From 88832a22d6bb50e3b5f9d5ecc6cf26707c35f322 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Tue, 7 Jun 2016 19:27:51 +0100 Subject: net-sysfs: fix missing The of_find_net_device_by_node() function is defined in but not included in the .c file that implements it. Fix the following warning by including the header: net/core/net-sysfs.c:1494:19: warning: symbol 'of_find_net_device_by_node' was not declared. Should it be static? Signed-off-by: Ben Dooks Signed-off-by: David S. Miller --- net/core/net-sysfs.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 2b3f76fe65f4..7a0b616557ab 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "net-sysfs.h" -- cgit v1.2.3 From e0d194adfa9f5f473068cc546bee60fb84ab77ba Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Jun 2016 06:19:45 -0700 Subject: net_sched: add missing paddattr description "make htmldocs" complains otherwise: .//net/core/gen_stats.c:65: warning: No description found for parameter 'padattr' .//net/core/gen_stats.c:101: warning: No description found for parameter 'padattr' Fixes: 9854518ea04d ("sched: align nlattr properly when needed") Signed-off-by: Eric Dumazet Reported-by: kbuild test robot Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/core/gen_stats.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/core') diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index f96ee8b9478d..be873e4e3125 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -47,6 +47,7 @@ nla_put_failure: * @xstats_type: TLV type for backward compatibility xstats TLV * @lock: statistics lock * @d: dumping handle + * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all @@ -87,6 +88,7 @@ EXPORT_SYMBOL(gnet_stats_start_copy_compat); * @type: TLV type for top level statistic TLV * @lock: statistics lock * @d: dumping handle + * @padattr: padding attribute * * Initializes the dumping handle, grabs the statistic lock and appends * an empty TLV header to the socket buffer for use a container for all -- cgit v1.2.3 From 19de99f70b87fcc3338da52a89c439b088cbff71 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 15 Jun 2016 18:25:38 -0700 Subject: bpf: fix matching of data/data_end in verifier The ctx structure passed into bpf programs is different depending on bpf program type. The verifier incorrectly marked ctx->data and ctx->data_end access based on ctx offset only. That caused loads in tracing programs int bpf_prog(struct pt_regs *ctx) { .. ctx->ax .. } to be incorrectly marked as PTR_TO_PACKET which later caused verifier to reject the program that was actually valid in tracing context. Fix this by doing program type specific matching of ctx offsets. Fixes: 969bf05eb3ce ("bpf: direct packet access") Reported-by: Sasha Goldshtein Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/bpf.h | 28 +++++++++++++++++++++++++++- kernel/bpf/verifier.c | 41 +++++++---------------------------------- kernel/trace/bpf_trace.c | 6 ++++-- net/core/filter.c | 16 ++++++++++++++-- 4 files changed, 52 insertions(+), 39 deletions(-) (limited to 'net/core') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8ee27b8afe81..8269cafc6eb1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -111,6 +111,31 @@ enum bpf_access_type { BPF_WRITE = 2 }; +/* types of values stored in eBPF registers */ +enum bpf_reg_type { + NOT_INIT = 0, /* nothing was written into register */ + UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ + PTR_TO_CTX, /* reg points to bpf_context */ + CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ + PTR_TO_MAP_VALUE, /* reg points to map element value */ + PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + FRAME_PTR, /* reg == frame_pointer */ + PTR_TO_STACK, /* reg == frame_pointer + imm */ + CONST_IMM, /* constant integer value */ + + /* PTR_TO_PACKET represents: + * skb->data + * skb->data + imm + * skb->data + (u16) var + * skb->data + (u16) var + imm + * if (range > 0) then [ptr, ptr + range - off) is safe to access + * if (id > 0) means that some 'var' was added + * if (off > 0) menas that 'imm' was added + */ + PTR_TO_PACKET, + PTR_TO_PACKET_END, /* skb->data + headlen */ +}; + struct bpf_prog; struct bpf_verifier_ops { @@ -120,7 +145,8 @@ struct bpf_verifier_ops { /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ - bool (*is_valid_access)(int off, int size, enum bpf_access_type type); + bool (*is_valid_access)(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type); u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg, int src_reg, int ctx_off, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 668e07903c8f..eec9f90ba030 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -126,31 +126,6 @@ * are set to NOT_INIT to indicate that they are no longer readable. */ -/* types of values stored in eBPF registers */ -enum bpf_reg_type { - NOT_INIT = 0, /* nothing was written into register */ - UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */ - PTR_TO_CTX, /* reg points to bpf_context */ - CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ - PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ - FRAME_PTR, /* reg == frame_pointer */ - PTR_TO_STACK, /* reg == frame_pointer + imm */ - CONST_IMM, /* constant integer value */ - - /* PTR_TO_PACKET represents: - * skb->data - * skb->data + imm - * skb->data + (u16) var - * skb->data + (u16) var + imm - * if (range > 0) then [ptr, ptr + range - off) is safe to access - * if (id > 0) means that some 'var' was added - * if (off > 0) menas that 'imm' was added - */ - PTR_TO_PACKET, - PTR_TO_PACKET_END, /* skb->data + headlen */ -}; - struct reg_state { enum bpf_reg_type type; union { @@ -695,10 +670,10 @@ static int check_packet_access(struct verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields */ static int check_ctx_access(struct verifier_env *env, int off, int size, - enum bpf_access_type t) + enum bpf_access_type t, enum bpf_reg_type *reg_type) { if (env->prog->aux->ops->is_valid_access && - env->prog->aux->ops->is_valid_access(off, size, t)) { + env->prog->aux->ops->is_valid_access(off, size, t, reg_type)) { /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -798,21 +773,19 @@ static int check_mem_access(struct verifier_env *env, u32 regno, int off, mark_reg_unknown_value(state->regs, value_regno); } else if (reg->type == PTR_TO_CTX) { + enum bpf_reg_type reg_type = UNKNOWN_VALUE; + if (t == BPF_WRITE && value_regno >= 0 && is_pointer_value(env, value_regno)) { verbose("R%d leaks addr into ctx\n", value_regno); return -EACCES; } - err = check_ctx_access(env, off, size, t); + err = check_ctx_access(env, off, size, t, ®_type); if (!err && t == BPF_READ && value_regno >= 0) { mark_reg_unknown_value(state->regs, value_regno); - if (off == offsetof(struct __sk_buff, data) && - env->allow_ptr_leaks) + if (env->allow_ptr_leaks) /* note that reg.[id|off|range] == 0 */ - state->regs[value_regno].type = PTR_TO_PACKET; - else if (off == offsetof(struct __sk_buff, data_end) && - env->allow_ptr_leaks) - state->regs[value_regno].type = PTR_TO_PACKET_END; + state->regs[value_regno].type = reg_type; } } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 720b7bb01d43..e7af6cb9d5cf 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -349,7 +349,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ -static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { /* check bounds */ if (off < 0 || off >= sizeof(struct pt_regs)) @@ -427,7 +428,8 @@ static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) } } -static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type) +static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, + enum bpf_reg_type *reg_type) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; diff --git a/net/core/filter.c b/net/core/filter.c index 68adb5f52110..c4b330c85c02 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2085,7 +2085,8 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type) } static bool sk_filter_is_valid_access(int off, int size, - enum bpf_access_type type) + enum bpf_access_type type, + enum bpf_reg_type *reg_type) { switch (off) { case offsetof(struct __sk_buff, tc_classid): @@ -2108,7 +2109,8 @@ static bool sk_filter_is_valid_access(int off, int size, } static bool tc_cls_act_is_valid_access(int off, int size, - enum bpf_access_type type) + enum bpf_access_type type, + enum bpf_reg_type *reg_type) { if (type == BPF_WRITE) { switch (off) { @@ -2123,6 +2125,16 @@ static bool tc_cls_act_is_valid_access(int off, int size, return false; } } + + switch (off) { + case offsetof(struct __sk_buff, data): + *reg_type = PTR_TO_PACKET; + break; + case offsetof(struct __sk_buff, data_end): + *reg_type = PTR_TO_PACKET_END; + break; + } + return __is_valid_access(off, size, type); } -- cgit v1.2.3 From b560f03ddfb072bca65e9440ff0dc4f9b1d1f056 Mon Sep 17 00:00:00 2001 From: David Barroso Date: Tue, 28 Jun 2016 11:16:43 +0300 Subject: neigh: Explicitly declare RCU-bh read side critical section in neigh_xmit() neigh_xmit() expects to be called inside an RCU-bh read side critical section, and while one of its two current callers gets this right, the other one doesn't. More specifically, neigh_xmit() has two callers, mpls_forward() and mpls_output(), and while both callers call neigh_xmit() under rcu_read_lock(), this provides sufficient protection for neigh_xmit() only in the case of mpls_forward(), as that is always called from softirq context and therefore doesn't need explicit BH protection, while mpls_output() can be called from process context with softirqs enabled. When mpls_output() is called from process context, with softirqs enabled, we can be preempted by a softirq at any time, and RCU-bh considers the completion of a softirq as signaling the end of any pending read-side critical sections, so if we do get a softirq while we are in the part of neigh_xmit() that expects to be run inside an RCU-bh read side critical section, we can end up with an unexpected RCU grace period running right in the middle of that critical section, making things go boom. This patch fixes this impedance mismatch in the callee, by making neigh_xmit() always take rcu_read_{,un}lock_bh() around the code that expects to be treated as an RCU-bh read side critical section, as this seems a safer option than fixing it in the callers. Fixes: 4fd3d7d9e868f ("neigh: Add helper function neigh_xmit") Signed-off-by: David Barroso Signed-off-by: Lennert Buytenhek Acked-by: David Ahern Acked-by: Robert Shearman Signed-off-by: David S. Miller --- net/core/neighbour.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 29dd8cc22bbf..510cd62fcb99 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2469,13 +2469,17 @@ int neigh_xmit(int index, struct net_device *dev, tbl = neigh_tables[index]; if (!tbl) goto out; + rcu_read_lock_bh(); neigh = __neigh_lookup_noref(tbl, addr, dev); if (!neigh) neigh = __neigh_create(tbl, addr, dev, false); err = PTR_ERR(neigh); - if (IS_ERR(neigh)) + if (IS_ERR(neigh)) { + rcu_read_unlock_bh(); goto out_kfree_skb; + } err = neigh->output(neigh, skb); + rcu_read_unlock_bh(); } else if (index == NEIGH_LINK_TABLE) { err = dev_hard_header(skb, dev, ntohs(skb->protocol), -- cgit v1.2.3 From eb70db8756717b90c01ccc765fdefc4dd969fc74 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 1 Jul 2016 16:07:50 -0400 Subject: packet: Use symmetric hash for PACKET_FANOUT_HASH. People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that they want packets going in both directions on a flow to hash to the same bucket. The core kernel SKB hash became non-symmetric when the ipv6 flow label and other entities were incorporated into the standard flow hash order to increase entropy. But there are no users of PACKET_FANOUT_HASH who want an assymetric hash, they all want a symmetric one. Therefore, use the flow dissector to compute a flat symmetric hash over only the protocol, addresses and ports. This hash does not get installed into and override the normal skb hash, so this change has no effect whatsoever on the rest of the stack. Reported-by: Eric Leblond Tested-by: Eric Leblond Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++ net/packet/af_packet.c | 2 +- 3 files changed, 45 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ee38a4127475..24859d40acde 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1062,6 +1062,7 @@ __skb_set_sw_hash(struct sk_buff *skb, __u32 hash, bool is_l4) } void __skb_get_hash(struct sk_buff *skb); +u32 __skb_get_hash_symmetric(struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, const struct flow_keys *keys, int hlen); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a669dea146c6..61ad43f61c5e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9bff6ef16fa7..9f0983fa4d52 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_scale(skb_get_hash(skb), num); + return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, -- cgit v1.2.3 From 82a31b9231f02d9c1b7b290a46999d517b0d312a Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 30 Jun 2016 10:15:22 -0700 Subject: net_sched: fix mirrored packets checksum Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation") we need to fixup the checksum for CHECKSUM_COMPLETE when pushing skb on RX path. Otherwise we get similar splats. Cc: Jamal Hadi Salim Cc: Tom Herbert Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 +++++++++++++++++++ net/core/skbuff.c | 18 ------------------ net/sched/act_mirred.c | 2 +- 3 files changed, 20 insertions(+), 19 deletions(-) (limited to 'net/core') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 24859d40acde..f39b37180c41 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2870,6 +2870,25 @@ static inline void skb_postpush_rcsum(struct sk_buff *skb, skb->csum = csum_partial(start, len, skb->csum); } +/** + * skb_push_rcsum - push skb and update receive checksum + * @skb: buffer to update + * @len: length of data pulled + * + * This function performs an skb_push on the packet and updates + * the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_push unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. + */ +static inline unsigned char *skb_push_rcsum(struct sk_buff *skb, + unsigned int len) +{ + skb_push(skb, len); + skb_postpush_rcsum(skb, skb->data, len); + return skb->data; +} + /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e549c03..eb12d2161fb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3015,24 +3015,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, } EXPORT_SYMBOL_GPL(skb_append_pagefrags); -/** - * skb_push_rcsum - push skb and update receive checksum - * @skb: buffer to update - * @len: length of data pulled - * - * This function performs an skb_push on the packet and updates - * the CHECKSUM_COMPLETE checksum. It should be used on - * receive path processing instead of skb_push unless you know - * that the checksum difference is zero (e.g., a valid IP header) - * or you are setting ip_summed to CHECKSUM_NONE. - */ -static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) -{ - skb_push(skb, len); - skb_postpush_rcsum(skb, skb->data, len); - return skb->data; -} - /** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942bc9e42..1f5bd6ccbd2c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb->mac_len); + skb_push_rcsum(skb2, skb->mac_len); } /* mirror is always swallowed */ -- cgit v1.2.3