From cb4d2b3f03d8eed90be3a194e5b54b734ec4bbe9 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:52 -0700 Subject: bpf: Add name, load_time, uid and map_ids to bpf_prog_info The patch adds name and load_time to struct bpf_prog_aux. They are also exported to bpf_prog_info. The bpf_prog's name is passed by userspace during BPF_PROG_LOAD. The kernel only stores the first (BPF_PROG_NAME_LEN - 1) bytes and the name stored in the kernel is always \0 terminated. The kernel will reject name that contains characters other than isalnum() and '_'. It will also reject name that is not null terminated. The existing 'user->uid' of the bpf_prog_aux is also exported to the bpf_prog_info as created_by_uid. The existing 'used_maps' of the bpf_prog_aux is exported to the newly added members 'nr_map_ids' and 'map_ids' of the bpf_prog_info. On the input, nr_map_ids tells how big the userspace's map_ids buffer is. On the output, nr_map_ids tells the exact user_map_cnt and it will only copy up to the userspace's map_ids buffer is allowed. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 50 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 25d074920a00..45970df3f820 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -23,6 +23,9 @@ #include #include #include +#include +#include +#include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -312,6 +315,30 @@ int bpf_map_new_fd(struct bpf_map *map) offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL +/* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. + * Return 0 on success and < 0 on error. + */ +static int bpf_obj_name_cpy(char *dst, const char *src) +{ + const char *end = src + BPF_OBJ_NAME_LEN; + + /* Copy all isalnum() and '_' char */ + while (src < end && *src) { + if (!isalnum(*src) && *src != '_') + return -EINVAL; + *dst++ = *src++; + } + + /* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */ + if (src == end) + return -EINVAL; + + /* '\0' terminates dst */ + *dst = 0; + + return 0; +} + #define BPF_MAP_CREATE_LAST_FIELD numa_node /* called via syscall */ static int map_create(union bpf_attr *attr) @@ -973,7 +1000,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_flags +#define BPF_PROG_LOAD_LAST_FIELD prog_name static int bpf_prog_load(union bpf_attr *attr) { @@ -1037,6 +1064,11 @@ static int bpf_prog_load(union bpf_attr *attr) if (err < 0) goto free_prog; + prog->aux->load_time = ktime_get_boot_ns(); + err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name); + if (err) + goto free_prog; + /* run eBPF verifier */ err = bpf_check(&prog, attr); if (err < 0) @@ -1358,8 +1390,25 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.type = prog->type; info.id = prog->aux->id; + info.load_time = prog->aux->load_time; + info.created_by_uid = from_kuid_munged(current_user_ns(), + prog->aux->user->uid); memcpy(info.tag, prog->tag, sizeof(prog->tag)); + memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); + + ulen = info.nr_map_ids; + info.nr_map_ids = prog->aux->used_map_cnt; + ulen = min_t(u32, info.nr_map_ids, ulen); + if (ulen) { + u32 *user_map_ids = (u32 *)info.map_ids; + u32 i; + + for (i = 0; i < ulen; i++) + if (put_user(prog->aux->used_maps[i]->id, + &user_map_ids[i])) + return -EFAULT; + } if (!capable(CAP_SYS_ADMIN)) { info.jited_prog_len = 0; -- cgit v1.2.3 From ad5b177bd73f5107d97c36f56395c4281fb6f089 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 27 Sep 2017 14:37:53 -0700 Subject: bpf: Add map_name to bpf_map_info This patch allows userspace to specify a name for a map during BPF_MAP_CREATE. The map's name can later be exported to user space via BPF_OBJ_GET_INFO_BY_FD. Signed-off-by: Martin KaFai Lau Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 2 ++ kernel/bpf/syscall.c | 7 ++++++- 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 33ccc474fb04..252f4bc9eb25 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -56,6 +56,7 @@ struct bpf_map { struct work_struct work; atomic_t usercnt; struct bpf_map *inner_map_meta; + u8 name[BPF_OBJ_NAME_LEN]; }; /* function argument constraints */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd6348269bf5..6d2137b4cf38 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -190,6 +190,7 @@ union bpf_attr { __u32 numa_node; /* numa node (effective only if * BPF_F_NUMA_NODE is set). */ + __u8 map_name[BPF_OBJ_NAME_LEN]; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -829,6 +830,7 @@ struct bpf_map_info { __u32 value_size; __u32 max_entries; __u32 map_flags; + __u8 name[BPF_OBJ_NAME_LEN]; } __attribute__((aligned(8))); /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 45970df3f820..11a7f82a55d1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -339,7 +339,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD numa_node +#define BPF_MAP_CREATE_LAST_FIELD map_name /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -361,6 +361,10 @@ static int map_create(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + err = bpf_obj_name_cpy(map->name, attr->map_name); + if (err) + goto free_map_nouncharge; + atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); @@ -1462,6 +1466,7 @@ static int bpf_map_get_info_by_fd(struct bpf_map *map, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + memcpy(info.name, map->name, sizeof(map->name)); if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- cgit v1.2.3 From 721e08dad17e226ef68819d0a23dc53c25fe8ea5 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 29 Sep 2017 10:52:17 -0700 Subject: bpf: Fix compiler warning on info.map_ids for 32bit platform This patch uses u64_to_user_ptr() to cast info.map_ids to a userspace ptr. It also tags the user_map_ids with '__user' for sparse check. Fixes: cb4d2b3f03d8 ("bpf: Add name, load_time, uid and map_ids to bpf_prog_info") Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 11a7f82a55d1..b927da66f653 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1405,7 +1405,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { - u32 *user_map_ids = (u32 *)info.map_ids; + u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) -- cgit v1.2.3 From 324bda9e6c5add86ba2e1066476481c48132aca0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:21 -0700 Subject: bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 46 +++-- include/linux/bpf.h | 32 ++++ include/linux/filter.h | 2 +- include/uapi/linux/bpf.h | 42 +++- kernel/bpf/cgroup.c | 467 ++++++++++++++++++++++++++++++++------------- kernel/bpf/core.c | 31 +++ kernel/bpf/syscall.c | 37 ++-- kernel/cgroup/cgroup.c | 28 ++- 8 files changed, 516 insertions(+), 169 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index d41d40ac3efd..102e56fbb6de 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -14,27 +14,42 @@ struct bpf_sock_ops_kern; extern struct static_key_false cgroup_bpf_enabled_key; #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key) +struct bpf_prog_list { + struct list_head node; + struct bpf_prog *prog; +}; + +struct bpf_prog_array; + struct cgroup_bpf { - /* - * Store two sets of bpf_prog pointers, one for programs that are - * pinned directly to this cgroup, and one for those that are effective - * when this cgroup is accessed. + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS */ - struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE]; - struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE]; - bool disallow_override[MAX_BPF_ATTACH_TYPE]; + struct list_head progs[MAX_BPF_ATTACH_TYPE]; + u32 flags[MAX_BPF_ATTACH_TYPE]; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array __rcu *inactive; }; void cgroup_bpf_put(struct cgroup *cgrp); -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent); +int cgroup_bpf_inherit(struct cgroup *cgrp); -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool overridable); +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); -/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */ -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable); +/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, @@ -96,8 +111,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} -static inline void cgroup_bpf_inherit(struct cgroup *cgrp, - struct cgroup *parent) {} +static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 252f4bc9eb25..a6964b75f070 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -241,6 +241,38 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +/* an array of programs to be executed under rcu_lock. + * + * Typical usage: + * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN); + * + * the structure returned by bpf_prog_array_alloc() should be populated + * with program pointers and the last pointer must be NULL. + * The user has to keep refcnt on the program and make sure the program + * is removed from the array before bpf_prog_put(). + * The 'struct bpf_prog_array *' should only be replaced with xchg() + * since other cpus are walking the array of pointers in parallel. + */ +struct bpf_prog_array { + struct rcu_head rcu; + struct bpf_prog *progs[0]; +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); + +#define BPF_PROG_RUN_ARRAY(array, ctx, func) \ + ({ \ + struct bpf_prog **_prog; \ + u32 _ret = 1; \ + rcu_read_lock(); \ + _prog = rcu_dereference(array)->progs; \ + for (; *_prog; _prog++) \ + _ret &= func(*_prog, ctx); \ + rcu_read_unlock(); \ + _ret; \ + }) + #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/linux/filter.h b/include/linux/filter.h index 911d454af107..2d2db394b0ca 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -481,7 +481,7 @@ struct sk_filter { struct bpf_prog *prog; }; -#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi) +#define BPF_PROG_RUN(filter, ctx) (*(filter)->bpf_func)(ctx, (filter)->insnsi) #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6d2137b4cf38..762f74bc6c47 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,11 +143,47 @@ enum bpf_attach_type { #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE -/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command - * to the given target_fd cgroup the descendent cgroup will be able to - * override effective bpf program that was inherited from this cgroup +/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command + * + * NONE(default): No further bpf programs allowed in the subtree. + * + * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, + * the program in this cgroup yields to sub-cgroup program. + * + * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, + * that cgroup program gets run in addition to the program in this cgroup. + * + * Only one program is allowed to be attached to a cgroup with + * NONE or BPF_F_ALLOW_OVERRIDE flag. + * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will + * release old program and attach the new one. Attach flags has to match. + * + * Multiple programs are allowed to be attached to a cgroup with + * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order + * (those that were attached first, run first) + * The programs of sub-cgroup are executed first, then programs of + * this cgroup and then programs of parent cgroup. + * When children program makes decision (like picking TCP CA or sock bind) + * parent program has a chance to override it. + * + * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups. + * A cgroup with NONE doesn't allow any programs in sub-cgroups. + * Ex1: + * cgrp1 (MULTI progs A, B) -> + * cgrp2 (OVERRIDE prog C) -> + * cgrp3 (MULTI prog D) -> + * cgrp4 (OVERRIDE prog E) -> + * cgrp5 (NONE prog F) + * the event in cgrp5 triggers execution of F,D,A,B in that order. + * if prog F is detached, the execution is E,D,A,B + * if prog F and D are detached, the execution is E,A,B + * if prog F, E and D are detached, the execution is C,A,B + * + * All eligible programs are executed regardless of return code from + * earlier programs. */ #define BPF_F_ALLOW_OVERRIDE (1U << 0) +#define BPF_F_ALLOW_MULTI (1U << 1) /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the * verifier will perform strict alignment checking as if the kernel diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 546113430049..6b7500bbdb53 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -27,129 +27,361 @@ void cgroup_bpf_put(struct cgroup *cgrp) { unsigned int type; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.prog); type++) { - struct bpf_prog *prog = cgrp->bpf.prog[type]; - - if (prog) { - bpf_prog_put(prog); + for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog_list *pl, *tmp; + + list_for_each_entry_safe(pl, tmp, progs, node) { + list_del(&pl->node); + bpf_prog_put(pl->prog); + kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key); } + bpf_prog_array_free(cgrp->bpf.effective[type]); + } +} + +/* count number of elements in the list. + * it's slow but the list cannot be long + */ +static u32 prog_list_length(struct list_head *head) +{ + struct bpf_prog_list *pl; + u32 cnt = 0; + + list_for_each_entry(pl, head, node) { + if (!pl->prog) + continue; + cnt++; } + return cnt; +} + +/* if parent has non-overridable prog attached, + * disallow attaching new programs to the descendent cgroup. + * if parent has overridable or multi-prog, allow attaching + */ +static bool hierarchy_allows_attach(struct cgroup *cgrp, + enum bpf_attach_type type, + u32 new_flags) +{ + struct cgroup *p; + + p = cgroup_parent(cgrp); + if (!p) + return true; + do { + u32 flags = p->bpf.flags[type]; + u32 cnt; + + if (flags & BPF_F_ALLOW_MULTI) + return true; + cnt = prog_list_length(&p->bpf.progs[type]); + WARN_ON_ONCE(cnt > 1); + if (cnt == 1) + return !!(flags & BPF_F_ALLOW_OVERRIDE); + p = cgroup_parent(p); + } while (p); + return true; +} + +/* compute a chain of effective programs for a given cgroup: + * start from the list of programs in this cgroup and add + * all parent programs. + * Note that parent's F_ALLOW_OVERRIDE-type program is yielding + * to programs in this cgroup + */ +static int compute_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu **array) +{ + struct bpf_prog_array __rcu *progs; + struct bpf_prog_list *pl; + struct cgroup *p = cgrp; + int cnt = 0; + + /* count number of effective programs by walking parents */ + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + cnt += prog_list_length(&p->bpf.progs[type]); + p = cgroup_parent(p); + } while (p); + + progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); + if (!progs) + return -ENOMEM; + + /* populate the array with effective progs */ + cnt = 0; + p = cgrp; + do { + if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI)) + list_for_each_entry(pl, + &p->bpf.progs[type], node) { + if (!pl->prog) + continue; + rcu_dereference_protected(progs, 1)-> + progs[cnt++] = pl->prog; + } + p = cgroup_parent(p); + } while (p); + + *array = progs; + return 0; +} + +static void activate_effective_progs(struct cgroup *cgrp, + enum bpf_attach_type type, + struct bpf_prog_array __rcu *array) +{ + struct bpf_prog_array __rcu *old_array; + + old_array = xchg(&cgrp->bpf.effective[type], array); + /* free prog array after grace period, since __cgroup_bpf_run_*() + * might be still walking the array + */ + bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify - * @parent: the parent to inherit from */ -void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent) +int cgroup_bpf_inherit(struct cgroup *cgrp) { - unsigned int type; +/* has to use marco instead of const int, since compiler thinks + * that array below is variable length + */ +#define NR ARRAY_SIZE(cgrp->bpf.effective) + struct bpf_prog_array __rcu *arrays[NR] = {}; + int i; - for (type = 0; type < ARRAY_SIZE(cgrp->bpf.effective); type++) { - struct bpf_prog *e; + for (i = 0; i < NR; i++) + INIT_LIST_HEAD(&cgrp->bpf.progs[i]); - e = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - rcu_assign_pointer(cgrp->bpf.effective[type], e); - cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type]; - } + for (i = 0; i < NR; i++) + if (compute_effective_progs(cgrp, i, &arrays[i])) + goto cleanup; + + for (i = 0; i < NR; i++) + activate_effective_progs(cgrp, i, arrays[i]); + + return 0; +cleanup: + for (i = 0; i < NR; i++) + bpf_prog_array_free(arrays[i]); + return -ENOMEM; } +#define BPF_CGROUP_MAX_PROGS 64 + /** - * __cgroup_bpf_update() - Update the pinned program of a cgroup, and + * __cgroup_bpf_attach() - Attach the program to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse - * @parent: The parent of @cgrp, or %NULL if @cgrp is the root - * @prog: A new program to pin - * @type: Type of pinning operation (ingress/egress) - * - * Each cgroup has a set of two pointers for bpf programs; one for eBPF - * programs it owns, and which is effective for execution. - * - * If @prog is not %NULL, this function attaches a new program to the cgroup - * and releases the one that is currently attached, if any. @prog is then made - * the effective program of type @type in that cgroup. - * - * If @prog is %NULL, the currently attached program of type @type is released, - * and the effective program of the parent cgroup (if any) is inherited to - * @cgrp. - * - * Then, the descendants of @cgrp are walked and the effective program for - * each of them is set to the effective program of @cgrp unless the - * descendant has its own program attached, in which case the subbranch is - * skipped. This ensures that delegated subcgroups with own programs are left - * untouched. + * @prog: A program to attach + * @type: Type of attach operation * * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent, - struct bpf_prog *prog, enum bpf_attach_type type, - bool new_overridable) +int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct bpf_prog *old_prog, *effective = NULL; - struct cgroup_subsys_state *pos; - bool overridable = true; - - if (parent) { - overridable = !parent->bpf.disallow_override[type]; - effective = rcu_dereference_protected(parent->bpf.effective[type], - lockdep_is_held(&cgroup_mutex)); - } - - if (prog && effective && !overridable) - /* if parent has non-overridable prog attached, disallow - * attaching new programs to descendent cgroup - */ + struct list_head *progs = &cgrp->bpf.progs[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + bool pl_was_allocated; + u32 old_flags; + int err; + + if ((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) + /* invalid combination */ + return -EINVAL; + + if (!hierarchy_allows_attach(cgrp, type, flags)) return -EPERM; - if (prog && effective && overridable != new_overridable) - /* if parent has overridable prog attached, only - * allow overridable programs in descendent cgroup + if (!list_empty(progs) && cgrp->bpf.flags[type] != flags) + /* Disallow attaching non-overridable on top + * of existing overridable in this cgroup. + * Disallow attaching multi-prog if overridable or none */ return -EPERM; - old_prog = cgrp->bpf.prog[type]; - - if (prog) { - overridable = new_overridable; - effective = prog; - if (old_prog && - cgrp->bpf.disallow_override[type] == new_overridable) - /* disallow attaching non-overridable on top - * of existing overridable in this cgroup - * and vice versa - */ - return -EPERM; + if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + return -E2BIG; + + if (flags & BPF_F_ALLOW_MULTI) { + list_for_each_entry(pl, progs, node) + if (pl->prog == prog) + /* disallow attaching the same prog twice */ + return -EINVAL; + + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + pl->prog = prog; + list_add_tail(&pl->node, progs); + } else { + if (list_empty(progs)) { + pl = kmalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + pl_was_allocated = true; + list_add_tail(&pl->node, progs); + } else { + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl_was_allocated = false; + } + pl->prog = prog; } - if (!prog && !old_prog) - /* report error when trying to detach and nothing is attached */ - return -ENOENT; + old_flags = cgrp->bpf.flags[type]; + cgrp->bpf.flags[type] = flags; - cgrp->bpf.prog[type] = prog; + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); - css_for_each_descendant_pre(pos, &cgrp->self) { - struct cgroup *desc = container_of(pos, struct cgroup, self); - - /* skip the subtree if the descendant has its own program */ - if (desc->bpf.prog[type] && desc != cgrp) { - pos = css_rightmost_descendant(pos); - } else { - rcu_assign_pointer(desc->bpf.effective[type], - effective); - desc->bpf.disallow_override[type] = !overridable; - } + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; } - if (prog) - static_branch_inc(&cgroup_bpf_enabled_key); + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + static_branch_inc(&cgroup_bpf_enabled_key); if (old_prog) { bpf_prog_put(old_prog); static_branch_dec(&cgroup_bpf_enabled_key); } return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and cleanup the prog list */ + pl->prog = old_prog; + if (pl_was_allocated) { + list_del(&pl->node); + kfree(pl); + } + return err; +} + +/** + * __cgroup_bpf_detach() - Detach the program from a cgroup, and + * propagate the change to descendants + * @cgrp: The cgroup which descendants to traverse + * @prog: A program to detach or NULL + * @type: Type of detach operation + * + * Must be called with cgroup_mutex held. + */ +int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 unused_flags) +{ + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + struct bpf_prog *old_prog = NULL; + struct cgroup_subsys_state *css; + struct bpf_prog_list *pl; + int err; + + if (flags & BPF_F_ALLOW_MULTI) { + if (!prog) + /* to detach MULTI prog the user has to specify valid FD + * of the program to be detached + */ + return -EINVAL; + } else { + if (list_empty(progs)) + /* report error when trying to detach and nothing is attached */ + return -ENOENT; + } + + if (flags & BPF_F_ALLOW_MULTI) { + /* find the prog and detach it */ + list_for_each_entry(pl, progs, node) { + if (pl->prog != prog) + continue; + old_prog = prog; + /* mark it deleted, so it's ignored while + * recomputing effective + */ + pl->prog = NULL; + break; + } + if (!old_prog) + return -ENOENT; + } else { + /* to maintain backward compatibility NONE and OVERRIDE cgroups + * allow detaching with invalid FD (prog==NULL) + */ + pl = list_first_entry(progs, typeof(*pl), node); + old_prog = pl->prog; + pl->prog = NULL; + } + + /* allocate and recompute effective prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + err = compute_effective_progs(desc, type, &desc->bpf.inactive); + if (err) + goto cleanup; + } + + /* all allocations were successful. Activate all prog arrays */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + activate_effective_progs(desc, type, desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* now can actually delete it from this cgroup list */ + list_del(&pl->node); + kfree(pl); + if (list_empty(progs)) + /* last program was detached, reset flags to zero */ + cgrp->bpf.flags[type] = 0; + + bpf_prog_put(old_prog); + static_branch_dec(&cgroup_bpf_enabled_key); + return 0; + +cleanup: + /* oom while computing effective. Free all computed effective arrays + * since they were not activated + */ + css_for_each_descendant_pre(css, &cgrp->self) { + struct cgroup *desc = container_of(css, struct cgroup, self); + + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + + /* and restore back old_prog */ + pl->prog = old_prog; + return err; } /** @@ -171,36 +403,26 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum bpf_attach_type type) { - struct bpf_prog *prog; + unsigned int offset = skb->data - skb_network_header(skb); + struct sock *save_sk; struct cgroup *cgrp; - int ret = 0; + int ret; if (!sk || !sk_fullsock(sk)) return 0; - if (sk->sk_family != AF_INET && - sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) { - unsigned int offset = skb->data - skb_network_header(skb); - struct sock *save_sk = skb->sk; - - skb->sk = sk; - __skb_push(skb, offset); - ret = bpf_prog_run_save_cb(prog, skb) == 1 ? 0 : -EPERM; - __skb_pull(skb, offset); - skb->sk = save_sk; - } - - rcu_read_unlock(); - - return ret; + save_sk = skb->sk; + skb->sk = sk; + __skb_push(skb, offset); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, + bpf_prog_run_save_cb); + __skb_pull(skb, offset); + skb->sk = save_sk; + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); @@ -221,19 +443,10 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sk) == 1 ? 0 : -EPERM; + int ret; - rcu_read_unlock(); - - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sk, BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); @@ -258,18 +471,10 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, enum bpf_attach_type type) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - struct bpf_prog *prog; - int ret = 0; - - - rcu_read_lock(); - - prog = rcu_dereference(cgrp->bpf.effective[type]); - if (prog) - ret = BPF_PROG_RUN(prog, sock_ops) == 1 ? 0 : -EPERM; - - rcu_read_unlock(); + int ret; - return ret; + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], sock_ops, + BPF_PROG_RUN); + return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 917cc04a0a94..6b49e1991ae7 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1381,6 +1381,37 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) } EXPORT_SYMBOL_GPL(bpf_prog_select_runtime); +/* to avoid allocating empty bpf_prog_array for cgroups that + * don't have bpf program attached use one global 'empty_prog_array' + * It will not be modified the caller of bpf_prog_array_alloc() + * (since caller requested prog_cnt == 0) + * that pointer should be 'freed' by bpf_prog_array_free() + */ +static struct { + struct bpf_prog_array hdr; + struct bpf_prog *null_prog; +} empty_prog_array = { + .null_prog = NULL, +}; + +struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +{ + if (prog_cnt) + return kzalloc(sizeof(struct bpf_prog_array) + + sizeof(struct bpf_prog *) * (prog_cnt + 1), + flags); + + return &empty_prog_array.hdr; +} + +void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) +{ + if (!progs || + progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + return; + kfree_rcu(progs, rcu); +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b927da66f653..51bee695d32c 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1168,6 +1168,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach) return 0; } +#define BPF_F_ATTACH_MASK \ + (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI) + static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; @@ -1181,7 +1184,7 @@ static int bpf_prog_attach(const union bpf_attr *attr) if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; - if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE) + if (attr->attach_flags & ~BPF_F_ATTACH_MASK) return -EINVAL; switch (attr->attach_type) { @@ -1212,8 +1215,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) return PTR_ERR(cgrp); } - ret = cgroup_bpf_update(cgrp, prog, attr->attach_type, - attr->attach_flags & BPF_F_ALLOW_OVERRIDE); + ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type, + attr->attach_flags); if (ret) bpf_prog_put(prog); cgroup_put(cgrp); @@ -1225,6 +1228,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) static int bpf_prog_detach(const union bpf_attr *attr) { + enum bpf_prog_type ptype; + struct bpf_prog *prog; struct cgroup *cgrp; int ret; @@ -1237,23 +1242,33 @@ static int bpf_prog_detach(const union bpf_attr *attr) switch (attr->attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: + ptype = BPF_PROG_TYPE_CGROUP_SKB; + break; case BPF_CGROUP_INET_SOCK_CREATE: + ptype = BPF_PROG_TYPE_CGROUP_SOCK; + break; case BPF_CGROUP_SOCK_OPS: - cgrp = cgroup_get_from_fd(attr->target_fd); - if (IS_ERR(cgrp)) - return PTR_ERR(cgrp); - - ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false); - cgroup_put(cgrp); + ptype = BPF_PROG_TYPE_SOCK_OPS; break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - ret = sockmap_get_from_fd(attr, false); - break; + return sockmap_get_from_fd(attr, false); default: return -EINVAL; } + cgrp = cgroup_get_from_fd(attr->target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + + prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); + if (IS_ERR(prog)) + prog = NULL; + + ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0); + if (prog) + bpf_prog_put(prog); + cgroup_put(cgrp); return ret; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..57eb866ae78d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) if (ret) goto destroy_root; + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + trace_cgroup_setup_root(root); /* @@ -4713,6 +4716,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_idr_free; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4747,13 +4753,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - if (parent) - cgroup_bpf_inherit(cgrp, parent); - cgroup_propagate_control(cgrp); return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5736,14 +5741,23 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable) +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct cgroup *parent = cgroup_parent(cgrp); int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); + ret = __cgroup_bpf_detach(cgrp, prog, type, flags); mutex_unlock(&cgroup_mutex); return ret; } -- cgit v1.2.3 From 468e2f64d220fe2dc11caa2bcb9b3a1e50fc7321 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:22 -0700 Subject: bpf: introduce BPF_PROG_QUERY command introduce BPF_PROG_QUERY command to retrieve a set of either attached programs to given cgroup or a set of effective programs that will execute for events within a cgroup Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 4 ++++ include/linux/bpf.h | 3 +++ include/uapi/linux/bpf.h | 13 +++++++++++++ kernel/bpf/cgroup.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 38 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 ++++++++++++++++++++++++++++++++++ kernel/cgroup/cgroup.c | 10 ++++++++++ 7 files changed, 148 insertions(+) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 102e56fbb6de..359b6f5d3d90 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -44,12 +44,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr); int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a6964b75f070..a67daea731ab 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -260,6 +260,9 @@ struct bpf_prog_array { struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt); #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ ({ \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 762f74bc6c47..cb2b9f95160a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -92,6 +92,7 @@ enum bpf_cmd { BPF_PROG_GET_FD_BY_ID, BPF_MAP_GET_FD_BY_ID, BPF_OBJ_GET_INFO_BY_FD, + BPF_PROG_QUERY, }; enum bpf_map_type { @@ -211,6 +212,9 @@ enum bpf_attach_type { /* Specify numa node during map creation */ #define BPF_F_NUMA_NODE (1U << 2) +/* flags for BPF_PROG_QUERY */ +#define BPF_F_QUERY_EFFECTIVE (1U << 0) + #define BPF_OBJ_NAME_LEN 16U union bpf_attr { @@ -289,6 +293,15 @@ union bpf_attr { __u32 info_len; __aligned_u64 info; } info; + + struct { /* anonymous struct used by BPF_PROG_QUERY command */ + __u32 target_fd; /* container object to query */ + __u32 attach_type; + __u32 query_flags; + __u32 attach_flags; + __aligned_u64 prog_ids; + __u32 prog_cnt; + } query; } __attribute__((aligned(8))); /* BPF helper function descriptions: diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 6b7500bbdb53..e88abc0865d5 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -384,6 +384,52 @@ cleanup: return err; } +/* Must be called with cgroup_mutex held to avoid races. */ +int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + enum bpf_attach_type type = attr->query.attach_type; + struct list_head *progs = &cgrp->bpf.progs[type]; + u32 flags = cgrp->bpf.flags[type]; + int cnt, ret = 0, i; + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) + cnt = bpf_prog_array_length(cgrp->bpf.effective[type]); + else + cnt = prog_list_length(progs); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) + return -EFAULT; + if (attr->query.prog_cnt == 0 || !prog_ids || !cnt) + /* return early if user requested only program count + flags */ + return 0; + if (attr->query.prog_cnt < cnt) { + cnt = attr->query.prog_cnt; + ret = -ENOSPC; + } + + if (attr->query.query_flags & BPF_F_QUERY_EFFECTIVE) { + return bpf_prog_array_copy_to_user(cgrp->bpf.effective[type], + prog_ids, cnt); + } else { + struct bpf_prog_list *pl; + u32 id; + + i = 0; + list_for_each_entry(pl, progs, node) { + id = pl->prog->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) + return -EFAULT; + if (++i == cnt) + break; + } + } + return ret; +} + /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6b49e1991ae7..eba966c09053 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1412,6 +1412,44 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) kfree_rcu(progs, rcu); } +int bpf_prog_array_length(struct bpf_prog_array __rcu *progs) +{ + struct bpf_prog **prog; + u32 cnt = 0; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) + cnt++; + rcu_read_unlock(); + return cnt; +} + +int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, + __u32 __user *prog_ids, u32 cnt) +{ + struct bpf_prog **prog; + u32 i = 0, id; + + rcu_read_lock(); + prog = rcu_dereference(progs)->progs; + for (; *prog; prog++) { + id = (*prog)->aux->id; + if (copy_to_user(prog_ids + i, &id, sizeof(id))) { + rcu_read_unlock(); + return -EFAULT; + } + if (++i == cnt) { + prog++; + break; + } + } + rcu_read_unlock(); + if (*prog) + return -ENOSPC; + return 0; +} + static void bpf_prog_free_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 51bee695d32c..0048cb24ba7b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1272,6 +1272,37 @@ static int bpf_prog_detach(const union bpf_attr *attr) return ret; } +#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt + +static int bpf_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + struct cgroup *cgrp; + int ret; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (CHECK_ATTR(BPF_PROG_QUERY)) + return -EINVAL; + if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) + return -EINVAL; + + switch (attr->query.attach_type) { + case BPF_CGROUP_INET_INGRESS: + case BPF_CGROUP_INET_EGRESS: + case BPF_CGROUP_INET_SOCK_CREATE: + case BPF_CGROUP_SOCK_OPS: + break; + default: + return -EINVAL; + } + cgrp = cgroup_get_from_fd(attr->query.target_fd); + if (IS_ERR(cgrp)) + return PTR_ERR(cgrp); + ret = cgroup_bpf_query(cgrp, attr, uattr); + cgroup_put(cgrp); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration @@ -1568,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; + case BPF_PROG_QUERY: + err = bpf_prog_query(&attr, uattr); + break; #endif case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 57eb866ae78d..269512b94a94 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, mutex_unlock(&cgroup_mutex); return ret; } +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + mutex_unlock(&cgroup_mutex); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ -- cgit v1.2.3 From 473d97343f94ff20f5196078314e4dd83156d3a2 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Thu, 5 Oct 2017 21:52:11 -0700 Subject: bpf: Change bpf_obj_name_cpy() to better ensure map's name is init by 0 During get_info_by_fd, the prog/map name is memcpy-ed. It depends on the prog->aux->name and map->name to be zero initialized. bpf_prog_aux is easy to guarantee that aux->name is zero init. The name in bpf_map may be harder to be guaranteed in the future when new map type is added. Hence, this patch makes bpf_obj_name_cpy() to always zero init the prog/map name. Suggested-by: Daniel Borkmann Signed-off-by: Martin KaFai Lau Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0048cb24ba7b..d124e702e040 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -322,6 +322,8 @@ static int bpf_obj_name_cpy(char *dst, const char *src) { const char *end = src + BPF_OBJ_NAME_LEN; + memset(dst, 0, BPF_OBJ_NAME_LEN); + /* Copy all isalnum() and '_' char */ while (src < end && *src) { if (!isalnum(*src) && *src != '_') @@ -333,9 +335,6 @@ static int bpf_obj_name_cpy(char *dst, const char *src) if (src == end) return -EINVAL; - /* '\0' terminates dst */ - *dst = 0; - return 0; } -- cgit v1.2.3 From 6710e1126934d8b4372b4d2f9ae1646cd3f151bf Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Mon, 16 Oct 2017 12:19:28 +0200 Subject: bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP The 'cpumap' is primarily used as a backend map for XDP BPF helper call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. This patch implement the main part of the map. It is not connected to the XDP redirect system yet, and no SKB allocation are done yet. The main concern in this patch is to ensure the datapath can run without any locking. This adds complexity to the setup and tear-down procedure, which assumptions are extra carefully documented in the code comments. V2: - make sure array isn't larger than NR_CPUS - make sure CPUs added is a valid possible CPU V3: fix nitpicks from Jakub Kicinski V5: - Restrict map allocation to root / CAP_SYS_ADMIN - WARN_ON_ONCE if queue is not empty on tear-down - Return -EPERM on memlock limit instead of -ENOMEM - Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup() - Moved cpu_map_enqueue() to next patch V6: all notice by Daniel Borkmann - Fix err return code in cpu_map_alloc() introduced in V5 - Move cpu_possible() check after max_entries boundary check - Forbid usage initially in check_map_func_compatibility() V7: - Fix alloc error path spotted by Daniel Borkmann - Did stress test adding+removing CPUs from the map concurrently - Fixed refcnt issue on cpu_map_entry, kthread started too soon - Make sure packets are flushed during tear-down, involved use of rcu_barrier() and kthread_run only exit after queue is empty - Fix alloc error path in __cpu_map_entry_alloc() for ptr_ring V8: - Nitpicking comments and gramma by Edward Cree - Fix missing semi-colon introduced in V7 due to rebasing - Move struct bpf_cpu_map_entry members cpu+map_id to tracepoint patch Signed-off-by: Jesper Dangaard Brouer Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/cpumap.c | 560 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 8 +- kernel/bpf/verifier.c | 5 + tools/include/uapi/linux/bpf.h | 1 + 7 files changed, 576 insertions(+), 1 deletion(-) create mode 100644 kernel/bpf/cpumap.c (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 6f1a567667b8..814c1081a4a9 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) #ifdef CONFIG_STREAM_PARSER BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) #endif diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6db9e1d679cd..4303fb6c3817 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 53fb09f92e3f..e597daae6120 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o +obj-$(CONFIG_BPF_SYSCALL) += cpumap.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c new file mode 100644 index 000000000000..e1e25ddba038 --- /dev/null +++ b/kernel/bpf/cpumap.c @@ -0,0 +1,560 @@ +/* bpf/cpumap.c + * + * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. + * Released under terms in GPL version 2. See COPYING. + */ + +/* The 'cpumap' is primarily used as a backend map for XDP BPF helper + * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'. + * + * Unlike devmap which redirects XDP frames out another NIC device, + * this map type redirects raw XDP frames to another CPU. The remote + * CPU will do SKB-allocation and call the normal network stack. + * + * This is a scalability and isolation mechanism, that allow + * separating the early driver network XDP layer, from the rest of the + * netstack, and assigning dedicated CPUs for this stage. This + * basically allows for 10G wirespeed pre-filtering via bpf. + */ +#include +#include +#include + +#include +#include +#include +#include + +/* General idea: XDP packets getting XDP redirected to another CPU, + * will maximum be stored/queued for one driver ->poll() call. It is + * guaranteed that setting flush bit and flush operation happen on + * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() + * which queue in bpf_cpu_map_entry contains packets. + */ + +#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct xdp_bulk_queue { + void *q[CPU_MAP_BULK_SIZE]; + unsigned int count; +}; + +/* Struct for every remote "destination" CPU in map */ +struct bpf_cpu_map_entry { + u32 qsize; /* Queue size placeholder for map lookup */ + + /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ + struct xdp_bulk_queue __percpu *bulkq; + + /* Queue with potential multi-producers, and single-consumer kthread */ + struct ptr_ring *queue; + struct task_struct *kthread; + struct work_struct kthread_stop_wq; + + atomic_t refcnt; /* Control when this struct can be free'ed */ + struct rcu_head rcu; +}; + +struct bpf_cpu_map { + struct bpf_map map; + /* Below members specific for map type */ + struct bpf_cpu_map_entry **cpu_map; + unsigned long __percpu *flush_needed; +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq); + +static u64 cpu_map_bitmap_size(const union bpf_attr *attr) +{ + return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); +} + +static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) +{ + struct bpf_cpu_map *cmap; + int err = -ENOMEM; + u64 cost; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + return ERR_PTR(-EINVAL); + + cmap = kzalloc(sizeof(*cmap), GFP_USER); + if (!cmap) + return ERR_PTR(-ENOMEM); + + /* mandatory map attributes */ + cmap->map.map_type = attr->map_type; + cmap->map.key_size = attr->key_size; + cmap->map.value_size = attr->value_size; + cmap->map.max_entries = attr->max_entries; + cmap->map.map_flags = attr->map_flags; + cmap->map.numa_node = bpf_map_attr_numa_node(attr); + + /* Pre-limit array size based on NR_CPUS, not final CPU check */ + if (cmap->map.max_entries > NR_CPUS) { + err = -E2BIG; + goto free_cmap; + } + + /* make sure page count doesn't overflow */ + cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); + cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_cmap; + cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + ret = bpf_map_precharge_memlock(cmap->map.pages); + if (ret) { + err = ret; + goto free_cmap; + } + + /* A per cpu bitfield with a bit per possible CPU in map */ + cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), + __alignof__(unsigned long)); + if (!cmap->flush_needed) + goto free_cmap; + + /* Alloc array for possible remote "destination" CPUs */ + cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * + sizeof(struct bpf_cpu_map_entry *), + cmap->map.numa_node); + if (!cmap->cpu_map) + goto free_percpu; + + return &cmap->map; +free_percpu: + free_percpu(cmap->flush_needed); +free_cmap: + kfree(cmap); + return ERR_PTR(err); +} + +void __cpu_map_queue_destructor(void *ptr) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + if (WARN_ON_ONCE(ptr)) + page_frag_free(ptr); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); + kfree(rcpu->queue); + kfree(rcpu); + } +} + +static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + atomic_inc(&rcpu->refcnt); +} + +/* called from workqueue, to workaround syscall using preempt_disable */ +static void cpu_map_kthread_stop(struct work_struct *work) +{ + struct bpf_cpu_map_entry *rcpu; + + rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq); + + /* Wait for flush in __cpu_map_entry_free(), via full RCU barrier, + * as it waits until all in-flight call_rcu() callbacks complete. + */ + rcu_barrier(); + + /* kthread_stop will wake_up_process and wait for it to complete */ + kthread_stop(rcpu->kthread); +} + +static int cpu_map_kthread_run(void *data) +{ + struct bpf_cpu_map_entry *rcpu = data; + + set_current_state(TASK_INTERRUPTIBLE); + + /* When kthread gives stop order, then rcpu have been disconnected + * from map, thus no new packets can enter. Remaining in-flight + * per CPU stored packets are flushed to this queue. Wait honoring + * kthread_stop signal until queue is empty. + */ + while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { + struct xdp_pkt *xdp_pkt; + + schedule(); + /* Do work */ + while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) { + /* For now just "refcnt-free" */ + page_frag_free(xdp_pkt); + } + __set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + put_cpu_map_entry(rcpu); + return 0; +} + +struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id) +{ + gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN; + struct bpf_cpu_map_entry *rcpu; + int numa, err; + + /* Have map->numa_node, but choose node of redirect target CPU */ + numa = cpu_to_node(cpu); + + rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + if (!rcpu) + return NULL; + + /* Alloc percpu bulkq */ + rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), + sizeof(void *), gfp); + if (!rcpu->bulkq) + goto free_rcu; + + /* Alloc queue */ + rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + if (!rcpu->queue) + goto free_bulkq; + + err = ptr_ring_init(rcpu->queue, qsize, gfp); + if (err) + goto free_queue; + + rcpu->qsize = qsize; + + /* Setup kthread */ + rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, + "cpumap/%d/map:%d", cpu, map_id); + if (IS_ERR(rcpu->kthread)) + goto free_ptr_ring; + + get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */ + get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */ + + /* Make sure kthread runs on a single CPU */ + kthread_bind(rcpu->kthread, cpu); + wake_up_process(rcpu->kthread); + + return rcpu; + +free_ptr_ring: + ptr_ring_cleanup(rcpu->queue, NULL); +free_queue: + kfree(rcpu->queue); +free_bulkq: + free_percpu(rcpu->bulkq); +free_rcu: + kfree(rcpu); + return NULL; +} + +void __cpu_map_entry_free(struct rcu_head *rcu) +{ + struct bpf_cpu_map_entry *rcpu; + int cpu; + + /* This cpu_map_entry have been disconnected from map and one + * RCU graze-period have elapsed. Thus, XDP cannot queue any + * new packets and cannot change/set flush_needed that can + * find this entry. + */ + rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu); + + /* Flush remaining packets in percpu bulkq */ + for_each_online_cpu(cpu) { + struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); + + /* No concurrent bq_enqueue can run at this point */ + bq_flush_to_queue(rcpu, bq); + } + free_percpu(rcpu->bulkq); + /* Cannot kthread_stop() here, last put free rcpu resources */ + put_cpu_map_entry(rcpu); +} + +/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to + * ensure any driver rcu critical sections have completed, but this + * does not guarantee a flush has happened yet. Because driver side + * rcu_read_lock/unlock only protects the running XDP program. The + * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a + * pending flush op doesn't fail. + * + * The bpf_cpu_map_entry is still used by the kthread, and there can + * still be pending packets (in queue and percpu bulkq). A refcnt + * makes sure to last user (kthread_stop vs. call_rcu) free memory + * resources. + * + * The rcu callback __cpu_map_entry_free flush remaining packets in + * percpu bulkq to queue. Due to caller map_delete_elem() disable + * preemption, cannot call kthread_stop() to make sure queue is empty. + * Instead a work_queue is started for stopping kthread, + * cpu_map_kthread_stop, which waits for an RCU graze period before + * stopping kthread, emptying the queue. + */ +void __cpu_map_entry_replace(struct bpf_cpu_map *cmap, + u32 key_cpu, struct bpf_cpu_map_entry *rcpu) +{ + struct bpf_cpu_map_entry *old_rcpu; + + old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu); + if (old_rcpu) { + call_rcu(&old_rcpu->rcu, __cpu_map_entry_free); + INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop); + schedule_work(&old_rcpu->kthread_stop_wq); + } +} + +int cpu_map_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 key_cpu = *(u32 *)key; + + if (key_cpu >= map->max_entries) + return -EINVAL; + + /* notice caller map_delete_elem() use preempt_disable() */ + __cpu_map_entry_replace(cmap, key_cpu, NULL); + return 0; +} + +int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + /* Array index key correspond to CPU number */ + u32 key_cpu = *(u32 *)key; + /* Value is the queue size */ + u32 qsize = *(u32 *)value; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(key_cpu >= cmap->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + if (unlikely(qsize > 16384)) /* sanity limit on qsize */ + return -EOVERFLOW; + + /* Make sure CPU is a valid possible cpu */ + if (!cpu_possible(key_cpu)) + return -ENODEV; + + if (qsize == 0) { + rcpu = NULL; /* Same as deleting */ + } else { + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); + if (!rcpu) + return -ENOMEM; + } + rcu_read_lock(); + __cpu_map_entry_replace(cmap, key_cpu, rcpu); + rcu_read_unlock(); + return 0; +} + +void cpu_map_free(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + int cpu; + u32 i; + + /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the bpf programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete. The rcu critical section only guarantees + * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map. + * It does __not__ ensure pending flush operations (if any) are + * complete. + */ + synchronize_rcu(); + + /* To ensure all pending flush operations have completed wait for flush + * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * Because the above synchronize_rcu() ensures the map is disconnected + * from the program we can assume no new bits will be set. + */ + for_each_online_cpu(cpu) { + unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + + while (!bitmap_empty(bitmap, cmap->map.max_entries)) + cond_resched(); + } + + /* For cpu_map the remote CPUs can still be using the entries + * (struct bpf_cpu_map_entry). + */ + for (i = 0; i < cmap->map.max_entries; i++) { + struct bpf_cpu_map_entry *rcpu; + + rcpu = READ_ONCE(cmap->cpu_map[i]); + if (!rcpu) + continue; + + /* bq flush and cleanup happens after RCU graze-period */ + __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ + } + free_percpu(cmap->flush_needed); + bpf_map_area_free(cmap->cpu_map); + kfree(cmap); +} + +struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + struct bpf_cpu_map_entry *rcpu; + + if (key >= map->max_entries) + return NULL; + + rcpu = READ_ONCE(cmap->cpu_map[key]); + return rcpu; +} + +static void *cpu_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_cpu_map_entry *rcpu = + __cpu_map_lookup_elem(map, *(u32 *)key); + + return rcpu ? &rcpu->qsize : NULL; +} + +static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= cmap->map.max_entries) { + *next = 0; + return 0; + } + + if (index == cmap->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +const struct bpf_map_ops cpu_map_ops = { + .map_alloc = cpu_map_alloc, + .map_free = cpu_map_free, + .map_delete_elem = cpu_map_delete_elem, + .map_update_elem = cpu_map_update_elem, + .map_lookup_elem = cpu_map_lookup_elem, + .map_get_next_key = cpu_map_get_next_key, +}; + +static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, + struct xdp_bulk_queue *bq) +{ + struct ptr_ring *q; + int i; + + if (unlikely(!bq->count)) + return 0; + + q = rcpu->queue; + spin_lock(&q->producer_lock); + + for (i = 0; i < bq->count; i++) { + void *xdp_pkt = bq->q[i]; + int err; + + err = __ptr_ring_produce(q, xdp_pkt); + if (err) { + /* Free xdp_pkt */ + page_frag_free(xdp_pkt); + } + } + bq->count = 0; + spin_unlock(&q->producer_lock); + + return 0; +} + +/* Notice: Will change in later patch */ +struct xdp_pkt { + void *data; + u16 len; + u16 headroom; +}; + +/* Runs under RCU-read-side, plus in softirq under NAPI protection. + * Thus, safe percpu variable access. + */ +int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +{ + struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + + if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) + bq_flush_to_queue(rcpu, bq); + + /* Notice, xdp_buff/page MUST be queued here, long enough for + * driver to code invoking us to finished, due to driver + * (e.g. ixgbe) recycle tricks based on page-refcnt. + * + * Thus, incoming xdp_pkt is always queued here (else we race + * with another CPU on page-refcnt and remaining driver code). + * Queue time is very short, as driver will invoke flush + * operation, when completing napi->poll call. + */ + bq->q[bq->count++] = xdp_pkt; + return 0; +} + +void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + + __set_bit(bit, bitmap); +} + +void __cpu_map_flush(struct bpf_map *map) +{ + struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); + unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); + u32 bit; + + /* The napi->poll softirq makes sure __cpu_map_insert_ctx() + * and __cpu_map_flush() happen on same CPU. Thus, the percpu + * bitmap indicate which percpu bulkq have packets. + */ + for_each_set_bit(bit, bitmap, map->max_entries) { + struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); + struct xdp_bulk_queue *bq; + + /* This is possible if entry is removed by user space + * between xdp redirect and flush op. + */ + if (unlikely(!rcpu)) + continue; + + __clear_bit(bit, bitmap); + + /* Flush all frames in bulkq to real queue */ + bq = this_cpu_ptr(rcpu->bulkq); + bq_flush_to_queue(rcpu, bq); + + /* If already running, costs spin_lock_irqsave + smb_mb */ + wake_up_process(rcpu->kthread); + } +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d124e702e040..54fba06942f5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -592,6 +592,12 @@ static int map_update_elem(union bpf_attr *attr) if (copy_from_user(value, uvalue, value_size) != 0) goto free_value; + /* Need to create a kthread, thus must support schedule */ + if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + err = map->ops->map_update_elem(map, key, value, attr->flags); + goto out; + } + /* must increment bpf_prog_active to avoid kprobe+bpf triggering from * inside bpf map update or delete otherwise deadlocks are possible */ @@ -622,7 +628,7 @@ static int map_update_elem(union bpf_attr *attr) } __this_cpu_dec(bpf_prog_active); preempt_enable(); - +out: if (!err) trace_bpf_map_update_elem(map, ufd, key, value); free_value: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9755279d94cb..cefa64be9a2f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1444,6 +1444,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; + /* Restrict bpf side of cpumap, open when use-cases appear */ + case BPF_MAP_TYPE_CPUMAP: + if (func_id != BPF_FUNC_redirect_map) + goto error; + break; case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH_OF_MAPS: if (func_id != BPF_FUNC_map_lookup_elem) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fb4fb81ce5b0..fa93033dc521 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -112,6 +112,7 @@ enum bpf_map_type { BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, + BPF_MAP_TYPE_CPUMAP, }; enum bpf_prog_type { -- cgit v1.2.3 From 7de16e3a35578f4f5accc6f5f23970310483d0a2 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:53 -0700 Subject: bpf: split verifier and program ops struct bpf_verifier_ops contains both verifier ops and operations used later during program's lifetime (test_run). Split the runtime ops into a different structure. BPF_PROG_TYPE() will now append ## _prog_ops or ## _verifier_ops to the names. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 15 ++++++++++----- include/linux/bpf_types.h | 28 ++++++++++++++-------------- kernel/bpf/syscall.c | 16 +++++++++++++--- kernel/bpf/verifier.c | 12 ++++++------ kernel/trace/bpf_trace.c | 15 ++++++++++++--- net/core/filter.c | 45 ++++++++++++++++++++++++++++++++++++--------- 6 files changed, 91 insertions(+), 40 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6d4dd844828a..e1fba5504ca5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -157,6 +157,11 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +struct bpf_prog_ops { + int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +}; + struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id); @@ -172,8 +177,6 @@ struct bpf_verifier_ops { const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); - int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, - union bpf_attr __user *uattr); }; struct bpf_prog_aux { @@ -184,7 +187,8 @@ struct bpf_prog_aux { u32 id; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; - const struct bpf_verifier_ops *ops; + const struct bpf_prog_ops *ops; + const struct bpf_verifier_ops *vops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; @@ -279,8 +283,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); -#define BPF_PROG_TYPE(_id, _ops) \ - extern const struct bpf_verifier_ops _ops; +#define BPF_PROG_TYPE(_id, _name) \ + extern const struct bpf_prog_ops _name ## _prog_ops; \ + extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #include diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 814c1081a4a9..36418ad43245 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -1,22 +1,22 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_inout) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint_prog_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event_prog_ops) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 54fba06942f5..444902b5a30d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -739,9 +739,18 @@ err_put: return err; } -static const struct bpf_verifier_ops * const bpf_prog_types[] = { -#define BPF_PROG_TYPE(_id, _ops) \ - [_id] = &_ops, +static const struct bpf_prog_ops * const bpf_prog_types[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _prog_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, #define BPF_MAP_TYPE(_id, _ops) #include #undef BPF_PROG_TYPE @@ -754,6 +763,7 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) return -EINVAL; prog->aux->ops = bpf_prog_types[type]; + prog->aux->vops = bpf_verifier_ops[type]; prog->type = type; return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e4d5136725a2..38e24d69fc95 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -856,8 +856,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, *reg_type = info.reg_type; return 0; } - } else if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t, &info)) { + } else if (env->prog->aux->vops->is_valid_access && + env->prog->aux->vops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -1565,8 +1565,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return -EINVAL; } - if (env->prog->aux->ops->get_func_proto) - fn = env->prog->aux->ops->get_func_proto(func_id); + if (env->prog->aux->vops->get_func_proto) + fn = env->prog->aux->vops->get_func_proto(func_id); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), @@ -4035,7 +4035,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->ops; + const struct bpf_verifier_ops *ops = env->prog->aux->vops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4236,7 +4236,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->ops->get_func_proto(insn->imm); + fn = prog->aux->vops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 04ea5314f2bc..3126da2f468a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -561,11 +561,14 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type return true; } -const struct bpf_verifier_ops kprobe_prog_ops = { +const struct bpf_verifier_ops kprobe_verifier_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; +const struct bpf_prog_ops kprobe_prog_ops = { +}; + BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { @@ -667,11 +670,14 @@ static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type return true; } -const struct bpf_verifier_ops tracepoint_prog_ops = { +const struct bpf_verifier_ops tracepoint_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; +const struct bpf_prog_ops tracepoint_prog_ops = { +}; + static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { @@ -727,8 +733,11 @@ static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops perf_event_prog_ops = { +const struct bpf_verifier_ops perf_event_verifier_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; + +const struct bpf_prog_ops perf_event_prog_ops = { +}; diff --git a/net/core/filter.c b/net/core/filter.c index 4d88e0665c41..1dd3034f846f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4395,68 +4395,95 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; } -const struct bpf_verifier_ops sk_filter_prog_ops = { +const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, }; -const struct bpf_verifier_ops tc_cls_act_prog_ops = { +const struct bpf_prog_ops sk_filter_prog_ops = { +}; + +const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .get_func_proto = tc_cls_act_func_proto, .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops tc_cls_act_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops xdp_prog_ops = { +const struct bpf_verifier_ops xdp_verifier_ops = { .get_func_proto = xdp_func_proto, .is_valid_access = xdp_is_valid_access, .convert_ctx_access = xdp_convert_ctx_access, +}; + +const struct bpf_prog_ops xdp_prog_ops = { .test_run = bpf_prog_test_run_xdp, }; -const struct bpf_verifier_ops cg_skb_prog_ops = { +const struct bpf_verifier_ops cg_skb_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops cg_skb_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_inout_prog_ops = { +const struct bpf_verifier_ops lwt_inout_verifier_ops = { .get_func_proto = lwt_inout_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, +}; + +const struct bpf_prog_ops lwt_inout_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops lwt_xmit_prog_ops = { +const struct bpf_verifier_ops lwt_xmit_verifier_ops = { .get_func_proto = lwt_xmit_func_proto, .is_valid_access = lwt_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, +}; + +const struct bpf_prog_ops lwt_xmit_prog_ops = { .test_run = bpf_prog_test_run_skb, }; -const struct bpf_verifier_ops cg_sock_prog_ops = { +const struct bpf_verifier_ops cg_sock_verifier_ops = { .get_func_proto = sock_filter_func_proto, .is_valid_access = sock_filter_is_valid_access, .convert_ctx_access = sock_filter_convert_ctx_access, }; -const struct bpf_verifier_ops sock_ops_prog_ops = { +const struct bpf_prog_ops cg_sock_prog_ops = { +}; + +const struct bpf_verifier_ops sock_ops_verifier_ops = { .get_func_proto = sock_ops_func_proto, .is_valid_access = sock_ops_is_valid_access, .convert_ctx_access = sock_ops_convert_ctx_access, }; -const struct bpf_verifier_ops sk_skb_prog_ops = { +const struct bpf_prog_ops sock_ops_prog_ops = { +}; + +const struct bpf_verifier_ops sk_skb_verifier_ops = { .get_func_proto = sk_skb_func_proto, .is_valid_access = sk_skb_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, .gen_prologue = sk_skb_prologue, }; +const struct bpf_prog_ops sk_skb_prog_ops = { +}; + int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; -- cgit v1.2.3 From 00176a34d9e27ab1e77db75fe13abc005cffe0ca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 16 Oct 2017 16:40:54 -0700 Subject: bpf: remove the verifier ops from program structure Since the verifier ops don't have to be associated with the program for its entire lifetime we can move it to verifier's struct bpf_verifier_env. Signed-off-by: Jakub Kicinski Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 - include/linux/bpf_verifier.h | 1 + kernel/bpf/syscall.c | 10 ---------- kernel/bpf/verifier.c | 23 +++++++++++++++++------ 4 files changed, 18 insertions(+), 17 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e1fba5504ca5..cf91977e8719 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -188,7 +188,6 @@ struct bpf_prog_aux { struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; - const struct bpf_verifier_ops *vops; struct bpf_map **used_maps; struct bpf_prog *prog; struct user_struct *user; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index f00ef751c1c5..feeaea93d959 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -141,6 +141,7 @@ struct bpf_ext_analyzer_ops { */ struct bpf_verifier_env { struct bpf_prog *prog; /* eBPF program being verified */ + const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ int stack_size; /* number of states to be processed */ bool strict_alignment; /* perform strict pointer alignment checks */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 444902b5a30d..0e893cac6795 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -748,22 +748,12 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = { #undef BPF_MAP_TYPE }; -static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { -#define BPF_PROG_TYPE(_id, _name) \ - [_id] = & _name ## _verifier_ops, -#define BPF_MAP_TYPE(_id, _ops) -#include -#undef BPF_PROG_TYPE -#undef BPF_MAP_TYPE -}; - static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) return -EINVAL; prog->aux->ops = bpf_prog_types[type]; - prog->aux->vops = bpf_verifier_ops[type]; prog->type = type; return 0; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 38e24d69fc95..3b6e2c550e96 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -23,6 +23,15 @@ #include "disasm.h" +static const struct bpf_verifier_ops * const bpf_verifier_ops[] = { +#define BPF_PROG_TYPE(_id, _name) \ + [_id] = & _name ## _verifier_ops, +#define BPF_MAP_TYPE(_id, _ops) +#include +#undef BPF_PROG_TYPE +#undef BPF_MAP_TYPE +}; + /* bpf_check() is a static code analyzer that walks eBPF program * instruction by instruction and updates register/stack state. * All paths of conditional branches are analyzed until 'bpf_exit' insn. @@ -856,8 +865,8 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, *reg_type = info.reg_type; return 0; } - } else if (env->prog->aux->vops->is_valid_access && - env->prog->aux->vops->is_valid_access(off, size, t, &info)) { + } else if (env->ops->is_valid_access && + env->ops->is_valid_access(off, size, t, &info)) { /* A non zero info.ctx_field_size indicates that this field is a * candidate for later verifier transformation to load the whole * field and then apply a mask when accessed with a narrower @@ -1565,8 +1574,8 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return -EINVAL; } - if (env->prog->aux->vops->get_func_proto) - fn = env->prog->aux->vops->get_func_proto(func_id); + if (env->ops->get_func_proto) + fn = env->ops->get_func_proto(func_id); if (!fn) { verbose(env, "unknown func %s#%d\n", func_id_name(func_id), @@ -4035,7 +4044,7 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of */ static int convert_ctx_accesses(struct bpf_verifier_env *env) { - const struct bpf_verifier_ops *ops = env->prog->aux->vops; + const struct bpf_verifier_ops *ops = env->ops; int i, cnt, size, ctx_field_size, delta = 0; const int insn_cnt = env->prog->len; struct bpf_insn insn_buf[16], *insn; @@ -4236,7 +4245,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) insn = new_prog->insnsi + i + delta; } patch_call_imm: - fn = prog->aux->vops->get_func_proto(insn->imm); + fn = env->ops->get_func_proto(insn->imm); /* all functions that have prototype and verifier allowed * programs to call them, must be real in-kernel functions */ @@ -4294,6 +4303,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!env->insn_aux_data) goto err_free_env; env->prog = *prog; + env->ops = bpf_verifier_ops[env->prog->type]; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -4406,6 +4416,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, if (!env->insn_aux_data) goto err_free_env; env->prog = prog; + env->ops = bpf_verifier_ops[env->prog->type]; env->analyzer_ops = ops; env->analyzer_priv = priv; -- cgit v1.2.3 From 6e71b04a82248ccf13a94b85cbc674a9fefe53f5 Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Wed, 18 Oct 2017 13:00:22 -0700 Subject: bpf: Add file mode configuration into bpf maps Introduce the map read/write flags to the eBPF syscalls that returns the map fd. The flags is used to set up the file mode when construct a new file descriptor for bpf maps. To not break the backward capability, the f_flags is set to O_RDWR if the flag passed by syscall is 0. Otherwise it should be O_RDONLY or O_WRONLY. When the userspace want to modify or read the map content, it will check the file mode to see if it is allowed to make the change. Signed-off-by: Chenbo Feng Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 8 +++-- include/uapi/linux/bpf.h | 6 ++++ kernel/bpf/arraymap.c | 6 +++- kernel/bpf/devmap.c | 5 ++- kernel/bpf/hashtab.c | 5 +-- kernel/bpf/inode.c | 15 ++++++--- kernel/bpf/lpm_trie.c | 3 +- kernel/bpf/sockmap.c | 5 ++- kernel/bpf/stackmap.c | 5 ++- kernel/bpf/syscall.c | 88 ++++++++++++++++++++++++++++++++++++++++++------ net/netfilter/xt_bpf.c | 2 +- 11 files changed, 122 insertions(+), 26 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d67ccdc0099f..3e5508f2fa87 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -315,11 +315,11 @@ void bpf_map_area_free(void *base); extern int sysctl_unprivileged_bpf_disabled; -int bpf_map_new_fd(struct bpf_map *map); +int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); int bpf_obj_pin_user(u32 ufd, const char __user *pathname); -int bpf_obj_get_user(const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname, int flags); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); @@ -338,6 +338,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); +int bpf_get_file_flag(int flags); + /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent @@ -421,7 +423,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } -static inline int bpf_obj_get_user(const char __user *pathname) +static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4303fb6c3817..d83f95ea6a1b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -218,6 +218,10 @@ enum bpf_attach_type { #define BPF_OBJ_NAME_LEN 16U +/* Flags for accessing BPF object */ +#define BPF_F_RDONLY (1U << 3) +#define BPF_F_WRONLY (1U << 4) + union bpf_attr { struct { /* anonymous struct used by BPF_MAP_CREATE command */ __u32 map_type; /* one of enum bpf_map_type */ @@ -260,6 +264,7 @@ union bpf_attr { struct { /* anonymous struct used by BPF_OBJ_* commands */ __aligned_u64 pathname; __u32 bpf_fd; + __u32 file_flags; }; struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */ @@ -287,6 +292,7 @@ union bpf_attr { __u32 map_id; }; __u32 next_id; + __u32 open_flags; }; struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 68d866628be0..988c04c91e10 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -19,6 +19,9 @@ #include "map_in_map.h" +#define ARRAY_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + static void bpf_array_free_percpu(struct bpf_array *array) { int i; @@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE || + attr->value_size == 0 || + attr->map_flags & ~ARRAY_CREATE_FLAG_MASK || (percpu && numa_node != NUMA_NO_NODE)) return ERR_PTR(-EINVAL); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index e093d9a2c4dd..e5d3de7cff2e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -50,6 +50,9 @@ #include #include +#define DEV_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_dtab_netdev { struct net_device *dev; struct bpf_dtab *dtab; @@ -80,7 +83,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); dtab = kzalloc(sizeof(*dtab), GFP_USER); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 431126f31ea3..919955236e63 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -18,8 +18,9 @@ #include "bpf_lru_list.h" #include "map_in_map.h" -#define HTAB_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE) +#define HTAB_CREATE_FLAG_MASK \ + (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) struct bucket { struct hlist_nulls_head head; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index be1dde967208..01aaef1a77c5 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -295,7 +295,7 @@ out: } static void *bpf_obj_do_get(const struct filename *pathname, - enum bpf_type *type) + enum bpf_type *type, int flags) { struct inode *inode; struct path path; @@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname, return ERR_PTR(ret); inode = d_backing_inode(path.dentry); - ret = inode_permission(inode, MAY_WRITE); + ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; @@ -326,18 +326,23 @@ out: return ERR_PTR(ret); } -int bpf_obj_get_user(const char __user *pathname) +int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; + int f_flags; void *raw; + f_flags = bpf_get_file_flag(flags); + if (f_flags < 0) + return f_flags; + pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); - raw = bpf_obj_do_get(pname, &type); + raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; @@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname) if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) - ret = bpf_map_new_fd(raw); + ret = bpf_map_new_fd(raw, f_flags); else goto out; diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 34d8a690ea05..885e45479680 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -495,7 +495,8 @@ out: #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index a298d6666698..86ec846f2d5e 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -40,6 +40,9 @@ #include #include +#define SOCK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct bpf_stab { struct bpf_map map; struct sock **sock_map; @@ -489,7 +492,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE) + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); if (attr->value_size > KMALLOC_MAX_SIZE) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 135be433e9a0..a15bc636cc98 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -11,6 +11,9 @@ #include #include "percpu_freelist.h" +#define STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + struct stack_map_bucket { struct pcpu_freelist_node fnode; u32 hash; @@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); - if (attr->map_flags & ~BPF_F_NUMA_NODE) + if (attr->map_flags & ~STACK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); /* check sanity of attributes */ diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0e893cac6795..676a06e6b322 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -34,6 +34,8 @@ #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) +#define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) + DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); @@ -294,17 +296,48 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) } #endif +static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, + loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_READ. + */ + return -EINVAL; +} + +static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, + size_t siz, loff_t *ppos) +{ + /* We need this handler such that alloc_file() enables + * f_mode with FMODE_CAN_WRITE. + */ + return -EINVAL; +} + static const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; -int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map, int flags) { return anon_inode_getfd("bpf-map", &bpf_map_fops, map, - O_RDWR | O_CLOEXEC); + flags | O_CLOEXEC); +} + +int bpf_get_file_flag(int flags) +{ + if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) + return -EINVAL; + if (flags & BPF_F_RDONLY) + return O_RDONLY; + if (flags & BPF_F_WRONLY) + return O_WRONLY; + return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ @@ -344,12 +377,17 @@ static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_map *map; + int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); + if (f_flags < 0) + return f_flags; + if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) @@ -375,7 +413,7 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map; - err = bpf_map_new_fd(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put() is needed because the above @@ -490,6 +528,11 @@ static int map_lookup_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -570,6 +613,11 @@ static int map_update_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -659,6 +707,11 @@ static int map_delete_elem(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -702,6 +755,11 @@ static int map_get_next_key(union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); + if (!(f.file->f_mode & FMODE_CAN_READ)) { + err = -EPERM; + goto err_put; + } + if (ukey) { key = memdup_user(ukey, map->key_size); if (IS_ERR(key)) { @@ -908,6 +966,8 @@ static const struct file_operations bpf_prog_fops = { .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, + .read = bpf_dummy_read, + .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) @@ -1117,11 +1177,11 @@ free_prog_nouncharge: return err; } -#define BPF_OBJ_LAST_FIELD bpf_fd +#define BPF_OBJ_LAST_FIELD file_flags static int bpf_obj_pin(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ)) + if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0) return -EINVAL; return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname)); @@ -1129,10 +1189,12 @@ static int bpf_obj_pin(const union bpf_attr *attr) static int bpf_obj_get(const union bpf_attr *attr) { - if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || + attr->file_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; - return bpf_obj_get_user(u64_to_user_ptr(attr->pathname)); + return bpf_obj_get_user(u64_to_user_ptr(attr->pathname), + attr->file_flags); } #ifdef CONFIG_CGROUP_BPF @@ -1392,20 +1454,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) return fd; } -#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id +#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; + int f_flags; int fd; - if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID)) + if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || + attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; + f_flags = bpf_get_file_flag(attr->open_flags); + if (f_flags < 0) + return f_flags; + spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) @@ -1417,7 +1485,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) if (IS_ERR(map)) return PTR_ERR(map); - fd = bpf_map_new_fd(map); + fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put(map); diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 29123934887b..041da0d9c06f 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -56,7 +56,7 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) int retval, fd; set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path); + fd = bpf_obj_get_user(path, 0); set_fs(oldfs); if (fd < 0) return fd; -- cgit v1.2.3 From afdb09c720b62b8090584c11151d856df330e57d Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Wed, 18 Oct 2017 13:00:24 -0700 Subject: security: bpf: Add LSM hooks for bpf object related syscall Introduce several LSM hooks for the syscalls that will allow the userspace to access to eBPF object such as eBPF programs and eBPF maps. The security check is aimed to enforce a per object security protection for eBPF object so only processes with the right priviliges can read/write to a specific map or use a specific eBPF program. Besides that, a general security hook is added before the multiplexer of bpf syscall to check the cmd and the attribute used for the command. The actual security module can decide which command need to be checked and how the cmd should be checked. Signed-off-by: Chenbo Feng Acked-by: James Morris Signed-off-by: David S. Miller --- include/linux/bpf.h | 6 ++++++ include/linux/lsm_hooks.h | 54 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/security.h | 45 +++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 +++++++++++++++++++++++++++-- security/security.c | 32 ++++++++++++++++++++++++++++ 5 files changed, 169 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3e5508f2fa87..84c192da3e0b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -57,6 +57,9 @@ struct bpf_map { atomic_t usercnt; struct bpf_map *inner_map_meta; char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif }; /* function argument constraints */ @@ -193,6 +196,9 @@ struct bpf_prog_aux { struct user_struct *user; u64 load_time; /* ns since boottime */ char name[BPF_OBJ_NAME_LEN]; +#ifdef CONFIG_SECURITY + void *security; +#endif union { struct work_struct work; struct rcu_head rcu; diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index c9258124e417..7161d8e7ee79 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1351,6 +1351,40 @@ * @inode we wish to get the security context of. * @ctx is a pointer in which to place the allocated security context. * @ctxlen points to the place to put the length of @ctx. + * + * Security hooks for using the eBPF maps and programs functionalities through + * eBPF syscalls. + * + * @bpf: + * Do a initial check for all bpf syscalls after the attribute is copied + * into the kernel. The actual security module can implement their own + * rules to check the specific cmd they need. + * + * @bpf_map: + * Do a check when the kernel generate and return a file descriptor for + * eBPF maps. + * + * @map: bpf map that we want to access + * @mask: the access flags + * + * @bpf_prog: + * Do a check when the kernel generate and return a file descriptor for + * eBPF programs. + * + * @prog: bpf prog that userspace want to use. + * + * @bpf_map_alloc_security: + * Initialize the security field inside bpf map. + * + * @bpf_map_free_security: + * Clean up the security information stored inside bpf map. + * + * @bpf_prog_alloc_security: + * Initialize the security field inside bpf program. + * + * @bpf_prog_free_security: + * Clean up the security information stored inside bpf prog. + * */ union security_list_options { int (*binder_set_context_mgr)(struct task_struct *mgr); @@ -1682,6 +1716,17 @@ union security_list_options { struct audit_context *actx); void (*audit_rule_free)(void *lsmrule); #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL + int (*bpf)(int cmd, union bpf_attr *attr, + unsigned int size); + int (*bpf_map)(struct bpf_map *map, fmode_t fmode); + int (*bpf_prog)(struct bpf_prog *prog); + int (*bpf_map_alloc_security)(struct bpf_map *map); + void (*bpf_map_free_security)(struct bpf_map *map); + int (*bpf_prog_alloc_security)(struct bpf_prog_aux *aux); + void (*bpf_prog_free_security)(struct bpf_prog_aux *aux); +#endif /* CONFIG_BPF_SYSCALL */ }; struct security_hook_heads { @@ -1901,6 +1946,15 @@ struct security_hook_heads { struct list_head audit_rule_match; struct list_head audit_rule_free; #endif /* CONFIG_AUDIT */ +#ifdef CONFIG_BPF_SYSCALL + struct list_head bpf; + struct list_head bpf_map; + struct list_head bpf_prog; + struct list_head bpf_map_alloc_security; + struct list_head bpf_map_free_security; + struct list_head bpf_prog_alloc_security; + struct list_head bpf_prog_free_security; +#endif /* CONFIG_BPF_SYSCALL */ } __randomize_layout; /* diff --git a/include/linux/security.h b/include/linux/security.h index ce6265960d6c..18800b0911e5 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -31,6 +31,7 @@ #include #include #include +#include struct linux_binprm; struct cred; @@ -1730,6 +1731,50 @@ static inline void securityfs_remove(struct dentry *dentry) #endif +#ifdef CONFIG_BPF_SYSCALL +#ifdef CONFIG_SECURITY +extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); +extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); +extern int security_bpf_prog(struct bpf_prog *prog); +extern int security_bpf_map_alloc(struct bpf_map *map); +extern void security_bpf_map_free(struct bpf_map *map); +extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); +extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +#else +static inline int security_bpf(int cmd, union bpf_attr *attr, + unsigned int size) +{ + return 0; +} + +static inline int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return 0; +} + +static inline int security_bpf_prog(struct bpf_prog *prog) +{ + return 0; +} + +static inline int security_bpf_map_alloc(struct bpf_map *map) +{ + return 0; +} + +static inline void security_bpf_map_free(struct bpf_map *map) +{ } + +static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return 0; +} + +static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ } +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_BPF_SYSCALL */ + #ifdef CONFIG_SECURITY static inline char *alloc_secdata(void) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 676a06e6b322..5cb56d06b48d 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -212,6 +212,7 @@ static void bpf_map_free_deferred(struct work_struct *work) struct bpf_map *map = container_of(work, struct bpf_map, work); bpf_map_uncharge_memlock(map); + security_bpf_map_free(map); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -325,6 +326,12 @@ static const struct file_operations bpf_map_fops = { int bpf_map_new_fd(struct bpf_map *map, int flags) { + int ret; + + ret = security_bpf_map(map, OPEN_FMODE(flags)); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } @@ -405,10 +412,14 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); - err = bpf_map_charge_memlock(map); + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; + err = bpf_map_charge_memlock(map); + if (err) + goto free_map_sec; + err = bpf_map_alloc_id(map); if (err) goto free_map; @@ -430,6 +441,8 @@ static int map_create(union bpf_attr *attr) free_map: bpf_map_uncharge_memlock(map); +free_map_sec: + security_bpf_map_free(map); free_map_nouncharge: map->ops->map_free(map); return err; @@ -914,6 +927,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) free_used_maps(aux); bpf_prog_uncharge_memlock(aux->prog); + security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -972,6 +986,12 @@ static const struct file_operations bpf_prog_fops = { int bpf_prog_new_fd(struct bpf_prog *prog) { + int ret; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ret; + return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } @@ -1111,10 +1131,14 @@ static int bpf_prog_load(union bpf_attr *attr) if (!prog) return -ENOMEM; - err = bpf_prog_charge_memlock(prog); + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog_nouncharge; + err = bpf_prog_charge_memlock(prog); + if (err) + goto free_prog_sec; + prog->len = attr->insn_cnt; err = -EFAULT; @@ -1172,6 +1196,8 @@ free_used_maps: free_used_maps(prog->aux); free_prog: bpf_prog_uncharge_memlock(prog); +free_prog_sec: + security_bpf_prog_free(prog->aux); free_prog_nouncharge: bpf_prog_free(prog); return err; @@ -1640,6 +1666,10 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (copy_from_user(&attr, uattr, size) != 0) return -EFAULT; + err = security_bpf(cmd, &attr, size); + if (err < 0) + return err; + switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); diff --git a/security/security.c b/security/security.c index 4bf0f571b4ef..1cd8526cb0b7 100644 --- a/security/security.c +++ b/security/security.c @@ -12,6 +12,7 @@ * (at your option) any later version. */ +#include #include #include #include @@ -1703,3 +1704,34 @@ int security_audit_rule_match(u32 secid, u32 field, u32 op, void *lsmrule, actx); } #endif /* CONFIG_AUDIT */ + +#ifdef CONFIG_BPF_SYSCALL +int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) +{ + return call_int_hook(bpf, 0, cmd, attr, size); +} +int security_bpf_map(struct bpf_map *map, fmode_t fmode) +{ + return call_int_hook(bpf_map, 0, map, fmode); +} +int security_bpf_prog(struct bpf_prog *prog) +{ + return call_int_hook(bpf_prog, 0, prog); +} +int security_bpf_map_alloc(struct bpf_map *map) +{ + return call_int_hook(bpf_map_alloc_security, 0, map); +} +int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +{ + return call_int_hook(bpf_prog_alloc_security, 0, aux); +} +void security_bpf_map_free(struct bpf_map *map) +{ + call_void_hook(bpf_map_free_security, map); +} +void security_bpf_prog_free(struct bpf_prog_aux *aux) +{ + call_void_hook(bpf_prog_free_security, aux); +} +#endif /* CONFIG_BPF_SYSCALL */ -- cgit v1.2.3 From f66e448cfda021b0bcd884f26709796fe19c7cc1 Mon Sep 17 00:00:00 2001 From: Chenbo Feng Date: Wed, 18 Oct 2017 13:00:26 -0700 Subject: selinux: bpf: Add addtional check for bpf object file receive Introduce a bpf object related check when sending and receiving files through unix domain socket as well as binder. It checks if the receiving process have privilege to read/write the bpf map or use the bpf program. This check is necessary because the bpf maps and programs are using a anonymous inode as their shared inode so the normal way of checking the files and sockets when passing between processes cannot work properly on eBPF object. This check only works when the BPF_SYSCALL is configured. Signed-off-by: Chenbo Feng Acked-by: Stephen Smalley Reviewed-by: James Morris Signed-off-by: David S. Miller --- include/linux/bpf.h | 3 +++ kernel/bpf/syscall.c | 4 ++-- security/selinux/hooks.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 2 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 84c192da3e0b..1e334b248ff6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -288,6 +288,9 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); +extern const struct file_operations bpf_map_fops; +extern const struct file_operations bpf_prog_fops; + #define BPF_PROG_TYPE(_id, _name) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5cb56d06b48d..323be2473c4b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -315,7 +315,7 @@ static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, return -EINVAL; } -static const struct file_operations bpf_map_fops = { +const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif @@ -975,7 +975,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) } #endif -static const struct file_operations bpf_prog_fops = { +const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 12cf7de8cbed..2e3a627fc0b1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1815,6 +1815,10 @@ static inline int file_path_has_perm(const struct cred *cred, return inode_has_perm(cred, file_inode(file), av, &ad); } +#ifdef CONFIG_BPF_SYSCALL +static int bpf_fd_pass(struct file *file, u32 sid); +#endif + /* Check whether a task can use an open file descriptor to access an inode in a given way. Check access to the descriptor itself, and then use dentry_has_perm to @@ -1845,6 +1849,12 @@ static int file_has_perm(const struct cred *cred, goto out; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, cred_sid(cred)); + if (rc) + return rc; +#endif + /* av is zero if only checking access to the descriptor. */ rc = 0; if (av) @@ -2165,6 +2175,12 @@ static int selinux_binder_transfer_file(struct task_struct *from, return rc; } +#ifdef CONFIG_BPF_SYSCALL + rc = bpf_fd_pass(file, sid); + if (rc) + return rc; +#endif + if (unlikely(IS_PRIVATE(d_backing_inode(dentry)))) return 0; @@ -6288,6 +6304,39 @@ static u32 bpf_map_fmode_to_av(fmode_t fmode) return av; } +/* This function will check the file pass through unix socket or binder to see + * if it is a bpf related object. And apply correspinding checks on the bpf + * object based on the type. The bpf maps and programs, not like other files and + * socket, are using a shared anonymous inode inside the kernel as their inode. + * So checking that inode cannot identify if the process have privilege to + * access the bpf object and that's why we have to add this additional check in + * selinux_file_receive and selinux_binder_transfer_files. + */ +static int bpf_fd_pass(struct file *file, u32 sid) +{ + struct bpf_security_struct *bpfsec; + struct bpf_prog *prog; + struct bpf_map *map; + int ret; + + if (file->f_op == &bpf_map_fops) { + map = file->private_data; + bpfsec = map->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + bpf_map_fmode_to_av(file->f_mode), NULL); + if (ret) + return ret; + } else if (file->f_op == &bpf_prog_fops) { + prog = file->private_data; + bpfsec = prog->aux->security; + ret = avc_has_perm(sid, bpfsec->sid, SECCLASS_BPF, + BPF__PROG_RUN, NULL); + if (ret) + return ret; + } + return 0; +} + static int selinux_bpf_map(struct bpf_map *map, fmode_t fmode) { u32 sid = current_sid(); -- cgit v1.2.3 From ab3f0063c48c26c927851b6767824e35a716d878 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:17 -0700 Subject: bpf: offload: add infrastructure for loading programs for a specific netdev The fact that we don't know which device the program is going to be used on is quite limiting in current eBPF infrastructure. We have to reverse or limit the changes which kernel makes to the loaded bytecode if we want it to be offloaded to a networking device. We also have to invent new APIs for debugging and troubleshooting support. Make it possible to load programs for a specific netdev. This helps us to bring the debug information closer to the core eBPF infrastructure (e.g. we will be able to reuse the verifer log in device JIT). It allows device JITs to perform translation on the original bytecode. __bpf_prog_get() when called to get a reference for an attachment point will now refuse to give it if program has a device assigned. Following patches will add a version of that function which passes the expected netdev in. @type argument in __bpf_prog_get() is renamed to attach_type to make it clearer that it's only set on attachment. All calls to ndo_bpf are protected by rtnl, only verifier callbacks are not. We need a wait queue to make sure netdev doesn't get destroyed while verifier is still running and calling its driver. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 36 +++++++++ include/linux/bpf_verifier.h | 10 +++ include/linux/netdevice.h | 14 ++++ include/uapi/linux/bpf.h | 1 + kernel/bpf/Makefile | 1 + kernel/bpf/core.c | 10 ++- kernel/bpf/offload.c | 182 +++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 17 +++- kernel/bpf/verifier.c | 15 +++- 9 files changed, 278 insertions(+), 8 deletions(-) create mode 100644 kernel/bpf/offload.c (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 520aeebe0d93..e45d43f9ec92 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -15,6 +15,7 @@ #include #include #include +#include struct perf_event; struct bpf_prog; @@ -182,6 +183,16 @@ struct bpf_verifier_ops { struct bpf_prog *prog, u32 *target_size); }; +struct bpf_dev_offload { + struct bpf_prog *prog; + struct net_device *netdev; + void *dev_priv; + struct list_head offloads; + bool dev_state; + bool verifier_running; + wait_queue_head_t verifier_done; +}; + struct bpf_prog_aux { atomic_t refcnt; u32 used_map_cnt; @@ -199,6 +210,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_dev_offload *offload; union { struct work_struct work; struct rcu_head rcu; @@ -317,6 +329,7 @@ extern const struct file_operations bpf_prog_fops; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE +extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; @@ -491,6 +504,29 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, } #endif /* CONFIG_BPF_SYSCALL */ +int bpf_prog_offload_compile(struct bpf_prog *prog); +void bpf_prog_offload_destroy(struct bpf_prog *prog); + +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return aux->offload; +} +#else +static inline int bpf_prog_offload_init(struct bpf_prog *prog, + union bpf_attr *attr) +{ + return -EOPNOTSUPP; +} + +static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) +{ + return false; +} +#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ + #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3b0976aaac75..e45011dbc02d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -153,6 +153,7 @@ struct bpf_verifier_env { struct bpf_verifier_state *cur_state; /* current verifier state */ struct bpf_verifier_state_list **explored_states; /* search pruning optimization */ const struct bpf_ext_analyzer_ops *analyzer_ops; /* external analyzer ops */ + const struct bpf_ext_analyzer_ops *dev_ops; /* device analyzer ops */ void *analyzer_priv; /* pointer to external analyzer's private data */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ @@ -169,6 +170,15 @@ static inline struct bpf_reg_state *cur_regs(struct bpf_verifier_env *env) return env->cur_state->regs; } +#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env); +#else +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + return -EOPNOTSUPP; +} +#endif + int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops, void *priv); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9af9feaaeb64..fda527ccb263 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -797,8 +797,13 @@ enum bpf_netdev_command { * is equivalent to XDP_ATTACHED_DRV. */ XDP_QUERY_PROG, + /* BPF program for offload callbacks, invoked at program load time. */ + BPF_OFFLOAD_VERIFIER_PREP, + BPF_OFFLOAD_TRANSLATE, + BPF_OFFLOAD_DESTROY, }; +struct bpf_ext_analyzer_ops; struct netlink_ext_ack; struct netdev_bpf { @@ -815,6 +820,15 @@ struct netdev_bpf { u8 prog_attached; u32 prog_id; }; + /* BPF_OFFLOAD_VERIFIER_PREP */ + struct { + struct bpf_prog *prog; + const struct bpf_ext_analyzer_ops *ops; /* callee set */ + } verifier; + /* BPF_OFFLOAD_TRANSLATE, BPF_OFFLOAD_DESTROY */ + struct { + struct bpf_prog *prog; + } offload; }; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a9820677c2ff..80d191a93fb0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -260,6 +260,7 @@ union bpf_attr { __u32 kern_version; /* checked when prog_type=kprobe */ __u32 prog_flags; char prog_name[BPF_OBJ_NAME_LEN]; + __u32 prog_target_ifindex; /* ifindex of netdev to prep for */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 16e95c8e749e..e691da0b3bab 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,6 +7,7 @@ obj-$(CONFIG_BPF_SYSCALL) += disasm.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) obj-$(CONFIG_BPF_SYSCALL) += sockmap.o endif diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 7fe448799d76..8a6c37762330 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1380,7 +1380,13 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) * valid program, which in this case would simply not * be JITed, but falls back to the interpreter. */ - fp = bpf_int_jit_compile(fp); + if (!bpf_prog_is_dev_bound(fp->aux)) { + fp = bpf_int_jit_compile(fp); + } else { + *err = bpf_prog_offload_compile(fp); + if (*err) + return fp; + } bpf_prog_lock_ro(fp); /* The tail call compatibility check can only be done at @@ -1549,6 +1555,8 @@ static void bpf_prog_free_deferred(struct work_struct *work) struct bpf_prog_aux *aux; aux = container_of(work, struct bpf_prog_aux, work); + if (bpf_prog_is_dev_bound(aux)) + bpf_prog_offload_destroy(aux->prog); bpf_jit_free(aux->prog); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c new file mode 100644 index 000000000000..5553e0e2f8b1 --- /dev/null +++ b/kernel/bpf/offload.c @@ -0,0 +1,182 @@ +#include +#include +#include +#include +#include +#include +#include + +/* protected by RTNL */ +static LIST_HEAD(bpf_prog_offload_devs); + +int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +{ + struct net *net = current->nsproxy->net_ns; + struct bpf_dev_offload *offload; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->prog_flags) + return -EINVAL; + + offload = kzalloc(sizeof(*offload), GFP_USER); + if (!offload) + return -ENOMEM; + + offload->prog = prog; + init_waitqueue_head(&offload->verifier_done); + + rtnl_lock(); + offload->netdev = __dev_get_by_index(net, attr->prog_target_ifindex); + if (!offload->netdev) { + rtnl_unlock(); + kfree(offload); + return -EINVAL; + } + + prog->aux->offload = offload; + list_add_tail(&offload->offloads, &bpf_prog_offload_devs); + rtnl_unlock(); + + return 0; +} + +static int __bpf_offload_ndo(struct bpf_prog *prog, enum bpf_netdev_command cmd, + struct netdev_bpf *data) +{ + struct net_device *netdev = prog->aux->offload->netdev; + + ASSERT_RTNL(); + + if (!netdev) + return -ENODEV; + if (!netdev->netdev_ops->ndo_bpf) + return -EOPNOTSUPP; + + data->command = cmd; + + return netdev->netdev_ops->ndo_bpf(netdev, data); +} + +int bpf_prog_offload_verifier_prep(struct bpf_verifier_env *env) +{ + struct netdev_bpf data = {}; + int err; + + data.verifier.prog = env->prog; + + rtnl_lock(); + err = __bpf_offload_ndo(env->prog, BPF_OFFLOAD_VERIFIER_PREP, &data); + if (err) + goto exit_unlock; + + env->dev_ops = data.verifier.ops; + + env->prog->aux->offload->dev_state = true; + env->prog->aux->offload->verifier_running = true; +exit_unlock: + rtnl_unlock(); + return err; +} + +static void __bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + + data.offload.prog = prog; + + if (offload->verifier_running) + wait_event(offload->verifier_done, !offload->verifier_running); + + if (offload->dev_state) + WARN_ON(__bpf_offload_ndo(prog, BPF_OFFLOAD_DESTROY, &data)); + + offload->dev_state = false; + list_del_init(&offload->offloads); + offload->netdev = NULL; +} + +void bpf_prog_offload_destroy(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + __bpf_prog_offload_destroy(prog); + rtnl_unlock(); + + kfree(offload); +} + +static int bpf_prog_offload_translate(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + struct netdev_bpf data = {}; + int ret; + + data.offload.prog = prog; + + offload->verifier_running = false; + wake_up(&offload->verifier_done); + + rtnl_lock(); + ret = __bpf_offload_ndo(prog, BPF_OFFLOAD_TRANSLATE, &data); + rtnl_unlock(); + + return ret; +} + +static unsigned int bpf_prog_warn_on_exec(const void *ctx, + const struct bpf_insn *insn) +{ + WARN(1, "attempt to execute device eBPF program on the host!"); + return 0; +} + +int bpf_prog_offload_compile(struct bpf_prog *prog) +{ + prog->bpf_func = bpf_prog_warn_on_exec; + + return bpf_prog_offload_translate(prog); +} + +const struct bpf_prog_ops bpf_offload_prog_ops = { +}; + +static int bpf_offload_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_dev_offload *offload, *tmp; + + ASSERT_RTNL(); + + switch (event) { + case NETDEV_UNREGISTER: + list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, + offloads) { + if (offload->netdev == netdev) + __bpf_prog_offload_destroy(offload->prog); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block bpf_offload_notifier = { + .notifier_call = bpf_offload_notification, +}; + +static int __init bpf_offload_init(void) +{ + register_netdevice_notifier(&bpf_offload_notifier); + return 0; +} + +subsys_initcall(bpf_offload_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 323be2473c4b..1574b9f0f24e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -824,7 +824,10 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) return -EINVAL; - prog->aux->ops = bpf_prog_types[type]; + if (!bpf_prog_is_dev_bound(prog->aux)) + prog->aux->ops = bpf_prog_types[type]; + else + prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } @@ -1054,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -1062,7 +1065,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *type) prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (type && prog->type != *type) { + if (attach_type && (prog->type != *attach_type || prog->aux->offload)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -1089,7 +1092,7 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) EXPORT_SYMBOL_GPL(bpf_prog_get_type); /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD prog_name +#define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex static int bpf_prog_load(union bpf_attr *attr) { @@ -1152,6 +1155,12 @@ static int bpf_prog_load(union bpf_attr *attr) atomic_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; + if (attr->prog_target_ifindex) { + err = bpf_prog_offload_init(prog, attr); + if (err) + goto free_prog; + } + /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 04357ad5a812..51aabb32ad67 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3736,10 +3736,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) static int ext_analyzer_insn_hook(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx) { - if (!env->analyzer_ops || !env->analyzer_ops->insn_hook) - return 0; + if (env->analyzer_ops && env->analyzer_ops->insn_hook) + return env->analyzer_ops->insn_hook(env, insn_idx, + prev_insn_idx); + if (env->dev_ops && env->dev_ops->insn_hook) + return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx); - return env->analyzer_ops->insn_hook(env, insn_idx, prev_insn_idx); + return 0; } static int do_check(struct bpf_verifier_env *env) @@ -4516,6 +4519,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + if (env->prog->aux->offload) { + ret = bpf_prog_offload_verifier_prep(env); + if (ret) + goto err_unlock; + } + ret = replace_map_fd_with_map_ptr(env); if (ret < 0) goto skip_full_check; -- cgit v1.2.3 From bd601b6ada11fdfb9e277f24ad2eb54bc599156b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:18 -0700 Subject: bpf: report offload info to user space Extend struct bpf_prog_info to contain information about program being bound to a device. Since the netdev may get destroyed while program still exists we need a flag to indicate the program is loaded for a device, even if the device is gone. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 6 ++++++ kernel/bpf/offload.c | 12 ++++++++++++ kernel/bpf/syscall.c | 5 +++++ 4 files changed, 24 insertions(+) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e45d43f9ec92..98bacd0fa5cc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -506,6 +506,7 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 80d191a93fb0..4455dd195201 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -895,6 +895,10 @@ enum sk_action { #define BPF_TAG_SIZE 8 +enum bpf_prog_status { + BPF_PROG_STATUS_DEV_BOUND = (1 << 0), +}; + struct bpf_prog_info { __u32 type; __u32 id; @@ -908,6 +912,8 @@ struct bpf_prog_info { __u32 nr_map_ids; __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; + __u32 ifindex; + __u32 status; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 5553e0e2f8b1..2816feb38be1 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -144,6 +144,18 @@ int bpf_prog_offload_compile(struct bpf_prog *prog) return bpf_prog_offload_translate(prog); } +u32 bpf_prog_offload_ifindex(struct bpf_prog *prog) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + u32 ifindex; + + rtnl_lock(); + ifindex = offload->netdev ? offload->netdev->ifindex : 0; + rtnl_unlock(); + + return ifindex; +} + const struct bpf_prog_ops bpf_offload_prog_ops = { }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 1574b9f0f24e..3217c20ea91b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1592,6 +1592,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, return -EFAULT; } + if (bpf_prog_is_dev_bound(prog->aux)) { + info.status |= BPF_PROG_STATUS_DEV_BOUND; + info.ifindex = bpf_prog_offload_ifindex(prog); + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) -- cgit v1.2.3 From 248f346ffe9508dee0039db4ac839cb31ba3bdec Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:20 -0700 Subject: xdp: allow attaching programs loaded for specific device Pass the netdev pointer to bpf_prog_get_type(). This way BPF code can decide whether the device matches what the code was loaded/translated for. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- include/linux/bpf.h | 10 ++++++++++ kernel/bpf/syscall.c | 33 +++++++++++++++++++++++++++++---- net/core/dev.c | 6 +++++- 3 files changed, 44 insertions(+), 5 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 98bacd0fa5cc..c397934f91dd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -335,6 +335,8 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev); struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); @@ -428,6 +430,14 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, { return ERR_PTR(-EOPNOTSUPP); } + +static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, + enum bpf_prog_type type, + struct net_device *netdev) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3217c20ea91b..68f9123acd39 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1057,7 +1057,22 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) +static bool bpf_prog_can_attach(struct bpf_prog *prog, + enum bpf_prog_type *attach_type, + struct net_device *netdev) +{ + struct bpf_dev_offload *offload = prog->aux->offload; + + if (prog->type != *attach_type) + return false; + if (offload && offload->netdev != netdev) + return false; + + return true; +} + +static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, + struct net_device *netdev) { struct fd f = fdget(ufd); struct bpf_prog *prog; @@ -1065,7 +1080,7 @@ static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type) prog = ____bpf_prog_get(f); if (IS_ERR(prog)) return prog; - if (attach_type && (prog->type != *attach_type || prog->aux->offload)) { + if (attach_type && !bpf_prog_can_attach(prog, attach_type, netdev)) { prog = ERR_PTR(-EINVAL); goto out; } @@ -1078,12 +1093,12 @@ out: struct bpf_prog *bpf_prog_get(u32 ufd) { - return __bpf_prog_get(ufd, NULL); + return __bpf_prog_get(ufd, NULL, NULL); } struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type); + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, NULL); if (!IS_ERR(prog)) trace_bpf_prog_get_type(prog); @@ -1091,6 +1106,16 @@ struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) } EXPORT_SYMBOL_GPL(bpf_prog_get_type); +struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, + struct net_device *netdev) +{ + struct bpf_prog *prog = __bpf_prog_get(ufd, &type, netdev); + + if (!IS_ERR(prog)) + trace_bpf_prog_get_type(prog); + return prog; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex diff --git a/net/core/dev.c b/net/core/dev.c index 10cde58d3275..30b5fe32c525 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7157,7 +7157,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, __dev_xdp_attached(dev, bpf_op, NULL)) return -EBUSY; - prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); + if (bpf_op == ops->ndo_bpf) + prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, + dev); + else + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP); if (IS_ERR(prog)) return PTR_ERR(prog); } -- cgit v1.2.3 From 6c8dfe21c435cf2953e3cee43e12180cbc4f0820 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Nov 2017 13:56:21 -0700 Subject: cls_bpf: allow attaching programs loaded for specific device If TC program is loaded with skip_sw flag, we should allow the device-specific programs to be accepted. Signed-off-by: Jakub Kicinski Reviewed-by: Simon Horman Reviewed-by: Quentin Monnet Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 1 + net/sched/cls_bpf.c | 10 +++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'kernel/bpf/syscall.c') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 68f9123acd39..416d70cdfc76 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1115,6 +1115,7 @@ struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, trace_bpf_prog_get_type(prog); return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD prog_target_ifindex diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index bc3edde1b9d7..dc9bd9a0070b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -374,7 +374,7 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) } static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, - const struct tcf_proto *tp) + u32 gen_flags, const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -382,7 +382,11 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, bpf_fd = nla_get_u32(tb[TCA_BPF_FD]); - fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); + if (gen_flags & TCA_CLS_FLAGS_SKIP_SW) + fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS, + qdisc_dev(tp->q)); + else + fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS); if (IS_ERR(fp)) return PTR_ERR(fp); @@ -440,7 +444,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, prog->gen_flags = gen_flags; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, tp); + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) return ret; -- cgit v1.2.3 From ebc614f687369f9df99828572b1d85a7c2de3d92 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Sun, 5 Nov 2017 08:15:32 -0500 Subject: bpf, cgroup: implement eBPF-based device controller for cgroup v2 Cgroup v2 lacks the device controller, provided by cgroup v1. This patch adds a new eBPF program type, which in combination of previously added ability to attach multiple eBPF programs to a cgroup, will provide a similar functionality, but with some additional flexibility. This patch introduces a BPF_PROG_TYPE_CGROUP_DEVICE program type. A program takes major and minor device numbers, device type (block/character) and access type (mknod/read/write) as parameters and returns an integer which defines if the operation should be allowed or terminated with -EPERM. Signed-off-by: Roman Gushchin Acked-by: Alexei Starovoitov Acked-by: Tejun Heo Cc: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf-cgroup.h | 15 ++++++++++ include/linux/bpf_types.h | 3 ++ include/linux/device_cgroup.h | 8 ++++- include/uapi/linux/bpf.h | 15 ++++++++++ kernel/bpf/cgroup.c | 67 ++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 7 +++++ kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 15 ++++++++++ 8 files changed, 130 insertions(+), 1 deletion(-) (limited to 'kernel/bpf/syscall.c') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 87a7db9feb38..a7f16e0f8d68 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -67,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum bpf_attach_type type); +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type); + /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */ #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb) \ ({ \ @@ -112,6 +115,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, } \ __ret; \ }) + +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_check_dev_permission(type, major, minor, \ + access, \ + BPF_CGROUP_DEVICE); \ + \ + __ret; \ +}) #else struct cgroup_bpf {}; @@ -122,6 +136,7 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #endif /* CONFIG_CGROUP_BPF */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 53c5b9ad7220..978c1d9c9383 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -19,6 +19,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) #endif +#ifdef CONFIG_CGROUP_BPF +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) +#endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h index 2d93d7ecd479..8557efe096dc 100644 --- a/include/linux/device_cgroup.h +++ b/include/linux/device_cgroup.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include +#include #define DEVCG_ACC_MKNOD 1 #define DEVCG_ACC_READ 2 @@ -19,10 +20,15 @@ static inline int __devcgroup_check_permission(short type, u32 major, u32 minor, { return 0; } #endif -#ifdef CONFIG_CGROUP_DEVICE +#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF) static inline int devcgroup_check_permission(short type, u32 major, u32 minor, short access) { + int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access); + + if (rc) + return -EPERM; + return __devcgroup_check_permission(type, major, minor, access); } diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4455dd195201..e880ae6434ee 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -132,6 +132,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, }; enum bpf_attach_type { @@ -141,6 +142,7 @@ enum bpf_attach_type { BPF_CGROUP_SOCK_OPS, BPF_SK_SKB_STREAM_PARSER, BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, __MAX_BPF_ATTACH_TYPE }; @@ -991,4 +993,17 @@ struct bpf_perf_event_value { __u64 running; }; +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + __u32 access_type; /* (access << 16) | type */ + __u32 major; + __u32 minor; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 3db5a17fcfe8..b789ab78d28f 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -522,3 +522,70 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, return ret == 1 ? 0 : -EPERM; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); + +int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, + short access, enum bpf_attach_type type) +{ + struct cgroup *cgrp; + struct bpf_cgroup_dev_ctx ctx = { + .access_type = (access << 16) | dev_type, + .major = major, + .minor = minor, + }; + int allow = 1; + + rcu_read_lock(); + cgrp = task_dfl_cgroup(current); + allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, + BPF_PROG_RUN); + rcu_read_unlock(); + + return !allow; +} +EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission); + +static const struct bpf_func_proto * +cgroup_dev_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + case BPF_FUNC_get_current_uid_gid: + return &bpf_get_current_uid_gid_proto; + case BPF_FUNC_trace_printk: + if (capable(CAP_SYS_ADMIN)) + return bpf_get_trace_printk_proto(); + default: + return NULL; + } +} + +static bool cgroup_dev_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (type == BPF_WRITE) + return false; + + if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx)) + return false; + /* The verifier guarantees that size > 0. */ + if (off % size != 0) + return false; + if (size != sizeof(__u32)) + return false; + + return true; +} + +const struct bpf_prog_ops cg_dev_prog_ops = { +}; + +const struct bpf_verifier_ops cg_dev_verifier_ops = { + .get_func_proto = cgroup_dev_func_proto, + .is_valid_access = cgroup_dev_is_valid_access, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 416d70cdfc76..09badc37e864 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1326,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, true); @@ -1378,6 +1381,9 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_SOCK_OPS: ptype = BPF_PROG_TYPE_SOCK_OPS; break; + case BPF_CGROUP_DEVICE: + ptype = BPF_PROG_TYPE_CGROUP_DEVICE; + break; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: return sockmap_get_from_fd(attr, false); @@ -1420,6 +1426,7 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_SOCK_OPS: + case BPF_CGROUP_DEVICE: break; default: return -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index add845fe788a..4a942e2e753d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3124,6 +3124,7 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_SOCK_OPS: + case BPF_PROG_TYPE_CGROUP_DEVICE: break; default: return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e92f62cf933a..b280f37cd057 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -131,6 +131,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_LWT_XMIT, BPF_PROG_TYPE_SOCK_OPS, BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_CGROUP_DEVICE, }; enum bpf_attach_type { @@ -140,6 +141,7 @@ enum bpf_attach_type { BPF_CGROUP_SOCK_OPS, BPF_SK_SKB_STREAM_PARSER, BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_DEVICE, __MAX_BPF_ATTACH_TYPE }; @@ -990,4 +992,17 @@ struct bpf_perf_event_value { __u64 running; }; +#define BPF_DEVCG_ACC_MKNOD (1ULL << 0) +#define BPF_DEVCG_ACC_READ (1ULL << 1) +#define BPF_DEVCG_ACC_WRITE (1ULL << 2) + +#define BPF_DEVCG_DEV_BLOCK (1ULL << 0) +#define BPF_DEVCG_DEV_CHAR (1ULL << 1) + +struct bpf_cgroup_dev_ctx { + __u32 access_type; /* (access << 16) | type */ + __u32 major; + __u32 minor; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ -- cgit v1.2.3