From e454cf5958538666635488030046b6a84a22d447 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Mon, 18 Sep 2017 15:30:55 -0400 Subject: bpf: Implement map_delete_elem for BPF_MAP_TYPE_LPM_TRIE This is a simple non-recursive delete operation. It prunes paths of empty nodes in the tree, but it does not try to further compress the tree as nodes are removed. Signed-off-by: Craig Gallek Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/lpm_trie.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b767844a76f..9d58a576b2ae 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -389,10 +389,84 @@ out: return ret; } -static int trie_delete_elem(struct bpf_map *map, void *key) +/* Called from syscall or from eBPF program */ +static int trie_delete_elem(struct bpf_map *map, void *_key) { - /* TODO */ - return -ENOSYS; + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct bpf_lpm_trie_key *key = _key; + struct lpm_trie_node __rcu **trim; + struct lpm_trie_node *node; + unsigned long irq_flags; + unsigned int next_bit; + size_t matchlen = 0; + int ret = 0; + + if (key->prefixlen > trie->max_prefixlen) + return -EINVAL; + + raw_spin_lock_irqsave(&trie->lock, irq_flags); + + /* Walk the tree looking for an exact key/length match and keeping + * track of where we could begin trimming the tree. The trim-point + * is the sub-tree along the walk consisting of only single-child + * intermediate nodes and ending at a leaf node that we want to + * remove. + */ + trim = &trie->root; + node = rcu_dereference_protected( + trie->root, lockdep_is_held(&trie->lock)); + while (node) { + matchlen = longest_prefix_match(trie, node, key); + + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen) + break; + + next_bit = extract_bit(key->data, node->prefixlen); + /* If we hit a node that has more than one child or is a valid + * prefix itself, do not remove it. Reset the root of the trim + * path to its descendant on our path. + */ + if (!(node->flags & LPM_TREE_NODE_FLAG_IM) || + (node->child[0] && node->child[1])) + trim = &node->child[next_bit]; + node = rcu_dereference_protected( + node->child[next_bit], lockdep_is_held(&trie->lock)); + } + + if (!node || node->prefixlen != key->prefixlen || + (node->flags & LPM_TREE_NODE_FLAG_IM)) { + ret = -ENOENT; + goto out; + } + + trie->n_entries--; + + /* If the node we are removing is not a leaf node, simply mark it + * as intermediate and we are done. + */ + if (rcu_access_pointer(node->child[0]) || + rcu_access_pointer(node->child[1])) { + node->flags |= LPM_TREE_NODE_FLAG_IM; + goto out; + } + + /* trim should now point to the slot holding the start of a path from + * zero or more intermediate nodes to our leaf node for deletion. + */ + while ((node = rcu_dereference_protected( + *trim, lockdep_is_held(&trie->lock)))) { + RCU_INIT_POINTER(*trim, NULL); + trim = rcu_access_pointer(node->child[0]) ? + &node->child[0] : + &node->child[1]; + kfree_rcu(node, rcu); + } + +out: + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + + return ret; } #define LPM_DATA_SIZE_MAX 256 -- cgit v1.2.3 From b5d7388f9db78f19e6af7b56a469ca8d1860329d Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Thu, 21 Sep 2017 18:43:29 -0400 Subject: bpf: Optimize lpm trie delete Before the delete operator was added, this datastructure maintained an invariant that intermediate nodes were only present when necessary to build the tree. This patch updates the delete operation to reinstate that invariant by removing unnecessary intermediate nodes after a node is removed and thus keeping the tree structure at a minimal size. Suggested-by: Daniel Mack Signed-off-by: Craig Gallek Signed-off-by: David S. Miller --- kernel/bpf/lpm_trie.c | 71 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 9d58a576b2ae..34d8a690ea05 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -394,8 +394,8 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct bpf_lpm_trie_key *key = _key; - struct lpm_trie_node __rcu **trim; - struct lpm_trie_node *node; + struct lpm_trie_node __rcu **trim, **trim2; + struct lpm_trie_node *node, *parent; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; @@ -407,31 +407,26 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) raw_spin_lock_irqsave(&trie->lock, irq_flags); /* Walk the tree looking for an exact key/length match and keeping - * track of where we could begin trimming the tree. The trim-point - * is the sub-tree along the walk consisting of only single-child - * intermediate nodes and ending at a leaf node that we want to - * remove. + * track of the path we traverse. We will need to know the node + * we wish to delete, and the slot that points to the node we want + * to delete. We may also need to know the nodes parent and the + * slot that contains it. */ trim = &trie->root; - node = rcu_dereference_protected( - trie->root, lockdep_is_held(&trie->lock)); - while (node) { + trim2 = trim; + parent = NULL; + while ((node = rcu_dereference_protected( + *trim, lockdep_is_held(&trie->lock)))) { matchlen = longest_prefix_match(trie, node, key); if (node->prefixlen != matchlen || node->prefixlen == key->prefixlen) break; + parent = node; + trim2 = trim; next_bit = extract_bit(key->data, node->prefixlen); - /* If we hit a node that has more than one child or is a valid - * prefix itself, do not remove it. Reset the root of the trim - * path to its descendant on our path. - */ - if (!(node->flags & LPM_TREE_NODE_FLAG_IM) || - (node->child[0] && node->child[1])) - trim = &node->child[next_bit]; - node = rcu_dereference_protected( - node->child[next_bit], lockdep_is_held(&trie->lock)); + trim = &node->child[next_bit]; } if (!node || node->prefixlen != key->prefixlen || @@ -442,27 +437,47 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) trie->n_entries--; - /* If the node we are removing is not a leaf node, simply mark it + /* If the node we are removing has two children, simply mark it * as intermediate and we are done. */ - if (rcu_access_pointer(node->child[0]) || + if (rcu_access_pointer(node->child[0]) && rcu_access_pointer(node->child[1])) { node->flags |= LPM_TREE_NODE_FLAG_IM; goto out; } - /* trim should now point to the slot holding the start of a path from - * zero or more intermediate nodes to our leaf node for deletion. + /* If the parent of the node we are about to delete is an intermediate + * node, and the deleted node doesn't have any children, we can delete + * the intermediate parent as well and promote its other child + * up the tree. Doing this maintains the invariant that all + * intermediate nodes have exactly 2 children and that there are no + * unnecessary intermediate nodes in the tree. */ - while ((node = rcu_dereference_protected( - *trim, lockdep_is_held(&trie->lock)))) { - RCU_INIT_POINTER(*trim, NULL); - trim = rcu_access_pointer(node->child[0]) ? - &node->child[0] : - &node->child[1]; + if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && + !node->child[0] && !node->child[1]) { + if (node == rcu_access_pointer(parent->child[0])) + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[1])); + else + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[0])); + kfree_rcu(parent, rcu); kfree_rcu(node, rcu); + goto out; } + /* The node we are removing has either zero or one child. If there + * is a child, move it into the removed node's slot then delete + * the node. Otherwise just clear the slot and delete the node. + */ + if (node->child[0]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); + else if (node->child[1]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); + else + RCU_INIT_POINTER(*trim, NULL); + kfree_rcu(node, rcu); + out: raw_spin_unlock_irqrestore(&trie->lock, irq_flags); -- cgit v1.2.3 From 6aaae2b6c4330a46204bca042f1d2f41e8e18dea Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:50 +0200 Subject: bpf: rename bpf_compute_data_end into bpf_compute_data_pointers Just do the rename into bpf_compute_data_pointers() as we'll add one more pointer here to recompute. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- kernel/bpf/sockmap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 6424ce0e4969..a298d6666698 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -102,7 +102,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb) skb_orphan(skb); skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; @@ -369,7 +369,7 @@ static int smap_parse_func_strparser(struct strparser *strp, * any socket yet. */ skb->sk = psock->sock; - bpf_compute_data_end(skb); + bpf_compute_data_pointers(skb); rc = (*prog->bpf_func)(skb, prog->insnsi); skb->sk = NULL; rcu_read_unlock(); -- cgit v1.2.3 From de8f3a83b0a0fddb2cf56e7a718127e9619ea3da Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 25 Sep 2017 02:25:51 +0200 Subject: bpf: add meta pointer for direct access This work enables generic transfer of metadata from XDP into skb. The basic idea is that we can make use of the fact that the resulting skb must be linear and already comes with a larger headroom for supporting bpf_xdp_adjust_head(), which mangles xdp->data. Here, we base our work on a similar principle and introduce a small helper bpf_xdp_adjust_meta() for adjusting a new pointer called xdp->data_meta. Thus, the packet has a flexible and programmable room for meta data, followed by the actual packet data. struct xdp_buff is therefore laid out that we first point to data_hard_start, then data_meta directly prepended to data followed by data_end marking the end of packet. bpf_xdp_adjust_head() takes into account whether we have meta data already prepended and if so, memmove()s this along with the given offset provided there's enough room. xdp->data_meta is optional and programs are not required to use it. The rationale is that when we process the packet in XDP (e.g. as DoS filter), we can push further meta data along with it for the XDP_PASS case, and give the guarantee that a clsact ingress BPF program on the same device can pick this up for further post-processing. Since we work with skb there, we can also set skb->mark, skb->priority or other skb meta data out of BPF, thus having this scratch space generic and programmable allows for more flexibility than defining a direct 1:1 transfer of potentially new XDP members into skb (it's also more efficient as we don't need to initialize/handle each of such new members). The facility also works together with GRO aggregation. The scratch space at the head of the packet can be multiple of 4 byte up to 32 byte large. Drivers not yet supporting xdp->data_meta can simply be set up with xdp->data_meta as xdp->data + 1 as bpf_xdp_adjust_meta() will detect this and bail out, such that the subsequent match against xdp->data for later access is guaranteed to fail. The verifier treats xdp->data_meta/xdp->data the same way as we treat xdp->data/xdp->data_end pointer comparisons. The requirement for doing the compare against xdp->data is that it hasn't been modified from it's original address we got from ctx access. It may have a range marking already from prior successful xdp->data/xdp->data_end pointer comparisons though. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 114 +++++++++++++++++++++++++++++++++++++------------- 1 file changed, 86 insertions(+), 28 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b914fbe1383e..f849eca36052 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -177,6 +177,12 @@ static __printf(1, 2) void verbose(const char *fmt, ...) va_end(args); } +static bool type_is_pkt_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_PACKET || + type == PTR_TO_PACKET_META; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -187,6 +193,7 @@ static const char * const reg_type_str[] = { [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", [PTR_TO_STACK] = "fp", [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", [PTR_TO_PACKET_END] = "pkt_end", }; @@ -226,7 +233,7 @@ static void print_verifier_state(struct bpf_verifier_state *state) verbose("(id=%d", reg->id); if (t != SCALAR_VALUE) verbose(",off=%d", reg->off); - if (t == PTR_TO_PACKET) + if (type_is_pkt_pointer(t)) verbose(",r=%d", reg->range); else if (t == CONST_PTR_TO_MAP || t == PTR_TO_MAP_VALUE || @@ -519,6 +526,31 @@ static void mark_reg_known_zero(struct bpf_reg_state *regs, u32 regno) __mark_reg_known_zero(regs + regno); } +static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) +{ + return type_is_pkt_pointer(reg->type); +} + +static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg) +{ + return reg_is_pkt_pointer(reg) || + reg->type == PTR_TO_PACKET_END; +} + +/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */ +static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg, + enum bpf_reg_type which) +{ + /* The register can already have a range from prior markings. + * This is fine as long as it hasn't been advanced from its + * origin. + */ + return reg->type == which && + reg->id == 0 && + reg->off == 0 && + tnum_equals_const(reg->var_off, 0); +} + /* Attempts to improve min/max values based on var_off information */ static void __update_reg_bounds(struct bpf_reg_state *reg) { @@ -702,6 +734,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: + case PTR_TO_PACKET_META: case PTR_TO_PACKET_END: case CONST_PTR_TO_MAP: return true; @@ -1047,7 +1080,10 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, switch (reg->type) { case PTR_TO_PACKET: - /* special case, because of NET_IP_ALIGN */ + case PTR_TO_PACKET_META: + /* Special case, because of NET_IP_ALIGN. Given metadata sits + * right in front, treat it the very same way. + */ return check_pkt_ptr_alignment(reg, off, size, strict); case PTR_TO_MAP_VALUE: pointer_desc = "value "; @@ -1124,8 +1160,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_ctx_access(env, insn_idx, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { /* ctx access returns either a scalar, or a - * PTR_TO_PACKET[_END]. In the latter case, we know - * the offset is zero. + * PTR_TO_PACKET[_META,_END]. In the latter + * case, we know the offset is zero. */ if (reg_type == SCALAR_VALUE) mark_reg_unknown(state->regs, value_regno); @@ -1170,7 +1206,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { err = check_stack_read(state, off, size, value_regno); } - } else if (reg->type == PTR_TO_PACKET) { + } else if (reg_is_pkt_pointer(reg)) { if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) { verbose("cannot write into packet\n"); return -EACCES; @@ -1310,6 +1346,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, switch (reg->type) { case PTR_TO_PACKET: + case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size); case PTR_TO_MAP_VALUE: return check_map_access(env, regno, reg->off, access_size); @@ -1342,7 +1379,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return 0; } - if (type == PTR_TO_PACKET && + if (type_is_pkt_pointer(type) && !may_access_direct_pkt_data(env, meta, BPF_READ)) { verbose("helper access to the packet is not allowed\n"); return -EACCES; @@ -1351,7 +1388,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (type != PTR_TO_PACKET && type != expected_type) + if (!type_is_pkt_pointer(type) && + type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || arg_type == ARG_CONST_SIZE_OR_ZERO) { @@ -1375,7 +1413,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, */ if (register_is_null(*reg)) /* final test in check_stack_boundary() */; - else if (type != PTR_TO_PACKET && type != PTR_TO_MAP_VALUE && + else if (!type_is_pkt_pointer(type) && + type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM; @@ -1401,7 +1440,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->key\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->key_size); else @@ -1417,7 +1456,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose("invalid map_ptr to access map->value\n"); return -EACCES; } - if (type == PTR_TO_PACKET) + if (type_is_pkt_pointer(type)) err = check_packet_access(env, regno, reg->off, meta->map_ptr->value_size); else @@ -1590,8 +1629,8 @@ static int check_raw_mode(const struct bpf_func_proto *fn) return count > 1 ? -EINVAL : 0; } -/* Packet data might have moved, any old PTR_TO_PACKET[_END] are now invalid, - * so turn them into unknown SCALAR_VALUE. +/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END] + * are now invalid, so turn them into unknown SCALAR_VALUE. */ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) { @@ -1600,18 +1639,15 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env) int i; for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET || - regs[i].type == PTR_TO_PACKET_END) + if (reg_is_pkt_pointer_any(®s[i])) mark_reg_unknown(regs, i); for (i = 0; i < MAX_BPF_STACK; i += BPF_REG_SIZE) { if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type != PTR_TO_PACKET && - reg->type != PTR_TO_PACKET_END) - continue; - __mark_reg_unknown(reg); + if (reg_is_pkt_pointer_any(reg)) + __mark_reg_unknown(reg); } } @@ -1871,7 +1907,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ dst_reg->range = 0; @@ -1931,7 +1967,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; - if (ptr_reg->type == PTR_TO_PACKET) { + if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) @@ -2421,7 +2457,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } static void find_good_pkt_pointers(struct bpf_verifier_state *state, - struct bpf_reg_state *dst_reg) + struct bpf_reg_state *dst_reg, + enum bpf_reg_type type) { struct bpf_reg_state *regs = state->regs, *reg; int i; @@ -2483,7 +2520,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16. */ for (i = 0; i < MAX_BPF_REG; i++) - if (regs[i].type == PTR_TO_PACKET && regs[i].id == dst_reg->id) + if (regs[i].type == type && regs[i].id == dst_reg->id) /* keep the maximum range already checked */ regs[i].range = max_t(u16, regs[i].range, dst_reg->off); @@ -2491,7 +2528,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *state, if (state->stack_slot_type[i] != STACK_SPILL) continue; reg = &state->spilled_regs[i / BPF_REG_SIZE]; - if (reg->type == PTR_TO_PACKET && reg->id == dst_reg->id) + if (reg->type == type && reg->id == dst_reg->id) reg->range = max_t(u16, reg->range, dst_reg->off); } } @@ -2856,19 +2893,39 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(this_branch, dst_reg); + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && dst_reg->type == PTR_TO_PACKET && regs[insn->src_reg].type == PTR_TO_PACKET_END) { - find_good_pkt_pointers(other_branch, dst_reg); + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(other_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET); } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && dst_reg->type == PTR_TO_PACKET_END && regs[insn->src_reg].type == PTR_TO_PACKET) { - find_good_pkt_pointers(this_branch, ®s[insn->src_reg]); + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(this_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLT && + dst_reg->type == PTR_TO_PACKET_META && + reg_is_init_pkt_pointer(®s[insn->src_reg], PTR_TO_PACKET)) { + find_good_pkt_pointers(other_branch, dst_reg, PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JGE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(other_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); + } else if (BPF_SRC(insn->code) == BPF_X && opcode == BPF_JLE && + reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) && + regs[insn->src_reg].type == PTR_TO_PACKET_META) { + find_good_pkt_pointers(this_branch, ®s[insn->src_reg], + PTR_TO_PACKET_META); } else if (is_pointer_value(env, insn->dst_reg)) { verbose("R%d pointer comparison prohibited\n", insn->dst_reg); return -EACCES; @@ -3298,8 +3355,9 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return false; /* Check our ids match any regs they're supposed to */ return check_ids(rold->id, rcur->id, idmap); + case PTR_TO_PACKET_META: case PTR_TO_PACKET: - if (rcur->type != PTR_TO_PACKET) + if (rcur->type != rold->type) return false; /* We must have at least as much range as the old ptr * did, so that any accesses which were safe before are -- cgit v1.2.3 From 2b7c6ba945fd3c10ca3e030be402098aff2f89d3 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 26 Sep 2017 16:35:13 +0100 Subject: bpf/verifier: improve disassembly of BPF_END instructions print_bpf_insn() was treating all BPF_ALU[64] the same, but BPF_END has a different structure: it has a size in insn->imm (even if it's BPF_X) and uses the BPF_SRC (X or K) to indicate which endianness to use. So it needs different code to print it. Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f849eca36052..e8d7bb8e6b98 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -332,26 +332,40 @@ static const char *const bpf_jmp_string[16] = { [BPF_EXIT >> 4] = "exit", }; +static void print_bpf_end_insn(const struct bpf_verifier_env *env, + const struct bpf_insn *insn) +{ + verbose("(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, + BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", + insn->imm, insn->dst_reg); +} + static void print_bpf_insn(const struct bpf_verifier_env *env, const struct bpf_insn *insn) { u8 class = BPF_CLASS(insn->code); if (class == BPF_ALU || class == BPF_ALU64) { - if (BPF_SRC(insn->code) == BPF_X) + if (BPF_OP(insn->code) == BPF_END) { + if (class == BPF_ALU64) + verbose("BUG_alu64_%02x\n", insn->code); + else + print_bpf_end_insn(env, insn); + } else if (BPF_SRC(insn->code) == BPF_X) { verbose("(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->src_reg); - else + } else { verbose("(%02x) %sr%d %s %s%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? "(u32) " : "", insn->imm); + } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) verbose("(%02x) *(%s *)(r%d %+d) = r%d\n", -- cgit v1.2.3 From 73c864b38383f4abc9b559025cd663f4a81afa89 Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Tue, 26 Sep 2017 16:35:29 +0100 Subject: bpf/verifier: improve disassembly of BPF_NEG instructions BPF_NEG takes only one operand, unlike the bulk of BPF_ALU[64] which are compound-assignments. So give it its own format in print_bpf_insn(). Signed-off-by: Edward Cree Acked-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e8d7bb8e6b98..4cf9b72c59a0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -351,6 +351,11 @@ static void print_bpf_insn(const struct bpf_verifier_env *env, verbose("BUG_alu64_%02x\n", insn->code); else print_bpf_end_insn(env, insn); + } else if (BPF_OP(insn->code) == BPF_NEG) { + verbose("(%02x) r%d = %s-r%d\n", + insn->code, insn->dst_reg, + class == BPF_ALU ? "(u32) " : "", + insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { verbose("(%02x) %sr%d %s %sr%d\n", insn->code, class == BPF_ALU ? "(u32) " : "", -- cgit v1.2.3 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') 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 --- kernel/bpf/syscall.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'kernel') 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') 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 --- kernel/bpf/cgroup.c | 467 +++++++++++++++++++++++++++++++++++-------------- kernel/bpf/core.c | 31 ++++ kernel/bpf/syscall.c | 37 ++-- kernel/cgroup/cgroup.c | 28 ++- 4 files changed, 414 insertions(+), 149 deletions(-) (limited to '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 --- kernel/bpf/cgroup.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/core.c | 38 ++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 34 ++++++++++++++++++++++++++++++++++ kernel/cgroup/cgroup.c | 10 ++++++++++ 4 files changed, 128 insertions(+) (limited to 'kernel') 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 390ee7e29fc8e6e90d3065b00afb047c4ee552f9 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:23 -0700 Subject: bpf: enforce return code for cgroup-bpf programs with addition of tnum logic the verifier got smart enough and we can enforce return codes at program load time. For now do so for cgroup-bpf program types. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4cf9b72c59a0..52b022310f6a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3073,6 +3073,43 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return 0; } +static int check_return_code(struct bpf_