From 3a5913183aa1b14148c723bda030e6102ad73008 Mon Sep 17 00:00:00 2001 From: Eyal Birger Date: Sun, 9 Oct 2022 22:16:43 +0300 Subject: xfrm: fix "disable_policy" on ipv4 early demux The commit in the "Fixes" tag tried to avoid a case where policy check is ignored due to dst caching in next hops. However, when the traffic is locally consumed, the dst may be cached in a local TCP or UDP socket as part of early demux. In this case the "disable_policy" flag is not checked as ip_route_input_noref() was only called before caching, and thus, packets after the initial packet in a flow will be dropped if not matching policies. Fix by checking the "disable_policy" flag also when a valid dst is already available. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216557 Reported-by: Monil Patel Fixes: e6175a2ed1f1 ("xfrm: fix "disable_policy" flag use when arriving from different devices") Signed-off-by: Eyal Birger ---- v2: use dev instead of skb->dev Signed-off-by: Steffen Klassert --- net/ipv4/ip_input.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1b512390b3cf..e880ce77322a 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, iph->tos, dev); if (unlikely(err)) goto drop_error; + } else { + struct in_device *in_dev = __in_dev_get_rcu(dev); + + if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY)) + IPCB(skb)->flags |= IPSKB_NOPOLICY; } #ifdef CONFIG_IP_ROUTE_CLASSID -- cgit v1.2.3 From 4b549ccce941798703f159b227aa28c716aa78fa Mon Sep 17 00:00:00 2001 From: Christian Langrock Date: Mon, 17 Oct 2022 08:34:47 +0200 Subject: xfrm: replay: Fix ESN wrap around for GSO When using GSO it can happen that the wrong seq_hi is used for the last packets before the wrap around. This can lead to double usage of a sequence number. To avoid this, we should serialize this last GSO packet. Fixes: d7dbefc45cf5 ("xfrm: Add xfrm_replay_overflow functions for offloading") Co-developed-by: Steffen Klassert Signed-off-by: Christian Langrock Signed-off-by: Steffen Klassert --- net/ipv4/esp4_offload.c | 3 +++ net/ipv6/esp6_offload.c | 3 +++ net/xfrm/xfrm_device.c | 15 ++++++++++++++- net/xfrm/xfrm_replay.c | 2 +- 4 files changed, 21 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 170152772d33..3969fa805679 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32)); ip_hdr(skb)->tot_len = htons(skb->len); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 79d43548279c..242f4295940e 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -346,6 +346,9 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features xo->seq.low += skb_shinfo(skb)->gso_segs; } + if (xo->seq.low < seq) + xo->seq.hi++; + esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); len = skb->len - sizeof(struct ipv6hdr); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5f5aafd418af..21269e8f2db4 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -97,6 +97,18 @@ static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb) } } +static inline bool xmit_xfrm_check_overflow(struct sk_buff *skb) +{ + struct xfrm_offload *xo = xfrm_offload(skb); + __u32 seq = xo->seq.low; + + seq += skb_shinfo(skb)->gso_segs; + if (unlikely(seq < xo->seq.low)) + return true; + + return false; +} + struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { int err; @@ -134,7 +146,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { + if (skb_is_gso(skb) && (unlikely(x->xso.dev != dev) || + unlikely(xmit_xfrm_check_overflow(skb)))) { struct sk_buff *segs; /* Packet got rerouted, fixup features and segment it. */ diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 9f4d42eb090f..ce56d659c55a 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,7 +714,7 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(oseq < replay_esn->oseq)) { + if (unlikely(xo->seq.low < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; -- cgit v1.2.3 From 52d1aa8b8249ff477aaa38b6f74a8ced780d079c Mon Sep 17 00:00:00 2001 From: Daniel Xu Date: Wed, 9 Nov 2022 12:39:07 -0700 Subject: netfilter: conntrack: Fix data-races around ct mark nf_conn:mark can be read from and written to in parallel. Use READ_ONCE()/WRITE_ONCE() for reads and writes to prevent unwanted compiler optimizations. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Daniel Xu Signed-off-by: Pablo Neira Ayuso --- net/core/flow_dissector.c | 2 +- net/ipv4/netfilter/ipt_CLUSTERIP.c | 4 ++-- net/netfilter/nf_conntrack_core.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 24 ++++++++++++++---------- net/netfilter/nf_conntrack_standalone.c | 2 +- net/netfilter/nft_ct.c | 6 +++--- net/netfilter/xt_connmark.c | 18 ++++++++++-------- net/openvswitch/conntrack.c | 8 ++++---- net/sched/act_connmark.c | 4 ++-- net/sched/act_ct.c | 8 ++++---- net/sched/act_ctinfo.c | 6 +++--- 11 files changed, 45 insertions(+), 39 deletions(-) (limited to 'net/ipv4') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 25cd35f5922e..007730412947 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -296,7 +296,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, key->ct_zone = ct->zone.id; #endif #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - key->ct_mark = ct->mark; + key->ct_mark = READ_ONCE(ct->mark); #endif cl = nf_ct_labels_find(ct); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index f8e176c77d1c..b3cc416ed292 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) switch (ctinfo) { case IP_CT_NEW: - ct->mark = hash; + WRITE_ONCE(ct->mark, hash); break; case IP_CT_RELATED: case IP_CT_RELATED_REPLY: @@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) #ifdef DEBUG nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); #endif - pr_debug("hash=%u ct_hash=%u ", hash, ct->mark); + pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark)); if (!clusterip_responsible(cipinfo->config, hash)) { pr_debug("not responsible\n"); return NF_DROP; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index f97bda06d2a9..2692139ce417 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1781,7 +1781,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } #ifdef CONFIG_NF_CONNTRACK_MARK - ct->mark = exp->master->mark; + ct->mark = READ_ONCE(exp->master->mark); #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK ct->secmark = exp->master->secmark; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 7562b215b932..d71150a40fb0 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -328,9 +328,9 @@ nla_put_failure: } #ifdef CONFIG_NF_CONNTRACK_MARK -static int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) +static int ctnetlink_dump_mark(struct sk_buff *skb, u32 mark) { - if (nla_put_be32(skb, CTA_MARK, htonl(ct->mark))) + if (nla_put_be32(skb, CTA_MARK, htonl(mark))) goto nla_put_failure; return 0; @@ -543,7 +543,7 @@ static int ctnetlink_dump_extinfo(struct sk_buff *skb, static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct) { if (ctnetlink_dump_status(skb, ct) < 0 || - ctnetlink_dump_mark(skb, ct) < 0 || + ctnetlink_dump_mark(skb, READ_ONCE(ct->mark)) < 0 || ctnetlink_dump_secctx(skb, ct) < 0 || ctnetlink_dump_id(skb, ct) < 0 || ctnetlink_dump_use(skb, ct) < 0 || @@ -722,6 +722,7 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) struct sk_buff *skb; unsigned int type; unsigned int flags = 0, group; + u32 mark; int err; if (events & (1 << IPCT_DESTROY)) { @@ -826,8 +827,9 @@ ctnetlink_conntrack_event(unsigned int events, const struct nf_ct_event *item) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((events & (1 << IPCT_MARK) || ct->mark) - && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if ((events & (1 << IPCT_MARK) || mark) && + ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif nlmsg_end(skb, nlh); @@ -1154,7 +1156,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((ct->mark & filter->mark.mask) != filter->mark.val) + if ((READ_ONCE(ct->mark) & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif status = (u32)READ_ONCE(ct->status); @@ -2002,9 +2004,9 @@ static void ctnetlink_change_mark(struct nf_conn *ct, mask = ~ntohl(nla_get_be32(cda[CTA_MARK_MASK])); mark = ntohl(nla_get_be32(cda[CTA_MARK])); - newmark = (ct->mark & mask) ^ mark; - if (newmark != ct->mark) - ct->mark = newmark; + newmark = (READ_ONCE(ct->mark) & mask) ^ mark; + if (newmark != READ_ONCE(ct->mark)) + WRITE_ONCE(ct->mark, newmark); } #endif @@ -2669,6 +2671,7 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) { const struct nf_conntrack_zone *zone; struct nlattr *nest_parms; + u32 mark; zone = nf_ct_zone(ct); @@ -2730,7 +2733,8 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct) goto nla_put_failure; #ifdef CONFIG_NF_CONNTRACK_MARK - if (ct->mark && ctnetlink_dump_mark(skb, ct) < 0) + mark = READ_ONCE(ct->mark); + if (mark && ctnetlink_dump_mark(skb, mark) < 0) goto nla_put_failure; #endif if (ctnetlink_dump_labels(skb, ct) < 0) diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..bca839ab1ae8 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -366,7 +366,7 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #if defined(CONFIG_NF_CONNTRACK_MARK) - seq_printf(s, "mark=%u ", ct->mark); + seq_printf(s, "mark=%u ", READ_ONCE(ct->mark)); #endif ct_show_secctx(s, ct); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a3f01f209a53..641dc21f92b4 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -98,7 +98,7 @@ static void nft_ct_get_eval(const struct nft_expr *expr, return; #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - *dest = ct->mark; + *dest = READ_ONCE(ct->mark); return; #endif #ifdef CONFIG_NF_CONNTRACK_SECMARK @@ -297,8 +297,8 @@ static void nft_ct_set_eval(const struct nft_expr *expr, switch (priv->key) { #ifdef CONFIG_NF_CONNTRACK_MARK case NFT_CT_MARK: - if (ct->mark != value) { - ct->mark = value; + if (READ_ONCE(ct->mark) != value) { + WRITE_ONCE(ct->mark, value); nf_conntrack_event_cache(IPCT_MARK, ct); } break; diff --git a/net/netfilter/xt_connmark.c b/net/netfilter/xt_connmark.c index e5ebc0810675..ad3c033db64e 100644 --- a/net/netfilter/xt_connmark.c +++ b/net/netfilter/xt_connmark.c @@ -30,6 +30,7 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) u_int32_t new_targetmark; struct nf_conn *ct; u_int32_t newmark; + u_int32_t oldmark; ct = nf_ct_get(skb, &ctinfo); if (ct == NULL) @@ -37,14 +38,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) switch (info->mode) { case XT_CONNMARK_SET: - newmark = (ct->mark & ~info->ctmask) ^ info->ctmark; + oldmark = READ_ONCE(ct->mark); + newmark = (oldmark & ~info->ctmask) ^ info->ctmark; if (info->shift_dir == D_SHIFT_RIGHT) newmark >>= info->shift_bits; else newmark <<= info->shift_bits; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; @@ -55,15 +57,15 @@ connmark_tg_shift(struct sk_buff *skb, const struct xt_connmark_tginfo2 *info) else new_targetmark <<= info->shift_bits; - newmark = (ct->mark & ~info->ctmask) ^ + newmark = (READ_ONCE(ct->mark) & ~info->ctmask) ^ new_targetmark; - if (ct->mark != newmark) { - ct->mark = newmark; + if (READ_ONCE(ct->mark) != newmark) { + WRITE_ONCE(ct->mark, newmark); nf_conntrack_event_cache(IPCT_MARK, ct); } break; case XT_CONNMARK_RESTORE: - new_targetmark = (ct->mark & info->ctmask); + new_targetmark = (READ_ONCE(ct->mark) & info->ctmask); if (info->shift_dir == D_SHIFT_RIGHT) new_targetmark >>= info->shift_bits; else @@ -126,7 +128,7 @@ connmark_mt(const struct sk_buff *skb, struct xt_action_param *par) if (ct == NULL) return false; - return ((ct->mark & info->mask) == info->mark) ^ info->invert; + return ((READ_ONCE(ct->mark) & info->mask) == info->mark) ^ info->invert; } static int connmark_mt_check(const struct xt_mtchk_param *par) diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c7b10234cf7c..c8eaf4234b2e 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -152,7 +152,7 @@ static u8 ovs_ct_get_state(enum ip_conntrack_info ctinfo) static u32 ovs_ct_get_mark(const struct nf_conn *ct) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - return ct ? ct->mark : 0; + return ct ? READ_ONCE(ct->mark) : 0; #else return 0; #endif @@ -340,9 +340,9 @@ static int ovs_ct_set_mark(struct nf_conn *ct, struct sw_flow_key *key, #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) u32 new_mark; - new_mark = ct_mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = ct_mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); key->ct.mark = new_mark; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 66b143bb04ac..d41002e4613f 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -61,7 +61,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_get(skb, &ctinfo); if (c) { - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; goto out; @@ -81,7 +81,7 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, c = nf_ct_tuplehash_to_ctrack(thash); /* using overlimits stats to count how many packets marked */ ca->tcf_qstats.overlimits++; - skb->mark = c->mark; + skb->mark = READ_ONCE(c->mark); nf_ct_put(c); out: diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b38d91d6b249..4c7f7861ea96 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -178,7 +178,7 @@ static void tcf_ct_flow_table_add_action_meta(struct nf_conn *ct, entry = tcf_ct_flow_table_flow_action_get_next(action); entry->id = FLOW_ACTION_CT_METADATA; #if IS_ENABLED(CONFIG_NF_CONNTRACK_MARK) - entry->ct_metadata.mark = ct->mark; + entry->ct_metadata.mark = READ_ONCE(ct->mark); #endif ctinfo = dir == IP_CT_DIR_ORIGINAL ? IP_CT_ESTABLISHED : IP_CT_ESTABLISHED_REPLY; @@ -936,9 +936,9 @@ static void tcf_ct_act_set_mark(struct nf_conn *ct, u32 mark, u32 mask) if (!mask) return; - new_mark = mark | (ct->mark & ~(mask)); - if (ct->mark != new_mark) { - ct->mark = new_mark; + new_mark = mark | (READ_ONCE(ct->mark) & ~(mask)); + if (READ_ONCE(ct->mark) != new_mark) { + WRITE_ONCE(ct->mark, new_mark); if (nf_ct_is_confirmed(ct)) nf_conntrack_event_cache(IPCT_MARK, ct); } diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index d4102f0a9abd..eaa02f098d1c 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -32,7 +32,7 @@ static void tcf_ctinfo_dscp_set(struct nf_conn *ct, struct tcf_ctinfo *ca, { u8 dscp, newdscp; - newdscp = (((ct->mark & cp->dscpmask) >> cp->dscpmaskshift) << 2) & + newdscp = (((READ_ONCE(ct->mark) & cp->dscpmask) >> cp->dscpmaskshift) << 2) & ~INET_ECN_MASK; switch (proto) { @@ -72,7 +72,7 @@ static void tcf_ctinfo_cpmark_set(struct nf_conn *ct, struct tcf_ctinfo *ca, struct sk_buff *skb) { ca->stats_cpmark_set++; - skb->mark = ct->mark & cp->cpmarkmask; + skb->mark = READ_ONCE(ct->mark) & cp->cpmarkmask; } static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, @@ -130,7 +130,7 @@ static int tcf_ctinfo_act(struct sk_buff *skb, const struct tc_action *a, } if (cp->mode & CTINFO_MODE_DSCP) - if (!cp->dscpstatemask || (ct->mark & cp->dscpstatemask)) + if (!cp->dscpstatemask || (READ_ONCE(ct->mark) & cp->dscpstatemask)) tcf_ctinfo_dscp_set(ct, ca, cp, skb, wlen, proto); if (cp->mode & CTINFO_MODE_CPMARK) -- cgit v1.2.3 From 764f8485890d4988a2083f5dea90cfe0116b25f6 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Nov 2022 20:21:52 -0800 Subject: ipv4/fib: Replace zero-length array with DECLARE_FLEX_ARRAY() helper Zero-length arrays are deprecated[1] and are being replaced with flexible array members in support of the ongoing efforts to tighten the FORTIFY_SOURCE routines on memcpy(), correctly instrument array indexing with UBSAN_BOUNDS, and to globally enable -fstrict-flex-arrays=3. Replace zero-length array with flexible-array member in struct key_vector. This results in no differences in binary output. [1] https://github.com/KSPP/linux/issues/78 Cc: Jakub Kicinski Cc: "David S. Miller" Cc: Hideaki YOSHIFUJI Cc: David Ahern Cc: Eric Dumazet Cc: Paolo Abeni Cc: "Gustavo A. R. Silva" Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 452ff177e4da..c88bf856c443 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -126,7 +126,7 @@ struct key_vector { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ - struct key_vector __rcu *tnode[0]; + DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; -- cgit v1.2.3 From 77934dc6db0d2b111a8f2759e9ad2fb67f5cffa5 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:11 -0800 Subject: dccp/tcp: Reset saddr on failure after inet6?_hash_connect(). When connect() is called on a socket bound to the wildcard address, we change the socket's saddr to a local address. If the socket fails to connect() to the destination, we have to reset the saddr. However, when an error occurs after inet_hash6?_connect() in (dccp|tcp)_v[46]_conect(), we forget to reset saddr and leave the socket bound to the address. From the user's point of view, whether saddr is reset or not varies with errno. Let's fix this inconsistent behaviour. Note that after this patch, the repro [0] will trigger the WARN_ON() in inet_csk_get_port() again, but this patch is not buggy and rather fixes a bug papering over the bhash2's bug for which we need another fix. For the record, the repro causes -EADDRNOTAVAIL in inet_hash6_connect() by this sequence: s1 = socket() s1.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s1.bind(('127.0.0.1', 10000)) s1.sendto(b'hello', MSG_FASTOPEN, (('127.0.0.1', 10000))) # or s1.connect(('127.0.0.1', 10000)) s2 = socket() s2.setsockopt(SOL_SOCKET, SO_REUSEADDR, 1) s2.bind(('0.0.0.0', 10000)) s2.connect(('127.0.0.1', 10000)) # -EADDRNOTAVAIL s2.listen(32) # WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); [0]: https://syzkaller.appspot.com/bug?extid=015d756bbd1f8b5c8f09 Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/dccp/ipv4.c | 2 ++ net/dccp/ipv6.c | 2 ++ net/ipv4/tcp_ipv4.c | 2 ++ net/ipv6/tcp_ipv6.c | 2 ++ 4 files changed, 8 insertions(+) (limited to 'net/ipv4') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 713b7b8dad7e..40640c26680e 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -157,6 +157,8 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index e57b43006074..626166cb6d7e 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -985,6 +985,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 87d440f47a70..6a3a732b584d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -343,6 +343,8 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2a3f9296df1e..81b396e5cf79 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -359,6 +359,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + inet_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; -- cgit v1.2.3 From 8acdad37cd13ce777b0811b2d332314037fcefa8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:12 -0800 Subject: dccp/tcp: Remove NULL check for prev_saddr in inet_bhash2_update_saddr(). When we call inet_bhash2_update_saddr(), prev_saddr is always non-NULL. Let's remove the unnecessary test. Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- net/ipv4/inet_hashtables.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 033bf3c2538f..d745f962745e 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -877,13 +877,10 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - if (prev_saddr) { - spin_lock_bh(&prev_saddr->lock); - __sk_del_bind2_node(sk); - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); - } + spin_lock_bh(&prev_saddr->lock); + __sk_del_bind2_node(sk); + inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); + spin_unlock_bh(&prev_saddr->lock); spin_lock_bh(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); -- cgit v1.2.3 From 8c5dae4c1a49489499e6708c7dd284370ca36287 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:13 -0800 Subject: dccp/tcp: Update saddr under bhash's lock. When we call connect() for a socket bound to a wildcard address, we update saddr locklessly. However, it could result in a data race; another thread iterating over bhash might see a corrupted address. Let's update saddr under the bhash bucket's lock. Fixes: 3df80d9320bc ("[DCCP]: Introduce DCCPv6") Fixes: 7c657876b63c ("[DCCP]: Initial implementation") Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 2 +- net/dccp/ipv4.c | 22 ++++----------------- net/dccp/ipv6.c | 23 ++++------------------ net/ipv4/af_inet.c | 11 +---------- net/ipv4/inet_hashtables.c | 45 +++++++++++++++++++++++++++++++++++++------ net/ipv4/tcp_ipv4.c | 20 ++++--------------- net/ipv6/tcp_ipv6.c | 19 +++--------------- 7 files changed, 56 insertions(+), 86 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 3af1e927247d..ba06e8b52264 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -281,7 +281,7 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in * sk_v6_rcv_saddr (ipv6) changes after it has been binded. The socket's * rcv_saddr field should already have been updated when this is called. */ -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk); +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 40640c26680e..95e376e3b911 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -45,11 +45,10 @@ static unsigned int dccp_v4_pernet_id __read_mostly; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -91,26 +90,13 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) daddr = fl4->daddr; if (inet->inet_saddr == 0) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = - inet_bhashfn_portaddr(&dccp_hashinfo, sk, - sock_net(sk), - inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } inet->inet_dport = usin->sin_port; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 626166cb6d7e..94c101ed57a9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -934,26 +934,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, } if (saddr == NULL) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(&dccp_hashinfo, - sk, sock_net(sk), - inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } - saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4728087c42a5..0da679411330 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1230,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw); static int inet_sk_reselect_saddr(struct sock *sk) { - struct inet_bind_hashbucket *prev_addr_hashbucket; struct inet_sock *inet = inet_sk(sk); __be32 old_saddr = inet->inet_saddr; __be32 daddr = inet->inet_daddr; @@ -1260,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; } - prev_addr_hashbucket = - inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk, - sock_net(sk), inet->inet_num); - - inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; - - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET); if (err) { - inet->inet_saddr = old_saddr; - inet->inet_rcv_saddr = old_saddr; ip_rt_put(rt); return err; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index d745f962745e..18ef370af113 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -858,14 +858,34 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; } -int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk) +static void inet_update_saddr(struct sock *sk, void *saddr, int family) +{ + if (family == AF_INET) { + inet_sk(sk)->inet_saddr = *(__be32 *)saddr; + sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr); + } +#if IS_ENABLED(CONFIG_IPV6) + else { + sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr; + } +#endif +} + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); + struct inet_bind_hashbucket *head, *head2; struct inet_bind2_bucket *tb2, *new_tb2; int l3mdev = inet_sk_bound_l3mdev(sk); - struct inet_bind_hashbucket *head2; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); + int bhash; + + if (!inet_csk(sk)->icsk_bind2_hash) { + /* Not bind()ed before. */ + inet_update_saddr(sk, saddr, family); + return 0; + } /* Allocate a bind2 bucket ahead of time to avoid permanently putting * the bhash2 table in an inconsistent state if a new tb2 bucket @@ -875,14 +895,25 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc if (!new_tb2) return -ENOMEM; + bhash = inet_bhashfn(net, port, hinfo->bhash_size); + head = &hinfo->bhash[bhash]; head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); - spin_lock_bh(&prev_saddr->lock); + /* If we change saddr locklessly, another thread + * iterating over bhash might see corrupted address. + */ + spin_lock_bh(&head->lock); + + spin_lock(&head2->lock); __sk_del_bind2_node(sk); inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); - spin_unlock_bh(&prev_saddr->lock); + spin_unlock(&head2->lock); + + inet_update_saddr(sk, saddr, family); - spin_lock_bh(&head2->lock); + head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); + + spin_lock(&head2->lock); tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk); if (!tb2) { tb2 = new_tb2; @@ -890,7 +921,9 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc } sk_add_bind2_node(sk, &tb2->owners); inet_csk(sk)->icsk_bind2_hash = tb2; - spin_unlock_bh(&head2->lock); + spin_unlock(&head2->lock); + + spin_unlock_bh(&head->lock); if (tb2 != new_tb2) kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6a3a732b584d..23dd7e9df2d5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; - __be32 daddr, nexthop, prev_sk_rcv_saddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct ip_options_rcu *inet_opt; struct net *net = sock_net(sk); __be16 orig_sport, orig_dport; + __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; @@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!inet->inet_saddr) { - if (inet_csk(sk)->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_sk_rcv_saddr = sk->sk_rcv_saddr; - } - inet->inet_saddr = fl4->saddr; - } - - sk_rcv_saddr_set(sk, inet->inet_saddr); - - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); + err = inet_bhash2_update_saddr(sk, &fl4->saddr, AF_INET); if (err) { - inet->inet_saddr = 0; - sk_rcv_saddr_set(sk, prev_sk_rcv_saddr); ip_rt_put(rt); return err; } + } else { + sk_rcv_saddr_set(sk, inet->inet_saddr); } if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 81b396e5cf79..2f3ca3190d26 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -292,24 +292,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { - struct inet_bind_hashbucket *prev_addr_hashbucket = NULL; - struct in6_addr prev_v6_rcv_saddr; - - if (icsk->icsk_bind2_hash) { - prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo, - sk, net, inet->inet_num); - prev_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - } saddr = &fl6.saddr; - sk->sk_v6_rcv_saddr = *saddr; - if (prev_addr_hashbucket) { - err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk); - if (err) { - sk->sk_v6_rcv_saddr = prev_v6_rcv_saddr; - goto failure; - } - } + err = inet_bhash2_update_saddr(sk, saddr, AF_INET6); + if (err) + goto failure; } /* set the source address */ -- cgit v1.2.3 From e0833d1fedb02f038b526ae7dde178a076f56545 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Fri, 18 Nov 2022 17:49:14 -0800 Subject: dccp/tcp: Fixup bhash2 bucket when connect() fails. If a socket bound to a wildcard address fails to connect(), we only reset saddr and keep the port. Then, we have to fix up the bhash2 bucket; otherwise, the bucket has an inconsistent address in the list. Also, listen() for such a socket will fire the WARN_ON() in inet_csk_get_port(). [0] Note that when a system runs out of memory, we give up fixing the bucket and unlink sk from bhash and bhash2 by inet_put_port(). [0]: WARNING: CPU: 0 PID: 207 at net/ipv4/inet_connection_sock.c:548 inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Modules linked in: CPU: 0 PID: 207 Comm: bhash2_prev_rep Not tainted 6.1.0-rc3-00799-gc8421681c845 #63 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.amzn2022.0.1 04/01/2014 RIP: 0010:inet_csk_get_port (net/ipv4/inet_connection_sock.c:548 (discriminator 1)) Code: 74 a7 eb 93 48 8b 54 24 18 0f b7 cb 4c 89 e6 4c 89 ff e8 48 b2 ff ff 49 8b 87 18 04 00 00 e9 32 ff ff ff 0f 0b e9 34 ff ff ff <0f> 0b e9 42 ff ff ff 41 8b 7f 50 41 8b 4f 54 89 fe 81 f6 00 00 ff RSP: 0018:ffffc900003d7e50 EFLAGS: 00010202 RAX: ffff8881047fb500 RBX: 0000000000004e20 RCX: 0000000000000000 RDX: 000000000000000a RSI: 00000000fffffe00 RDI: 00000000ffffffff RBP: ffffffff8324dc00 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 R13: 0000000000000001 R14: 0000000000004e20 R15: ffff8881054e1280 FS: 00007f8ac04dc740(0000) GS:ffff88842fc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020001540 CR3: 00000001055fa003 CR4: 0000000000770ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: inet_csk_listen_start (net/ipv4/inet_connection_sock.c:1205) inet_listen (net/ipv4/af_inet.c:228) __sys_listen (net/socket.c:1810) __x64_sys_listen (net/socket.c:1819 net/socket.c:1817 net/socket.c:1817) do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120) RIP: 0033:0x7f8ac051de5d Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 93 af 1b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc1c177248 EFLAGS: 00000206 ORIG_RAX: 0000000000000032 RAX: ffffffffffffffda RBX: 0000000020001550 RCX: 00007f8ac051de5d RDX: ffffffffffffff80 RSI: 0000000000000000 RDI: 0000000000000004 RBP: 00007ffc1c177270 R08: 0000000000000018 R09: 0000000000000007 R10: 0000000020001540 R11: 0000000000000206 R12: 00007ffc1c177388 R13: 0000000000401169 R14: 0000000000403e18 R15: 00007f8ac0723000 Fixes: 28044fc1d495 ("net: Add a bhash2 table hashed by port and address") Reported-by: syzbot Reported-by: Mat Martineau Signed-off-by: Kuniyuki Iwashima Acked-by: Joanne Koong Reviewed-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/net/inet_hashtables.h | 1 + net/dccp/ipv4.c | 3 +-- net/dccp/ipv6.c | 3 +-- net/dccp/proto.c | 3 +-- net/ipv4/inet_hashtables.c | 38 ++++++++++++++++++++++++++++++++++---- net/ipv4/tcp.c | 3 +-- net/ipv4/tcp_ipv4.c | 3 +-- net/ipv6/tcp_ipv6.c | 3 +-- 8 files changed, 41 insertions(+), 16 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index ba06e8b52264..69174093078f 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -282,6 +282,7 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in * rcv_saddr field should already have been updated when this is called. */ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family); +void inet_bhash2_reset_saddr(struct sock *sk); void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 95e376e3b911..b780827f5e0a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -143,8 +143,7 @@ failure: * This unhashes the socket and releases the local port, if necessary. */ dccp_set_state(sk, DCCP_CLOSED); - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 94c101ed57a9..602f3432d80b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -970,8 +970,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: dccp_set_state(sk, DCCP_CLOSED); - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); __sk_dst_reset(sk); failure: inet->inet_dport = 0; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index c548ca3e9b0e..85e35c5e8890 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -279,8 +279,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 18ef370af113..3cec471a2cd2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -871,7 +871,7 @@ static void inet_update_saddr(struct sock *sk, void *saddr, int family) #endif } -int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset) { struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk); struct inet_bind_hashbucket *head, *head2; @@ -883,7 +883,11 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) if (!inet_csk(sk)->icsk_bind2_hash) { /* Not bind()ed before. */ - inet_update_saddr(sk, saddr, family); + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); + return 0; } @@ -892,8 +896,19 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) * allocation fails. */ new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC); - if (!new_tb2) + if (!new_tb2) { + if (reset) { + /* The (INADDR_ANY, port) bucket might have already + * been freed, then we cannot fixup icsk_bind2_hash, + * so we give up and unlink sk from bhash/bhash2 not + * to leave inconsistency in bhash2. + */ + inet_put_port(sk); + inet_reset_saddr(sk); + } + return -ENOMEM; + } bhash = inet_bhashfn(net, port, hinfo->bhash_size); head = &hinfo->bhash[bhash]; @@ -909,7 +924,10 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash); spin_unlock(&head2->lock); - inet_update_saddr(sk, saddr, family); + if (reset) + inet_reset_saddr(sk); + else + inet_update_saddr(sk, saddr, family); head2 = inet_bhashfn_portaddr(hinfo, sk, net, port); @@ -930,8 +948,20 @@ int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) return 0; } + +int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family) +{ + return __inet_bhash2_update_saddr(sk, saddr, family, false); +} EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr); +void inet_bhash2_reset_saddr(struct sock *sk) +{ + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + __inet_bhash2_update_saddr(sk, NULL, 0, true); +} +EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr); + /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 54836a6b81d6..4f2205756cfe 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3114,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 23dd7e9df2d5..da46357f501b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -331,8 +331,7 @@ failure: * if necessary. */ tcp_set_state(sk, TCP_CLOSE); - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2f3ca3190d26..f0548dbcabd2 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -346,8 +346,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, late_failure: tcp_set_state(sk, TCP_CLOSE); - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) - inet_reset_saddr(sk); + inet_bhash2_reset_saddr(sk); failure: inet->inet_dport = 0; sk->sk_route_caps = 0; -- cgit v1.2.3 From 568fe84940ac0e4e0b2cd7751b8b4911f7b9c215 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Sun, 20 Nov 2022 15:28:38 +0800 Subject: ipv4: Fix error return code in fib_table_insert() In fib_table_insert(), if the alias was already inserted, but node not exist, the error code should be set before return from error handling path. Fixes: a6c76c17df02 ("ipv4: Notify route after insertion to the routing table") Signed-off-by: Ziyang Xuan Link: https://lore.kernel.org/r/20221120072838.2167047-1-william.xuanziyang@huawei.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_trie.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index c88bf856c443..74d403dbd2b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); - if (WARN_ON_ONCE(!l)) + if (WARN_ON_ONCE(!l)) { + err = -ENOENT; goto out_free_new_fa; + } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { -- cgit v1.2.3 From d5082d386eee7e8ec46fa8581932c81a4961dcef Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 24 Nov 2022 23:09:32 +0200 Subject: ipv4: Fix route deletion when nexthop info is not specified When the kernel receives a route deletion request from user space it tries to delete a route that matches the route attributes specified in the request. If only prefix information is specified in the request, the kernel should delete the first matching FIB alias regardless of its associated FIB info. However, an error is currently returned when the FIB info is backed by a nexthop object: # ip nexthop add id 1 via 192.0.2.2 dev dummy10 # ip route add 198.51.100.0/24 nhid 1 # ip route del 198.51.100.0/24 RTNETLINK answers: No such process Fix by matching on such a FIB info when legacy nexthop attributes are not specified in the request. An earlier check already covers the case where a nexthop ID is specified in the request. Add tests that cover these flows. Before the fix: # ./fib_nexthops.sh -t ipv4_fcnal ... TEST: Delete route when not specifying nexthop attributes [FAIL] Tests passed: 11 Tests failed: 1 After the fix: # ./fib_nexthops.sh -t ipv4_fcnal ... TEST: Delete route when not specifying nexthop attributes [ OK ] Tests passed: 12 Tests failed: 0 No regressions in other tests: # ./fib_nexthops.sh ... Tests passed: 228 Tests failed: 0 # ./fib_tests.sh ... Tests passed: 186 Tests failed: 0 Cc: stable@vger.kernel.org Reported-by: Jonas Gorski Tested-by: Jonas Gorski Fixes: 493ced1ac47c ("ipv4: Allow routes to use nexthop objects") Fixes: 6bf92d70e690 ("net: ipv4: fix route with nexthop object delete warning") Fixes: 61b91eb33a69 ("ipv4: Handle attempt to delete multipath route when fib_info contains an nh reference") Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20221124210932.2470010-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski --- net/ipv4/fib_semantics.c | 8 +++++--- tools/testing/selftests/net/fib_nexthops.sh | 11 +++++++++++ 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f721c308248b..19a662003eef 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -888,9 +888,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi, return 1; } - /* cannot match on nexthop object attributes */ - if (fi->nh) - return 1; + if (fi->nh) { + if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp) + return 1; + return 0; + } if (cfg->fc_oif || cfg->fc_gw_family) { struct fib_nh *nh; diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index ee5e98204d3d..a47b26ab48f2 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1228,6 +1228,17 @@ ipv4_fcnal() run_cmd "$IP ro add 172.16.101.0/24 nhid 21" run_cmd "$IP ro del 172.16.101.0/24 nexthop via 172.16.1.7 dev veth1 nexthop via 172.16.1.8 dev veth1" log_test $? 2 "Delete multipath route with only nh id based entry" + + run_cmd "$IP nexthop add id 22 via 172.16.1.6 dev veth1" + run_cmd "$IP ro add 172.16.102.0/24 nhid 22" + run_cmd "$IP ro del 172.16.102.0/24 dev veth1" + log_test $? 2 "Delete route when specifying only nexthop device" + + run_cmd "$IP ro del 172.16.102.0/24 via 172.16.1.6" + log_test $? 2 "Delete route when specifying only gateway" + + run_cmd "$IP ro del 172.16.102.0/24" + log_test $? 0 "Delete route when not specifying nexthop attributes" } ipv4_grp_fcnal() -- cgit v1.2.3