From ec8de7544778a329484b6aead305b7549aa9beaa Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:46 -0700 Subject: nexthop: Move nlmsg_parse() in rtm_to_nh_config() to rtm_new_nexthop(). We will split rtm_to_nh_config() into non-RTNL and RTNL parts, and then the latter also needs tb. As a prep, let's move nlmsg_parse() to rtm_new_nexthop(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: David Ahern Reviewed-by: Eric Dumazet Link: https://patch.msgid.link/20250319230743.65267-2-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 01df7dd795f0..487933ecdb68 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3016,19 +3016,13 @@ static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg, } static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct nh_config *cfg, + struct nlmsghdr *nlh, struct nlattr **tb, + struct nh_config *cfg, struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; int err; - err = nlmsg_parse(nlh, sizeof(*nhm), tb, - ARRAY_SIZE(rtm_nh_policy_new) - 1, - rtm_nh_policy_new, extack); - if (err < 0) - return err; - err = -EINVAL; if (nhm->resvd || nhm->nh_scope) { NL_SET_ERR_MSG(extack, "Invalid values in ancillary header"); @@ -3093,7 +3087,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, NL_SET_ERR_MSG(extack, "Invalid group type"); goto out; } - err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb), + + err = nh_check_attr_group(net, tb, ARRAY_SIZE(rtm_nh_policy_new), cfg->nh_grp_type, extack); if (err) goto out; @@ -3211,18 +3206,26 @@ out: static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)]; struct net *net = sock_net(skb->sk); struct nh_config cfg; struct nexthop *nh; int err; - err = rtm_to_nh_config(net, skb, nlh, &cfg, extack); - if (!err) { - nh = nexthop_add(net, &cfg, extack); - if (IS_ERR(nh)) - err = PTR_ERR(nh); - } + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, + ARRAY_SIZE(rtm_nh_policy_new) - 1, + rtm_nh_policy_new, extack); + if (err < 0) + goto out; + err = rtm_to_nh_config(net, skb, nlh, tb, &cfg, extack); + if (err) + goto out; + + nh = nexthop_add(net, &cfg, extack); + if (IS_ERR(nh)) + err = PTR_ERR(nh); +out: return err; } -- cgit v1.2.3 From 9b9674f3e73a2be9a702d65b77fdac279590a009 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:47 -0700 Subject: nexthop: Split nh_check_attr_group(). We will push RTNL down to rtm_new_nexthop(), and then we want to move non-RTNL operations out of the scope. nh_check_attr_group() validates NHA_GROUP attributes, and nexthop_find_by_id() and some validation requires RTNL. Let's factorise such parts as nh_check_attr_group_rtnl() and call it from rtm_to_nh_config_rtnl(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-3-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 68 +++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 47 insertions(+), 21 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 487933ecdb68..d30edc14b039 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1272,10 +1272,8 @@ static int nh_check_attr_group(struct net *net, u16 nh_grp_type, struct netlink_ext_ack *extack) { unsigned int len = nla_len(tb[NHA_GROUP]); - u8 nh_family = AF_UNSPEC; struct nexthop_grp *nhg; unsigned int i, j; - u8 nhg_fdb = 0; if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, @@ -1307,10 +1305,41 @@ static int nh_check_attr_group(struct net *net, } } - if (tb[NHA_FDB]) - nhg_fdb = 1; nhg = nla_data(tb[NHA_GROUP]); - for (i = 0; i < len; ++i) { + for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { + if (!tb[i]) + continue; + switch (i) { + case NHA_HW_STATS_ENABLE: + case NHA_FDB: + continue; + case NHA_RES_GROUP: + if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) + continue; + break; + } + NL_SET_ERR_MSG(extack, + "No other attributes can be set in nexthop groups"); + return -EINVAL; + } + + return 0; +} + +static int nh_check_attr_group_rtnl(struct net *net, struct nlattr *tb[], + struct netlink_ext_ack *extack) +{ + u8 nh_family = AF_UNSPEC; + struct nexthop_grp *nhg; + unsigned int len; + unsigned int i; + u8 nhg_fdb; + + len = nla_len(tb[NHA_GROUP]) / sizeof(*nhg); + nhg = nla_data(tb[NHA_GROUP]); + nhg_fdb = !!tb[NHA_FDB]; + + for (i = 0; i < len; i++) { struct nexthop *nh; bool is_fdb_nh; @@ -1330,22 +1359,6 @@ static int nh_check_attr_group(struct net *net, return -EINVAL; } } - for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) { - if (!tb[i]) - continue; - switch (i) { - case NHA_HW_STATS_ENABLE: - case NHA_FDB: - continue; - case NHA_RES_GROUP: - if (nh_grp_type == NEXTHOP_GRP_TYPE_RES) - continue; - break; - } - NL_SET_ERR_MSG(extack, - "No other attributes can be set in nexthop groups"); - return -EINVAL; - } return 0; } @@ -3202,6 +3215,15 @@ out: return err; } +static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + if (tb[NHA_GROUP]) + return nh_check_attr_group_rtnl(net, tb, extack); + + return 0; +} + /* rtnl */ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) @@ -3222,6 +3244,10 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto out; + err = rtm_to_nh_config_rtnl(net, tb, extack); + if (err) + goto out; + nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); -- cgit v1.2.3 From caa074573ca0a110b609bf35b7fec3d967945315 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:48 -0700 Subject: nexthop: Move NHA_OIF validation to rtm_to_nh_config_rtnl(). NHA_OIF needs to look up a device by __dev_get_by_index(), which requires RTNL. Let's move NHA_OIF validation to rtm_to_nh_config_rtnl(). Note that the proceeding checks made the original !cfg->nh_fdb check redundant. NHA_FDB is set -> NHA_OIF cannot be set NHA_FDB is set but false -> NHA_OIF must be set NHA_FDB is not set -> NHA_OIF must be set Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-4-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 43 +++++++++++++++++++++++-------------------- 1 file changed, 23 insertions(+), 20 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d30edc14b039..426cdf301c6f 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3134,25 +3134,6 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } - if (!cfg->nh_fdb && tb[NHA_OIF]) { - cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); - if (cfg->nh_ifindex) - cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); - - if (!cfg->dev) { - NL_SET_ERR_MSG(extack, "Invalid device index"); - goto out; - } else if (!(cfg->dev->flags & IFF_UP)) { - NL_SET_ERR_MSG(extack, "Nexthop device is not up"); - err = -ENETDOWN; - goto out; - } else if (!netif_carrier_ok(cfg->dev)) { - NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); - err = -ENETDOWN; - goto out; - } - } - err = -EINVAL; if (tb[NHA_GATEWAY]) { struct nlattr *gwa = tb[NHA_GATEWAY]; @@ -3216,11 +3197,33 @@ out: } static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb, + struct nh_config *cfg, struct netlink_ext_ack *extack) { if (tb[NHA_GROUP]) return nh_check_attr_group_rtnl(net, tb, extack); + if (tb[NHA_OIF]) { + cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]); + if (cfg->nh_ifindex) + cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex); + + if (!cfg->dev) { + NL_SET_ERR_MSG(extack, "Invalid device index"); + return -EINVAL; + } + + if (!(cfg->dev->flags & IFF_UP)) { + NL_SET_ERR_MSG(extack, "Nexthop device is not up"); + return -ENETDOWN; + } + + if (!netif_carrier_ok(cfg->dev)) { + NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down"); + return -ENETDOWN; + } + } + return 0; } @@ -3244,7 +3247,7 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto out; - err = rtm_to_nh_config_rtnl(net, tb, extack); + err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack); if (err) goto out; -- cgit v1.2.3 From 53b18aa998b733d91ee4be45619d8e9738aac67c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:49 -0700 Subject: nexthop: Check NLM_F_REPLACE and NHA_ID in rtm_new_nexthop(). nexthop_add() checks if NLM_F_REPLACE is specified without non-zero NHA_ID, which does not require RTNL. Let's move the check to rtm_new_nexthop(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-5-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 426cdf301c6f..fb129c830040 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2928,11 +2928,6 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg, struct nexthop *nh; int err; - if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) { - NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); - return ERR_PTR(-EINVAL); - } - if (!cfg->nh_id) { cfg->nh_id = nh_find_unused_id(net); if (!cfg->nh_id) { @@ -3247,6 +3242,12 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) goto out; + if (cfg.nlflags & NLM_F_REPLACE && !cfg.nh_id) { + NL_SET_ERR_MSG(extack, "Replace requires nexthop id"); + err = -EINVAL; + goto out; + } + err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack); if (err) goto out; -- cgit v1.2.3 From b6af3890574a674d54216dacb66470fb7147b835 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:50 -0700 Subject: nexthop: Remove redundant group len check in nexthop_create_group(). The number of NHA_GROUP entries is guaranteed to be non-zero in nh_check_attr_group(). Let's remove the redundant check in nexthop_create_group(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-6-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index fb129c830040..c552bb46aa23 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2692,9 +2692,6 @@ static struct nexthop *nexthop_create_group(struct net *net, int err; int i; - if (WARN_ON(!num_nh)) - return ERR_PTR(-EINVAL); - nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From f5fabaff86cbb049dbb149c91d21807069d38de3 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:51 -0700 Subject: nexthop: Convert RTM_NEWNEXTHOP to per-netns RTNL. If we pass false to the rtnl_held param of lwtunnel_valid_encap_type(), we can move RTNL down before rtm_to_nh_config_rtnl(). Let's use rtnl_net_lock() in rtm_new_nexthop(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-7-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index c552bb46aa23..06d5467eadc1 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3169,7 +3169,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->nh_encap_type, - extack, true); + extack, false); if (err < 0) goto out; @@ -3245,13 +3245,18 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } + rtnl_net_lock(net); + err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack); if (err) - goto out; + goto unlock; nh = nexthop_add(net, &cfg, extack); if (IS_ERR(nh)) err = PTR_ERR(nh); + +unlock: + rtnl_net_unlock(net); out: return err; } @@ -4067,18 +4072,19 @@ static struct pernet_operations nexthop_net_ops = { }; static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = { - {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop}, + {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, + .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop}, {.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop, .dumpit = rtm_dump_nexthop}, {.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket, .dumpit = rtm_dump_nexthop_bucket}, {.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP, - .doit = rtm_new_nexthop}, + .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, {.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP, - .doit = rtm_new_nexthop}, + .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, {.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP, .dumpit = rtm_dump_nexthop}, }; -- cgit v1.2.3 From 29c8e323320f2a1c54d7dfb0937255fa8c2ff901 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 19 Mar 2025 16:06:52 -0700 Subject: nexthop: Convert RTM_DELNEXTHOP to per-netns RTNL. In rtm_del_nexthop(), only nexthop_find_by_id() and remove_nexthop() require RTNL as they touch net->nexthop.rb_root. Let's move RTNL down as rtnl_net_lock() before nexthop_find_by_id(). Signed-off-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Link: https://patch.msgid.link/20250319230743.65267-8-kuniyu@amazon.com Signed-off-by: Jakub Kicinski --- net/ipv4/nexthop.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 06d5467eadc1..467151517023 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3314,13 +3314,17 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; + rtnl_net_lock(net); + nh = nexthop_find_by_id(net, id); - if (!nh) - return -ENOENT; + if (nh) + remove_nexthop(net, nh, &nlinfo); + else + err = -ENOENT; - remove_nexthop(net, nh, &nlinfo); + rtnl_net_unlock(net); - return 0; + return err; } /* rtnl */ @@ -4074,7 +4078,8 @@ static struct pernet_operations nexthop_net_ops = { static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET}, - {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop}, + {.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop, + .flags = RTNL_FLAG_DOIT_PERNET}, {.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop, .dumpit = rtm_dump_nexthop}, {.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket, -- cgit v1.2.3