From 0c317a02ca982ca093e71bf07cb562265ba40032 Mon Sep 17 00:00:00 2001 From: Purushottam Kushwaha Date: Wed, 12 Oct 2016 18:26:51 +0530 Subject: cfg80211: support virtual interfaces with different beacon intervals This commit provides a mechanism for the host drivers to advertise the support for different beacon intervals among the respective interface combinations in a group, through NL80211_IFACE_COMB_BI_MIN_GCD (u32). This value will be compared against GCD of all beaconing interfaces of matching combinations. If the driver doesn't advertise this value, the old behaviour where all beacon intervals must be identical is retained. If it is specified, then any beacon interval for an interface in the interface combination as well as the GCD of all active beacon intervals in the combination must be greater or equal to this value. Signed-off-by: Purushottam Kushwaha [change commit message, some variable names, small other things] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 56368e9b4622..1362d24957b5 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4280,6 +4280,9 @@ enum nl80211_iface_limit_attrs { * of supported channel widths for radar detection. * @NL80211_IFACE_COMB_RADAR_DETECT_REGIONS: u32 attribute containing the bitmap * of supported regulatory regions for radar detection. + * @NL80211_IFACE_COMB_BI_MIN_GCD: u32 attribute specifying the minimum GCD of + * different beacon intervals supported by all the interface combinations + * in this group (if not present, all beacon intervals be identical). * @NUM_NL80211_IFACE_COMB: number of attributes * @MAX_NL80211_IFACE_COMB: highest attribute number * @@ -4287,8 +4290,8 @@ enum nl80211_iface_limit_attrs { * limits = [ #{STA} <= 1, #{AP} <= 1 ], matching BI, channels = 1, max = 2 * => allows an AP and a STA that must match BIs * - * numbers = [ #{AP, P2P-GO} <= 8 ], channels = 1, max = 8 - * => allows 8 of AP/GO + * numbers = [ #{AP, P2P-GO} <= 8 ], BI min gcd, channels = 1, max = 8, + * => allows 8 of AP/GO that can have BI gcd >= min gcd * * numbers = [ #{STA} <= 2 ], channels = 2, max = 2 * => allows two STAs on different channels @@ -4314,6 +4317,7 @@ enum nl80211_if_combination_attrs { NL80211_IFACE_COMB_NUM_CHANNELS, NL80211_IFACE_COMB_RADAR_DETECT_WIDTHS, NL80211_IFACE_COMB_RADAR_DETECT_REGIONS, + NL80211_IFACE_COMB_BI_MIN_GCD, /* keep last */ NUM_NL80211_IFACE_COMB, -- cgit v1.2.3 From a52ad514fdf3b8a57ca4322c92d2d8d5c6182485 Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Fri, 7 Oct 2016 22:04:34 -0400 Subject: net: deprecate eth_change_mtu, remove usage With centralized MTU checking, there's nothing productive done by eth_change_mtu that isn't already done in dev_set_mtu, so mark it as deprecated and remove all usage of it in the kernel. All callers have been audited for calls to alloc_etherdev* or ether_setup directly, which means they all have a valid dev->min_mtu and dev->max_mtu. Now eth_change_mtu prints out a netdev_warn about being deprecated, for the benefit of out-of-tree drivers that might be utilizing it. Of note, dvb_net.c actually had dev->mtu = 4096, while using eth_change_mtu, meaning that if you ever tried changing it's mtu, you couldn't set it above 1500 anymore. It's now getting dev->max_mtu also set to 4096 to remedy that. v2: fix up lantiq_etop, missed breakage due to drive not compiling on x86 CC: netdev@vger.kernel.org Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 117d02e0fc31..864d6f2b2cb0 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -35,6 +35,8 @@ #define ETH_FRAME_LEN 1514 /* Max. octets in frame sans FCS */ #define ETH_FCS_LEN 4 /* Octets in the FCS */ +#define ETH_MIN_MTU 68 /* Min IPv4 MTU per RFC791 */ + /* * These are the defined Ethernet Protocol ID's. */ -- cgit v1.2.3 From d894be57ca92c8a8819ab544d550809e8731137b Mon Sep 17 00:00:00 2001 From: Jarod Wilson Date: Thu, 20 Oct 2016 13:55:16 -0400 Subject: ethernet: use net core MTU range checking in more drivers Somehow, I missed a healthy number of ethernet drivers in the last pass. Most of these drivers either were in need of an updated max_mtu to make jumbo frames possible to enable again. In a few cases, also setting a different min_mtu to match previous lower bounds. There are also a few drivers that had no upper bounds checking, so they're getting a brand new ETH_MAX_MTU that is identical to IP_MAX_MTU, but accessible by includes all ethernet and ethernet-like drivers all have already. acenic: - min_mtu = 0, max_mtu = 9000 amazon/ena: - min_mtu = 128, max_mtu = adapter->max_mtu amd/xgbe: - min_mtu = 0, max_mtu = 9000 sb1250: - min_mtu = 0, max_mtu = 1518 cxgb3: - min_mtu = 81, max_mtu = 65535 cxgb4: - min_mtu = 81, max_mtu = 9600 cxgb4vf: - min_mtu = 81, max_mtu = 65535 benet: - min_mtu = 256, max_mtu = 9000 ibmveth: - min_mtu = 68, max_mtu = 65535 ibmvnic: - min_mtu = adapter->min_mtu, max_mtu = adapter->max_mtu - remove now redundant ibmvnic_change_mtu jme: - min_mtu = 1280, max_mtu = 9202 mv643xx_eth: - min_mtu = 64, max_mtu = 9500 mlxsw: - min_mtu = 0, max_mtu = 65535 - Basically bypassing the core checks, and instead relying on dynamic checks in the respective switch drivers' ndo_change_mtu functions ns83820: - min_mtu = 0 - remove redundant ns83820_change_mtu, only checked for mtu > 1500 netxen: - min_mtu = 0, max_mtu = 8000 (P2), max_mtu = 9600 (P3) qlge: - min_mtu = 1500, max_mtu = 9000 - driver only supports setting mtu to 1500 or 9000, so the core check only rules out < 1500 and > 9000, qlge_change_mtu still needs to check that the value is 1500 or 9000 qualcomm/emac: - min_mtu = 46, max_mtu = 9194 xilinx_axienet: - min_mtu = 64, max_mtu = 9000 Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") CC: netdev@vger.kernel.org CC: Jes Sorensen CC: Netanel Belgazal CC: Tom Lendacky CC: Santosh Raspatur CC: Hariprasad S CC: Sathya Perla CC: Ajit Khaparde CC: Sriharsha Basavapatna CC: Somnath Kotur CC: Thomas Falcon CC: John Allen CC: Guo-Fu Tseng CC: Sebastian Hesselbarth CC: Jiri Pirko CC: Ido Schimmel CC: Manish Chopra CC: Sony Chacko CC: Rajesh Borundia CC: Timur Tabi CC: Anirudha Sarangi CC: John Linn Signed-off-by: Jarod Wilson Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 864d6f2b2cb0..3e5185e9ef03 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -36,6 +36,7 @@ #define ETH_FCS_LEN 4 /* Octets in the FCS */ #define ETH_MIN_MTU 68 /* Min IPv4 MTU per RFC791 */ +#define ETH_MAX_MTU 0xFFFFU /* 65535, same as IP_MAX_MTU */ /* * These are the defined Ethernet Protocol ID's. -- cgit v1.2.3 From 2d0e30c30f84d08dc16f0f2af41f1b8a85f0755e Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 21 Oct 2016 12:46:33 +0200 Subject: bpf: add helper for retrieving current numa node id Use case is mainly for soreuseport to select sockets for the local numa node, but since generic, lets also add this for other networking and tracing program types. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f09c70b97eca..374ef582ae18 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -426,6 +426,12 @@ enum bpf_func_id { */ BPF_FUNC_set_hash_invalid, + /** + * bpf_get_numa_node_id() + * Returns the id of the current NUMA node. + */ + BPF_FUNC_get_numa_node_id, + __BPF_FUNC_MAX_ID, }; -- cgit v1.2.3 From 432490f9d455fb842d70219f22d9d2c812371676 Mon Sep 17 00:00:00 2001 From: Cyrill Gorcunov Date: Fri, 21 Oct 2016 13:03:44 +0300 Subject: net: ip, diag -- Add diag interface for raw sockets In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. v2: - add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@) - implement @destroy for diag requests (by dsa@) v3: - add export of raw_abort for IPv6 (by dsa@) - pass net-admin flag into inet_sk_diag_fill due to changes in net-next branch (by dsa@) v4: - use @pad in struct inet_diag_req_v2 for raw socket protocol specification: raw module carries sockets which may have custom protocol passed from socket() syscall and sole @sdiag_protocol is not enough to match underlied ones - start reporting protocol specifed in socket() call when sockets are raw ones for the same reason: user space tools like ss may parse this attribute and use it for socket matching v5 (by eric.dumazet@): - use sock_hold in raw_sock_get instead of atomic_inc, we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock when looking up so counter won't be zero here. v6: - use sdiag_raw_protocol() helper which will access @pad structure used for raw sockets protocol specification: we can't simply rename this member without breaking uapi v7: - sine sdiag_raw_protocol() helper is not suitable for uapi lets rather make an alias structure with proper names. __check_inet_diag_req_raw helper will catch if any of structure unintentionally changed. CC: David S. Miller CC: Eric Dumazet CC: David Ahern CC: Alexey Kuznetsov CC: James Morris CC: Hideaki YOSHIFUJI CC: Patrick McHardy CC: Andrey Vagin CC: Stephen Hemminger Signed-off-by: Cyrill Gorcunov Signed-off-by: David S. Miller --- include/uapi/linux/inet_diag.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 509cd961068d..bbe201047df6 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -43,6 +43,23 @@ struct inet_diag_req_v2 { struct inet_diag_sockid id; }; +/* + * SOCK_RAW sockets require the underlied protocol to be + * additionally specified so we can use @pad member for + * this, but we can't rename it because userspace programs + * still may depend on this name. Instead lets use another + * structure definition as an alias for struct + * @inet_diag_req_v2. + */ +struct inet_diag_req_raw { + __u8 sdiag_family; + __u8 sdiag_protocol; + __u8 idiag_ext; + __u8 sdiag_raw_protocol; + __u32 idiag_states; + struct inet_diag_sockid id; +}; + enum { INET_DIAG_REQ_NONE, INET_DIAG_REQ_BYTECODE, -- cgit v1.2.3 From 11b6b5a4ced2f2c76073b97ee08ca0eab8358fde Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:41:58 +0300 Subject: cfg80211: Rename SAE_DATA to more generic AUTH_DATA This adds defines and nl80211 extensions to allow FILS Authentication to be implemented similarly to SAE. FILS does not need the special rules for the Authentication transaction number and Status code fields, but it does need to add non-IE fields. The previously used NL80211_ATTR_SAE_DATA can be reused for this to avoid having to duplicate that implementation. Rename that attribute to more generic NL80211_ATTR_AUTH_DATA (with backwards compatibility define for NL80211_SAE_DATA). Also document the special rules related to the Authentication transaction number and Status code fiels. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 1362d24957b5..18bcf44899aa 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1638,8 +1638,16 @@ enum nl80211_commands { * the connection request from a station. nl80211_connect_failed_reason * enum has different reasons of connection failure. * - * @NL80211_ATTR_SAE_DATA: SAE elements in Authentication frames. This starts - * with the Authentication transaction sequence number field. + * @NL80211_ATTR_AUTH_DATA: Fields and elements in Authentication frames. + * This contains the authentication frame body (non-IE and IE data), + * excluding the Authentication algorithm number, i.e., starting at the + * Authentication transaction sequence number field. It is used with + * authentication algorithms that need special fields to be added into + * the frames (SAE and FILS). Currently, only the SAE cases use the + * initial two fields (Authentication transaction sequence number and + * Status code). However, those fields are included in the attribute data + * for all authentication algorithms to keep the attribute definition + * consistent. * * @NL80211_ATTR_VHT_CAPABILITY: VHT Capability information element (from * association request when used with NL80211_CMD_NEW_STATION) @@ -2195,7 +2203,7 @@ enum nl80211_attrs { NL80211_ATTR_CONN_FAILED_REASON, - NL80211_ATTR_SAE_DATA, + NL80211_ATTR_AUTH_DATA, NL80211_ATTR_VHT_CAPABILITY, @@ -2347,6 +2355,7 @@ enum nl80211_attrs { #define NL80211_ATTR_SCAN_GENERATION NL80211_ATTR_GENERATION #define NL80211_ATTR_MESH_PARAMS NL80211_ATTR_MESH_CONFIG #define NL80211_ATTR_IFACE_SOCKET_OWNER NL80211_ATTR_SOCKET_OWNER +#define NL80211_ATTR_SAE_DATA NL80211_ATTR_AUTH_DATA /* * Allow user space programs to use #ifdef on new attributes by defining them -- cgit v1.2.3 From 60b8084e844814631b57da3d35f272e0ff799ab2 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:00 +0300 Subject: cfg80211: Add feature flag for Fast Initial Link Setup (FILS) as STA This defines a feature flag that drivers can use to indicate that they support FILS authentication/association (IEEE 802.11ai) when using user space SME (NL80211_CMD_AUTHENTICATE) in station mode. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 18bcf44899aa..7825fd4db19e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4647,6 +4647,8 @@ enum nl80211_feature_flags { * configuration (AP/mesh) with HT rates. * @NL80211_EXT_FEATURE_BEACON_RATE_VHT: Driver supports beacon rate * configuration (AP/mesh) with VHT rates. + * @NL80211_EXT_FEATURE_FILS_STA: This driver supports Fast Initial Link Setup + * with user space SME (NL80211_CMD_AUTHENTICATE) in station mode. * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. @@ -4661,6 +4663,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_BEACON_RATE_LEGACY, NL80211_EXT_FEATURE_BEACON_RATE_HT, NL80211_EXT_FEATURE_BEACON_RATE_VHT, + NL80211_EXT_FEATURE_FILS_STA, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, -- cgit v1.2.3 From 631810603a20874554b2f17adf42b72d0f15eda5 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:02 +0300 Subject: cfg80211: Add Fast Initial Link Setup (FILS) auth algs This defines authentication algorithms for FILS (IEEE 802.11ai). Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 7825fd4db19e..4dc21265cd12 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3669,6 +3669,9 @@ enum nl80211_bss_status { * @NL80211_AUTHTYPE_FT: Fast BSS Transition (IEEE 802.11r) * @NL80211_AUTHTYPE_NETWORK_EAP: Network EAP (some Cisco APs and mainly LEAP) * @NL80211_AUTHTYPE_SAE: Simultaneous authentication of equals + * @NL80211_AUTHTYPE_FILS_SK: Fast Initial Link Setup shared key + * @NL80211_AUTHTYPE_FILS_SK_PFS: Fast Initial Link Setup shared key with PFS + * @NL80211_AUTHTYPE_FILS_PK: Fast Initial Link Setup public key * @__NL80211_AUTHTYPE_NUM: internal * @NL80211_AUTHTYPE_MAX: maximum valid auth algorithm * @NL80211_AUTHTYPE_AUTOMATIC: determine automatically (if necessary by @@ -3681,6 +3684,9 @@ enum nl80211_auth_type { NL80211_AUTHTYPE_FT, NL80211_AUTHTYPE_NETWORK_EAP, NL80211_AUTHTYPE_SAE, + NL80211_AUTHTYPE_FILS_SK, + NL80211_AUTHTYPE_FILS_SK_PFS, + NL80211_AUTHTYPE_FILS_PK, /* keep last */ __NL80211_AUTHTYPE_NUM, -- cgit v1.2.3 From 348bd456699801920a309c66e382380809fbdf41 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Thu, 27 Oct 2016 00:42:03 +0300 Subject: cfg80211: Add KEK/nonces for FILS association frames The new nl80211 attributes can be used to provide KEK and nonces to allow the driver to encrypt and decrypt FILS (Re)Association Request/Response frames in station mode. Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 4dc21265cd12..a268a009528a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1944,6 +1944,11 @@ enum nl80211_commands { * attribute. * @NL80211_ATTR_NAN_MATCH: used to report a match. This is a nested attribute. * See &enum nl80211_nan_match_attributes. + * @NL80211_ATTR_FILS_KEK: KEK for FILS (Re)Association Request/Response frame + * protection. + * @NL80211_ATTR_FILS_NONCES: Nonces (part of AAD) for FILS (Re)Association + * Request/Response frame protection. This attribute contains the 16 octet + * STA Nonce followed by 16 octets of AP Nonce. * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined @@ -2344,6 +2349,9 @@ enum nl80211_attrs { NL80211_ATTR_NAN_FUNC, NL80211_ATTR_NAN_MATCH, + NL80211_ATTR_FILS_KEK, + NL80211_ATTR_FILS_NONCES, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From ce0ce13a1c89ff8b94b7f8fb32eb4c43e111c82e Mon Sep 17 00:00:00 2001 From: Michael Braun Date: Mon, 10 Oct 2016 19:12:22 +0200 Subject: cfg80211: configure multicast to unicast for AP interfaces Add the ability to configure if an AP (and associated VLANs) will do multicast-to-unicast conversion for ARP, IPv4 and IPv6 frames (possibly within 802.1Q). If enabled, such frames are to be sent to each station separately, with the DA replaced by their own MAC address rather than the group address. Note that this may break certain expectations of the receiver, such as the ability to drop unicast IP packets received within multicast L2 frames, or the ability to not send ICMP destination unreachable messages for packets received in L2 multicast (which is required, but the receiver can't tell the difference if this new option is enabled.) This also doesn't implement the 802.11 DMS (directed multicast service). Signed-off-by: Michael Braun [fix disabling, add better documentation & commit message] Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index a268a009528a..e21d23dcb588 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -600,6 +600,20 @@ * * @NL80211_CMD_SET_WDS_PEER: Set the MAC address of the peer on a WDS interface. * + * @NL80211_CMD_SET_MULTICAST_TO_UNICAST: Configure if this AP should perform + * multicast to unicast conversion. When enabled, all multicast packets + * with ethertype ARP, IPv4 or IPv6 (possibly within an 802.1Q header) + * will be sent out to each station once with the destination (multicast) + * MAC address replaced by the station's MAC address. Note that this may + * break certain expectations of the receiver, e.g. the ability to drop + * unicast IP packets encapsulated in multicast L2 frames, or the ability + * to not send destination unreachable messages in such cases. + * This can only be toggled per BSS. Configure this on an interface of + * type %NL80211_IFTYPE_AP. It applies to all its VLAN interfaces + * (%NL80211_IFTYPE_AP_VLAN), except for those in 4addr (WDS) mode. + * If %NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED is not present with this + * command, the feature is disabled. + * * @NL80211_CMD_JOIN_MESH: Join a mesh. The mesh ID must be given, and initial * mesh config parameters may be given. * @NL80211_CMD_LEAVE_MESH: Leave the mesh network -- no special arguments, the @@ -1069,6 +1083,8 @@ enum nl80211_commands { NL80211_CMD_CHANGE_NAN_CONFIG, NL80211_CMD_NAN_MATCH, + NL80211_CMD_SET_MULTICAST_TO_UNICAST, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -1950,6 +1966,9 @@ enum nl80211_commands { * Request/Response frame protection. This attribute contains the 16 octet * STA Nonce followed by 16 octets of AP Nonce. * + * @NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED: Indicates whether or not multicast + * packets should be send out as unicast to all stations (flag attribute). + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2352,6 +2371,8 @@ enum nl80211_attrs { NL80211_ATTR_FILS_KEK, NL80211_ATTR_FILS_NONCES, + NL80211_ATTR_MULTICAST_TO_UNICAST_ENABLED, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, -- cgit v1.2.3 From 088e8df82f91a24728d49d9532cab7ebdee5117f Mon Sep 17 00:00:00 2001 From: vamsi krishna Date: Thu, 27 Oct 2016 16:51:11 +0300 Subject: cfg80211: Add support to update connection parameters Add functionality to update the connection parameters when in connected state, so that driver/firmware uses the updated parameters for subsequent roaming. This is for drivers that support internal BSS selection and roaming. The new command does not change the current association state, i.e., it can be used to update IE contents for future (re)associations without causing an immediate disassociation or reassociation with the current BSS. This commit implements the required functionality for updating IEs for (Re)Association Request frame only. Other parameters can be added in future when required. Signed-off-by: vamsi krishna Signed-off-by: Jouni Malinen Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e21d23dcb588..259c9c77fdc1 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -888,6 +888,12 @@ * This will contain a %NL80211_ATTR_NAN_MATCH nested attribute and * %NL80211_ATTR_COOKIE. * + * @NL80211_CMD_UPDATE_CONNECT_PARAMS: Update one or more connect parameters + * for subsequent roaming cases if the driver or firmware uses internal + * BSS selection. This command can be issued only while connected and it + * does not result in a change for the current association. Currently, + * only the %NL80211_ATTR_IE data is used and updated with this command. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1085,6 +1091,8 @@ enum nl80211_commands { NL80211_CMD_SET_MULTICAST_TO_UNICAST, + NL80211_CMD_UPDATE_CONNECT_PARAMS, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ -- cgit v1.2.3 From 4fe77d82ef80c77031c9c6f8554cd0dee2aa423a Mon Sep 17 00:00:00 2001 From: Antonio Quartulli Date: Mon, 24 Oct 2016 20:32:57 +0800 Subject: skbedit: allow the user to specify bitmask for mark The user may want to use only some bits of the skb mark in his skbedit rules because the remaining part might be used by something else. Introduce the "mask" parameter to the skbedit actor in order to implement such functionality. When the mask is specified, only those bits selected by the latter are altered really changed by the actor, while the rest is left untouched. Signed-off-by: Antonio Quartulli Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/uapi/linux/tc_act/tc_skbedit.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index a4d00c608d8f..2884425738ce 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -28,6 +28,7 @@ #define SKBEDIT_F_QUEUE_MAPPING 0x2 #define SKBEDIT_F_MARK 0x4 #define SKBEDIT_F_PTYPE 0x8 +#define SKBEDIT_F_MASK 0x10 struct tc_skbedit { tc_gen; @@ -42,6 +43,7 @@ enum { TCA_SKBEDIT_MARK, TCA_SKBEDIT_PAD, TCA_SKBEDIT_PTYPE, + TCA_SKBEDIT_MASK, __TCA_SKBEDIT_MAX }; #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1) -- cgit v1.2.3 From a07ea4d9941af5a0c6f0be2a71b51ac9c083c5e5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:02 +0200 Subject: genetlink: no longer support using static family IDs Static family IDs have never really been used, the only use case was the workaround I introduced for those users that assumed their family ID was also their multicast group ID. Additionally, because static family IDs would never be reserved by the generic netlink code, using a relatively low ID would only work for built-in families that can be registered immediately after generic netlink is started, which is basically only the control family (apart from the workaround code, which I also had to add code for so it would reserve those IDs) Thus, anything other than GENL_ID_GENERATE is flawed and luckily not used except in the cases I mentioned. Move those workarounds into a few lines of code, and then get rid of GENL_ID_GENERATE entirely, making it more robust. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/uapi/linux/genetlink.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index 5512c90af7e3..d9b2db4a29c6 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -26,7 +26,6 @@ struct genlmsghdr { /* * List of reserved static generic netlink identifiers: */ -#define GENL_ID_GENERATE 0 #define GENL_ID_CTRL NLMSG_MIN_TYPE #define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1) #define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2) -- cgit v1.2.3 From 2ae0f17df1cd52aafd1ab0415ea1f1dd56dc0e2a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 24 Oct 2016 14:40:04 +0200 Subject: genetlink: use idr to track families Since generic netlink family IDs are small integers, allocated densely, IDR is an ideal match for lookups. Replace the existing hand-written hash-table with IDR for allocation and lookup. This lets the families only be written to once, during register, since the list_head can be removed and removal of a family won't cause any writes. It also slightly reduces the code size (by about 1.3k on x86-64). Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/uapi/linux/genetlink.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/genetlink.h b/include/uapi/linux/genetlink.h index d9b2db4a29c6..adc899381e0d 100644 --- a/include/uapi/linux/genetlink.h +++ b/include/uapi/linux/genetlink.h @@ -29,6 +29,8 @@ struct genlmsghdr { #define GENL_ID_CTRL NLMSG_MIN_TYPE #define GENL_ID_VFS_DQUOT (NLMSG_MIN_TYPE + 1) #define GENL_ID_PMCRAID (NLMSG_MIN_TYPE + 2) +/* must be last reserved + 1 */ +#define GENL_START_ALLOC (NLMSG_MIN_TYPE + 3) /************************************************************************** * Controller -- cgit v1.2.3 From ebb676daa1a340ccef25eb769aefc09b79c01f8a Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 27 Oct 2016 11:23:51 +0200 Subject: bpf: Print function name in addition to function id The verifier currently prints raw function ids when printing CALL instructions or when complaining: 5: (85) call 23 unknown func 23 print a meaningful function name instead: 5: (85) call bpf_redirect#23 unknown func bpf_redirect#23 Moves the function documentation to a single comment and renames all helpers names in the list to conform to the bpf_ prefix notation so they can be greped in the kernel source. Signed-off-by: Thomas Graf Acked-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 574 ++++++++++++++++++++++++----------------------- 1 file changed, 289 insertions(+), 285 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 374ef582ae18..e2f38e0091b6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -143,297 +143,301 @@ union bpf_attr { }; } __attribute__((aligned(8))); +/* BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(&map, &key) + * Return: Map value or NULL + * + * int bpf_map_update_elem(&map, &key, &value, flags) + * Return: 0 on success or negative error + * + * int bpf_map_delete_elem(&map, &key) + * Return: 0 on success or negative error + * + * int bpf_probe_read(void *dst, int size, void *src) + * Return: 0 on success or negative error + * + * u64 bpf_ktime_get_ns(void) + * Return: current ktime + * + * int bpf_trace_printk(const char *fmt, int fmt_size, ...) + * Return: length of buffer written or negative error + * + * u32 bpf_prandom_u32(void) + * Return: random value + * + * u32 bpf_raw_smp_processor_id(void) + * Return: SMP processor ID + * + * int bpf_skb_store_bytes(skb, offset, from, len, flags) + * store bytes into packet + * @skb: pointer to skb + * @offset: offset within packet from skb->mac_header + * @from: pointer where to copy bytes from + * @len: number of bytes to store into packet + * @flags: bit 0 - if true, recompute skb->csum + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l3_csum_replace(skb, offset, from, to, flags) + * recompute IP checksum + * @skb: pointer to skb + * @offset: offset within packet where IP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_l4_csum_replace(skb, offset, from, to, flags) + * recompute TCP/UDP checksum + * @skb: pointer to skb + * @offset: offset within packet where TCP/UDP checksum is located + * @from: old value of header field + * @to: new value of header field + * @flags: bits 0-3 - size of header field + * bit 4 - is pseudo header + * other bits - reserved + * Return: 0 on success or negative error + * + * int bpf_tail_call(ctx, prog_array_map, index) + * jump into another BPF program + * @ctx: context pointer passed to next program + * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY + * @index: index inside array that selects specific program to run + * Return: 0 on success or negative error + * + * int bpf_clone_redirect(skb, ifindex, flags) + * redirect to another netdev + * @skb: pointer to skb + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: 0 on success or negative error + * + * u64 bpf_get_current_pid_tgid(void) + * Return: current->tgid << 32 | current->pid + * + * u64 bpf_get_current_uid_gid(void) + * Return: current_gid << 32 | current_uid + * + * int bpf_get_current_comm(char *buf, int size_of_buf) + * stores current->comm into buf + * Return: 0 on success or negative error + * + * u32 bpf_get_cgroup_classid(skb) + * retrieve a proc's classid + * @skb: pointer to skb + * Return: classid if != 0 + * + * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) + * Return: 0 on success or negative error + * + * int bpf_skb_vlan_pop(skb) + * Return: 0 on success or negative error + * + * int bpf_skb_get_tunnel_key(skb, key, size, flags) + * int bpf_skb_set_tunnel_key(skb, key, size, flags) + * retrieve or populate tunnel metadata + * @skb: pointer to skb + * @key: pointer to 'struct bpf_tunnel_key' + * @size: size of 'struct bpf_tunnel_key' + * @flags: room for future extensions + * Return: 0 on success or negative error + * + * u64 bpf_perf_event_read(&map, index) + * Return: Number events read or error code + * + * int bpf_redirect(ifindex, flags) + * redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + * + * u32 bpf_get_route_realm(skb) + * retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + * + * int bpf_perf_event_output(ctx, map, index, data, size) + * output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success or negative error + * + * int bpf_get_stackid(ctx, map, flags) + * walk user or kernel stack and return id + * @ctx: struct pt_regs* + * @map: pointer to stack_trace map + * @flags: bits 0-7 - numer of stack frames to skip + * bit 8 - collect user stack instead of kernel + * bit 9 - compare stacks by hash only + * bit 10 - if two different stacks hash into the same stackid + * discard old + * other bits - reserved + * Return: >= 0 stackid on success or negative error + * + * s64 bpf_csum_diff(from, from_size, to, to_size, seed) + * calculate csum diff + * @from: raw from buffer + * @from_size: length of from buffer + * @to: raw to buffer + * @to_size: length of to buffer + * @seed: optional seed + * Return: csum result or negative error code + * + * int bpf_skb_get_tunnel_opt(skb, opt, size) + * retrieve tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: option size + * + * int bpf_skb_set_tunnel_opt(skb, opt, size) + * populate tunnel options metadata + * @skb: pointer to skb + * @opt: pointer to raw tunnel option data + * @size: size of @opt + * Return: 0 on success or negative error + * + * int bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is v4 -> v6, + * v6 -> v4 transitions. The helper will also resize the skb. eBPF + * program is expected to fill the new headers via skb_store_bytes + * and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + * + * int bpf_skb_under_cgroup(skb, map, index) + * Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + * + * u32 bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + * + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + * + * int bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + * + * int bpf_current_task_under_cgroup(map, index) + * Check cgroup2 membership of current task + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 current failed the cgroup2 descendant test + * == 1 current succeeded the cgroup2 descendant test + * < 0 error + * + * int bpf_skb_change_tail(skb, len, flags) + * The helper will resize the skb to the given new size, to be used f.e. + * with control messages. + * @skb: pointer to skb + * @len: new skb length + * @flags: reserved + * Return: 0 on success or negative error + * + * int bpf_skb_pull_data(skb, len) + * The helper will pull in non-linear data in case the skb is non-linear + * and not all of len are part of the linear section. Only needed for + * read/write with direct packet access. + * @skb: pointer to skb + * @len: len to make read/writeable + * Return: 0 on success or negative error + * + * s64 bpf_csum_update(skb, csum) + * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. + * @skb: pointer to skb + * @csum: csum to add + * Return: csum on success or negative error + * + * void bpf_set_hash_invalid(skb) + * Invalidate current skb->hash. + * @skb: pointer to skb + * + * int bpf_get_numa_node_id() + * Return: Id of current NUMA node. + */ +#define __BPF_FUNC_MAPPER(FN) \ + FN(unspec), \ + FN(map_lookup_elem), \ + FN(map_update_elem), \ + FN(map_delete_elem), \ + FN(probe_read), \ + FN(ktime_get_ns), \ + FN(trace_printk), \ + FN(get_prandom_u32), \ + FN(get_smp_processor_id), \ + FN(skb_store_bytes), \ + FN(l3_csum_replace), \ + FN(l4_csum_replace), \ + FN(tail_call), \ + FN(clone_redirect), \ + FN(get_current_pid_tgid), \ + FN(get_current_uid_gid), \ + FN(get_current_comm), \ + FN(get_cgroup_classid), \ + FN(skb_vlan_push), \ + FN(skb_vlan_pop), \ + FN(skb_get_tunnel_key), \ + FN(skb_set_tunnel_key), \ + FN(perf_event_read), \ + FN(redirect), \ + FN(get_route_realm), \ + FN(perf_event_output), \ + FN(skb_load_bytes), \ + FN(get_stackid), \ + FN(csum_diff), \ + FN(skb_get_tunnel_opt), \ + FN(skb_set_tunnel_opt), \ + FN(skb_change_proto), \ + FN(skb_change_type), \ + FN(skb_under_cgroup), \ + FN(get_hash_recalc), \ + FN(get_current_task), \ + FN(probe_write_user), \ + FN(current_task_under_cgroup), \ + FN(skb_change_tail), \ + FN(skb_pull_data), \ + FN(csum_update), \ + FN(set_hash_invalid), \ + FN(get_numa_node_id), + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ +#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x enum bpf_func_id { - BPF_FUNC_unspec, - BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */ - BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */ - BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */ - BPF_FUNC_probe_read, /* int bpf_probe_read(void *dst, int size, void *src) */ - BPF_FUNC_ktime_get_ns, /* u64 bpf_ktime_get_ns(void) */ - BPF_FUNC_trace_printk, /* int bpf_trace_printk(const char *fmt, int fmt_size, ...) */ - BPF_FUNC_get_prandom_u32, /* u32 prandom_u32(void) */ - BPF_FUNC_get_smp_processor_id, /* u32 raw_smp_processor_id(void) */ - - /** - * skb_store_bytes(skb, offset, from, len, flags) - store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_skb_store_bytes, - - /** - * l3_csum_replace(skb, offset, from, to, flags) - recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_l3_csum_replace, - - /** - * l4_csum_replace(skb, offset, from, to, flags) - recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_l4_csum_replace, - - /** - * bpf_tail_call(ctx, prog_array_map, index) - jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: index inside array that selects specific program to run - * Return: 0 on success - */ - BPF_FUNC_tail_call, - - /** - * bpf_clone_redirect(skb, ifindex, flags) - redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success - */ - BPF_FUNC_clone_redirect, - - /** - * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid - */ - BPF_FUNC_get_current_pid_tgid, - - /** - * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - */ - BPF_FUNC_get_current_uid_gid, - - /** - * bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success - */ - BPF_FUNC_get_current_comm, - - /** - * bpf_get_cgroup_classid(skb) - retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - */ - BPF_FUNC_get_cgroup_classid, - BPF_FUNC_skb_vlan_push, /* bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) */ - BPF_FUNC_skb_vlan_pop, /* bpf_skb_vlan_pop(skb) */ - - /** - * bpf_skb_[gs]et_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Retrun: 0 on success - */ - BPF_FUNC_skb_get_tunnel_key, - BPF_FUNC_skb_set_tunnel_key, - BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ - /** - * bpf_redirect(ifindex, flags) - redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: TC_ACT_REDIRECT - */ - BPF_FUNC_redirect, - - /** - * bpf_get_route_realm(skb) - retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - */ - BPF_FUNC_get_route_realm, - - /** - * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @index: index of event in the map - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success - */ - BPF_FUNC_perf_event_output, - BPF_FUNC_skb_load_bytes, - - /** - * bpf_get_stackid(ctx, map, flags) - walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - */ - BPF_FUNC_get_stackid, - - /** - * bpf_csum_diff(from, from_size, to, to_size, seed) - calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result - */ - BPF_FUNC_csum_diff, - - /** - * bpf_skb_[gs]et_tunnel_opt(skb, opt, size) - * retrieve or populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success for set, option size for get - */ - BPF_FUNC_skb_get_tunnel_opt, - BPF_FUNC_skb_set_tunnel_opt, - - /** - * bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is - * v4 -> v6, v6 -> v4 transitions. The helper will also - * resize the skb. eBPF program is expected to fill the - * new headers via skb_store_bytes and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_proto, - - /** - * bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_type, - - /** - * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - */ - BPF_FUNC_skb_under_cgroup, - - /** - * bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash - */ - BPF_FUNC_get_hash_recalc, - - /** - * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - */ - BPF_FUNC_get_current_task, - - /** - * bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - */ - BPF_FUNC_probe_write_user, - - /** - * bpf_current_task_under_cgroup(map, index) - Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - */ - BPF_FUNC_current_task_under_cgroup, - - /** - * bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, - * to be used f.e. with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_change_tail, - - /** - * bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the - * skb is non-linear and not all of len are part of the - * linear section. Only needed for read/write with direct - * packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - */ - BPF_FUNC_skb_pull_data, - - /** - * bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - */ - BPF_FUNC_csum_update, - - /** - * bpf_set_hash_invalid(skb) - * Invalidate current skb>hash. - * @skb: pointer to skb - */ - BPF_FUNC_set_hash_invalid, - - /** - * bpf_get_numa_node_id() - * Returns the id of the current NUMA node. - */ - BPF_FUNC_get_numa_node_id, - + __BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; +#undef __BPF_ENUM_FN /* All flags used by eBPF helper functions, placed here. */ -- cgit v1.2.3 From c62cce2caee558e18aa05c01c2fd3b40f07174f2 Mon Sep 17 00:00:00 2001 From: Andrey Vagin Date: Mon, 24 Oct 2016 18:29:13 -0700 Subject: net: add an ioctl to get a socket network namespace Each socket operates in a network namespace where it has been created, so if we want to dump and restore a socket, we have to know its network namespace. We have a socket_diag to get information about sockets, it doesn't report sockets which are not bound or connected. This patch introduces a new socket ioctl, which is called SIOCGSKNS and used to get a file descriptor for a socket network namespace. A task must have CAP_NET_ADMIN in a target network namespace to use this ioctl. Cc: "David S. Miller" Cc: Eric W. Biederman Signed-off-by: Andrei Vagin Signed-off-by: David S. Miller --- include/uapi/linux/sockios.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index 8e7890b26d9a..83cc54ce6081 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -84,6 +84,7 @@ #define SIOCWANDEV 0x894A /* get/set netdev parameters */ #define SIOCOUTQNSD 0x894B /* output queue size (not sent only) */ +#define SIOCGSKNS 0x894C /* get socket network namespace */ /* ARP cache control calls. */ /* 0x8950 - 0x8952 * obsolete calls, don't re-use */ -- cgit v1.2.3 From 20861f26e33d76a4f3587bcc866fa1dab3e01094 Mon Sep 17 00:00:00 2001 From: Gao Feng Date: Thu, 27 Oct 2016 09:05:22 +0800 Subject: driver: tun: Use new macro SOCK_IOC_TYPE instead of literal number 0x89 The current codes use _IOC_TYPE(cmd) == 0x89 to check if the cmd is one socket ioctl command like SIOCGIFHWADDR. But the literal number 0x89 may confuse readers. So create one macro SOCK_IOC_TYPE to enhance the readability. Signed-off-by: Gao Feng Signed-off-by: David S. Miller --- include/uapi/linux/sockios.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h index 83cc54ce6081..79d029d25310 100644 --- a/include/uapi/linux/sockios.h +++ b/include/uapi/linux/sockios.h @@ -24,6 +24,8 @@ #define SIOCINQ FIONREAD #define SIOCOUTQ TIOCOUTQ /* output queue size (not sent + not acked) */ +#define SOCK_IOC_TYPE 0x89 + /* Routing table calls. */ #define SIOCADDRT 0x890B /* add routing table entry */ #define SIOCDELRT 0x890C /* delete routing table entry */ -- cgit v1.2.3 From f6d0cbcf09c506b9b022df8f9d7693a7cec3c732 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 24 Oct 2016 16:56:40 +0200 Subject: netfilter: nf_tables: add fib expression Add FIB expression, supported for ipv4, ipv6 and inet family (the latter just dispatches to ipv4 or ipv6 one based on nfproto). Currently supports fetching output interface index/name and the rtm_type associated with an address. This can be used for adding path filtering. rtm_type is useful to e.g. enforce a strong-end host model where packets are only accepted if daddr is configured on the interface the packet arrived on. The fib expression is a native nftables alternative to the xtables addrtype and rp_filter matches. FIB result order for oif/oifname retrieval is as follows: - if packet is local (skb has rtable, RTF_LOCAL set, this will also catch looped-back multicast packets), set oif to the loopback interface. - if fib lookup returns an error, or result points to local, store zero result. This means '--local' option of -m rpfilter is not supported. It is possible to use 'fib type local' or add explicit saddr/daddr matching rules to create exceptions if this is really needed. - store result in the destination register. In case of multiple routes, search set for desired oif in case strict matching is requested. ipv4 and ipv6 behave fib expressions are supposed to behave the same. [ I have collapsed Arnd Bergmann's ("netfilter: nf_tables: fib warnings") http://patchwork.ozlabs.org/patch/688615/ to address fallout from this patch after rebasing nf-next, that was posted to address compilation warnings. --pablo ] Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 36 ++++++++++++++++++++++++++++++++ 1 file changed, 36 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 c6c4477c136b..a054ad2c8853 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1109,6 +1109,42 @@ enum nft_gen_attributes { }; #define NFTA_GEN_MAX (__NFTA_GEN_MAX - 1) +/* + * enum nft_fib_attributes - nf_tables fib expression netlink attributes + * + * @NFTA_FIB_DREG: destination register (NLA_U32) + * @NFTA_FIB_RESULT: desired result (NLA_U32) + * @NFTA_FIB_FLAGS: flowi fields to initialize when querying the FIB (NLA_U32) + * + * The FIB expression performs a route lookup according + * to the packet data. + */ +enum nft_fib_attributes { + NFTA_FIB_UNSPEC, + NFTA_FIB_DREG, + NFTA_FIB_RESULT, + NFTA_FIB_FLAGS, + __NFTA_FIB_MAX +}; +#define NFTA_FIB_MAX (__NFTA_FIB_MAX - 1) + +enum nft_fib_result { + NFT_FIB_RESULT_UNSPEC, + NFT_FIB_RESULT_OIF, + NFT_FIB_RESULT_OIFNAME, + NFT_FIB_RESULT_ADDRTYPE, + __NFT_FIB_RESULT_MAX +}; +#define NFT_FIB_RESULT_MAX (__NFT_FIB_RESULT_MAX - 1) + +enum nft_fib_flags { + NFTA_FIB_F_SADDR = 1 << 0, /* look up src */ + NFTA_FIB_F_DADDR = 1 << 1, /* look up dst */ + NFTA_FIB_F_MARK = 1 << 2, /* use skb->mark */ + NFTA_FIB_F_IIF = 1 << 3, /* restrict to iif */ + NFTA_FIB_F_OIF = 1 << 4, /* restrict to oif */ +}; + /** * enum nft_trace_attributes - nf_tables trace netlink attributes * -- cgit v1.2.3 From 2fa841938c648fe4359691f41e8e1f37ff1a3aa2 Mon Sep 17 00:00:00 2001 From: "Anders K. Pedersen" Date: Fri, 28 Oct 2016 05:54:15 +0000 Subject: netfilter: nf_tables: introduce routing expression Introduces an nftables rt expression for routing related data with support for nexthop (i.e. the directly connected IP address that an outgoing packet is sent to), which can be used either for matching or accounting, eg. # nft add rule filter postrouting \ ip daddr 192.168.1.0/24 rt nexthop != 192.168.0.1 drop This will drop any traffic to 192.168.1.0/24 that is not routed via 192.168.0.1. # nft add rule filter postrouting \ flow table acct { rt nexthop timeout 600s counter } # nft add rule ip6 filter postrouting \ flow table acct { rt nexthop timeout 600s counter } These rules count outgoing traffic per nexthop. Note that the timeout releases an entry if no traffic is seen for this nexthop within 10 minutes. # nft add rule inet filter postrouting \ ether type ip \ flow table acct { rt nexthop timeout 600s counter } # nft add rule inet filter postrouting \ ether type ip6 \ flow table acct { rt nexthop timeout 600s counter } Same as above, but via the inet family, where the ether type must be specified explicitly. "rt classid" is also implemented identical to "meta rtclassid", since it is more logical to have this match in the routing expression going forward. Signed-off-by: Anders K. Pedersen Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 27 +++++++++++++++++++++++++++ 1 file changed, 27 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 a054ad2c8853..14e5f619167e 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -758,6 +758,19 @@ enum nft_meta_keys { NFT_META_PRANDOM, }; +/** + * enum nft_rt_keys - nf_tables routing expression keys + * + * @NFT_RT_CLASSID: realm value of packet's route (skb->dst->tclassid) + * @NFT_RT_NEXTHOP4: routing nexthop for IPv4 + * @NFT_RT_NEXTHOP6: routing nexthop for IPv6 + */ +enum nft_rt_keys { + NFT_RT_CLASSID, + NFT_RT_NEXTHOP4, + NFT_RT_NEXTHOP6, +}; + /** * enum nft_hash_attributes - nf_tables hash expression netlink attributes * @@ -796,6 +809,20 @@ enum nft_meta_attributes { }; #define NFTA_META_MAX (__NFTA_META_MAX - 1) +/** + * enum nft_rt_attributes - nf_tables routing expression netlink attributes + * + * @NFTA_RT_DREG: destination register (NLA_U32) + * @NFTA_RT_KEY: routing data item to load (NLA_U32: nft_rt_keys) + */ +enum nft_rt_attributes { + NFTA_RT_UNSPEC, + NFTA_RT_DREG, + NFTA_RT_KEY, + __NFTA_RT_MAX +}; +#define NFTA_RT_MAX (__NFTA_RT_MAX - 1) + /** * enum nft_ct_keys - nf_tables ct expression keys * -- cgit v1.2.3 From 06fd3a392bb36ff162d10cb7d5794185b94edb2f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 3 Nov 2016 10:56:17 +0100 Subject: netfilter: deprecate NF_STOP NF_STOP is only used by br_netfilter these days, and it can be emulated with a combination of NF_STOLEN plus explicit call to the ->okfn() function as Florian suggests. To retain binary compatibility with userspace nf_queue application, we have to keep NF_STOP around, so libnetfilter_queue userspace userspace applications still work if they use NF_STOP for some exotic reason. Out of tree modules using NF_STOP would break, but we don't care about those. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index d93f949d1d9a..7550e9176a54 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -13,7 +13,7 @@ #define NF_STOLEN 2 #define NF_QUEUE 3 #define NF_REPEAT 4 -#define NF_STOP 5 +#define NF_STOP 5 /* Deprecated, for userspace nf_queue compatibility. */ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue -- cgit v1.2.3 From 70ecc24841326396a827deb55c3fefac582a729d Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 2 Nov 2016 11:02:16 -0400 Subject: ipv4: add IP_RECVFRAGSIZE cmsg The IP stack records the largest fragment of a reassembled packet in IPCB(skb)->frag_max_size. When reading a datagram or raw packet that arrived fragmented, expose the value to allow applications to estimate receive path MTU. Tested: Sent data over a veth pair of which the source has a small mtu. Sent data using netcat, received using a dedicated process. Verified that the cmsg IP_RECVFRAGSIZE is returned only when data arrives fragmented, and in that cases matches the veth mtu. ip link add veth0 type veth peer name veth1 ip netns add from ip netns add to ip link set dev veth1 netns to ip netns exec to ip addr add dev veth1 192.168.10.1/24 ip netns exec to ip link set dev veth1 up ip link set dev veth0 netns from ip netns exec from ip addr add dev veth0 192.168.10.2/24 ip netns exec from ip link set dev veth0 up ip netns exec from ip link set dev veth0 mtu 1300 ip netns exec from ethtool -K veth0 ufo off dd if=/dev/zero bs=1 count=1400 2>/dev/null > payload ip netns exec to ./recv_cmsg_recvfragsize -4 -u -p 6000 & ip netns exec from nc -q 1 -u 192.168.10.1 6000 < payload using github.com/wdebruij/kerneltools/blob/master/tests/recvfragsize.c Signed-off-by: Willem de Bruijn Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index eaf94919291a..4e557f4e9553 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -117,6 +117,7 @@ struct in_addr { #define IP_NODEFRAG 22 #define IP_CHECKSUM 23 #define IP_BIND_ADDRESS_NO_PORT 24 +#define IP_RECVFRAGSIZE 25 /* IP_MTU_DISCOVER values */ #define IP_PMTUDISC_DONT 0 /* Never send DF frames */ -- cgit v1.2.3 From 0cc0aa614b4c24b21b2492c0a1753035ee8c6edb Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 2 Nov 2016 11:02:17 -0400 Subject: ipv6: add IPV6_RECVFRAGSIZE cmsg When reading a datagram or raw packet that arrived fragmented, expose the maximum fragment size if recorded to allow applications to estimate receive path MTU. At this point, the field is only recorded when ipv6 connection tracking is enabled. A follow-up patch will record this field also in the ipv6 input path. Tested using the test for IP_RECVFRAGSIZE plus ip netns exec to ip addr add dev veth1 fc07::1/64 ip netns exec from ip addr add dev veth0 fc07::2/64 ip netns exec to ./recv_cmsg_recvfragsize -6 -u -p 6000 & ip netns exec from nc -q 1 -u fc07::1 6000 < payload Both with and without enabling connection tracking ip6tables -A INPUT -m state --state NEW -p udp -j LOG Signed-off-by: Willem de Bruijn Acked-by: Eric Dumazet 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 b39ea4f2e701..46444f8fbee4 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -283,6 +283,7 @@ struct in6_flowlabel_req { #define IPV6_RECVORIGDSTADDR IPV6_ORIGDSTADDR #define IPV6_TRANSPARENT 75 #define IPV6_UNICAST_IF 76 +#define IPV6_RECVFRAGSIZE 77 /* * Multicast Routing: -- cgit v1.2.3 From 5976c5f45c40588b90dda173ded9010917f8f45e Mon Sep 17 00:00:00 2001 From: Simon Horman Date: Thu, 3 Nov 2016 13:24:21 +0100 Subject: net/sched: cls_flower: Support matching on SCTP ports Support matching on SCTP ports in the same way that matching on TCP and UDP ports is already supported. Example usage: tc qdisc add dev eth0 ingress tc filter add dev eth0 protocol ip parent ffff: \ flower indev eth0 ip_proto sctp dst_port 80 \ action drop Signed-off-by: Simon Horman