From 089b19a9204fc090793d389a265f54124eacb05d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:44 -0700 Subject: flow_dissector: switch kernel context to struct bpf_flow_dissector struct bpf_flow_dissector has a small subset of sk_buff fields that flow dissector BPF program is allowed to access and an optional pointer to real skb. Real skb is used only in bpf_skb_load_bytes helper to read non-linear data. The real motivation for this is to be able to call flow dissector from eth_get_headlen context where we don't have an skb and need to dissect raw bytes. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- net/core/filter.c | 105 ++++++++++++++++++++++++++++++++++++---------- net/core/flow_dissector.c | 45 +++++++++----------- 2 files changed, 102 insertions(+), 48 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index fa8fb0548217..edb3a7c22f6c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1730,6 +1730,40 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_SIZE, }; +BPF_CALL_4(bpf_flow_dissector_load_bytes, + const struct bpf_flow_dissector *, ctx, u32, offset, + void *, to, u32, len) +{ + void *ptr; + + if (unlikely(offset > 0xffff)) + goto err_clear; + + if (unlikely(!ctx->skb)) + goto err_clear; + + ptr = skb_header_pointer(ctx->skb, offset, len, to); + if (unlikely(!ptr)) + goto err_clear; + if (ptr != to) + memcpy(to, ptr, len); + + return 0; +err_clear: + memset(to, 0, len); + return -EFAULT; +} + +static const struct bpf_func_proto bpf_flow_dissector_load_bytes_proto = { + .func = bpf_flow_dissector_load_bytes, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { @@ -6121,7 +6155,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_skb_load_bytes: - return &bpf_skb_load_bytes_proto; + return &bpf_flow_dissector_load_bytes_proto; default: return bpf_base_func_proto(func_id); } @@ -6248,9 +6282,7 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): - if (size != sizeof(__u64)) - return false; - break; + return false; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -6285,7 +6317,6 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, data_end): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): @@ -6312,7 +6343,6 @@ static bool cg_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, wire_len): return false; case bpf_ctx_range(struct __sk_buff, data): @@ -6358,7 +6388,6 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6601,7 +6630,6 @@ static bool tc_cls_act_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_end): info->reg_type = PTR_TO_PACKET_END; break; - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range_till(struct __sk_buff, family, local_port): return false; } @@ -6803,7 +6831,6 @@ static bool sk_skb_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct __sk_buff, tc_classid): case bpf_ctx_range(struct __sk_buff, data_meta): - case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): return false; @@ -6877,24 +6904,65 @@ static bool flow_dissector_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { + const int size_default = sizeof(__u32); + + if (off < 0 || off >= sizeof(struct __sk_buff)) + return false; + if (type == BPF_WRITE) return false; switch (off) { case bpf_ctx_range(struct __sk_buff, data): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET; - break; + return true; case bpf_ctx_range(struct __sk_buff, data_end): + if (size != size_default) + return false; info->reg_type = PTR_TO_PACKET_END; - break; + return true; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): + if (size != sizeof(__u64)) + return false; info->reg_type = PTR_TO_FLOW_KEYS; - break; + return true; default: return false; } +} - return bpf_skb_is_valid_access(off, size, type, prog, info); +static u32 flow_dissector_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) + +{ + struct bpf_insn *insn = insn_buf; + + switch (si->off) { + case offsetof(struct __sk_buff, data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data)); + break; + + case offsetof(struct __sk_buff, data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, data_end)); + break; + + case offsetof(struct __sk_buff, flow_keys): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_flow_dissector, flow_keys), + si->dst_reg, si->src_reg, + offsetof(struct bpf_flow_dissector, flow_keys)); + break; + } + + return insn - insn_buf; } static u32 bpf_convert_ctx_access(enum bpf_access_type type, @@ -7201,15 +7269,6 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, skc_num, 2, target_size)); break; - case offsetof(struct __sk_buff, flow_keys): - off = si->off; - off -= offsetof(struct __sk_buff, flow_keys); - off += offsetof(struct sk_buff, cb); - off += offsetof(struct qdisc_skb_cb, flow_keys); - *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, - si->src_reg, off); - break; - case offsetof(struct __sk_buff, tstamp): BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); @@ -8214,7 +8273,7 @@ const struct bpf_prog_ops sk_msg_prog_ops = { const struct bpf_verifier_ops flow_dissector_verifier_ops = { .get_func_proto = flow_dissector_func_proto, .is_valid_access = flow_dissector_is_valid_access, - .convert_ctx_access = bpf_convert_ctx_access, + .convert_ctx_access = flow_dissector_convert_ctx_access, }; const struct bpf_prog_ops flow_dissector_prog_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 795449713ba4..ef6d9443cc75 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -688,39 +688,34 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog, struct flow_dissector *flow_dissector, struct bpf_flow_keys *flow_keys) { - struct bpf_skb_data_end cb_saved; - struct bpf_skb_data_end *cb; - u32 result; - - /* Note that even though the const qualifier is discarded - * throughout the execution of the BPF program, all changes(the - * control block) are reverted after the BPF program returns. - * Therefore, __skb_flow_dissect does not alter the skb. - */ - - cb = (struct bpf_skb_data_end *)skb->cb; + struct bpf_flow_dissector ctx = { + .flow_keys = flow_keys, + .skb = skb, + .data = skb->data, + .data_end = skb->data + skb_headlen(skb), + }; + + return bpf_flow_dissect(prog, &ctx, skb->protocol, + skb_network_offset(skb), skb_headlen(skb)); +} - /* Save Control Block */ - memcpy(&cb_saved, cb, sizeof(cb_saved)); - memset(cb, 0, sizeof(*cb)); +bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, + __be16 proto, int nhoff, int hlen) +{ + struct bpf_flow_keys *flow_keys = ctx->flow_keys; + u32 result; /* Pass parameters to the BPF program */ memset(flow_keys, 0, sizeof(*flow_keys)); - cb->qdisc_cb.flow_keys = flow_keys; - flow_keys->n_proto = skb->protocol; - flow_keys->nhoff = skb_network_offset(skb); + flow_keys->n_proto = proto; + flow_keys->nhoff = nhoff; flow_keys->thoff = flow_keys->nhoff; - bpf_compute_data_pointers((struct sk_buff *)skb); - result = BPF_PROG_RUN(prog, skb); - - /* Restore state */ - memcpy(cb, &cb_saved, sizeof(cb_saved)); + result = BPF_PROG_RUN(prog, ctx); - flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, - skb_network_offset(skb), skb->len); + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, nhoff, hlen); flow_keys->thoff = clamp_t(u16, flow_keys->thoff, - flow_keys->nhoff, skb->len); + flow_keys->nhoff, hlen); return result == BPF_OK; } -- cgit From 3cbf4ffba5eeec60f82868a5facc1962d8a44d00 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:46 -0700 Subject: net: plumb network namespace into __skb_flow_dissect This new argument will be used in the next patches for the eth_get_headlen use case. eth_get_headlen calls flow dissector with only data (without skb) so there is currently no way to pull attached BPF flow dissector program. With this new argument, we can amend the callers to explicitly pass network namespace so we can use attached BPF program. Signed-off-by: Stanislav Fomichev Reviewed-by: Saeed Mahameed Signed-off-by: Daniel Borkmann --- net/core/flow_dissector.c | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index ef6d9443cc75..f32c7e737fc6 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -722,6 +722,7 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, /** * __skb_flow_dissect - extract the flow_keys struct and return it + * @net: associated network namespace, derived from @skb if NULL * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified * @flow_dissector: list of keys to dissect * @target_container: target structure to put dissected values into @@ -738,7 +739,8 @@ bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, * * Caller must take care of zeroing target container memory. */ -bool __skb_flow_dissect(const struct sk_buff *skb, +bool __skb_flow_dissect(const struct net *net, + const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, void *data, __be16 proto, int nhoff, int hlen, @@ -797,13 +799,17 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct bpf_prog *attached = NULL; rcu_read_lock(); + if (!net) { + if (skb->dev) + net = dev_net(skb->dev); + else if (skb->sk) + net = sock_net(skb->sk); + else + WARN_ON_ONCE(1); + } - if (skb->dev) - attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); - else if (skb->sk) - attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); - else - WARN_ON_ONCE(1); + if (net) + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { ret = __skb_flow_bpf_dissect(attached, skb, @@ -1405,8 +1411,8 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) __flow_hash_secret_init(); memset(&keys, 0, sizeof(keys)); - __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, - NULL, 0, 0, 0, + __skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric, + &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); return __flow_hash_from_keys(&keys, hashrnd); @@ -1507,7 +1513,8 @@ u32 skb_get_poff(const struct sk_buff *skb) { struct flow_keys_basic keys; - if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); -- cgit From 9b52e3f267a6835efd50ed9002d530666d16a411 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 22 Apr 2019 08:55:47 -0700 Subject: flow_dissector: handle no-skb use case When called without skb, gather all required data from the __skb_flow_dissect's arguments and use recently introduces no-skb mode of bpf flow dissector. Note: WARN_ON_ONCE(!net) will now trigger for eth_get_headlen users. Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- net/core/flow_dissector.c | 52 +++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 27 deletions(-) (limited to 'net/core') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index f32c7e737fc6..fac712cee9d5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -683,22 +683,6 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } } -bool __skb_flow_bpf_dissect(struct bpf_prog *prog, - const struct sk_buff *skb, - struct flow_dissector *flow_dissector, - struct bpf_flow_keys *flow_keys) -{ - struct bpf_flow_dissector ctx = { - .flow_keys = flow_keys, - .skb = skb, - .data = skb->data, - .data_end = skb->data + skb_headlen(skb), - }; - - return bpf_flow_dissect(prog, &ctx, skb->protocol, - skb_network_offset(skb), skb_headlen(skb)); -} - bool bpf_flow_dissect(struct bpf_prog *prog, struct bpf_flow_dissector *ctx, __be16 proto, int nhoff, int hlen) { @@ -753,6 +737,7 @@ bool __skb_flow_dissect(const struct net *net, struct flow_dissector_key_icmp *key_icmp; struct flow_dissector_key_tags *key_tags; struct flow_dissector_key_vlan *key_vlan; + struct bpf_prog *attached = NULL; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; int num_hdrs = 0; @@ -795,26 +780,39 @@ bool __skb_flow_dissect(const struct net *net, target_container); if (skb) { - struct bpf_flow_keys flow_keys; - struct bpf_prog *attached = NULL; - - rcu_read_lock(); if (!net) { if (skb->dev) net = dev_net(skb->dev); else if (skb->sk) net = sock_net(skb->sk); - else - WARN_ON_ONCE(1); } + } - if (net) - attached = rcu_dereference(net->flow_dissector_prog); + WARN_ON_ONCE(!net); + if (net) { + rcu_read_lock(); + attached = rcu_dereference(net->flow_dissector_prog); if (attached) { - ret = __skb_flow_bpf_dissect(attached, skb, - flow_dissector, - &flow_keys); + struct bpf_flow_keys flow_keys; + struct bpf_flow_dissector ctx = { + .flow_keys = &flow_keys, + .data = data, + .data_end = data + hlen, + }; + __be16 n_proto = proto; + + if (skb) { + ctx.skb = skb; + /* we can't use 'proto' in the skb case + * because it might be set to skb->vlan_proto + * which has been pulled from the data + */ + n_proto = skb->protocol; + } + + ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff, + hlen); __skb_flow_bpf_to_target(&flow_keys, flow_dissector, target_container); rcu_read_unlock(); -- cgit From 1b00e0dfe7d08a17d818c34d4c9968047a3f3e4b Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Tue, 23 Apr 2019 14:43:48 -0400 Subject: bpf: update skb->protocol in bpf_skb_net_grow Some tunnels, like sit, change the network protocol of packet. If so, update skb->protocol to match the new type. Signed-off-by: Willem de Bruijn Reviewed-by: Alan Maguire Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- net/core/filter.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index edb3a7c22f6c..2f88baf39cc2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3081,6 +3081,14 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, skb_set_transport_header(skb, mac_len + nh_len); } + + /* Match skb->protocol to new outer l3 protocol */ + if (skb->protocol == htons(ETH_P_IP) && + flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6) + skb->protocol = htons(ETH_P_IPV6); + else if (skb->protocol == htons(ETH_P_IPV6) && + flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4) + skb->protocol = htons(ETH_P_IP); } if (skb_is_gso(skb)) { -- cgit From 118c8e9ae629d35fa9b3d27a7b9d59298b1b4183 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Thu, 25 Apr 2019 14:37:23 -0700 Subject: bpf: support BPF_PROG_QUERY for BPF_FLOW_DISSECTOR attach_type target_fd is target namespace. If there is a flow dissector BPF program attached to that namespace, its (single) id is returned. v5: * drop net ref right after rcu unlock (Daniel Borkmann) v4: * add missing put_net (Jann Horn) v3: * add missing inline to skb_flow_dissector_prog_query static def (kbuild test robot ) v2: * don't sleep in rcu critical section (Jakub Kicinski) * check input prog_cnt (exit early) Cc: Jann Horn Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- net/core/flow_dissector.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'net/core') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index fac712cee9d5..9ca784c592ac 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,45 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); +int skb_flow_dissector_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); + u32 prog_id, prog_cnt = 0, flags = 0; + struct bpf_prog *attached; + struct net *net; + + if (attr->query.query_flags) + return -EINVAL; + + net = get_net_ns_by_fd(attr->query.target_fd); + if (IS_ERR(net)) + return PTR_ERR(net); + + rcu_read_lock(); + attached = rcu_dereference(net->flow_dissector_prog); + if (attached) { + prog_cnt = 1; + prog_id = attached->aux->id; + } + rcu_read_unlock(); + + put_net(net); + + if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) + return -EFAULT; + if (copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt))) + return -EFAULT; + + if (!attr->query.prog_cnt || !prog_ids || !prog_cnt) + return 0; + + if (copy_to_user(prog_ids, &prog_id, sizeof(u32))) + return -EFAULT; + + return 0; +} + int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { -- cgit From 6ac99e8f23d4b10258406ca0dd7bffca5f31da9d Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 26 Apr 2019 16:39:39 -0700 Subject: bpf: Introduce bpf sk local storage MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit After allowing a bpf prog to - directly read the skb->sk ptr - get the fullsock bpf_sock by "bpf_sk_fullsock()" - get the bpf_tcp_sock by "bpf_tcp_sock()" - get the listener sock by "bpf_get_listener_sock()" - avoid duplicating the fields of "(bpf_)sock" and "(bpf_)tcp_sock" into different bpf running context. this patch is another effort to make bpf's network programming more intuitive to do (together with memory and performance benefit). When bpf prog needs to store data for a sk, the current practice is to define a map with the usual 4-tuples (src/dst ip/port) as the key. If multiple bpf progs require to store different sk data, multiple maps have to be defined. Hence, wasting memory to store the duplicated keys (i.e. 4 tuples here) in each of the bpf map. [ The smallest key could be the sk pointer itself which requires some enhancement in the verifier and it is a separate topic. ] Also, the bpf prog needs to clean up the elem when sk is freed. Otherwise, the bpf map will become full and un-usable quickly. The sk-free tracking currently could be done during sk state transition (e.g. BPF_SOCK_OPS_STATE_CB). The size of the map needs to be predefined which then usually ended-up with an over-provisioned map in production. Even the map was re-sizable, while the sk naturally come and go away already, this potential re-size operation is arguably redundant if the data can be directly connected to the sk itself instead of proxy-ing through a bpf map. This patch introduces sk->sk_bpf_storage to provide local storage space at sk for bpf prog to use. The space will be allocated when the first bpf prog has created data for this particular sk. The design optimizes the bpf prog's lookup (and then optionally followed by an inline update). bpf_spin_lock should be used if the inline update needs to be protected. BPF_MAP_TYPE_SK_STORAGE: ----------------------- To define a bpf "sk-local-storage", a BPF_MAP_TYPE_SK_STORAGE map (new in this patch) needs to be created. Multiple BPF_MAP_TYPE_SK_STORAGE maps can be created to fit different bpf progs' needs. The map enforces BTF to allow printing the sk-local-storage during a system-wise sk dump (e.g. "ss -ta") in the future. The purpose of a BPF_MAP_TYPE_SK_STORAGE map is not for lookup/update/delete a "sk-local-storage" data from a particular sk. Think of the map as a meta-data (or "type") of a "sk-local-storage". This particular "type" of "sk-local-storage" data can then be stored in any sk. The main purposes of this map are mostly: 1. Define the size of a "sk-local-storage" type. 2. Provide a similar syscall userspace API as the map (e.g. lookup/update, map-id, map-btf...etc.) 3. Keep track of all sk's storages of this "type" and clean them up when the map is freed. sk->sk_bpf_storage: ------------------ The main lookup/update/delete is done on sk->sk_bpf_storage (which is a "struct bpf_sk_storage"). When doing a lookup, the "map" pointer is now used as the "key" to search on the sk_storage->list. The "map" pointer is actually serving as the "type" of the "sk-local-storage" that is being requested. To allow very fast lookup, it should be as fast as looking up an array at a stable-offset. At the same time, it is not ideal to set a hard limit on the number of sk-local-storage "type" that the system can have. Hence, this patch takes a cache approach. The last search result from sk_storage->list is cached in sk_storage->cache[] which is a stable sized array. Each "sk-local-storage" type has a stable offset to the cache[] array. In the future, a map's flag could be introduced to do cache opt-out/enforcement if it became necessary. The cache size is 16 (i.e. 16 types of "sk-local-storage"). Programs can share map. On the program side, having a few bpf_progs running in the networking hotpath is already a lot. The bpf_prog should have already consolidated the existing sock-key-ed map usage to minimize the map lookup penalty. 16 has enough runway to grow. All sk-local-storage data will be removed from sk->sk_bpf_storage during sk destruction. bpf_sk_storage_get() and bpf_sk_storage_delete(): ------------------------------------------------ Instead of using bpf_map_(lookup|update|delete)_elem(), the bpf prog needs to use the new helper bpf_sk_storage_get() and bpf_sk_storage_delete(). The verifier can then enforce the ARG_PTR_TO_SOCKET argument. The bpf_sk_storage_get() also allows to "create" new elem if one does not exist in the sk. It is done by the new BPF_SK_STORAGE_GET_F_CREATE flag. An optional value can also be provided as the initial value during BPF_SK_STORAGE_GET_F_CREATE. The BPF_MAP_TYPE_SK_STORAGE also supports bpf_spin_lock. Together, it has eliminated the potential use cases for an equivalent bpf_map_update_elem() API (for bpf_prog) in this patch. Misc notes: ---------- 1. map_get_next_key is not supported. From the userspace syscall perspective, the map has the socket fd as the key while the map can be shared by pinned-file or map-id. Since btf is enforced, the existing "ss" could be enhanced to pretty print the local-storage. Supporting a kernel defined btf with 4 tuples as the return key could be explored later also. 2. The sk->sk_lock cannot be acquired. Atomic operations is used instead. e.g. cmpxchg is done on the sk->sk_bpf_storage ptr. Please refer to the source code comments for the details in synchronization cases and considerations. 3. The mem is charged to the sk->sk_omem_alloc as the sk filter does. Benchmark: --------- Here is the benchmark data collected by turning on the "kernel.bpf_stats_enabled" sysctl. Two bpf progs are tested: One bpf prog with the usual bpf hashmap (max_entries = 8192) with the sk ptr as the key. (verifier is modified to support sk ptr as the key That should have shortened the key lookup time.) Another bpf prog is with the new BPF_MAP_TYPE_SK_STORAGE. Both are storing a "u32 cnt", do a lookup on "egress_skb/cgroup" for each egress skb and then bump the cnt. netperf is used to drive data with 4096 connected UDP sockets. BPF_MAP_TYPE_HASH with a modifier verifier (152ns per bpf run) 27: cgroup_skb name egress_sk_map tag 74f56e832918070b run_time_ns 58280107540 run_cnt 381347633 loaded_at 2019-04-15T13:46:39-0700 uid 0 xlated 344B jited 258B memlock 4096B map_ids 16 btf_id 5 BPF_MAP_TYPE_SK_STORAGE in this patch (66ns per bpf run) 30: cgroup_skb name egress_sk_stora tag d4aa70984cc7bbf6 run_time_ns 25617093319 run_cnt 390989739 loaded_at 2019-04-15T13:47:54-0700 uid 0 xlated 168B jited 156B memlock 4096B map_ids 17 btf_id 6 Here is a high-level picture on how are the objects organized: sk ┌──────┐ │ │ │ │ │ │ │*sk_bpf_storage─────▶ bpf_sk_storage └──────┘ ┌───────┐ ┌───────────┤ list │ │ │ │ │ │ │ │ │ │ │ └───────┘ │ │ elem │ ┌────────┐ ├─▶│ snode │ │ ├────────┤ │ │ data │ bpf_map │ ├────────┤ ┌─────────┐ │ │map_node│◀─┬─────┤ list │ │ └────────┘ │ │ │ │ │ │ │ │ elem │ │ │ │ ┌────────┐ │ └─────────┘ └─▶│ snode │ │ ├────────┤ │ bpf_map │ data │ │ ┌─────────┐ ├────────┤ │ │ list ├───────▶│map_node│ │ │ │ └────────┘ │ │ │ │ │ │ elem │ └─────────┘ ┌────────┐ │ ┌─▶│ snode │ │ │ ├────────┤ │ │ │ data │ │ │ ├────────┤ │ │ │map_node│◀─┘ │ └────────┘ │ │ │ ┌───────┐ sk └──────────│ list │ ┌──────┐ │ │ │ │ │ │ │ │ │ │ │ │ └───────┘ │*sk_bpf_storage───────▶bpf_sk_storage └──────┘ Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov --- net/core/Makefile | 1 + net/core/bpf_sk_storage.c | 804 ++++++++++++++++++++++++++++++++++++++++++++++ net/core/filter.c | 12 + net/core/sock.c | 5 + 4 files changed, 822 insertions(+) create mode 100644 net/core/bpf_sk_storage.c (limited to 'net/core') diff --git a/net/core/Makefile b/net/core/Makefile index f97d6254e564..a104dc8faafc 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -34,3 +34,4 @@ obj-$(CONFIG_HWBM) += hwbm.o obj-$(CONFIG_NET_DEVLINK) += devlink.o obj-$(CONFIG_GRO_CELLS) += gro_cells.o obj-$(CONFIG_FAILOVER) += failover.o +obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c new file mode 100644 index 000000000000..a8e9ac71b22d --- /dev/null +++ b/net/core/bpf_sk_storage.c @@ -0,0 +1,804 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static atomic_t cache_idx; + +struct bucket { + struct hlist_head list; + raw_spinlock_t lock; +}; + +/* Thp map is not the primary owner of a bpf_sk_storage_elem. + * Instead, the sk->sk_bpf_storage is. + * + * The map (bpf_sk_storage_map) is for two purposes + * 1. Define the size of the "sk local storage". It is + * the map's value_size. + * + * 2. Maintain a list to keep track of all elems such + * that they can be cleaned up during the map destruction. + * + * When a bpf local storage is being looked up for a + * particular sk, the "bpf_map" pointer is actually used + * as the "key" to search in the list of elem in + * sk->sk_bpf_storage. + * + * Hence, consider sk->sk_bpf_storage is the mini-map + * with the "bpf_map" pointer as the searching key. + */ +struct bpf_sk_storage_map { + struct bpf_map map; + /* Lookup elem does not require accessing the map. + * + * Updating/Deleting requires a bucket lock to + * link/unlink the elem from the map. Having + * multiple buckets to improve contention. + */ + struct bucket *buckets; + u32 bucket_log; + u16 elem_size; + u16 cache_idx; +}; + +struct bpf_sk_storage_data { + /* smap is used as the searching key when looking up + * from sk->sk_bpf_storage. + * + * Put it in the same cacheline as the data to minimize + * the number of cachelines access during the cache hit case. + */ + struct bpf_sk_storage_map __rcu *smap; + u8 data[0] __aligned(8); +}; + +/* Linked to bpf_sk_storage and bpf_sk_storage_map */ +struct bpf_sk_storage_elem { + struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ + struct hlist_node snode; /* Linked to bpf_sk_storage */ + struct bpf_sk_storage __rcu *sk_storage; + struct rcu_head rcu; + /* 8 bytes hole */ + /* The data is stored in aother cacheline to minimize + * the number of cachelines access during a cache hit. + */ + struct bpf_sk_storage_data sdata ____cacheline_aligned; +}; + +#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) +#define SDATA(_SELEM) (&(_SELEM)->sdata) +#define BPF_SK_STORAGE_CACHE_SIZE 16 + +struct bpf_sk_storage { + struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; + struct hlist_head list; /* List of bpf_sk_storage_elem */ + struct sock *sk; /* The sk that owns the the above "list" of + * bpf_sk_storage_elem. + */ + struct rcu_head rcu; + raw_spinlock_t lock; /* Protect adding/removing from the "list" */ +}; + +static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; +} + +static int omem_charge(struct sock *sk, unsigned int size) +{ + /* same check as in sock_kmalloc() */ + if (size <= sysctl_optmem_max && + atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) { + atomic_add(size, &sk->sk_omem_alloc); + return 0; + } + + return -ENOMEM; +} + +static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->snode); +} + +static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) +{ + return !hlist_unhashed(&selem->map_node); +} + +static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, + struct sock *sk, void *value, + bool charge_omem) +{ + struct bpf_sk_storage_elem *selem; + + if (charge_omem && omem_charge(sk, smap->elem_size)) + return NULL; + + selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + if (selem) { + if (value) + memcpy(SDATA(selem)->data, value, smap->map.value_size); + return selem; + } + + if (charge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + return NULL; +} + +/* sk_storage->lock must be held and selem->sk_storage == sk_storage. + * The caller must ensure selem->smap is still valid to be + * dereferenced for its smap->elem_size and smap->cache_idx. + */ +static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem, + bool uncharge_omem) +{ + struct bpf_sk_storage_map *smap; + bool free_sk_storage; + struct sock *sk; + + smap = rcu_dereference(SDATA(selem)->smap); + sk = sk_storage->sk; + + /* All uncharging on sk->sk_omem_alloc must be done first. + * sk may be freed once the last selem is unlinked from sk_storage. + */ + if (uncharge_omem) + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + + free_sk_storage = hlist_is_singular_node(&selem->snode, + &sk_storage->list); + if (free_sk_storage) { + atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); + sk_storage->sk = NULL; + /* After this RCU_INIT, sk may be freed and cannot be used */ + RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); + + /* sk_storage is not freed now. sk_storage->lock is + * still held and raw_spin_unlock_bh(&sk_storage->lock) + * will be done by the caller. + * + * Although the unlock will be done under + * rcu_read_lock(), it is more intutivie to + * read if kfree_rcu(sk_storage, rcu) is done + * after the raw_spin_unlock_bh(&sk_storage->lock). + * + * Hence, a "bool free_sk_storage" is returned + * to the caller which then calls the kfree_rcu() + * after unlock. + */ + } + hlist_del_init_rcu(&selem->snode); + if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == + SDATA(selem)) + RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); + + kfree_rcu(selem, rcu); + + return free_sk_storage; +} + +static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + + if (unlikely(!selem_linked_to_sk(selem))) + /* selem has already been unlinked from sk */ + return; + + sk_storage = rcu_dereference(selem->sk_storage); + raw_spin_lock_bh(&sk_storage->lock); + if (likely(selem_linked_to_sk(selem))) + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + raw_spin_unlock_bh(&sk_storage->lock); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +/* sk_storage->lock must be held and sk_storage->list cannot be empty */ +static void __selem_link_sk(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_elem *selem) +{ + RCU_INIT_POINTER(selem->sk_storage, sk_storage); + hlist_add_head(&selem->snode, &sk_storage->list); +} + +static void selem_unlink_map(struct bpf_sk_storage_elem *selem) +{ + struct bpf_sk_storage_map *smap; + struct bucket *b; + + if (unlikely(!selem_linked_to_map(selem))) + /* selem has already be unlinked from smap */ + return; + + smap = rcu_dereference(SDATA(selem)->smap); + b = select_bucket(smap, selem); + raw_spin_lock_bh(&b->lock); + if (likely(selem_linked_to_map(selem))) + hlist_del_init_rcu(&selem->map_node); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_link_map(struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *selem) +{ + struct bucket *b = select_bucket(smap, selem); + + raw_spin_lock_bh(&b->lock); + RCU_INIT_POINTER(SDATA(selem)->smap, smap); + hlist_add_head_rcu(&selem->map_node, &b->list); + raw_spin_unlock_bh(&b->lock); +} + +static void selem_unlink(struct bpf_sk_storage_elem *selem) +{ + /* Always unlink from map before unlinking from sk_storage + * because selem will be freed after successfully unlinked from + * the sk_storage. + */ + selem_unlink_map(selem); + selem_unlink_sk(selem); +} + +static struct bpf_sk_storage_data * +__sk_storage_lookup(struct bpf_sk_storage *sk_storage, + struct bpf_sk_storage_map *smap, + bool cacheit_lockit) +{ + struct bpf_sk_storage_data *sdata; + struct bpf_sk_storage_elem *selem; + + /* Fast path (cache hit) */ + sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); + if (sdata && rcu_access_pointer(sdata->smap) == smap) + return sdata; + + /* Slow path (cache miss) */ + hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) + if (rcu_access_pointer(SDATA(selem)->smap) == smap) + break; + + if (!selem) + return NULL; + + sdata = SDATA(selem); + if (cacheit_lockit) { + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next __sk_storage_lookup(). + */ + raw_spin_lock_bh(&sk_storage->lock); + if (selem_linked_to_sk(selem)) + rcu_assign_pointer(sk_storage->cache[smap->cache_idx], + sdata); + raw_spin_unlock_bh(&sk_storage->lock); + } + + return sdata; +} + +static struct bpf_sk_storage_data * +sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) + return NULL; + + smap = (struct bpf_sk_storage_map *)map; + return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); +} + +static int check_flags(const struct bpf_sk_storage_data *old_sdata, + u64 map_flags) +{ + if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) + /* elem already exists */ + return -EEXIST; + + if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) + /* elem doesn't exist, cannot update it */ + return -ENOENT; + + return 0; +} + +static int sk_storage_alloc(struct sock *sk, + struct bpf_sk_storage_map *smap, + struct bpf_sk_storage_elem *first_selem) +{ + struct bpf_sk_storage *prev_sk_storage, *sk_storage; + int err; + + err = omem_charge(sk, sizeof(*sk_storage)); + if (err) + return err; + + sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); + if (!sk_storage) { + err = -ENOMEM; + goto uncharge; + } + INIT_HLIST_HEAD(&sk_storage->list); + raw_spin_lock_init(&sk_storage->lock); + sk_storage->sk = sk; + + __selem_link_sk(sk_storage, first_selem); + selem_link_map(smap, first_selem); + /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. + * Hence, atomic ops is used to set sk->sk_bpf_storage + * from NULL to the newly allocated sk_storage ptr. + * + * From now on, the sk->sk_bpf_storage pointer is protected + * by the sk_storage->lock. Hence, when freeing + * the sk->sk_bpf_storage, the sk_storage->lock must + * be held before setting sk->sk_bpf_storage to NULL. + */ + prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, + NULL, sk_storage); + if (unlikely(prev_sk_storage)) { + selem_unlink_map(first_selem); + err = -EAGAIN; + goto uncharge; + + /* Note that even first_selem was linked to smap's + * bucket->list, first_selem can be freed immediately + * (instead of kfree_rcu) because + * bpf_sk_storage_map_free() does a + * synchronize_rcu() before walking the bucket->list. + * Hence, no one is accessing selem from the + * bucket->list under rcu_read_lock(). + */ + } + + return 0; + +uncharge: + kfree(sk_storage); + atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); + return err; +} + +/* sk cannot be going away because it is linking new elem + * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). + * Otherwise, it will become a leak (and other memory issues + * during map destruction). + */ +static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, + struct bpf_map *map, + void *value, + u64 map_flags) +{ + struct bpf_sk_storage_data *old_sdata = NULL; + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + struct bpf_sk_storage_map *smap; + int err; + + /* BPF_EXIST and BPF_NOEXIST cannot be both set */ + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || + /* BPF_F_LOCK can only be used in a value with spin_lock */ + unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) + return ERR_PTR(-EINVAL); + + smap = (struct bpf_sk_storage_map *)map; + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage || hlist_empty(&sk_storage->list)) { + /* Very first elem for this sk */ + err = check_flags(NULL, map_flags); + if (err) + return ERR_PTR(err); + + selem = selem_alloc(smap, sk, value, true); + if (!selem) + return ERR_PTR(-ENOMEM); + + err = sk_storage_alloc(sk, smap, selem); + if (err) { + kfree(selem); + atomic_sub(smap->elem_size, &sk->sk_omem_alloc); + return ERR_PTR(err); + } + + return SDATA(selem); + } + + if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { + /* Hoping to find an old_sdata to do inline update + * such that it can avoid taking the sk_storage->lock + * and changing the lists. + */ + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + return ERR_PTR(err); + if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { + copy_map_value_locked(map, old_sdata->data, + value, false); + return old_sdata; + } + } + + raw_spin_lock_bh(&sk_storage->lock); + + /* Recheck sk_storage->list under sk_storage->lock */ + if (unlikely(hlist_empty(&sk_storage->list))) { + /* A parallel del is happening and sk_storage is going + * away. It has just been checked before, so very + * unlikely. Return instead of retry to keep things + * simple. + */ + err = -EAGAIN; + goto unlock_err; + } + + old_sdata = __sk_storage_lookup(sk_storage, smap, false); + err = check_flags(old_sdata, map_flags); + if (err) + goto unlock_err; + + if (old_sdata && (map_flags & BPF_F_LOCK)) { + copy_map_value_locked(map, old_sdata->data, value, false); + selem = SELEM(old_sdata); + goto unlock; + } + + /* sk_storage->lock is held. Hence, we are sure + * we can unlink and uncharge the old_sdata successfully + * later. Hence, instead of charging the new selem now + * and then uncharge the old selem later (which may cause + * a potential but unnecessary charge failure), avoid taking + * a charge at all here (the "!old_sdata" check) and the + * old_sdata will not be uncharged later during __selem_unlink_sk(). + */ + selem = selem_alloc(smap, sk, value, !old_sdata); + if (!selem) { + err = -ENOMEM; + goto unlock_err; + } + + /* First, link the new selem to the map */ + selem_link_map(smap, selem); + + /* Second, link (and publish) the new selem to sk_storage */ + __selem_link_sk(sk_storage, selem); + + /* Third, remove old selem, SELEM(old_sdata) */ + if (old_sdata) { + selem_unlink_map(SELEM(old_sdata)); + __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); + } + +unlock: + raw_spin_unlock_bh(&sk_storage->lock); + return SDATA(selem); + +unlock_err: + raw_spin_unlock_bh(&sk_storage->lock); + return ERR_PTR(err); +} + +static int sk_storage_delete(struct sock *sk, struct bpf_map *map) +{ + struct bpf_sk_storage_data *sdata; + + sdata = sk_storage_lookup(sk, map, false); + if (!sdata) + return -ENOENT; + + selem_unlink(SELEM(sdata)); + + return 0; +} + +/* Called by __sk_destruct() */ +void bpf_sk_storage_free(struct sock *sk) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage *sk_storage; + bool free_sk_storage = false; + struct hlist_node *n; + + rcu_read_lock(); + sk_storage = rcu_dereference(sk->sk_bpf_storage); + if (!sk_storage) { + rcu_read_unlock(); + return; + } + + /* Netiher the bpf_prog nor the bpf-map's syscall + * could be modifying the sk_storage->list now. + * Thus, no elem can be added-to or deleted-from the + * sk_storage->list by the bpf_prog or by the bpf-map's syscall. + * + * It is racing with bpf_sk_storage_map_free() alone + * when unlinking elem from the sk_storage->list and + * the map's bucket->list. + */ + raw_spin_lock_bh(&sk_storage->lock); + hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { + /* Always unlink from map before unlinking from + * sk_storage. + */ + selem_unlink_map(selem); + free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + } + raw_spin_unlock_bh(&sk_storage->lock); + rcu_read_unlock(); + + if (free_sk_storage) + kfree_rcu(sk_storage, rcu); +} + +static void bpf_sk_storage_map_free(struct bpf_map *map) +{ + struct bpf_sk_storage_elem *selem; + struct bpf_sk_storage_map *smap; + struct bucket *b; + unsigned int i; + + smap = (struct bpf_sk_storage_map *)map; + + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the sk->sk_bpf_storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_sk_storage_elem, + map_node))) { + selem_unlink(selem); + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* bpf_sk_storage_free() may still need to access the map. + * e.g. bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exited immediately. + * + * However, the bpf_sk_storage_free() still needs to access + * the smap->elem_size to do the uncharging in + * __selem_unlink_sk(). + * + * Hence, wait another rcu grace period for the + * bpf_sk_storage_free() to finish. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + kfree(map); +} + +static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +{ + if (attr->map_flags != BPF_F_NO_PREALLOC || attr->max_entries || + attr->key_size != sizeof(int) || !attr->value_size || + /* Enforce BTF for userspace sk dumping */ + !attr->btf_key_type_id || !attr->btf_value_type_id) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (attr->value_size >= KMALLOC_MAX_SIZE - + MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem) || + /* U16_MAX is much more than enough for sk local storage + * considering a tcp_sock is ~2k. + */ + attr->value_size > U16_MAX - sizeof(struct bpf_sk_storage_elem)) + return -E2BIG; + + return 0; +} + +static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +{ + struct bpf_sk_storage_map *smap; + unsigned int i; + u32 nbuckets; + u64 cost; + + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + if (!smap) + return ERR_PTR(-ENOMEM); + bpf_map_init_from_attr(&smap->map, attr); + + smap->bucket_log = ilog2(roundup_pow_of_two(num_possible_cpus())); + nbuckets = 1U << smap->bucket_log; + smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, + GFP_USER | __GFP_NOWARN); + if (!smap->buckets) { + kfree(smap); + return ERR_PTR(-ENOMEM); + } + cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); + + for (i = 0; i < nbuckets; i++) { + INIT_HLIST_HEAD(&smap->buckets[i].list); + raw_spin_lock_init(&smap->buckets[i].lock); + } + + smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; + smap->cache_idx = (unsigned int)atomic_inc_return(&cache_idx) % + BPF_SK_STORAGE_CACHE_SIZE; + smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + return &smap->map; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -ENOTSUPP; +} + +static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, + const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + u32 int_data; + + if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) + return -EINVAL; + + return 0; +} + +static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_lookup(sock->sk, map, true); + sockfd_put(sock); + return sdata ? sdata->data : NULL; + } + + return ERR_PTR(err); +} + +static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_sk_storage_data *sdata; + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + sdata = sk_storage_update(sock->sk, map, value, map_flags); + sockfd_put(sock); + return IS_ERR(sdata) ? PTR_ERR(sdata) : 0; + } + + return err; +} + +static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct socket *sock; + int fd, err; + + fd = *(int *)key; + sock = sockfd_lookup(fd, &err); + if (sock) { + err = sk_storage_delete(sock->sk, map); + sockfd_put(sock); + return err; + } + + return err; +} + +BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, + void *, value, u64, flags) +{ + struct bpf_sk_storage_data *sdata; + + if (flags > BPF_SK_STORAGE_GET_F_CREATE) + return (unsigned long)NULL; + + sdata = sk_storage_lookup(sk, map, true); + if (sdata) + return (unsigned long)sdata->data; + + if (flags == BPF_SK_STORAGE_GET_F_CREATE && + /* Cannot add new elem to a going away sk. + * Otherwise, the new elem may become a leak + * (and also other memory issues during map + * destruction). + */ + refcount_inc_not_zero(&sk->sk_refcnt)) { + sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + /* sk must be a fullsock (guaranteed by verifier), + * so sock_gen_put() is unnecessary. + */ + sock_put(sk); + return IS_ERR(sdata) ? + (unsigned long)NULL : (unsigned long)sdata->data; + } + + return (unsigned long)NULL; +} + +BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) +{ + if (refcount_inc_not_zero(&sk->sk_refcnt)) { + int err; + + err = sk_storage_delete(sk, map); + sock_put(sk); + return err; + } + + return -ENOENT; +} + +const struct bpf_map_ops sk_storage_map_ops = { + .map_alloc_check = bpf_sk_storage_map_alloc_check, + .map_alloc = bpf_sk_storage_map_alloc, + .map_free = bpf_sk_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, + .map_update_elem = bpf_fd_sk_storage_update_elem, + .map_delete_elem = bpf_fd_sk_storage_delete_elem, + .map_check_btf = bpf_sk_storage_map_check_btf, +}; + +const struct bpf_func_proto bpf_sk_storage_get_proto = { + .func = bpf_sk_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_sk_storage_delete_proto = { + .func = bpf_sk_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_SOCKET, +}; diff --git a/net/core/filter.c b/net/core/filter.c index 2f88baf39cc2..27b0dc01dc3f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -75,6 +75,7 @@ #include #include #include +#include /** * sk_filter_trim_cap - run a packet through a socket filter @@ -5903,6 +5904,9 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } } +const struct bpf_func_proto bpf_sk_storage_get_proto __weak; +const struct bpf_func_proto bpf_sk_storage_delete_proto __weak; + static const struct bpf_func_proto * cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -5911,6 +5915,10 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_local_storage_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; @@ -5992,6 +6000,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_fib_lookup_proto; case BPF_FUNC_sk_fullsock: return &bpf_sk_fullsock_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; diff --git a/net/core/sock.c b/net/core/sock.c index 443b98d05f1e..9773be724aa9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -137,6 +137,7 @@ #include #include +#include #include @@ -1709,6 +1710,10 @@ static void __sk_destruct(struct rcu_head *head) sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP); +#ifdef CONFIG_BPF_SYSCALL + bpf_sk_storage_free(sk); +#endif + if (atomic_read(&sk->sk_omem_alloc)) pr_debug("%s: optmem leakage (%d bytes) detected\n", __func__, atomic_read(&sk->sk_omem_alloc)); -- cgit