diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-08 21:40:54 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-08 21:40:54 -0400 |
commit | 35a9ad8af0bb0fa3525e6d0d20e32551d226f38e (patch) | |
tree | 15b4b33206818886d9cff371fd2163e073b70568 /net/openvswitch/flow_netlink.c | |
parent | d5935b07da53f74726e2a65dd4281d0f2c70e5d4 (diff) | |
parent | 64b1f00a0830e1c53874067273a096b228d83d36 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Most notable changes in here:
1) By far the biggest accomplishment, thanks to a large range of
contributors, is the addition of multi-send for transmit. This is
the result of discussions back in Chicago, and the hard work of
several individuals.
Now, when the ->ndo_start_xmit() method of a driver sees
skb->xmit_more as true, it can choose to defer the doorbell
telling the driver to start processing the new TX queue entires.
skb->xmit_more means that the generic networking is guaranteed to
call the driver immediately with another SKB to send.
There is logic added to the qdisc layer to dequeue multiple
packets at a time, and the handling mis-predicted offloads in
software is now done with no locks held.
Finally, pktgen is extended to have a "burst" parameter that can
be used to test a multi-send implementation.
Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
virtio_net
Adding support is almost trivial, so export more drivers to
support this optimization soon.
I want to thank, in no particular or implied order, Jesper
Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
David Tat, Hannes Frederic Sowa, and Rusty Russell.
2) PTP and timestamping support in bnx2x, from Michal Kalderon.
3) Allow adjusting the rx_copybreak threshold for a driver via
ethtool, and add rx_copybreak support to enic driver. From
Govindarajulu Varadarajan.
4) Significant enhancements to the generic PHY layer and the bcm7xxx
driver in particular (EEE support, auto power down, etc.) from
Florian Fainelli.
5) Allow raw buffers to be used for flow dissection, allowing drivers
to determine the optimal "linear pull" size for devices that DMA
into pools of pages. The objective is to get exactly the
necessary amount of headers into the linear SKB area pre-pulled,
but no more. The new interface drivers use is eth_get_headlen().
From WANG Cong, with driver conversions (several had their own
by-hand duplicated implementations) by Alexander Duyck and Eric
Dumazet.
6) Support checksumming more smoothly and efficiently for
encapsulations, and add "foo over UDP" facility. From Tom
Herbert.
7) Add Broadcom SF2 switch driver to DSA layer, from Florian
Fainelli.
8) eBPF now can load programs via a system call and has an extensive
testsuite. Alexei Starovoitov and Daniel Borkmann.
9) Major overhaul of the packet scheduler to use RCU in several major
areas such as the classifiers and rate estimators. From John
Fastabend.
10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
Duyck.
11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
Dumazet.
12) Add Datacenter TCP congestion control algorithm support, From
Florian Westphal.
13) Reorganize sk_buff so that __copy_skb_header() is significantly
faster. From Eric Dumazet"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
netlabel: directly return netlbl_unlabel_genl_init()
net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
net: description of dma_cookie cause make xmldocs warning
cxgb4: clean up a type issue
cxgb4: potential shift wrapping bug
i40e: skb->xmit_more support
net: fs_enet: Add NAPI TX
net: fs_enet: Remove non NAPI RX
r8169:add support for RTL8168EP
net_sched: copy exts->type in tcf_exts_change()
wimax: convert printk to pr_foo()
af_unix: remove 0 assignment on static
ipv6: Do not warn for informational ICMP messages, regardless of type.
Update Intel Ethernet Driver maintainers list
bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
tipc: fix bug in multicast congestion handling
net: better IFF_XMIT_DST_RELEASE support
net/mlx4_en: remove NETDEV_TX_BUSY
3c59x: fix bad split of cpu_to_le32(pci_map_single())
net: bcmgenet: fix Tx ring priority programming
...
Diffstat (limited to 'net/openvswitch/flow_netlink.c')
-rw-r--r-- | net/openvswitch/flow_netlink.c | 292 |
1 files changed, 239 insertions, 53 deletions
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d757848da89c..368f23307911 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2007-2013 Nicira, Inc. + * Copyright (c) 2007-2014 Nicira, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public @@ -42,6 +42,7 @@ #include <linux/icmp.h> #include <linux/icmpv6.h> #include <linux/rculist.h> +#include <net/geneve.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ndisc.h> @@ -88,18 +89,20 @@ static void update_range__(struct sw_flow_match *match, } \ } while (0) -#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \ - do { \ - update_range__(match, offsetof(struct sw_flow_key, field), \ - len, is_mask); \ - if (is_mask) { \ - if ((match)->mask) \ - memcpy(&(match)->mask->key.field, value_p, len);\ - } else { \ - memcpy(&(match)->key->field, value_p, len); \ - } \ +#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \ + do { \ + update_range__(match, offset, len, is_mask); \ + if (is_mask) \ + memcpy((u8 *)&(match)->mask->key + offset, value_p, \ + len); \ + else \ + memcpy((u8 *)(match)->key + offset, value_p, len); \ } while (0) +#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \ + SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \ + value_p, len, is_mask) + static u16 range_n_bytes(const struct sw_flow_key_range *range) { return range->end - range->start; @@ -251,6 +254,8 @@ static const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6), [OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp), [OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd), + [OVS_KEY_ATTR_RECIRC_ID] = sizeof(u32), + [OVS_KEY_ATTR_DP_HASH] = sizeof(u32), [OVS_KEY_ATTR_TUNNEL] = -1, }; @@ -333,6 +338,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, int rem; bool ttl = false; __be16 tun_flags = 0; + unsigned long opt_key_offset; nla_for_each_nested(a, attr, rem) { int type = nla_type(a); @@ -344,6 +350,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, [OVS_TUNNEL_KEY_ATTR_TTL] = 1, [OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0, [OVS_TUNNEL_KEY_ATTR_CSUM] = 0, + [OVS_TUNNEL_KEY_ATTR_OAM] = 0, + [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1, }; if (type > OVS_TUNNEL_KEY_ATTR_MAX) { @@ -352,7 +360,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return -EINVAL; } - if (ovs_tunnel_key_lens[type] != nla_len(a)) { + if (ovs_tunnel_key_lens[type] != nla_len(a) && + ovs_tunnel_key_lens[type] != -1) { OVS_NLERR("IPv4 tunnel attribute type has unexpected " " length (type=%d, length=%d, expected=%d).\n", type, nla_len(a), ovs_tunnel_key_lens[type]); @@ -388,7 +397,63 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_CSUM: tun_flags |= TUNNEL_CSUM; break; + case OVS_TUNNEL_KEY_ATTR_OAM: + tun_flags |= TUNNEL_OAM; + break; + case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS: + tun_flags |= TUNNEL_OPTIONS_PRESENT; + if (nla_len(a) > sizeof(match->key->tun_opts)) { + OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n", + nla_len(a), + sizeof(match->key->tun_opts)); + return -EINVAL; + } + + if (nla_len(a) % 4 != 0) { + OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n", + nla_len(a)); + return -EINVAL; + } + + /* We need to record the length of the options passed + * down, otherwise packets with the same format but + * additional options will be silently matched. + */ + if (!is_mask) { + SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a), + false); + } else { + /* This is somewhat unusual because it looks at + * both the key and mask while parsing the + * attributes (and by extension assumes the key + * is parsed first). Normally, we would verify + * that each is the correct length and that the + * attributes line up in the validate function. + * However, that is difficult because this is + * variable length and we won't have the + * information later. + */ + if (match->key->tun_opts_len != nla_len(a)) { + OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).", + match->key->tun_opts_len, + nla_len(a)); + return -EINVAL; + } + + SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, + true); + } + + opt_key_offset = (unsigned long)GENEVE_OPTS( + (struct sw_flow_key *)0, + nla_len(a)); + SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, + nla_data(a), nla_len(a), + is_mask); + break; default: + OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n", + type); return -EINVAL; } } @@ -415,45 +480,80 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, return 0; } -static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ovs_key_ipv4_tunnel *tun_key, - const struct ovs_key_ipv4_tunnel *output) +static int __ipv4_tun_to_nlattr(struct sk_buff *skb, + const struct ovs_key_ipv4_tunnel *output, + const struct geneve_opt *tun_opts, + int swkey_tun_opts_len) { - struct nlattr *nla; - - nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL); - if (!nla) - return -EMSGSIZE; - if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; if (output->ipv4_src && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src)) + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src)) return -EMSGSIZE; if (output->ipv4_dst && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst)) + nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst)) return -EMSGSIZE; if (output->ipv4_tos && - nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) + nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos)) return -EMSGSIZE; if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl)) return -EMSGSIZE; if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) && - nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT)) return -EMSGSIZE; if ((output->tun_flags & TUNNEL_CSUM) && - nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM)) + return -EMSGSIZE; + if ((output->tun_flags & TUNNEL_OAM) && + nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM)) + return -EMSGSIZE; + if (tun_opts && + nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, + swkey_tun_opts_len, tun_opts)) return -EMSGSIZE; - nla_nest_end(skb, nla); return 0; } +static int ipv4_tun_to_nlattr(struct sk_buff *skb, + const struct ovs_key_ipv4_tunnel *output, + const struct geneve_opt *tun_opts, + int swkey_tun_opts_len) +{ + struct nlattr *nla; + int err; + + nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL); + if (!nla) + return -EMSGSIZE; + + err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len); + if (err) + return err; + + nla_nest_end(skb, nla); + return 0; +} + static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs, const struct nlattr **a, bool is_mask) { + if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) { + u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]); + + SW_FLOW_KEY_PUT(match, ovs_flow_hash, hash_val, is_mask); + *attrs &= ~(1 << OVS_KEY_ATTR_DP_HASH); + } + + if (*attrs & (1 << OVS_KEY_ATTR_RECIRC_ID)) { + u32 recirc_id = nla_get_u32(a[OVS_KEY_ATTR_RECIRC_ID]); + + SW_FLOW_KEY_PUT(match, recirc_id, recirc_id, is_mask); + *attrs &= ~(1 << OVS_KEY_ATTR_RECIRC_ID); + } + if (*attrs & (1 << OVS_KEY_ATTR_PRIORITY)) { SW_FLOW_KEY_PUT(match, phy.priority, nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]), is_mask); @@ -836,7 +936,7 @@ int ovs_nla_get_match(struct sw_flow_match *match, /** * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key. - * @flow: Receives extracted in_port, priority, tun_key and skb_mark. + * @key: Receives extracted in_port, priority, tun_key and skb_mark. * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute * sequence. * @@ -846,32 +946,24 @@ int ovs_nla_get_match(struct sw_flow_match *match, * extracted from the packet itself. */ -int ovs_nla_get_flow_metadata(struct sw_flow *flow, - const struct nlattr *attr) +int ovs_nla_get_flow_metadata(const struct nlattr *attr, + struct sw_flow_key *key) { - struct ovs_key_ipv4_tunnel *tun_key = &flow->key.tun_key; const struct nlattr *a[OVS_KEY_ATTR_MAX + 1]; + struct sw_flow_match match; u64 attrs = 0; int err; - struct sw_flow_match match; - - flow->key.phy.in_port = DP_MAX_PORTS; - flow->key.phy.priority = 0; - flow->key.phy.skb_mark = 0; - memset(tun_key, 0, sizeof(flow->key.tun_key)); err = parse_flow_nlattrs(attr, a, &attrs); if (err) return -EINVAL; memset(&match, 0, sizeof(match)); - match.key = &flow->key; + match.key = key; - err = metadata_from_nlattrs(&match, &attrs, a, false); - if (err) - return err; + key->phy.in_port = DP_MAX_PORTS; - return 0; + return metadata_from_nlattrs(&match, &attrs, a, false); } int ovs_nla_put_flow(const struct sw_flow_key *swkey, @@ -881,13 +973,26 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, struct nlattr *nla, *encap; bool is_mask = (swkey != output); - if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) + if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id)) + goto nla_put_failure; + + if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash)) goto nla_put_failure; - if ((swkey->tun_key.ipv4_dst || is_mask) && - ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key)) + if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority)) goto nla_put_failure; + if ((swkey->tun_key.ipv4_dst || is_mask)) { + const struct geneve_opt *opts = NULL; + + if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) + opts = GENEVE_OPTS(output, swkey->tun_opts_len); + + if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, + swkey->tun_opts_len)) + goto nla_put_failure; + } + if (swkey->phy.in_port == DP_MAX_PORTS) { if (is_mask && (output->phy.in_port == 0xffff)) if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, 0xffffffff)) @@ -1127,13 +1232,14 @@ out: return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset); } -static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len) +static struct nlattr *__add_action(struct sw_flow_actions **sfa, + int attrtype, void *data, int len) { struct nlattr *a; a = reserve_sfa_size(sfa, nla_attr_size(len)); if (IS_ERR(a)) - return PTR_ERR(a); + return a; a->nla_type = attrtype; a->nla_len = nla_attr_size(len); @@ -1142,6 +1248,18 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, in memcpy(nla_data(a), data, len); memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len)); + return a; +} + +static int add_action(struct sw_flow_actions **sfa, int attrtype, + void *data, int len) +{ + struct nlattr *a; + + a = __add_action(sfa, attrtype, data, len); + if (IS_ERR(a)) + return PTR_ERR(a); + return 0; } @@ -1247,6 +1365,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, { struct sw_flow_match match; struct sw_flow_key key; + struct ovs_tunnel_info *tun_info; + struct nlattr *a; int err, start; ovs_match_init(&match, &key, NULL); @@ -1254,12 +1374,56 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, if (err) return err; + if (key.tun_opts_len) { + struct geneve_opt *option = GENEVE_OPTS(&key, + key.tun_opts_len); + int opts_len = key.tun_opts_len; + bool crit_opt = false; + + while (opts_len > 0) { + int len; + + if (opts_len < sizeof(*option)) + return -EINVAL; + + len = sizeof(*option) + option->length * 4; + if (len > opts_len) + return -EINVAL; + + crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE); + + option = (struct geneve_opt *)((u8 *)option + len); + opts_len -= len; + }; + + key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0; + }; + start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET); if (start < 0) return start; - err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key, - sizeof(match.key->tun_key)); + a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL, + sizeof(*tun_info) + key.tun_opts_len); + if (IS_ERR(a)) + return PTR_ERR(a); + + tun_info = nla_data(a); + tun_info->tunnel = key.tun_key; + tun_info->options_len = key.tun_opts_len; + + if (tun_info->options_len) { + /* We need to store the options in the action itself since + * everything else will go away after flow setup. We can append + * it to tun_info and then point there. + */ + memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len), + key.tun_opts_len); + tun_info->options = (struct geneve_opt *)(tun_info + 1); + } else { + tun_info->options = NULL; + } + add_nested_action_end(*sfa, start); return err; @@ -1409,11 +1573,13 @@ int ovs_nla_copy_actions(const struct nlattr *attr, /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { [OVS_ACTION_ATTR_OUTPUT] = sizeof(u32), + [OVS_ACTION_ATTR_RECIRC] = sizeof(u32), [OVS_ACTION_ATTR_USERSPACE] = (u32)-1, [OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan), [OVS_ACTION_ATTR_POP_VLAN] = 0, [OVS_ACTION_ATTR_SET] = (u32)-1, - [OVS_ACTION_ATTR_SAMPLE] = (u32)-1 + [OVS_ACTION_ATTR_SAMPLE] = (u32)-1, + [OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash) }; const struct ovs_action_push_vlan *vlan; int type = nla_type(a); @@ -1440,6 +1606,18 @@ int ovs_nla_copy_actions(const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_HASH: { + const struct ovs_action_hash *act_hash = nla_data(a); + + switch (act_hash->hash_alg) { + case OVS_HASH_ALG_L4: + break; + default: + return -EINVAL; + } + + break; + } case OVS_ACTION_ATTR_POP_VLAN: break; @@ -1452,6 +1630,9 @@ int ovs_nla_copy_actions(const struct nlattr *attr, return -EINVAL; break; + case OVS_ACTION_ATTR_RECIRC: + break; + case OVS_ACTION_ATTR_SET: err = validate_set(a, key, sfa, &skip_copy); if (err) @@ -1525,17 +1706,22 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) int err; switch (key_type) { - case OVS_KEY_ATTR_IPV4_TUNNEL: + case OVS_KEY_ATTR_TUNNEL_INFO: { + struct ovs_tunnel_info *tun_info = nla_data(ovs_key); + start = nla_nest_start(skb, OVS_ACTION_ATTR_SET); if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key), - nla_data(ovs_key)); + err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel, + tun_info->options_len ? + tun_info->options : NULL, + tun_info->options_len); if (err) return err; nla_nest_end(skb, start); break; + } default: if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key)) return -EMSGSIZE; |