diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-03 14:04:18 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-03 14:04:18 -0700 |
| commit | 5bb053bef82523a8fd78d650bca81c9f114fa276 (patch) | |
| tree | 58c2fe47f60bb69230bb05d57a6c9e3f47f7b1fe /net/ipv4 | |
| parent | bb2407a7219760926760f0448fddf00d625e5aec (diff) | |
| parent | 159f02977b2feb18a4bece5e586c838a6d26d44b (diff) | |
| download | op-kernel-dev-5bb053bef82523a8fd78d650bca81c9f114fa276.zip op-kernel-dev-5bb053bef82523a8fd78d650bca81c9f114fa276.tar.gz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) Support offloading wireless authentication to userspace via
NL80211_CMD_EXTERNAL_AUTH, from Srinivas Dasari.
2) A lot of work on network namespace setup/teardown from Kirill Tkhai.
Setup and cleanup of namespaces now all run asynchronously and thus
performance is significantly increased.
3) Add rx/tx timestamping support to mv88e6xxx driver, from Brandon
Streiff.
4) Support zerocopy on RDS sockets, from Sowmini Varadhan.
5) Use denser instruction encoding in x86 eBPF JIT, from Daniel
Borkmann.
6) Support hw offload of vlan filtering in mvpp2 dreiver, from Maxime
Chevallier.
7) Support grafting of child qdiscs in mlxsw driver, from Nogah
Frankel.
8) Add packet forwarding tests to selftests, from Ido Schimmel.
9) Deal with sub-optimal GSO packets better in BBR congestion control,
from Eric Dumazet.
10) Support 5-tuple hashing in ipv6 multipath routing, from David Ahern.
11) Add path MTU tests to selftests, from Stefano Brivio.
12) Various bits of IPSEC offloading support for mlx5, from Aviad
Yehezkel, Yossi Kuperman, and Saeed Mahameed.
13) Support RSS spreading on ntuple filters in SFC driver, from Edward
Cree.
14) Lots of sockmap work from John Fastabend. Applications can use eBPF
to filter sendmsg and sendpage operations.
15) In-kernel receive TLS support, from Dave Watson.
16) Add XDP support to ixgbevf, this is significant because it should
allow optimized XDP usage in various cloud environments. From Tony
Nguyen.
17) Add new Intel E800 series "ice" ethernet driver, from Anirudh
Venkataramanan et al.
18) IP fragmentation match offload support in nfp driver, from Pieter
Jansen van Vuuren.
19) Support XDP redirect in i40e driver, from Björn Töpel.
20) Add BPF_RAW_TRACEPOINT program type for accessing the arguments of
tracepoints in their raw form, from Alexei Starovoitov.
21) Lots of striding RQ improvements to mlx5 driver with many
performance improvements, from Tariq Toukan.
22) Use rhashtable for inet frag reassembly, from Eric Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1678 commits)
net: mvneta: improve suspend/resume
net: mvneta: split rxq/txq init and txq deinit into SW and HW parts
ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh
net: bgmac: Fix endian access in bgmac_dma_tx_ring_free()
net: bgmac: Correctly annotate register space
route: check sysctl_fib_multipath_use_neigh earlier than hash
fix typo in command value in drivers/net/phy/mdio-bitbang.
sky2: Increase D3 delay to sky2 stops working after suspend
net/mlx5e: Set EQE based as default TX interrupt moderation mode
ibmvnic: Disable irqs before exiting reset from closed state
net: sched: do not emit messages while holding spinlock
vlan: also check phy_driver ts_info for vlan's real device
Bluetooth: Mark expected switch fall-throughs
Bluetooth: Set HCI_QUIRK_SIMULTANEOUS_DISCOVERY for BTUSB_QCA_ROME
Bluetooth: btrsi: remove unused including <linux/version.h>
Bluetooth: hci_bcm: Remove DMI quirk for the MINIX Z83-4
sh_eth: kill useless check in __sh_eth_get_regs()
sh_eth: add sh_eth_cpu_data::no_xdfar flag
ipv6: factorize sk_wmem_alloc updates done by __ip6_append_data()
ipv4: factorize sk_wmem_alloc updates done by __ip_append_data()
...
Diffstat (limited to 'net/ipv4')
46 files changed, 1225 insertions, 1472 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index f48fe6f..80dad30 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -212,9 +212,14 @@ config NET_IPGRE_BROADCAST Network), but can be distributed all over the Internet. If you want to do that, say Y here and to "IP multicast routing" below. +config IP_MROUTE_COMMON + bool + depends on IP_MROUTE || IPV6_MROUTE + config IP_MROUTE bool "IP: multicast routing" depends on IP_MULTICAST + select IP_MROUTE_COMMON help This is used if you want your machine to act as a router for IP packets that have several destination addresses. It is needed on the diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 47a0a66..a07b7dd 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o +obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o obj-$(CONFIG_NET_IPIP) += ipip.o gre-y := gre_demux.o obj-$(CONFIG_NET_FOU) += fou.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e4329e1..eaed036 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -432,23 +432,37 @@ EXPORT_SYMBOL(inet_release); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { - struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; struct sock *sk = sock->sk; - struct inet_sock *inet = inet_sk(sk); - struct net *net = sock_net(sk); - unsigned short snum; - int chk_addr_ret; - u32 tb_id = RT_TABLE_LOCAL; int err; /* If the socket has its own bind function then use it. (RAW) */ if (sk->sk_prot->bind) { - err = sk->sk_prot->bind(sk, uaddr, addr_len); - goto out; + return sk->sk_prot->bind(sk, uaddr, addr_len); } - err = -EINVAL; if (addr_len < sizeof(struct sockaddr_in)) - goto out; + return -EINVAL; + + /* BPF prog is run before any checks are done so that if the prog + * changes context in a wrong way it will be caught. + */ + err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr); + if (err) + return err; + + return __inet_bind(sk, uaddr, addr_len, false, true); +} +EXPORT_SYMBOL(inet_bind); + +int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, + bool force_bind_address_no_port, bool with_lock) +{ + struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; + struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); + unsigned short snum; + int chk_addr_ret; + u32 tb_id = RT_TABLE_LOCAL; + int err; if (addr->sin_family != AF_INET) { /* Compatibility games : accept AF_UNSPEC (mapped to AF_INET) @@ -492,7 +506,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * would be illegal to use them (multicast/broadcast) in * which case the sending device address is used. */ - lock_sock(sk); + if (with_lock) + lock_sock(sk); /* Check these errors (active socket, double bind). */ err = -EINVAL; @@ -504,11 +519,18 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ - if ((snum || !inet->bind_address_no_port) && - sk->sk_prot->get_port(sk, snum)) { - inet->inet_saddr = inet->inet_rcv_saddr = 0; - err = -EADDRINUSE; - goto out_release_sock; + if (snum || !(inet->bind_address_no_port || + force_bind_address_no_port)) { + if (sk->sk_prot->get_port(sk, snum)) { + inet->inet_saddr = inet->inet_rcv_saddr = 0; + err = -EADDRINUSE; + goto out_release_sock; + } + err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk); + if (err) { + inet->inet_saddr = inet->inet_rcv_saddr = 0; + goto out_release_sock; + } } if (inet->inet_rcv_saddr) @@ -521,22 +543,29 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); err = 0; out_release_sock: - release_sock(sk); + if (with_lock) + release_sock(sk); out: return err; } -EXPORT_SYMBOL(inet_bind); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; + int err; if (addr_len < sizeof(uaddr->sa_family)) return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) return sk->sk_prot->disconnect(sk, flags); + if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { + err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); + if (err) + return err; + } + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, uaddr, addr_len); @@ -617,6 +646,12 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (sk->sk_state != TCP_CLOSE) goto out; + if (BPF_CGROUP_PRE_CONNECT_ENABLED(sk)) { + err = sk->sk_prot->pre_connect(sk, uaddr, addr_len); + if (err) + goto out; + } + err = sk->sk_prot->connect(sk, uaddr, addr_len); if (err < 0) goto out; @@ -723,7 +758,7 @@ EXPORT_SYMBOL(inet_accept); * This does both peername and sockname. */ int inet_getname(struct socket *sock, struct sockaddr *uaddr, - int *uaddr_len, int peer) + int peer) { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); @@ -745,8 +780,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin_addr.s_addr = addr; } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - *uaddr_len = sizeof(*sin); - return 0; + return sizeof(*sin); } EXPORT_SYMBOL(inet_getname); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f28f06c..be4c595 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1434,7 +1434,7 @@ static const struct file_operations arp_seq_fops = { static int __net_init arp_net_init(struct net *net) { - if (!proc_create("arp", S_IRUGO, net->proc_net, &arp_seq_fops)) + if (!proc_create("arp", 0444, net->proc_net, &arp_seq_fops)) return -ENOMEM; return 0; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 296d0b9..9768901 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -654,7 +654,7 @@ static void esp_input_restore_header(struct sk_buff *skb) static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi) { struct xfrm_state *x = xfrm_input_state(skb); - struct ip_esp_hdr *esph = (struct ip_esp_hdr *)skb->data; + struct ip_esp_hdr *esph; /* For ESN we move the header forward by 4 bytes to * accomodate the high bits. We will move it back after diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index da5635f..7cf755e 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -138,6 +138,8 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle || (x->xso.dev != skb->dev)) esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); + else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) + esp_features = features & ~NETIF_F_CSUM_MASK; xo->flags |= XFRM_GSO_SEGMENT; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 35d646a..737d11b 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -182,6 +182,17 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) if (r->tos && (r->tos != fl4->flowi4_tos)) return 0; + if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto)) + return 0; + + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport)) + return 0; + + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport)) + return 0; + return 1; } @@ -244,6 +255,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, } #endif + if (fib_rule_requires_fldissect(rule)) + net->ipv4.fib_rules_require_fldissect++; + rule4->src_len = frh->src_len; rule4->srcmask = inet_make_mask(rule4->src_len); rule4->dst_len = frh->dst_len; @@ -272,6 +286,10 @@ static int fib4_rule_delete(struct fib_rule *rule) net->ipv4.fib_num_tclassid_users--; #endif net->ipv4.fib_has_custom_rules = true; + + if (net->ipv4.fib_rules_require_fldissect && + fib_rule_requires_fldissect(rule)) + net->ipv4.fib_rules_require_fldissect--; errout: return err; } @@ -389,6 +407,7 @@ int __net_init fib4_rules_init(struct net *net) goto fail; net->ipv4.rules_ops = ops; net->ipv4.fib_has_custom_rules = false; + net->ipv4.fib_rules_require_fldissect = 0; return 0; fail: diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 7d36a95..c27122f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -171,7 +171,7 @@ static void free_nh_exceptions(struct fib_nh *nh) fnhe = rcu_dereference_protected(hash[i].chain, 1); while (fnhe) { struct fib_nh_exception *next; - + next = rcu_dereference_protected(fnhe->fnhe_next, 1); rt_fibinfo_free(&fnhe->fnhe_rth_input); @@ -1746,18 +1746,20 @@ void fib_select_multipath(struct fib_result *res, int hash) bool first = false; for_nexthops(fi) { + if (net->ipv4.sysctl_fib_multipath_use_neigh) { + if (!fib_good_nh(nh)) + continue; + if (!first) { + res->nh_sel = nhsel; + first = true; + } + } + if (hash > atomic_read(&nh->nh_upper_bound)) continue; - if (!net->ipv4.sysctl_fib_multipath_use_neigh || - fib_good_nh(nh)) { - res->nh_sel = nhsel; - return; - } - if (!first) { - res->nh_sel = nhsel; - first = true; - } + res->nh_sel = nhsel; + return; } endfor_nexthops(fi); } #endif @@ -1765,14 +1767,12 @@ void fib_select_multipath(struct fib_result *res, int hash) void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb) { - bool oif_check; - - oif_check = (fl4->flowi4_oif == 0 || - fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF); + if (fl4->flowi4_oif && !(fl4->flowi4_flags & FLOWI_FLAG_SKIP_NH_OIF)) + goto check_saddr; #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi->fib_nhs > 1 && oif_check) { - int h = fib_multipath_hash(res->fi, fl4, skb); + if (res->fi->fib_nhs > 1) { + int h = fib_multipath_hash(net, fl4, skb, NULL); fib_select_multipath(res, h); } @@ -1780,10 +1780,10 @@ void fib_select_path(struct net *net, struct fib_result *res, #endif if (!res->prefixlen && res->table->tb_num_default > 1 && - res->type == RTN_UNICAST && oif_check) + res->type == RTN_UNICAST) fib_select_default(fl4, res); +check_saddr: if (!fl4->saddr) fl4->saddr = FIB_RES_PREFSRC(net, *res); } -EXPORT_SYMBOL_GPL(fib_select_path); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5530cd6..3dcffd3 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -50,6 +50,7 @@ #define VERSION "0.409" +#include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> @@ -191,8 +192,8 @@ static size_t tnode_free_size; */ static const int sync_pages = 128; -static struct kmem_cache *fn_alias_kmem __read_mostly; -static struct kmem_cache *trie_leaf_kmem __read_mostly; +static struct kmem_cache *fn_alias_kmem __ro_after_init; +static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { @@ -1064,6 +1065,9 @@ noleaf: return -ENOMEM; } +/* fib notifier for ADD is sent before calling fib_insert_alias with + * the expectation that the only possible failure ENOMEM + */ static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) @@ -1215,8 +1219,13 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, - key, plen, new_fa, extack); + err = call_fib_entry_notifiers(net, + FIB_EVENT_ENTRY_REPLACE, + key, plen, new_fa, + extack); + if (err) + goto out_free_new_fa; + rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); @@ -1262,21 +1271,32 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; + err = call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); + if (err) + goto out_free_new_fa; + /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) - goto out_free_new_fa; + goto out_fib_notif; if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); - call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; +out_fib_notif: + /* notifier was sent that entry would be added to trie, but + * the add failed and need to recover. Only failure for + * fib_insert_alias is ENOMEM. + */ + NL_SET_ERR_MSG(extack, "Failed to insert route into trie"); + call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, + plen, new_fa, NULL); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -2721,14 +2741,14 @@ static const struct file_operations fib_route_fops = { int __net_init fib_proc_init(struct net *net) { - if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops)) + if (!proc_create("fib_trie", 0444, net->proc_net, &fib_trie_fops)) goto out1; - if (!proc_create("fib_triestat", S_IRUGO, net->proc_net, + if (!proc_create("fib_triestat", 0444, net->proc_net, &fib_triestat_fops)) goto out2; - if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops)) + if (!proc_create("route", 0444, net->proc_net, &fib_route_fops)) goto out3; return 0; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index f240258..b26a81a 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2993,10 +2993,10 @@ static int __net_init igmp_net_init(struct net *net) struct proc_dir_entry *pde; int err; - pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops); + pde = proc_create("igmp", 0444, net->proc_net, &igmp_mc_seq_fops); if (!pde) goto out_igmp; - pde = proc_create("mcfilter", S_IRUGO, net->proc_net, + pde = proc_create("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_fops); if (!pde) goto out_mcfilter; diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index e8ec289..c9e35b8 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,12 +25,6 @@ #include <net/inet_frag.h> #include <net/inet_ecn.h> -#define INETFRAGS_EVICT_BUCKETS 128 -#define INETFRAGS_EVICT_MAX 512 - -/* don't rebuild inetfrag table with new secret more often than this */ -#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ) - /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. * 0 or INET_ECN_CE value, to be ORed in to final iph->tos field @@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = { }; EXPORT_SYMBOL(ip_frag_ecn_table); -static unsigned int -inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q) -{ - return f->hashfn(q) & (INETFRAGS_HASHSZ - 1); -} - -static bool inet_frag_may_rebuild(struct inet_frags *f) -{ - return time_after(jiffies, - f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL); -} - -static void inet_frag_secret_rebuild(struct inet_frags *f) -{ - int i; - - write_seqlock_bh(&f->rnd_seqlock); - - if (!inet_frag_may_rebuild(f)) - goto out; - - get_random_bytes(&f->rnd, sizeof(u32)); - - for (i = 0; i < INETFRAGS_HASHSZ; i++) { - struct inet_frag_bucket *hb; - struct inet_frag_queue *q; - struct hlist_node *n; - - hb = &f->hash[i]; - spin_lock(&hb->chain_lock); - - hlist_for_each_entry_safe(q, n, &hb->chain, list) { - unsigned int hval = inet_frag_hashfn(f, q); - - if (hval != i) { - struct inet_frag_bucket *hb_dest; - - hlist_del(&q->list); - - /* Relink to new hash chain. */ - hb_dest = &f->hash[hval]; - - /* This is the only place where we take - * another chain_lock while already holding - * one. As this will not run concurrently, - * we cannot deadlock on hb_dest lock below, if its - * already locked it will be released soon since - * other caller cannot be waiting for hb lock - * that we've taken above. - */ - spin_lock_nested(&hb_dest->chain_lock, - SINGLE_DEPTH_NESTING); - hlist_add_head(&q->list, &hb_dest->chain); - spin_unlock(&hb_dest->chain_lock); - } - } - spin_unlock(&hb->chain_lock); - } - - f->rebuild = false; - f->last_rebuild_jiffies = jiffies; -out: - write_sequnlock_bh(&f->rnd_seqlock); -} - -static bool inet_fragq_should_evict(const struct inet_frag_queue *q) -{ - if (!hlist_unhashed(&q->list_evictor)) - return false; - - return q->net->low_thresh == 0 || - frag_mem_limit(q->net) >= q->net->low_thresh; -} - -static unsigned int -inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb) -{ - struct inet_frag_queue *fq; - struct hlist_node *n; - unsigned int evicted = 0; - HLIST_HEAD(expired); - - spin_lock(&hb->chain_lock); - - hlist_for_each_entry_safe(fq, n, &hb->chain, list) { - if (!inet_fragq_should_evict(fq)) - continue; - - if (!del_timer(&fq->timer)) - continue; - - hlist_add_head(&fq->list_evictor, &expired); - ++evicted; - } - - spin_unlock(&hb->chain_lock); - - hlist_for_each_entry_safe(fq, n, &expired, list_evictor) - f->frag_expire(&fq->timer); - - return evicted; -} - -static void inet_frag_worker(struct work_struct *work) -{ - unsigned int budget = INETFRAGS_EVICT_BUCKETS; - unsigned int i, evicted = 0; - struct inet_frags *f; - - f = container_of(work, struct inet_frags, frags_work); - - BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ); - - local_bh_disable(); - - for (i = READ_ONCE(f->next_bucket); budget; --budget) { - evicted += inet_evict_bucket(f, &f->hash[i]); - i = (i + 1) & (INETFRAGS_HASHSZ - 1); - if (evicted > INETFRAGS_EVICT_MAX) - break; - } - - f->next_bucket = i; - - local_bh_enable(); - - if (f->rebuild && inet_frag_may_rebuild(f)) - inet_frag_secret_rebuild(f); -} - -static void inet_frag_schedule_worker(struct inet_frags *f) -{ - if (unlikely(!work_pending(&f->frags_work))) - schedule_work(&f->frags_work); -} - int inet_frags_init(struct inet_frags *f) { - int i; - - INIT_WORK(&f->frags_work, inet_frag_worker); - - for (i = 0; i < INETFRAGS_HASHSZ; i++) { - struct inet_frag_bucket *hb = &f->hash[i]; - - spin_lock_init(&hb->chain_lock); - INIT_HLIST_HEAD(&hb->chain); - } - - seqlock_init(&f->rnd_seqlock); - f->last_rebuild_jiffies = 0; f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0, NULL); if (!f->frags_cachep) @@ -214,83 +59,75 @@ EXPORT_SYMBOL(inet_frags_init); void inet_frags_fini(struct inet_frags *f) { - cancel_work_sync(&f->frags_work); + /* We must wait that all inet_frag_destroy_rcu() have completed. */ + rcu_barrier(); + kmem_cache_destroy(f->frags_cachep); + f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini); -void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) +static void inet_frags_free_cb(void *ptr, void *arg) { - unsigned int seq; - int i; - - nf->low_thresh = 0; + struct inet_frag_queue *fq = ptr; -evict_again: - local_bh_disable(); - seq = read_seqbegin(&f->rnd_seqlock); - - for (i = 0; i < INETFRAGS_HASHSZ ; i++) - inet_evict_bucket(f, &f->hash[i]); - - local_bh_enable(); - cond_resched(); - - if (read_seqretry(&f->rnd_seqlock, seq) || - sum_frag_mem_limit(nf)) - goto evict_again; -} -EXPORT_SYMBOL(inet_frags_exit_net); - -static struct inet_frag_bucket * -get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f) -__acquires(hb->chain_lock) -{ - struct inet_frag_bucket *hb; - unsigned int seq, hash; - - restart: - seq = read_seqbegin(&f->rnd_seqlock); - - hash = inet_frag_hashfn(f, fq); - hb = &f->hash[hash]; + /* If we can not cancel the timer, it means this frag_queue + * is already disappearing, we have nothing to do. + * Otherwise, we own a refcount until the end of this function. + */ + if (!del_timer(&fq->timer)) + return; - spin_lock(&hb->chain_lock); - if (read_seqretry(&f->rnd_seqlock, seq)) { - spin_unlock(&hb->chain_lock); - goto restart; + spin_lock_bh(&fq->lock); + if (!(fq->flags & INET_FRAG_COMPLETE)) { + fq->flags |= INET_FRAG_COMPLETE; + refcount_dec(&fq->refcnt); } + spin_unlock_bh(&fq->lock); - return hb; + inet_frag_put(fq); } -static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f) +void inet_frags_exit_net(struct netns_frags *nf) { - struct inet_frag_bucket *hb; + nf->low_thresh = 0; /* prevent creation of new frags */ - hb = get_frag_bucket_locked(fq, f); - hlist_del(&fq->list); - fq->flags |= INET_FRAG_COMPLETE; - spin_unlock(&hb->chain_lock); + rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); } +EXPORT_SYMBOL(inet_frags_exit_net); -void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f) +void inet_frag_kill(struct inet_frag_queue *fq) { if (del_timer(&fq->timer)) refcount_dec(&fq->refcnt); if (!(fq->flags & INET_FRAG_COMPLETE)) { - fq_unlink(fq, f); + struct netns_frags *nf = fq->net; + + fq->flags |= INET_FRAG_COMPLETE; + rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params); refcount_dec(&fq->refcnt); } } EXPORT_SYMBOL(inet_frag_kill); -void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) +static void inet_frag_destroy_rcu(struct rcu_head *head) +{ + struct inet_frag_queue *q = container_of(head, struct inet_frag_queue, + rcu); + struct inet_frags *f = q->net->f; + + if (f->destructor) + f->destructor(q); + kmem_cache_free(f->frags_cachep, q); +} + +void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; struct netns_frags *nf; unsigned int sum, sum_truesize = 0; + struct inet_frags *f; WARN_ON(!(q->flags & INET_FRAG_COMPLETE)); WARN_ON(del_timer(&q->timer) != 0); @@ -298,6 +135,7 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) /* Release all fragment data. */ fp = q->fragments; nf = q->net; + f = nf->f; while (fp) { struct sk_buff *xp = fp->next; @@ -307,59 +145,20 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f) } sum = sum_truesize + f->qsize; - if (f->destructor) - f->destructor(q); - kmem_cache_free(f->frags_cachep, q); + call_rcu(&q->rcu, inet_frag_destroy_rcu); sub_frag_mem_limit(nf, sum); } EXPORT_SYMBOL(inet_frag_destroy); -static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, - struct inet_frag_queue *qp_in, - struct inet_frags *f, - void *arg) -{ - struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f); - struct inet_frag_queue *qp; - -#ifdef CONFIG_SMP - /* With SMP race we have to recheck hash table, because - * such entry could have been created on other cpu before - * we acquired hash bucket lock. - */ - hlist_for_each_entry(qp, &hb->chain, list) { - if (qp->net == nf && f->match(qp, arg)) { - refcount_inc(&qp->refcnt); - spin_unlock(&hb->chain_lock); - qp_in->flags |= INET_FRAG_COMPLETE; - inet_frag_put(qp_in, f); - return qp; - } - } -#endif - qp = qp_in; - if (!mod_timer(&qp->timer, jiffies + nf->timeout)) - refcount_inc(&qp->refcnt); - - refcount_inc(&qp->refcnt); - hlist_add_head(&qp->list, &hb->chain); - - spin_unlock(&hb->chain_lock); - - return qp; -} - static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, struct inet_frags *f, void *arg) { struct inet_frag_queue *q; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) { - inet_frag_schedule_worker(f); + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; - } q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) @@ -371,70 +170,51 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, timer_setup(&q->timer, f->frag_expire, 0); spin_lock_init(&q->lock); - refcount_set(&q->refcnt, 1); + refcount_set(&q->refcnt, 3); return q; } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - struct inet_frags *f, void *arg) { + struct inet_frags *f = nf->f; struct inet_frag_queue *q; + int err; q = inet_frag_alloc(nf, f, arg); if (!q) return NULL; - return inet_frag_intern(nf, q, f, arg); + mod_timer(&q->timer, jiffies + nf->timeout); + + err = rhashtable_insert_fast(&nf->rhashtable, &q->node, + f->rhash_params); + if (err < 0) { + q->flags |= INET_FRAG_COMPLETE; + inet_frag_kill(q); + inet_frag_destroy(q); + return NULL; + } + return q; } -struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, - struct inet_frags *f, void *key, - unsigned int hash) +/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ +struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_bucket *hb; - struct inet_frag_queue *q; - int depth = 0; - - if (frag_mem_limit(nf) > nf->low_thresh) - inet_frag_schedule_worker(f); - - hash &= (INETFRAGS_HASHSZ - 1); - hb = &f->hash[hash]; - - spin_lock(&hb->chain_lock); - hlist_for_each_entry(q, &hb->chain, list) { - if (q->net == nf && f->match(q, key)) { - refcount_inc(&q->refcnt); - spin_unlock(&hb->chain_lock); - return q; - } - depth++; - } - spin_unlock(&hb->chain_lock); + struct inet_frag_queue *fq; - if (depth <= INETFRAGS_MAXDEPTH) - return inet_frag_create(nf, f, key); + rcu_read_lock(); - if (inet_frag_may_rebuild(f)) { - if (!f->rebuild) - f->rebuild = true; - inet_frag_schedule_worker(f); + fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (fq) { + if (!refcount_inc_not_zero(&fq->refcnt)) + fq = NULL; + rcu_read_unlock(); + return fq; } + rcu_read_unlock(); - return ERR_PTR(-ENOBUFS); + return inet_frag_create(nf, key); } EXPORT_SYMBOL(inet_frag_find); - -void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, - const char *prefix) -{ - static const char msg[] = "inet_frag_find: Fragment hash bucket" - " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) - ". Dropping fragment.\n"; - - if (PTR_ERR(q) == -ENOBUFS) - net_dbg_ratelimited("%s%s", prefix, msg); -} -EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 914d569..1f04bd9 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -6,6 +6,7 @@ * Authors: Andrey V. Savochkin <saw@msu.ru> */ +#include <linux/cache.h> #include <linux/module.h> #include <linux/types.h> #include <linux/slab.h> @@ -51,7 +52,7 @@ * daddr: unchangeable */ -static struct kmem_cache *peer_cachep __read_mostly; +static struct kmem_cache *peer_cachep __ro_after_init; void inet_peer_base_init(struct inet_peer_base *bp) { diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index bbf1b94..994fa70 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,27 +57,13 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; -struct ipfrag_skb_cb -{ - struct inet_skb_parm h; - int offset; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; - u32 user; - __be32 saddr; - __be32 daddr; - __be16 id; - u8 protocol; u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; - int vif; /* L3 master device index */ unsigned int rid; struct inet_peer *peer; }; @@ -89,49 +75,9 @@ static u8 ip4_frag_ecn(u8 tos) static struct inet_frags ip4_frags; -int ip_frag_mem(struct net *net) -{ - return sum_frag_mem_limit(&net->ipv4.frags); -} - static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct net_device *dev); -struct ip4_create_arg { - struct iphdr *iph; - u32 user; - int vif; -}; - -static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) -{ - net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd)); - return jhash_3words((__force u32)id << 16 | prot, - (__force u32)saddr, (__force u32)daddr, - ip4_frags.rnd); -} - -static unsigned int ip4_hashfn(const struct inet_frag_queue *q) -{ - const struct ipq *ipq; - - ipq = container_of(q, struct ipq, q); - return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); -} - -static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) -{ - const struct ipq *qp; - const struct ip4_create_arg *arg = a; - - qp = container_of(q, struct ipq, q); - return qp->id == arg->iph->id && - qp->saddr == arg->iph->saddr && - qp->daddr == arg->iph->daddr && - qp->protocol == arg->iph->protocol && - qp->user == arg->user && - qp->vif == arg->vif; -} static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { @@ -140,17 +86,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a) frags); struct net *net = container_of(ipv4, struct net, ipv4); - const struct ip4_create_arg *arg = a; + const struct frag_v4_compare_key *key = a; - qp->protocol = arg->iph->protocol; - qp->id = arg->iph->id; - qp->ecn = ip4_frag_ecn(arg->iph->tos); - qp->saddr = arg->iph->saddr; - qp->daddr = arg->iph->daddr; - qp->vif = arg->vif; - qp->user = arg->user; + q->key.v4 = *key; + qp->ecn = 0; qp->peer = q->net->max_dist ? - inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) : + inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : NULL; } @@ -168,7 +109,7 @@ static void ip4_frag_free(struct inet_frag_queue *q) static void ipq_put(struct ipq *ipq) { - inet_frag_put(&ipq->q, &ip4_frags); + inet_frag_put(&ipq->q); } /* Kill ipq entry. It is not destroyed immediately, @@ -176,7 +117,7 @@ static void ipq_put(struct ipq *ipq) */ static void ipq_kill(struct ipq *ipq) { - inet_frag_kill(&ipq->q, &ip4_frags); + inet_frag_kill(&ipq->q); } static bool frag_expire_skip_icmp(u32 user) @@ -194,8 +135,11 @@ static bool frag_expire_skip_icmp(u32 user) static void ip_expire(struct timer_list *t) { struct inet_frag_queue *frag = from_timer(frag, t, timer); - struct ipq *qp; + const struct iphdr *iph; + struct sk_buff *head; struct net *net; + struct ipq *qp; + int err; qp = container_of(frag, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); @@ -209,46 +153,38 @@ static void ip_expire(struct timer_list *t) ipq_kill(qp); __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); - if (!inet_frag_evicting(&qp->q)) { - struct sk_buff *clone, *head = qp->q.fragments; - const struct iphdr *iph; - int err; + head = qp->q.fragments; - __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); + __IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT); - if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments) - goto out; + if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head) + goto out; - head->dev = dev_get_by_index_rcu(net, qp->iif); - if (!head->dev) - goto out; + head->dev = dev_get_by_index_rcu(net, qp->iif); + if (!head->dev) + goto out; - /* skb has no dst, perform route lookup again */ - iph = ip_hdr(head); - err = ip_route_input_noref(head, iph->daddr, iph->saddr, + /* skb has no dst, perform route lookup again */ + iph = ip_hdr(head); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); - if (err) - goto out; + if (err) + goto out; + + /* Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. + */ + if (frag_expire_skip_icmp(qp->q.key.v4.user) && + (skb_rtable(head)->rt_type != RTN_LOCAL)) + goto out; + + skb_get(head); + spin_unlock(&qp->q.lock); + icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); + kfree_skb(head); + goto out_rcu_unlock; - /* Only an end host needs to send an ICMP - * "Fragment Reassembly Timeout" message, per RFC792. - */ - if (frag_expire_skip_icmp(qp->user) && - (skb_rtable(head)->rt_type != RTN_LOCAL)) - goto out; - - clone = skb_clone(head, GFP_ATOMIC); - - /* Send an ICMP "Fragment Reassembly Timeout" message. */ - if (clone) { - spin_unlock(&qp->q.lock); - icmp_send(clone, ICMP_TIME_EXCEEDED, - ICMP_EXC_FRAGTIME, 0); - consume_skb(clone); - goto out_rcu_unlock; - } - } out: spin_unlock(&qp->q.lock); out_rcu_unlock: @@ -262,21 +198,20 @@ out_rcu_unlock: static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user, int vif) { + struct frag_v4_compare_key key = { + .saddr = iph->saddr, + .daddr = iph->daddr, + .user = user, + .vif = vif, + .id = iph->id, + .protocol = iph->protocol, + }; struct inet_frag_queue *q; - struct ip4_create_arg arg; - unsigned int hash; - - arg.iph = iph; - arg.user = user; - arg.vif = vif; - hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); - - q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); - if (IS_ERR_OR_NULL(q)) { - inet_frag_maybe_warn_overflow(q, pr_fmt()); + q = inet_frag_find(&net->ipv4.frags, &key); + if (!q) return NULL; - } + return container_of(q, struct ipq, q); } @@ -410,13 +345,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * this fragment, right? */ prev = qp->q.fragments_tail; - if (!prev || FRAG_CB(prev)->offset < offset) { + if (!prev || prev->ip_defrag_offset < offset) { next = NULL; goto found; } prev = NULL; for (next = qp->q.fragments; next != NULL; next = next->next) { - if (FRAG_CB(next)->offset >= offset) + if (next->ip_defrag_offset >= offset) break; /* bingo! */ prev = next; } @@ -427,7 +362,7 @@ found: * any overlaps are eliminated. */ if (prev) { - int i = (FRAG_CB(prev)->offset + prev->len) - offset; + int i = (prev->ip_defrag_offset + prev->len) - offset; if (i > 0) { offset += i; @@ -444,8 +379,8 @@ found: err = -ENOMEM; - while (next && FRAG_CB(next)->offset < end) { - int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */ + while (next && next->ip_defrag_offset < end) { + int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ if (i < next->len) { /* Eat head of the next overlapped fragment @@ -453,7 +388,7 @@ found: */ if (!pskb_pull(next, i)) goto err; - FRAG_CB(next)->offset += i; + next->ip_defrag_offset += i; qp->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) next->ip_summed = CHECKSUM_NONE; @@ -477,7 +412,13 @@ found: } } - FRAG_CB(skb)->offset = offset; + /* Note : skb->ip_defrag_offset and skb->dev share the same location */ + dev = skb->dev; + if (dev) + qp->iif = dev->ifindex; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); + skb->ip_defrag_offset = offset; /* Insert this fragment in the chain of fragments. */ skb->next = next; @@ -488,11 +429,6 @@ found: else qp->q.fragments = skb; - dev = skb->dev; - if (dev) { - qp->iif = dev->ifindex; - skb->dev = NULL; - } qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; @@ -568,7 +504,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, } WARN_ON(!head); - WARN_ON(FRAG_CB(head)->offset != 0); + WARN_ON(head->ip_defrag_offset != 0); /* Allocate a new buffer for the datagram. */ ihlen = ip_hdrlen(head); @@ -656,7 +592,7 @@ out_nomem: err = -ENOMEM; goto out_fail; out_oversize: - net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr); + net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr); out_fail: __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); return err; @@ -731,23 +667,23 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) EXPORT_SYMBOL(ip_check_defrag); #ifdef CONFIG_SYSCTL -static int zero; +static long zero; static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .data = &init_net.ipv4.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ipv4.frags.low_thresh }, { .procname = "ipfrag_low_thresh", .data = &init_net.ipv4.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.ipv4.frags.high_thresh }, @@ -846,6 +782,8 @@ static void __init ip4_frags_ctl_register(void) static int __net_init ipv4_frags_init_net(struct net *net) { + int res; + /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for @@ -870,16 +808,21 @@ static int __net_init ipv4_frags_init_net(struct net *net) net->ipv4.frags.timeout = IP_FRAG_TIME; net->ipv4.frags.max_dist = 64; - - inet_frags_init_net(&net->ipv4.frags); - - return ip4_frags_ns_ctl_register(net); + net->ipv4.frags.f = &ip4_frags; + + res = inet_frags_init_net(&net->ipv4.frags); + if (res < 0) + return res; + res = ip4_frags_ns_ctl_register(net); + if (res < 0) + inet_frags_exit_net(&net->ipv4.frags); + return res; } static void __net_exit ipv4_frags_exit_net(struct net *net) { ip4_frags_ns_ctl_unregister(net); - inet_frags_exit_net(&net->ipv4.frags, &ip4_frags); + inet_frags_exit_net(&net->ipv4.frags); } static struct pernet_operations ip4_frags_ops = { @@ -887,17 +830,49 @@ static struct pernet_operations ip4_frags_ops = { .exit = ipv4_frags_exit_net, }; + +static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); +} + +static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key.v4, + sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); +} + +static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_v4_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static const struct rhashtable_params ip4_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .key_offset = offsetof(struct inet_frag_queue, key), + .key_len = sizeof(struct frag_v4_compare_key), + .hashfn = ip4_key_hashfn, + .obj_hashfn = ip4_obj_hashfn, + .obj_cmpfn = ip4_obj_cmpfn, + .automatic_shrinking = true, +}; + void __init ipfrag_init(void) { - ip4_frags_ctl_register(); - register_pernet_subsys(&ip4_frags_ops); - ip4_frags.hashfn = ip4_hashfn; ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.qsize = sizeof(struct ipq); - ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; ip4_frags.frags_cache_name = ip_frag_cache_name; + ip4_frags.rhash_params = ip4_rhash_params; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); + ip4_frags_ctl_register(); + register_pernet_subsys(&ip4_frags_ops); } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0901de4..a8772a9 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -522,6 +522,7 @@ err_free_skb: static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { + struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct rtable *rt = NULL; @@ -545,9 +546,11 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) goto err_free_rt; - flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + flags = tun_info->key.tun_flags & + (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, - tunnel_id_to_key32(tun_info->key.tun_id), 0); + tunnel_id_to_key32(tun_info->key.tun_id), + (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -1317,6 +1320,12 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } +bool is_gretap_dev(const struct net_device *dev) +{ + return dev->netdev_ops == &gre_tap_netdev_ops; +} +EXPORT_SYMBOL_GPL(is_gretap_dev); + static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 57fc13c..7582713 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -159,7 +159,7 @@ bool ip_call_ra_chain(struct sk_buff *skb) struct net_device *dev = skb->dev; struct net *net = dev_net(dev); - for (ra = rcu_dereference(ip_ra_chain); ra; ra = rcu_dereference(ra->next)) { + for (ra = rcu_dereference(net->ipv4.ra_chain); ra; ra = rcu_dereference(ra->next)) { struct sock *sk = ra->sk; /* If socket is bound to an interface, only report @@ -167,8 +167,7 @@ bool ip_call_ra_chain(struct sk_buff *skb) */ if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || - sk->sk_bound_dev_if == dev->ifindex) && - net_eq(sock_net(sk), net)) { + sk->sk_bound_dev_if == dev->ifindex)) { if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(net, skb, IP_DEFRAG_CALL_RA_CHAIN)) return true; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 66340ab..94cacae 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -876,6 +876,7 @@ static int __ip_append_data(struct sock *sk, unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; + unsigned int wmem_alloc_delta = 0; u32 tskey = 0; skb = skb_peek_tail(queue); @@ -971,11 +972,10 @@ alloc_new_skb: (flags & MSG_DONTWAIT), &err); } else { skb = NULL; - if (refcount_read(&sk->sk_wmem_alloc) <= + if (refcount_read(&sk->sk_wmem_alloc) + wmem_alloc_delta <= 2 * sk->sk_sndbuf) - skb = sock_wmalloc(sk, - alloclen + hh_len + 15, 1, - sk->sk_allocation); + skb = alloc_skb(alloclen + hh_len + 15, + sk->sk_allocation); if (unlikely(!skb)) err = -ENOBUFS; } @@ -1033,6 +1033,11 @@ alloc_new_skb: /* * Put the packet on the pending queue. */ + if (!skb->destructor) { + skb->destructor = sock_wfree; + skb->sk = sk; + wmem_alloc_delta += skb->truesize; + } __skb_queue_tail(queue, skb); continue; } @@ -1079,12 +1084,13 @@ alloc_new_skb: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - refcount_add(copy, &sk->sk_wmem_alloc); + wmem_alloc_delta += copy; } offset += copy; length -= copy; } + refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return 0; error_efault: @@ -1092,6 +1098,7 @@ error_efault: error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); + refcount_add(wmem_alloc_delta, &sk->sk_wmem_alloc); return err; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 74c962b..5ad2d8e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -322,20 +322,6 @@ int ip_cmsg_send(struct sock *sk, struct msghdr *msg, struct ipcm_cookie *ipc, return 0; } - -/* Special input handler for packets caught by router alert option. - They are selected only by protocol field, and then processed likely - local ones; but only if someone wants them! Otherwise, router - not running rsvpd will kill RSVP. - - It is user level problem, what it will make with them. - I have no idea, how it will masquearde or NAT them (it is joke, joke :-)), - but receiver should be enough clever f.e. to forward mtrace requests, - sent to multicast group to reach destination designated router. - */ -struct ip_ra_chain __rcu *ip_ra_chain; - - static void ip_ra_destroy_rcu(struct rcu_head *head) { struct ip_ra_chain *ra = container_of(head, struct ip_ra_chain, rcu); @@ -349,23 +335,28 @@ int ip_ra_control(struct sock *sk, unsigned char on, { struct ip_ra_chain *ra, *new_ra; struct ip_ra_chain __rcu **rap; + struct net *net = sock_net(sk); if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; - for (rap = &ip_ra_chain; - (ra = rtnl_dereference(*rap)) != NULL; + mutex_lock(&net->ipv4.ra_mutex); + for (rap = &net->ipv4.ra_chain; + (ra = rcu_dereference_protected(*rap, + lockdep_is_held(&net->ipv4.ra_mutex))) != NULL; rap = &ra->next) { if (ra->sk == sk) { if (on) { + mutex_unlock(&net->ipv4.ra_mutex); kfree(new_ra); return -EADDRINUSE; } /* dont let ip_call_ra_chain() use sk again */ ra->sk = NULL; RCU_INIT_POINTER(*rap, ra->next); + mutex_unlock(&net->ipv4.ra_mutex); if (ra->destructor) ra->destructor(sk); @@ -379,14 +370,17 @@ int ip_ra_control(struct sock *sk, unsigned char on, return 0; } } - if (!new_ra) + if (!new_ra) { + mutex_unlock(&net->ipv4.ra_mutex); return -ENOBUFS; + } new_ra->sk = sk; new_ra->destructor = destructor; RCU_INIT_POINTER(new_ra->next, ra); rcu_assign_pointer(*rap, new_ra); sock_hold(sk); + mutex_unlock(&net->ipv4.ra_mutex); return 0; } @@ -586,7 +580,6 @@ static bool setsockopt_needs_rtnl(int optname) case MCAST_LEAVE_GROUP: case MCAST_LEAVE_SOURCE_GROUP: case MCAST_UNBLOCK_SOURCE: - case IP_ROUTER_ALERT: return true; } return false; @@ -639,6 +632,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, /* If optlen==0, it is equivalent to val == 0 */ + if (optname == IP_ROUTER_ALERT) + return ip_ra_control(sk, val ? 1 : 0, NULL); if (ip_mroute_opt(optname)) return ip_mroute_setsockopt(sk, optname, optval, optlen); @@ -1149,9 +1144,6 @@ mc_msf_out: goto e_inval; inet->mc_all = val; break; - case IP_ROUTER_ALERT: - err = ip_ra_control(sk, val ? 1 : 0, NULL); - break; case IP_FREEBIND: if (optlen < 1) diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index a7fd1c5..de6d944 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -290,22 +290,6 @@ failed: return ERR_PTR(err); } -static inline void init_tunnel_flow(struct flowi4 *fl4, - int proto, - __be32 daddr, __be32 saddr, - __be32 key, __u8 tos, int oif, - __u32 mark) -{ - memset(fl4, 0, sizeof(*fl4)); - fl4->flowi4_oif = oif; - fl4->daddr = daddr; - fl4->saddr = saddr; - fl4->flowi4_tos = tos; - fl4->flowi4_proto = proto; - fl4->fl4_gre_key = key; - fl4->flowi4_mark = mark; -} - static int ip_tunnel_bind_dev(struct net_device *dev) { struct net_device *tdev = NULL; @@ -322,10 +306,10 @@ static int ip_tunnel_bind_dev(struct net_device *dev) struct flowi4 fl4; struct rtable *rt; - init_tunnel_flow(&fl4, iph->protocol, iph->daddr, - iph->saddr, tunnel->parms.o_key, - RT_TOS(iph->tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, iph->protocol, iph->daddr, + iph->saddr, tunnel->parms.o_key, + RT_TOS(iph->tos), tunnel->parms.link, + tunnel->fwmark); rt = ip_route_output_key(tunnel->net, &fl4); if (!IS_ERR(rt)) { @@ -365,8 +349,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, int mtu; int err; - BUG_ON(!itn->fb_tunnel_dev); - dev = __ip_tunnel_create(net, itn->fb_tunnel_dev->rtnl_link_ops, parms); + dev = __ip_tunnel_create(net, itn->rtnl_link_ops, parms); if (IS_ERR(dev)) return ERR_CAST(dev); @@ -590,8 +573,8 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } - init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, - RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); + ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, + RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; rt = ip_route_output_key(tunnel->net, &fl4); @@ -719,9 +702,9 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } } - init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr, - tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, - tunnel->fwmark); + ip_tunnel_init_flow(&fl4, protocol, dst, tnl_params->saddr, + tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link, + tunnel->fwmark); if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0) goto tx_error; @@ -847,7 +830,6 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) struct net *net = t->net; struct ip_tunnel_net *itn = net_generic(net, t->ip_tnl_net_id); - BUG_ON(!itn->fb_tunnel_dev); switch (cmd) { case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { @@ -872,7 +854,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) p->o_key = 0; } - t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); + t = ip_tunnel_find(itn, p, itn->type); if (cmd == SIOCADDTUNNEL) { if (!t) { @@ -1016,10 +998,15 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, struct ip_tunnel_parm parms; unsigned int i; + itn->rtnl_link_ops = ops; for (i = 0; i < IP_TNL_HASH_SIZE; i++) INIT_HLIST_HEAD(&itn->tunnels[i]); - if (!ops) { + if (!ops || !net_has_fallback_tunnels(net)) { + struct ip_tunnel_net *it_init_net; + + it_init_net = net_generic(&init_net, ip_tnl_net_id); + itn->type = it_init_net->type; itn->fb_tunnel_dev = NULL; return 0; } @@ -1037,6 +1024,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev); ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev)); + itn->type = itn->fb_tunnel_dev->type; } rtnl_unlock(); @@ -1044,10 +1032,10 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id, } EXPORT_SYMBOL_GPL(ip_tunnel_init_net); -static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head, +static void ip_tunnel_destroy(struct net *net, struct ip_tunnel_net *itn, + struct list_head *head, struct rtnl_link_ops *ops) { - struct net *net = dev_net(itn->fb_tunnel_dev); struct net_device *dev, *aux; int h; @@ -1079,7 +1067,7 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id, rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { itn = net_generic(net, id); - ip_tunnel_destroy(itn, &list, ops); + ip_tunnel_destroy(net, itn, &list, ops); } unregister_netdevice_many(&list); rtnl_unlock(); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index f75802a..43f620f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1369,7 +1369,7 @@ static int __init ip_auto_config(void) unsigned int i; #ifdef CONFIG_PROC_FS - proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops); + proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index b05689b..2fb4de3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -28,9 +28,9 @@ #include <linux/uaccess.h> #include <linux/types.h> +#include <linux/cache.h> #include <linux/capability.h> #include <linux/errno.h> -#include <linux/timer.h> #include <linux/mm.h> #include <linux/kernel.h> #include <linux/fcntl.h> @@ -52,7 +52,6 @@ #include <net/protocol.h> #include <linux/skbuff.h> #include <net/route.h> -#include <net/sock.h> #include <net/icmp.h> #include <net/udp.h> #include <net/raw.h> @@ -96,7 +95,7 @@ static DEFINE_SPINLOCK(mfc_unres_lock); * In this case data path is free of exclusive locks at all. */ -static struct kmem_cache *mrt_cachep __read_mostly; +static struct kmem_cache *mrt_cachep __ro_after_init; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); @@ -106,8 +105,6 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct mfc_cache *cache, int local); static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); -static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - struct mfc_cache *c, struct rtmsg *rtm); static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, int cmd); static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt); @@ -118,6 +115,23 @@ static void ipmr_expire_process(struct timer_list *t); #define ipmr_for_each_table(mrt, net) \ list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +static struct mr_table *ipmr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + struct mr_table *ret; + + if (!mrt) + ret = list_entry_rcu(net->ipv4.mr_tables.next, + struct mr_table, list); + else + ret = list_entry_rcu(mrt->list.next, + struct mr_table, list); + + if (&ret->list == &net->ipv4.mr_tables) + return NULL; + return ret; +} + static struct mr_table *ipmr_get_table(struct net *net, u32 id) { struct mr_table *mrt; @@ -285,6 +299,14 @@ EXPORT_SYMBOL(ipmr_rule_default); #define ipmr_for_each_table(mrt, net) \ for (mrt = net->ipv4.mrt; mrt; mrt = NULL) +static struct mr_table *ipmr_mr_table_iter(struct net *net, + struct mr_table *mrt) +{ + if (!mrt) + return net->ipv4.mrt; + return NULL; +} + static struct mr_table *ipmr_get_table(struct net *net, u32 id) { return net->ipv4.mrt; @@ -344,7 +366,7 @@ static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg, } static const struct rhashtable_params ipmr_rht_params = { - .head_offset = offsetof(struct mfc_cache, mnode), + .head_offset = offsetof(struct mr_mfc, mnode), .key_offset = offsetof(struct mfc_cache, cmparg), .key_len = sizeof(struct mfc_cache_cmp_arg), .nelem_hint = 3, @@ -353,6 +375,24 @@ static const struct rhashtable_params ipmr_rht_params = { .automatic_shrinking = true, }; +static void ipmr_new_table_set(struct mr_table *mrt, + struct net *net) +{ +#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES + list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); +#endif +} + +static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = { + .mfc_mcastgrp = htonl(INADDR_ANY), + .mfc_origin = htonl(INADDR_ANY), +}; + +static struct mr_table_ops ipmr_mr_table_ops = { + .rht_params = &ipmr_rht_params, + .cmparg_any = &ipmr_mr_table_ops_cmparg_any, +}; + static struct mr_table *ipmr_new_table(struct net *net, u32 id) { struct mr_table *mrt; @@ -365,23 +405,8 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) if (mrt) return mrt; - mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (!mrt) - return ERR_PTR(-ENOMEM); - write_pnet(&mrt->net, net); - mrt->id = id; - - rhltable_init(&mrt->mfc_hash, &ipmr_rht_params); - INIT_LIST_HEAD(&mrt->mfc_cache_list); - INIT_LIST_HEAD(&mrt->mfc_unres_queue); - - timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0); - - mrt->mroute_reg_vif_num = -1; -#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES - list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables); -#endif - return mrt; + return mr_table_alloc(net, id, &ipmr_mr_table_ops, + ipmr_expire_process, ipmr_new_table_set); } static void ipmr_free_table(struct mr_table *mrt) @@ -619,80 +644,22 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) } #endif -static int call_ipmr_vif_entry_notifier(struct notifier_block *nb, - struct net *net, - enum fib_event_type event_type, - struct vif_device *vif, - vifi_t vif_index, u32 tb_id) -{ - struct vif_entry_notifier_info info = { - .info = { - .family = RTNL_FAMILY_IPMR, - .net = net, - }, - .dev = vif->dev, - .vif_index = vif_index, - .vif_flags = vif->flags, - .tb_id = tb_id, - }; - - return call_fib_notifier(nb, net, event_type, &info.info); -} - static int call_ipmr_vif_entry_notifiers(struct net *net, enum fib_event_type event_type, struct vif_device *vif, vifi_t vif_index, u32 tb_id) { - struct vif_entry_notifier_info info = { - .info = { - .family = RTNL_FAMILY_IPMR, - .net = net, - }, - .dev = vif->dev, - .vif_index = vif_index, - .vif_flags = vif->flags, - .tb_id = tb_id, - }; - - ASSERT_RTNL(); - net->ipv4.ipmr_seq++; - return call_fib_notifiers(net, event_type, &info.info); -} - -static int call_ipmr_mfc_entry_notifier(struct notifier_block *nb, - struct net *net, - enum fib_event_type event_type, - struct mfc_cache *mfc, u32 tb_id) -{ - struct mfc_entry_notifier_info info = { - .info = { - .family = RTNL_FAMILY_IPMR, - .net = net, - }, - .mfc = mfc, - .tb_id = tb_id - }; - - return call_fib_notifier(nb, net, event_type, &info.info); + return mr_call_vif_notifiers(net, RTNL_FAMILY_IPMR, event_type, + vif, vif_index, tb_id, + &net->ipv4.ipmr_seq); } static int call_ipmr_mfc_entry_notifiers(struct net *net, enum fib_event_type event_type, struct mfc_cache *mfc, u32 tb_id) { - struct mfc_entry_notifier_info info = { - .info = { - .family = RTNL_FAMILY_IPMR, - .net = net, - }, - .mfc = mfc, - .tb_id = tb_id - }; - - ASSERT_RTNL(); - net->ipv4.ipmr_seq++; - return call_fib_notifiers(net, event_type, &info.info); + return mr_call_mfc_notifiers(net, RTNL_FAMILY_IPMR, event_type, + &mfc->_c, tb_id, &net->ipv4.ipmr_seq); } /** @@ -760,16 +727,15 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, static void ipmr_cache_free_rcu(struct rcu_head *head) { - struct mfc_cache *c = container_of(head, struct mfc_cache, rcu); + struct mr_mfc *c = container_of(head, struct mr_mfc, rcu); - kmem_cache_free(mrt_cachep, c); + kmem_cache_free(mrt_cachep, (struct mfc_cache *)c); } -void ipmr_cache_free(struct mfc_cache *c) +static void ipmr_cache_free(struct mfc_cache *c) { - call_rcu(&c->rcu, ipmr_cache_free_rcu); + call_rcu(&c->_c.rcu, ipmr_cache_free_rcu); } -EXPORT_SYMBOL(ipmr_cache_free); /* Destroy an unresolved cache entry, killing queued skbs * and reporting error to netlink readers. @@ -782,7 +748,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) atomic_dec(&mrt->cache_resolve_queue_len); - while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { + while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); @@ -806,9 +772,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) static void ipmr_expire_process(struct timer_list *t) { struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer); - unsigned long now; + struct mr_mfc *c, *next; unsigned long expires; - struct mfc_cache *c, *next; + unsigned long now; if (!spin_trylock(&mfc_unres_lock)) { mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10); @@ -830,8 +796,8 @@ static void ipmr_expire_process(struct timer_list *t) } list_del(&c->list); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_destroy_unres(mrt, c); + mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE); + ipmr_destroy_unres(mrt, (struct mfc_cache *)c); } if (!list_empty(&mrt->mfc_unres_queue)) @@ -842,7 +808,7 @@ out: } /* Fill oifs list. It is called under write locked mrt_lock. */ -static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache, +static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, unsigned char *ttls) { int vifi; @@ -944,6 +910,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, ip_rt_multicast_event(in_dev); /* Fill in the VIF structures */ + vif_device_init(v, dev, vifc->vifc_rate_limit, + vifc->vifc_threshold, + vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), + (VIFF_TUNNEL | VIFF_REGISTER)); attr.orig_dev = dev; if (!switchdev_port_attr_get(dev, &attr)) { @@ -952,20 +922,9 @@ static int vif_add(struct net *net, struct mr_table *mrt, } else { v->dev_parent_id.id_len = 0; } - v->rate_limit = vifc->vifc_rate_limit; + v->local = vifc->vifc_lcl_addr.s_addr; v->remote = vifc->vifc_rmt_addr.s_addr; - v->flags = vifc->vifc_flags; - if (!mrtsock) - v->flags |= VIFF_STATIC; - v->threshold = vifc->vifc_threshold; - v->bytes_in = 0; - v->bytes_out = 0; - v->pkt_in = 0; - v->pkt_out = 0; - v->link = dev->ifindex; - if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER)) - v->link = dev_get_iflink(dev); /* And finish update writing critical data */ write_lock_bh(&mrt_lock); @@ -988,33 +947,8 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = origin }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - return c; - - return NULL; -} - -/* Look for a (*,*,oif) entry */ -static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt, - int vifi) -{ - struct mfc_cache_cmp_arg arg = { - .mfc_mcastgrp = htonl(INADDR_ANY), - .mfc_origin = htonl(INADDR_ANY) - }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - if (c->mfc_un.res.ttls[vifi] < 255) - return c; - return NULL; + return mr_mfc_find(mrt, &arg); } /* Look for a (*,G) entry */ @@ -1025,25 +959,10 @@ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = htonl(INADDR_ANY) }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c, *proxy; if (mcastgrp == htonl(INADDR_ANY)) - goto skip; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) { - if (c->mfc_un.res.ttls[vifi] < 255) - return c; - - /* It's ok if the vifi is part of the static tree */ - proxy = ipmr_cache_find_any_parent(mrt, c->mfc_parent); - if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) - return c; - } - -skip: - return ipmr_cache_find_any_parent(mrt, vifi); + return mr_mfc_find_any_parent(mrt, vifi); + return mr_mfc_find_any(mrt, vifi, &arg); } /* Look for a (S,G,iif) entry if parent != -1 */ @@ -1055,15 +974,8 @@ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt, .mfc_mcastgrp = mcastgrp, .mfc_origin = origin, }; - struct rhlist_head *tmp, *list; - struct mfc_cache *c; - - list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params); - rhl_for_each_entry_rcu(c, tmp, list, mnode) - if (parent == -1 || parent == c->mfc_parent) - return c; - return NULL; + return mr_mfc_find_parent(mrt, &arg, parent); } /* Allocate a multicast cache entry */ @@ -1072,9 +984,10 @@ static struct mfc_cache *ipmr_cache_alloc(void) struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); if (c) { - c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; - c->mfc_un.res.minvif = MAXVIFS; - refcount_set(&c->mfc_un.res.refcount, 1); + c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1; + c->_c.mfc_un.res.minvif = MAXVIFS; + c->_c.free = ipmr_cache_free_rcu; + refcount_set(&c->_c.mfc_un.res.refcount, 1); } return c; } @@ -1084,8 +997,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void) struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); if (c) { - skb_queue_head_init(&c->mfc_un.unres.unresolved); - c->mfc_un.unres.expires = jiffies + 10*HZ; + skb_queue_head_init(&c->_c.mfc_un.unres.unresolved); + c->_c.mfc_un.unres.expires = jiffies + 10 * HZ; } return c; } @@ -1098,12 +1011,13 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct nlmsgerr *e; /* Play the pending entries through our router */ - while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = skb_pull(skb, sizeof(struct iphdr)); - if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) { + if (mr_fill_mroute(mrt, skb, &c->_c, + nlmsg_data(nlh)) > 0) { nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh; } else { @@ -1211,7 +1125,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, int err; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(c, &mrt->mfc_unres_queue, list) { + list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) { if (c->mfc_mcastgrp == iph->daddr && c->mfc_origin == iph->saddr) { found = true; @@ -1230,12 +1144,13 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, } /* Fill in the new cache entry */ - c->mfc_parent = -1; + c->_c.mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; /* Reflect first query at mrouted. */ err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); + if (err < 0) { /* If the report failed throw the cache entry out - Brad Parker @@ -1248,15 +1163,16 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, } atomic_inc(&mrt->cache_resolve_queue_len); - list_add(&c->list, &mrt->mfc_unres_queue); + list_add(&c->_c.list, &mrt->mfc_unres_queue); mroute_netlink_event(mrt, c, RTM_NEWROUTE); if (atomic_read(&mrt->cache_resolve_queue_len) == 1) - mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); + mod_timer(&mrt->ipmr_expire_timer, + c->_c.mfc_un.unres.expires); } /* See if we can append the packet */ - if (c->mfc_un.unres.unresolved.qlen > 3) { + if (c->_c.mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { @@ -1264,7 +1180,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, skb->dev = dev; skb->skb_iif = dev->ifindex; } - skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb); err = 0; } @@ -1286,11 +1202,11 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent) rcu_read_unlock(); if (!c) return -ENOENT; - rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); - list_del_rcu(&c->list); + rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params); + list_del_rcu(&c->_c.list); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id); mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_put(c); + mr_cache_put(&c->_c); return 0; } @@ -1299,6 +1215,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, struct mfcctl *mfc, int mrtsock, int parent) { struct mfc_cache *uc, *c; + struct mr_mfc *_uc; bool found; int ret; @@ -1312,10 +1229,10 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, rcu_read_unlock(); if (c) { write_lock_bh(&mrt_lock); - c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); + c->_c.mfc_parent = mfc->mfcc_parent; + ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; write_unlock_bh(&mrt_lock); call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c, mrt->id); @@ -1333,28 +1250,29 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, c->mfc_origin = mfc->mfcc_origin.s_addr; c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; - c->mfc_parent = mfc->mfcc_parent; - ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls); + c->_c.mfc_parent = mfc->mfcc_parent; + ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls); if (!mrtsock) - c->mfc_flags |= MFC_STATIC; + c->_c.mfc_flags |= MFC_STATIC; - ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->mnode, + ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode, ipmr_rht_params); if (ret) { pr_err("ipmr: rhtable insert error %d\n", ret); ipmr_cache_free(c); return ret; } - list_add_tail_rcu(&c->list, &mrt->mfc_cache_list); + list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list); /* Check to see if we resolved a queued list. If so we * need to send on the frames and tidy up. */ found = false; spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(uc, &mrt->mfc_unres_queue, list) { + list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) { + uc = (struct mfc_cache *)_uc; if (uc->mfc_origin == c->mfc_origin && uc->mfc_mcastgrp == c->mfc_mcastgrp) { - list_del(&uc->list); + list_del(&_uc->list); atomic_dec(&mrt->cache_resolve_queue_len); found = true; break; @@ -1377,7 +1295,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, static void mroute_clean_tables(struct mr_table *mrt, bool all) { struct net *net = read_pnet(&mrt->net); - struct mfc_cache *c, *tmp; + struct mr_mfc *c, *tmp; + struct mfc_cache *cache; LIST_HEAD(list); int i; @@ -1395,18 +1314,20 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params); list_del_rcu(&c->list); - call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, + cache = (struct mfc_cache *)c; + call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache, mrt->id); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_cache_put(c); + mroute_netlink_event(mrt, cache, RTM_DELROUTE); + mr_cache_put(c); } if (atomic_read(&mrt->cache_resolve_queue_len) != 0) { spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - mroute_netlink_event(mrt, c, RTM_DELROUTE); - ipmr_destroy_unres(mrt, c); + cache = (struct mfc_cache *)c; + mroute_netlink_event(mrt, cache, RTM_DELROUTE); + ipmr_destroy_unres(mrt, cache); } spin_unlock_bh(&mfc_unres_lock); } @@ -1420,7 +1341,7 @@ static void mrtsock_destruct(struct sock *sk) struct net *net = sock_net(sk); struct mr_table *mrt; - ASSERT_RTNL(); + rtnl_lock(); ipmr_for_each_table(mrt, net) { if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; @@ -1432,6 +1353,7 @@ static void mrtsock_destruct(struct sock *sk) mroute_clean_tables(mrt, false); } } + rtnl_unlock(); } /* Socket options and virtual interface manipulation. The whole @@ -1496,8 +1418,13 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, if (sk != rcu_access_pointer(mrt->mroute_sk)) { ret = -EACCES; } else { + /* We need to unlock here because mrtsock_destruct takes + * care of rtnl itself and we can't change that due to + * the IP_ROUTER_ALERT setsockopt which runs without it. + */ + rtnl_unlock(); ret = ip_ra_control(sk, 0, NULL); - goto out_unlock; + goto out; } break; case MRT_ADD_VIF: @@ -1609,6 +1536,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, } out_unlock: rtnl_unlock(); +out: return ret; } @@ -1698,9 +1626,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1772,9 +1700,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { - sr.pktcnt = c->mfc_un.res.pkt; - sr.bytecnt = c->mfc_un.res.bytes; - sr.wrong_if = c->mfc_un.res.wrong_if; + sr.pktcnt = c->_c.mfc_un.res.pkt; + sr.bytecnt = c->_c.mfc_un.res.bytes; + sr.wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) @@ -1998,26 +1926,26 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ static void ip_mr_forward(struct net *net, struct mr_table *mrt, struct net_device *dev, struct sk_buff *skb, - struct mfc_cache *cache, int local) + struct mfc_cache *c, int local) { int true_vifi = ipmr_find_vif(mrt, dev); int psend = -1; int vif, ct; - vif = cache->mfc_parent; - cache->mfc_un.res.pkt++; - cache->mfc_un.res.bytes += skb->len; - cache->mfc_un.res.lastuse = jiffies; + vif = c->_c.mfc_parent; + c->_c.mfc_un.res.pkt++; + c->_c.mfc_un.res.bytes += skb->len; + c->_c.mfc_un.res.lastuse = jiffies; - if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { + if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) { struct mfc_cache *cache_proxy; /* For an (*,G) entry, we only check that the incomming * interface is part of the static tree. */ - cache_proxy = ipmr_cache_find_any_parent(mrt, vif); + cache_proxy = mr_mfc_find_any_parent(mrt, vif); if (cache_proxy && - cache_proxy->mfc_un.res.ttls[true_vifi] < 255) + cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) goto forward; } @@ -2038,7 +1966,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, goto dont_forward; } - cache->mfc_un.res.wrong_if++; + c->_c.mfc_un.res.wrong_if++; if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, @@ -2047,10 +1975,11 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt, * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || - cache->mfc_un.res.ttls[true_vifi] < 255) && + c->_c.mfc_un.res.ttls[true_vifi] < 255) && time_after(jiffies, - cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) { - cache->mfc_un.res.last_assert = jiffies; + c->_c.mfc_un.res.last_assert + + MFC_ASSERT_THRESH)) { + c->_c.mfc_un.res.last_assert = jiffies; ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF); } goto dont_forward; @@ -2061,33 +1990,33 @@ forward: mrt->vif_table[vif].bytes_in += skb->len; /* Forward the frame */ - if (cache->mfc_origin == htonl(INADDR_ANY) && - cache->mfc_mcastgrp == htonl(INADDR_ANY)) { + if (c->mfc_origin == htonl(INADDR_ANY) && + c->mfc_mcastgrp == htonl(INADDR_ANY)) { if (true_vifi >= 0 && - true_vifi != cache->mfc_parent && + true_vifi != c->_c.mfc_parent && ip_hdr(skb)->ttl > - cache->mfc_un.res.ttls[cache->mfc_parent]) { + c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) { /* It's an (*,*) entry and the packet is not coming from * the upstream: forward the packet to the upstream * only. */ - psend = cache->mfc_parent; + psend = c->_c.mfc_parent; goto last_forward; } goto dont_forward; } - for (ct = cache->mfc_un.res.maxvif - 1; - ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = c->_c.mfc_un.res.maxvif - 1; + ct >= c->_c.mfc_un.res.minvif; ct--) { /* For (*,G) entry, don't forward to the incoming interface */ - if ((cache->mfc_origin != htonl(INADDR_ANY) || + if ((c->mfc_origin != htonl(INADDR_ANY) || ct != true_vifi) && - ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { + ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, - skb2, cache, psend); + skb2, c, psend); } psend = ct; } @@ -2099,9 +2028,9 @@ last_forward: if (skb2) ipmr_queue_xmit(net, mrt, true_vifi, skb2, - cache, psend); + c, psend); } else { - ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend); + ipmr_queue_xmit(net, mrt, true_vifi, skb, c, psend); return; } } @@ -2299,62 +2228,6 @@ drop: } #endif -static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - struct mfc_cache *c, struct rtmsg *rtm) -{ - struct rta_mfc_stats mfcs; - struct nlattr *mp_attr; - struct rtnexthop *nhp; - unsigned long lastuse; - int ct; - - /* If cache is unresolved, don't try to parse IIF and OIF */ - if (c->mfc_parent >= MAXVIFS) { - rtm->rtm_flags |= RTNH_F_UNRESOLVED; - return -ENOENT; - } - - if (VIF_EXISTS(mrt, c->mfc_parent) && - nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) - return -EMSGSIZE; - - if (c->mfc_flags & MFC_OFFLOAD) - rtm->rtm_flags |= RTNH_F_OFFLOAD; - - if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH))) - return -EMSGSIZE; - - for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { - if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { - if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) { - nla_nest_cancel(skb, mp_attr); - return -EMSGSIZE; - } - - nhp->rtnh_flags = 0; - nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; - nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex; - nhp->rtnh_len = sizeof(*nhp); - } - } - - nla_nest_end(skb, mp_attr); - - lastuse = READ_ONCE(c->mfc_un.res.lastuse); - lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; - - mfcs.mfcs_packets = c->mfc_un.res.pkt; - mfcs.mfcs_bytes = c->mfc_un.res.bytes; - mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; - if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || - nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), - RTA_PAD)) - return -EMSGSIZE; - - rtm->rtm_type = RTN_MULTICAST; - return 1; -} - int ipmr_get_route(struct net *net, struct sk_buff *skb, __be32 saddr, __be32 daddr, struct rtmsg *rtm, u32 portid) @@ -2412,7 +2285,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } read_lock(&mrt_lock); - err = __ipmr_fill_mroute(mrt, skb, cache, rtm); + err = mr_fill_mroute(mrt, skb, &cache->_c, rtm); read_unlock(&mrt_lock); rcu_read_unlock(); return err; @@ -2440,7 +2313,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_type = RTN_MULTICAST; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - if (c->mfc_flags & MFC_STATIC) + if (c->_c.mfc_flags & MFC_STATIC) rtm->rtm_protocol = RTPROT_STATIC; else rtm->rtm_protocol = RTPROT_MROUTED; @@ -2449,7 +2322,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) || nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp)) goto nla_put_failure; - err = __ipmr_fill_mroute(mrt, skb, c, rtm); + err = mr_fill_mroute(mrt, skb, &c->_c, rtm); /* do not break the dump if cache is unresolved */ if (err < 0 && err != -ENOENT) goto nla_put_failure; @@ -2462,6 +2335,14 @@ nla_put_failure: return -EMSGSIZE; } +static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, int cmd, + int flags) +{ + return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c, + cmd, flags); +} + static size_t mroute_msgsize(bool unresolved, int maxvif) { size_t len = @@ -2490,7 +2371,8 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), + skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS, + mrt->maxvif), GFP_ATOMIC); if (!skb) goto errout; @@ -2634,62 +2516,8 @@ errout_free: static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = sock_net(skb->sk); - struct mr_table *mrt; - struct mfc_cache *mfc; - unsigned int t = 0, s_t; - unsigned int e = 0, s_e; - - s_t = cb->args[0]; - s_e = cb->args[1]; - - rcu_read_lock(); - ipmr_for_each_table(mrt, net) { - if (t < s_t) - goto next_table; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { - if (e < s_e) - goto next_entry; - if (ipmr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) - goto done; -next_entry: - e++; - } - e = 0; - s_e = 0; - - spin_lock_bh(&mfc_unres_lock); - list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { - if (e < s_e) - goto next_entry2; - if (ipmr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - mfc, RTM_NEWROUTE, - NLM_F_MULTI) < 0) { - spin_unlock_bh(&mfc_unres_lock); - goto done; - } -next_entry2: - e++; - } - spin_unlock_bh(&mfc_unres_lock); - e = 0; - s_e = 0; -next_table: - t++; - } -done: - rcu_read_unlock(); - - cb->args[1] = e; - cb->args[0] = t; - - return skb->len; + return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter, + _ipmr_fill_mroute, &mfc_unres_lock); } static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = { @@ -2946,31 +2774,11 @@ out: /* The /proc interfaces to multicast routing : * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ -struct ipmr_vif_iter { - struct seq_net_private p; - struct mr_table *mrt; - int ct; -}; - -static struct vif_device *ipmr_vif_seq_idx(struct net *net, - struct ipmr_vif_iter *iter, - loff_t pos) -{ - struct mr_table *mrt = iter->mrt; - - for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { - if (!VIF_EXISTS(mrt, iter->ct)) - continue; - if (pos-- == 0) - return &mrt->vif_table[iter->ct]; - } - return NULL; -} static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) __acquires(mrt_lock) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; @@ -2981,26 +2789,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) iter->mrt = mrt; read_lock(&mrt_lock); - return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_vif_iter *iter = seq->private; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = iter->mrt; - - ++*pos; - if (v == SEQ_START_TOKEN) - return ipmr_vif_seq_idx(net, iter, 0); - - while (++iter->ct < mrt->maxvif) { - if (!VIF_EXISTS(mrt, iter->ct)) - continue; - return &mrt->vif_table[iter->ct]; - } - return NULL; + return mr_vif_seq_start(seq, pos); } static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) @@ -3011,7 +2800,7 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v) static int ipmr_vif_seq_show(struct seq_file *seq, void *v) { - struct ipmr_vif_iter *iter = seq->private; + struct mr_vif_iter *iter = seq->private; struct mr_table *mrt = iter->mrt; if (v == SEQ_START_TOKEN) { @@ -3019,7 +2808,8 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) "Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n"); } else { const struct vif_device *vif = v; - const char *name = vif->dev ? vif->dev->name : "none"; + const char *name = vif->dev ? + vif->dev->name : "none"; seq_printf(seq, "%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n", @@ -3033,7 +2823,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_vif_seq_ops = { .start = ipmr_vif_seq_start, - .next = ipmr_vif_seq_next, + .next = mr_vif_seq_next, .stop = ipmr_vif_seq_stop, .show = ipmr_vif_seq_show, }; @@ -3041,7 +2831,7 @@ static const struct seq_operations ipmr_vif_seq_ops = { static int ipmr_vif_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_vif_seq_ops, - sizeof(struct ipmr_vif_iter)); + sizeof(struct mr_vif_iter)); } static const struct file_operations ipmr_vif_fops = { @@ -3051,40 +2841,8 @@ static const struct file_operations ipmr_vif_fops = { .release = seq_release_net, }; -struct ipmr_mfc_iter { - struct seq_net_private p; - struct mr_table *mrt; - struct list_head *cache; -}; - -static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, - struct ipmr_mfc_iter *it, loff_t pos) -{ - struct mr_table *mrt = it->mrt; - struct mfc_cache *mfc; - - rcu_read_lock(); - it->cache = &mrt->mfc_cache_list; - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - if (pos-- == 0) - return mfc; - rcu_read_unlock(); - - spin_lock_bh(&mfc_unres_lock); - it->cache = &mrt->mfc_unres_queue; - list_for_each_entry(mfc, it->cache, list) - if (pos-- == 0) - return mfc; - spin_unlock_bh(&mfc_unres_lock); - - it->cache = NULL; - return NULL; -} - - static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) { - struct ipmr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt; @@ -3092,54 +2850,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) if (!mrt) return ERR_PTR(-ENOENT); - it->mrt = mrt; - it->cache = NULL; - return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1) - : SEQ_START_TOKEN; -} - -static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct ipmr_mfc_iter *it = seq->private; - struct net *net = seq_file_net(seq); - struct mr_table *mrt = it->mrt; - struct mfc_cache *mfc = v; - - ++*pos; - - if (v == SEQ_START_TOKEN) - return ipmr_mfc_seq_idx(net, seq->private, 0); - - if (mfc->list.next != it->cache) - return list_entry(mfc->list.next, struct mfc_cache, list); - - if (it->cache == &mrt->mfc_unres_queue) - goto end_of_list; - - /* exhausted cache_array, show unresolved */ - rcu_read_unlock(); - it->cache = &mrt->mfc_unres_queue; - - spin_lock_bh(&mfc_unres_lock); - if (!list_empty(it->cache)) - return list_first_entry(it->cache, struct mfc_cache, list); - -end_of_list: - spin_unlock_bh(&mfc_unres_lock); - it->cache = NULL; - - return NULL; -} - -static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) -{ - struct ipmr_mfc_iter *it = seq->private; - struct mr_table *mrt = it->mrt; - - if (it->cache == &mrt->mfc_unres_queue) - spin_unlock_bh(&mfc_unres_lock); - else if (it->cache == &mrt->mfc_cache_list) - rcu_read_unlock(); + return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -3151,26 +2862,26 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) "Group Origin Iif Pkts Bytes Wrong Oifs\n"); } else { const struct mfc_cache *mfc = v; - const struct ipmr_mfc_iter *it = seq->private; + const struct mr_mfc_iter *it = seq->private; const struct mr_table *mrt = it->mrt; seq_printf(seq, "%08X %08X %-3hd", (__force u32) mfc->mfc_mcastgrp, (__force u32) mfc->mfc_origin, - mfc->mfc_parent); + mfc->_c.mfc_parent); if (it->cache != &mrt->mfc_unres_queue) { seq_printf(seq, " %8lu %8lu %8lu", - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); - for (n = mfc->mfc_un.res.minvif; - n < mfc->mfc_un.res.maxvif; n++) { + mfc->_c.mfc_un.res.pkt, + mfc->_c.mfc_un.res.bytes, + mfc->_c.mfc_un.res.wrong_if); + for (n = mfc->_c.mfc_un.res.minvif; + n < mfc->_c.mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && - mfc->mfc_un.res.ttls[n] < 255) + mfc->_c.mfc_un.res.ttls[n] < 255) seq_printf(seq, " %2d:%-3d", - n, mfc->mfc_un.res.ttls[n]); + n, mfc->_c.mfc_un.res.ttls[n]); } } else { /* unresolved mfc_caches don't contain @@ -3185,15 +2896,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) static const struct seq_operations ipmr_mfc_seq_ops = { .start = ipmr_mfc_seq_start, - .next = ipmr_mfc_seq_next, - .stop = ipmr_mfc_seq_stop, + .next = mr_mfc_seq_next, + .stop = mr_mfc_seq_stop, .show = ipmr_mfc_seq_show, }; static int ipmr_mfc_open(struct inode *inode, struct file *file) { return seq_open_net(inode, file, &ipmr_mfc_seq_ops, - sizeof(struct ipmr_mfc_iter)); + sizeof(struct mr_mfc_iter)); } static const struct file_operations ipmr_mfc_fops = { @@ -3220,37 +2931,8 @@ static unsigned int ipmr_seq_read(struct net *net) static int ipmr_dump(struct net *net, struct notifier_block *nb) { - struct mr_table *mrt; - int err; - - err = ipmr_rules_dump(net, nb); - if (err) - return err; - - ipmr_for_each_table(mrt, net) { - struct vif_device *v = &mrt->vif_table[0]; - struct mfc_cache *mfc; - int vifi; - - /* Notifiy on table VIF entries */ - read_lock(&mrt_lock); - for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { - if (!v->dev) - continue; - - call_ipmr_vif_entry_notifier(nb, net, FIB_EVENT_VIF_ADD, - v, vifi, mrt->id); - } - read_unlock(&mrt_lock); - - /* Notify on table MFC entries */ - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - call_ipmr_mfc_entry_notifier(nb, net, - FIB_EVENT_ENTRY_ADD, mfc, - mrt->id); - } - - return 0; + return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, + ipmr_mr_table_iter, &mrt_lock); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c new file mode 100644 index 0000000..4fe9772 --- /dev/null +++ b/net/ipv4/ipmr_base.c @@ -0,0 +1,365 @@ +/* Linux multicast routing support + * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation + */ + +#include <linux/mroute_base.h> + +/* Sets everything common except 'dev', since that is done under locking */ +void vif_device_init(struct vif_device *v, + struct net_device *dev, + unsigned long rate_limit, + unsigned char threshold, + unsigned short flags, + unsigned short get_iflink_mask) +{ + v->dev = NULL; + v->bytes_in = 0; + v->bytes_out = 0; + v->pkt_in = 0; + v->pkt_out = 0; + v->rate_limit = rate_limit; + v->flags = flags; + v->threshold = threshold; + if (v->flags & get_iflink_mask) + v->link = dev_get_iflink(dev); + else + v->link = dev->ifindex; +} +EXPORT_SYMBOL(vif_device_init); + +struct mr_table * +mr_table_alloc(struct net *net, u32 id, + struct mr_table_ops *ops, + void (*expire_func)(struct timer_list *t), + void (*table_set)(struct mr_table *mrt, + struct net *net)) +{ + struct mr_table *mrt; + + mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); + if (!mrt) + return NULL; + mrt->id = id; + write_pnet(&mrt->net, net); + + mrt->ops = *ops; + rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); + INIT_LIST_HEAD(&mrt->mfc_cache_list); + INIT_LIST_HEAD(&mrt->mfc_unres_queue); + + timer_setup(&mrt->ipmr_expire_timer, expire_func, 0); + + mrt->mroute_reg_vif_num = -1; + table_set(mrt, net); + return mrt; +} +EXPORT_SYMBOL(mr_table_alloc); + +void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c; + + list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) + if (parent == -1 || parent == c->mfc_parent) + return c; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_find_parent); + +void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c; + + list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any, + *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_find_any_parent); + +void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) +{ + struct rhlist_head *tmp, *list; + struct mr_mfc *c, *proxy; + + list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); + rhl_for_each_entry_rcu(c, tmp, list, mnode) { + if (c->mfc_un.res.ttls[vifi] < 255) + return c; + + /* It's ok if the vifi is part of the static tree */ + proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent); + if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) + return c; + } + + return mr_mfc_find_any_parent(mrt, vifi); +} +EXPORT_SYMBOL(mr_mfc_find_any); + +#ifdef CONFIG_PROC_FS +void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) +{ + struct mr_table *mrt = iter->mrt; + + for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { + if (!VIF_EXISTS(mrt, iter->ct)) + continue; + if (pos-- == 0) + return &mrt->vif_table[iter->ct]; + } + return NULL; +} +EXPORT_SYMBOL(mr_vif_seq_idx); + +void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct mr_vif_iter *iter = seq->private; + struct net *net = seq_file_net(seq); + struct mr_table *mrt = iter->mrt; + + ++*pos; + if (v == SEQ_START_TOKEN) + return mr_vif_seq_idx(net, iter, 0); + + while (++iter->ct < mrt->maxvif) { + if (!VIF_EXISTS(mrt, iter->ct)) + continue; + return &mrt->vif_table[iter->ct]; + } + return NULL; +} +EXPORT_SYMBOL(mr_vif_seq_next); + +void *mr_mfc_seq_idx(struct net *net, + struct mr_mfc_iter *it, loff_t pos) +{ + struct mr_table *mrt = it->mrt; + struct mr_mfc *mfc; + + rcu_read_lock(); + it->cache = &mrt->mfc_cache_list; + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + if (pos-- == 0) + return mfc; + rcu_read_unlock(); + + spin_lock_bh(it->lock); + it->cache = &mrt->mfc_unres_queue; + list_for_each_entry(mfc, it->cache, list) + if (pos-- == 0) + return mfc; + spin_unlock_bh(it->lock); + + it->cache = NULL; + return NULL; +} +EXPORT_SYMBOL(mr_mfc_seq_idx); + +void *mr_mfc_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct mr_mfc_iter *it = seq->private; + struct net *net = seq_file_net(seq); + struct mr_table *mrt = it->mrt; + struct mr_mfc *c = v; + + ++*pos; + + if (v == SEQ_START_TOKEN) + return mr_mfc_seq_idx(net, seq->private, 0); + + if (c->list.next != it->cache) + return list_entry(c->list.next, struct mr_mfc, list); + + if (it->cache == &mrt->mfc_unres_queue) + goto end_of_list; + + /* exhausted cache_array, show unresolved */ + rcu_read_unlock(); + it->cache = &mrt->mfc_unres_queue; + + spin_lock_bh(it->lock); + if (!list_empty(it->cache)) + return list_first_entry(it->cache, struct mr_mfc, list); + +end_of_list: + spin_unlock_bh(it->lock); + it->cache = NULL; + + return NULL; +} +EXPORT_SYMBOL(mr_mfc_seq_next); +#endif + +int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, + struct mr_mfc *c, struct rtmsg *rtm) +{ + struct rta_mfc_stats mfcs; + struct nlattr *mp_attr; + struct rtnexthop *nhp; + unsigned long lastuse; + int ct; + + /* If cache is unresolved, don't try to parse IIF and OIF */ + if (c->mfc_parent >= MAXVIFS) { + rtm->rtm_flags |= RTNH_F_UNRESOLVED; + return -ENOENT; + } + + if (VIF_EXISTS(mrt, c->mfc_parent) && + nla_put_u32(skb, RTA_IIF, + mrt->vif_table[c->mfc_parent].dev->ifindex) < 0) + return -EMSGSIZE; + + if (c->mfc_flags & MFC_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; + + mp_attr = nla_nest_start(skb, RTA_MULTIPATH); + if (!mp_attr) + return -EMSGSIZE; + + for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { + if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) { + struct vif_device *vif; + + nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); + if (!nhp) { + nla_nest_cancel(skb, mp_attr); + return -EMSGSIZE; + } + + nhp->rtnh_flags = 0; + nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; + vif = &mrt->vif_table[ct]; + nhp->rtnh_ifindex = vif->dev->ifindex; + nhp->rtnh_len = sizeof(*nhp); + } + } + + nla_nest_end(skb, mp_attr); + + lastuse = READ_ONCE(c->mfc_un.res.lastuse); + lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; + + mfcs.mfcs_packets = c->mfc_un.res.pkt; + mfcs.mfcs_bytes = c->mfc_un.res.bytes; + mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if; + if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || + nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), + RTA_PAD)) + return -EMSGSIZE; + + rtm->rtm_type = RTN_MULTICAST; + return 1; +} +EXPORT_SYMBOL(mr_fill_mroute); + +int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, + struct mr_table *(*iter)(struct net *net, + struct mr_table *mrt), + int (*fill)(struct mr_table *mrt, + struct sk_buff *skb, + u32 portid, u32 seq, struct mr_mfc *c, + int cmd, int flags), + spinlock_t *lock) +{ + unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1]; + struct net *net = sock_net(skb->sk); + struct mr_table *mrt; + struct mr_mfc *mfc; + + rcu_read_lock(); + for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) { + if (t < s_t) + goto next_table; + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { + if (e < s_e) + goto next_entry; + if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, + RTM_NEWROUTE, NLM_F_MULTI) < 0) + goto done; +next_entry: + e++; + } + e = 0; + s_e = 0; + + spin_lock_bh(lock); + list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { + if (e < s_e) + goto next_entry2; + if (fill(mrt, skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, mfc, + RTM_NEWROUTE, NLM_F_MULTI) < 0) { + spin_unlock_bh(lock); + goto done; + } +next_entry2: + e++; + } + spin_unlock_bh(lock); + e = 0; + s_e = 0; +next_table: + t++; + } +done: + rcu_read_unlock(); + + cb->args[1] = e; + cb->args[0] = t; + + return skb->len; +} +EXPORT_SYMBOL(mr_rtm_dumproute); + +int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, + int (*rules_dump)(struct net *net, + struct notifier_block *nb), + struct mr_table *(*mr_iter)(struct net *net, + struct mr_table *mrt), + rwlock_t *mrt_lock) +{ + struct mr_table *mrt; + int err; + + err = rules_dump(net, nb); + if (err) + return err; + + for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) { + struct vif_device *v = &mrt->vif_table[0]; + struct mr_mfc *mfc; + int vifi; + + /* Notifiy on table VIF entries */ + read_lock(mrt_lock); + for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { + if (!v->dev) + continue; + + mr_call_vif_notifier(nb, net, family, + FIB_EVENT_VIF_ADD, + v, vifi, mrt->id); + } + read_unlock(mrt_lock); + + /* Notify on table MFC entries */ + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) + mr_call_mfc_notifier(nb, net, family, + FIB_EVENT_ENTRY_ADD, + mfc, mrt->id); + } + + return 0; +} +EXPORT_SYMBOL(mr_dump); diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index dfe6fa4..280048e 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -34,7 +34,7 @@ config NF_SOCKET_IPV4 if NF_TABLES config NF_TABLES_IPV4 - tristate "IPv4 nf_tables support" + bool "IPv4 nf_tables support" help This option enables the IPv4 support for nf_tables. @@ -71,7 +71,7 @@ config NFT_FIB_IPV4 endif # NF_TABLES_IPV4 config NF_TABLES_ARP - tristate "ARP nf_tables support" + bool "ARP nf_tables support" select NETFILTER_FAMILY_ARP help This option enables the ARP support for nf_tables. diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 9bd19cd..7523ddb 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -39,7 +39,6 @@ obj-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o # NAT protocols (nf_nat) obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o -obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o @@ -47,7 +46,6 @@ obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o -obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # flow table support obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e3e420f..2dc83de 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -334,11 +334,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo, t->verdict < 0) || visited) { unsigned int oldpos, size; - if ((strcmp(t->target.u.user.name, - XT_STANDARD_TARGET) == 0) && - t->verdict < -NF_MAX_VERDICT - 1) - return 0; - /* Return: backtrack through the last * big jump. */ @@ -560,16 +555,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, if (i != repl->num_entries) goto out_free; - /* Check hooks all assigned */ - for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(repl->valid_hooks & (1 << i))) - continue; - if (newinfo->hook_entry[i] == 0xFFFFFFFF) - goto out_free; - if (newinfo->underflow[i] == 0xFFFFFFFF) - goto out_free; - } + ret = xt_check_table_hooks(newinfo, repl->valid_hooks); + if (ret) + goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; @@ -781,7 +769,9 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; - xt_compat_init_offsets(NFPROTO_ARP, info->number); + ret = xt_compat_init_offsets(NFPROTO_ARP, info->number); + if (ret) + return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -895,7 +885,7 @@ static int __do_replace(struct net *net, const char *name, struct arpt_entry *iter; ret = 0; - counters = vzalloc(num_counters * sizeof(struct xt_counters)); + counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; @@ -925,6 +915,8 @@ static int __do_replace(struct net *net, const char *name, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); + xt_table_unlock(t); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ @@ -939,7 +931,6 @@ static int __do_replace(struct net *net, const char *name, net_warn_ratelimited("arptables: counters copy to user failed while replacing table\n"); } vfree(counters); - xt_table_unlock(t); return ret; put_module: @@ -1167,7 +1158,7 @@ static int translate_compat_table(struct xt_table_info **pinfo, struct compat_arpt_entry *iter0; struct arpt_replace repl; unsigned int size; - int ret = 0; + int ret; info = *pinfo; entry0 = *pentry0; @@ -1176,7 +1167,9 @@ static int translate_compat_table(struct xt_table_info **pinfo, j = 0; xt_compat_lock(NFPROTO_ARP); - xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); + ret = xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries); + if (ret) + goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e38395a..44b308d 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -402,11 +402,6 @@ mark_source_chains(const struct xt_table_info *newinfo, t->verdict < 0) || visited) { unsigned int oldpos, size; - if ((strcmp(t->target.u.user.name, - XT_STANDARD_TARGET) == 0) && - t->verdict < -NF_MAX_VERDICT - 1) - return 0; - /* Return: backtrack through the last big jump. */ do { @@ -707,16 +702,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0, if (i != repl->num_entries) goto out_free; - /* Check hooks all assigned */ - for (i = 0; i < NF_INET_NUMHOOKS; i++) { - /* Only hooks which are valid */ - if (!(repl->valid_hooks & (1 << i))) - continue; - if (newinfo->hook_entry[i] == 0xFFFFFFFF) - goto out_free; - if (newinfo->underflow[i] == 0xFFFFFFFF) - goto out_free; - } + ret = xt_check_table_hooks(newinfo, repl->valid_hooks); + if (ret) + goto out_free; if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) { ret = -ELOOP; @@ -945,7 +933,9 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries; - xt_compat_init_offsets(AF_INET, info->number); + ret = xt_compat_init_offsets(AF_INET, info->number); + if (ret) + return ret; xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1057,7 +1047,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct ipt_entry *iter; ret = 0; - counters = vzalloc(num_counters * sizeof(struct xt_counters)); + counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; goto out; @@ -1087,6 +1077,8 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, (newinfo->number <= oldinfo->initial_entries)) module_put(t->me); + xt_table_unlock(t); + get_old_counters(oldinfo, counters); /* Decrease module usage counts and free resource */ @@ -1100,7 +1092,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); - xt_table_unlock(t); return ret; put_module: @@ -1418,7 +1409,9 @@ translate_compat_table(struct net *net, j = 0; xt_compat_lock(AF_INET); - xt_compat_init_offsets(AF_INET, compatr->num_entries); + ret = xt_compat_init_offsets(AF_INET, compatr->num_entries); + if (ret) + goto out_unlock; /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, compatr->size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 8a8ae61..2c8d313 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -250,7 +250,7 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, /* create proc dir entry */ sprintf(buffer, "%pI4", &ip); - c->pde = proc_create_data(buffer, S_IWUSR|S_IRUSR, + c->pde = proc_create_data(buffer, 0600, cn->procdir, &clusterip_proc_fops, c); if (!c->pde) { diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index f75fc6b..690b17e 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -16,6 +16,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_seqadj.h> #include <net/netfilter/nf_conntrack_synproxy.h> +#include <net/netfilter/nf_conntrack_ecache.h> static struct iphdr * synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, @@ -384,6 +385,8 @@ static unsigned int ipv4_synproxy_hook(void *priv, synproxy->isn = ntohl(th->ack_seq); if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy->its = opts.tsecr; + + nf_conntrack_event_cache(IPCT_SYNPROXY, ct); break; case TCP_CONNTRACK_SYN_RECV: if (!th->syn || !th->ack) @@ -392,8 +395,10 @@ static unsigned int ipv4_synproxy_hook(void *priv, if (!synproxy_parse_options(skb, thoff, th, &opts)) return NF_DROP; - if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) + if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) { synproxy->tsoff = opts.tsval - synproxy->its; + nf_conntrack_event_cache(IPCT_SYNPROXY, ct); + } opts.options &= ~(XT_SYNPROXY_OPT_MSS | XT_SYNPROXY_OPT_WSCALE | @@ -403,6 +408,7 @@ static unsigned int ipv4_synproxy_hook(void *priv, synproxy_send_server_ack(net, state, skb, th, &opts); nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq)); + nf_conntrack_event_cache(IPCT_SEQADJ, ct); swap(opts.tsval, opts.tsecr); synproxy_send_client_ack(net, skb, th, &opts); diff --git a/net/ipv4/netfilter/ipt_ah.c b/net/ipv4/netfilter/ipt_ah.c index a787d07..7c6c20e 100644 --- a/net/ipv4/netfilter/ipt_ah.c +++ b/net/ipv4/netfilter/ipt_ah.c @@ -47,7 +47,7 @@ static bool ah_mt(const struct sk_buff *skb, struct xt_action_param *par) */ pr_debug("Dropping evil AH tinygram.\n"); par->hotdrop = true; - return 0; + return false; } return spi_match(ahinfo->spis[0], ahinfo->spis[1], diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c deleted file mode 100644 index 036c074..0000000 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ /dev/null @@ -1,58 +0,0 @@ -/* - * Copyright (c) 2008-2010 Patrick McHardy <kaber@trash.net> - * Copyright (c) 2013 Pablo Neira Ayuso <pablo@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/netfilter_arp.h> -#include <net/netfilter/nf_tables.h> - -static unsigned int -nft_do_chain_arp(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_unspec(&pkt, skb); - - return nft_do_chain(&pkt, priv); -} - -static const struct nf_chain_type filter_arp = { - .name = "filter", - .type = NFT_CHAIN_T_DEFAULT, - .family = NFPROTO_ARP, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_ARP_IN) | - (1 << NF_ARP_OUT), - .hooks = { - [NF_ARP_IN] = nft_do_chain_arp, - [NF_ARP_OUT] = nft_do_chain_arp, - }, -}; - -static int __init nf_tables_arp_init(void) -{ - return nft_register_chain_type(&filter_arp); -} - -static void __exit nf_tables_arp_exit(void) -{ - nft_unregister_chain_type(&filter_arp); -} - -module_init(nf_tables_arp_init); -module_exit(nf_tables_arp_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_CHAIN(3, "filter"); /* NFPROTO_ARP */ diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c deleted file mode 100644 index 96f9554..0000000 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ /dev/null @@ -1,67 +0,0 @@ -/* - * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> - * Copyright (c) 2012-2013 Pablo Neira Ayuso <pablo@netfilter.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Development of this code funded by Astaro AG (http://www.astaro.com/) - */ - -#include <linux/init.h> -#include <linux/module.h> -#include <linux/ip.h> -#include <linux/netfilter_ipv4.h> -#include <net/netfilter/nf_tables.h> -#include <net/net_namespace.h> -#include <net/ip.h> -#include <net/netfilter/nf_tables_ipv4.h> - -static unsigned int nft_do_chain_ipv4(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nft_pktinfo pkt; - - nft_set_pktinfo(&pkt, skb, state); - nft_set_pktinfo_ipv4(&pkt, skb); - - return nft_do_chain(&pkt, priv); -} - -static const struct nf_chain_type filter_ipv4 = { - .name = "filter", - .type = NFT_CHAIN_T_DEFAULT, - .family = NFPROTO_IPV4, - .owner = THIS_MODULE, - .hook_mask = (1 << NF_INET_LOCAL_IN) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_FORWARD) | - (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_POST_ROUTING), - .hooks = { - [NF_INET_LOCAL_IN] = nft_do_chain_ipv4, - [NF_INET_LOCAL_OUT] = nft_do_chain_ipv4, - [NF_INET_FORWARD] = nft_do_chain_ipv4, - [NF_INET_PRE_ROUTING] = nft_do_chain_ipv4, - [NF_INET_POST_ROUTING] = nft_do_chain_ipv4, - }, -}; - -static int __init nf_tables_ipv4_init(void) -{ - return nft_register_chain_type(&filter_ipv4); -} - -static void __exit nf_tables_ipv4_exit(void) -{ - nft_unregister_chain_type(&filter_ipv4); -} - -module_init(nf_tables_ipv4_init); -module_exit(nf_tables_ipv4_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_CHAIN(AF_INET, "filter"); diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index f2a4909..b5464a3 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -67,7 +67,17 @@ static unsigned int nft_nat_ipv4_local_fn(void *priv, return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain); } -static const struct nf_chain_type nft_chain_nat_ipv4 = { +static int nft_nat_ipv4_init(struct nft_ctx *ctx) +{ + return nf_ct_netns_get(ctx->net, ctx->family); +} + +static void nft_nat_ipv4_free(struct nft_ctx *ctx) +{ + nf_ct_netns_put(ctx->net, ctx->family); +} + +static const struct nft_chain_type nft_chain_nat_ipv4 = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_IPV4, @@ -82,15 +92,13 @@ static const struct nf_chain_type nft_chain_nat_ipv4 = { [NF_INET_LOCAL_OUT] = nft_nat_ipv4_local_fn, [NF_INET_LOCAL_IN] = nft_nat_ipv4_fn, }, + .init = nft_nat_ipv4_init, + .free = nft_nat_ipv4_free, }; static int __init nft_chain_nat_init(void) { - int err; - - err = nft_register_chain_type(&nft_chain_nat_ipv4); - if (err < 0) - return err; + nft_register_chain_type(&nft_chain_nat_ipv4); return 0; } diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index d965c22..7d82934 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -58,7 +58,7 @@ static unsigned int nf_route_table_hook(void *priv, return ret; } -static const struct nf_chain_type nft_chain_route_ipv4 = { +static const struct nft_chain_type nft_chain_route_ipv4 = { .name = "route", .type = NFT_CHAIN_T_ROUTE, .family = NFPROTO_IPV4, @@ -71,7 +71,9 @@ static const struct nf_chain_type nft_chain_route_ipv4 = { static int __init nft_chain_route_init(void) { - return nft_register_chain_type(&nft_chain_route_ipv4); + nft_register_chain_type(&nft_chain_route_ipv4); + + return 0; } static void __exit nft_chain_route_exit(void) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b8f0db5..05e47d7 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -1177,7 +1177,7 @@ static struct ping_seq_afinfo ping_v4_seq_afinfo = { int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo) { struct proc_dir_entry *p; - p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + p = proc_create_data(afinfo->name, 0444, net->proc_net, afinfo->seq_fops, afinfo); if (!p) return -ENOMEM; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index dc5edc8..a058de6 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -54,7 +54,6 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; - unsigned int frag_mem; int orphans, sockets; orphans = percpu_counter_sum_positive(&tcp_orphan_count); @@ -72,8 +71,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(net, &raw_prot)); - frag_mem = ip_frag_mem(net); - seq_printf(seq, "FRAG: inuse %u memory %u\n", !!frag_mem, frag_mem); + seq_printf(seq, "FRAG: inuse %u memory %lu\n", + atomic_read(&net->ipv4.frags.rhashtable.nelems), + frag_mem_limit(&net->ipv4.frags)); return 0; } @@ -521,12 +521,12 @@ static const struct file_operations netstat_seq_fops = { static __net_init int ip_proc_init_net(struct net *net) { - if (!proc_create("sockstat", S_IRUGO, net->proc_net, + if (!proc_create("sockstat", 0444, net->proc_net, &sockstat_seq_fops)) goto out_sockstat; - if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops)) + if (!proc_create("netstat", 0444, net->proc_net, &netstat_seq_fops)) goto out_netstat; - if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops)) + if (!proc_create("snmp", 0444, net->proc_net, &snmp_seq_fops)) goto out_snmp; return 0; @@ -555,4 +555,3 @@ int __init ip_misc_proc_init(void) { return register_pernet_subsys(&ip_proc_ops); } - diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9b367fc..1b4d335 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -711,9 +711,7 @@ static void raw_close(struct sock *sk, long timeout) /* * Raw sockets may have direct kernel references. Kill them. */ - rtnl_lock(); ip_ra_control(sk, 0, NULL); - rtnl_unlock(); sk_common_release(sk); } @@ -1142,7 +1140,7 @@ static const struct file_operations raw_seq_fops = { static __net_init int raw_init_net(struct net *net) { - if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops)) + if (!proc_create("raw", 0444, net->proc_net, &raw_seq_fops)) return -ENOMEM; return 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 299e247..8322e47 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -379,12 +379,12 @@ static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; - pde = proc_create("rt_cache", S_IRUGO, net->proc_net, + pde = proc_create("rt_cache", 0444, net->proc_net, &rt_cache_seq_fops); if (!pde) goto err1; - pde = proc_create("rt_cache", S_IRUGO, + pde = proc_create("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_fops); if (!pde) goto err2; @@ -1532,7 +1532,6 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_mtu_locked = 0; rt->rt_gateway = 0; rt->rt_uses_gateway = 0; - rt->rt_table_id = 0; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; @@ -1668,19 +1667,6 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) spin_unlock_bh(&fnhe_lock); } -static void set_lwt_redirect(struct rtable *rth) -{ - if (lwtunnel_output_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_output = rth->dst.output; - rth->dst.output = lwtunnel_output; - } - - if (lwtunnel_input_redirect(rth->dst.lwtstate)) { - rth->dst.lwtstate->orig_input = rth->dst.input; - rth->dst.input = lwtunnel_input; - } -} - /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1763,15 +1749,13 @@ rt_cache: } rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1787,44 +1771,45 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); + const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; - hash_keys->addrs.v4addrs.src = outer_iph->saddr; - hash_keys->addrs.v4addrs.dst = outer_iph->daddr; if (likely(outer_iph->protocol != IPPROTO_ICMP)) - return; + goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) - return; + goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) - return; + goto out; if (icmph->type != ICMP_DEST_UNREACH && icmph->type != ICMP_REDIRECT && icmph->type != ICMP_TIME_EXCEEDED && icmph->type != ICMP_PARAMETERPROB) - return; + goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) - return; - hash_keys->addrs.v4addrs.src = inner_iph->saddr; - hash_keys->addrs.v4addrs.dst = inner_iph->daddr; + goto out; + + key_iph = inner_iph; +out: + hash_keys->addrs.v4addrs.src = key_iph->saddr; + hash_keys->addrs.v4addrs.dst = key_iph->daddr; } /* if skb is set it will be used and fl4 can be NULL */ -int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, - const struct sk_buff *skb) +int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, + const struct sk_buff *skb, struct flow_keys *flkeys) { - struct net *net = fi->fib_net; struct flow_keys hash_keys; u32 mhash; @@ -1848,15 +1833,20 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; + memset(&hash_keys, 0, sizeof(hash_keys)); - skb_flow_dissect_flow_keys(skb, &keys, flag); + + if (!flkeys) { + skb_flow_dissect_flow_keys(skb, &keys, flag); + flkeys = &keys; + } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; - hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; - hash_keys.ports.src = keys.ports.src; - hash_keys.ports.dst = keys.ports.dst; - hash_keys.basic.ip_proto = keys.basic.ip_proto; + hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; + hash_keys.ports.src = flkeys->ports.src; + hash_keys.ports.dst = flkeys->ports.dst; + hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -1872,17 +1862,17 @@ int fib_multipath_hash(const struct fib_info *fi, const struct flowi4 *fl4, return mhash >> 1; } -EXPORT_SYMBOL_GPL(fib_multipath_hash); #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, - __be32 daddr, __be32 saddr, u32 tos) + __be32 daddr, __be32 saddr, u32 tos, + struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && res->fi->fib_nhs > 1) { - int h = fib_multipath_hash(res->fi, NULL, skb); + int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); } @@ -1908,13 +1898,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct fib_result *res) { struct in_device *in_dev = __in_dev_get_rcu(dev); + struct flow_keys *flkeys = NULL, _flkeys; + struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; - struct flowi4 fl4; + int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; - int err = -EINVAL; - struct net *net = dev_net(dev); + struct flowi4 fl4; bool do_cache; /* IP on this device is disabled. */ @@ -1973,6 +1964,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + + if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) + flkeys = &_flkeys; + err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) @@ -1998,7 +1993,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res->type != RTN_UNICAST) goto martian_destination; - err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos); + err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: @@ -2040,8 +2035,6 @@ local_input: rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { @@ -2270,8 +2263,6 @@ add: return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; - if (res->table) - rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(out_slow_tot); @@ -2293,7 +2284,7 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); - set_lwt_redirect(rth); + lwtunnel_set_redirect(&rth->dst); return rth; } @@ -2804,7 +2795,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) - table_id = rt->rt_table_id; + table_id = res.table ? res.table->tb_id : 0; if (rtm->rtm_flags & RTM_F_FIB_MATCH) { if (!res.fi) { diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 93e1721..4b195ba 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -400,7 +400,7 @@ static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write, ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) - call_netevent_notifiers(NETEVENT_MULTIPATH_HASH_UPDATE, net); + call_netevent_notifiers(NETEVENT_IPV4_MPATH_HASH_UPDATE, net); return ret; } @@ -520,22 +520,6 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, - { - .procname = "udp_rmem_min", - .data = &sysctl_udp_rmem_min, - .maxlen = sizeof(sysctl_udp_rmem_min), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one - }, - { - .procname = "udp_wmem_min", - .data = &sysctl_udp_wmem_min, - .maxlen = sizeof(sysctl_udp_wmem_min), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &one - }, { } }; @@ -1167,6 +1151,22 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &one, }, + { + .procname = "udp_rmem_min", + .data = &init_net.ipv4.sysctl_udp_rmem_min, + .maxlen = sizeof(init_net.ipv4.sysctl_udp_rmem_min), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, + { + .procname = "udp_wmem_min", + .data = &init_net.ipv4.sysctl_udp_wmem_min, + .maxlen = sizeof(init_net.ipv4.sysctl_udp_wmem_min), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8b8059b..bccc4c2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -453,6 +453,7 @@ void tcp_init_sock(struct sock *sk) sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; sk_sockets_allocated_inc(sk); + sk->sk_route_forced_caps = NETIF_F_GSO; } EXPORT_SYMBOL(tcp_init_sock); @@ -484,6 +485,14 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) } } +static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, + int target, struct sock *sk) +{ + return (tp->rcv_nxt - tp->copied_seq >= target) || + (sk->sk_prot->stream_memory_read ? + sk->sk_prot->stream_memory_read(sk) : false); +} + /* * Wait for a TCP event. * @@ -553,7 +562,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) tp->urg_data) target++; - if (tp->rcv_nxt - tp->copied_seq >= target) + if (tcp_stream_is_readable(tp, target, sk)) mask |= EPOLLIN | EPOLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { @@ -897,7 +906,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, struct tcp_sock *tp = tcp_sk(sk); u32 new_size_goal, size_goal; - if (!large_allowed || !sk_can_gso(sk)) + if (!large_allowed) return mss_now; /* Note : tcp_tso_autosize() will eventually split this later */ @@ -993,7 +1002,9 @@ new_segment: get_page(page); skb_fill_page_desc(skb, i, page, offset, copy); } - skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; + + if (!(flags & MSG_NO_SHARED_FRAGS)) + skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; skb->len += copy; skb->data_len += copy; @@ -1062,8 +1073,7 @@ EXPORT_SYMBOL_GPL(do_tcp_sendpages); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { - if (!(sk->sk_route_caps & NETIF_F_SG) || - !sk_check_csum_caps(sk)) + if (!(sk->sk_route_caps & NETIF_F_SG)) return sock_no_sendpage_locked(sk, page, offset, size, flags); tcp_rate_check_app_limited(sk); /* is sending application-limited? */ @@ -1102,27 +1112,11 @@ static int linear_payload_sz(bool first_skb) return 0; } -static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc) +static int select_size(bool first_skb, bool zc) { - const struct tcp_sock *tp = tcp_sk(sk); - int tmp = tp->mss_cache; - - if (sg) { - if (zc) - return 0; - - if (sk_can_gso(sk)) { - tmp = linear_payload_sz(first_skb); - } else { - int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); - - if (tmp >= pgbreak && - tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE) - tmp = pgbreak; - } - } - - return tmp; + if (zc) + return 0; + return linear_payload_sz(first_skb); } void tcp_free_fastopen_req(struct tcp_sock *tp) @@ -1187,7 +1181,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool process_backlog = false; - bool sg, zc = false; + bool zc = false; long timeo; flags = msg->msg_flags; @@ -1205,7 +1199,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) goto out_err; } - zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + zc = sk->sk_route_caps & NETIF_F_SG; if (!zc) uarg->zerocopy = 0; } @@ -1268,18 +1262,12 @@ restart: if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; - sg = !!(sk->sk_route_caps & NETIF_F_SG); - while (msg_data_left(msg)) { int copy = 0; - int max = size_goal; skb = tcp_write_queue_tail(sk); - if (skb) { - if (skb->ip_summed == CHECKSUM_NONE) - max = mss_now; - copy = max - skb->len; - } + if (skb) + copy = size_goal - skb->len; if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; @@ -1297,22 +1285,17 @@ new_segment: goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - linear = select_size(sk, sg, first_skb, zc); + linear = select_size(first_skb, zc); skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; process_backlog = true; - /* - * Check whether we can use HW checksum. - */ - if (sk_check_csum_caps(sk)) - skb->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); copy = size_goal; - max = size_goal; /* All packets are restored as if they have * already been sent. skb_mstamp isn't set to @@ -1343,7 +1326,7 @@ new_segment: if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { - if (i >= sysctl_max_skb_frags || !sg) { + if (i >= sysctl_max_skb_frags) { tcp_mark_push(tp, skb); goto new_segment; } @@ -1396,7 +1379,7 @@ new_segment: goto out; } - if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair)) + if (skb->len < size_goal || (flags & MSG_OOB) || unlikely(tp->repair)) continue; if (forced_push(tp)) { @@ -3058,8 +3041,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u32 rate; stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 3 * nla_total_size(sizeof(u32)) + - 2 * nla_total_size(sizeof(u8)), GFP_ATOMIC); + 5 * nla_total_size(sizeof(u32)) + + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -3088,6 +3071,10 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); + nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); + + nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); + nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); return stats; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index a471f69..158d105 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -97,10 +97,9 @@ struct bbr { packet_conservation:1, /* use packet conservation? */ restore_cwnd:1, /* decided to revert cwnd to old value */ round_start:1, /* start of packet-timed tx->ack round? */ - tso_segs_goal:7, /* segments we want in each skb we send */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ - unused:5, + unused:12, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ @@ -261,23 +260,25 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) sk->sk_pacing_rate = rate; } -/* Return count of segments we want in the skbs we send, or 0 for default. */ -static u32 bbr_tso_segs_goal(struct sock *sk) +/* override sysctl_tcp_min_tso_segs */ +static u32 bbr_min_tso_segs(struct sock *sk) { - struct bbr *bbr = inet_csk_ca(sk); - - return bbr->tso_segs_goal; + return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; } -static void bbr_set_tso_segs_goal(struct sock *sk) +static u32 bbr_tso_segs_goal(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - struct bbr *bbr = inet_csk_ca(sk); - u32 min_segs; + u32 segs, bytes; + + /* Sort of tcp_tso_autosize() but ignoring + * driver provided sk_gso_max_size. + */ + bytes = min_t(u32, sk->sk_pacing_rate >> sk->sk_pacing_shift, + GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); + segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); - min_segs = sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; - bbr->tso_segs_goal = min(tcp_tso_autosize(sk, tp->mss_cache, min_segs), - 0x7FU); + return min(segs, 0x7FU); } /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ @@ -348,7 +349,7 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; /* Allow enough full-sized skbs in flight to utilize end systems. */ - cwnd += 3 * bbr->tso_segs_goal; + cwnd += 3 * bbr_tso_segs_goal(sk); /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; @@ -730,6 +731,8 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) bbr->mode = BBR_DRAIN; /* drain queue we created */ bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ + tcp_sk(sk)->snd_ssthresh = + bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && tcp_packets_in_flight(tcp_sk(sk)) <= @@ -824,7 +827,6 @@ static void bbr_main(struct sock *sk, const struct rate_sample *rs) bw = bbr_bw(sk); bbr_set_pacing_rate(sk, bw, bbr->pacing_gain); - bbr_set_tso_segs_goal(sk); bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } @@ -834,7 +836,7 @@ static void bbr_init(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->prior_cwnd = 0; - bbr->tso_segs_goal = 0; /* default segs per skb until first ACK */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; bbr->rtt_cnt = 0; bbr->next_rtt_delivered = 0; bbr->prev_ca_state = TCP_CA_Open; @@ -887,7 +889,7 @@ static u32 bbr_undo_cwnd(struct sock *sk) static u32 bbr_ssthresh(struct sock *sk) { bbr_save_cwnd(sk); - return TCP_INFINITE_SSTHRESH; /* BBR does not use ssthresh */ + return tcp_sk(sk)->snd_ssthresh; } static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, @@ -936,7 +938,7 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .undo_cwnd = bbr_undo_cwnd, .cwnd_event = bbr_cwnd_event, .ssthresh = bbr_ssthresh, - .tso_segs_goal = bbr_tso_segs_goal, + .min_tso_segs = bbr_min_tso_segs, .get_info = bbr_get_info, .set_state = bbr_set_state, }; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ff6cd98..367def6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1358,9 +1358,6 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, int len; int in_sack; - if (!sk_can_gso(sk)) - goto fallback; - /* Normally R but no L won't result in plain S */ if (!dup_sack && (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) @@ -5862,10 +5859,12 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tp->rx_opt.saw_tstamp = 0; req = tp->fastopen_rsk; if (req) { + bool req_stolen; + WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (!tcp_check_req(sk, skb, req, true)) + if (!tcp_check_req(sk, skb, req, true, &req_stolen)) goto discard; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f8ad397..f70586b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -140,6 +140,21 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_SYMBOL_GPL(tcp_twsk_unique); +static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, + int addr_len) +{ + /* This check is replicated from tcp_v4_connect() and intended to + * prevent BPF program called below from accessing bytes that are out + * of the bound specified by user in addr_len. + */ + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; + + sock_owned_by_me(sk); + + return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); +} + /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -561,16 +576,9 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v4_check(skb->len, saddr, daddr, - csum_partial(th, - th->doff << 2, - skb->csum)); - } + th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ @@ -1672,6 +1680,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); + bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; @@ -1694,10 +1703,20 @@ process: th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); - nsk = tcp_check_req(sk, skb, req, false); + nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); + if (req_stolen) { + /* Another cpu got exclusive access to req + * and created a full blown socket. + * Try to feed this packet to this socket + * instead of discarding it. + */ + tcp_v4_restore_cb(skb); + sock_put(sk); + goto lookup; + } goto discard_and_relse; } if (nsk == sk) { @@ -2211,7 +2230,7 @@ int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo) afinfo->seq_ops.next = tcp_seq_next; afinfo->seq_ops.stop = tcp_seq_stop; - p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + p = proc_create_data(afinfo->name, 0444, net->proc_net, afinfo->seq_fops, afinfo); if (!p) rc = -ENOMEM; @@ -2404,6 +2423,7 @@ struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, .close = tcp_close, + .pre_connect = tcp_v4_pre_connect, .connect = tcp_v4_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a8384b0c..57b5468 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -332,6 +332,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcp_update_metrics(sk); tcp_done(sk); } +EXPORT_SYMBOL(tcp_time_wait); void tcp_twsk_destructor(struct sock *sk) { @@ -578,7 +579,7 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - bool fastopen) + bool fastopen, bool *req_stolen) { struct tcp_options_received tmp_opt; struct sock *child; @@ -785,6 +786,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, sock_rps_save_rxhash(child, skb); tcp_synack_rtt_meas(child, req); + *req_stolen = !own_req; return inet_csk_complete_hashdance(sk, child, req, own_req); listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6818042..383cac0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1206,7 +1206,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { + if (skb->len <= mss_now) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1335,21 +1335,9 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); - if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { - /* Copy and checksum data tail into the new buffer. */ - buff->csum = csum_partial_copy_nocheck(skb->data + len, - skb_put(buff, nsize), - nsize, 0); - - skb_trim(skb, len); - - skb->csum = csum_block_sub(skb->csum, buff->csum, len); - } else { - skb->ip_summed = CHECKSUM_PARTIAL; - skb_split(skb, buff, len); - } + skb_split(skb, buff, len); - buff->ip_summed = skb->ip_summed; + buff->ip_summed = CHECKSUM_PARTIAL; buff->tstamp = skb->tstamp; tcp_fragment_tstamp(skb, buff); @@ -1715,8 +1703,8 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ -u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, - int min_tso_segs) +static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, + int min_tso_segs) { u32 bytes, segs; @@ -1732,7 +1720,6 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, return segs; } -EXPORT_SYMBOL(tcp_tso_autosize); /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. @@ -1740,11 +1727,13 @@ EXPORT_SYMBOL(tcp_tso_autosize); static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; - u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; + u32 min_tso, tso_segs; - if (!tso_segs) - tso_segs = tcp_tso_autosize(sk, mss_now, - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); + min_tso = ca_ops->min_tso_segs ? + ca_ops->min_tso_segs(sk) : + sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; + + tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } @@ -1902,7 +1891,7 @@ static int tso_fragment(struct sock *sk, enum tcp_queue tcp_queue, tcp_skb_fragment_eor(skb, buff); - buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; + buff->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); @@ -2135,7 +2124,7 @@ static int tcp_mtu_probe(struct sock *sk) TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; - nskb->ip_summed = skb->ip_summed; + nskb->ip_summed = CHECKSUM_PARTIAL; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); @@ -2143,14 +2132,7 @@ static int tcp_mtu_probe(struct sock *sk) len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); - if (nskb->ip_summed) { - skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); - } else { - __wsum csum = skb_copy_and_csum_bits(skb, 0, - skb_put(nskb, copy), - copy, 0); - nskb->csum = csum_block_add(nskb->csum, csum, len); - } + skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); if (skb->len <= copy) { /* We've eaten all the data from this skb. @@ -2167,9 +2149,6 @@ static int tcp_mtu_probe(struct sock *sk) ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_partial(skb->data, - skb->len, 0); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); @@ -2747,12 +2726,6 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) } tcp_highest_sack_replace(sk, next_skb, skb); - if (next_skb->ip_summed == CHECKSUM_PARTIAL) - skb->ip_summed = CHECKSUM_PARTIAL; - - if (skb->ip_summed != CHECKSUM_PARTIAL) - skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); - /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index ec35eaa..c063001 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -90,7 +90,7 @@ EXPORT_SYMBOL(xfrm4_tunnel_deregister); for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ - + static int tunnel4_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e5ef7c3..24b5c59 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -122,12 +122,6 @@ EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); -int sysctl_udp_rmem_min __read_mostly; -EXPORT_SYMBOL(sysctl_udp_rmem_min); - -int sysctl_udp_wmem_min __read_mostly; -EXPORT_SYMBOL(sysctl_udp_wmem_min); - atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); @@ -1664,6 +1658,19 @@ csum_copy_err: goto try_again; } +int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +{ + /* This check is replicated from __ip4_datagram_connect() and + * intended to prevent BPF program called below from accessing bytes + * that are out of the bound specified by user in addr_len. + */ + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; + + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); +} +EXPORT_SYMBOL(udp_pre_connect); + int __udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); @@ -2533,35 +2540,36 @@ int udp_abort(struct sock *sk, int err) EXPORT_SYMBOL_GPL(udp_abort); struct proto udp_prot = { - .name = "UDP", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .init = udp_init_sock, - .destroy = udp_destroy_sock, - .setsockopt = udp_setsockopt, - .getsockopt = udp_getsockopt, - .sendmsg = udp_sendmsg, - .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, - .release_cb = ip4_datagram_release_cb, - .hash = udp_lib_hash, - .unhash = udp_lib_unhash, - .rehash = udp_v4_rehash, - .get_port = udp_v4_get_port, - .memory_allocated = &udp_memory_allocated, - .sysctl_mem = sysctl_udp_mem, - .sysctl_wmem = &sysctl_udp_wmem_min, - .sysctl_rmem = &sysctl_udp_rmem_min, - .obj_size = sizeof(struct udp_sock), - .h.udp_table = &udp_table, + .name = "UDP", + .owner = THIS_MODULE, + .close = udp_lib_close, + .pre_connect = udp_pre_connect, + .connect = ip4_datagram_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udp_init_sock, + .destroy = udp_destroy_sock, + .setsockopt = udp_setsockopt, + .getsockopt = udp_getsockopt, + .sendmsg = udp_sendmsg, + .recvmsg = udp_recvmsg, + .sendpage = udp_sendpage, + .release_cb = ip4_datagram_release_cb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, + .get_port = udp_v4_get_port, + .memory_allocated = &udp_memory_allocated, + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), + .obj_size = sizeof(struct udp_sock), + .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udp_setsockopt, - .compat_getsockopt = compat_udp_getsockopt, + .compat_setsockopt = compat_udp_setsockopt, + .compat_getsockopt = compat_udp_getsockopt, #endif - .diag_destroy = udp_abort, + .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -2679,7 +2687,7 @@ int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) afinfo->seq_ops.next = udp_seq_next; afinfo->seq_ops.stop = udp_seq_stop; - p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + p = proc_create_data(afinfo->name, 0444, net->proc_net, afinfo->seq_fops, afinfo); if (!p) rc = -ENOMEM; @@ -2830,6 +2838,26 @@ u32 udp_flow_hashrnd(void) } EXPORT_SYMBOL(udp_flow_hashrnd); +static void __udp_sysctl_init(struct net *net) +{ + net->ipv4.sysctl_udp_rmem_min = SK_MEM_QUANTUM; + net->ipv4.sysctl_udp_wmem_min = SK_MEM_QUANTUM; + +#ifdef CONFIG_NET_L3_MASTER_DEV + net->ipv4.sysctl_udp_l3mdev_accept = 0; +#endif +} + +static int __net_init udp_sysctl_init(struct net *net) +{ + __udp_sysctl_init(net); + return 0; +} + +static struct pernet_operations __net_initdata udp_sysctl_ops = { + .init = udp_sysctl_init, +}; + void __init udp_init(void) { unsigned long limit; @@ -2842,8 +2870,7 @@ void __init udp_init(void) sysctl_udp_mem[1] = limit; sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; - sysctl_udp_rmem_min = SK_MEM_QUANTUM; - sysctl_udp_wmem_min = SK_MEM_QUANTUM; + __udp_sysctl_init(&init_net); /* 16 spinlocks per cpu */ udp_busylocks_log = ilog2(nr_cpu_ids) + 4; @@ -2853,4 +2880,7 @@ void __init udp_init(void) panic("UDP: failed to alloc udp_busylocks\n"); for (i = 0; i < (1U << udp_busylocks_log); i++) spin_lock_init(udp_busylocks + i); + + if (register_pernet_subsys(&udp_sysctl_ops)) + panic("UDP: failed to init sysctl parameters.\n"); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index fbebda6..d73a6d6 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -101,7 +101,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; - xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); @@ -382,4 +381,3 @@ void __init xfrm4_init(void) xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } - |
