From 31fa97c5defca3895dc6c823096d7ba59df76125 Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Wed, 11 Jun 2014 17:18:21 +0300 Subject: cfg80211: pass TDLS initiator in tdls_mgmt operations The TDLS initiator is set once during link setup. If determines the address ordering in the link identifier IE. Fix dependent drivers - mwifiex and mac80211. Signed-off-by: Arik Nemtsov Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index be9519b52bb1..f1db15b9c041 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1591,6 +1591,9 @@ enum nl80211_commands { * creation then the new interface will be owned by the netlink socket * that created it and will be destroyed when the socket is closed * + * @NL80211_ATTR_TDLS_INITIATOR: flag attribute indicating the current end is + * the TDLS link initiator. + * * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use */ @@ -1931,6 +1934,8 @@ enum nl80211_attrs { NL80211_ATTR_CSA_C_OFFSETS_TX, NL80211_ATTR_MAX_CSA_COUNTERS, + NL80211_ATTR_TDLS_INITIATOR, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 7200135bc1e61f1437dc326ae2ef2f310c50b4eb Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 16 Jun 2014 13:01:52 +0200 Subject: netfilter: kill ulog targets This has been marked as deprecated for quite some time and the NFLOG target replacement has been also available since 2006. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter_bridge/Kbuild | 1 - include/uapi/linux/netfilter_bridge/ebt_ulog.h | 38 -------------------- include/uapi/linux/netfilter_ipv4/Kbuild | 1 - include/uapi/linux/netfilter_ipv4/ipt_ULOG.h | 49 -------------------------- 4 files changed, 89 deletions(-) delete mode 100644 include/uapi/linux/netfilter_bridge/ebt_ulog.h delete mode 100644 include/uapi/linux/netfilter_ipv4/ipt_ULOG.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter_bridge/Kbuild b/include/uapi/linux/netfilter_bridge/Kbuild index 348717c3a22f..0fbad8ef96de 100644 --- a/include/uapi/linux/netfilter_bridge/Kbuild +++ b/include/uapi/linux/netfilter_bridge/Kbuild @@ -14,6 +14,5 @@ header-y += ebt_nflog.h header-y += ebt_pkttype.h header-y += ebt_redirect.h header-y += ebt_stp.h -header-y += ebt_ulog.h header-y += ebt_vlan.h header-y += ebtables.h diff --git a/include/uapi/linux/netfilter_bridge/ebt_ulog.h b/include/uapi/linux/netfilter_bridge/ebt_ulog.h deleted file mode 100644 index 89a6becb5269..000000000000 --- a/include/uapi/linux/netfilter_bridge/ebt_ulog.h +++ /dev/null @@ -1,38 +0,0 @@ -#ifndef _EBT_ULOG_H -#define _EBT_ULOG_H - -#include - -#define EBT_ULOG_DEFAULT_NLGROUP 0 -#define EBT_ULOG_DEFAULT_QTHRESHOLD 1 -#define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */ -#define EBT_ULOG_PREFIX_LEN 32 -#define EBT_ULOG_MAX_QLEN 50 -#define EBT_ULOG_WATCHER "ulog" -#define EBT_ULOG_VERSION 1 - -struct ebt_ulog_info { - __u32 nlgroup; - unsigned int cprange; - unsigned int qthreshold; - char prefix[EBT_ULOG_PREFIX_LEN]; -}; - -typedef struct ebt_ulog_packet_msg { - int version; - char indev[IFNAMSIZ]; - char outdev[IFNAMSIZ]; - char physindev[IFNAMSIZ]; - char physoutdev[IFNAMSIZ]; - char prefix[EBT_ULOG_PREFIX_LEN]; - struct timeval stamp; - unsigned long mark; - unsigned int hook; - size_t data_len; - /* The complete packet, including Ethernet header and perhaps - * the VLAN header is appended */ - unsigned char data[0] __attribute__ - ((aligned (__alignof__(struct ebt_ulog_info)))); -} ebt_ulog_packet_msg_t; - -#endif /* _EBT_ULOG_H */ diff --git a/include/uapi/linux/netfilter_ipv4/Kbuild b/include/uapi/linux/netfilter_ipv4/Kbuild index fb008437dde1..ecb291df390e 100644 --- a/include/uapi/linux/netfilter_ipv4/Kbuild +++ b/include/uapi/linux/netfilter_ipv4/Kbuild @@ -5,7 +5,6 @@ header-y += ipt_ECN.h header-y += ipt_LOG.h header-y += ipt_REJECT.h header-y += ipt_TTL.h -header-y += ipt_ULOG.h header-y += ipt_ah.h header-y += ipt_ecn.h header-y += ipt_ttl.h diff --git a/include/uapi/linux/netfilter_ipv4/ipt_ULOG.h b/include/uapi/linux/netfilter_ipv4/ipt_ULOG.h deleted file mode 100644 index 417aad280bcc..000000000000 --- a/include/uapi/linux/netfilter_ipv4/ipt_ULOG.h +++ /dev/null @@ -1,49 +0,0 @@ -/* Header file for IP tables userspace logging, Version 1.8 - * - * (C) 2000-2002 by Harald Welte - * - * Distributed under the terms of GNU GPL */ - -#ifndef _IPT_ULOG_H -#define _IPT_ULOG_H - -#ifndef NETLINK_NFLOG -#define NETLINK_NFLOG 5 -#endif - -#define ULOG_DEFAULT_NLGROUP 1 -#define ULOG_DEFAULT_QTHRESHOLD 1 - -#define ULOG_MAC_LEN 80 -#define ULOG_PREFIX_LEN 32 - -#define ULOG_MAX_QLEN 50 -/* Why 50? Well... there is a limit imposed by the slab cache 131000 - * bytes. So the multipart netlink-message has to be < 131000 bytes. - * Assuming a standard ethernet-mtu of 1500, we could define this up - * to 80... but even 50 seems to be big enough. */ - -/* private data structure for each rule with a ULOG target */ -struct ipt_ulog_info { - unsigned int nl_group; - size_t copy_range; - size_t qthreshold; - char prefix[ULOG_PREFIX_LEN]; -}; - -/* Format of the ULOG packets passed through netlink */ -typedef struct ulog_packet_msg { - unsigned long mark; - long timestamp_sec; - long timestamp_usec; - unsigned int hook; - char indev_name[IFNAMSIZ]; - char outdev_name[IFNAMSIZ]; - size_t data_len; - char prefix[ULOG_PREFIX_LEN]; - unsigned char mac_len; - unsigned char mac[ULOG_MAC_LEN]; - unsigned char payload[0]; -} ulog_packet_msg_t; - -#endif /*_IPT_ULOG_H*/ -- cgit v1.2.3 From a6eacef7fba7834da4d22762ea0d8524df3993a8 Mon Sep 17 00:00:00 2001 From: Erik Hugne Date: Wed, 25 Jun 2014 10:07:05 +0200 Subject: tipc: bump max configurable window size The maximum window size is limited by the sequence gap field, which was expanded with bd7845337b105e090dd18912d511139945fa7586 ("tipc: Expand link sequence gap field to 13 bits") We remove the artificial limit that prevents the link window to be set larger than 150. Signed-off-by: Erik Hugne Reviewed-by: Jon Maloy Signed-off-by: David S. Miller --- include/uapi/linux/tipc_config.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 41a76acbb305..876d0a14863c 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -182,7 +182,7 @@ #define TIPC_MIN_LINK_WIN 16 #define TIPC_DEF_LINK_WIN 50 -#define TIPC_MAX_LINK_WIN 150 +#define TIPC_MAX_LINK_WIN 8191 struct tipc_node_info { -- cgit v1.2.3 From 09d27b88f15f08fcfbaf57d9b0b4489816264815 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 25 Jun 2014 13:37:13 +0200 Subject: netfilter: nft_log: complete logging support Use the unified nf_log_packet() interface that allows us explicit logger selection through the nf_loginfo structure. If you specify the group attribute, this means you want to receive logging messages through nfnetlink_log. In that case, the snaplen and qthreshold attributes allows you to tune internal aspects of the netlink logging infrastructure. On the other hand, if the level is specified, then the plain text format through the kernel logging ring is used instead, which is also used by default if neither group nor level are indicated. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 2a88f645a5d8..801bdd1e56e3 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -697,6 +697,8 @@ enum nft_counter_attributes { * @NFTA_LOG_PREFIX: prefix to prepend to log messages (NLA_STRING) * @NFTA_LOG_SNAPLEN: length of payload to include in netlink message (NLA_U32) * @NFTA_LOG_QTHRESHOLD: queue threshold (NLA_U32) + * @NFTA_LOG_LEVEL: log level (NLA_U32) + * @NFTA_LOG_FLAGS: logging flags (NLA_U32) */ enum nft_log_attributes { NFTA_LOG_UNSPEC, @@ -704,6 +706,8 @@ enum nft_log_attributes { NFTA_LOG_PREFIX, NFTA_LOG_SNAPLEN, NFTA_LOG_QTHRESHOLD, + NFTA_LOG_LEVEL, + NFTA_LOG_FLAGS, __NFTA_LOG_MAX }; #define NFTA_LOG_MAX (__NFTA_LOG_MAX - 1) -- cgit v1.2.3 From d93331965729850303f6111381c1a4a9e9b8ae5a Mon Sep 17 00:00:00 2001 From: Ben Greear Date: Wed, 25 Jun 2014 14:44:53 -0700 Subject: ipv6: Allow accepting RA from local IP addresses. This can be used in virtual networking applications, and may have other uses as well. The option is disabled by default. A specific use case is setting up virtual routers, bridges, and hosts on a single OS without the use of network namespaces or virtual machines. With proper use of ip rules, routing tables, veth interface pairs and/or other virtual interfaces, and applications that can bind to interfaces and/or IP addresses, it is possibly to create one or more virtual routers with multiple hosts attached. The host interfaces can act as IPv6 systems, with radvd running on the ports in the virtual routers. With the option provided in this patch enabled, those hosts can now properly obtain IPv6 addresses from the radvd. Signed-off-by: Ben Greear Signed-off-by: David S. Miller --- include/uapi/linux/ipv6.h | 1 + include/uapi/linux/sysctl.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 593b0e32d956..efa2666f4b8a 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -163,6 +163,7 @@ enum { DEVCONF_MLDV1_UNSOLICITED_REPORT_INTERVAL, DEVCONF_MLDV2_UNSOLICITED_REPORT_INTERVAL, DEVCONF_SUPPRESS_FRAG_NDISC, + DEVCONF_ACCEPT_RA_FROM_LOCAL, DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 6d6721341f49..43aaba1cc037 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -568,6 +568,7 @@ enum { NET_IPV6_ACCEPT_RA_RT_INFO_MAX_PLEN=22, NET_IPV6_PROXY_NDP=23, NET_IPV6_ACCEPT_SOURCE_ROUTE=25, + NET_IPV6_ACCEPT_RA_FROM_LOCAL=26, __NET_IPV6_MAX }; -- cgit v1.2.3 From cb1ce2ef387b01686469487edd45994872d52d73 Mon Sep 17 00:00:00 2001 From: Tom Herbert Date: Tue, 1 Jul 2014 21:33:10 -0700 Subject: ipv6: Implement automatic flow label generation on transmit Automatically generate flow labels for IPv6 packets on transmit. The flow label is computed based on skb_get_hash. The flow label will only automatically be set when it is zero otherwise (i.e. flow label manager hasn't set one). This supports the transmit side functionality of RFC 6438. Added an IPv6 sysctl auto_flowlabels to enable/disable this behavior system wide, and added IPV6_AUTOFLOWLABEL socket option to enable this functionality per socket. By default, auto flowlabels are disabled to avoid possible conflicts with flow label manager, however if this feature proves useful we may want to enable it by default. It should also be noted that FreeBSD has already implemented automatic flow labels (including the sysctl and socket option). In FreeBSD, automatic flow labels default to enabled. Performance impact: Running super_netperf with 200 flows for TCP_RR and UDP_RR for IPv6. Note that in UDP case, __skb_get_hash will be called for every packet with explains slight regression. In the TCP case the hash is saved in the socket so there is no regression. Automatic flow labels disabled: TCP_RR: 86.53% CPU utilization 127/195/322 90/95/99% latencies 1.40498e+06 tps UDP_RR: 90.70% CPU utilization 118/168/243 90/95/99% latencies 1.50309e+06 tps Automatic flow labels enabled: TCP_RR: 85.90% CPU utilization 128/199/337 90/95/99% latencies 1.40051e+06 UDP_RR 92.61% CPU utilization 115/164/236 90/95/99% latencies 1.4687e+06 Signed-off-by: Tom Herbert Signed-off-by: David S. Miller --- include/uapi/linux/in6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index 0d8e0f0342dc..22b7a69619d8 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -233,6 +233,7 @@ struct in6_flowlabel_req { #if 0 /* not yet */ #define IPV6_USE_MIN_MTU 63 #endif +#define IPV6_AUTOFLOWLABEL 64 /* * Netfilter (1) -- cgit v1.2.3 From bc91b0f07ada5535427373a4e2050877bcc12218 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 11 Jul 2014 21:10:18 +0200 Subject: ipv6: addrconf: implement address generation modes This patch introduces a possibility for userspace to set various (so far two) modes of generating addresses. This is useful for example for NetworkManager because it can set the mode to NONE and take care of link local addresses itself. That allow it to have the interface up, monitoring carrier but still don't have any addresses on it. One more use-case by Dan Williams: WWAN devices often have their LL address provided by the firmware of the device, which sometimes refuses to respond to incorrect LL addresses when doing DHCPv6 or IPv6 ND. The kernel cannot generate the correct LL address for two reasons: 1) WWAN pseudo-ethernet interfaces often construct a fake MAC address, or read a meaningless MAC address from the firmware. Thus the EUI64 and the IPv6LL address the kernel assigns will be wrong. The real LL address is often retrieved from the firmware with AT or proprietary commands. 2) WWAN PPP interfaces receive their LL address from IPV6CP, not from kernel assignments. Only after IPV6CP has completed do we know the LL address of the PPP interface and its peer. But the kernel has already assigned an incorrect LL address to the interface. So being able to suppress the kernel LL address generation and assign the one retrieved from the firmware is less complicated and more robust. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b38534895db5..ff957604a721 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -204,11 +204,17 @@ enum { IFLA_INET6_CACHEINFO, /* time values and max reasm size */ IFLA_INET6_ICMP6STATS, /* statistics (icmpv6) */ IFLA_INET6_TOKEN, /* device token */ + IFLA_INET6_ADDR_GEN_MODE, /* implicit address generator mode */ __IFLA_INET6_MAX }; #define IFLA_INET6_MAX (__IFLA_INET6_MAX - 1) +enum in6_addr_gen_mode { + IN6_ADDR_GEN_MODE_EUI64, + IN6_ADDR_GEN_MODE_NONE, +}; + enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, -- cgit v1.2.3 From f736d9985e69e72d9a2ebfd131a72ee8f870c6f3 Mon Sep 17 00:00:00 2001 From: Nikita Edward Baruzdin Date: Fri, 11 Jul 2014 16:13:21 +0400 Subject: can: netlink: Remove space before tab Fixes the corresponing checkpatch.pl warning. Signed-off-by: Nikita Edward Baruzdin Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 813d11f54977..3bbf5c7e1500 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -92,7 +92,7 @@ struct can_ctrlmode { }; #define CAN_CTRLMODE_LOOPBACK 0x01 /* Loopback mode */ -#define CAN_CTRLMODE_LISTENONLY 0x02 /* Listen-only mode */ +#define CAN_CTRLMODE_LISTENONLY 0x02 /* Listen-only mode */ #define CAN_CTRLMODE_3_SAMPLES 0x04 /* Triple sampling mode */ #define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */ #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ -- cgit v1.2.3 From 4b9e1bab12c9b6de965268c2fbe6ebbb35dddd89 Mon Sep 17 00:00:00 2001 From: Nikita Edward Baruzdin Date: Fri, 11 Jul 2014 16:13:22 +0400 Subject: can: netlink: Add CAN_CTRLMODE_PRESUME_ACK flag Most CAN controllers have a support for ignoring ACK absence. Some of them refer to this feature as a self test mode (e. g. SJA1000) and some include it as a part of a loopback mode (e. g. MCP2510). Setting the introduced flag via netlink should make CAN controller perform a successful transmission, even if there is no acknowledgement (dominant ACK bit) received. Signed-off-by: Nikita Edward Baruzdin Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/netlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 3bbf5c7e1500..3e4323a3918d 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -97,6 +97,7 @@ struct can_ctrlmode { #define CAN_CTRLMODE_ONE_SHOT 0x08 /* One-Shot mode */ #define CAN_CTRLMODE_BERR_REPORTING 0x10 /* Bus-error reporting */ #define CAN_CTRLMODE_FD 0x20 /* CAN FD mode */ +#define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ /* * CAN device statistics -- cgit v1.2.3 From 685343fc3ba61a1f6eef361b786601123db16c28 Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Mon, 14 Jul 2014 16:37:22 +0200 Subject: net: add name_assign_type netdev attribute Based on a patch by David Herrmann. The name_assign_type attribute gives hints where the interface name of a given net-device comes from. These values are currently defined: NET_NAME_ENUM: The ifname is provided by the kernel with an enumerated suffix, typically based on order of discovery. Names may be reused and unpredictable. NET_NAME_PREDICTABLE: The ifname has been assigned by the kernel in a predictable way that is guaranteed to avoid reuse and always be the same for a given device. Examples include statically created devices like the loopback device and names deduced from hardware properties (including being given explicitly by the firmware). Names depending on the order of discovery, or in any other way on the existence of other devices, must not be marked as PREDICTABLE. NET_NAME_USER: The ifname was provided by user-space during net-device setup. NET_NAME_RENAMED: The net-device has been renamed from userspace. Once this type is set, it cannot change again. NET_NAME_UNKNOWN: This is an internal placeholder to indicate that we yet haven't yet categorized the name. It will not be exposed to userspace, rather -EINVAL is returned. The aim of these patches is to improve user-space renaming of interfaces. As a general rule, userspace must rename interfaces to guarantee that names stay the same every time a given piece of hardware appears (at boot, or when attaching it). However, there are several situations where userspace should not perform the renaming, and that depends on both the policy of the local admin, but crucially also on the nature of the current interface name. If an interface was created in repsonse to a userspace request, and userspace already provided a name, we most probably want to leave that name alone. The main instance of this is wifi-P2P devices created over nl80211, which currently have a long-standing bug where they are getting renamed by udev. We label such names NET_NAME_USER. If an interface, unbeknown to us, has already been renamed from userspace, we most probably want to leave also that alone. This will typically happen when third-party plugins (for instance to udev, but the interface is generic so could be from anywhere) renames the interface without informing udev about it. A typical situation is when you switch root from an installer or an initrd to the real system and the new instance of udev does not know what happened before the switch. These types of problems have caused repeated issues in the past. To solve this, once an interface has been renamed, its name is labelled NET_NAME_RENAMED. In many cases, the kernel is actually able to name interfaces in such a way that there is no need for userspace to rename them. This is the case when the enumeration order of devices, or in fact any other (non-parent) device on the system, can not influence the name of the interface. Examples include statically created devices, or any naming schemes based on hardware properties of the interface. In this case the admin may prefer to use the kernel-provided names, and to make that possible we label such names NET_NAME_PREDICTABLE. We want the kernel to have tho possibilty of performing predictable interface naming itself (and exposing to userspace that it has), as the information necessary for a proper naming scheme for a certain class of devices may not be exposed to userspace. The case where renaming is almost certainly desired, is when the kernel has given the interface a name using global device enumeration based on order of discovery (ethX, wlanY, etc). These naming schemes are labelled NET_NAME_ENUM. Lastly, a fallback is left as NET_NAME_UNKNOWN, to indicate that a driver has not yet been ported. This is mostly useful as a transitionary measure, allowing us to label the various naming schemes bit by bit. v8: minor documentation fixes v9: move comment to the right commit Signed-off-by: Tom Gundersen Reviewed-by: David Herrmann Reviewed-by: Kay Sievers Signed-off-by: David S. Miller --- include/uapi/linux/netdevice.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netdevice.h b/include/uapi/linux/netdevice.h index fdfbd1c17065..55818543342d 100644 --- a/include/uapi/linux/netdevice.h +++ b/include/uapi/linux/netdevice.h @@ -37,6 +37,12 @@ #define INIT_NETDEV_GROUP 0 +/* interface name assignment types (sysfs name_assign_type attribute) */ +#define NET_NAME_UNKNOWN 0 /* unknown origin (not exposed to userspace) */ +#define NET_NAME_ENUM 1 /* enumerated by kernel */ +#define NET_NAME_PREDICTABLE 2 /* predictably named by the kernel */ +#define NET_NAME_USER 3 /* provided by user-space */ +#define NET_NAME_RENAMED 4 /* renamed by user-space */ /* Media selection options. */ enum { -- cgit v1.2.3 From 63b949382c5f263746b1c177f6ff84de2201ae9d Mon Sep 17 00:00:00 2001 From: Geir Ola Vaagland Date: Sat, 12 Jul 2014 20:30:36 +0200 Subject: net: sctp: implement rfc6458, 5.3.4. SCTP_SNDINFO cmsg support This patch implements section 5.3.4. of RFC6458, that is, support for 'SCTP Send Information Structure' (SCTP_SNDINFO) which can be placed into ancillary data cmsghdr structure for sendmsg() calls. The sctp_sndinfo structure is defined as per RFC as below ... struct sctp_sndinfo { uint16_t snd_sid; uint16_t snd_flags; uint32_t snd_ppid; uint32_t snd_context; sctp_assoc_t snd_assoc_id; }; ... and supplied under cmsg_level IPPROTO_SCTP, cmsg_type SCTP_SNDINFO, while cmsg_data[] contains struct sctp_sndinfo. An sctp_sndinfo item always corresponds to the data in msg_iov. Joint work with Daniel Borkmann. Signed-off-by: Geir Ola Vaagland Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 266022a2be4a..a387761f7e02 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -154,6 +154,22 @@ struct sctp_sndrcvinfo { sctp_assoc_t sinfo_assoc_id; }; +/* 5.3.4 SCTP Send Information Structure (SCTP_SNDINFO) + * + * This cmsghdr structure specifies SCTP options for sendmsg(). + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ ------------------- + * IPPROTO_SCTP SCTP_SNDINFO struct sctp_sndinfo + */ +struct sctp_sndinfo { + __u16 snd_sid; + __u16 snd_flags; + __u32 snd_ppid; + __u32 snd_context; + sctp_assoc_t snd_assoc_id; +}; + /* * sinfo_flags: 16 bits (unsigned integer) * @@ -177,10 +193,12 @@ typedef union { /* These are cmsg_types. */ typedef enum sctp_cmsg_type { - SCTP_INIT, /* 5.2.1 SCTP Initiation Structure */ + SCTP_INIT, /* 5.2.1 SCTP Initiation Structure */ #define SCTP_INIT SCTP_INIT - SCTP_SNDRCV, /* 5.2.2 SCTP Header Information Structure */ + SCTP_SNDRCV, /* 5.2.2 SCTP Header Information Structure */ #define SCTP_SNDRCV SCTP_SNDRCV + SCTP_SNDINFO, /* 5.3.4 SCTP Send Information Structure */ +#define SCTP_SNDINFO SCTP_SNDINFO } sctp_cmsg_t; /* -- cgit v1.2.3 From 0d3a421d284812d07970b4ccee74d4fa38737e4d Mon Sep 17 00:00:00 2001 From: Geir Ola Vaagland Date: Sat, 12 Jul 2014 20:30:37 +0200 Subject: net: sctp: implement rfc6458, 5.3.5. SCTP_RCVINFO cmsg support This patch implements section 5.3.5. of RFC6458, that is, support for 'SCTP Receive Information Structure' (SCTP_RCVINFO) which is placed into ancillary data cmsghdr structure for each recvmsg() call. This option can be enabled/disabled via setsockopt(2) on SOL_SCTP level by setting an int value with 1/0 for SCTP_RECVRCVINFO in user space applications as per RFC6458, section 8.1.29. The sctp_rcvinfo structure is defined as per RFC as below ... struct sctp_rcvinfo { uint16_t rcv_sid; uint16_t rcv_ssn; uint16_t rcv_flags; <-- 2 bytes hole --> uint32_t rcv_ppid; uint32_t rcv_tsn; uint32_t rcv_cumtsn; uint32_t rcv_context; sctp_assoc_t rcv_assoc_id; }; ... and provided under cmsg_level IPPROTO_SCTP, cmsg_type SCTP_RCVINFO, while cmsg_data[] contains struct sctp_rcvinfo. An sctp_rcvinfo item always corresponds to the data in msg_iov. Joint work with Daniel Borkmann. Signed-off-by: Geir Ola Vaagland Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index a387761f7e02..29b81bbfc53d 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -95,6 +95,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_GET_ASSOC_ID_LIST 29 /* Read only */ #define SCTP_AUTO_ASCONF 30 #define SCTP_PEER_ADDR_THLDS 31 +#define SCTP_RECVRCVINFO 32 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. @@ -110,8 +111,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ #define SCTP_GET_ASSOC_STATS 112 /* Read only */ -/* - * 5.2.1 SCTP Initiation Structure (SCTP_INIT) +/* 5.3.1 SCTP Initiation Structure (SCTP_INIT) * * This cmsghdr structure provides information for initializing new * SCTP associations with sendmsg(). The SCTP_INITMSG socket option @@ -121,7 +121,6 @@ typedef __s32 sctp_assoc_t; * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_INIT struct sctp_initmsg - * */ struct sctp_initmsg { __u16 sinit_num_ostreams; @@ -130,8 +129,7 @@ struct sctp_initmsg { __u16 sinit_max_init_timeo; }; -/* - * 5.2.2 SCTP Header Information Structure (SCTP_SNDRCV) +/* 5.3.2 SCTP Header Information Structure (SCTP_SNDRCV) * * This cmsghdr structure specifies SCTP options for sendmsg() and * describes SCTP header information about a received message through @@ -140,7 +138,6 @@ struct sctp_initmsg { * cmsg_level cmsg_type cmsg_data[] * ------------ ------------ ---------------------- * IPPROTO_SCTP SCTP_SNDRCV struct sctp_sndrcvinfo - * */ struct sctp_sndrcvinfo { __u16 sinfo_stream; @@ -170,13 +167,32 @@ struct sctp_sndinfo { sctp_assoc_t snd_assoc_id; }; +/* 5.3.5 SCTP Receive Information Structure (SCTP_RCVINFO) + * + * This cmsghdr structure describes SCTP receive information + * about a received message through recvmsg(). + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ ------------------- + * IPPROTO_SCTP SCTP_RCVINFO struct sctp_rcvinfo + */ +struct sctp_rcvinfo { + __u16 rcv_sid; + __u16 rcv_ssn; + __u16 rcv_flags; + __u32 rcv_ppid; + __u32 rcv_tsn; + __u32 rcv_cumtsn; + __u32 rcv_context; + sctp_assoc_t rcv_assoc_id; +}; + /* * sinfo_flags: 16 bits (unsigned integer) * * This field may contain any of the following flags and is composed of * a bitwise OR of these values. */ - enum sctp_sinfo_flags { SCTP_UNORDERED = 1, /* Send/receive message unordered. */ SCTP_ADDR_OVER = 2, /* Override the primary destination. */ @@ -199,6 +215,8 @@ typedef enum sctp_cmsg_type { #define SCTP_SNDRCV SCTP_SNDRCV SCTP_SNDINFO, /* 5.3.4 SCTP Send Information Structure */ #define SCTP_SNDINFO SCTP_SNDINFO + SCTP_RCVINFO, /* 5.3.5 SCTP Receive Information Structure */ +#define SCTP_RCVINFO SCTP_RCVINFO } sctp_cmsg_t; /* -- cgit v1.2.3 From 2347c80ff127b94ddaa675e2b78ab4cef46dc905 Mon Sep 17 00:00:00 2001 From: Geir Ola Vaagland Date: Sat, 12 Jul 2014 20:30:38 +0200 Subject: net: sctp: implement rfc6458, 5.3.6. SCTP_NXTINFO cmsg support This patch implements section 5.3.6. of RFC6458, that is, support for 'SCTP Next Receive Information Structure' (SCTP_NXTINFO) which is placed into ancillary data cmsghdr structure for each recvmsg() call, if this information is already available when delivering the current message. This option can be enabled/disabled via setsockopt(2) on SOL_SCTP level by setting an int value with 1/0 for SCTP_RECVNXTINFO in user space applications as per RFC6458, section 8.1.30. The sctp_nxtinfo structure is defined as per RFC as below ... struct sctp_nxtinfo { uint16_t nxt_sid; uint16_t nxt_flags; uint32_t nxt_ppid; uint32_t nxt_length; sctp_assoc_t nxt_assoc_id; }; ... and provided under cmsg_level IPPROTO_SCTP, cmsg_type SCTP_NXTINFO, while cmsg_data[] contains struct sctp_nxtinfo. Joint work with Daniel Borkmann. Signed-off-by: Geir Ola Vaagland Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 47 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 29b81bbfc53d..222f82ffeca4 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -96,6 +96,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_AUTO_ASCONF 30 #define SCTP_PEER_ADDR_THLDS 31 #define SCTP_RECVRCVINFO 32 +#define SCTP_RECVNXTINFO 33 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. @@ -111,6 +112,13 @@ typedef __s32 sctp_assoc_t; #define SCTP_SOCKOPT_CONNECTX3 111 /* CONNECTX requests (updated) */ #define SCTP_GET_ASSOC_STATS 112 /* Read only */ +/* These are bit fields for msghdr->msg_flags. See section 5.1. */ +/* On user space Linux, these live in as an enum. */ +enum sctp_msg_flags { + MSG_NOTIFICATION = 0x8000, +#define MSG_NOTIFICATION MSG_NOTIFICATION +}; + /* 5.3.1 SCTP Initiation Structure (SCTP_INIT) * * This cmsghdr structure provides information for initializing new @@ -187,6 +195,25 @@ struct sctp_rcvinfo { sctp_assoc_t rcv_assoc_id; }; +/* 5.3.6 SCTP Next Receive Information Structure (SCTP_NXTINFO) + * + * This cmsghdr structure describes SCTP receive information + * of the next message that will be delivered through recvmsg() + * if this information is already available when delivering + * the current message. + * + * cmsg_level cmsg_type cmsg_data[] + * ------------ ------------ ------------------- + * IPPROTO_SCTP SCTP_NXTINFO struct sctp_nxtinfo + */ +struct sctp_nxtinfo { + __u16 nxt_sid; + __u16 nxt_flags; + __u32 nxt_ppid; + __u32 nxt_length; + sctp_assoc_t nxt_assoc_id; +}; + /* * sinfo_flags: 16 bits (unsigned integer) * @@ -194,11 +221,12 @@ struct sctp_rcvinfo { * a bitwise OR of these values. */ enum sctp_sinfo_flags { - SCTP_UNORDERED = 1, /* Send/receive message unordered. */ - SCTP_ADDR_OVER = 2, /* Override the primary destination. */ - SCTP_ABORT=4, /* Send an ABORT message to the peer. */ - SCTP_SACK_IMMEDIATELY = 8, /* SACK should be sent without delay */ - SCTP_EOF=MSG_FIN, /* Initiate graceful shutdown process. */ + SCTP_UNORDERED = (1 << 0), /* Send/receive message unordered. */ + SCTP_ADDR_OVER = (1 << 1), /* Override the primary destination. */ + SCTP_ABORT = (1 << 2), /* Send an ABORT message to the peer. */ + SCTP_SACK_IMMEDIATELY = (1 << 3), /* SACK should be sent without delay. */ + SCTP_NOTIFICATION = MSG_NOTIFICATION, /* Next message is not user msg but notification. */ + SCTP_EOF = MSG_FIN, /* Initiate graceful shutdown process. */ }; typedef union { @@ -217,6 +245,8 @@ typedef enum sctp_cmsg_type { #define SCTP_SNDINFO SCTP_SNDINFO SCTP_RCVINFO, /* 5.3.5 SCTP Receive Information Structure */ #define SCTP_RCVINFO SCTP_RCVINFO + SCTP_NXTINFO, /* 5.3.6 SCTP Next Receive Information Structure */ +#define SCTP_NXTINFO SCTP_NXTINFO } sctp_cmsg_t; /* @@ -844,13 +874,6 @@ struct sctp_assoc_stats { __u64 sas_ictrlchunks; /* Control chunks received */ }; -/* These are bit fields for msghdr->msg_flags. See section 5.1. */ -/* On user space Linux, these live in as an enum. */ -enum sctp_msg_flags { - MSG_NOTIFICATION = 0x8000, -#define MSG_NOTIFICATION MSG_NOTIFICATION -}; - /* * 8.1 sctp_bindx() * -- cgit v1.2.3 From 6b3fd5f3a2bbc8464a8e0bf134a183b8fa026439 Mon Sep 17 00:00:00 2001 From: Geir Ola Vaagland Date: Sat, 12 Jul 2014 20:30:39 +0200 Subject: net: sctp: implement rfc6458, 8.1.31. SCTP_DEFAULT_SNDINFO support This patch implements section 8.1.31. of RFC6458, which adds support for setting/retrieving SCTP_DEFAULT_SNDINFO: Applications that wish to use the sendto() system call may wish to specify a default set of parameters that would normally be supplied through the inclusion of ancillary data. This socket option allows such an application to set the default sctp_sndinfo structure. The application that wishes to use this socket option simply passes the sctp_sndinfo structure (defined in Section 5.3.4) to this call. The input parameters accepted by this call include snd_sid, snd_flags, snd_ppid, and snd_context. The snd_flags parameter is composed of a bitwise OR of SCTP_UNORDERED, SCTP_EOF, and SCTP_SENDALL. The snd_assoc_id field specifies the association to which to apply the parameters. For a one-to-many style socket, any of the predefined constants are also allowed in this field. The field is ignored for one-to-one style sockets. Joint work with Daniel Borkmann. Signed-off-by: Geir Ola Vaagland Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/uapi/linux/sctp.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 222f82ffeca4..ce70fe6b45df 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -97,6 +97,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_PEER_ADDR_THLDS 31 #define SCTP_RECVRCVINFO 32 #define SCTP_RECVNXTINFO 33 +#define SCTP_DEFAULT_SNDINFO 34 /* Internal Socket Options. Some of the sctp library functions are * implemented using these socket options. -- cgit v1.2.3 From 5cd667b0a4567048bb555927d6ee564f4e5620a9 Mon Sep 17 00:00:00 2001 From: Alex Wang Date: Thu, 17 Jul 2014 15:14:13 -0700 Subject: openvswitch: Allow each vport to have an array of 'port_id's. In order to allow handlers directly read upcalls from datapath, we need to support per-handler netlink socket for each vport in datapath. This commit makes this happen. Also, it is guaranteed to be backward compatible with previous branch. Signed-off-by: Alex Wang Acked-by: Thomas Graf Signed-off-by: Pravin B Shelar --- include/uapi/linux/openvswitch.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 0b979ee4bfc0..a794d1dd7b40 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -118,6 +118,9 @@ struct ovs_vport_stats { /* Allow last Netlink attribute to be unaligned */ #define OVS_DP_F_UNALIGNED (1 << 0) +/* Allow datapath to associate multiple Netlink PIDs to each vport */ +#define OVS_DP_F_VPORT_PIDS (1 << 1) + /* Fixed logical ports. */ #define OVSP_LOCAL ((__u32)0) @@ -203,9 +206,10 @@ enum ovs_vport_type { * this is the name of the network device. Maximum length %IFNAMSIZ-1 bytes * plus a null terminator. * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information. - * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that - * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on - * this port. A value of zero indicates that upcalls should not be sent. + * @OVS_VPORT_ATTR_UPCALL_PID: The array of Netlink socket pids in userspace + * among which OVS_PACKET_CMD_MISS upcalls will be distributed for packets + * received on this port. If this is a single-element array of value 0, + * upcalls should not be sent. * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for * packets sent or received through the vport. * @@ -228,7 +232,8 @@ enum ovs_vport_attr { OVS_VPORT_ATTR_TYPE, /* u32 OVS_VPORT_TYPE_* constant. */ OVS_VPORT_ATTR_NAME, /* string name, up to IFNAMSIZ bytes long */ OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */ - OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */ + OVS_VPORT_ATTR_UPCALL_PID, /* array of u32 Netlink socket PIDs for */ + /* receiving upcalls */ OVS_VPORT_ATTR_STATS, /* struct ovs_vport_stats */ __OVS_VPORT_ATTR_MAX }; -- cgit v1.2.3 From 68a360e82e55c9b35097e7be7f7991d8f401032f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Fri, 25 Jul 2014 18:01:31 -0400 Subject: packet: remove deprecated syststamp timestamp No device driver will ever return an skb_shared_info structure with syststamp non-zero, so remove the branch that tests for this and optionally marks the packet timestamp as TP_STATUS_TS_SYS_HARDWARE. Do not remove the definition TP_STATUS_TS_SYS_HARDWARE, as processes may refer to it. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/if_packet.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index bac27fa05f5b..da2d668b8cf1 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -108,7 +108,7 @@ struct tpacket_auxdata { /* Rx and Tx ring - header status */ #define TP_STATUS_TS_SOFTWARE (1 << 29) -#define TP_STATUS_TS_SYS_HARDWARE (1 << 30) +#define TP_STATUS_TS_SYS_HARDWARE (1 << 30) /* deprecated, never set */ #define TP_STATUS_TS_RAW_HARDWARE (1 << 31) /* Rx ring - feature request bits */ -- cgit v1.2.3 From 16eecd9be4b05e3216b8b12707aa6f51fb197903 Mon Sep 17 00:00:00 2001 From: Anish Bhatt Date: Mon, 28 Jul 2014 20:57:07 -0700 Subject: dcbnl : Fix misleading dcb_app->priority explanation Current explanation of dcb_app->priority is wrong. It says priority is expected to be a 3-bit unsigned integer which is only true when working with DCBx-IEEE. Use of dcb_app->priority by DCBx-CEE expects it to be 802.1p user priority bitmap. Updated accordingly This affects the cxgb4 driver, but I will post those changes as part of a larger changeset shortly. Fixes: 3e29027af4372 ("dcbnl: add support for ieee8021Qaz attributes") Signed-off-by: Anish Bhatt Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/uapi/linux/dcbnl.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index 6bb43382f3f3..e711f20dc522 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -148,7 +148,8 @@ struct cee_pfc { * * @selector: protocol identifier type * @protocol: protocol of type indicated - * @priority: 3-bit unsigned integer indicating priority + * @priority: 3-bit unsigned integer indicating priority for IEEE + * 8-bit 802.1p user priority bitmap for CEE * * ---- * Selector field values -- cgit v1.2.3 From e10038a8ec06ac819b7552bb67aaa6d2d6f850c1 Mon Sep 17 00:00:00 2001 From: Pablo Neira Date: Tue, 29 Jul 2014 18:12:15 +0200 Subject: netfilter: xt_bpf: add mising opaque struct sk_filter definition This structure is not exposed to userspace, so fix this by defining struct sk_filter; so we skip the casting in kernelspace. This is safe since userspace has no way to lurk with that internal pointer. Fixes: e6f30c7 ("netfilter: x_tables: add xt_bpf match") Signed-off-by: Pablo Neira Ayuso Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/netfilter/xt_bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index 5dda450eb55b..2ec9fbcd06f9 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -6,6 +6,8 @@ #define XT_BPF_MAX_NUM_INSTR 64 +struct sk_filter; + struct xt_bpf_info { __u16 bpf_program_num_elem; struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; -- cgit v1.2.3 From 7ae457c1e5b45a1b826fad9d62b32191d2bdcfdb Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 30 Jul 2014 20:34:16 -0700 Subject: net: filter: split 'struct sk_filter' into socket and bpf parts clean up names related to socket filtering and bpf in the following way: - everything that deals with sockets keeps 'sk_*' prefix - everything that is pure BPF is changed to 'bpf_*' prefix split 'struct sk_filter' into struct sk_filter { atomic_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; and struct bpf_prog { u32 jited:1, len:31; struct sock_fprog_kern *orig_prog; unsigned int (*bpf_func)(const struct sk_buff *skb, const struct bpf_insn *filter); union { struct sock_filter insns[0]; struct bpf_insn insnsi[0]; struct work_struct work; }; }; so that 'struct bpf_prog' can be used independent of sockets and cleans up 'unattached' bpf use cases split SK_RUN_FILTER macro into: SK_RUN_FILTER to be used with 'struct sk_filter *' and BPF_PROG_RUN to be used with 'struct bpf_prog *' __sk_filter_release(struct sk_filter *) gains __bpf_prog_release(struct bpf_prog *) helper function also perform related renames for the functions that work with 'struct bpf_prog *', since they're on the same lines: sk_filter_size -> bpf_prog_size sk_filter_select_runtime -> bpf_prog_select_runtime sk_filter_free -> bpf_prog_free sk_unattached_filter_create -> bpf_prog_create sk_unattached_filter_destroy -> bpf_prog_destroy sk_store_orig_filter -> bpf_prog_store_orig_filter sk_release_orig_filter -> bpf_release_orig_filter __sk_migrate_filter -> bpf_migrate_filter __sk_prepare_filter -> bpf_prepare_filter API for attaching classic BPF to a socket stays the same: sk_attach_filter(prog, struct sock *)/sk_detach_filter(struct sock *) and SK_RUN_FILTER(struct sk_filter *, ctx) to execute a program which is used by sockets, tun, af_packet API for 'unattached' BPF programs becomes: bpf_prog_create(struct bpf_prog **)/bpf_prog_destroy(struct bpf_prog *) and BPF_PROG_RUN(struct bpf_prog *, ctx) to execute a program which is used by isdn, ppp, team, seccomp, ptp, xt_bpf, cls_bpf, test_bpf Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/netfilter/xt_bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index 2ec9fbcd06f9..1fad2c27ac32 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -6,14 +6,14 @@ #define XT_BPF_MAX_NUM_INSTR 64 -struct sk_filter; +struct bpf_prog; struct xt_bpf_info { __u16 bpf_program_num_elem; struct sock_filter bpf_program[XT_BPF_MAX_NUM_INSTR]; /* only used in the kernel */ - struct sk_filter *filter __attribute__((aligned(8))); + struct bpf_prog *filter __attribute__((aligned(8))); }; #endif /*_XT_BPF_H */ -- cgit v1.2.3 From f24b9be5957b38bb420b838115040dc2031b7d0c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 4 Aug 2014 22:11:45 -0400 Subject: net-timestamp: extend SCM_TIMESTAMPING ancillary data struct Applications that request kernel tx timestamps with SO_TIMESTAMPING read timestamps as recvmsg() ancillary data. The response is defined implicitly as timespec[3]. 1) define struct scm_timestamping explicitly and 2) add support for new tstamp types. On tx, scm_timestamping always accompanies a sock_extended_err. Define previously unused field ee_info to signal the type of ts[0]. Introduce SCM_TSTAMP_SND to define the existing behavior. The reception path is not modified. On rx, no struct similar to sock_extended_err is passed along with SCM_TIMESTAMPING. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/errqueue.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index aacd4fb7102a..accee72cae7c 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -22,5 +22,23 @@ struct sock_extended_err { #define SO_EE_OFFENDER(ee) ((struct sockaddr*)((ee)+1)) +/** + * struct scm_timestamping - timestamps exposed through cmsg + * + * The timestamping interfaces SO_TIMESTAMPING, MSG_TSTAMP_* + * communicate network timestamps by passing this struct in a cmsg with + * recvmsg(). See Documentation/networking/timestamping.txt for details. + */ +struct scm_timestamping { + struct timespec ts[3]; +}; + +/* The type of scm_timestamping, passed in sock_extended_err ee_info. + * This defines the type of ts[0]. For SCM_TSTAMP_SND only, if ts[0] + * is zero, then this is a hardware timestamp and recorded in ts[2]. + */ +enum { + SCM_TSTAMP_SND, /* driver passed skb to NIC, or HW */ +}; #endif /* _UAPI_LINUX_ERRQUEUE_H */ -- cgit v1.2.3 From 09c2d251b70723650ba47e83571ff49281320f7c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 4 Aug 2014 22:11:47 -0400 Subject: net-timestamp: add key to disambiguate concurrent datagrams Datagrams timestamped on transmission can coexist in the kernel stack and be reordered in packet scheduling. When reading looped datagrams from the socket error queue it is not always possible to unique correlate looped data with original send() call (for application level retransmits). Even if possible, it may be expensive and complex, requiring packet inspection. Introduce a data-independent ID mechanism to associate timestamps with send calls. Pass an ID alongside the timestamp in field ee_data of sock_extended_err. The ID is a simple 32 bit unsigned int that is associated with the socket and incremented on each send() call for which software tx timestamp generation is enabled. The feature is enabled only if SOF_TIMESTAMPING_OPT_ID is set, to avoid changing ee_data for existing applications that expect it 0. The counter is reset each time the flag is reenabled. Reenabling does not change the ID of already submitted data. It is possible to receive out of order IDs if the timestamp stream is not quiesced first. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/net_tstamp.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index f53879c0f590..1e861d2e1a31 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -20,9 +20,11 @@ enum { SOF_TIMESTAMPING_SOFTWARE = (1<<4), SOF_TIMESTAMPING_SYS_HARDWARE = (1<<5), SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6), - SOF_TIMESTAMPING_MASK = - (SOF_TIMESTAMPING_RAW_HARDWARE - 1) | - SOF_TIMESTAMPING_RAW_HARDWARE + SOF_TIMESTAMPING_OPT_ID = (1<<7), + + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID, + SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | + SOF_TIMESTAMPING_LAST }; /** -- cgit v1.2.3 From e7fd2885385157d46c85f282fc6d7d297db43e1f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 4 Aug 2014 22:11:48 -0400 Subject: net-timestamp: SCHED timestamp on entering packet scheduler Kernel transmit latency is often incurred in the packet scheduler. Introduce a new timestamp on transmission just before entering the scheduler. When data travels through multiple devices (bonding, tunneling, ...) each device will export an individual timestamp. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/errqueue.h | 1 + include/uapi/linux/net_tstamp.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index accee72cae7c..17437cf297b7 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -39,6 +39,7 @@ struct scm_timestamping { */ enum { SCM_TSTAMP_SND, /* driver passed skb to NIC, or HW */ + SCM_TSTAMP_SCHED, /* data entered the packet scheduler */ }; #endif /* _UAPI_LINUX_ERRQUEUE_H */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 1e861d2e1a31..60733845fcdd 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -21,8 +21,9 @@ enum { SOF_TIMESTAMPING_SYS_HARDWARE = (1<<5), SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6), SOF_TIMESTAMPING_OPT_ID = (1<<7), + SOF_TIMESTAMPING_TX_SCHED = (1<<8), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_SCHED, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; -- cgit v1.2.3 From e1c8a607b28190cd09a271508aa3025d3c2f312e Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 4 Aug 2014 22:11:50 -0400 Subject: net-timestamp: ACK timestamp for bytestreams Add SOF_TIMESTAMPING_TX_ACK, a request for a tstamp when the last byte in the send() call is acknowledged. It implements the feature for TCP. The timestamp is generated when the TCP socket cumulative ACK is moved beyond the tracked seqno for the first time. The feature ignores SACK and FACK, because those acknowledge the specific byte, but not necessarily the entire contents of the buffer up to that byte. Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/uapi/linux/errqueue.h | 1 + include/uapi/linux/net_tstamp.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index 17437cf297b7..07bdce1f444a 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -40,6 +40,7 @@ struct scm_timestamping { enum { SCM_TSTAMP_SND, /* driver passed skb to NIC, or HW */ SCM_TSTAMP_SCHED, /* data entered the packet scheduler */ + SCM_TSTAMP_ACK, /* data acknowledged by peer */ }; #endif /* _UAPI_LINUX_ERRQUEUE_H */ diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 60733845fcdd..ff354021bb69 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -22,8 +22,9 @@ enum { SOF_TIMESTAMPING_RAW_HARDWARE = (1<<6), SOF_TIMESTAMPING_OPT_ID = (1<<7), SOF_TIMESTAMPING_TX_SCHED = (1<<8), + SOF_TIMESTAMPING_TX_ACK = (1<<9), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_SCHED, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_ACK, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; -- cgit v1.2.3