From a190d04db93710ae166749055b6985397c6d13f5 Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 26 Oct 2017 15:09:21 -0700 Subject: ipvlan: introduce 'private' attribute for all existing modes. IPvlan has always operated in bridge mode. However there are scenarios where each slave should be able to talk through the master device but not necessarily across each other. Think of an environment where each of a namespace is a private and independant customer. In this scenario the machine which is hosting these namespaces neither want to tell who their neighbor is nor the individual namespaces care to talk to neighbor on short-circuited network path. This patch implements the mode that is very similar to the 'private' mode in macvlan where individual slaves can send and receive traffic through the master device, just that they can not talk among slave devices. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- Documentation/networking/ipvlan.txt | 30 ++++++++++++++++++++++++++--- drivers/net/ipvlan/ipvlan.h | 16 ++++++++++++++++ drivers/net/ipvlan/ipvlan_core.c | 15 ++++++++++++--- drivers/net/ipvlan/ipvlan_main.c | 38 +++++++++++++++++++++++++++++++++++-- include/uapi/linux/if_link.h | 3 +++ 5 files changed, 94 insertions(+), 8 deletions(-) diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index 1fe42a874aae..bfa91c77a4c9 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -22,9 +22,19 @@ The driver can be built into the kernel (CONFIG_IPVLAN=y) or as a module There are no module parameters for this driver and it can be configured using IProute2/ip utility. - ip link add link name type ipvlan mode { l2 | l3 | l3s } + ip link add link name type ipvlan [ mode MODE ] [ FLAGS ] + where + MODE: l3 (default) | l3s | l2 + FLAGS: bridge (default) | private - e.g. ip link add link eth0 name ipvl0 type ipvlan mode l2 + e.g. + (a) Following will create IPvlan link with eth0 as master in + L3 bridge mode + bash# ip link add link eth0 name ipvl0 type ipvlan + (b) This command will create IPvlan link in L2 bridge mode. + bash# ip link add link eth0 name ipvl0 type ipvlan mode l2 bridge + (c) This command will create an IPvlan device in L2 private mode. + bash# ip link add link eth0 name ipvlan type ipvlan mode l2 private 4. Operating modes: @@ -54,7 +64,21 @@ works in this mode and hence it is L3-symmetric (L3s). This will have slightly l performance but that shouldn't matter since you are choosing this mode over plain-L3 mode to make conn-tracking work. -5. What to choose (macvlan vs. ipvlan)? +5. Mode flags: + At this time following mode flags are available + +5.1 bridge: + This is the default option. To configure the IPvlan port in this mode, +user can choose to either add this option on the command-line or don't specify +anything. This is the traditional mode where slaves can cross-talk among +themseleves apart from talking through the master device. + +5.2 private: + If this option is added to the command-line, the port is set in private +mode. i.e. port wont allow cross communication between slaves. + + +6. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use case could very well define which device to choose. if one of the following situations defines your use case then you can choose to use ipvlan - diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index ba8173a0b62e..9941851bcc13 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -96,6 +96,7 @@ struct ipvl_port { struct hlist_head hlhead[IPVLAN_HASH_SIZE]; struct list_head ipvlans; u16 mode; + u16 flags; u16 dev_id_start; struct work_struct wq; struct sk_buff_head backlog; @@ -123,6 +124,21 @@ static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d) return rtnl_dereference(d->rx_handler_data); } +static inline bool ipvlan_is_private(const struct ipvl_port *port) +{ + return !!(port->flags & IPVLAN_F_PRIVATE); +} + +static inline void ipvlan_mark_private(struct ipvl_port *port) +{ + port->flags |= IPVLAN_F_PRIVATE; +} + +static inline void ipvlan_clear_private(struct ipvl_port *port) +{ + port->flags &= ~IPVLAN_F_PRIVATE; +} + void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 1f3295e274d0..72fd56de9c00 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -515,9 +515,13 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) goto out; addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } return ipvlan_rcv_frame(addr, &skb, true); - + } out: ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); return ipvlan_process_outbound(skb); @@ -535,8 +539,13 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) lyr3h = ipvlan_get_L3_hdr(skb, &addr_type); if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } return ipvlan_rcv_frame(addr, &skb, true); + } } skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index f0ab55df57f1..4368afb1934c 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -462,11 +462,24 @@ static int ipvlan_nl_changelink(struct net_device *dev, struct ipvl_port *port = ipvlan_port_get_rtnl(ipvlan->phy_dev); int err = 0; - if (data && data[IFLA_IPVLAN_MODE]) { + if (!data) + return 0; + + if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); err = ipvlan_set_port_mode(port, nmode); } + + if (!err && data[IFLA_IPVLAN_FLAGS]) { + u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + + if (flags & IPVLAN_F_PRIVATE) + ipvlan_mark_private(port); + else + ipvlan_clear_private(port); + } + return err; } @@ -474,18 +487,30 @@ static size_t ipvlan_nl_getsize(const struct net_device *dev) { return (0 + nla_total_size(2) /* IFLA_IPVLAN_MODE */ + + nla_total_size(2) /* IFLA_IPVLAN_FLAGS */ ); } static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { - if (data && data[IFLA_IPVLAN_MODE]) { + if (!data) + return 0; + + if (data[IFLA_IPVLAN_MODE]) { u16 mode = nla_get_u16(data[IFLA_IPVLAN_MODE]); if (mode < IPVLAN_MODE_L2 || mode >= IPVLAN_MODE_MAX) return -EINVAL; } + if (data[IFLA_IPVLAN_FLAGS]) { + u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + + /* Only one bit is used at this moment. */ + if (flags & ~IPVLAN_F_PRIVATE) + return -EINVAL; + } + return 0; } @@ -502,6 +527,8 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb, ret = -EMSGSIZE; if (nla_put_u16(skb, IFLA_IPVLAN_MODE, port->mode)) goto err; + if (nla_put_u16(skb, IFLA_IPVLAN_FLAGS, port->flags)) + goto err; return 0; @@ -549,6 +576,12 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, ipvlan_adjust_mtu(ipvlan, phy_dev); INIT_LIST_HEAD(&ipvlan->addrs); + /* Flags are per port and latest update overrides. User has + * to be consistent in setting it just like the mode attribute. + */ + if (data && data[IFLA_IPVLAN_FLAGS]) + ipvlan->port->flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); + /* If the port-id base is at the MAX value, then wrap it around and * begin from 0x1 again. This may be due to a busy system where lots * of slaves are getting created and deleted. @@ -644,6 +677,7 @@ EXPORT_SYMBOL_GPL(ipvlan_link_setup); static const struct nla_policy ipvlan_nl_policy[IFLA_IPVLAN_MAX + 1] = { [IFLA_IPVLAN_MODE] = { .type = NLA_U16 }, + [IFLA_IPVLAN_FLAGS] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipvlan_link_ops = { diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b037e0ab1975..052e32cd584c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -465,6 +465,7 @@ enum macsec_validation_type { enum { IFLA_IPVLAN_UNSPEC, IFLA_IPVLAN_MODE, + IFLA_IPVLAN_FLAGS, __IFLA_IPVLAN_MAX }; @@ -477,6 +478,8 @@ enum ipvlan_mode { IPVLAN_MODE_MAX }; +#define IPVLAN_F_PRIVATE 0x01 + /* VXLAN section */ enum { IFLA_VXLAN_UNSPEC, -- cgit v1.2.3 From fe89aa6b250c1011ccf425fbb7998e96bd54263f Mon Sep 17 00:00:00 2001 From: Mahesh Bandewar Date: Thu, 26 Oct 2017 15:09:25 -0700 Subject: ipvlan: implement VEPA mode This is very similar to the Macvlan VEPA mode, however, there is some difference. IPvlan uses the mac-address of the lower device, so the VEPA mode has implications of ICMP-redirects for packets destined for its immediate neighbors sharing same master since the packets will have same source and dest mac. The external switch/router will send redirect msg. Having said that, this will be useful tool in terms of debugging since IPvlan will not switch packets within its slaves and rely completely on the external entity as intended in 802.1Qbg. Signed-off-by: Mahesh Bandewar Signed-off-by: David S. Miller --- Documentation/networking/ipvlan.txt | 12 +++++++++++- drivers/net/ipvlan/ipvlan.h | 15 +++++++++++++++ drivers/net/ipvlan/ipvlan_core.c | 17 ++++++++++------- drivers/net/ipvlan/ipvlan_main.c | 13 +++++++++++-- include/uapi/linux/if_link.h | 1 + 5 files changed, 48 insertions(+), 10 deletions(-) diff --git a/Documentation/networking/ipvlan.txt b/Documentation/networking/ipvlan.txt index bfa91c77a4c9..812ef003e0a8 100644 --- a/Documentation/networking/ipvlan.txt +++ b/Documentation/networking/ipvlan.txt @@ -25,7 +25,7 @@ using IProute2/ip utility. ip link add link name type ipvlan [ mode MODE ] [ FLAGS ] where MODE: l3 (default) | l3s | l2 - FLAGS: bridge (default) | private + FLAGS: bridge (default) | private | vepa e.g. (a) Following will create IPvlan link with eth0 as master in @@ -35,6 +35,8 @@ using IProute2/ip utility. bash# ip link add link eth0 name ipvl0 type ipvlan mode l2 bridge (c) This command will create an IPvlan device in L2 private mode. bash# ip link add link eth0 name ipvlan type ipvlan mode l2 private + (d) This command will create an IPvlan device in L2 vepa mode. + bash# ip link add link eth0 name ipvlan type ipvlan mode l2 vepa 4. Operating modes: @@ -77,6 +79,14 @@ themseleves apart from talking through the master device. If this option is added to the command-line, the port is set in private mode. i.e. port wont allow cross communication between slaves. +5.3 vepa: + If this is added to the command-line, the port is set in VEPA mode. +i.e. port will offload switching functionality to the external entity as +described in 802.1Qbg +Note: VEPA mode in IPvlan has limitations. IPvlan uses the mac-address of the +master-device, so the packets which are emitted in this mode for the adjacent +neighbor will have source and destination mac same. This will make the switch / +router send the redirect message. 6. What to choose (macvlan vs. ipvlan)? These two devices are very similar in many regards and the specific use diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index 9941851bcc13..5166575a164d 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -139,6 +139,21 @@ static inline void ipvlan_clear_private(struct ipvl_port *port) port->flags &= ~IPVLAN_F_PRIVATE; } +static inline bool ipvlan_is_vepa(const struct ipvl_port *port) +{ + return !!(port->flags & IPVLAN_F_VEPA); +} + +static inline void ipvlan_mark_vepa(struct ipvl_port *port) +{ + port->flags |= IPVLAN_F_VEPA; +} + +static inline void ipvlan_clear_vepa(struct ipvl_port *port) +{ + port->flags &= ~IPVLAN_F_VEPA; +} + void ipvlan_init_secret(void); unsigned int ipvlan_mac_hash(const unsigned char *addr); rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb); diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 72fd56de9c00..034ae4c57196 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -514,13 +514,15 @@ static int ipvlan_xmit_mode_l3(struct sk_buff *skb, struct net_device *dev) if (!lyr3h) goto out; - addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); - if (addr) { - if (ipvlan_is_private(ipvlan->port)) { - consume_skb(skb); - return NET_XMIT_DROP; + if (!ipvlan_is_vepa(ipvlan->port)) { + addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); + if (addr) { + if (ipvlan_is_private(ipvlan->port)) { + consume_skb(skb); + return NET_XMIT_DROP; + } + return ipvlan_rcv_frame(addr, &skb, true); } - return ipvlan_rcv_frame(addr, &skb, true); } out: ipvlan_skb_crossing_ns(skb, ipvlan->phy_dev); @@ -535,7 +537,8 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev) void *lyr3h; int addr_type; - if (ether_addr_equal(eth->h_dest, eth->h_source)) { + if (!ipvlan_is_vepa(ipvlan->port) && + ether_addr_equal(eth->h_dest, eth->h_source)) { lyr3h = ipvlan_get_L3_hdr(skb, &addr_type); if (lyr3h) { addr = ipvlan_addr_lookup(ipvlan->port, lyr3h, addr_type, true); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 4368afb1934c..a266aa435d4d 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -478,6 +478,11 @@ static int ipvlan_nl_changelink(struct net_device *dev, ipvlan_mark_private(port); else ipvlan_clear_private(port); + + if (flags & IPVLAN_F_VEPA) + ipvlan_mark_vepa(port); + else + ipvlan_clear_vepa(port); } return err; @@ -506,8 +511,12 @@ static int ipvlan_nl_validate(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_IPVLAN_FLAGS]) { u16 flags = nla_get_u16(data[IFLA_IPVLAN_FLAGS]); - /* Only one bit is used at this moment. */ - if (flags & ~IPVLAN_F_PRIVATE) + /* Only two bits are used at this moment. */ + if (flags & ~(IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) + return -EINVAL; + /* Also both flags can't be active at the same time. */ + if ((flags & (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) == + (IPVLAN_F_PRIVATE | IPVLAN_F_VEPA)) return -EINVAL; } diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 052e32cd584c..81f26473d728 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -479,6 +479,7 @@ enum ipvlan_mode { }; #define IPVLAN_F_PRIVATE 0x01 +#define IPVLAN_F_VEPA 0x02 /* VXLAN section */ enum { -- cgit v1.2.3