym *ksym; char *ret = NULL; rcu_read_lock(); - prog = bpf_prog_kallsyms_find(addr); - if (prog) { - bpf_get_prog_addr_region(prog, &symbol_start, &symbol_end); - bpf_get_prog_name(prog, sym); + ksym = bpf_ksym_find(addr); + if (ksym) { + unsigned long symbol_start = ksym->start; + unsigned long symbol_end = ksym->end; + + strncpy(sym, ksym->name, KSYM_NAME_LEN); ret = sym; if (size) @@ -703,19 +702,28 @@ bool is_bpf_text_address(unsigned long addr) bool ret; rcu_read_lock(); - ret = bpf_prog_kallsyms_find(addr) != NULL; + ret = bpf_ksym_find(addr) != NULL; rcu_read_unlock(); return ret; } +static struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +{ + struct bpf_ksym *ksym = bpf_ksym_find(addr); + + return ksym && ksym->prog ? + container_of(ksym, struct bpf_prog_aux, ksym)->prog : + NULL; +} + const struct exception_table_entry *search_bpf_extables(unsigned long addr) { const struct exception_table_entry *e = NULL; struct bpf_prog *prog; rcu_read_lock(); - prog = bpf_prog_kallsyms_find(addr); + prog = bpf_prog_ksym_find(addr); if (!prog) goto out; if (!prog->aux->num_exentries) @@ -730,7 +738,7 @@ out: int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - struct bpf_prog_aux *aux; + struct bpf_ksym *ksym; unsigned int it = 0; int ret = -ERANGE; @@ -738,13 +746,13 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, return ret; rcu_read_lock(); - list_for_each_entry_rcu(aux, &bpf_kallsyms, ksym_lnode) { + list_for_each_entry_rcu(ksym, &bpf_kallsyms, lnode) { if (it++ != symnum) continue; - bpf_get_prog_name(aux->prog, sym); + strncpy(sym, ksym->name, KSYM_NAME_LEN); - *value = (unsigned long)aux->prog->bpf_func; + *value = ksym->start; *type = BPF_SYM_ELF_TYPE; ret = 0; @@ -2148,7 +2156,9 @@ const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; const struct bpf_func_proto bpf_get_current_comm_proto __weak; const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak; +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak; const struct bpf_func_proto bpf_get_local_storage_proto __weak; +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak; const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) { diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c index b3e5b214fed8..2444bd15cc2d 100644 --- a/kernel/bpf/dispatcher.c +++ b/kernel/bpf/dispatcher.c @@ -113,7 +113,7 @@ static void bpf_dispatcher_update(struct bpf_dispatcher *d, int prev_num_progs) noff = 0; } else { old = d->image + d->image_off; - noff = d->image_off ^ (BPF_IMAGE_SIZE / 2); + noff = d->image_off ^ (PAGE_SIZE / 2); } new = d->num_progs ? d->image + noff : NULL; @@ -140,9 +140,10 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, mutex_lock(&d->mutex); if (!d->image) { - d->image = bpf_image_alloc(); + d->image = bpf_jit_alloc_exec_page(); if (!d->image) goto out; + bpf_image_ksym_add(d->image, &d->ksym); } prev_num_progs = d->num_progs; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a1468e3f5af2..d541c8486c95 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -27,9 +27,62 @@ .map_delete_batch = \ generic_map_delete_batch +/* + * The bucket lock has two protection scopes: + * + * 1) Serializing concurrent operations from BPF programs on differrent + * CPUs + * + * 2) Serializing concurrent operations from BPF programs and sys_bpf() + * + * BPF programs can execute in any context including perf, kprobes and + * tracing. As there are almost no limits where perf, kprobes and tracing + * can be invoked from the lock operations need to be protected against + * deadlocks. Deadlocks can be caused by recursion and by an invocation in + * the lock held section when functions which acquire this lock are invoked + * from sys_bpf(). BPF recursion is prevented by incrementing the per CPU + * variable bpf_prog_active, which prevents BPF programs attached to perf + * events, kprobes and tracing to be invoked before the prior invocation + * from one of these contexts completed. sys_bpf() uses the same mechanism + * by pinning the task to the current CPU and incrementing the recursion + * protection accross the map operation. + * + * This has subtle implications on PREEMPT_RT. PREEMPT_RT forbids certain + * operations like memory allocations (even with GFP_ATOMIC) from atomic + * contexts. This is required because even with GFP_ATOMIC the memory + * allocator calls into code pathes which acquire locks with long held lock + * sections. To ensure the deterministic behaviour these locks are regular + * spinlocks, which are converted to 'sleepable' spinlocks on RT. The only + * true atomic contexts on an RT kernel are the low level hardware + * handling, scheduling, low level interrupt handling, NMIs etc. None of + * these contexts should ever do memory allocations. + * + * As regular device interrupt handlers and soft interrupts are forced into + * thread context, the existing code which does + * spin_lock*(); alloc(GPF_ATOMIC); spin_unlock*(); + * just works. + * + * In theory the BPF locks could be converted to regular spinlocks as well, + * but the bucket locks and percpu_freelist locks can be taken from + * arbitrary contexts (perf, kprobes, tracepoints) which are required to be + * atomic contexts even on RT. These mechanisms require preallocated maps, + * so there is no need to invoke memory allocations within the lock held + * sections. + * + * BPF maps which need dynamic allocation are only used from (forced) + * thread context on RT and can therefore use regular spinlocks which in + * turn allows to invoke memory allocations from the lock held section. + * + * On a non RT kernel this distinction is neither possible nor required. + * spinlock maps to raw_spinlock and the extra code is optimized out by the + * compiler. + */ struct bucket { struct hlist_nulls_head head; - raw_spinlock_t lock; + union { + raw_spinlock_t raw_lock; + spinlock_t lock; + }; }; struct bpf_htab { @@ -65,9 +118,54 @@ struct htab_elem { struct bpf_lru_node lru_node; }; u32 hash; - char key[0] __aligned(8); + char key[] __aligned(8); }; +static inline bool htab_is_prealloc(const struct bpf_htab *htab) +{ + return !(htab->map.map_flags & BPF_F_NO_PREALLOC); +} + +static inline bool htab_use_raw_lock(const struct bpf_htab *htab) +{ + return (!IS_ENABLED(CONFIG_PREEMPT_RT) || htab_is_prealloc(htab)); +} + +static void htab_init_buckets(struct bpf_htab *htab) +{ + unsigned i; + + for (i = 0; i < htab->n_buckets; i++) { + INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); + if (htab_use_raw_lock(htab)) + raw_spin_lock_init(&htab->buckets[i].raw_lock); + else + spin_lock_init(&htab->buckets[i].lock); + } +} + +static inline unsigned long htab_lock_bucket(const struct bpf_htab *htab, + struct bucket *b) +{ + unsigned long flags; + + if (htab_use_raw_lock(htab)) + raw_spin_lock_irqsave(&b->raw_lock, flags); + else + spin_lock_irqsave(&b->lock, flags); + return flags; +} + +static inline void htab_unlock_bucket(const struct bpf_htab *htab, + struct bucket *b, + unsigned long flags) +{ + if (htab_use_raw_lock(htab)) + raw_spin_unlock_irqrestore(&b->raw_lock, flags); + else + spin_unlock_irqrestore(&b->lock, flags); +} + static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); static bool htab_is_lru(const struct bpf_htab *htab) @@ -82,11 +180,6 @@ static bool htab_is_percpu(const struct bpf_htab *htab) htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } -static bool htab_is_prealloc(const struct bpf_htab *htab) -{ - return !(htab->map.map_flags & BPF_F_NO_PREALLOC); -} - static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { @@ -328,8 +421,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; - int err, i; u64 cost; + int err; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) @@ -391,10 +484,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->hashrnd = get_random_int(); - for (i = 0; i < htab->n_buckets; i++) { - INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); - raw_spin_lock_init(&htab->buckets[i].lock); - } + htab_init_buckets(htab); if (prealloc) { err = prealloc_init(htab); @@ -602,7 +692,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) b = __select_bucket(htab, tgt_l->hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { @@ -610,7 +700,7 @@ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) break; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return l == tgt_l; } @@ -686,15 +776,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; - /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); } static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) @@ -884,8 +966,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, */ } - /* bpf_map_update_elem() can be called in_irq() */ - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -926,7 +1007,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -964,8 +1045,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, return -ENOMEM; memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); - /* bpf_map_update_elem() can be called in_irq() */ - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -984,7 +1064,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (ret) bpf_lru_push_free(&htab->lru, &l_new->lru_node); @@ -1019,8 +1099,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, b = __select_bucket(htab, hash); head = &b->head; - /* bpf_map_update_elem() can be called in_irq() */ - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1043,7 +1122,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -1083,8 +1162,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, return -ENOMEM; } - /* bpf_map_update_elem() can be called in_irq() */ - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l_old = lookup_elem_raw(head, hash, key, key_size); @@ -1106,7 +1184,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, } ret = 0; err: - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; @@ -1144,7 +1222,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l = lookup_elem_raw(head, hash, key, key_size); @@ -1154,7 +1232,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) ret = 0; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); return ret; } @@ -1176,7 +1254,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) b = __select_bucket(htab, hash); head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); l = lookup_elem_raw(head, hash, key, key_size); @@ -1185,7 +1263,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) ret = 0; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); if (l) bpf_lru_push_free(&htab->lru, &l->lru_node); return ret; @@ -1325,8 +1403,7 @@ alloc: } again: - preempt_disable(); - this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); again_nocopy: dst_key = keys; @@ -1335,7 +1412,7 @@ again_nocopy: head = &b->head; /* do not grab the lock unless need it (bucket_cnt > 0). */ if (locked) - raw_spin_lock_irqsave(&b->lock, flags); + flags = htab_lock_bucket(htab, b); bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) @@ -1352,10 +1429,9 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); goto after_loop; } @@ -1364,10 +1440,9 @@ again_nocopy: /* Note that since bucket_cnt > 0 here, it is implicit * that the locked was grabbed, so release it. */ - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); kvfree(keys); kvfree(values); goto alloc; @@ -1418,7 +1493,7 @@ again_nocopy: dst_val += value_size; } - raw_spin_unlock_irqrestore(&b->lock, flags); + htab_unlock_bucket(htab, b, flags); locked = false; while (node_to_free) { @@ -1437,8 +1512,7 @@ next_batch: } rcu_read_unlock(); - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); if (bucket_cnt && (copy_to_user(ukeys + total * key_size, keys, key_size * bucket_cnt) || copy_to_user(uvalues + total * value_size, values, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index d8b7b110a1c5..bafc53ddd350 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -12,6 +12,8 @@ #include <linux/filter.h> #include <linux/ctype.h> #include <linux/jiffies.h> +#include <linux/pid_namespace.h> +#include <linux/proc_ns.h> #include "../../lib/kstrtox.h" @@ -338,6 +340,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_1(bpf_get_current_ancestor_cgroup_id, int, ancestor_level) +{ + struct cgroup *cgrp = task_dfl_cgroup(current); + struct cgroup *ancestor; + + ancestor = cgroup_ancestor(cgrp, ancestor_level); + if (!ancestor) + return 0; + return cgroup_id(ancestor); +} + +const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto = { + .func = bpf_get_current_ancestor_cgroup_id, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + #ifdef CONFIG_CGROUP_BPF DECLARE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]); @@ -499,3 +519,46 @@ const struct bpf_func_proto bpf_strtoul_proto = { .arg4_type = ARG_PTR_TO_LONG, }; #endif + +BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, + struct bpf_pidns_info *, nsdata, u32, size) +{ + struct task_struct *task = current; + struct pid_namespace *pidns; + int err = -EINVAL; + + if (unlikely(size != sizeof(struct bpf_pidns_info))) + goto clear; + + if (unlikely((u64)(dev_t)dev != dev)) + goto clear; + + if (unlikely(!task)) + goto clear; + + pidns = task_active_pid_ns(task); + if (unlikely(!pidns)) { + err = -ENOENT; + goto clear; + } + + if (!ns_match(&pidns->ns, (dev_t)dev, ino)) + goto clear; + + nsdata->pid = task_pid_nr_ns(task, pidns); + nsdata->tgid = task_tgid_nr_ns(task, pidns); + return 0; +clear: + memset((void *)nsdata, 0, (size_t) size); + return err; +} + +const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto = { + .func = bpf_get_ns_current_pid_tgid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 5e40e7fccc21..95087d9f4ed3 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -25,6 +25,7 @@ enum bpf_type { BPF_TYPE_UNSPEC = 0, BPF_TYPE_PROG, BPF_TYPE_MAP, + BPF_TYPE_LINK, }; static void *bpf_any_get(void *raw, enum bpf_type type) @@ -36,6 +37,9 @@ static void *bpf_any_get(void *raw, enum bpf_type type) case BPF_TYPE_MAP: bpf_map_inc_with_uref(raw); break; + case BPF_TYPE_LINK: + bpf_link_inc(raw); + break; default: WARN_ON_ONCE(1); break; @@ -53,6 +57,9 @@ static void bpf_any_put(void *raw, enum bpf_type type) case BPF_TYPE_MAP: bpf_map_put_with_uref(raw); break; + case BPF_TYPE_LINK: + bpf_link_put(raw); + break; default: WARN_ON_ONCE(1); break; @@ -63,20 +70,32 @@ static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) { void *raw; - *type = BPF_TYPE_MAP; raw = bpf_map_get_with_uref(ufd); - if (IS_ERR(raw)) { + if (!IS_ERR(raw)) { + *type = BPF_TYPE_MAP; + return raw; + } + + raw = bpf_prog_get(ufd); + if (!IS_ERR(raw)) { *type = BPF_TYPE_PROG; - raw = bpf_prog_get(ufd); + return raw; } - return raw; + raw = bpf_link_get_from_fd(ufd); + if (!IS_ERR(raw)) { + *type = BPF_TYPE_LINK; + return raw; + } + + return ERR_PTR(-EINVAL); } static const struct inode_operations bpf_dir_iops; static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; +static const struct inode_operations bpf_link_iops = { }; static struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, @@ -114,6 +133,8 @@ static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) *type = BPF_TYPE_PROG; else if (inode->i_op == &bpf_map_iops) *type = BPF_TYPE_MAP; + else if (inode->i_op == &bpf_link_iops) + *type = BPF_TYPE_LINK; else return -EACCES; @@ -335,6 +356,12 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) &bpffs_map_fops : &bpffs_obj_fops); } +static int bpf_mklink(struct dentry *dentry, umode_t mode, void *arg) +{ + return bpf_mkobj_ops(dentry, mode, arg, &bpf_link_iops, + &bpffs_obj_fops); +} + static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { @@ -411,6 +438,9 @@ static int bpf_obj_do_pin(const char __user *pathname, void *raw, case BPF_TYPE_MAP: ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw); break; + case BPF_TYPE_LINK: + ret = vfs_mkobj(dentry, mode, bpf_mklink, raw); + break; default: ret = -EPERM; } @@ -487,6 +517,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); + else if (type == BPF_TYPE_LINK) + ret = bpf_link_new_fd(raw); else return -ENOENT; @@ -504,6 +536,8 @@ static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type if (inode->i_op == &bpf_map_iops) return ERR_PTR(-EINVAL); + if (inode->i_op == &bpf_link_iops) + return ERR_PTR(-EINVAL); if (inode->i_op != &bpf_prog_iops) return ERR_PTR(-EACCES); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 56e6c75d354d..65c236cf341e 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -25,7 +25,7 @@ struct lpm_trie_node { struct lpm_trie_node __rcu *child[2]; u32 prefixlen; u32 flags; - u8 data[0]; + u8 data[]; }; struct lpm_trie { @@ -34,7 +34,7 @@ struct lpm_trie { size_t n_entries; size_t max_prefixlen; size_t data_size; - raw_spinlock_t lock; + spinlock_t lock; }; /* This trie implements a longest prefix match algorithm that can be used to @@ -315,7 +315,7 @@ static int trie_update_elem(struct bpf_map *map, if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - raw_spin_lock_irqsave(&trie->lock, irq_flags); + spin_lock_irqsave(&trie->lock, irq_flags); /* Allocate and fill a new node */ @@ -422,7 +422,7 @@ out: kfree(im_node); } - raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } @@ -442,7 +442,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) if (key->prefixlen > trie->max_prefixlen) return -EINVAL; - raw_spin_lock_irqsave(&trie->lock, irq_flags); + 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 @@ -518,7 +518,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) kfree_rcu(node, rcu); out: - raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + spin_unlock_irqrestore(&trie->lock, irq_flags); return ret; } @@ -575,7 +575,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) if (ret) goto out_err; - raw_spin_lock_init(&trie->lock); + spin_lock_init(&trie->lock); return &trie->map; out_err: diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 6e090140b924..b367430e611c 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -25,12 +25,18 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } +static inline void pcpu_freelist_push_node(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) +{ + node->next = head->first; + head->first = node; +} + static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); - node->next = head->first; - head->first = node; + pcpu_freelist_push_node(head, node); raw_spin_unlock(&head->lock); } @@ -56,21 +62,16 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems) { struct pcpu_freelist_head *head; - unsigned long flags; int i, cpu, pcpu_entries; pcpu_entries = nr_elems / num_possible_cpus() + 1; i = 0; - /* disable irq to workaround lockdep false positive - * in bpf usage pcpu_freelist_populate() will never race - * with pcpu_freelist_push() - */ - local_irq_save(flags); for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - ___pcpu_freelist_push(head, buf); + /* No locking required as this is not visible yet. */ + pcpu_freelist_push_node(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -78,7 +79,6 @@ again: if (i % pcpu_entries) goto again; } - local_irq_restore(flags); } struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 50c083ba978c..01badd3eda7a 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -305,11 +305,6 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, if (err) goto put_file_unlock; - /* Ensure reuse->reuseport_id is set */ - err = reuseport_get_id(reuse); - if (err < 0) - goto put_file_unlock; - WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 3f958b90d914..db76339fe358 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -40,6 +40,9 @@ static void do_up_read(struct irq_work *entry) { struct stack_map_irq_work *work; + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + work = container_of(entry, struct stack_map_irq_work, irq_work); up_read_non_owner(work->sem); work->sem = NULL; @@ -288,10 +291,19 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, struct stack_map_irq_work *work = NULL; if (irqs_disabled()) { - work = this_cpu_ptr(&up_read_work); - if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) - /* cannot queue more up_read, fallback */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&up_read_work); + if (atomic_read(&work->irq_work.flags) & IRQ_WORK_BUSY) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ irq_work_busy = true; + } } /* diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 966b7b34cde0..64783da34202 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,6 +25,7 @@ #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> +#include <linux/bpf_lsm.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -171,11 +172,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, flags); } - /* must increment bpf_prog_active to avoid kprobe+bpf triggering from - * inside bpf map update or delete otherwise deadlocks are possible - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); @@ -206,8 +203,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); } - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -222,8 +218,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, if (bpf_map_is_dev_bound(map)) return bpf_map_offload_lookup_elem(map, key, value); - preempt_disable(); - this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); @@ -268,8 +263,7 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, rcu_read_unlock(); } - this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); return err; @@ -911,6 +905,21 @@ void bpf_map_inc_with_uref(struct bpf_map *map) } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); +struct bpf_map *bpf_map_get(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_map *map; + + map = __bpf_map_get(f); + if (IS_ERR(map)) + return map; + + bpf_map_inc(map); + fdput(f); + + return map; +} + struct bpf_map *bpf_map_get_with_uref(u32 ufd) { struct fd f = fdget(ufd); @@ -1138,13 +1147,11 @@ static int map_delete_elem(union bpf_attr *attr) goto out; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); out: kfree(key); @@ -1256,13 +1263,11 @@ int generic_map_delete_batch(struct bpf_map *map, break; } - preempt_disable(); - __this_cpu_inc(bpf_prog_active); + bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); + bpf_enable_instrumentation(); maybe_wait_bpf_programs(map); if (err) break; @@ -1938,6 +1943,7 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, switch (prog_type) { case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; @@ -2177,84 +2183,288 @@ static int bpf_obj_get(const union bpf_attr *attr) attr->file_flags); } -static int bpf_tracing_prog_release(struct inode *inode, struct file *filp) +void bpf_link_init(struct bpf_link *link, const struct bpf_link_ops *ops, + struct bpf_prog *prog) { - struct bpf_prog *prog = filp->private_data; + atomic64_set(&link->refcnt, 1); + link->ops = ops; + link->prog = prog; +} - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - bpf_prog_put(prog); +/* Clean up bpf_link and corresponding anon_inode file and FD. After + * anon_inode is created, bpf_link can't be just kfree()'d due to deferred + * anon_inode's release() call. This helper manages marking bpf_link as + * defunct, releases anon_inode file and puts reserved FD. + */ +void bpf_link_cleanup(struct bpf_link *link, struct file *link_file, + int link_fd) +{ + link->prog = NULL; + fput(link_file); + put_unused_fd(link_fd); +} + +void bpf_link_inc(struct bpf_link *link) +{ + atomic64_inc(&link->refcnt); +} + +/* bpf_link_free is guaranteed to be called from process context */ +static void bpf_link_free(struct bpf_link *link) +{ + if (link->prog) { + /* detach BPF program, clean up used resources */ + link->ops->release(link); + bpf_prog_put(link->prog); + } + /* free bpf_link and its containing memory */ + link->ops->dealloc(link); +} + +static void bpf_link_put_deferred(struct work_struct *work) +{ + struct bpf_link *link = container_of(work, struct bpf_link, work); + + bpf_link_free(link); +} + +/* bpf_link_put can be called from atomic context, but ensures that resources + * are freed from process context + */ +void bpf_link_put(struct bpf_link *link) +{ + if (!atomic64_dec_and_test(&link->refcnt)) + return; + + if (in_atomic()) { + INIT_WORK(&link->work, bpf_link_put_deferred); + schedule_work(&link->work); + } else { + bpf_link_free(link); + } +} + +static int bpf_link_release(struct inode *inode, struct file *filp) +{ + struct bpf_link *link = filp->private_data; + + bpf_link_put(link); return 0; } -static const struct file_operations bpf_tracing_prog_fops = { - .release = bpf_tracing_prog_release, +#ifdef CONFIG_PROC_FS +static const struct bpf_link_ops bpf_raw_tp_lops; +static const struct bpf_link_ops bpf_tracing_link_lops; + +static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) +{ + const struct bpf_link *link = filp->private_data; + const struct bpf_prog *prog = link->prog; + char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; + const char *link_type; + + if (link->ops == &bpf_raw_tp_lops) + link_type = "raw_tracepoint"; + else if (link->ops == &bpf_tracing_link_lops) + link_type = "tracing"; +#ifdef CONFIG_CGROUP_BPF + else if (link->ops == &bpf_cgroup_link_lops) + link_type = "cgroup"; +#endif + else + link_type = "unknown"; + + bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); + seq_printf(m, + "link_type:\t%s\n" + "prog_tag:\t%s\n" + "prog_id:\t%u\n", + link_type, + prog_tag, + prog->aux->id); +} +#endif + +const struct file_operations bpf_link_fops = { +#ifdef CONFIG_PROC_FS + .show_fdinfo = bpf_link_show_fdinfo, +#endif + .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; +int bpf_link_new_fd(struct bpf_link *link) +{ + return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC); +} + +/* Similar to bpf_link_new_fd, create anon_inode for given bpf_link, but + * instead of immediately installing fd in fdtable, just reserve it and + * return. Caller then need to either install it with fd_install(fd, file) or + * release with put_unused_fd(fd). + * This is useful for cases when bpf_link attachment/detachment are + * complicated and expensive operations and should be delayed until all the fd + * reservation and anon_inode creation succeeds. + */ +struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd) +{ + struct file *file; + int fd; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) + return ERR_PTR(fd); + + file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC); + if (IS_ERR(file)) { + put_unused_fd(fd); + return file; + } + + *reserved_fd = fd; + return file; +} + +struct bpf_link *bpf_link_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_link *link; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_link_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + link = f.file->private_data; + bpf_link_inc(link); + fdput(f); + + return link; +} + +struct bpf_tracing_link { + struct bpf_link link; +}; + +static void bpf_tracing_link_release(struct bpf_link *link) +{ + WARN_ON_ONCE(bpf_trampoline_unlink_prog(link->prog)); +} + +static void bpf_tracing_link_dealloc(struct bpf_link *link) +{ + struct bpf_tracing_link *tr_link = + container_of(link, struct bpf_tracing_link, link); + + kfree(tr_link); +} + +static const struct bpf_link_ops bpf_tracing_link_lops = { + .release = bpf_tracing_link_release, + .dealloc = bpf_tracing_link_dealloc, +}; + static int bpf_tracing_prog_attach(struct bpf_prog *prog) { - int tr_fd, err; + struct bpf_tracing_link *link; + struct file *link_file; + int link_fd, err; - if (prog->expected_attach_type != BPF_TRACE_FENTRY && - prog->expected_attach_type != BPF_TRACE_FEXIT && - prog->type != BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + if (prog->expected_attach_type != BPF_TRACE_FENTRY && + prog->expected_attach_type != BPF_TRACE_FEXIT && + prog->expected_attach_type != BPF_MODIFY_RETURN) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_EXT: + if (prog->expected_attach_type != 0) { + err = -EINVAL; + goto out_put_prog; + } + break; + case BPF_PROG_TYPE_LSM: + if (prog->expected_attach_type != BPF_LSM_MAC) { + err = -EINVAL; + goto out_put_prog; + } + break; + default: err = -EINVAL; goto out_put_prog; } - err = bpf_trampoline_link_prog(prog); - if (err) + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { + err = -ENOMEM; + goto out_put_prog; + } + bpf_link_init(&link->link, &bpf_tracing_link_lops, prog); + + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); goto out_put_prog; + } - tr_fd = anon_inode_getfd("bpf-tracing-prog", &bpf_tracing_prog_fops, - prog, O_CLOEXEC); - if (tr_fd < 0) { - WARN_ON_ONCE(bpf_trampoline_unlink_prog(prog)); - err = tr_fd; + err = bpf_trampoline_link_prog(prog); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); goto out_put_prog; } - return tr_fd; + + fd_install(link_fd, link_file); + return link_fd; out_put_prog: bpf_prog_put(prog); return err; } -struct bpf_raw_tracepoint { +struct bpf_raw_tp_link { + struct bpf_link link; struct bpf_raw_event_map *btp; - struct bpf_prog *prog; }; -static int bpf_raw_tracepoint_release(struct inode *inode, struct file *filp) +static void bpf_raw_tp_link_release(struct bpf_link *link) { - struct bpf_raw_tracepoint *raw_tp = filp->private_data; + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); - if (raw_tp->prog) { - bpf_probe_unregister(raw_tp->btp, raw_tp->prog); - bpf_prog_put(raw_tp->prog); - } + bpf_probe_unregister(raw_tp->btp, raw_tp->link.prog); bpf_put_raw_tracepoint(raw_tp->btp); +} + +static void bpf_raw_tp_link_dealloc(struct bpf_link *link) +{ + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + kfree(raw_tp); - return 0; } -static const struct file_operations bpf_raw_tp_fops = { - .release = bpf_raw_tracepoint_release, - .read = bpf_dummy_read, - .write = bpf_dummy_write, +static const struct bpf_link_ops bpf_raw_tp_lops = { + .release = bpf_raw_tp_link_release, + .dealloc = bpf_raw_tp_link_dealloc, }; #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.prog_fd static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { - struct bpf_raw_tracepoint *raw_tp; + struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; + struct file *link_file; struct bpf_prog *prog; const char *tp_name; char buf[128]; - int tp_fd, err; + int link_fd, err; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; @@ -2263,16 +2473,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) if (IS_ERR(prog)) return PTR_ERR(prog); - if (prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT && - prog->type != BPF_PROG_TYPE_TRACING && - prog->type != BPF_PROG_TYPE_EXT && - prog->type != BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) { - err = -EINVAL; - goto out_put_prog; - } - - if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { + switch (prog->type) { + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + case BPF_PROG_TYPE_LSM: if (attr->raw_tracepoint.name) { /* The attach point for this category of programs * should be specified via btf_id during program load. @@ -2280,11 +2484,14 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) err = -EINVAL; goto out_put_prog; } - if (prog->expected_attach_type == BPF_TRACE_RAW_TP) + if (prog->type == BPF_PROG_TYPE_TRACING && + prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; - else - return bpf_tracing_prog_attach(prog); - } else { + break; + } + return bpf_tracing_prog_attach(prog); + case BPF_PROG_TYPE_RAW_TRACEPOINT: + case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, u64_to_user_ptr(attr->raw_tracepoint.name), sizeof(buf) - 1) < 0) { @@ -2293,6 +2500,10 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) } buf[sizeof(buf) - 1] = 0; tp_name = buf; + break; + default: + err = -EINVAL; + goto out_put_prog; } btp = bpf_get_raw_tracepoint(tp_name); @@ -2301,29 +2512,30 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr) goto out_put_prog; } - raw_tp = kzalloc(sizeof(*raw_tp), GFP_USER); - if (!raw_tp) { + link = kzalloc(sizeof(*link), GFP_USER); + if (!link) { err = -ENOMEM; goto out_put_btp; } - raw_tp->btp = btp; - raw_tp->prog = prog; + bpf_link_init(&link->link, &bpf_raw_tp_lops, prog); + link->btp = btp; - err = bpf_probe_register(raw_tp->btp, prog); - if (err) - goto out_free_tp; + link_file = bpf_link_new_file(&link->link, &link_fd); + if (IS_ERR(link_file)) { + kfree(link); + err = PTR_ERR(link_file); + goto out_put_btp; + } - tp_fd = anon_inode_getfd("bpf-raw-tracepoint", &bpf_raw_tp_fops, raw_tp, - O_CLOEXEC); - if (tp_fd < 0) { - bpf_probe_unregister(raw_tp->btp, prog); - err = tp_fd; - goto out_free_tp; + err = bpf_probe_register(link->btp, prog); + if (err) { + bpf_link_cleanup(&link->link, link_file, link_fd); + goto out_put_btp; } - return tp_fd; -out_free_tp: - kfree(raw_tp); + fd_install(link_fd, link_file); + return link_fd; + out_put_btp: bpf_put_raw_tracepoint(btp); out_put_prog: @@ -2348,36 +2560,18 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, } } -#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd - -#define BPF_F_ATTACH_MASK \ - (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) - -static int bpf_prog_attach(const union bpf_attr *attr) +static enum bpf_prog_type +attach_type_to_prog_type(enum bpf_attach_type attach_type) { - enum bpf_prog_type ptype; - struct bpf_prog *prog; - int ret; - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (CHECK_ATTR(BPF_PROG_ATTACH)) - return -EINVAL; - - if (attr->attach_flags & ~BPF_F_ATTACH_MASK) - return -EINVAL; - - switch (attr->attach_type) { + switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: - ptype = BPF_PROG_TYPE_CGROUP_SKB; + return BPF_PROG_TYPE_CGROUP_SKB; break; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; + return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: @@ -2386,37 +2580,53 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; + return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: - ptype = BPF_PROG_TYPE_SOCK_OPS; - break; + return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: - ptype = BPF_PROG_TYPE_CGROUP_DEVICE; - break; + return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: - ptype = BPF_PROG_TYPE_SK_MSG; - break; + return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ptype = BPF_PROG_TYPE_SK_SKB; - break; + return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: - ptype = BPF_PROG_TYPE_LIRC_MODE2; - break; + return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: - ptype = BPF_PROG_TYPE_FLOW_DISSECTOR; - break; + return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; + return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + return BPF_PROG_TYPE_CGROUP_SOCKOPT; default: - return -EINVAL; + return BPF_PROG_TYPE_UNSPEC; } +} + +#define BPF_PROG_ATTACH_LAST_FIELD replace_bpf_fd + +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI | BPF_F_REPLACE) + +static int bpf_prog_attach(const union bpf_attr *attr) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_PROG_ATTACH)) + return -EINVAL; + + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) + return -EINVAL; + + ptype = attach_type_to_prog_type(attr->attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) @@ -2438,8 +2648,17 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = skb_flow_dissector_bpf_prog_attach(attr, prog); break; - default: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: ret = cgroup_bpf_prog_attach(attr, ptype, prog); + break; + default: + ret = -EINVAL; } if (ret) @@ -2459,53 +2678,27 @@ static int bpf_prog_detach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; - 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: - case BPF_CGROUP_INET4_POST_BIND: - case BPF_CGROUP_INET6_POST_BIND: - ptype = BPF_PROG_TYPE_CGROUP_SOCK; - break; - case BPF_CGROUP_INET4_BIND: - case BPF_CGROUP_INET6_BIND: - case BPF_CGROUP_INET4_CONNECT: - case BPF_CGROUP_INET6_CONNECT: - case BPF_CGROUP_UDP4_SENDMSG: - case BPF_CGROUP_UDP6_SENDMSG: - case BPF_CGROUP_UDP4_RECVMSG: - case BPF_CGROUP_UDP6_RECVMSG: - ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - break; - 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_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); - case BPF_SK_SKB_STREAM_PARSER: - case BPF_SK_SKB_STREAM_VERDICT: + ptype = attach_type_to_prog_type(attr->attach_type); + + switch (ptype) { + case BPF_PROG_TYPE_SK_MSG: + case BPF_PROG_TYPE_SK_SKB: return sock_map_get_from_fd(attr, NULL); - case BPF_LIRC_MODE2: + case BPF_PROG_TYPE_LIRC_MODE2: return lirc_prog_detach(attr); - case BPF_FLOW_DISSECTOR: + case BPF_PROG_TYPE_FLOW_DISSECTOR: return skb_flow_dissector_bpf_prog_detach(attr); - case BPF_CGROUP_SYSCTL: - ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; - break; - case BPF_CGROUP_GETSOCKOPT: - case BPF_CGROUP_SETSOCKOPT: - ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; - break; + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_SOCK_OPS: + return cgroup_bpf_prog_detach(attr, ptype); default: return -EINVAL; } - - return cgroup_bpf_prog_detach(attr, ptype); } #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt @@ -2539,7 +2732,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: - break; + return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: @@ -2547,8 +2740,6 @@ static int bpf_prog_query(const union bpf_attr *attr, default: return -EINVAL; } - - return cgroup_bpf_prog_query(attr, uattr); } #define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out @@ -3272,15 +3463,21 @@ static int bpf_task_fd_query(const union bpf_attr *attr, if (err) goto out; - if (file->f_op == &bpf_raw_tp_fops) { - struct bpf_raw_tracepoint *raw_tp = file->private_data; - struct bpf_raw_event_map *btp = raw_tp->btp; + if (file->f_op == &bpf_link_fops) { + struct bpf_link *link = file->private_data; - err = bpf_task_fd_query_copy(attr, uattr, - raw_tp->prog->aux->id, - BPF_FD_TYPE_RAW_TRACEPOINT, - btp->tp->name, 0, 0); - goto put_file; + if (link->ops == &bpf_raw_tp_lops) { + struct bpf_raw_tp_link *raw_tp = + container_of(link, struct bpf_raw_tp_link, link); + struct bpf_raw_event_map *btp = raw_tp->btp; + + err = bpf_task_fd_query_copy(attr, uattr, + raw_tp->link.prog->aux->id, + BPF_FD_TYPE_RAW_TRACEPOINT, + btp->tp->name, 0, 0); + goto put_file; + } + goto out_not_supp; } event = perf_get_event(file); @@ -3300,6 +3497,7 @@ static int bpf_task_fd_query(const union bpf_attr *attr, goto put_file; } +out_not_supp: err = -ENOTSUPP; put_file: fput(file); @@ -3362,6 +3560,104 @@ err_put: return err; } +#define BPF_LINK_CREATE_LAST_FIELD link_create.flags +static int link_create(union bpf_attr *attr) +{ + enum bpf_prog_type ptype; + struct bpf_prog *prog; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_LINK_CREATE)) + return -EINVAL; + + ptype = attach_type_to_prog_type(attr->link_create.attach_type); + if (ptype == BPF_PROG_TYPE_UNSPEC) + return -EINVAL; + + prog = bpf_prog_get_type(attr->link_create.prog_fd, ptype); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + ret = bpf_prog_attach_check_attach_type(prog, + attr->link_create.attach_type); + if (ret) + goto err_out; + + switch (ptype) { + case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_CGROUP_DEVICE: + case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + ret = cgroup_bpf_link_attach(attr, prog); + break; + default: + ret = -EINVAL; + } + +err_out: + if (ret < 0) + bpf_prog_put(prog); + return ret; +} + +#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd + +static int link_update(union bpf_attr *attr) +{ + struct bpf_prog *old_prog = NULL, *new_prog; + struct bpf_link *link; + u32 flags; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (CHECK_ATTR(BPF_LINK_UPDATE)) + return -EINVAL; + + flags = attr->link_update.flags; + if (flags & ~BPF_F_REPLACE) + return -EINVAL; + + link = bpf_link_get_from_fd(attr->link_update.link_fd); + if (IS_ERR(link)) + return PTR_ERR(link); + + new_prog = bpf_prog_get(attr->link_update.new_prog_fd); + if (IS_ERR(new_prog)) + return PTR_ERR(new_prog); + + if (flags & BPF_F_REPLACE) { + old_prog = bpf_prog_get(attr->link_update.old_prog_fd); + if (IS_ERR(old_prog)) { + ret = PTR_ERR(old_prog); + old_prog = NULL; + goto out_put_progs; + } + } + +#ifdef CONFIG_CGROUP_BPF + if (link->ops == &bpf_cgroup_link_lops) { + ret = cgroup_bpf_replace(link, old_prog, new_prog); + goto out_put_progs; + } +#endif + ret = -EINVAL; + +out_put_progs: + if (old_prog) + bpf_prog_put(old_prog); + if (ret) + bpf_prog_put(new_prog); + return ret; +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr; @@ -3473,6 +3769,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr, BPF_MAP_DELETE_BATCH); break; + case BPF_LINK_CREATE: + err = link_create(&attr); + break; + case BPF_LINK_UPDATE: + err = link_update(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 7ae5dddd1fe6..3b495773de5a 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -9,15 +9,15 @@ #include <linux/sysfs.h> /* See scripts/link-vmlinux.sh, gen_btf() func for details */ -extern char __weak _binary__btf_vmlinux_bin_start[]; -extern char __weak _binary__btf_vmlinux_bin_end[]; +extern char __weak __start_BTF[]; +extern char __weak __stop_BTF[]; static ssize_t btf_vmlinux_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) { - memcpy(buf, _binary__btf_vmlinux_bin_start + off, len); + memcpy(buf, __start_BTF + off, len); return len; } @@ -30,15 +30,14 @@ static struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { - if (!_binary__btf_vmlinux_bin_start) + if (!__start_BTF) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); if (!btf_kobj) return -ENOMEM; - bin_attr_btf_vmlinux.size = _binary__btf_vmlinux_bin_end - - _binary__btf_vmlinux_bin_start; + bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); } diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index d4f335a9a899..ceac5281bd31 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -194,3 +194,18 @@ int tnum_sbin(char *str, size_t size, struct tnum a) str[min(size - 1, (size_t)64)] = 0; return 64; } + +struct tnum tnum_subreg(struct tnum a) +{ + return tnum_cast(a, 4); +} + +struct tnum tnum_clear_subreg(struct tnum a) +{ + return tnum_lshift(tnum_rshift(a, 32), 32); +} + +struct tnum tnum_const_subreg(struct tnum a, u32 value) +{ + return tnum_or(tnum_clear_subreg(a), tnum_const(value)); +} diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 6b264a92064b..9be85aa4ec5f 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -5,6 +5,8 @@ #include <linux/filter.h> #include <linux/ftrace.h> #include <linux/rbtree_latch.h> +#include <linux/perf_event.h> +#include <linux/btf.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -17,12 +19,11 @@ const struct bpf_prog_ops bpf_extension_prog_ops = { #define TRAMPOLINE_TABLE_SIZE (1 << TRAMPOLINE_HASH_BITS) static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; -static struct latch_tree_root image_tree __cacheline_aligned; -/* serializes access to trampoline_table and image_tree */ +/* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); -static void *bpf_jit_alloc_exec_page(void) +void *bpf_jit_alloc_exec_page(void) { void *image; @@ -38,62 +39,28 @@ static void *bpf_jit_alloc_exec_page(void) return image; } -static __always_inline bool image_tree_less(struct latch_tree_node *a, - struct latch_tree_node *b) +void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym) { - struct bpf_image *ia = container_of(a, struct bpf_image, tnode); - struct bpf_image *ib = container_of(b, struct bpf_image, tnode); - - return ia < ib; -} - -static __always_inline int image_tree_comp(void *addr, struct latch_tree_node *n) -{ - void *image = container_of(n, struct bpf_image, tnode); - - if (addr < image) - return -1; - if (addr >= image + PAGE_SIZE) - return 1; - - return 0; -} - -static const struct latch_tree_ops image_tree_ops = { - .less = image_tree_less, - .comp = image_tree_comp, -}; - -static void *__bpf_image_alloc(bool lock) -{ - struct bpf_image *image; - - image = bpf_jit_alloc_exec_page(); - if (!image) - return NULL; - - if (lock) - mutex_lock(&trampoline_mutex); - latch_tree_insert(&image->tnode, &image_tree, &image_tree_ops); - if (lock) - mutex_unlock(&trampoline_mutex); - return image->data; + ksym->start = (unsigned long) data; + ksym->end = ksym->start + PAGE_SIZE; + bpf_ksym_add(ksym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, + PAGE_SIZE, false, ksym->name); } -void *bpf_image_alloc(void) +void bpf_image_ksym_del(struct bpf_ksym *ksym) { - return __bpf_image_alloc(true); + bpf_ksym_del(ksym); + perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, ksym->start, + PAGE_SIZE, true, ksym->name); } -bool is_bpf_image_address(unsigned long addr) +static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr) { - bool ret; - - rcu_read_lock(); - ret = latch_tree_find((void *) addr, &image_tree, &image_tree_ops) != NULL; - rcu_read_unlock(); + struct bpf_ksym *ksym = &tr->ksym; - return ret; + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key); + bpf_image_ksym_add(tr->image, ksym); } struct bpf_trampoline *bpf_trampoline_lookup(u64 key) @@ -116,7 +83,7 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) goto out; /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = __bpf_image_alloc(false); + image = bpf_jit_alloc_exec_page(); if (!image) { kfree(tr); tr = NULL; @@ -131,6 +98,8 @@ struct bpf_trampoline *bpf_trampoline_lookup(u64 key) for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); tr->image = image; + INIT_LIST_HEAD_RCU(&tr->ksym.lnode); + bpf_trampoline_ksym_add(tr); out: mutex_unlock(&trampoline_mutex); return tr; @@ -190,40 +159,50 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) return ret; } -/* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 - * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 - */ -#define BPF_MAX_TRAMP_PROGS 40 +static struct bpf_tramp_progs * +bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) +{ + const struct bpf_prog_aux *aux; + struct bpf_tramp_progs *tprogs; + struct bpf_prog **progs; + int kind; + + *total = 0; + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) + return ERR_PTR(-ENOMEM); + + for (kind = 0; kind < BPF_TRAMP_MAX; kind++) { + tprogs[kind].nr_progs = tr->progs_cnt[kind]; + *total += tr->progs_cnt[kind]; + progs = tprogs[kind].progs; + + hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) + *progs++ = aux->prog; + } + return tprogs; +} static int bpf_trampoline_update(struct bpf_trampoline *tr) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * BPF_IMAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * BPF_IMAGE_SIZE/2; - struct bpf_prog *progs_to_run[BPF_MAX_TRAMP_PROGS]; - int fentry_cnt = tr->progs_cnt[BPF_TRAMP_FENTRY]; - int fexit_cnt = tr->progs_cnt[BPF_TRAMP_FEXIT]; - struct bpf_prog **progs, **fentry, **fexit; + void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; + void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + struct bpf_tramp_progs *tprogs; u32 flags = BPF_TRAMP_F_RESTORE_REGS; - struct bpf_prog_aux *aux; - int err; + int err, total; + + tprogs = bpf_trampoline_get_progs(tr, &total); + if (IS_ERR(tprogs)) + return PTR_ERR(tprogs); - if (fentry_cnt + fexit_cnt == 0) { + if (total == 0) { err = unregister_fentry(tr, old_image); tr->selector = 0; goto out; } - /* populate fentry progs */ - fentry = progs = progs_to_run; - hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FENTRY], tramp_hlist) - *progs++ = aux->prog; - - /* populate fexit progs */ - fexit = progs; - hlist_for_each_entry(aux, &tr->progs_hlist[BPF_TRAMP_FEXIT], tramp_hlist) - *progs++ = aux->prog; - - if (fexit_cnt) + if (tprogs[BPF_TRAMP_FEXIT].nr_progs || + tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; /* Though the second half of trampoline page is unused a task could be @@ -232,12 +211,11 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) * preempted task. Hence wait for tasks to voluntarily schedule or go * to userspace. */ + synchronize_rcu_tasks(); - err = arch_prepare_bpf_trampoline(new_image, new_image + BPF_IMAGE_SIZE / 2, - &tr->func.model, flags, - fentry, fentry_cnt, - fexit, fexit_cnt, + err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, + &tr->func.model, flags, tprogs, tr->func.addr); if (err < 0) goto out; @@ -252,16 +230,27 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) goto out; tr->selector++; out: + kfree(tprogs); return err; } -static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t) +static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(struct bpf_prog *prog) { - switch (t) { + switch (prog->expected_attach_type) { case BPF_TRACE_FENTRY: return BPF_TRAMP_FENTRY; + case BPF_MODIFY_RETURN: + return BPF_TRAMP_MODIFY_RETURN; case BPF_TRACE_FEXIT: return BPF_TRAMP_FEXIT; + case BPF_LSM_MAC: + if (!prog->aux->attach_func_proto->type) + /* The function returns void, we cannot modify its + * return value. + */ + return BPF_TRAMP_FEXIT; + else + return BPF_TRAMP_MODIFY_RETURN; default: return BPF_TRAMP_REPLACE; } @@ -275,7 +264,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog) int cnt; tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + kind = bpf_attach_type_to_tramp(prog); mutex_lock(&tr->mutex); if (tr->extension_prog) { /* cannot attach fentry/fexit if extension prog is attached. @@ -325,7 +314,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog) int err; tr = prog->aux->trampoline; - kind = bpf_attach_type_to_tramp(prog->expected_attach_type); + kind = bpf_attach_type_to_tramp(prog); mutex_lock(&tr->mutex); if (kind == BPF_TRAMP_REPLACE) { WARN_ON_ONCE(!tr->extension_prog); @@ -344,8 +333,6 @@ out: void bpf_trampoline_put(struct bpf_trampoline *tr) { - struct bpf_image *image; - if (!tr) return; mutex_lock(&trampoline_mutex); @@ -356,35 +343,37 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) goto out; if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; - image = container_of(tr->image, struct bpf_image, data); - latch_tree_erase(&image->tnode, &image_tree, &image_tree_ops); + bpf_image_ksym_del(&tr->ksym); /* wait for tasks to get out of trampoline before freeing it */ synchronize_rcu_tasks(); - bpf_jit_free_exec(image); + bpf_jit_free_exec(tr->image); hlist_del(&tr->hlist); kfree(tr); out: mutex_unlock(&trampoline_mutex); } -/* The logic is similar to BPF_PROG_RUN, but with explicit rcu and preempt that - * are needed for trampoline. The macro is split into +/* The logic is similar to BPF_PROG_RUN, but with an explicit + * rcu_read_lock() and migrate_disable() which are required + * for the trampoline. The macro is split into * call _bpf_prog_enter * call prog->bpf_func * call __bpf_prog_exit */ u64 notrace __bpf_prog_enter(void) + __acquires(RCU) { u64 start = 0; rcu_read_lock(); - preempt_disable(); + migrate_disable(); if (static_branch_unlikely(&bpf_stats_enabled_key)) start = sched_clock(); return start; } void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) + __releases(RCU) { struct bpf_prog_stats *stats; @@ -401,15 +390,14 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start) stats->nsecs += sched_clock() - start; u64_stats_update_end(&stats->syncp); } - preempt_enable(); + migrate_enable(); rcu_read_unlock(); } int __weak arch_prepare_bpf_trampoline(void *image, void *image_end, const struct btf_func_model *m, u32 flags, - struct bpf_prog **fentry_progs, int fentry_cnt, - struct bpf_prog **fexit_progs, int fexit_cnt, + struct bpf_tramp_progs *tprogs, void *orig_call) { return -ENOTSUPP; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1cc945daa9c8..04c6630cc18f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -19,6 +19,8 @@ #include <linux/sort.h> #include <linux/perf_event.h> #include <linux/ctype.h> +#include <linux/error-injection.h> +#include <linux/bpf_lsm.h> #include "disasm.h" @@ -227,8 +229,7 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; - s64 msize_smax_value; - u64 msize_umax_value; + u64 msize_max_value; int ref_obj_id; int func_id; u32 btf_id; @@ -549,6 +550,22 @@ static void print_verifier_state(struct bpf_verifier_env *env, tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); verbose(env, ",var_off=%s", tn_buf); } + if (reg->s32_min_value != reg->smin_value && + reg->s32_min_value != S32_MIN) + verbose(env, ",s32_min_value=%d", + (int)(reg->s32_min_value)); + if (reg->s32_max_value != reg->smax_value && + reg->s32_max_value != S32_MAX) + verbose(env, ",s32_max_value=%d", + (int)(reg->s32_max_value)); + if (reg->u32_min_value != reg->umin_value && + reg->u32_min_value != U32_MIN) + verbose(env, ",u32_min_value=%d", + (int)(reg->u32_min_value)); + if (reg->u32_max_value != reg->umax_value && + reg->u32_max_value != U32_MAX) + verbose(env, ",u32_max_value=%d", + (int)(reg->u32_max_value)); } verbose(env, ")"); } @@ -923,6 +940,20 @@ static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm) reg->smax_value = (s64)imm; reg->umin_value = imm; reg->umax_value = imm; + + reg->s32_min_value = (s32)imm; + reg->s32_max_value = (s32)imm; + reg->u32_min_value = (u32)imm; + reg->u32_max_value = (u32)imm; +} + +static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm) +{ + reg->var_off = tnum_const_subreg(reg->var_off, imm); + reg->s32_min_value = (s32)imm; + reg->s32_max_value = (s32)imm; + reg->u32_min_value = (u32)imm; + reg->u32_max_value = (u32)imm; } /* Mark the 'variable offset' part of a register as zero. This should be @@ -977,8 +1008,52 @@ static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, 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) +/* Reset the min/max bounds of a register */ +static void __mark_reg_unbounded(struct bpf_reg_state *reg) +{ + reg->smin_value = S64_MIN; + reg->smax_value = S64_MAX; + reg->umin_value = 0; + reg->umax_value = U64_MAX; + + reg->s32_min_value = S32_MIN; + reg->s32_max_value = S32_MAX; + reg->u32_min_value = 0; + reg->u32_max_value = U32_MAX; +} + +static void __mark_reg64_unbounded(struct bpf_reg_state *reg) +{ + reg->smin_value = S64_MIN; + reg->smax_value = S64_MAX; + reg->umin_value = 0; + reg->umax_value = U64_MAX; +} + +static void __mark_reg32_unbounded(struct bpf_reg_state *reg) +{ + reg->s32_min_value = S32_MIN; + reg->s32_max_value = S32_MAX; + reg->u32_min_value = 0; + reg->u32_max_value = U32_MAX; +} + +static void __update_reg32_bounds(struct bpf_reg_state *reg) +{ + struct tnum var32_off = tnum_subreg(reg->var_off); + + /* min signed is max(sign bit) | min(other bits) */ + reg->s32_min_value = max_t(s32, reg->s32_min_value, + var32_off.value | (var32_off.mask & S32_MIN)); + /* max signed is min(sign bit) | max(other bits) */ + reg->s32_max_value = min_t(s32, reg->s32_max_value, + var32_off.value | (var32_off.mask & S32_MAX)); + reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value); + reg->u32_max_value = min(reg->u32_max_value, + (u32)(var32_off.value | var32_off.mask)); +} + +static void __update_reg64_bounds(struct bpf_reg_state *reg) { /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, @@ -991,8 +1066,48 @@ static void __update_reg_bounds(struct bpf_reg_state *reg) reg->var_off.value | reg->var_off.mask); } +static void __update_reg_bounds(struct bpf_reg_state *reg) +{ + __update_reg32_bounds(reg); + __update_reg64_bounds(reg); +} + /* Uses signed min/max values to inform unsigned, and vice-versa */ -static void __reg_deduce_bounds(struct bpf_reg_state *reg) +static void __reg32_deduce_bounds(struct bpf_reg_state *reg) +{ + /* Learn sign from signed bounds. + * If we cannot cross the sign boundary, then signed and unsigned bounds + * are the same, so combine. This works even in the negative case, e.g. + * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff. + */ + if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) { + reg->s32_min_value = reg->u32_min_value = + max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = reg->u32_max_value = + min_t(u32, reg->s32_max_value, reg->u32_max_value); + return; + } + /* Learn sign from unsigned bounds. Signed bounds cross the sign + * boundary, so we must be careful. + */ + if ((s32)reg->u32_max_value >= 0) { + /* Positive. We can't learn anything from the smin, but smax + * is positive, hence safe. + */ + reg->s32_min_value = reg->u32_min_value; + reg->s32_max_value = reg->u32_max_value = + min_t(u32, reg->s32_max_value, reg->u32_max_value); + } else if ((s32)reg->u32_min_value < 0) { + /* Negative. We can't learn anything from the smax, but smin + * is negative, hence safe. + */ + reg->s32_min_value = reg->u32_min_value = + max_t(u32, reg->s32_min_value, reg->u32_min_value); + reg->s32_max_value = reg->u32_max_value; + } +} + +static void __reg64_deduce_bounds(struct bpf_reg_state *reg) { /* Learn sign from signed bounds. * If we cannot cross the sign boundary, then signed and unsigned bounds @@ -1026,32 +1141,106 @@ static void __reg_deduce_bounds(struct bpf_reg_state *reg) } } +static void __reg_deduce_bounds(struct bpf_reg_state *reg) +{ + __reg32_deduce_bounds(reg); + __reg64_deduce_bounds(reg); +} + /* Attempts to improve var_off based on unsigned min/max information */ static void __reg_bound_offset(struct bpf_reg_state *reg) { - reg->var_off = tnum_intersect(reg->var_off, - tnum_range(reg->umin_value, - reg->umax_value)); + struct tnum var64_off = tnum_intersect(reg->var_off, + tnum_range(reg->umin_value, + reg->umax_value)); + struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off), + tnum_range(reg->u32_min_value, + reg->u32_max_value)); + + reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off); +} + +static void __reg_assign_32_into_64(struct bpf_reg_state *reg) +{ + reg->umin_value = reg->u32_min_value; + reg->umax_value = reg->u32_max_value; + /* Attempt to pull 32-bit signed bounds into 64-bit bounds + * but must be positive otherwise set to worse case bounds + * and refine later from tnum. + */ + if (reg->s32_min_value > 0) + reg->smin_value = reg->s32_min_value; + else + reg->smin_value = 0; + if (reg->s32_max_value > 0) + reg->smax_value = reg->s32_max_value; + else + reg->smax_value = U32_MAX; } -static void __reg_bound_offset32(struct bpf_reg_state *reg) +static void __reg_combine_32_into_64(struct bpf_reg_state *reg) { - u64 mask = 0xffffFFFF; - struct tnum range = tnum_range(reg->umin_value & mask, - reg->umax_value & mask); - struct tnum lo32 = tnum_cast(reg->var_off, 4); - struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32); + /* special case when 64-bit register has upper 32-bit register + * zeroed. Typically happens after zext or <<32, >>32 sequence + * allowing us to use 32-bit bounds directly, + */ + if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) { + __reg_assign_32_into_64(reg); + } else { + /* Otherwise the best we can do is push lower 32bit known and + * unknown bits into register (var_off set from jmp logic) + * then learn as much as possible from the 64-bit tnum + * known and unknown bits. The previous smin/smax bounds are + * invalid here because of jmp32 compare so mark them unknown + * so they do not impact tnum bounds calculation. + */ + __mark_reg64_unbounded(reg); + __update_reg_bounds(reg); + } - reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range)); + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __reg_deduce_bounds(reg); + __reg_bound_offset(reg); + __update_reg_bounds(reg); } -/* Reset the min/max bounds of a register */ -static void __mark_reg_unbounded(struct bpf_reg_state *reg) +static bool __reg64_bound_s32(s64 a) { - reg->smin_value = S64_MIN; - reg->smax_value = S64_MAX; - reg->umin_value = 0; - reg->umax_value = U64_MAX; + if (a > S32_MIN && a < S32_MAX) + return true; + return false; +} + +static bool __reg64_bound_u32(u64 a) +{ + if (a > U32_MIN && a < U32_MAX) + return true; + return false; +} + +static void __reg_combine_64_into_32(struct bpf_reg_state *reg) +{ + __mark_reg32_unbounded(reg); + + if (__reg64_bound_s32(reg->smin_value)) + reg->s32_min_value = (s32)reg->smin_value; + if (__reg64_bound_s32(reg->smax_value)) + reg->s32_max_value = (s32)reg->smax_value; + if (__reg64_bound_u32(reg->umin_value)) + reg->u32_min_value = (u32)reg->umin_value; + if (__reg64_bound_u32(reg->umax_value)) + reg->u32_max_value = (u32)reg->umax_value; + + /* Intersecting with the old var_off might have improved our bounds + * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), + * then new var_off is (0; 0x7f...fc) which improves our umax. + */ + __reg_deduce_bounds(reg); + __reg_bound_offset(reg); + __update_reg_bounds(reg); } /* Mark a register as having a completely unknown (scalar) value. */ @@ -2784,6 +2973,12 @@ static int check_tp_buffer_access(struct bpf_verifier_env *env, return 0; } +/* BPF architecture zero extends alu32 ops into 64-bit registesr */ +static void zext_32_to_64(struct bpf_reg_state *reg) +{ + reg->var_off = tnum_subreg(reg->var_off); + __reg_assign_32_into_64(reg); +} /* truncate register to smaller size (in bytes) * must be called with size < BPF_REG_SIZE @@ -2806,6 +3001,14 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) } reg->smin_value = reg->umin_value; reg->smax_value = reg->umax_value; + + /* If size is smaller than 32bit register the 32bit register + * values are also truncated so we push 64-bit bounds into + * 32-bit bounds. Above were truncated < 32-bits already. + */ + if (size >= 4) + return; + __reg_combine_64_into_32(reg); } static bool bpf_map_is_rdonly(const struct bpf_map *map) @@ -3460,13 +3663,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, expected_type = CONST_PTR_TO_MAP; if (type != expected_type) goto err_type; - } else if (arg_type == ARG_PTR_TO_CTX) { + } else if (arg_type == ARG_PTR_TO_CTX || + arg_type == ARG_PTR_TO_CTX_OR_NULL) { expected_type = PTR_TO_CTX; - if (type != expected_type) - goto err_type; - err = check_ctx_reg(env, reg, regno); - if (err < 0) - return err; + if (!(register_is_null(reg) && + arg_type == ARG_PTR_TO_CTX_OR_NULL)) { + if (type != expected_type) + goto err_type; + err = check_ctx_reg(env, reg, regno); + if (err < 0) + return err; + } } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { expected_type = PTR_TO_SOCK_COMMON; /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ @@ -3576,11 +3783,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); - /* remember the mem_size which may be used later - * to refine return values. + /* This is used to refine r0 return value bounds for helpers + * that enforce this value as an upper bound on return values. + * See do_refine_retval_range() for helpers that can refine + * the return value. C type of helper is u32 so we pull register + * bound from umax_value however, if negative verifier errors + * out. Only upper bounds can be learned because retval is an + * int type and negative retvals are allowed. */ - meta->msize_smax_value = reg->smax_value; - meta->msize_umax_value = reg->umax_value; + meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. @@ -3649,7 +3860,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_perf_event_read && func_id != BPF_FUNC_perf_event_output && func_id != BPF_FUNC_skb_output && - func_id != BPF_FUNC_perf_event_read_value) + func_id != BPF_FUNC_perf_event_read_value && + func_id != BPF_FUNC_xdp_output) goto error; break; case BPF_MAP_TYPE_STACK_TRACE: @@ -3693,14 +3905,16 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_redirect_map && func_id != BPF_FUNC_sock_map_update && func_id != BPF_FUNC_map_delete_elem && - func_id != BPF_FUNC_msg_redirect_map) + func_id != BPF_FUNC_msg_redirect_map && + func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_SOCKHASH: if (func_id != BPF_FUNC_sk_redirect_hash && func_id != BPF_FUNC_sock_hash_update && func_id != BPF_FUNC_map_delete_elem && - func_id != BPF_FUNC_msg_redirect_hash) + func_id != BPF_FUNC_msg_redirect_hash && + func_id != BPF_FUNC_sk_select_reuseport) goto error; break; case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: @@ -3737,6 +3951,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_perf_event_output: case BPF_FUNC_perf_event_read_value: case BPF_FUNC_skb_output: + case BPF_FUNC_xdp_output: if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) goto error; break; @@ -3774,7 +3989,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, goto error; break; case BPF_FUNC_sk_select_reuseport: - if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) + if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY && + map->map_type != BPF_MAP_TYPE_SOCKMAP && + map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; case BPF_FUNC_map_peek_elem: @@ -4117,10 +4334,11 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, func_id != BPF_FUNC_probe_read_str)) return; - ret_reg->smax_value = meta->msize_smax_value; - ret_reg->umax_value = meta->msize_umax_value; + ret_reg->smax_value = meta->msize_max_value; + ret_reg->s32_max_value = meta->msize_max_value; __reg_deduce_bounds(ret_reg); __reg_bound_offset(ret_reg); + __update_reg_bounds(ret_reg); } static int @@ -4427,7 +4645,17 @@ static bool signed_add_overflows(s64 a, s64 b) return res < a; } -static bool signed_sub_overflows(s64 a, s64 b) +static bool signed_add32_overflows(s64 a, s64 b) +{ + /* Do the add in u32, where overflow is well-defined */ + s32 res = (s32)((u32)a + (u32)b); + + if (b < 0) + return res > a; + return res < a; +} + +static bool signed_sub_overflows(s32 a, s32 b) { /* Do the sub in u64, where overflow is well-defined */ s64 res = (s64)((u64)a - (u64)b); @@ -4437,6 +4665,16 @@ static bool signed_sub_overflows(s64 a, s64 b) return res > a; } +static bool signed_sub32_overflows(s32 a, s32 b) +{ + /* Do the sub in u64, where overflow is well-defined */ + s32 res = (s32)((u32)a - (u32)b); + + if (b < 0) + return res < a; + return res > a; +} + static bool check_reg_sane_offset(struct bpf_verifier_env *env, const struct bpf_reg_state *reg, enum bpf_reg_type type) @@ -4673,6 +4911,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) return -EINVAL; + /* pointer types do not carry 32-bit bounds at the moment. */ + __mark_reg32_unbounded(dst_reg); + switch (opcode) { case BPF_ADD: ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); @@ -4836,6 +5077,518 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return 0; } +static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + s32 smax_val = src_reg->s32_max_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) || + signed_add32_overflows(dst_reg->s32_max_value, smax_val)) { + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value += smin_val; + dst_reg->s32_max_value += smax_val; + } + if (dst_reg->u32_min_value + umin_val < umin_val || + dst_reg->u32_max_value + umax_val < umax_val) { + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + dst_reg->u32_min_value += umin_val; + dst_reg->u32_max_value += umax_val; + } +} + +static void scalar_min_max_add(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + s64 smax_val = src_reg->smax_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (signed_add_overflows(dst_reg->smin_value, smin_val) || + signed_add_overflows(dst_reg->smax_value, smax_val)) { + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value += smin_val; + dst_reg->smax_value += smax_val; + } + if (dst_reg->umin_value + umin_val < umin_val || + dst_reg->umax_value + umax_val < umax_val) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value += umin_val; + dst_reg->umax_value += umax_val; + } +} + +static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + s32 smax_val = src_reg->s32_max_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) || + signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value -= smax_val; + dst_reg->s32_max_value -= smin_val; + } + if (dst_reg->u32_min_value < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->u32_min_value -= umax_val; + dst_reg->u32_max_value -= umin_val; + } +} + +static void scalar_min_max_sub(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + s64 smax_val = src_reg->smax_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (signed_sub_overflows(dst_reg->smin_value, smax_val) || + signed_sub_overflows(dst_reg->smax_value, smin_val)) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value -= smax_val; + dst_reg->smax_value -= smin_val; + } + if (dst_reg->umin_value < umax_val) { + /* Overflow possible, we know nothing */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + /* Cannot overflow (as long as bounds are consistent) */ + dst_reg->umin_value -= umax_val; + dst_reg->umax_value -= umin_val; + } +} + +static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s32 smin_val = src_reg->s32_min_value; + u32 umin_val = src_reg->u32_min_value; + u32 umax_val = src_reg->u32_max_value; + + if (smin_val < 0 || dst_reg->s32_min_value < 0) { + /* Ain't nobody got time to multiply that sign */ + __mark_reg32_unbounded(dst_reg); + return; + } + /* Both values are positive, so we can work with unsigned and + * copy the result to signed (unless it exceeds S32_MAX). + */ + if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) { + /* Potential overflow, we know nothing */ + __mark_reg32_unbounded(dst_reg); + return; + } + dst_reg->u32_min_value *= umin_val; + dst_reg->u32_max_value *= umax_val; + if (dst_reg->u32_max_value > S32_MAX) { + /* Overflow possible, we know nothing */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; + } +} + +static void scalar_min_max_mul(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + s64 smin_val = src_reg->smin_value; + u64 umin_val = src_reg->umin_value; + u64 umax_val = src_reg->umax_value; + + if (smin_val < 0 || dst_reg->smin_value < 0) { + /* Ain't nobody got time to multiply that sign */ + __mark_reg64_unbounded(dst_reg); + return; + } + /* Both values are positive, so we can work with unsigned and + * copy the result to signed (unless it exceeds S64_MAX). + */ + if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { + /* Potential overflow, we know nothing */ + __mark_reg64_unbounded(dst_reg); + return; + } + dst_reg->umin_value *= umin_val; + dst_reg->umax_value *= umax_val; + if (dst_reg->umax_value > S64_MAX) { + /* Overflow possible, we know nothing */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } +} + +static void scalar32_min_max_and(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_subreg_is_const(src_reg->var_off); + bool dst_known = tnum_subreg_is_const(dst_reg->var_off); + struct tnum var32_off = tnum_subreg(dst_reg->var_off); + s32 smin_val = src_reg->s32_min_value; + u32 umax_val = src_reg->u32_max_value; + + /* Assuming scalar64_min_max_and will be called so its safe + * to skip updating register for known 32-bit case. + */ + if (src_known && dst_known) + return; + + /* We get our minimum from the var_off, since that's inherently + * bitwise. Our maximum is the minimum of the operands' maxima. + */ + dst_reg->u32_min_value = var32_off.value; + dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val); + if (dst_reg->s32_min_value < 0 || smin_val < 0) { + /* Lose signed bounds when ANDing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + /* ANDing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; + } + +} + +static void scalar_min_max_and(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + s64 smin_val = src_reg->smin_value; + u64 umax_val = src_reg->umax_value; + + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value & + src_reg->var_off.value); + return; + } + + /* We get our minimum from the var_off, since that's inherently + * bitwise. Our maximum is the minimum of the operands' maxima. + */ + dst_reg->umin_value = dst_reg->var_off.value; + dst_reg->umax_value = min(dst_reg->umax_value, umax_val); + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ANDing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + /* ANDing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_subreg_is_const(src_reg->var_off); + bool dst_known = tnum_subreg_is_const(dst_reg->var_off); + struct tnum var32_off = tnum_subreg(dst_reg->var_off); + s32 smin_val = src_reg->smin_value; + u32 umin_val = src_reg->umin_value; + + /* Assuming scalar64_min_max_or will be called so it is safe + * to skip updating register for known case. + */ + if (src_known && dst_known) + return; + + /* We get our maximum from the var_off, and our minimum is the + * maximum of the operands' minima + */ + dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val); + dst_reg->u32_max_value = var32_off.value | var32_off.mask; + if (dst_reg->s32_min_value < 0 || smin_val < 0) { + /* Lose signed bounds when ORing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + } else { + /* ORing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->s32_min_value = dst_reg->umin_value; + dst_reg->s32_max_value = dst_reg->umax_value; + } +} + +static void scalar_min_max_or(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + bool src_known = tnum_is_const(src_reg->var_off); + bool dst_known = tnum_is_const(dst_reg->var_off); + s64 smin_val = src_reg->smin_value; + u64 umin_val = src_reg->umin_value; + + if (src_known && dst_known) { + __mark_reg_known(dst_reg, dst_reg->var_off.value | + src_reg->var_off.value); + return; + } + + /* We get our maximum from the var_off, and our minimum is the + * maximum of the operands' minima + */ + dst_reg->umin_value = max(dst_reg->umin_value, umin_val); + dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask; + if (dst_reg->smin_value < 0 || smin_val < 0) { + /* Lose signed bounds when ORing negative numbers, + * ain't nobody got time for that. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + } else { + /* ORing two positives gives a positive, so safe to + * cast result into s64. + */ + dst_reg->smin_value = dst_reg->umin_value; + dst_reg->smax_value = dst_reg->umax_value; + } + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, + u64 umin_val, u64 umax_val) +{ + /* We lose all sign bit information (except what we can pick + * up from var_off) + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + /* If we might shift our top bit out, then we know nothing */ + if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) { + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + } else { + dst_reg->u32_min_value <<= umin_val; + dst_reg->u32_max_value <<= umax_val; + } +} + +static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u32 umax_val = src_reg->u32_max_value; + u32 umin_val = src_reg->u32_min_value; + /* u32 alu operation will zext upper bits */ + struct tnum subreg = tnum_subreg(dst_reg->var_off); + + __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); + dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val)); + /* Not required but being careful mark reg64 bounds as unknown so + * that we are forced to pick them up from tnum and zext later and + * if some path skips this step we are still safe. + */ + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg, + u64 umin_val, u64 umax_val) +{ + /* Special case <<32 because it is a common compiler pattern to sign + * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are + * positive we know this shift will also be positive so we can track + * bounds correctly. Otherwise we lose all sign bit information except + * what we can pick up from var_off. Perhaps we can generalize this + * later to shifts of any length. + */ + if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0) + dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32; + else + dst_reg->smax_value = S64_MAX; + + if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0) + dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32; + else + dst_reg->smin_value = S64_MIN; + + /* If we might shift our top bit out, then we know nothing */ + if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + } else { + dst_reg->umin_value <<= umin_val; + dst_reg->umax_value <<= umax_val; + } +} + +static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umax_val = src_reg->umax_value; + u64 umin_val = src_reg->umin_value; + + /* scalar64 calc uses 32bit unshifted bounds so must be called first */ + __scalar64_min_max_lsh(dst_reg, umin_val, umax_val); + __scalar32_min_max_lsh(dst_reg, umin_val, umax_val); + + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); + /* We may learn something more from the var_off */ + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + struct tnum subreg = tnum_subreg(dst_reg->var_off); + u32 umax_val = src_reg->u32_max_value; + u32 umin_val = src_reg->u32_min_value; + + /* BPF_RSH is an unsigned shift. If the value in dst_reg might + * be negative, then either: + * 1) src_reg might be zero, so the sign bit of the result is + * unknown, so we lose our signed bounds + * 2) it's known negative, thus the unsigned bounds capture the + * signed bounds + * 3) the signed bounds cross zero, so they tell us nothing + * about the result + * If the value in dst_reg is known nonnegative, then again the + * unsigned bounts capture the signed bounds. + * Thus, in all cases it suffices to blow away our signed bounds + * and rely on inferring new ones from the unsigned bounds and + * var_off of the result. + */ + dst_reg->s32_min_value = S32_MIN; + dst_reg->s32_max_value = S32_MAX; + + dst_reg->var_off = tnum_rshift(subreg, umin_val); + dst_reg->u32_min_value >>= umax_val; + dst_reg->u32_max_value >>= umin_val; + + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umax_val = src_reg->umax_value; + u64 umin_val = src_reg->umin_value; + + /* BPF_RSH is an unsigned shift. If the value in dst_reg might + * be negative, then either: + * 1) src_reg might be zero, so the sign bit of the result is + * unknown, so we lose our signed bounds + * 2) it's known negative, thus the unsigned bounds capture the + * signed bounds + * 3) the signed bounds cross zero, so they tell us nothing + * about the result + * If the value in dst_reg is known nonnegative, then again the + * unsigned bounts capture the signed bounds. + * Thus, in all cases it suffices to blow away our signed bounds + * and rely on inferring new ones from the unsigned bounds and + * var_off of the result. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; + dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); + dst_reg->umin_value >>= umax_val; + dst_reg->umax_value >>= umin_val; + + /* Its not easy to operate on alu32 bounds here because it depends + * on bits being shifted in. Take easy way out and mark unbounded + * so we can recalculate later from tnum. + */ + __mark_reg32_unbounded(dst_reg); + __update_reg_bounds(dst_reg); +} + +static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umin_val = src_reg->u32_min_value; + + /* Upon reaching here, src_known is true and + * umax_val is equal to umin_val. + */ + dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val); + dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val); + + dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->u32_min_value = 0; + dst_reg->u32_max_value = U32_MAX; + + __mark_reg64_unbounded(dst_reg); + __update_reg32_bounds(dst_reg); +} + +static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg, + struct bpf_reg_state *src_reg) +{ + u64 umin_val = src_reg->umin_value; + + /* Upon reaching here, src_known is true and umax_val is equal + * to umin_val. + */ + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + + /* Its not easy to operate on alu32 bounds here because it depends + * on bits being shifted in from upper 32-bits. Take easy way out + * and mark unbounded so we can recalculate later from tnum. + */ + __mark_reg32_unbounded(dst_reg); + __update_reg_bounds(dst_reg); +} + /* WARNING: This function does calculations on 64-bit values, but the actual * execution may occur on 32-bit values. Therefore, things like bitshifts * need extra checks in the 32-bit case. @@ -4850,33 +5603,47 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, bool src_known, dst_known; s64 smin_val, smax_val; u64 umin_val, umax_val; + s32 s32_min_val, s32_max_val; + u32 u32_min_val, u32_max_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; u32 dst = insn->dst_reg; int ret; - - if (insn_bitness == 32) { - /* Relevant for 32-bit RSH: Information can propagate towards - * LSB, so it isn't sufficient to only truncate the output to - * 32 bits. - */ - coerce_reg_to_size(dst_reg, 4); - coerce_reg_to_size(&src_reg, 4); - } + bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; umax_val = src_reg.umax_value; - src_known = tnum_is_const(src_reg.var_off); - dst_known = tnum_is_const(dst_reg->var_off); - if ((src_known && (smin_val != smax_val || umin_val != umax_val)) || - smin_val > smax_val || umin_val > umax_val) { - /* Taint dst register if offset had invalid bounds derived from - * e.g. dead branches. - */ - __mark_reg_unknown(env, dst_reg); - return 0; + s32_min_val = src_reg.s32_min_value; + s32_max_val = src_reg.s32_max_value; + u32_min_val = src_reg.u32_min_value; + u32_max_val = src_reg.u32_max_value; + + if (alu32) { + src_known = tnum_subreg_is_const(src_reg.var_off); + dst_known = tnum_subreg_is_const(dst_reg->var_off); + if ((src_known && + (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) || + s32_min_val > s32_max_val || u32_min_val > u32_max_val) { + /* Taint dst register if offset had invalid bounds + * derived from e.g. dead branches. + */ + __mark_reg_unknown(env, dst_reg); + return 0; + } + } else { + src_known = tnum_is_const(src_reg.var_off); + dst_known = tnum_is_const(dst_reg->var_off); + if ((src_known && + (smin_val != smax_val || umin_val != umax_val)) || + smin_val > smax_val || umin_val > umax_val) { + /* Taint dst register if offset had invalid bounds + * derived from e.g. dead branches. + */ + __mark_reg_unknown(env, dst_reg); + return 0; + } } if (!src_known && @@ -4885,6 +5652,20 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, return 0; } + /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. + * There are two classes of instructions: The first class we track both + * alu32 and alu64 sign/unsigned bounds independently this provides the + * greatest amount of precision when alu operations are mixed with jmp32 + * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD, + * and BPF_OR. This is possible because these ops have fairly easy to + * understand and calculate behavior in both 32-bit and 64-bit alu ops. + * See alu32 verifier tests for examples. The second class of + * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy + * with regards to tracking sign/unsigned bounds because the bits may + * cross subreg boundaries in the alu64 case. When this happens we mark + * the reg unbounded in the subreg bound space and use the resulting + * tnum to calculate an approximation of the sign/unsigned bounds. + */ switch (opcode) { case BPF_ADD: ret = sanitize_val_alu(env, insn); @@ -4892,22 +5673,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d tried to add from different pointers or scalars\n", dst); return ret; } - if (signed_add_overflows(dst_reg->smin_value, smin_val) || - signed_add_overflows(dst_reg->smax_value, smax_val)) { - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value += smin_val; - dst_reg->smax_value += smax_val; - } - if (dst_reg->umin_value + umin_val < umin_val || - dst_reg->umax_value + umax_val < umax_val) { - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value += umin_val; - dst_reg->umax_value += umax_val; - } + scalar32_min_max_add(dst_reg, &src_reg); + scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: @@ -4916,111 +5683,24 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); return ret; } - if (signed_sub_overflows(dst_reg->smin_value, smax_val) || - signed_sub_overflows(dst_reg->smax_value, smin_val)) { - /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value -= smax_val; - dst_reg->smax_value -= smin_val; - } - if (dst_reg->umin_value < umax_val) { - /* Overflow possible, we know nothing */ - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - /* Cannot overflow (as long as bounds are consistent) */ - dst_reg->umin_value -= umax_val; - dst_reg->umax_value -= umin_val; - } + scalar32_min_max_sub(dst_reg, &src_reg); + scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); break; case BPF_MUL: dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off); - if (smin_val < 0 || dst_reg->smin_value < 0) { - /* Ain't nobody got time to multiply that sign */ - __mark_reg_unbounded(dst_reg); - __update_reg_bounds(dst_reg); - break; - } - /* Both values are positive, so we can work with unsigned and - * copy the result to signed (unless it exceeds S64_MAX). - */ - if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) { - /* Potential overflow, we know nothing */ - __mark_reg_unbounded(dst_reg); - /* (except what we can learn from the var_off) */ - __update_reg_bounds(dst_reg); - break; - } - dst_reg->umin_value *= umin_val; - dst_reg->umax_value *= umax_val; - if (dst_reg->umax_value > S64_MAX) { - /* Overflow possible, we know nothing */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } + scalar32_min_max_mul(dst_reg, &src_reg); + scalar_min_max_mul(dst_reg, &src_reg); break; case BPF_AND: - if (src_known && dst_known) { - __mark_reg_known(dst_reg, dst_reg->var_off.value & - src_reg.var_off.value); - break; - } - /* We get our minimum from the var_off, since that's inherently - * bitwise. Our maximum is the minimum of the operands' maxima. - */ dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off); - dst_reg->umin_value = dst_reg->var_off.value; - dst_reg->umax_value = min(dst_reg->umax_value, umax_val); - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ANDing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ANDing two positives gives a positive, so safe to - * cast result into s64. - */ - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + scalar32_min_max_and(dst_reg, &src_reg); + scalar_min_max_and(dst_reg, &src_reg); break; case BPF_OR: - if (src_known && dst_known) { - __mark_reg_known(dst_reg, dst_reg->var_off.value | - src_reg.var_off.value); - break; - } - /* We get our maximum from the var_off, and our minimum is the - * maximum of the operands' minima - */ dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off); - dst_reg->umin_value = max(dst_reg->umin_value, umin_val); - dst_reg->umax_value = dst_reg->var_off.value | - dst_reg->var_off.mask; - if (dst_reg->smin_value < 0 || smin_val < 0) { - /* Lose signed bounds when ORing negative numbers, - * ain't nobody got time for that. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } else { - /* ORing two positives gives a positive, so safe to - * cast result into s64. - */ - dst_reg->smin_value = dst_reg->umin_value; - dst_reg->smax_value = dst_reg->umax_value; - } - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + scalar32_min_max_or(dst_reg, &src_reg); + scalar_min_max_or(dst_reg, &src_reg); break; case BPF_LSH: if (umax_val >= insn_bitness) { @@ -5030,22 +5710,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - /* We lose all sign bit information (except what we can pick - * up from var_off) - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - /* If we might shift our top bit out, then we know nothing */ - if (dst_reg->umax_value > 1ULL << (63 - umax_val)) { - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - } else { - dst_reg->umin_value <<= umin_val; - dst_reg->umax_value <<= umax_val; - } - dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_lsh(dst_reg, &src_reg); + else + scalar_min_max_lsh(dst_reg, &src_reg); break; case BPF_RSH: if (umax_val >= insn_bitness) { @@ -5055,27 +5723,10 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - /* BPF_RSH is an unsigned shift. If the value in dst_reg might - * be negative, then either: - * 1) src_reg might be zero, so the sign bit of the result is - * unknown, so we lose our signed bounds - * 2) it's known negative, thus the unsigned bounds capture the - * signed bounds - * 3) the signed bounds cross zero, so they tell us nothing - * about the result - * If the value in dst_reg is known nonnegative, then again the - * unsigned bounts capture the signed bounds. - * Thus, in all cases it suffices to blow away our signed bounds - * and rely on inferring new ones from the unsigned bounds and - * var_off of the result. - */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); - dst_reg->umin_value >>= umax_val; - dst_reg->umax_value >>= umin_val; - /* We may learn something more from the var_off */ - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_rsh(dst_reg, &src_reg); + else + scalar_min_max_rsh(dst_reg, &src_reg); break; case BPF_ARSH: if (umax_val >= insn_bitness) { @@ -5085,38 +5736,21 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, mark_reg_unknown(env, regs, insn->dst_reg); break; } - - /* Upon reaching here, src_known is true and - * umax_val is equal to umin_val. - */ - if (insn_bitness == 32) { - dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val); - dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val); - } else { - dst_reg->smin_value >>= umin_val; - dst_reg->smax_value >>= umin_val; - } - - dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, - insn_bitness); - - /* blow away the dst_reg umin_value/umax_value and rely on - * dst_reg var_off to refine the result. - */ - dst_reg->umin_value = 0; - dst_reg->umax_value = U64_MAX; - __update_reg_bounds(dst_reg); + if (alu32) + scalar32_min_max_arsh(dst_reg, &src_reg); + else + scalar_min_max_arsh(dst_reg, &src_reg); break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; } - if (BPF_CLASS(insn->code) != BPF_ALU64) { - /* 32-bit ALU ops are (32,32)->32 */ - coerce_reg_to_size(dst_reg, 4); - } + /* ALU32 ops are zero extended into 64bit register */ + if (alu32) + zext_32_to_64(dst_reg); + __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; @@ -5290,7 +5924,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_unknown(env, regs, insn->dst_reg); } - coerce_reg_to_size(dst_reg, 4); + zext_32_to_64(dst_reg); } } else { /* case: R = imm @@ -5460,55 +6094,83 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range); } -/* compute branch direction of the expression "if (reg opcode val) goto target;" - * and return: - * 1 - branch will be taken and "goto target" will be executed - * 0 - branch will not be taken and fall-through to next insn - * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10] - */ -static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, - bool is_jmp32) +static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) { - struct bpf_reg_state reg_lo; - s64 sval; + struct tnum subreg = tnum_subreg(reg->var_off); + s32 sval = (s32)val; - if (__is_pointer_value(false, reg)) - return -1; + switch (opcode) { + case BPF_JEQ: + if (tnum_is_const(subreg)) + return !!tnum_equals_const(subreg, val); + break; + case BPF_JNE: + if (tnum_is_const(subreg)) + return !tnum_equals_const(subreg, val); + break; + case BPF_JSET: + if ((~subreg.mask & subreg.value) & val) + return 1; + if (!((subreg.mask | subreg.value) & val)) + return 0; + break; + case BPF_JGT: + if (reg->u32_min_value > val) + return 1; + else if (reg->u32_max_value <= val) + return 0; + break; + case BPF_JSGT: + if (reg->s32_min_value > sval) + return 1; + else if (reg->s32_max_value < sval) + return 0; + break; + case BPF_JLT: + if (reg->u32_max_value < val) + return 1; + else if (reg->u32_min_value >= val) + return 0; + break; + case BPF_JSLT: + if (reg->s32_max_value < sval) + return 1; + else if (reg->s32_min_value >= sval) + return 0; + break; + case BPF_JGE: + if (reg->u32_min_value >= val) + return 1; + else if (reg->u32_max_value < val) + return 0; + break; + case BPF_JSGE: + if (reg->s32_min_value >= sval) + return 1; + else if (reg->s32_max_value < sval) + return 0; + break; + case BPF_JLE: + if (reg->u32_max_value <= val) + return 1; + else if (reg->u32_min_value > val) + return 0; + break; + case BPF_JSLE: + if (reg->s32_max_value <= sval) + return 1; + else if (reg->s32_min_value > sval) + return 0; + break; + } - if (is_jmp32) { - reg_lo = *reg; - reg = ®_lo; - /* For JMP32, only low 32 bits are compared, coerce_reg_to_size - * could truncate high bits and update umin/umax according to - * information of low bits. - */ - coerce_reg_to_size(reg, 4); - /* smin/smax need special handling. For example, after coerce, - * if smin_value is 0x00000000ffffffffLL, the value is -1 when - * used as operand to JMP32. It is a negative number from s32's - * point of view, while it is a positive number when seen as - * s64. The smin/smax are kept as s64, therefore, when used with - * JMP32, they need to be transformed into s32, then sign - * extended back to s64. - * - * Also, smin/smax were copied from umin/umax. If umin/umax has - * different sign bit, then min/max relationship doesn't - * maintain after casting into s32, for this case, set smin/smax - * to safest range. - */ - if ((reg->umax_value ^ reg->umin_value) & - (1ULL << 31)) { - reg->smin_value = S32_MIN; - reg->smax_value = S32_MAX; - } - reg->smin_value = (s64)(s32)reg->smin_value; - reg->smax_value = (s64)(s32)reg->smax_value; + return -1; +} - val = (u32)val; - sval = (s64)(s32)val; - } else { - sval = (s64)val; - } + +static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) +{ + s64 sval = (s64)val; switch (opcode) { case BPF_JEQ: @@ -5578,27 +6240,22 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, return -1; } -/* Generate min value of the high 32-bit from TNUM info. */ -static u64 gen_hi_min(struct tnum var) -{ - return var.value & ~0xffffffffULL; -} - -/* Generate max value of the high 32-bit from TNUM info. */ -static u64 gen_hi_max(struct tnum var) -{ - return (var.value | var.mask) & ~0xffffffffULL; -} - -/* Return true if VAL is compared with a s64 sign extended from s32, and they - * are with the same signedness. +/* compute branch direction of the expression "if (reg opcode val) goto target;" + * and return: + * 1 - branch will be taken and "goto target" will be executed + * 0 - branch will not be taken and fall-through to next insn + * -1 - unknown. Example: "if (reg < 5)" is unknown when register value + * range [0,10] */ -static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg) +static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode, + bool is_jmp32) { - return ((s32)sval >= 0 && - reg->smin_value >= 0 && reg->smax_value <= S32_MAX) || - ((s32)sval < 0 && - reg->smax_value <= 0 && reg->smin_value >= S32_MIN); + if (__is_pointer_value(false, reg)) + return -1; + + if (is_jmp32) + return is_branch32_taken(reg, val, opcode); + return is_branch64_taken(reg, val, opcode); } /* Adjusts the register min/max values in the case that the dst_reg is the @@ -5607,10 +6264,16 @@ static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg) * In JEQ/JNE cases we also adjust the var_off values. */ static void reg_set_min_max(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, u64 val, + struct bpf_reg_state *false_reg, + u64 val, u32 val32, u8 opcode, bool is_jmp32) { - s64 sval; + struct tnum false_32off = tnum_subreg(false_reg->var_off); + struct tnum false_64off = false_reg->var_off; + struct tnum true_32off = tnum_subreg(true_reg->var_off); + struct tnum true_64off = true_reg->var_off; + s64 sval = (s64)val; + s32 sval32 = (s32)val32; /* If the dst_reg is a pointer, we can't learn anything about its * variable offset from the compare (unless src_reg were a pointer into @@ -5621,9 +6284,6 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, if (__is_pointer_value(false, false_reg)) return; - val = is_jmp32 ? (u32)val : val; - sval = is_jmp32 ? (s64)(s32)val : (s64)val; - switch (opcode) { case BPF_JEQ: case BPF_JNE: @@ -5635,211 +6295,150 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg, * if it is true we know the value for sure. Likewise for * BPF_JNE. */ - if (is_jmp32) { - u64 old_v = reg->var_off.value; - u64 hi_mask = ~0xffffffffULL; - - reg->var_off.value = (old_v & hi_mask) | val; - reg->var_off.mask &= hi_mask; - } else { + if (is_jmp32) + __mark_reg32_known(reg, val32); + else __mark_reg_known(reg, val); - } break; } case BPF_JSET: - false_reg->var_off = tnum_and(false_reg->var_off, - tnum_const(~val)); - if (is_power_of_2(val)) - true_reg->var_off = tnum_or(true_reg->var_off, - tnum_const(val)); + if (is_jmp32) { + false_32off = tnum_and(false_32off, tnum_const(~val32)); + if (is_power_of_2(val32)) + true_32off = tnum_or(true_32off, + tnum_const(val32)); + } else { + false_64off = tnum_and(false_64off, tnum_const(~val)); + if (is_power_of_2(val)) + true_64off = tnum_or(true_64off, + tnum_const(val)); + } break; case BPF_JGE: case BPF_JGT: { - u64 false_umax = opcode == BPF_JGT ? val : val - 1; - u64 true_umin = opcode == BPF_JGT ? val + 1 : val; - if (is_jmp32) { - false_umax += gen_hi_max(false_reg->var_off); - true_umin += gen_hi_min(true_reg->var_off); + u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1; + u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32; + + false_reg->u32_max_value = min(false_reg->u32_max_value, + false_umax); + true_reg->u32_min_value = max(true_reg->u32_min_value, + true_umin); + } else { + u64 false_umax = opcode == BPF_JGT ? val : val - 1; + u64 true_umin = opcode == BPF_JGT ? val + 1 : val; + + false_reg->umax_value = min(false_reg->umax_value, false_umax); + true_reg->umin_value = max(true_reg->umin_value, true_umin); } - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); break; } case BPF_JSGE: case BPF_JSGT: { - s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; + if (is_jmp32) { + s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1; + s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32; - /* If the full s64 was not sign-extended from s32 then don't - * deduct further info. - */ - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); + false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax); + true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin); + } else { + s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1; + s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval; + + false_reg->smax_value = min(false_reg->smax_value, false_smax); + true_reg->smin_value = max(true_reg->smin_value, true_smin); + } break; } case BPF_JLE: case BPF_JLT: { - u64 false_umin = opcode == BPF_JLT ? val : val + 1; - u64 true_umax = opcode == BPF_JLT ? val - 1 : val; - if (is_jmp32) { - false_umin += gen_hi_min(false_reg->var_off); - true_umax += gen_hi_max(true_reg->var_off); + u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1; + u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32; + + false_reg->u32_min_value = max(false_reg->u32_min_value, + false_umin); + true_reg->u32_max_value = min(true_reg->u32_max_value, + true_umax); + } else { + u64 false_umin = opcode == BPF_JLT ? val : val + 1; + u64 true_umax = opcode == BPF_JLT ? val - 1 : val; + + false_reg->umin_value = max(false_reg->umin_value, false_umin); + true_reg->umax_value = min(true_reg->umax_value, true_umax); } - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); break; } case BPF_JSLE: case BPF_JSLT: { - s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; + if (is_jmp32) { + s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1; + s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32; - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); + false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin); + true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax); + } else { + s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1; + s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval; + + false_reg->smin_value = max(false_reg->smin_value, false_smin); + true_reg->smax_value = min(true_reg->smax_value, true_smax); + } break; } default: - break; + return; } - __reg_deduce_bounds(false_reg); - __reg_deduce_bounds(true_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(false_reg); - __reg_bound_offset(true_reg); if (is_jmp32) { - __reg_bound_offset32(false_reg); - __reg_bound_offset32(true_reg); + false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off), + tnum_subreg(false_32off)); + true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off), + tnum_subreg(true_32off)); + __reg_combine_32_into_64(false_reg); + __reg_combine_32_into_64(true_reg); + } else { + false_reg->var_off = false_64off; + true_reg->var_off = true_64off; + __reg_combine_64_into_32(false_reg); + __reg_combine_64_into_32(true_reg); } - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. - */ - __update_reg_bounds(false_reg); - __update_reg_bounds(true_reg); } /* Same as above, but for the case that dst_reg holds a constant and src_reg is * the variable reg. */ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg, - struct bpf_reg_state *false_reg, u64 val, + struct bpf_reg_state *false_reg, + u64 val, u32 val32, u8 opcode, bool is_jmp32) { - s64 sval; - - if (__is_pointer_value(false, false_reg)) - return; - - val = is_jmp32 ? (u32)val : val; - sval = is_jmp32 ? (s64)(s32)val : (s64)val; - - switch (opcode) { - case BPF_JEQ: - case BPF_JNE: - { - struct bpf_reg_state *reg = - opcode == BPF_JEQ ? true_reg : false_reg; - - if (is_jmp32) { - u64 old_v = reg->var_off.value; - u64 hi_mask = ~0xffffffffULL; - - reg->var_off.value = (old_v & hi_mask) | val; - reg->var_off.mask &= hi_mask; - } else { - __mark_reg_known(reg, val); - } - break; - } - case BPF_JSET: - false_reg->var_off = tnum_and(false_reg->var_off, - tnum_const(~val)); - if (is_power_of_2(val)) - true_reg->var_off = tnum_or(true_reg->var_off, - tnum_const(val)); - break; - case BPF_JGE: - case BPF_JGT: - { - u64 false_umin = opcode == BPF_JGT ? val : val + 1; - u64 true_umax = opcode == BPF_JGT ? val - 1 : val; - - if (is_jmp32) { - false_umin += gen_hi_min(false_reg->var_off); - true_umax += gen_hi_max(true_reg->var_off); - } - false_reg->umin_value = max(false_reg->umin_value, false_umin); - true_reg->umax_value = min(true_reg->umax_value, true_umax); - break; - } - case BPF_JSGE: - case BPF_JSGT: - { - s64 false_smin = opcode == BPF_JSGT ? sval : sval + 1; - s64 true_smax = opcode == BPF_JSGT ? sval - 1 : sval; - - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smin_value = max(false_reg->smin_value, false_smin); - true_reg->smax_value = min(true_reg->smax_value, true_smax); - break; - } - case BPF_JLE: - case BPF_JLT: - { - u64 false_umax = opcode == BPF_JLT ? val : val - 1; - u64 true_umin = opcode == BPF_JLT ? val + 1 : val; - - if (is_jmp32) { - false_umax += gen_hi_max(false_reg->var_off); - true_umin += gen_hi_min(true_reg->var_off); - } - false_reg->umax_value = min(false_reg->umax_value, false_umax); - true_reg->umin_value = max(true_reg->umin_value, true_umin); - break; - } - case BPF_JSLE: - case BPF_JSLT: - { - s64 false_smax = opcode == BPF_JSLT ? sval : sval - 1; - s64 true_smin = opcode == BPF_JSLT ? sval + 1 : sval; - - if (is_jmp32 && !cmp_val_with_extended_s64(sval, false_reg)) - break; - false_reg->smax_value = min(false_reg->smax_value, false_smax); - true_reg->smin_value = max(true_reg->smin_value, true_smin); - break; - } - default: - break; - } - - __reg_deduce_bounds(false_reg); - __reg_deduce_bounds(true_reg); - /* We might have learned some bits from the bounds. */ - __reg_bound_offset(false_reg); - __reg_bound_offset(true_reg); - if (is_jmp32) { - __reg_bound_offset32(false_reg); - __reg_bound_offset32(true_reg); - } - /* Intersecting with the old var_off might have improved our bounds - * slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc), - * then new var_off is (0; 0x7f...fc) which improves our umax. + /* How can we transform "a <op> b" into "b <op> a"? */ + static const u8 opcode_flip[16] = { + /* these stay the same */ + [BPF_JEQ >> 4] = BPF_JEQ, + [BPF_JNE >> 4] = BPF_JNE, + [BPF_JSET >> 4] = BPF_JSET, + /* these swap "lesser" and "greater" (L and G in the opcodes) */ + [BPF_JGE >> 4] = BPF_JLE, + [BPF_JGT >> 4] = BPF_JLT, + [BPF_JLE >> 4] = BPF_JGE, + [BPF_JLT >> 4] = BPF_JGT, + [BPF_JSGE >> 4] = BPF_JSLE, + [BPF_JSGT >> 4] = BPF_JSLT, + [BPF_JSLE >> 4] = BPF_JSGE, + [BPF_JSLT >> 4] = BPF_JSGT + }; + opcode = opcode_flip[opcode >> 4]; + /* This uses zero as "not present in table"; luckily the zero opcode, + * BPF_JA, can't get here. */ - __update_reg_bounds(false_reg); - __update_reg_bounds(true_reg); + if (opcode) + reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32); } /* Regs are known to be equal, so intersect their min/max/var_off */ @@ -6128,13 +6727,22 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; - if (BPF_SRC(insn->code) == BPF_K) - pred = is_branch_taken(dst_reg, insn->imm, - opcode, is_jmp32); - else if (src_reg->type == SCALAR_VALUE && - tnum_is_const(src_reg->var_off)) - pred = is_branch_taken(dst_reg, src_reg->var_off.value, - opcode, is_jmp32); + if (BPF_SRC(insn->code) == BPF_K) { + pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32); + } else if (src_reg->type == SCALAR_VALUE && + is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) { + pred = is_branch_taken(dst_reg, + tnum_subreg(src_reg->var_off).value, + opcode, + is_jmp32); + } else if (src_reg->type == SCALAR_VALUE && + !is_jmp32 && tnum_is_const(src_reg->var_off)) { + pred = is_branch_taken(dst_reg, + src_reg->var_off.value, + opcode, + is_jmp32); + } + if (pred >= 0) { err = mark_chain_precision(env, insn->dst_reg); if (BPF_SRC(insn->code) == BPF_X && !err) @@ -6168,32 +6776,24 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = ®s[insn->src_reg]; - struct bpf_reg_state lo_reg0 = *dst_reg; - struct bpf_reg_state lo_reg1 = *src_reg; - struct bpf_reg_state *src_lo, *dst_lo; - - dst_lo = &lo_reg0; - src_lo = &lo_reg1; - coerce_reg_to_size(dst_lo, 4); - coerce_reg_to_size(src_lo, 4); if (dst_reg->type == SCALAR_VALUE && src_reg->type == SCALAR_VALUE) { if (tnum_is_const(src_reg->var_off) || - (is_jmp32 && tnum_is_const(src_lo->var_off))) + (is_jmp32 && + tnum_is_const(tnum_subreg(src_reg->var_off)))) reg_set_min_max(&other_branch_regs[insn->dst_reg], dst_reg, - is_jmp32 - ? src_lo->var_off.value - : src_reg->var_off.value, + src_reg->var_off.value, + tnum_subreg(src_reg->var_off).value, opcode, is_jmp32); else if (tnum_is_const(dst_reg->var_off) || - (is_jmp32 && tnum_is_const(dst_lo->var_off))) + (is_jmp32 && + tnum_is_const(tnum_subreg(dst_reg->var_off)))) reg_set_min_max_inv(&other_branch_regs[insn->src_reg], src_reg, - is_jmp32 - ? dst_lo->var_off.value - : dst_reg->var_off.value, + dst_reg->var_off.value, + tnum_subreg(dst_reg->var_off).value, opcode, is_jmp32); else if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE)) @@ -6204,7 +6804,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } else if (dst_reg->type == SCALAR_VALUE) { reg_set_min_max(&other_branch_regs[insn->dst_reg], - dst_reg, insn->imm, opcode, is_jmp32); + dst_reg, insn->imm, (u32)insn->imm, + opcode, is_jmp32); } /* detect if R == 0 where R is returned from bpf_map_lookup_elem(). @@ -6405,8 +7006,9 @@ static int check_return_code(struct bpf_verifier_env *env) struct tnum range = tnum_range(0, 1); int err; - /* The struct_ops func-ptr's return type could be "void" */ - if (env->prog->type == BPF_PROG_TYPE_STRUCT_OPS && + /* LSM and struct_ops func-ptr's return type could be "void" */ + if ((env->prog->type == BPF_PROG_TYPE_STRUCT_OPS || + env->prog->type == BPF_PROG_TYPE_LSM) && !prog->aux->attach_func_proto->type) return 0; @@ -8139,26 +8741,48 @@ static bool is_tracing_prog_type(enum bpf_prog_type type) } } +static bool is_preallocated_map(struct bpf_map *map) +{ + if (!check_map_prealloc(map)) + return false; + if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta)) + return false; + return true; +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) { - /* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use - * preallocated hash maps, since doing memory allocation - * in overflow_handler can crash depending on where nmi got - * triggered. + /* + * Validate that trace type programs use preallocated hash maps. + * + * For programs attached to PERF events this is mandatory as the + * perf NMI can hit any arbitrary code sequence. + * + * All other trace types using preallocated hash maps are unsafe as + * well because tracepoint or kprobes can be inside locked regions + * of the memory allocator or at a place where a recursion into the + * memory allocator would see inconsistent state. + * + * On RT enabled kernels run-time allocation of all trace type + * programs is strictly prohibited due to lock type constraints. On + * !RT kernels it is allowed for backwards compatibility reasons for + * now, but warnings are emitted so developers are made aware of + * the unsafety and can fix their programs before this is enforced. */ - if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { - if (!check_map_prealloc(map)) { + if (is_tracing_prog_type(prog->type) && !is_preallocated_map(map)) { + if (prog->type == BPF_PROG_TYPE_PERF_EVENT) { 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(env, "perf_event programs can only use preallocated inner hash map\n"); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + verbose(env, "trace type programs can only use preallocated hash map\n"); return -EINVAL; } + WARN_ONCE(1, "trace type BPF program uses run-time allocation\n"); + verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n"); } if ((is_tracing_prog_type(prog->type) || @@ -9774,6 +10398,26 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return 0; } +#define SECURITY_PREFIX "security_" + +static int check_attach_modify_return(struct bpf_verifier_env *env) +{ + struct bpf_prog *prog = env->prog; + unsigned long addr = (unsigned long) prog->aux->trampoline->func.addr; + + /* This is expected to be cleaned up in the future with the KRSI effort + * introducing the LSM_HOOK macro for cleaning up lsm_hooks.h. + */ + if (within_error_injection_list(addr) || + !strncmp(SECURITY_PREFIX, prog->aux->attach_func_name, + sizeof(SECURITY_PREFIX) - 1)) + return 0; + + verbose(env, "fmod_ret attach_btf_id %u (%s) is not modifiable\n", + prog->aux->attach_btf_id, prog->aux->attach_func_name); + + return -EINVAL; +} static int check_attach_btf_id(struct bpf_verifier_env *env) { @@ -9794,7 +10438,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (prog->type == BPF_PROG_TYPE_STRUCT_OPS) return check_struct_ops_btf_id(env); - if (prog->type != BPF_PROG_TYPE_TRACING && !prog_extension) + if (prog->type != BPF_PROG_TYPE_TRACING && + prog->type != BPF_PROG_TYPE_LSM && + !prog_extension) return 0; if (!btf_id) { @@ -9924,8 +10570,17 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) if (!prog_extension) return -EINVAL; /* fallthrough */ + case BPF_MODIFY_RETURN: + case BPF_LSM_MAC: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: + prog->aux->attach_func_name = tname; + if (prog->type == BPF_PROG_TYPE_LSM) { + ret = bpf_lsm_verify_prog(&env->log, prog); + if (ret < 0) + return ret; + } + if (!btf_type_is_func(t)) { verbose(env, "attach_btf_id %u is not a function\n", btf_id); @@ -9940,7 +10595,6 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) tr = bpf_trampoline_lookup(key); if (!tr) return -ENOMEM; - prog->aux->attach_func_name = tname; /* t is either vmlinux type or another program's type */ prog->aux->attach_func_proto = t; mutex_lock(&tr->mutex); @@ -9973,6 +10627,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) } tr->func.addr = (void *)addr; prog->aux->trampoline = tr; + + if (prog->expected_attach_type == BPF_MODIFY_RETURN) + ret = check_attach_modify_return(env); out: mutex_unlock(&tr->mutex); if (ret) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index f2d7cea86ffe..191c329e482a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -38,10 +38,7 @@ static bool cgroup_no_v1_named; */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; -/* - * Protects cgroup_subsys->release_agent_path. Modifying it also requires - * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. - */ +/* protects cgroup_subsys->release_agent_path */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) @@ -775,22 +772,29 @@ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); - char *pathbuf = NULL, *agentbuf = NULL; + char *pathbuf, *agentbuf; char *argv[3], *envp[3]; int ret; - mutex_lock(&cgroup_mutex); + /* snoop agent path and exit early if empty */ + if (!cgrp->root->release_agent_path[0]) + return; + /* prepare argument buffers */ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); - agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!pathbuf || !agentbuf || !strlen(agentbuf)) - goto out; + agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathbuf || !agentbuf) + goto out_free; - spin_lock_irq(&css_set_lock); - ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); - spin_unlock_irq(&css_set_lock); + spin_lock(&release_agent_path_lock); + strlcpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); + spin_unlock(&release_agent_path_lock); + if (!agentbuf[0]) + goto out_free; + + ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); if (ret < 0 || ret >= PATH_MAX) - goto out; + goto out_free; argv[0] = agentbuf; argv[1] = pathbuf; @@ -801,11 +805,7 @@ void cgroup1_release_agent(struct work_struct *work) envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; - mutex_unlock(&cgroup_mutex); call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); - goto out_free; -out: - mutex_unlock(&cgroup_mutex); out_free: kfree(agentbuf); kfree(pathbuf); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 3dead0416b91..06b5ea9d899d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1813,12 +1813,14 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, enum cgroup2_param { Opt_nsdelegate, Opt_memory_localevents, + Opt_memory_recursiveprot, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("memory_localevents", Opt_memory_localevents), + fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), {} }; @@ -1839,6 +1841,9 @@ static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; + case Opt_memory_recursiveprot: + ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; + return 0; } return -EINVAL; } @@ -1855,6 +1860,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; + + if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) + cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; + else + cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; } } @@ -1864,6 +1874,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); + if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) + seq_puts(seq, ",memory_recursiveprot"); return 0; } @@ -1954,7 +1966,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | - KERNFS_ROOT_SUPPORT_EXPORTOP, + KERNFS_ROOT_SUPPORT_EXPORTOP | + KERNFS_ROOT_SUPPORT_USER_XATTR, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); @@ -2714,11 +2727,7 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; - int ret; - - ret = cgroup_migrate_vet_dst(dst_cgrp); - if (ret) - return ret; + int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); @@ -4148,7 +4157,8 @@ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { - list_for_each_entry_rcu(next, &parent->children, sibling) + list_for_each_entry_rcu(next, &parent->children, sibling, + lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } @@ -4391,29 +4401,24 @@ static void css_task_iter_advance_css_set(struct css_task_iter *it) lockdep_assert_held(&css_set_lock); - /* Advance to the next non-empty css_set */ - do { - cset = css_task_iter_next_css_set(it); - if (!cset) { - it->task_pos = NULL; - return; + /* Advance to the next non-empty css_set and find first non-empty tasks list*/ + while ((cset = css_task_iter_next_css_set(it))) { + if (!list_empty(&cset->tasks)) { + it->cur_tasks_head = &cset->tasks; + break; + } else if (!list_empty(&cset->mg_tasks)) { + it->cur_tasks_head = &cset->mg_tasks; + break; + } else if (!list_empty(&cset->dying_tasks)) { + it->cur_tasks_head = &cset->dying_tasks; + break; } - } while (!css_set_populated(cset) && list_empty(&cset->dying_tasks)); - - if (!list_empty(&cset->tasks)) { - it->task_pos = cset->tasks.next; - it->cur_tasks_head = &cset->tasks; - } else if (!list_empty(&cset->mg_tasks)) { - it->task_pos = cset->mg_tasks.next; - it->cur_tasks_head = &cset->mg_tasks; - } else { - it->task_pos = cset->dying_tasks.next; - it->cur_tasks_head = &cset->dying_tasks; } - - it->tasks_head = &cset->tasks; - it->mg_tasks_head = &cset->mg_tasks; - it->dying_tasks_head = &cset->dying_tasks; + if (!cset) { + it->task_pos = NULL; + return; + } + it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus @@ -4458,24 +4463,24 @@ static void css_task_iter_advance(struct css_task_iter *it) repeat: if (it->task_pos) { /* - * Advance iterator to find next entry. cset->tasks is - * consumed first and then ->mg_tasks. After ->mg_tasks, - * we move onto the next cset. + * Advance iterator to find next entry. We go through cset + * tasks, mg_tasks and dying_tasks, when consumed we move onto + * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; - if (it->task_pos == it->tasks_head) { - it->task_pos = it->mg_tasks_head->next; - it->cur_tasks_head = it->mg_tasks_head; + if (it->task_pos == &it->cur_cset->tasks) { + it->cur_tasks_head = &it->cur_cset->mg_tasks; + it->task_pos = it->cur_tasks_head->next; } - if (it->task_pos == it->mg_tasks_head) { - it->task_pos = it->dying_tasks_head->next; - it->cur_tasks_head = it->dying_tasks_head; + if (it->task_pos == &it->cur_cset->mg_tasks) { + it->cur_tasks_head = &it->cur_cset->dying_tasks; + it->task_pos = it->cur_tasks_head->next; } - if (it->task_pos == it->dying_tasks_head) + if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ @@ -4493,12 +4498,12 @@ repeat: goto repeat; /* and dying leaders w/o live member threads */ - if (it->cur_tasks_head == it->dying_tasks_head && + if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ - if (it->cur_tasks_head == it->dying_tasks_head) + if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } @@ -4662,13 +4667,28 @@ static int cgroup_procs_show(struct seq_file *s, void *v) return 0; } +static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) +{ + int ret; + struct inode *inode; + + lockdep_assert_held(&cgroup_mutex); + + inode = kernfs_get_inode(sb, cgrp->procs_file.kn); + if (!inode) + return -ENOMEM; + + ret = inode_permission(inode, MAY_WRITE); + iput(inode); + return ret; +} + static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb) { struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *com_cgrp = src_cgrp; - struct inode *inode; int ret; lockdep_assert_held(&cgroup_mutex); @@ -4678,12 +4698,7 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp, com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ - inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn); - if (!inode) - return -ENOMEM; - - ret = inode_permission(inode, MAY_WRITE); - iput(inode); + ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; @@ -4699,6 +4714,26 @@ static int cgroup_procs_write_permission(struct cgroup *src_cgrp, return 0; } +static int cgroup_attach_permissions(struct cgroup *src_cgrp, + struct cgroup *dst_cgrp, + struct super_block *sb, bool threadgroup) +{ + int ret = 0; + + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb); + if (ret) + return ret; + + ret = cgroup_migrate_vet_dst(dst_cgrp); + if (ret) + return ret; + + if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) + ret = -EOPNOTSUPP; + + return ret; +} + static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { @@ -4721,8 +4756,8 @@ static ssize_t cgroup_procs_write(struct kernfs_open_file *of, src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); - ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, + of->file->f_path.dentry->d_sb, true); if (ret) goto out_finish; @@ -4766,16 +4801,11 @@ static ssize_t cgroup_threads_write(struct kernfs_open_file *of, spin_unlock_irq(&css_set_lock); /* thread migrations follow the cgroup.procs delegation rule */ - ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, + of->file->f_path.dentry->d_sb, false); if (ret) goto out_finish; - /* and must be contained in the same domain */ - ret = -EOPNOTSUPP; - if (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp) - goto out_finish; - ret = cgroup_attach_task(dst_cgrp, task, false); out_finish: @@ -5864,8 +5894,7 @@ out: * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() - * attaches it to the parent's css_set. Empty cg_list indicates that - * @child isn't holding reference to its css_set. + * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { @@ -5873,21 +5902,172 @@ void cgroup_fork(struct task_struct *child) INIT_LIST_HEAD(&child->cg_list); } +static struct cgroup *cgroup_get_from_file(struct file *f) +{ + struct cgroup_subsys_state *css; + struct cgroup *cgrp; + + css = css_tryget_online_from_dir(f->f_path.dentry, NULL); + if (IS_ERR(css)) + return ERR_CAST(css); + + cgrp = css->cgroup; + if (!cgroup_on_dfl(cgrp)) { + cgroup_put(cgrp); + return ERR_PTR(-EBADF); + } + + return cgrp; +} + +/** + * cgroup_css_set_fork - find or create a css_set for a child process + * @kargs: the arguments passed to create the child process + * + * This functions finds or creates a new css_set which the child + * process will be attached to in cgroup_post_fork(). By default, + * the child process will be given the same css_set as its parent. + * + * If CLONE_INTO_CGROUP is specified this function will try to find an + * existing css_set which includes the requested cgroup and if not create + * a new css_set that the child will be attached to later. If this function + * succeeds it will hold cgroup_threadgroup_rwsem on return. If + * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex + * before grabbing cgroup_threadgroup_rwsem and will hold a reference + * to the target cgroup. + */ +static int cgroup_css_set_fork(struct kernel_clone_args *kargs) + __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) +{ + int ret; + struct cgroup *dst_cgrp = NULL; + struct css_set *cset; + struct super_block *sb; + struct file *f; + + if (kargs->flags & CLONE_INTO_CGROUP) + mutex_lock(&cgroup_mutex); + + cgroup_threadgroup_change_begin(current); + + spin_lock_irq(&css_set_lock); + cset = task_css_set(current); + get_css_set(cset); + spin_unlock_irq(&css_set_lock); + + if (!(kargs->flags & CLONE_INTO_CGROUP)) { + kargs->cset = cset; + return 0; + } + + f = fget_raw(kargs->cgroup); + if (!f) { + ret = -EBADF; + goto err; + } + sb = f->f_path.dentry->d_sb; + + dst_cgrp = cgroup_get_from_file(f); + if (IS_ERR(dst_cgrp)) { + ret = PTR_ERR(dst_cgrp); + dst_cgrp = NULL; + goto err; + } + + if (cgroup_is_dead(dst_cgrp)) { + ret = -ENODEV; + goto err; + } + + /* + * Verify that we the target cgroup is writable for us. This is + * usually done by the vfs layer but since we're not going through + * the vfs layer here we need to do it "manually". + */ + ret = cgroup_may_write(dst_cgrp, sb); + if (ret) + goto err; + + ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, + !(kargs->flags & CLONE_THREAD)); + if (ret) + goto err; + + kargs->cset = find_css_set(cset, dst_cgrp); + if (!kargs->cset) { + ret = -ENOMEM; + goto err; + } + + put_css_set(cset); + fput(f); + kargs->cgrp = dst_cgrp; + return ret; + +err: + cgroup_threadgroup_change_end(current); + mutex_unlock(&cgroup_mutex); + if (f) + fput(f); + if (dst_cgrp) + cgroup_put(dst_cgrp); + put_css_set(cset); + if (kargs->cset) + put_css_set(kargs->cset); + return ret; +} + +/** + * cgroup_css_set_put_fork - drop references we took during fork + * @kargs: the arguments passed to create the child process + * + * Drop references to the prepared css_set and target cgroup if + * CLONE_INTO_CGROUP was requested. + */ +static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) + __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) +{ + cgroup_threadgroup_change_end(current); + + if (kargs->flags & CLONE_INTO_CGROUP) { + struct cgroup *cgrp = kargs->cgrp; + struct css_set *cset = kargs->cset; + + mutex_unlock(&cgroup_mutex); + + if (cset) { + put_css_set(cset); + kargs->cset = NULL; + } + + if (cgrp) { + cgroup_put(cgrp); + kargs->cgrp = NULL; + } + } +} + /** * cgroup_can_fork - called on a new task before the process is exposed - * @child: the task in question. + * @child: the child process * - * This calls the subsystem can_fork() callbacks. If the can_fork() callback - * returns an error, the fork aborts with that error code. This allows for - * a cgroup subsystem to conditionally allow or deny new forks. + * This prepares a new css_set for the child process which the child will + * be attached to in cgroup_post_fork(). + * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() + * callback returns an error, the fork aborts with that error code. This + * allows for a cgroup subsystem to conditionally allow or deny new forks. */ -int cgroup_can_fork(struct task_struct *child) +int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; + ret = cgroup_css_set_fork(kargs); + if (ret) + return ret; + do_each_subsys_mask(ss, i, have_canfork_callback) { - ret = ss->can_fork(child); + ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); @@ -5899,54 +6079,64 @@ out_revert: if (j >= i) break; if (ss->cancel_fork) - ss->cancel_fork(child); + ss->cancel_fork(child, kargs->cset); } + cgroup_css_set_put_fork(kargs); + return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() - * @child: the task in question + * @child: the child process + * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* - * cgroup_can_fork() succeded. + * cgroup_can_fork() succeded and cleans up references we took to + * prepare a new css_set for the child process in cgroup_can_fork(). */ -void cgroup_cancel_fork(struct task_struct *child) +void cgroup_cancel_fork(struct task_struct *child, + struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) - ss->cancel_fork(child); + ss->cancel_fork(child, kargs->cset); + + cgroup_css_set_put_fork(kargs); } /** - * cgroup_post_fork - called on a new task after adding it to the task list - * @child: the task in question - * - * Adds the task to the list running through its css_set if necessary and - * call the subsystem fork() callbacks. Has to be after the task is - * visible on the task list in case we race with the first call to - * cgroup_task_iter_start() - to guarantee that the new task ends up on its - * list. + * cgroup_post_fork - finalize cgroup setup for the child process + * @child: the child process + * + * Attach the child process to its css_set calling the subsystem fork() + * callbacks. */ -void cgroup_post_fork(struct task_struct *child) +void cgroup_post_fork(struct task_struct *child, + struct kernel_clone_args *kargs) + __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { struct cgroup_subsys *ss; struct css_set *cset; int i; + cset = kargs->cset; + kargs->cset = NULL; + spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { WARN_ON_ONCE(!list_empty(&child->cg_list)); - cset = task_css_set(current); /* current is @child's parent */ - get_css_set(cset); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); + } else { + put_css_set(cset); + cset = NULL; } /* @@ -5978,6 +6168,17 @@ void cgroup_post_fork(struct task_struct *child) do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); + + /* Make the new cset the root_cset of the new cgroup namespace. */ + if (kargs->flags & CLONE_NEWCGROUP) { + struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; + + get_css_set(cset); + child->nsproxy->cgroup_ns->root_cset = cset; + put_css_set(rcset); + } + + cgroup_css_set_put_fork(kargs); } /** @@ -6164,7 +6365,6 @@ EXPORT_SYMBOL_GPL(cgroup_get_from_path); */ struct cgroup *cgroup_get_from_fd(int fd) { - struct cgroup_subsys_state *css; struct cgroup *cgrp; struct file *f; @@ -6172,17 +6372,8 @@ struct cgroup *cgroup_get_from_fd(int fd) if (!f) return ERR_PTR(-EBADF); - css = css_tryget_online_from_dir(f->f_path.dentry, NULL); + cgrp = cgroup_get_from_file(f); fput(f); - if (IS_ERR(css)) - return ERR_CAST(css); - - cgrp = css->cgroup; - if (!cgroup_on_dfl(cgrp)) { - cgroup_put(cgrp); - return ERR_PTR(-EBADF); - } - return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); @@ -6303,27 +6494,58 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_prog *replace_prog, enum bpf_attach_type type, +int cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, + enum bpf_attach_type type, u32 flags) { int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, type, flags); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); mutex_unlock(&cgroup_mutex); return ret; } + +int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog, + struct bpf_prog *new_prog) +{ + struct bpf_cgroup_link *cg_link; + int ret; + + if (link->ops != &bpf_cgroup_link_lops) + return -EINVAL; + + cg_link = container_of(link, struct bpf_cgroup_link, link); + + mutex_lock(&cgroup_mutex); + /* link might have been auto-released by dying cgroup, so fail */ + if (!cg_link->cgroup) { + ret = -EINVAL; + goto out_unlock; + } + if (old_prog && link->prog != old_prog) { + ret = -EPERM; + goto out_unlock; + } + ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); +out_unlock: + mutex_unlock(&cgroup_mutex); + return ret; +} + int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags) + enum bpf_attach_type type) { int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, type); + ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); mutex_unlock(&cgroup_mutex); return ret; } + int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { @@ -6381,7 +6603,10 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "nsdelegate\nmemory_localevents\n"); + return snprintf(buf, PAGE_SIZE, + "nsdelegate\n" + "memory_localevents\n" + "memory_recursiveprot\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 58f5073acff7..729d3a5c772e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -358,8 +358,12 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* - * Cgroup v2 behavior is used when on default hierarchy or the - * cgroup_v2_mode flag is set. + * Cgroup v2 behavior is used on the "cpus" and "mems" control files when + * on default hierarchy or when the cpuset_v2_mode flag is set by mounting + * the v1 cpuset cgroup filesystem with the "cpuset_v2_mode" mount option. + * With v2 behavior, "cpus" and "mems" are always what the users have + * requested and won't be changed by hotplug events. Only the effective + * cpus or mems will be affected. */ static inline bool is_in_v2_mode(void) { diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 138059eb730d..511af87f685e 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -33,6 +33,7 @@ #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/slab.h> +#include <linux/sched/task.h> #define PIDS_MAX (PID_MAX_LIMIT + 1ULL) #define PIDS_MAX_STR "max" @@ -214,13 +215,16 @@ static void pids_cancel_attach(struct cgroup_taskset *tset) * task_css_check(true) in pids_can_fork() and pids_cancel_fork() relies * on cgroup_threadgroup_change_begin() held by the copy_process(). */ -static int pids_can_fork(struct task_struct *task) +static int pids_can_fork(struct task_struct *task, struct css_set *cset) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; int err; - css = task_css_check(current, pids_cgrp_id, true); + if (cset) + css = cset->subsys[pids_cgrp_id]; + else + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); err = pids_try_charge(pids, 1); if (err) { @@ -235,12 +239,15 @@ static int pids_can_fork(struct task_struct *task) return err; } -static void pids_cancel_fork(struct task_struct *task) +static void pids_cancel_fork(struct task_struct *task, struct css_set *cset) { struct cgroup_subsys_state *css; struct pids_cgroup *pids; - css = task_css_check(current, pids_cgrp_id, true); + if (cset) + css = cset->subsys[pids_cgrp_id]; + else + css = task_css_check(current, pids_cgrp_id, true); pids = css_pids(css); pids_uncharge(pids, 1); } diff --git a/kernel/cred.c b/kernel/cred.c index 809a985b1793..71a792616917 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -675,8 +675,6 @@ void __init cred_init(void) * The caller may change these controls afterwards if desired. * * Returns the new credentials or NULL if out of memory. - * - * Does not take, and does not return holding current->cred_replace_mutex. */ struct cred *prepare_kernel_cred(struct task_struct *daemon) { diff --git a/kernel/debug/kdb/.gitignore b/kernel/debug/kdb/.gitignore index 396d12eda9e8..df259542a236 100644 --- a/kernel/debug/kdb/.gitignore +++ b/kernel/debug/kdb/.gitignore @@ -1 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only gen-kdb_cmds.c diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index ba12e9f4661e..515379cbf209 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -399,6 +399,13 @@ int kdb_set(int argc, const char **argv) return KDB_ARGCOUNT; /* + * Censor sensitive variables + */ + if (strcmp(argv[1], "PROMPT") == 0 && + !kdb_check_flags(KDB_ENABLE_MEM_READ, kdb_cmd_enabled, false)) + return KDB_NOPERM; + + /* * Check for internal variables */ if (strcmp(argv[1], "KDBDEBUG") == 0) { @@ -1102,12 +1109,12 @@ static int handle_ctrl_cmd(char *cmd) case CTRL_P: if (cmdptr != cmd_tail) cmdptr = (cmdptr-1) % KDB_CMD_HISTORY_COUNT; - strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); return 1; case CTRL_N: if (cmdptr != cmd_head) cmdptr = (cmdptr+1) % KDB_CMD_HISTORY_COUNT; - strncpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); + strscpy(cmd_cur, cmd_hist[cmdptr], CMD_BUFLEN); return 1; } return 0; @@ -1298,12 +1305,9 @@ static int kdb_local(kdb_reason_t reason, int error, struct pt_regs *regs, *(cmd_hist[cmd_head]) = '\0'; do_full_getstr: -#if defined(CONFIG_SMP) + /* PROMPT can only be set if we have MEM_READ permission. */ snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT"), raw_smp_processor_id()); -#else - snprintf(kdb_prompt_str, CMD_BUFLEN, kdbgetenv("PROMPT")); -#endif if (defcmd_in_progress) strncat(kdb_prompt_str, "[defcmd]", CMD_BUFLEN); @@ -1314,7 +1318,7 @@ do_full_getstr: if (*cmdbuf != '\n') { if (*cmdbuf < 32) { if (cmdptr == cmd_head) { - strncpy(cmd_hist[cmd_head], cmd_cur, + strscpy(cmd_hist[cmd_head], cmd_cur, CMD_BUFLEN); *(cmd_hist[cmd_head] + strlen(cmd_hist[cmd_head])-1) = '\0'; @@ -1324,7 +1328,7 @@ do_full_getstr: cmdbuf = cmd_cur; goto do_full_getstr; } else { - strncpy(cmd_hist[cmd_head], cmd_cur, + strscpy(cmd_hist[cmd_head], cmd_cur, CMD_BUFLEN); } diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c index 551b0eb7028a..2a0c4985f38e 100644 --- a/kernel/dma/coherent.c +++ b/kernel/dma/coherent.c @@ -134,7 +134,7 @@ static void *__dma_alloc_from_coherent(struct device *dev, spin_lock_irqsave(&mem->spinlock, flags); - if (unlikely(size > (mem->size << PAGE_SHIFT))) + if (unlikely(size > ((dma_addr_t)mem->size << PAGE_SHIFT))) goto err; pageno = bitmap_find_free_region(mem->bitmap, mem->size, order); @@ -144,8 +144,9 @@ static void *__dma_alloc_from_coherent(struct device *dev, /* * Memory was found in the coherent area. */ - *dma_handle = dma_get_device_base(dev, mem) + (pageno << PAGE_SHIFT); - ret = mem->virt_base + (pageno << PAGE_SHIFT); + *dma_handle = dma_get_device_base(dev, mem) + + ((dma_addr_t)pageno << PAGE_SHIFT); + ret = mem->virt_base + ((dma_addr_t)pageno << PAGE_SHIFT); spin_unlock_irqrestore(&mem->spinlock, flags); memset(ret, 0, size); return ret; @@ -194,7 +195,7 @@ static int __dma_release_from_coherent(struct dma_coherent_mem *mem, int order, void *vaddr) { if (mem && vaddr >= mem->virt_base && vaddr < - (mem->virt_base + (mem->size << PAGE_SHIFT))) { + (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; unsigned long flags; @@ -238,10 +239,10 @@ static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem, struct vm_area_struct *vma, void *vaddr, size_t size, int *ret) { if (mem && vaddr >= mem->virt_base && vaddr + size <= - (mem->virt_base + (mem->size << PAGE_SHIFT))) { + (mem->virt_base + ((dma_addr_t)mem->size << PAGE_SHIFT))) { unsigned long off = vma->vm_pgoff; int start = (vaddr - mem->virt_base) >> PAGE_SHIFT; - int user_count = vma_pages(vma); + unsigned long user_count = vma_pages(vma); int count = PAGE_ALIGN(size) >> PAGE_SHIFT; *ret = -ENXIO; diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index ac7956c38f69..a8560052a915 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -157,11 +157,8 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, ret = dma_common_contiguous_remap(page, PAGE_ALIGN(size), dma_pgprot(dev, PAGE_KERNEL, attrs), __builtin_return_address(0)); - if (!ret) { - dma_free_contiguous(dev, page, size); - return ret; - } - + if (!ret) + goto out_free_pages; memset(ret, 0, size); goto done; } @@ -174,8 +171,7 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, * so log an error and fail. */ dev_info(dev, "Rejecting highmem page from CMA.\n"); - dma_free_contiguous(dev, page, size); - return NULL; + goto out_free_pages; } ret = page_address(page); @@ -184,10 +180,12 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, memset(ret, 0, size); - if (IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && + if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && dma_alloc_need_uncached(dev, attrs)) { arch_dma_prep_coherent(page, size); - ret = uncached_kernel_address(ret); + ret = arch_dma_set_uncached(ret, size); + if (IS_ERR(ret)) + goto out_free_pages; } done: if (force_dma_unencrypted(dev)) @@ -195,6 +193,9 @@ done: else *dma_handle = phys_to_dma(dev, page_to_phys(page)); return ret; +out_free_pages: + dma_free_contiguous(dev, page, size); + return NULL; } void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, @@ -218,6 +219,8 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, if (IS_ENABLED(CONFIG_DMA_REMAP) && is_vmalloc_addr(cpu_addr)) vunmap(cpu_addr); + else if (IS_ENABLED(CONFIG_ARCH_HAS_DMA_CLEAR_UNCACHED)) + arch_dma_clear_uncached(cpu_addr, size); dma_free_contiguous(dev, dma_direct_to_page(dev, dma_addr), size); } @@ -225,7 +228,7 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr, void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && dma_alloc_need_uncached(dev, attrs)) return arch_dma_alloc(dev, size, dma_handle, gfp, attrs); @@ -235,7 +238,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_addr, unsigned long attrs) { - if (!IS_ENABLED(CONFIG_ARCH_HAS_UNCACHED_SEGMENT) && + if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) && !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && dma_alloc_need_uncached(dev, attrs)) arch_dma_free(dev, size, cpu_addr, dma_addr, attrs); diff --git a/kernel/events/core.c b/kernel/events/core.c index 1569979c8912..81e6d80cb219 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1296,7 +1296,7 @@ static void put_ctx(struct perf_event_context *ctx) * function. * * Lock order: - * cred_guard_mutex + * exec_update_mutex * task_struct::perf_event_mutex * perf_event_context::mutex * perf_event::child_mutex; @@ -8535,23 +8535,22 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog, enum perf_bpf_event_type type) { bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD; - char sym[KSYM_NAME_LEN]; int i; if (prog->aux->func_cnt == 0) { - bpf_get_prog_name(prog, sym); perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)prog->bpf_func, - prog->jited_len, unregister, sym); + prog->jited_len, unregister, + prog->aux->ksym.name); } else { for (i = 0; i < prog->aux->func_cnt; i++) { struct bpf_prog *subprog = prog->aux->func[i]; - bpf_get_prog_name(subprog, sym); perf_event_ksymbol( PERF_RECORD_KSYMBOL_TYPE_BPF, (u64)(unsigned long)subprog->bpf_func, - subprog->jited_len, unregister, sym); + subprog->jited_len, unregister, + prog->aux->ksym.name); } } } @@ -9486,7 +9485,6 @@ static void bpf_overflow_handler(struct perf_event *event, int ret = 0; ctx.regs = perf_arch_bpf_user_pt_regs(regs); - preempt_disable(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) goto out; rcu_read_lock(); @@ -9494,7 +9492,6 @@ static void bpf_overflow_handler(struct perf_event *event, rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); - preempt_enable(); if (!ret) return; @@ -11554,14 +11551,14 @@ SYSCALL_DEFINE5(perf_event_open, } if (task) { - err = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + err = mutex_lock_interruptible(&task->signal->exec_update_mutex); if (err) goto err_task; /* * Reuse ptrace permission checks for now. * - * We must hold cred_guard_mutex across this and any potential + * We must hold exec_update_mutex across this and any potential * perf_install_in_context() call for this new event to * serialize against exec() altering our credentials (and the * perf_event_exit_task() that could imply). @@ -11850,7 +11847,7 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(&ctx->mutex); if (task) { - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); put_task_struct(task); } @@ -11886,7 +11883,7 @@ err_alloc: free_event(event); err_cred: if (task) - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); err_task: if (task) put_task_struct(task); @@ -12191,7 +12188,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) /* * When a child task exits, feed back event values to parent events. * - * Can be called with cred_guard_mutex held when called from + * Can be called with exec_update_mutex held when called from * install_exec_creds(). */ void perf_event_exit_task(struct task_struct *child) diff --git a/kernel/exit.c b/kernel/exit.c index d70d47159640..389a88cb3081 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -182,6 +182,7 @@ void put_task_struct_rcu_user(struct task_struct *task) void release_task(struct task_struct *p) { struct task_struct *leader; + struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and @@ -190,11 +191,11 @@ repeat: atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); - proc_flush_task(p); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); + thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* @@ -217,6 +218,7 @@ repeat: } write_unlock_irq(&tasklist_lock); + proc_flush_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); diff --git a/kernel/extable.c b/kernel/extable.c index a0024f27d3a1..7681f87e89dd 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -149,8 +149,6 @@ int kernel_text_address(unsigned long addr) goto out; if (is_bpf_text_address(addr)) goto out; - if (is_bpf_image_address(addr)) - goto out; ret = 0; out: if (no_rcu) diff --git a/kernel/fork.c b/kernel/fork.c index d90af13431c7..d2a967bf85d5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -281,7 +281,7 @@ static inline void free_thread_stack(struct task_struct *tsk) MEMCG_KERNEL_STACK_KB, -(int)(PAGE_SIZE / 1024)); - memcg_kmem_uncharge(vm->pages[i], 0); + memcg_kmem_uncharge_page(vm->pages[i], 0); } for (i = 0; i < NR_CACHED_STACKS; i++) { @@ -413,12 +413,13 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk) for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { /* - * If memcg_kmem_charge() fails, page->mem_cgroup - * pointer is NULL, and both memcg_kmem_uncharge() + * If memcg_kmem_charge_page() fails, page->mem_cgroup + * pointer is NULL, and both memcg_kmem_uncharge_page() * and mod_memcg_page_state() in free_thread_stack() * will ignore this page. So it's safe. */ - ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0); + ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, + 0); if (ret) return ret; @@ -1224,7 +1225,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) struct mm_struct *mm; int err; - err = mutex_lock_killable(&task->signal->cred_guard_mutex); + err = mutex_lock_killable(&task->signal->exec_update_mutex); if (err) return ERR_PTR(err); @@ -1234,7 +1235,7 @@ struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) mmput(mm); mm = ERR_PTR(-EACCES); } - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return mm; } @@ -1594,6 +1595,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); + mutex_init(&sig->exec_update_mutex); return 0; } @@ -2174,16 +2176,15 @@ static __latent_entropy struct task_struct *copy_process( INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; - cgroup_threadgroup_change_begin(current); /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted the the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ - retval = cgroup_can_fork(p); + retval = cgroup_can_fork(p, args); if (retval) - goto bad_fork_cgroup_threadgroup_change_end; + goto bad_fork_put_pidfd; /* * From this point on we must avoid any synchronous user-space @@ -2288,8 +2289,7 @@ static __latent_entropy struct task_struct *copy_process( write_unlock_irq(&tasklist_lock); proc_fork_connector(p); - cgroup_post_fork(p); - cgroup_threadgroup_change_end(current); + cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); @@ -2300,9 +2300,7 @@ static __latent_entropy struct task_struct *copy_process( bad_fork_cancel_cgroup: spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); - cgroup_cancel_fork(p); -bad_fork_cgroup_threadgroup_change_end: - cgroup_threadgroup_change_end(current); + cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); @@ -2631,6 +2629,9 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, !valid_signal(args.exit_signal))) return -EINVAL; + if ((args.flags & CLONE_INTO_CGROUP) && args.cgroup < 0) + return -EINVAL; + *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), @@ -2641,6 +2642,7 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, + .cgroup = args.cgroup, }; if (args.set_tid && @@ -2684,7 +2686,8 @@ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ - if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND)) + if (kargs->flags & + ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* diff --git a/kernel/kcmp.c b/kernel/kcmp.c index a0e3d7a0e8b8..b3ff9288c6cc 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -173,8 +173,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, /* * One should have enough rights to inspect task details. */ - ret = kcmp_lock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + ret = kcmp_lock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); if (ret) goto err; if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) || @@ -229,8 +229,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type, } err_unlock: - kcmp_unlock(&task1->signal->cred_guard_mutex, - &task2->signal->cred_guard_mutex); + kcmp_unlock(&task1->signal->exec_update_mutex, + &task2->signal->exec_update_mutex); err: put_task_struct(task1); put_task_struct(task2); diff --git a/kernel/padata.c b/kernel/padata.c index 72777c10bb9c..a6afa12fb75e 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -512,7 +512,7 @@ static int padata_replace_one(struct padata_shell *ps) static int padata_replace(struct padata_instance *pinst) { struct padata_shell *ps; - int err; + int err = 0; pinst->flags |= PADATA_RESET; @@ -1038,12 +1038,13 @@ EXPORT_SYMBOL(padata_alloc_shell); */ void padata_free_shell(struct padata_shell *ps) { - struct padata_instance *pinst = ps->pinst; + if (!ps) + return; - mutex_lock(&pinst->lock); + mutex_lock(&ps->pinst->lock); list_del(&ps->list); padata_free_pd(rcu_dereference_protected(ps->pd, 1)); - mutex_unlock(&pinst->lock); + mutex_unlock(&ps->pinst->lock); kfree(ps); } diff --git a/kernel/pid.c b/kernel/pid.c index 647b4bb457b5..bc21c0fb26d8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -144,9 +144,6 @@ void free_pid(struct pid *pid) /* Handle a fork failure of the first process */ WARN_ON(ns->child_reaper); ns->pid_allocated = 0; - /* fall through */ - case 0: - schedule_work(&ns->proc_work); break; } @@ -257,17 +254,13 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, */ retval = -ENOMEM; - if (unlikely(is_child_reaper(pid))) { - if (pid_ns_prepare_proc(ns)) - goto out_free; - } - get_pid_ns(ns); refcount_set(&pid->count, 1); for (type = 0; type < PIDTYPE_MAX; ++type) INIT_HLIST_HEAD(&pid->tasks[type]); init_waitqueue_head(&pid->wait_pidfd); + INIT_HLIST_HEAD(&pid->inodes); upid = pid->numbers + ns->level; spin_lock_irq(&pidmap_lock); @@ -594,7 +587,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) struct file *file; int ret; - ret = mutex_lock_killable(&task->signal->cred_guard_mutex); + ret = mutex_lock_killable(&task->signal->exec_update_mutex); if (ret) return ERR_PTR(ret); @@ -603,7 +596,7 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) else file = ERR_PTR(-EPERM); - mutex_unlock(&task->signal->cred_guard_mutex); + mutex_unlock(&task->signal->exec_update_mutex); return file ?: ERR_PTR(-EBADF); } diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index d40017e79ebe..01f8ba32cc0c 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -57,12 +57,6 @@ static struct kmem_cache *create_pid_cachep(unsigned int level) return READ_ONCE(*pkc); } -static void proc_cleanup_work(struct work_struct *work) -{ - struct pid_namespace *ns = container_of(work, struct pid_namespace, proc_work); - pid_ns_release_proc(ns); -} - static struct ucounts *inc_pid_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES); @@ -114,7 +108,6 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; ns->pid_allocated = PIDNS_ADDING; - INIT_WORK(&ns->proc_work, proc_cleanup_work); return ns; @@ -231,20 +224,27 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) } while (rc != -ECHILD); /* - * kernel_wait4() above can't reap the EXIT_DEAD children but we do not - * really care, we could reparent them to the global init. We could - * exit and reap ->child_reaper even if it is not the last thread in - * this pid_ns, free_pid(pid_allocated == 0) calls proc_cleanup_work(), - * pid_ns can not go away until proc_kill_sb() drops the reference. + * kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE + * process whose parents processes are outside of the pid + * namespace. Such processes are created with setns()+fork(). + * + * If those EXIT_ZOMBIE processes are not reaped by their + * parents before their parents exit, they will be reparented + * to pid_ns->child_reaper. Thus pidns->child_reaper needs to + * stay valid until they all go away. + * + * The code relies on the the pid_ns->child_reaper ignoring + * SIGCHILD to cause those EXIT_ZOMBIE processes to be + * autoreaped if reparented. * - * But this ns can also have other tasks injected by setns()+fork(). - * Again, ignoring the user visible semantics we do not really need - * to wait until they are all reaped, but they can be reparented to - * us and thus we need to ensure that pid->child_reaper stays valid - * until they all go away. See free_pid()->wake_up_process(). + * Semantically it is also desirable to wait for EXIT_ZOMBIE + * processes before allowing the child_reaper to be reaped, as + * that gives the invariant that when the init process of a + * pid namespace is reaped all of the processes in the pid + * namespace are gone. * - * We rely on ignored SIGCHLD, an injected zombie must be autoreaped - * if reparented. + * Once all of the other tasks are gone from the pid_namespace + * free_pid() will awaken this task. */ for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 7cbfbeacd68a..c208566c844b 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -80,9 +80,6 @@ config HIBERNATION For more information take a look at <file:Documentation/power/swsusp.rst>. -config ARCH_SAVE_PAGE_KEYS - bool - config PM_STD_PARTITION string "Default resume partition" depends on HIBERNATION diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index d82b7b88d616..659800157b17 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1744,9 +1744,6 @@ int hibernate_preallocate_memory(void) count += highmem; count -= totalreserve_pages; - /* Add number of pages required for page keys (s390 only). */ - size += page_key_additional_pages(saveable); - /* Compute the maximum number of saveable pages to leave in memory. */ max_size = (count - (size + PAGES_FOR_IO)) / 2 - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE); @@ -2075,8 +2072,6 @@ static inline void pack_pfns(unsigned long *buf, struct memory_bitmap *bm) buf[j] = memory_bm_next_pfn(bm); if (unlikely(buf[j] == BM_END_OF_MAP)) break; - /* Save page key for data page (s390 only). */ - page_key_read(buf + j); } } @@ -2226,9 +2221,6 @@ static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm) if (unlikely(buf[j] == BM_END_OF_MAP)) break; - /* Extract and buffer page key for data page (s390 only). */ - page_key_memorize(buf + j); - if (pfn_valid(buf[j]) && memory_bm_pfn_present(bm, buf[j])) memory_bm_set_bit(bm, buf[j]); else @@ -2623,11 +2615,6 @@ int snapshot_write_next(struct snapshot_handle *handle) if (error) return error; - /* Allocate buffer for page keys. */ - error = page_key_alloc(nr_copy_pages); - if (error) - return error; - hibernate_restore_protection_begin(); } else if (handle->cur <= nr_meta_pages + 1) { error = unpack_orig_pfns(buffer, ©_bm); @@ -2649,8 +2636,6 @@ int snapshot_write_next(struct snapshot_handle *handle) } } else { copy_last_highmem_page(); - /* Restore page key for data page (s390 only). */ - page_key_write(handle->buffer); hibernate_restore_protect_page(handle->buffer); handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) @@ -2673,9 +2658,6 @@ int snapshot_write_next(struct snapshot_handle *handle) void snapshot_write_finalize(struct snapshot_handle *handle) { copy_last_highmem_page(); - /* Restore page key for data page (s390 only). */ - page_key_write(handle->buffer); - page_key_free(); hibernate_restore_protect_page(handle->buffer); /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages) { diff --git a/kernel/power/user.c b/kernel/power/user.c index 58ed9478787f..ef90eb1fb86e 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -27,8 +27,6 @@ #include "power.h" -#define SNAPSHOT_MINOR 231 - static struct snapshot_data { struct snapshot_handle handle; int swap; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index fada22dc4ab6..633f41a11d75 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1772,9 +1772,6 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, trace_console_rcuidle(text, len); - if (!console_drivers) - return; - for_each_console(con) { if (exclusive_console && con != exclusive_console) continue; @@ -2653,19 +2650,17 @@ void register_console(struct console *newcon) struct console_cmdline *c; static bool has_preferred; - if (console_drivers) - for_each_console(bcon) - if (WARN(bcon == newcon, - "console '%s%d' already registered\n", - bcon->name, bcon->index)) - return; + for_each_console(bcon) { + if (WARN(bcon == newcon, "console '%s%d' already registered\n", + bcon->name, bcon->index)) + return; + } /* * before we register a new CON_BOOT console, make sure we don't * already have a valid console */ - if (console_drivers && newcon->flags & CON_BOOT) { - /* find the last or real console */ + if (newcon->flags & CON_BOOT) { for_each_console(bcon) { if (!(bcon->flags & CON_BOOT)) { pr_info("Too late to register bootconsole %s%d\n", @@ -2813,7 +2808,7 @@ EXPORT_SYMBOL(register_console); int unregister_console(struct console *console) { - struct console *a, *b; + struct console *con; int res; pr_info("%sconsole [%s%d] disabled\n", @@ -2821,26 +2816,30 @@ int unregister_console(struct console *console) console->name, console->index); res = _braille_unregister_console(console); - if (res) + if (res < 0) return res; + if (res > 0) + return 0; - res = 1; + res = -ENODEV; console_lock(); if (console_drivers == console) { console_drivers=console->next; res = 0; - } else if (console_drivers) { - for (a=console_drivers->next, b=console_drivers ; - a; b=a, a=b->next) { - if (a == console) { - b->next = a->next; + } else { + for_each_console(con) { + if (con->next == console) { + con->next = console->next; res = 0; break; } } } - if (!res && (console->flags & CON_EXTENDED)) + if (res) + goto out_disable_unlock; + + if (console->flags & CON_EXTENDED) nr_ext_console_drivers--; /* @@ -2853,6 +2852,16 @@ int unregister_console(struct console *console) console->flags &= ~CON_ENABLED; console_unlock(); console_sysfs_notify(); + + if (console->exit) + res = console->exit(console); + + return res; + +out_disable_unlock: + console->flags &= ~CON_ENABLED; + console_unlock(); + return res; } EXPORT_SYMBOL(unregister_console); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index ec5c606bc3a1..55a6184f5990 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -268,16 +268,14 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ - preempt_disable(); for (; f; f = f->prev) { - u32 cur_ret = BPF_PROG_RUN(f->prog, sd); + u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } - preempt_enable(); return ret; } #endif /* CONFIG_SECCOMP_FILTER */ diff --git a/kernel/signal.c b/kernel/signal.c index 5b2396350dd1..e58a6c619824 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1931,7 +1931,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig) * This is only possible if parent == real_parent. * Check if it has changed security domain. */ - if (tsk->parent_exec_id != tsk->parent->self_exec_id) + if (tsk->parent_exec_id != READ_ONCE(tsk->parent->self_exec_id)) sig = SIGCHLD; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ad5b88a53c5a..8a176d8727a3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -212,6 +212,11 @@ static int proc_do_cad_pid(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); static int proc_taint(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_COMPACTION +static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, + int write, void __user *buffer, + size_t *lenp, loff_t *ppos); +#endif #endif #ifdef CONFIG_PRINTK @@ -229,25 +234,8 @@ static int proc_dopipe_max_size(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); #ifdef CONFIG_MAGIC_SYSRQ -/* Note: sysrq code uses its own private copy */ -static int __sysrq_enabled = CONFIG_MAGIC_SYSRQ_DEFAULT_ENABLE; - static int sysrq_sysctl_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) -{ - int error; - - error = proc_dointvec(table, write, buffer, lenp, ppos); - if (error) - return error; - - if (write) - sysrq_toggle_support(__sysrq_enabled); - - return 0; -} - + void __user *buffer, size_t *lenp, loff_t *ppos); #endif static struct ctl_table kern_table[]; @@ -747,7 +735,7 @@ static struct ctl_table kern_table[] = { #ifdef CONFIG_MAGIC_SYSRQ { .procname = "sysrq", - .data = &__sysrq_enabled, + .data = NULL, .maxlen = sizeof (int), .mode = 0644, .proc_handler = sysrq_sysctl_handler, @@ -1484,7 +1472,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_compact_unevictable_allowed, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax_warn_RT_change, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, @@ -2572,6 +2560,28 @@ int proc_dointvec(struct ctl_table *table, int write, return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); } +#ifdef CONFIG_COMPACTION +static int proc_dointvec_minmax_warn_RT_change(struct ctl_table *table, + int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret, old; + + if (!IS_ENABLED(CONFIG_PREEMPT_RT) || !write) + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); + + old = *(int *)table->data; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret) + return ret; + if (old != *(int *)table->data) + pr_warn_once("sysctl attribute %s changed by %s[%d]\n", + table->procname, current->comm, + task_pid_nr(current)); + return ret; +} +#endif + /** * proc_douintvec - read a vector of unsigned integers * @table: the sysctl table @@ -2835,6 +2845,26 @@ static int proc_dostring_coredump(struct ctl_table *table, int write, } #endif +#ifdef CONFIG_MAGIC_SYSRQ +static int sysrq_sysctl_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int tmp, ret; + + tmp = sysrq_mask(); + + ret = __do_proc_dointvec(&tmp, table, write, buffer, + lenp, ppos, NULL, NULL); + if (ret || !write) + return ret; + + if (write) + sysrq_toggle_support(tmp); + + return 0; +} +#endif + static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos, diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index d0a5ba37aff4..d89da1c7e005 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1480,6 +1480,7 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); + bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); @@ -1514,11 +1515,11 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); - lockdep_hrtimer_enter(timer); + expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); - lockdep_hrtimer_exit(timer); + lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 68250d433bd7..ca1796747a77 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -83,7 +83,7 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) if (in_nmi()) /* not supported yet */ return 1; - preempt_disable(); + cant_sleep(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* @@ -115,11 +115,9 @@ unsigned int trace_call_bpf(struct trace_event_call *call, void *ctx) out: __this_cpu_dec(bpf_prog_active); - preempt_enable(); return ret; } -EXPORT_SYMBOL_GPL(trace_call_bpf); #ifdef CONFIG_BPF_KPROBE_OVERRIDE BPF_CALL_2(bpf_override_return, struct pt_regs *, regs, unsigned long, rc) @@ -781,8 +779,8 @@ static const struct bpf_func_proto bpf_send_signal_thread_proto = { .arg1_type = ARG_ANYTHING, }; -static const struct bpf_func_proto * -tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +const struct bpf_func_proto * +bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -843,6 +841,10 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_send_signal_proto; case BPF_FUNC_send_signal_thread: return &bpf_send_signal_thread_proto; + case BPF_FUNC_perf_event_read_value: + return &bpf_perf_event_read_value_proto; + case BPF_FUNC_get_ns_current_pid_tgid: + return &bpf_get_ns_current_pid_tgid_proto; default: return NULL; } @@ -858,14 +860,12 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stackid_proto; case BPF_FUNC_get_stack: return &bpf_get_stack_proto; - case BPF_FUNC_perf_event_read_value: - return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE case BPF_FUNC_override_return: return &bpf_override_return_proto; #endif default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -975,7 +975,7 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_stack: return &bpf_get_stack_proto_tp; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -1028,6 +1028,45 @@ static const struct bpf_func_proto bpf_perf_prog_read_value_proto = { .arg3_type = ARG_CONST_SIZE, }; +BPF_CALL_4(bpf_read_branch_records, struct bpf_perf_event_data_kern *, ctx, + void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + struct perf_branch_stack *br_stack = ctx->data->br_stack; + u32 to_copy; + + if (unlikely(flags & ~BPF_F_GET_BRANCH_RECORDS_SIZE)) + return -EINVAL; + + if (unlikely(!br_stack)) + return -EINVAL; + + if (flags & BPF_F_GET_BRANCH_RECORDS_SIZE) + return br_stack->nr * br_entry_size; + + if (!buf || (size % br_entry_size != 0)) + return -EINVAL; + + to_copy = min_t(u32, br_stack->nr * br_entry_size, size); + memcpy(buf, br_stack->entries, to_copy); + + return to_copy; +#endif +} + +static const struct bpf_func_proto bpf_read_branch_records_proto = { + .func = bpf_read_branch_records, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1040,8 +1079,10 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; + case BPF_FUNC_read_branch_records: + return &bpf_read_branch_records_proto; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -1104,6 +1145,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { }; extern const struct bpf_func_proto bpf_skb_output_proto; +extern const struct bpf_func_proto bpf_xdp_output_proto; BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args, struct bpf_map *, map, u64, flags) @@ -1168,7 +1210,7 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_stack: return &bpf_get_stack_proto_raw_tp; default: - return tracing_func_proto(func_id, prog); + return bpf_tracing_func_proto(func_id, prog); } } @@ -1179,6 +1221,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #ifdef CONFIG_NET case BPF_FUNC_skb_output: return &bpf_skb_output_proto; + case BPF_FUNC_xdp_output: + return &bpf_xdp_output_proto; #endif default: return raw_tp_prog_func_proto(func_id, prog); @@ -1213,6 +1257,13 @@ static bool tracing_prog_is_valid_access(int off, int size, return btf_ctx_access(off, size, type, prog, info); } +int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} + const struct bpf_verifier_ops raw_tracepoint_verifier_ops = { .get_func_proto = raw_tp_prog_func_proto, .is_valid_access = raw_tp_prog_is_valid_access, @@ -1227,6 +1278,7 @@ const struct bpf_verifier_ops tracing_verifier_ops = { }; const struct bpf_prog_ops tracing_prog_ops = { + .test_run = bpf_prog_test_run_tracing, }; static bool raw_tp_writable_prog_is_valid_access(int off, int size, @@ -1475,10 +1527,9 @@ void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static __always_inline void __bpf_trace_run(struct bpf_prog *prog, u64 *args) { + cant_sleep(); rcu_read_lock(); - preempt_disable(); (void) BPF_PROG_RUN(prog, args); - preempt_enable(); rcu_read_unlock(); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fd81c7de77a7..041694a1eb74 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -102,7 +102,7 @@ static bool ftrace_pids_enabled(struct ftrace_ops *ops) tr = ops->private; - return tr->function_pids != NULL; + return tr->function_pids != NULL || tr->function_no_pids != NULL; } static void ftrace_update_trampoline(struct ftrace_ops *ops); @@ -139,13 +139,23 @@ static inline void ftrace_ops_init(struct ftrace_ops *ops) #endif } +#define FTRACE_PID_IGNORE -1 +#define FTRACE_PID_TRACE -2 + static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct pt_regs *regs) { struct trace_array *tr = op->private; + int pid; - if (tr && this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid)) - return; + if (tr) { + pid = this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid); + if (pid == FTRACE_PID_IGNORE) + return; + if (pid != FTRACE_PID_TRACE && + pid != current->pid) + return; + } op->saved_func(ip, parent_ip, op, regs); } @@ -6923,11 +6933,17 @@ ftrace_filter_pid_sched_switch_probe(void *data, bool preempt, { struct trace_array *tr = data; struct trace_pid_list *pid_list; + struct trace_pid_list *no_pid_list; pid_list = rcu_dereference_sched(tr->function_pids); + no_pid_list = rcu_dereference_sched(tr->function_no_pids); - this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, - trace_ignore_this_task(pid_list, next)); + if (trace_ignore_this_task(pid_list, no_pid_list, next)) + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, + FTRACE_PID_IGNORE); + else + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, + next->pid); } static void @@ -6940,6 +6956,9 @@ ftrace_pid_follow_sched_process_fork(void *data, pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, self, task); + + pid_list = rcu_dereference_sched(tr->function_no_pids); + trace_filter_add_remove_task(pid_list, self, task); } static void @@ -6950,6 +6969,9 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task) pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, NULL, task); + + pid_list = rcu_dereference_sched(tr->function_no_pids); + trace_filter_add_remove_task(pid_list, NULL, task); } void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) @@ -6967,42 +6989,57 @@ void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) } } -static void clear_ftrace_pids(struct trace_array *tr) +static void clear_ftrace_pids(struct trace_array *tr, int type) { struct trace_pid_list *pid_list; + struct trace_pid_list *no_pid_list; int cpu; pid_list = rcu_dereference_protected(tr->function_pids, lockdep_is_held(&ftrace_lock)); - if (!pid_list) + no_pid_list = rcu_dereference_protected(tr->function_no_pids, + lockdep_is_held(&ftrace_lock)); + + /* Make sure there's something to do */ + if (!pid_type_enabled(type, pid_list, no_pid_list)) return; - unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); + /* See if the pids still need to be checked after this */ + if (!still_need_pid_events(type, pid_list, no_pid_list)) { + unregister_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); + for_each_possible_cpu(cpu) + per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = FTRACE_PID_TRACE; + } - for_each_possible_cpu(cpu) - per_cpu_ptr(tr->array_buffer.data, cpu)->ftrace_ignore_pid = false; + if (type & TRACE_PIDS) + rcu_assign_pointer(tr->function_pids, NULL); - rcu_assign_pointer(tr->function_pids, NULL); + if (type & TRACE_NO_PIDS) + rcu_assign_pointer(tr->function_no_pids, NULL); /* Wait till all users are no longer using pid filtering */ synchronize_rcu(); - trace_free_pid_list(pid_list); + if ((type & TRACE_PIDS) && pid_list) + trace_free_pid_list(pid_list); + + if ((type & TRACE_NO_PIDS) && no_pid_list) + trace_free_pid_list(no_pid_list); } void ftrace_clear_pids(struct trace_array *tr) { mutex_lock(&ftrace_lock); - clear_ftrace_pids(tr); + clear_ftrace_pids(tr, TRACE_PIDS | TRACE_NO_PIDS); mutex_unlock(&ftrace_lock); } -static void ftrace_pid_reset(struct trace_array *tr) +static void ftrace_pid_reset(struct trace_array *tr, int type) { mutex_lock(&ftrace_lock); - clear_ftrace_pids(tr); + clear_ftrace_pids(tr, type); ftrace_update_pid_func(); ftrace_startup_all(0); @@ -7066,9 +7103,45 @@ static const struct seq_operations ftrace_pid_sops = { .show = fpid_show, }; -static int -ftrace_pid_open(struct inode *inode, struct file *file) +static void *fnpid_start(struct seq_file *m, loff_t *pos) + __acquires(RCU) +{ + struct trace_pid_list *pid_list; + struct trace_array *tr = m->private; + + mutex_lock(&ftrace_lock); + rcu_read_lock_sched(); + + pid_list = rcu_dereference_sched(tr->function_no_pids); + + if (!pid_list) + return !(*pos) ? FTRACE_NO_PIDS : NULL; + + return trace_pid_start(pid_list, pos); +} + +static void *fnpid_next(struct seq_file *m, void *v, loff_t *pos) { + struct trace_array *tr = m->private; + struct trace_pid_list *pid_list = rcu_dereference_sched(tr->function_no_pids); + + if (v == FTRACE_NO_PIDS) { + (*pos)++; + return NULL; + } + return trace_pid_next(pid_list, v, pos); +} + +static const struct seq_operations ftrace_no_pid_sops = { + .start = fnpid_start, + .next = fnpid_next, + .stop = fpid_stop, + .show = fpid_show, +}; + +static int pid_open(struct inode *inode, struct file *file, int type) +{ + const struct seq_operations *seq_ops; struct trace_array *tr = inode->i_private; struct seq_file *m; int ret = 0; @@ -7079,9 +7152,18 @@ ftrace_pid_open(struct inode *inode, struct file *file) if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_pid_reset(tr); + ftrace_pid_reset(tr, type); + + switch (type) { + case TRACE_PIDS: + seq_ops = &ftrace_pid_sops; + break; + case TRACE_NO_PIDS: + seq_ops = &ftrace_no_pid_sops; + break; + } - ret = seq_open(file, &ftrace_pid_sops); + ret = seq_open(file, seq_ops); if (ret < 0) { trace_array_put(tr); } else { @@ -7093,10 +7175,23 @@ ftrace_pid_open(struct inode *inode, struct file *file) return ret; } +static int +ftrace_pid_open(struct inode *inode, struct file *file) +{ + return pid_open(inode, file, TRACE_PIDS); +} + +static int +ftrace_no_pid_open(struct inode *inode, struct file *file) +{ + return pid_open(inode, file, TRACE_NO_PIDS); +} + static void ignore_task_cpu(void *data) { struct trace_array *tr = data; struct trace_pid_list *pid_list; + struct trace_pid_list *no_pid_list; /* * This function is called by on_each_cpu() while the @@ -7104,18 +7199,25 @@ static void ignore_task_cpu(void *data) */ pid_list = rcu_dereference_protected(tr->function_pids, mutex_is_locked(&ftrace_lock)); + no_pid_list = rcu_dereference_protected(tr->function_no_pids, + mutex_is_locked(&ftrace_lock)); - this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, - trace_ignore_this_task(pid_list, current)); + if (trace_ignore_this_task(pid_list, no_pid_list, current)) + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, + FTRACE_PID_IGNORE); + else + this_cpu_write(tr->array_buffer.data->ftrace_ignore_pid, + current->pid); } static ssize_t -ftrace_pid_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, int type) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; - struct trace_pid_list *filtered_pids = NULL; + struct trace_pid_list *filtered_pids; + struct trace_pid_list *other_pids; struct trace_pid_list *pid_list; ssize_t ret; @@ -7124,19 +7226,39 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, mutex_lock(&ftrace_lock); - filtered_pids = rcu_dereference_protected(tr->function_pids, + switch (type) { + case TRACE_PIDS: + filtered_pids = rcu_dereference_protected(tr->function_pids, + lockdep_is_held(&ftrace_lock)); + other_pids = rcu_dereference_protected(tr->function_no_pids, + lockdep_is_held(&ftrace_lock)); + break; + case TRACE_NO_PIDS: + filtered_pids = rcu_dereference_protected(tr->function_no_pids, + lockdep_is_held(&ftrace_lock)); + other_pids = rcu_dereference_protected(tr->function_pids, lockdep_is_held(&ftrace_lock)); + break; + } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) goto out; - rcu_assign_pointer(tr->function_pids, pid_list); + switch (type) { + case TRACE_PIDS: + rcu_assign_pointer(tr->function_pids, pid_list); + break; + case TRACE_NO_PIDS: + rcu_assign_pointer(tr->function_no_pids, pid_list); + break; + } + if (filtered_pids) { synchronize_rcu(); trace_free_pid_list(filtered_pids); - } else if (pid_list) { + } else if (pid_list && !other_pids) { /* Register a probe to set whether to ignore the tracing of a task */ register_trace_sched_switch(ftrace_filter_pid_sched_switch_probe, tr); } @@ -7159,6 +7281,20 @@ ftrace_pid_write(struct file *filp, const char __user *ubuf, return ret; } +static ssize_t +ftrace_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS); +} + +static ssize_t +ftrace_no_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS); +} + static int ftrace_pid_release(struct inode *inode, struct file *file) { @@ -7177,10 +7313,20 @@ static const struct file_operations ftrace_pid_fops = { .release = ftrace_pid_release, }; +static const struct file_operations ftrace_no_pid_fops = { + .open = ftrace_no_pid_open, + .write = ftrace_no_pid_write, + .read = seq_read, + .llseek = tracing_lseek, + .release = ftrace_pid_release, +}; + void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer) { trace_create_file("set_ftrace_pid", 0644, d_tracer, tr, &ftrace_pid_fops); + trace_create_file("set_ftrace_notrace_pid", 0644, d_tracer, + tr, &ftrace_no_pid_fops); } void __init ftrace_init_tracefs_toplevel(struct trace_array *tr, diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 61f0e92ace99..6f0b42ceeb00 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -441,6 +441,7 @@ enum { struct ring_buffer_per_cpu { int cpu; atomic_t record_disabled; + atomic_t resize_disabled; struct trace_buffer *buffer; raw_spinlock_t reader_lock; /* serialize readers */ arch_spinlock_t lock; @@ -484,7 +485,6 @@ struct trace_buffer { unsigned flags; int cpus; atomic_t record_disabled; - atomic_t resize_disabled; cpumask_var_t cpumask; struct lock_class_key *reader_lock_key; @@ -503,10 +503,14 @@ struct trace_buffer { struct ring_buffer_iter { struct ring_buffer_per_cpu *cpu_buffer; unsigned long head; + unsigned long next_event; struct buffer_page *head_page; struct buffer_page *cache_reader_page; unsigned long cache_read; u64 read_stamp; + u64 page_stamp; + struct ring_buffer_event *event; + int missed_events; }; /** @@ -1737,18 +1741,24 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, size = nr_pages * BUF_PAGE_SIZE; - /* - * Don't succeed if resizing is disabled, as a reader might be - * manipulating the ring buffer and is expecting a sane state while - * this is true. - */ - if (atomic_read(&buffer->resize_disabled)) - return -EBUSY; - /* prevent another thread from changing buffer sizes */ mutex_lock(&buffer->mutex); + if (cpu_id == RING_BUFFER_ALL_CPUS) { + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + for_each_buffer_cpu(buffer, cpu) { + cpu_buffer = buffer->buffers[cpu]; + if (atomic_read(&cpu_buffer->resize_disabled)) { + err = -EBUSY; + goto out_err_unlock; + } + } + /* calculate the pages to update */ for_each_buffer_cpu(buffer, cpu) { cpu_buffer = buffer->buffers[cpu]; @@ -1816,6 +1826,16 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, if (nr_pages == cpu_buffer->nr_pages) goto out; + /* + * Don't succeed if resizing is disabled, as a reader might be + * manipulating the ring buffer and is expecting a sane state while + * this is true. + */ + if (atomic_read(&cpu_buffer->resize_disabled)) { + err = -EBUSY; + goto out_err_unlock; + } + cpu_buffer->nr_pages_to_update = nr_pages - cpu_buffer->nr_pages; @@ -1885,6 +1905,7 @@ int ring_buffer_resize(struct trace_buffer *buffer, unsigned long size, free_buffer_page(bpage); } } + out_err_unlock: mutex_unlock(&buffer->mutex); return err; } @@ -1913,15 +1934,63 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->reader_page->read); } -static __always_inline struct ring_buffer_event * -rb_iter_head_event(struct ring_buffer_iter *iter) +static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) { - return __rb_page_index(iter->head_page, iter->head); + return local_read(&bpage->page->commit); } -static __always_inline unsigned rb_page_commit(struct buffer_page *bpage) +static struct ring_buffer_event * +rb_iter_head_event(struct ring_buffer_iter *iter) { - return local_read(&bpage->page->commit); + struct ring_buffer_event *event; + struct buffer_page *iter_head_page = iter->head_page; + unsigned long commit; + unsigned length; + + if (iter->head != iter->next_event) + return iter->event; + + /* + * When the writer goes across pages, it issues a cmpxchg which + * is a mb(), which will synchronize with the rmb here. + * (see rb_tail_page_update() and __rb_reserve_next()) + */ + commit = rb_page_commit(iter_head_page); + smp_rmb(); + event = __rb_page_index(iter_head_page, iter->head); + length = rb_event_length(event); + + /* + * READ_ONCE() doesn't work on functions and we don't want the + * compiler doing any crazy optimizations with length. + */ + barrier(); + + if ((iter->head + length) > commit || length > BUF_MAX_DATA_SIZE) + /* Writer corrupted the read? */ + goto reset; + + memcpy(iter->event, event, length); + /* + * If the page stamp is still the same after this rmb() then the + * event was safely copied without the writer entering the page. + */ + smp_rmb(); + + /* Make sure the page didn't change since we read this */ + if (iter->page_stamp != iter_head_page->page->time_stamp || + commit > rb_page_commit(iter_head_page)) + goto reset; + + iter->next_event = iter->head + length; + return iter->event; + reset: + /* Reset to the beginning */ + iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; + iter->head = 0; + iter->next_event = 0; + iter->missed_events = 1; + return NULL; } /* Size is determined by what has been committed */ @@ -1959,8 +2028,9 @@ static void rb_inc_iter(struct ring_buffer_iter *iter) else rb_inc_page(cpu_buffer, &iter->head_page); - iter->read_stamp = iter->head_page->page->time_stamp; + iter->page_stamp = iter->read_stamp = iter->head_page->page->time_stamp; iter->head = 0; + iter->next_event = 0; } /* @@ -3547,14 +3617,18 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) /* Iterator usage is expected to have record disabled */ iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; + iter->next_event = iter->head; iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; - if (iter->head) + if (iter->head) { iter->read_stamp = cpu_buffer->read_stamp; - else + iter->page_stamp = cpu_buffer->reader_page->page->time_stamp; + } else { iter->read_stamp = iter->head_page->page->time_stamp; + iter->page_stamp = iter->read_stamp; + } } /** @@ -3590,17 +3664,38 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter) struct buffer_page *reader; struct buffer_page *head_page; struct buffer_page *commit_page; + struct buffer_page *curr_commit_page; unsigned commit; + u64 curr_commit_ts; + u64 commit_ts; cpu_buffer = iter->cpu_buffer; - - /* Remember, trace recording is off when iterator is in use */ reader = cpu_buffer->reader_page; head_page = cpu_buffer->head_page; commit_page = cpu_buffer->commit_page; + commit_ts = commit_page->page->time_stamp; + + /* + * When the writer goes across pages, it issues a cmpxchg which + * is a mb(), which will synchronize with the rmb here. + * (see rb_tail_page_update()) + */ + smp_rmb(); commit = rb_page_commit(commit_page); + /* We want to make sure that the commit page doesn't change */ + smp_rmb(); - return ((iter->head_page == commit_page && iter->head == commit) || + /* Make sure commit page didn't change */ + curr_commit_page = READ_ONCE(cpu_buffer->commit_page); + curr_commit_ts = READ_ONCE(curr_commit_page->page->time_stamp); + + /* If the commit page changed, then there's more data */ + if (curr_commit_page != commit_page || + curr_commit_ts != commit_ts) + return 0; + + /* Still racy, as it may return a false positive, but that's OK */ + return ((iter->head_page == commit_page && iter->head >= commit) || (iter->head_page == reader && commit_page == head_page && head_page->read == commit && iter->head == rb_page_commit(cpu_buffer->reader_page))); @@ -3828,15 +3923,22 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer) static void rb_advance_iter(struct ring_buffer_iter *iter) { struct ring_buffer_per_cpu *cpu_buffer; - struct ring_buffer_event *event; - unsigned length; cpu_buffer = iter->cpu_buffer; + /* If head == next_event then we need to jump to the next event */ + if (iter->head == iter->next_event) { + /* If the event gets overwritten again, there's nothing to do */ + if (rb_iter_head_event(iter) == NULL) + return; + } + + iter->head = iter->next_event; + /* * Check if we are at the end of the buffer. */ - if (iter->head >= rb_page_size(iter->head_page)) { + if (iter->next_event >= rb_page_size(iter->head_page)) { /* discarded commits can make the page empty */ if (iter->head_page == cpu_buffer->commit_page) return; @@ -3844,27 +3946,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter) return; } - event = rb_iter_head_event(iter); - - length = rb_event_length(event); - - /* - * This should not be called to advance the header if we are - * at the tail of the buffer. - */ - if (RB_WARN_ON(cpu_buffer, - (iter->head_page == cpu_buffer->commit_page) && - (iter->head + length > rb_commit_index(cpu_buffer)))) - return; - - rb_update_iter_read_stamp(iter, event); - - iter->head += length; - - /* check for end of page padding */ - if ((iter->head >= rb_page_size(iter->head_page)) && - (iter->head_page != cpu_buffer->commit_page)) - rb_inc_iter(iter); + rb_update_iter_read_stamp(iter, iter->event); } static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer) @@ -3952,6 +4034,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; + bool failed = false; if (ts) *ts = 0; @@ -3978,10 +4061,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) * to a data event, we should never loop more than three times. * Once for going to next page, once on time extend, and * finally once to get the event. - * (We never hit the following condition more than thrice). + * We should never hit the following condition more than thrice, + * unless the buffer is very small, and there's a writer + * that is causing the reader to fail getting an event. */ - if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) + if (++nr_loops > 3) { + RB_WARN_ON(cpu_buffer, !failed); return NULL; + } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -3992,6 +4079,10 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); + if (!event) { + failed = true; + goto again; + } switch (event->type_len) { case RINGBUF_TYPE_PADDING: @@ -4102,6 +4193,20 @@ ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, return event; } +/** ring_buffer_iter_dropped - report if there are dropped events + * @iter: The ring buffer iterator + * + * Returns true if there was dropped events since the last peek. + */ +bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter) +{ + bool ret = iter->missed_events != 0; + + iter->missed_events = 0; + return ret; +} +EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped); + /** * ring_buffer_iter_peek - peek at the next event to be read * @iter: The ring buffer iterator @@ -4208,16 +4313,21 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return NULL; - iter = kmalloc(sizeof(*iter), flags); + iter = kzalloc(sizeof(*iter), flags); if (!iter) return NULL; + iter->event = kmalloc(BUF_MAX_DATA_SIZE, flags); + if (!iter->event) { + kfree(iter); + return NULL; + } + cpu_buffer = buffer->buffers[cpu]; iter->cpu_buffer = cpu_buffer; - atomic_inc(&buffer->resize_disabled); - atomic_inc(&cpu_buffer->record_disabled); + atomic_inc(&cpu_buffer->resize_disabled); return iter; } @@ -4290,42 +4400,31 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter) rb_check_pages(cpu_buffer); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&cpu_buffer->buffer->resize_disabled); + atomic_dec(&cpu_buffer->resize_disabled); + kfree(iter->event); kfree(iter); } EXPORT_SYMBOL_GPL(ring_buffer_read_finish); /** - * ring_buffer_read - read the next item in the ring buffer by the iterator + * ring_buffer_iter_advance - advance the iterator to the next location * @iter: The ring buffer iterator - * @ts: The time stamp of the event read. * - * This reads the next event in the ring buffer and increments the iterator. + * Move the location of the iterator such that the next read will + * be the next location of the iterator. */ -struct ring_buffer_event * -ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts) +void ring_buffer_iter_advance(struct ring_buffer_iter *iter) { - struct ring_buffer_event *event; struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - again: - event = rb_iter_peek(iter, ts); - if (!event) - goto out; - - if (event->type_len == RINGBUF_TYPE_PADDING) - goto again; rb_advance_iter(iter); - out: - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - return event; + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); } -EXPORT_SYMBOL_GPL(ring_buffer_read); +EXPORT_SYMBOL_GPL(ring_buffer_iter_advance); /** * ring_buffer_size - return the size of the ring buffer (in bytes) @@ -4406,7 +4505,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) if (!cpumask_test_cpu(cpu, buffer->cpumask)) return; - atomic_inc(&buffer->resize_disabled); + atomic_inc(&cpu_buffer->resize_disabled); atomic_inc(&cpu_buffer->record_disabled); /* Make sure all commits have finished */ @@ -4427,7 +4526,7 @@ void ring_buffer_reset_cpu(struct trace_buffer *buffer, int cpu) raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); atomic_dec(&cpu_buffer->record_disabled); - atomic_dec(&buffer->resize_disabled); + atomic_dec(&cpu_buffer->resize_disabled); } EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 6b11e4e2150c..8d2b98812625 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -386,16 +386,22 @@ trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) * Returns false if @task should be traced. */ bool -trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task) +trace_ignore_this_task(struct trace_pid_list *filtered_pids, + struct trace_pid_list *filtered_no_pids, + struct task_struct *task) { /* - * Return false, because if filtered_pids does not exist, - * all pids are good to trace. + * If filterd_no_pids is not empty, and the task's pid is listed + * in filtered_no_pids, then return true. + * Otherwise, if filtered_pids is empty, that means we can + * trace all tasks. If it has content, then only trace pids + * within filtered_pids. */ - if (!filtered_pids) - return false; - return !trace_find_filtered_pid(filtered_pids, task->pid); + return (filtered_pids && + !trace_find_filtered_pid(filtered_pids, task->pid)) || + (filtered_no_pids && + trace_find_filtered_pid(filtered_no_pids, task->pid)); } /** @@ -3378,7 +3384,7 @@ static void trace_iterator_increment(struct trace_iterator *iter) iter->idx++; if (buf_iter) - ring_buffer_read(buf_iter, NULL); + ring_buffer_iter_advance(buf_iter); } static struct trace_entry * @@ -3388,11 +3394,15 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); - if (buf_iter) + if (buf_iter) { event = ring_buffer_iter_peek(buf_iter, ts); - else + if (lost_events) + *lost_events = ring_buffer_iter_dropped(buf_iter) ? + (unsigned long)-1 : 0; + } else { event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts, lost_events); + } if (event) { iter->ent_size = ring_buffer_event_length(event); @@ -3462,11 +3472,51 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu, return next; } +#define STATIC_TEMP_BUF_SIZE 128 +static char static_temp_buf[STATIC_TEMP_BUF_SIZE]; + /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { - return __find_next_entry(iter, ent_cpu, NULL, ent_ts); + /* __find_next_entry will reset ent_size */ + int ent_size = iter->ent_size; + struct trace_entry *entry; + + /* + * If called from ftrace_dump(), then the iter->temp buffer + * will be the static_temp_buf and not created from kmalloc. + * If the entry size is greater than the buffer, we can + * not save it. Just return NULL in that case. This is only + * used to add markers when two consecutive events' time + * stamps have a large delta. See trace_print_lat_context() + */ + if (iter->temp == static_temp_buf && + STATIC_TEMP_BUF_SIZE < ent_size) + return NULL; + + /* + * The __find_next_entry() may call peek_next_entry(), which may + * call ring_buffer_peek() that may make the contents of iter->ent + * undefined. Need to copy iter->ent now. + */ + if (iter->ent && iter->ent != iter->temp) { + if ((!iter->temp || iter->temp_size < iter->ent_size) && + !WARN_ON_ONCE(iter->temp == static_temp_buf)) { + kfree(iter->temp); + iter->temp = kmalloc(iter->ent_size, GFP_KERNEL); + if (!iter->temp) + return NULL; + } + memcpy(iter->temp, iter->ent, iter->ent_size); + iter->temp_size = iter->ent_size; + iter->ent = iter->temp; + } + entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts); + /* Put back the original ent_size */ + iter->ent_size = ent_size; + + return entry; } /* Find the next real entry, and increment the iterator to the next entry */ @@ -3538,7 +3588,7 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu) if (ts >= iter->array_buffer->time_start) break; entries++; - ring_buffer_read(buf_iter, NULL); + ring_buffer_iter_advance(buf_iter); } per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; @@ -3981,8 +4031,12 @@ enum print_line_t print_trace_line(struct trace_iterator *iter) enum print_line_t ret; if (iter->lost_events) { - trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", - iter->cpu, iter->lost_events); + if (iter->lost_events == (unsigned long)-1) + trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n", + iter->cpu); + else + trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", + iter->cpu, iter->lost_events); if (trace_seq_has_overflowed(&iter->seq)) return TRACE_TYPE_PARTIAL_LINE; } @@ -4198,6 +4252,18 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) goto release; /* + * trace_find_next_entry() may need to save off iter->ent. + * It will place it into the iter->temp buffer. As most + * events are less than 128, allocate a buffer of that size. + * If one is greater, then trace_find_next_entry() will + * allocate a new buffer to adjust for the bigger iter->ent. + * It's not critical if it fails to get allocated here. + */ + iter->temp = kmalloc(128, GFP_KERNEL); + if (iter->temp) + iter->temp_size = 128; + + /* * We make a copy of the current tracer to avoid concurrent * changes on it while we are reading. */ @@ -4237,8 +4303,11 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; - /* stop the trace while dumping if we are not opening "snapshot" */ - if (!iter->snapshot) + /* + * If pause-on-trace is enabled, then stop the trace while + * dumping, unless this is the "snapshot" file + */ + if (!iter->snapshot && (tr->trace_flags & TRACE_ITER_PAUSE_ON_TRACE)) tracing_stop_tr(tr); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { @@ -4269,6 +4338,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) fail: mutex_unlock(&trace_types_lock); kfree(iter->trace); + kfree(iter->temp); kfree(iter->buffer_iter); release: seq_release_private(inode, file); @@ -4334,7 +4404,7 @@ static int tracing_release(struct inode *inode, struct file *file) if (iter->trace && iter->trace->close) iter->trace->close(iter); - if (!iter->snapshot) + if (!iter->snapshot && tr->stop_count) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); @@ -4344,6 +4414,7 @@ static int tracing_release(struct inode *inode, struct file *file) mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); + kfree(iter->temp); kfree(iter->trace); kfree(iter->buffer_iter); seq_release_private(inode, file); @@ -4964,6 +5035,8 @@ static const char readme_msg[] = #ifdef CONFIG_FUNCTION_TRACER " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n" "\t\t (function)\n" + " set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n" + "\t\t (function)\n" #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" @@ -9146,6 +9219,9 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) /* Simulate the iterator */ trace_init_global_iter(&iter); + /* Can not use kmalloc for iter.temp */ + iter.temp = static_temp_buf; + iter.temp_size = STATIC_TEMP_BUF_SIZE; for_each_tracing_cpu(cpu) { atomic_inc(&per_cpu_ptr(iter.array_buffer->data, cpu)->disabled); @@ -9334,7 +9410,7 @@ __init static int tracer_alloc_buffers(void) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ - if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt) + if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 99372dd7d168..4eb1d004d5f2 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -178,10 +178,10 @@ struct trace_array_cpu { kuid_t uid; char comm[TASK_COMM_LEN]; - bool ignore_pid; #ifdef CONFIG_FUNCTION_TRACER - bool ftrace_ignore_pid; + int ftrace_ignore_pid; #endif + bool ignore_pid; }; struct tracer; @@ -207,6 +207,30 @@ struct trace_pid_list { unsigned long *pids; }; +enum { + TRACE_PIDS = BIT(0), + TRACE_NO_PIDS = BIT(1), +}; + +static inline bool pid_type_enabled(int type, struct trace_pid_list *pid_list, + struct trace_pid_list *no_pid_list) +{ + /* Return true if the pid list in type has pids */ + return ((type & TRACE_PIDS) && pid_list) || + ((type & TRACE_NO_PIDS) && no_pid_list); +} + +static inline bool still_need_pid_events(int type, struct trace_pid_list *pid_list, + struct trace_pid_list *no_pid_list) +{ + /* + * Turning off what is in @type, return true if the "other" + * pid list, still has pids in it. + */ + return (!(type & TRACE_PIDS) && pid_list) || + (!(type & TRACE_NO_PIDS) && no_pid_list); +} + typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data); /** @@ -285,6 +309,7 @@ struct trace_array { #endif #endif struct trace_pid_list __rcu *filtered_pids; + struct trace_pid_list __rcu *filtered_no_pids; /* * max_lock is used to protect the swapping of buffers * when taking a max snapshot. The buffers themselves are @@ -331,6 +356,7 @@ struct trace_array { #ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops *ops; struct trace_pid_list __rcu *function_pids; + struct trace_pid_list __rcu *function_no_pids; #ifdef CONFIG_DYNAMIC_FTRACE /* All of these are protected by the ftrace_lock */ struct list_head func_probes; @@ -557,12 +583,7 @@ struct tracer { * caller, and we can skip the current check. */ enum { - TRACE_BUFFER_BIT, - TRACE_BUFFER_NMI_BIT, - TRACE_BUFFER_IRQ_BIT, - TRACE_BUFFER_SIRQ_BIT, - - /* Start of function recursion bits */ + /* Function recursion bits */ TRACE_FTRACE_BIT, TRACE_FTRACE_NMI_BIT, TRACE_FTRACE_IRQ_BIT, @@ -787,6 +808,7 @@ extern int pid_max; bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid); bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, + struct trace_pid_list *filtered_no_pids, struct task_struct *task); void trace_filter_add_remove_task(struct trace_pid_list *pid_list, struct task_struct *self, @@ -1307,6 +1329,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf, C(IRQ_INFO, "irq-info"), \ C(MARKERS, "markers"), \ C(EVENT_FORK, "event-fork"), \ + C(PAUSE_ON_TRACE, "pause-on-trace"), \ FUNCTION_FLAGS \ FGRAPH_FLAGS \ STACK_FLAGS \ diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index f22746f3c132..a523da0dae0a 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -325,14 +325,16 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field_desc( long, timestamp, tv_nsec ) __field( unsigned int, nmi_count ) __field( unsigned int, seqnum ) + __field( unsigned int, count ) ), - F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tcount:%d\tnmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, __entry->duration, __entry->outer_duration, + __entry->count, __entry->nmi_total_ts, __entry->nmi_count) ); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f38234ecea18..242f59e7f17d 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -232,10 +232,13 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file) { struct trace_array *tr = trace_file->tr; struct trace_array_cpu *data; + struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_raw(tr->filtered_pids); - if (!pid_list) + no_pid_list = rcu_dereference_raw(tr->filtered_no_pids); + + if (!pid_list && !no_pid_list) return false; data = this_cpu_ptr(tr->array_buffer.data); @@ -510,6 +513,9 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); + + pid_list = rcu_dereference_raw(tr->filtered_no_pids); + trace_filter_add_remove_task(pid_list, NULL, task); } static void @@ -522,6 +528,9 @@ event_filter_pid_sched_process_fork(void *data, pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); + + pid_list = rcu_dereference_sched(tr->filtered_no_pids); + trace_filter_add_remove_task(pid_list, self, task); } void trace_event_follow_fork(struct trace_array *tr, bool enable) @@ -544,13 +553,23 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt, struct task_struct *prev, struct task_struct *next) { struct trace_array *tr = data; + struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; + bool ret; pid_list = rcu_dereference_sched(tr->filtered_pids); + no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); - this_cpu_write(tr->array_buffer.data->ignore_pid, - trace_ignore_this_task(pid_list, prev) && - trace_ignore_this_task(pid_list, next)); + /* + * Sched switch is funny, as we only want to ignore it + * in the notrace case if both prev and next should be ignored. + */ + ret = trace_ignore_this_task(NULL, no_pid_list, prev) && + trace_ignore_this_task(NULL, no_pid_list, next); + + this_cpu_write(tr->array_buffer.data->ignore_pid, ret || + (trace_ignore_this_task(pid_list, NULL, prev) && + trace_ignore_this_task(pid_list, NULL, next))); } static void @@ -558,18 +577,21 @@ event_filter_pid_sched_switch_probe_post(void *data, bool preempt, struct task_struct *prev, struct task_struct *next) { struct trace_array *tr = data; + struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; pid_list = rcu_dereference_sched(tr->filtered_pids); + no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); this_cpu_write(tr->array_buffer.data->ignore_pid, - trace_ignore_this_task(pid_list, next)); + trace_ignore_this_task(pid_list, no_pid_list, next)); } static void event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) { struct trace_array *tr = data; + struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; /* Nothing to do if we are already tracing */ @@ -577,15 +599,17 @@ event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task) return; pid_list = rcu_dereference_sched(tr->filtered_pids); + no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); this_cpu_write(tr->array_buffer.data->ignore_pid, - trace_ignore_this_task(pid_list, task)); + trace_ignore_this_task(pid_list, no_pid_list, task)); } static void event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) { struct trace_array *tr = data; + struct trace_pid_list *no_pid_list; struct trace_pid_list *pid_list; /* Nothing to do if we are not tracing */ @@ -593,23 +617,15 @@ event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task) return; pid_list = rcu_dereference_sched(tr->filtered_pids); + no_pid_list = rcu_dereference_sched(tr->filtered_no_pids); /* Set tracing if current is enabled */ this_cpu_write(tr->array_buffer.data->ignore_pid, - trace_ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, no_pid_list, current)); } -static void __ftrace_clear_event_pids(struct trace_array *tr) +static void unregister_pid_events(struct trace_array *tr) { - struct trace_pid_list *pid_list; - struct trace_event_file *file; - int cpu; - - pid_list = rcu_dereference_protected(tr->filtered_pids, - lockdep_is_held(&event_mutex)); - if (!pid_list) - return; - unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr); unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr); @@ -621,26 +637,55 @@ static void __ftrace_clear_event_pids(struct trace_array *tr) unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr); unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr); +} - list_for_each_entry(file, &tr->events, list) { - clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); +static void __ftrace_clear_event_pids(struct trace_array *tr, int type) +{ + struct trace_pid_list *pid_list; + struct trace_pid_list *no_pid_list; + struct trace_event_file *file; + int cpu; + + pid_list = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + + /* Make sure there's something to do */ + if (!pid_type_enabled(type, pid_list, no_pid_list)) + return; + + if (!still_need_pid_events(type, pid_list, no_pid_list)) { + unregister_pid_events(tr); + + list_for_each_entry(file, &tr->events, list) { + clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); + } + + for_each_possible_cpu(cpu) + per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false; } - for_each_possible_cpu(cpu) - per_cpu_ptr(tr->array_buffer.data, cpu)->ignore_pid = false; + if (type & TRACE_PIDS) + rcu_assign_pointer(tr->filtered_pids, NULL); - rcu_assign_pointer(tr->filtered_pids, NULL); + if (type & TRACE_NO_PIDS) + rcu_assign_pointer(tr->filtered_no_pids, NULL); /* Wait till all users are no longer using pid filtering */ tracepoint_synchronize_unregister(); - trace_free_pid_list(pid_list); + if ((type & TRACE_PIDS) && pid_list) + trace_free_pid_list(pid_list); + + if ((type & TRACE_NO_PIDS) && no_pid_list) + trace_free_pid_list(no_pid_list); } -static void ftrace_clear_event_pids(struct trace_array *tr) +static void ftrace_clear_event_pids(struct trace_array *tr, int type) { mutex_lock(&event_mutex); - __ftrace_clear_event_pids(tr); + __ftrace_clear_event_pids(tr, type); mutex_unlock(&event_mutex); } @@ -1013,15 +1058,32 @@ static void t_stop(struct seq_file *m, void *p) } static void * -p_next(struct seq_file *m, void *v, loff_t *pos) +__next(struct seq_file *m, void *v, loff_t *pos, int type) { struct trace_array *tr = m->private; - struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids); + struct trace_pid_list *pid_list; + + if (type == TRACE_PIDS) + pid_list = rcu_dereference_sched(tr->filtered_pids); + else + pid_list = rcu_dereference_sched(tr->filtered_no_pids); return trace_pid_next(pid_list, v, pos); } -static void *p_start(struct seq_file *m, loff_t *pos) +static void * +p_next(struct seq_file *m, void *v, loff_t *pos) +{ + return __next(m, v, pos, TRACE_PIDS); +} + +static void * +np_next(struct seq_file *m, void *v, loff_t *pos) +{ + return __next(m, v, pos, TRACE_NO_PIDS); +} + +static void *__start(struct seq_file *m, loff_t *pos, int type) __acquires(RCU) { struct trace_pid_list *pid_list; @@ -1036,7 +1098,10 @@ static void *p_start(struct seq_file *m, loff_t *pos) mutex_lock(&event_mutex); rcu_read_lock_sched(); - pid_list = rcu_dereference_sched(tr->filtered_pids); + if (type == TRACE_PIDS) + pid_list = rcu_dereference_sched(tr->filtered_pids); + else + pid_list = rcu_dereference_sched(tr->filtered_no_pids); if (!pid_list) return NULL; @@ -1044,6 +1109,18 @@ static void *p_start(struct seq_file *m, loff_t *pos) return trace_pid_start(pid_list, pos); } +static void *p_start(struct seq_file *m, loff_t *pos) + __acquires(RCU) +{ + return __start(m, pos, TRACE_PIDS); +} + +static void *np_start(struct seq_file *m, loff_t *pos) + __acquires(RCU) +{ + return __start(m, pos, TRACE_NO_PIDS); +} + static void p_stop(struct seq_file *m, void *p) __releases(RCU) { @@ -1588,6 +1665,7 @@ static void ignore_task_cpu(void *data) { struct trace_array *tr = data; struct trace_pid_list *pid_list; + struct trace_pid_list *no_pid_list; /* * This function is called by on_each_cpu() while the @@ -1595,18 +1673,50 @@ static void ignore_task_cpu(void *data) */ pid_list = rcu_dereference_protected(tr->filtered_pids, mutex_is_locked(&event_mutex)); + no_pid_list = rcu_dereference_protected(tr->filtered_no_pids, + mutex_is_locked(&event_mutex)); this_cpu_write(tr->array_buffer.data->ignore_pid, - trace_ignore_this_task(pid_list, current)); + trace_ignore_this_task(pid_list, no_pid_list, current)); +} + +static void register_pid_events(struct trace_array *tr) +{ + /* + * Register a probe that is called before all other probes + * to set ignore_pid if next or prev do not match. + * Register a probe this is called after all other probes + * to only keep ignore_pid set if next pid matches. + */ + register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post, + tr, 0); + + register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, + tr, 0); + + register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, + tr, 0); + + register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre, + tr, INT_MAX); + register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post, + tr, 0); } static ssize_t -ftrace_event_pid_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +event_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos, int type) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; struct trace_pid_list *filtered_pids = NULL; + struct trace_pid_list *other_pids = NULL; struct trace_pid_list *pid_list; struct trace_event_file *file; ssize_t ret; @@ -1620,14 +1730,26 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, mutex_lock(&event_mutex); - filtered_pids = rcu_dereference_protected(tr->filtered_pids, - lockdep_is_held(&event_mutex)); + if (type == TRACE_PIDS) { + filtered_pids = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + other_pids = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + } else { + filtered_pids = rcu_dereference_protected(tr->filtered_no_pids, + lockdep_is_held(&event_mutex)); + other_pids = rcu_dereference_protected(tr->filtered_pids, + lockdep_is_held(&event_mutex)); + } ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt); if (ret < 0) goto out; - rcu_assign_pointer(tr->filtered_pids, pid_list); + if (type == TRACE_PIDS) + rcu_assign_pointer(tr->filtered_pids, pid_list); + else + rcu_assign_pointer(tr->filtered_no_pids, pid_list); list_for_each_entry(file, &tr->events, list) { set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags); @@ -1636,32 +1758,8 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, if (filtered_pids) { tracepoint_synchronize_unregister(); trace_free_pid_list(filtered_pids); - } else if (pid_list) { - /* - * Register a probe that is called before all other probes - * to set ignore_pid if next or prev do not match. - * Register a probe this is called after all other probes - * to only keep ignore_pid set if next pid matches. - */ - register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre, - tr, INT_MAX); - register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post, - tr, 0); - - register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, - tr, INT_MAX); - register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, - tr, 0); - - register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, - tr, INT_MAX); - register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, - tr, 0); - - register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre, - tr, INT_MAX); - register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post, - tr, 0); + } else if (pid_list && !other_pids) { + register_pid_events(tr); } /* @@ -1680,9 +1778,24 @@ ftrace_event_pid_write(struct file *filp, const char __user *ubuf, return ret; } +static ssize_t +ftrace_event_pid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return event_pid_write(filp, ubuf, cnt, ppos, TRACE_PIDS); +} + +static ssize_t +ftrace_event_npid_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return event_pid_write(filp, ubuf, cnt, ppos, TRACE_NO_PIDS); +} + static int ftrace_event_avail_open(struct inode *inode, struct file *file); static int ftrace_event_set_open(struct inode *inode, struct file *file); static int ftrace_event_set_pid_open(struct inode *inode, struct file *file); +static int ftrace_event_set_npid_open(struct inode *inode, struct file *file); static int ftrace_event_release(struct inode *inode, struct file *file); static const struct seq_operations show_event_seq_ops = { @@ -1706,6 +1819,13 @@ static const struct seq_operations show_set_pid_seq_ops = { .stop = p_stop, }; +static const struct seq_operations show_set_no_pid_seq_ops = { + .start = np_start, + .next = np_next, + .show = trace_pid_show, + .stop = p_stop, +}; + static const struct file_operations ftrace_avail_fops = { .open = ftrace_event_avail_open, .read = seq_read, @@ -1729,6 +1849,14 @@ static const struct file_operations ftrace_set_event_pid_fops = { .release = ftrace_event_release, }; +static const struct file_operations ftrace_set_event_notrace_pid_fops = { + .open = ftrace_event_set_npid_open, + .read = seq_read, + .write = ftrace_event_npid_write, + .llseek = seq_lseek, + .release = ftrace_event_release, +}; + static const struct file_operations ftrace_enable_fops = { .open = tracing_open_generic, .read = event_enable_read, @@ -1858,7 +1986,28 @@ ftrace_event_set_pid_open(struct inode *inode, struct file *file) if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) - ftrace_clear_event_pids(tr); + ftrace_clear_event_pids(tr, TRACE_PIDS); + + ret = ftrace_event_open(inode, file, seq_ops); + if (ret < 0) + trace_array_put(tr); + return ret; +} + +static int +ftrace_event_set_npid_open(struct inode *inode, struct file *file) +{ + const struct seq_operations *seq_ops = &show_set_no_pid_seq_ops; + struct trace_array *tr = inode->i_private; + int ret; + + ret = tracing_check_open_get_tr(tr); + if (ret) + return ret; + + if ((file->f_mode & FMODE_WRITE) && + (file->f_flags & O_TRUNC)) + ftrace_clear_event_pids(tr, TRACE_NO_PIDS); ret = ftrace_event_open(inode, file, seq_ops); if (ret < 0) @@ -3075,6 +3224,11 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr) if (!entry) pr_warn("Could not create tracefs 'set_event_pid' entry\n"); + entry = tracefs_create_file("set_event_notrace_pid", 0644, parent, + tr, &ftrace_set_event_notrace_pid_fops); + if (!entry) + pr_warn("Could not create tracefs 'set_event_notrace_pid' entry\n"); + /* ring buffer internal formats */ entry = trace_create_file("header_page", 0444, d_events, ring_buffer_print_page_header, @@ -3158,7 +3312,7 @@ int event_trace_del_tracer(struct trace_array *tr) clear_event_triggers(tr); /* Clear the pid list */ - __ftrace_clear_event_pids(tr); + __ftrace_clear_event_pids(tr, TRACE_PIDS | TRACE_NO_PIDS); /* Disable any running events */ __ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 7d71546ba00a..4a9c49c08ec9 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -482,7 +482,7 @@ get_return_for_leaf(struct trace_iterator *iter, /* this is a leaf, now advance the iterator */ if (ring_iter) - ring_buffer_read(ring_iter, NULL); + ring_buffer_iter_advance(ring_iter); return next; } diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c index a48808c43249..e2be7bb7ef7e 100644 --- a/kernel/trace/trace_hwlat.c +++ b/kernel/trace/trace_hwlat.c @@ -83,6 +83,7 @@ struct hwlat_sample { u64 nmi_total_ts; /* Total time spent in NMIs */ struct timespec64 timestamp; /* wall time */ int nmi_count; /* # NMIs during this sample */ + int count; /* # of iteratons over threash */ }; /* keep the global state somewhere. */ @@ -124,6 +125,7 @@ static void trace_hwlat_sample(struct hwlat_sample *sample) entry->timestamp = sample->timestamp; entry->nmi_total_ts = sample->nmi_total_ts; entry->nmi_count = sample->nmi_count; + entry->count = sample->count; if (!call_filter_check_discard(call, entry, buffer, event)) trace_buffer_unlock_commit_nostack(buffer, event); @@ -167,12 +169,14 @@ void trace_hwlat_callback(bool enter) static int get_sample(void) { struct trace_array *tr = hwlat_trace; + struct hwlat_sample s; time_type start, t1, t2, last_t2; - s64 diff, total, last_total = 0; + s64 diff, outer_diff, total, last_total = 0; u64 sample = 0; u64 thresh = tracing_thresh; u64 outer_sample = 0; int ret = -1; + unsigned int count = 0; do_div(thresh, NSEC_PER_USEC); /* modifies interval value */ @@ -186,6 +190,7 @@ static int get_sample(void) init_time(last_t2, 0); start = time_get(); /* start timestamp */ + outer_diff = 0; do { @@ -194,14 +199,14 @@ static int get_sample(void) if (time_u64(last_t2)) { /* Check the delta from outer loop (t2 to next t1) */ - diff = time_to_us(time_sub(t1, last_t2)); + outer_diff = time_to_us(time_sub(t1, last_t2)); /* This shouldn't happen */ - if (diff < 0) { + if (outer_diff < 0) { pr_err(BANNER "time running backwards\n"); goto out; } - if (diff > outer_sample) - outer_sample = diff; + if (outer_diff > outer_sample) + outer_sample = outer_diff; } last_t2 = t2; @@ -217,6 +222,12 @@ static int get_sample(void) /* This checks the inner loop (t1 to t2) */ diff = time_to_us(time_sub(t2, t1)); /* current diff */ + if (diff > thresh || outer_diff > thresh) { + if (!count) + ktime_get_real_ts64(&s.timestamp); + count++; + } + /* This shouldn't happen */ if (diff < 0) { pr_err(BANNER "time running backwards\n"); @@ -236,7 +247,6 @@ static int get_sample(void) /* If we exceed the threshold value, we have found a hardware latency */ if (sample > thresh || outer_sample > thresh) { - struct hwlat_sample s; u64 latency; ret = 1; @@ -249,9 +259,9 @@ static int get_sample(void) s.seqnum = hwlat_data.count; s.duration = sample; s.outer_duration = outer_sample; - ktime_get_real_ts64(&s.timestamp); s.nmi_total_ts = nmi_total_ts; s.nmi_count = nmi_count; + s.count = count; trace_hwlat_sample(&s); latency = max(sample, outer_sample); diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 362cca52f5de..d0568af4a0ef 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1078,6 +1078,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev) int i; seq_putc(m, trace_kprobe_is_return(tk) ? 'r' : 'p'); + if (trace_kprobe_is_return(tk) && tk->rp.maxactive) + seq_printf(m, "%d", tk->rp.maxactive); seq_printf(m, ":%s/%s", trace_probe_group_name(&tk->tp), trace_probe_name(&tk->tp)); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index b4909082f6a4..9a121e147102 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -617,22 +617,19 @@ int trace_print_context(struct trace_iterator *iter) int trace_print_lat_context(struct trace_iterator *iter) { + struct trace_entry *entry, *next_entry; struct trace_array *tr = iter->tr; - /* trace_find_next_entry will reset ent_size */ - int ent_size = iter->ent_size; struct trace_seq *s = &iter->seq; - u64 next_ts; - struct trace_entry *entry = iter->ent, - *next_entry = trace_find_next_entry(iter, NULL, - &next_ts); unsigned long verbose = (tr->trace_flags & TRACE_ITER_VERBOSE); + u64 next_ts; - /* Restore the original ent_size */ - iter->ent_size = ent_size; - + next_entry = trace_find_next_entry(iter, NULL, &next_ts); if (!next_entry) next_ts = iter->ts; + /* trace_find_next_entry() may change iter->ent */ + entry = iter->ent; + if (verbose) { char comm[TASK_COMM_LEN]; @@ -1158,12 +1155,12 @@ trace_hwlat_print(struct trace_iterator *iter, int flags, trace_assign_type(field, entry); - trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld", + trace_seq_printf(s, "#%-5u inner/outer(us): %4llu/%-5llu ts:%lld.%09ld count:%d", field->seqnum, field->duration, field->outer_duration, (long long)field->timestamp.tv_sec, - field->timestamp.tv_nsec); + field->timestamp.tv_nsec, field->count); if (field->nmi_count) { /* diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 18d16f3ef980..2a8e8e9c1c75 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1333,8 +1333,15 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, int size, esize; int rctx; - if (bpf_prog_array_valid(call) && !trace_call_bpf(call, regs)) - return; + if (bpf_prog_array_valid(call)) { + u32 ret; + + preempt_disable(); + ret = trace_call_bpf(call, regs); + preempt_enable(); + if (!ret) + return; + } esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4e01c448b4b4..3816a18c251e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2834,7 +2834,7 @@ void flush_workqueue(struct workqueue_struct *wq) * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ - if (wq->first_flusher != &this_flusher) + if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); @@ -2843,7 +2843,7 @@ void flush_workqueue(struct workqueue_struct *wq) if (wq->first_flusher != &this_flusher) goto out_unlock; - wq->first_flusher = NULL; + WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); @@ -5898,7 +5898,7 @@ static void __init wq_numa_init(void) * items. Actual work item execution starts only after kthreads can be * created and scheduled right before early initcalls. */ -int __init workqueue_init_early(void) +void __init workqueue_init_early(void) { int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ; @@ -5965,8 +5965,6 @@ int __init workqueue_init_early(void) !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq); - - return 0; } /** @@ -5978,7 +5976,7 @@ int __init workqueue_init_early(void) * are no kworkers executing the work items yet. Populate the worker pools * with the initial workers and enable future kworker creations. */ -int __init workqueue_init(void) +void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; @@ -6025,6 +6023,4 @@ int __init workqueue_init(void) wq_online = true; wq_watchdog_init(); - - return 0; } |