From 10708f37ae729baba9b67bd134c3720709d4ae62 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Thu, 11 Mar 2010 09:57:29 +0000 Subject: net: core: add IFLA_STATS64 support `ip -s link` shows interface counters truncated to 32 bit. This is because interface statistics are transported only in 32-bit quantity to userspace. This commit adds a new IFLA_STATS64 attribute that exports them in full 64 bit. References: http://lkml.indiana.edu/hypermail/linux/kernel/0307.3/0215.html Signed-off-by: Jan Engelhardt Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 42 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4568120d8533..e1121f0bca6a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -600,7 +600,39 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->rx_compressed = b->rx_compressed; a->tx_compressed = b->tx_compressed; -}; +} + +static void copy_rtnl_link_stats64(struct rtnl_link_stats64 *a, + const struct net_device_stats *b) +{ + a->rx_packets = b->rx_packets; + a->tx_packets = b->tx_packets; + a->rx_bytes = b->rx_bytes; + a->tx_bytes = b->tx_bytes; + a->rx_errors = b->rx_errors; + a->tx_errors = b->tx_errors; + a->rx_dropped = b->rx_dropped; + a->tx_dropped = b->tx_dropped; + + a->multicast = b->multicast; + a->collisions = b->collisions; + + a->rx_length_errors = b->rx_length_errors; + a->rx_over_errors = b->rx_over_errors; + a->rx_crc_errors = b->rx_crc_errors; + a->rx_frame_errors = b->rx_frame_errors; + a->rx_fifo_errors = b->rx_fifo_errors; + a->rx_missed_errors = b->rx_missed_errors; + + a->tx_aborted_errors = b->tx_aborted_errors; + a->tx_carrier_errors = b->tx_carrier_errors; + a->tx_fifo_errors = b->tx_fifo_errors; + a->tx_heartbeat_errors = b->tx_heartbeat_errors; + a->tx_window_errors = b->tx_window_errors; + + a->rx_compressed = b->rx_compressed; + a->tx_compressed = b->tx_compressed; +} static inline int rtnl_vfinfo_size(const struct net_device *dev) { @@ -698,6 +730,14 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, stats = dev_get_stats(dev); copy_rtnl_link_stats(nla_data(attr), stats); + attr = nla_reserve(skb, IFLA_STATS64, + sizeof(struct rtnl_link_stats64)); + if (attr == NULL) + goto nla_put_failure; + + stats = dev_get_stats(dev); + copy_rtnl_link_stats64(nla_data(attr), stats); + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { int i; struct ifla_vf_info ivi; -- cgit v1.2.3 From 755d0e77ac9c8d125388922dc33434ed5b2ebe80 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Mar 2010 04:42:24 +0000 Subject: net: rtnetlink: ignore NETDEV_PRE_TYPE_CHANGE in rtnetlink_event() Ignore the new NETDEV_PRE_TYPE_CHANGE event in rtnetlink_event() since there have been no changes userspace needs to be notified of. Also add a comment to the netdev notifier event definitions to remind people to update the exclusion list when adding new event types. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/notifier.h | 5 ++++- net/core/rtnetlink.c | 1 + 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f3635fc6e942..9c5d3fad01f3 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -182,7 +182,10 @@ static inline int notifier_to_errno(int ret) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ -/* netdevice notifier chain */ +/* netdevice notifier chain. Please remember to update the rtnetlink + * notification exclusion list in rtnetlink_event() when adding new + * types. + */ #define NETDEV_UP 0x0001 /* For now you can't veto a device up/down */ #define NETDEV_DOWN 0x0002 #define NETDEV_REBOOT 0x0003 /* Tell a protocol stack a network interface diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e1121f0bca6a..ffc6cf3495ac 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1513,6 +1513,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_POST_INIT: case NETDEV_REGISTER: case NETDEV_CHANGE: + case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: -- cgit v1.2.3 From 14a4b42bd6082b4ce3b94bad00cd367707cc1e97 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 27 Mar 2010 16:35:50 -0700 Subject: net: fix unaligned access in IFLA_STATS64 Tony Luck observes that the original IFLA_STATS64 submission causes unaligned accesses. This is because nla_data() returns a pointer to a memory region that is only aligned to 32 bits. Do some memcpying to workaround this. Signed-off-by: Jan Engelhardt Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 62 ++++++++++++++++++++++++++-------------------------- 1 file changed, 31 insertions(+), 31 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ffc6cf3495ac..ed0766f0181a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -602,36 +602,38 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; } -static void copy_rtnl_link_stats64(struct rtnl_link_stats64 *a, - const struct net_device_stats *b) +static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b) { - a->rx_packets = b->rx_packets; - a->tx_packets = b->tx_packets; - a->rx_bytes = b->rx_bytes; - a->tx_bytes = b->tx_bytes; - a->rx_errors = b->rx_errors; - a->tx_errors = b->tx_errors; - a->rx_dropped = b->rx_dropped; - a->tx_dropped = b->tx_dropped; - - a->multicast = b->multicast; - a->collisions = b->collisions; - - a->rx_length_errors = b->rx_length_errors; - a->rx_over_errors = b->rx_over_errors; - a->rx_crc_errors = b->rx_crc_errors; - a->rx_frame_errors = b->rx_frame_errors; - a->rx_fifo_errors = b->rx_fifo_errors; - a->rx_missed_errors = b->rx_missed_errors; - - a->tx_aborted_errors = b->tx_aborted_errors; - a->tx_carrier_errors = b->tx_carrier_errors; - a->tx_fifo_errors = b->tx_fifo_errors; - a->tx_heartbeat_errors = b->tx_heartbeat_errors; - a->tx_window_errors = b->tx_window_errors; - - a->rx_compressed = b->rx_compressed; - a->tx_compressed = b->tx_compressed; + struct rtnl_link_stats64 a; + + a.rx_packets = b->rx_packets; + a.tx_packets = b->tx_packets; + a.rx_bytes = b->rx_bytes; + a.tx_bytes = b->tx_bytes; + a.rx_errors = b->rx_errors; + a.tx_errors = b->tx_errors; + a.rx_dropped = b->rx_dropped; + a.tx_dropped = b->tx_dropped; + + a.multicast = b->multicast; + a.collisions = b->collisions; + + a.rx_length_errors = b->rx_length_errors; + a.rx_over_errors = b->rx_over_errors; + a.rx_crc_errors = b->rx_crc_errors; + a.rx_frame_errors = b->rx_frame_errors; + a.rx_fifo_errors = b->rx_fifo_errors; + a.rx_missed_errors = b->rx_missed_errors; + + a.tx_aborted_errors = b->tx_aborted_errors; + a.tx_carrier_errors = b->tx_carrier_errors; + a.tx_fifo_errors = b->tx_fifo_errors; + a.tx_heartbeat_errors = b->tx_heartbeat_errors; + a.tx_window_errors = b->tx_window_errors; + + a.rx_compressed = b->rx_compressed; + a.tx_compressed = b->tx_compressed; + memcpy(v, &a, sizeof(a)); } static inline int rtnl_vfinfo_size(const struct net_device *dev) @@ -734,8 +736,6 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, sizeof(struct rtnl_link_stats64)); if (attr == NULL) goto nla_put_failure; - - stats = dev_get_stats(dev); copy_rtnl_link_stats64(nla_data(attr), stats); if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { -- cgit v1.2.3 From adcfe1964e627b62fbc6e45609b1f0db2c64dd14 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Sat, 27 Mar 2010 17:15:29 -0700 Subject: net: increase preallocated size of nlmsg to accomodate for IFLA_STATS64 When more data is stuffed into an nlmsg than initially projected, an extra allocation needs to be done. Reserve enough for IFLA_STATS64 so that this does not to needlessy happen. Signed-off-by: Jan Engelhardt Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index ed0766f0181a..bf919b6acea2 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -653,6 +653,7 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + nla_total_size(sizeof(struct rtnl_link_ifmap)) + nla_total_size(sizeof(struct rtnl_link_stats)) + + nla_total_size(sizeof(struct rtnl_link_stats64)) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */ + nla_total_size(4) /* IFLA_TXQLEN */ -- cgit v1.2.3 From 0f87b1dd01b51dc3c789f7a212656a4a87eee1bd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Tue, 13 Apr 2010 05:03:17 +0000 Subject: net: fib_rules: decouple address families from real address families Decouple the address family values used for fib_rules from the real address families in socket.h. This allows to use fib_rules for code that is not a real address family without increasing AF_MAX/NPROTO. Values up to 127 are reserved for real address families and map directly to the corresponding AF value, values starting from 128 are for other uses. rtnetlink is changed to invoke the AF_UNSPEC dumpit/doit handlers for these families. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/fib_rules.h | 7 +++++++ net/core/rtnetlink.c | 15 ++++++++++----- net/decnet/dn_rules.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv6/fib6_rules.c | 2 +- 5 files changed, 20 insertions(+), 8 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 51da65b68b85..405e41139a4d 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -15,6 +15,13 @@ /* try to find source address in routing lookups */ #define FIB_RULE_FIND_SADDR 0x00010000 +/* fib_rules families. values up to 127 are reserved for real address + * families, values above 128 may be used arbitrarily. + */ +#define FIB_RULES_IPV4 AF_INET +#define FIB_RULES_IPV6 AF_INET6 +#define FIB_RULES_DECNET AF_DECnet + struct fib_rule_hdr { __u8 family; __u8 dst_len; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index bf919b6acea2..78c85985cb30 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -118,7 +118,11 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol < NPROTO) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].doit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -129,7 +133,11 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { struct rtnl_link *tab; - tab = rtnl_msg_handlers[protocol]; + if (protocol < NPROTO) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + if (tab == NULL || tab[msgindex].dumpit == NULL) tab = rtnl_msg_handlers[PF_UNSPEC]; @@ -1444,9 +1452,6 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return 0; family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; - if (family >= NPROTO) - return -EAFNOSUPPORT; - sz_idx = type>>2; kind = type&3; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 1c8cc6d5b645..af28dcc21844 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -217,7 +217,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) } static struct fib_rules_ops dn_fib_rules_ops_template = { - .family = AF_DECnet, + .family = FIB_RULES_DECNET, .rule_size = sizeof(struct dn_fib_rule), .addr_size = sizeof(u16), .action = dn_fib_rule_action, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index a18355e15111..3ec84fea5b71 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -246,7 +246,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) } static struct fib_rules_ops fib4_rules_ops_template = { - .family = AF_INET, + .family = FIB_RULES_IPV4, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 92b2b7fb6c3d..8124f16f2ac2 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -238,7 +238,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) } static struct fib_rules_ops fib6_rules_ops_template = { - .family = AF_INET6, + .family = FIB_RULES_IPV6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, -- cgit v1.2.3 From 25239cee7e8732dbdc9f5d324f1c22a3bdec1d1f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Mon, 26 Apr 2010 16:02:05 +0200 Subject: net: rtnetlink: decouple rtnetlink address families from real address families Decouple rtnetlink address families from real address families in socket.h to be able to add rtnetlink interfaces to code that is not a real address family without increasing AF_MAX/NPROTO. This will be used to add support for multicast route dumping from all tables as the proc interface can't be extended to support anything but the main table without breaking compatibility. This partialy undoes the patch to introduce independant families for routing rules and converts ipmr routing rules to a new rtnetlink family. Similar to that patch, values up to 127 are reserved for real address families, values above that may be used arbitrarily. Signed-off-by: Patrick McHardy --- include/linux/fib_rules.h | 8 -------- include/linux/rtnetlink.h | 6 ++++++ net/core/rtnetlink.c | 14 +++++++------- net/decnet/dn_rules.c | 2 +- net/ipv4/fib_rules.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv6/fib6_rules.c | 2 +- 7 files changed, 17 insertions(+), 19 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/linux/fib_rules.h b/include/linux/fib_rules.h index 04a397619ebe..51da65b68b85 100644 --- a/include/linux/fib_rules.h +++ b/include/linux/fib_rules.h @@ -15,14 +15,6 @@ /* try to find source address in routing lookups */ #define FIB_RULE_FIND_SADDR 0x00010000 -/* fib_rules families. values up to 127 are reserved for real address - * families, values above 128 may be used arbitrarily. - */ -#define FIB_RULES_IPV4 AF_INET -#define FIB_RULES_IPV6 AF_INET6 -#define FIB_RULES_DECNET AF_DECnet -#define FIB_RULES_IPMR 128 - struct fib_rule_hdr { __u8 family; __u8 dst_len; diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index d1c7c90e9cd4..5a42c36cb6aa 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -7,6 +7,12 @@ #include #include +/* rtnetlink families. Values up to 127 are reserved for real address + * families, values above 128 may be used arbitrarily. + */ +#define RTNL_FAMILY_IPMR 128 +#define RTNL_FAMILY_MAX 128 + /**** * Routing/neighbour discovery messages. ****/ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 78c85985cb30..fd781b62fa7f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -98,7 +98,7 @@ int lockdep_rtnl_is_held(void) EXPORT_SYMBOL(lockdep_rtnl_is_held); #endif /* #ifdef CONFIG_PROVE_LOCKING */ -static struct rtnl_link *rtnl_msg_handlers[NPROTO]; +static struct rtnl_link *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; static inline int rtm_msgindex(int msgtype) { @@ -118,7 +118,7 @@ static rtnl_doit_func rtnl_get_doit(int protocol, int msgindex) { struct rtnl_link *tab; - if (protocol < NPROTO) + if (protocol <= RTNL_FAMILY_MAX) tab = rtnl_msg_handlers[protocol]; else tab = NULL; @@ -133,7 +133,7 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) { struct rtnl_link *tab; - if (protocol < NPROTO) + if (protocol <= RTNL_FAMILY_MAX) tab = rtnl_msg_handlers[protocol]; else tab = NULL; @@ -167,7 +167,7 @@ int __rtnl_register(int protocol, int msgtype, struct rtnl_link *tab; int msgindex; - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); tab = rtnl_msg_handlers[protocol]; @@ -219,7 +219,7 @@ int rtnl_unregister(int protocol, int msgtype) { int msgindex; - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype); if (rtnl_msg_handlers[protocol] == NULL) @@ -241,7 +241,7 @@ EXPORT_SYMBOL_GPL(rtnl_unregister); */ void rtnl_unregister_all(int protocol) { - BUG_ON(protocol < 0 || protocol >= NPROTO); + BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); kfree(rtnl_msg_handlers[protocol]); rtnl_msg_handlers[protocol] = NULL; @@ -1384,7 +1384,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (s_idx == 0) s_idx = 1; - for (idx = 1; idx < NPROTO; idx++) { + for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 1226bcad776b..48fdf10be7a1 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -217,7 +217,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) } static const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = { - .family = FIB_RULES_DECNET, + .family = AF_DECnet, .rule_size = sizeof(struct dn_fib_rule), .addr_size = sizeof(u16), .action = dn_fib_rule_action, diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 8ab62a56701c..76daeb5ff564 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -246,7 +246,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops) } static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { - .family = FIB_RULES_IPV4, + .family = AF_INET, .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 7d3e382aed64..41e8fc0ce8b3 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -217,7 +217,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb, } static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = { - .family = FIB_RULES_IPMR, + .family = RTNL_FAMILY_IPMR, .rule_size = sizeof(struct ipmr_rule), .addr_size = sizeof(u32), .action = ipmr_rule_action, diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 35f6949446f0..8e44f8f9c188 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -238,7 +238,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) } static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = { - .family = FIB_RULES_IPV6, + .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, -- cgit v1.2.3 From 57b610805ce92dbd79fc97509f80fa5391b99623 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Mon, 17 May 2010 22:49:55 -0700 Subject: net: Add netlink support for virtual port management (was iovnl) Add new netdev ops ndo_{set|get}_vf_port to allow setting of port-profile on a netdev interface. Extends netlink socket RTM_SETLINK/ RTM_GETLINK with two new sub msgs called IFLA_VF_PORTS and IFLA_PORT_SELF (added to end of IFLA_cmd list). These are both nested atrtibutes using this layout: [IFLA_NUM_VF] [IFLA_VF_PORTS] [IFLA_VF_PORT] [IFLA_PORT_*], ... [IFLA_VF_PORT] [IFLA_PORT_*], ... ... [IFLA_PORT_SELF] [IFLA_PORT_*], ... These attributes are design to be set and get symmetrically. VF_PORTS is a list of VF_PORTs, one for each VF, when dealing with an SR-IOV device. PORT_SELF is for the PF of the SR-IOV device, in case it wants to also have a port-profile, or for the case where the VF==PF, like in enic patch 2/2 of this patch set. A port-profile is used to configure/enable the external switch virtual port backing the netdev interface, not to configure the host-facing side of the netdev. A port-profile is an identifier known to the switch. How port- profiles are installed on the switch or how available port-profiles are made know to the host is outside the scope of this patch. There are two types of port-profiles specs in the netlink msg. The first spec is for 802.1Qbg (pre-)standard, VDP protocol. The second spec is for devices that run a similar protocol as VDP but in firmware, thus hiding the protocol details. In either case, the specs have much in common and makes sense to define the netlink msg as the union of the two specs. For example, both specs have a notition of associating/deassociating a port-profile. And both specs require some information from the hypervisor manager, such as client port instance ID. The general flow is the port-profile is applied to a host netdev interface using RTM_SETLINK, the receiver of the RTM_SETLINK msg communicates with the switch, and the switch virtual port backing the host netdev interface is configured/enabled based on the settings defined by the port-profile. What those settings comprise, and how those settings are managed is again outside the scope of this patch, since this patch only deals with the first step in the flow. Signed-off-by: Scott Feldman Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/linux/if_link.h | 75 ++++++++++++++++++++ include/linux/netdevice.h | 8 +++ net/core/rtnetlink.c | 169 +++++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 251 insertions(+), 1 deletion(-) (limited to 'net/core/rtnetlink.c') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index c3af67fce3f2..85c812db5a3f 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -113,6 +113,8 @@ enum { IFLA_NUM_VF, /* Number of VFs if device is SR-IOV PF */ IFLA_VFINFO_LIST, IFLA_STATS64, + IFLA_VF_PORTS, + IFLA_PORT_SELF, __IFLA_MAX }; @@ -274,4 +276,77 @@ struct ifla_vf_info { __u32 qos; __u32 tx_rate; }; + +/* VF ports management section + * + * Nested layout of set/get msg is: + * + * [IFLA_NUM_VF] + * [IFLA_VF_PORTS] + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * [IFLA_VF_PORT] + * [IFLA_PORT_*], ... + * ... + * [IFLA_PORT_SELF] + * [IFLA_PORT_*], ... + */ + +enum { + IFLA_VF_PORT_UNSPEC, + IFLA_VF_PORT, /* nest */ + __IFLA_VF_PORT_MAX, +}; + +#define IFLA_VF_PORT_MAX (__IFLA_VF_PORT_MAX - 1) + +enum { + IFLA_PORT_UNSPEC, + IFLA_PORT_VF, /* __u32 */ + IFLA_PORT_PROFILE, /* string */ + IFLA_PORT_VSI_TYPE, /* 802.1Qbg (pre-)standard VDP */ + IFLA_PORT_INSTANCE_UUID, /* binary UUID */ + IFLA_PORT_HOST_UUID, /* binary UUID */ + IFLA_PORT_REQUEST, /* __u8 */ + IFLA_PORT_RESPONSE, /* __u16, output only */ + __IFLA_PORT_MAX, +}; + +#define IFLA_PORT_MAX (__IFLA_PORT_MAX - 1) + +#define PORT_PROFILE_MAX 40 +#define PORT_UUID_MAX 16 +#define PORT_SELF_VF -1 + +enum { + PORT_REQUEST_PREASSOCIATE = 0, + PORT_REQUEST_PREASSOCIATE_RR, + PORT_REQUEST_ASSOCIATE, + PORT_REQUEST_DISASSOCIATE, +}; + +enum { + PORT_VDP_RESPONSE_SUCCESS = 0, + PORT_VDP_RESPONSE_INVALID_FORMAT, + PORT_VDP_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_VDP_RESPONSE_UNUSED_VTID, + PORT_VDP_RESPONSE_VTID_VIOLATION, + PORT_VDP_RESPONSE_VTID_VERSION_VIOALTION, + PORT_VDP_RESPONSE_OUT_OF_SYNC, + /* 0x08-0xFF reserved for future VDP use */ + PORT_PROFILE_RESPONSE_SUCCESS = 0x100, + PORT_PROFILE_RESPONSE_INPROGRESS, + PORT_PROFILE_RESPONSE_INVALID, + PORT_PROFILE_RESPONSE_BADSTATE, + PORT_PROFILE_RESPONSE_INSUFFICIENT_RESOURCES, + PORT_PROFILE_RESPONSE_ERROR, +}; + +struct ifla_port_vsi { + __u8 vsi_mgr_id; + __u8 vsi_type_id[3]; + __u8 vsi_type_version; + __u8 pad[3]; +}; + #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c1b2341897c2..c3487a6bdf99 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -686,6 +686,9 @@ struct netdev_rx_queue { * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); + * int (*ndo_set_vf_port)(struct net_device *dev, int vf, + * struct nlattr *port[]); + * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -735,6 +738,11 @@ struct net_device_ops { int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); + int (*ndo_set_vf_port)(struct net_device *dev, + int vf, + struct nlattr *port[]); + int (*ndo_get_vf_port)(struct net_device *dev, + int vf, struct sk_buff *skb); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 66db1201da9b..e4b9870e4706 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -660,6 +660,31 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev) return 0; } +static size_t rtnl_port_size(const struct net_device *dev) +{ + size_t port_size = nla_total_size(4) /* PORT_VF */ + + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ + + nla_total_size(sizeof(struct ifla_port_vsi)) + /* PORT_VSI_TYPE */ + + nla_total_size(PORT_UUID_MAX) /* PORT_INSTANCE_UUID */ + + nla_total_size(PORT_UUID_MAX) /* PORT_HOST_UUID */ + + nla_total_size(1) /* PROT_VDP_REQUEST */ + + nla_total_size(2); /* PORT_VDP_RESPONSE */ + size_t vf_ports_size = nla_total_size(sizeof(struct nlattr)); + size_t vf_port_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + + port_size; + + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + return 0; + if (dev_num_vf(dev->dev.parent)) + return port_self_size + vf_ports_size + + vf_port_size * dev_num_vf(dev->dev.parent); + else + return port_self_size; +} + static inline size_t if_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) @@ -680,9 +705,82 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ } +static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *vf_ports; + struct nlattr *vf_port; + int vf; + int err; + + vf_ports = nla_nest_start(skb, IFLA_VF_PORTS); + if (!vf_ports) + return -EMSGSIZE; + + for (vf = 0; vf < dev_num_vf(dev->dev.parent); vf++) { + vf_port = nla_nest_start(skb, IFLA_VF_PORT); + if (!vf_port) { + nla_nest_cancel(skb, vf_ports); + return -EMSGSIZE; + } + NLA_PUT_U32(skb, IFLA_PORT_VF, vf); + err = dev->netdev_ops->ndo_get_vf_port(dev, vf, skb); + if (err) { +nla_put_failure: + nla_nest_cancel(skb, vf_port); + continue; + } + nla_nest_end(skb, vf_port); + } + + nla_nest_end(skb, vf_ports); + + return 0; +} + +static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) +{ + struct nlattr *port_self; + int err; + + port_self = nla_nest_start(skb, IFLA_PORT_SELF); + if (!port_self) + return -EMSGSIZE; + + err = dev->netdev_ops->ndo_get_vf_port(dev, PORT_SELF_VF, skb); + if (err) { + nla_nest_cancel(skb, port_self); + return err; + } + + nla_nest_end(skb, port_self); + + return 0; +} + +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + return 0; + + err = rtnl_port_self_fill(skb, dev); + if (err) + return err; + + if (dev_num_vf(dev->dev.parent)) { + err = rtnl_vf_ports_fill(skb, dev); + if (err) + return err; + } + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags) @@ -754,13 +852,15 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; copy_rtnl_link_stats64(nla_data(attr), stats); + if (dev->dev.parent) + NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { int i; struct nlattr *vfinfo, *vf; int num_vfs = dev_num_vf(dev->dev.parent); - NLA_PUT_U32(skb, IFLA_NUM_VF, num_vfs); vfinfo = nla_nest_start(skb, IFLA_VFINFO_LIST); if (!vfinfo) goto nla_put_failure; @@ -788,6 +888,10 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } nla_nest_end(skb, vfinfo); } + + if (rtnl_port_fill(skb, dev)) + goto nla_put_failure; + if (dev->rtnl_link_ops) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; @@ -849,6 +953,8 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, + [IFLA_VF_PORTS] = { .type = NLA_NESTED }, + [IFLA_PORT_SELF] = { .type = NLA_NESTED }, }; EXPORT_SYMBOL(ifla_policy); @@ -870,6 +976,20 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_tx_rate) }, }; +static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { + [IFLA_PORT_VF] = { .type = NLA_U32 }, + [IFLA_PORT_PROFILE] = { .type = NLA_STRING, + .len = PORT_PROFILE_MAX }, + [IFLA_PORT_VSI_TYPE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_port_vsi)}, + [IFLA_PORT_INSTANCE_UUID] = { .type = NLA_BINARY, + .len = PORT_UUID_MAX }, + [IFLA_PORT_HOST_UUID] = { .type = NLA_STRING, + .len = PORT_UUID_MAX }, + [IFLA_PORT_REQUEST] = { .type = NLA_U8, }, + [IFLA_PORT_RESPONSE] = { .type = NLA_U16, }, +}; + struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) { struct net *net; @@ -1089,6 +1209,53 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, } err = 0; + if (tb[IFLA_VF_PORTS]) { + struct nlattr *port[IFLA_PORT_MAX+1]; + struct nlattr *attr; + int vf; + int rem; + + err = -EOPNOTSUPP; + if (!ops->ndo_set_vf_port) + goto errout; + + nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) { + if (nla_type(attr) != IFLA_VF_PORT) + continue; + err = nla_parse_nested(port, IFLA_PORT_MAX, + attr, ifla_port_policy); + if (err < 0) + goto errout; + if (!port[IFLA_PORT_VF]) { + err = -EOPNOTSUPP; + goto errout; + } + vf = nla_get_u32(port[IFLA_PORT_VF]); + err = ops->ndo_set_vf_port(dev, vf, port); + if (err < 0) + goto errout; + modified = 1; + } + } + err = 0; + + if (tb[IFLA_PORT_SELF]) { + struct nlattr *port[IFLA_PORT_MAX+1]; + + err = nla_parse_nested(port, IFLA_PORT_MAX, + tb[IFLA_PORT_SELF], ifla_port_policy); + if (err < 0) + goto errout; + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_port) + err = ops->ndo_set_vf_port(dev, PORT_SELF_VF, port); + if (err < 0) + goto errout; + modified = 1; + } + err = 0; + errout: if (err < 0 && modified && net_ratelimit()) printk(KERN_WARNING "A link change request failed with " -- cgit v1.2.3